diff options
Diffstat (limited to 'tools')
64 files changed, 1585 insertions, 192 deletions
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 16e006f708ca..4602464ebdfb 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -27,6 +27,7 @@ #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -125,6 +126,18 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 serror_pending; + __u8 serror_has_esr; + /* Align it to 8 bytes */ + __u8 pad[6]; + __u64 serror_esr; + } exception; + __u32 reserved[12]; +}; + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 4e76630dd655..97c3478ee6e7 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -39,6 +39,7 @@ #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -154,6 +155,18 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 serror_pending; + __u8 serror_has_esr; + /* Align it to 8 bytes */ + __u8 pad[6]; + __u64 serror_esr; + } exception; + __u32 reserved[12]; +}; + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 4cdaa55fabfe..9a50f02b9894 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -4,7 +4,7 @@ /* * KVM s390 specific structures and definitions * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008, 2018 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -225,6 +225,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_FPRS (1UL << 8) #define KVM_SYNC_GSCB (1UL << 9) #define KVM_SYNC_BPBC (1UL << 10) +#define KVM_SYNC_ETOKEN (1UL << 11) /* length and alignment of the sdnx as a power of two */ #define SDNXC 8 #define SDNXL (1UL << SDNXC) @@ -258,6 +259,8 @@ struct kvm_sync_regs { struct { __u64 reserved1[2]; __u64 gscb[4]; + __u64 etoken; + __u64 etoken_extension; }; }; }; diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index c535c2fdea13..86299efa804a 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -378,4 +378,41 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_STATE_NESTED_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_RUN_PENDING 0x00000002 + +#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_SMM_VMXON 0x00000002 + +struct kvm_vmx_nested_state { + __u64 vmxon_pa; + __u64 vmcs_pa; + + struct { + __u16 flags; + } smm; +}; + +/* for KVM_CAP_NESTED_STATE */ +struct kvm_nested_state { + /* KVM_STATE_* flags */ + __u16 flags; + + /* 0 for VMX, 1 for SVM. */ + __u16 format; + + /* 128 for SVM, 128 + VMCS size for VMX. */ + __u32 size; + + union { + /* VMXON, VMCS */ + struct kvm_vmx_nested_state vmx; + + /* Pad the header to 128 bytes. */ + __u8 pad[120]; + }; + + __u8 data[0]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index dbf6e8bd98ba..bbb2a8ef367c 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -286,7 +286,7 @@ static int kvp_key_delete(int pool, const __u8 *key, int key_size) * Found a match; just move the remaining * entries up. */ - if (i == num_records) { + if (i == (num_records - 1)) { kvp_file_info[pool].num_records--; kvp_update_file(pool); return 0; diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h index 6b0c36a58fcb..e56997288f2b 100644 --- a/tools/include/linux/lockdep.h +++ b/tools/include/linux/lockdep.h @@ -30,9 +30,12 @@ struct task_struct { struct held_lock held_locks[MAX_LOCK_DEPTH]; gfp_t lockdep_reclaim_gfp; int pid; + int state; char comm[17]; }; +#define TASK_RUNNING 0 + extern struct task_struct *__curr(void); #define current (__curr()) diff --git a/tools/include/linux/nmi.h b/tools/include/linux/nmi.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/linux/nmi.h diff --git a/tools/include/tools/libc_compat.h b/tools/include/tools/libc_compat.h index 664ced8cb1b0..e907ba6f15e5 100644 --- a/tools/include/tools/libc_compat.h +++ b/tools/include/tools/libc_compat.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: (LGPL-2.0+ OR BSD-2-Clause) /* Copyright (C) 2018 Netronome Systems, Inc. */ #ifndef __TOOLS_LIBC_COMPAT_H diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 42990676a55e..df4bedb9b01c 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -734,9 +734,11 @@ __SYSCALL(__NR_pkey_free, sys_pkey_free) __SYSCALL(__NR_statx, sys_statx) #define __NR_io_pgetevents 292 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) +#define __NR_rseq 293 +__SYSCALL(__NR_rseq, sys_rseq) #undef __NR_syscalls -#define __NR_syscalls 293 +#define __NR_syscalls 294 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 9c660e1688ab..300f336633f2 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -687,6 +687,15 @@ struct drm_get_cap { */ #define DRM_CLIENT_CAP_ASPECT_RATIO 4 +/** + * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS + * + * If set to 1, the DRM core will expose special connectors to be used for + * writing back to memory the scene setup in the commit. Depends on client + * also supporting DRM_CLIENT_CAP_ATOMIC + */ +#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5 + /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ struct drm_set_client_cap { __u64 capability; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 43391e2d1153..58faab897201 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -161,6 +161,7 @@ enum { IFLA_EVENT, IFLA_NEW_NETNSID, IFLA_IF_NETNSID, + IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */ IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, IFLA_NEW_IFINDEX, @@ -554,6 +555,7 @@ enum { IFLA_GENEVE_UDP_ZERO_CSUM6_TX, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, IFLA_GENEVE_LABEL, + IFLA_GENEVE_TTL_INHERIT, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index b6270a3b38e9..07548de5c988 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -949,6 +949,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GET_MSR_FEATURES 153 #define KVM_CAP_HYPERV_EVENTFD 154 #define KVM_CAP_HYPERV_TLBFLUSH 155 +#define KVM_CAP_S390_HPAGE_1M 156 +#define KVM_CAP_NESTED_STATE 157 +#define KVM_CAP_ARM_INJECT_SERROR_ESR 158 #ifdef KVM_CAP_IRQ_ROUTING @@ -1391,6 +1394,9 @@ struct kvm_enc_region { /* Available with KVM_CAP_HYPERV_EVENTFD */ #define KVM_HYPERV_EVENTFD _IOW(KVMIO, 0xbd, struct kvm_hyperv_eventfd) +/* Available with KVM_CAP_NESTED_STATE */ +#define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state) +#define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state) /* Secure Encrypted Virtualization command */ enum sev_cmd_id { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index eeb787b1c53c..f35eb72739c0 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -144,7 +144,7 @@ enum perf_event_sample_format { PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; /* diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c51f8e5cc608..84c3de89696a 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -65,6 +65,7 @@ struct vhost_iotlb_msg { }; #define VHOST_IOTLB_MSG 0x1 +#define VHOST_IOTLB_MSG_V2 0x2 struct vhost_msg { int type; @@ -74,6 +75,15 @@ struct vhost_msg { }; }; +struct vhost_msg_v2 { + __u32 type; + __u32 reserved; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; + struct vhost_memory_region { __u64 guest_phys_addr; __u64 memory_size; /* bytes */ @@ -160,6 +170,14 @@ struct vhost_memory { #define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24, \ struct vhost_vring_state) +/* Set or get vhost backend capability */ + +/* Use message type V2 */ +#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 + +#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) +#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) + /* VHOST_NET specific defines */ /* Attach virtio net ring to a raw socket, or tap device. diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 56c4b3f8a01b..439b8a27488d 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -759,12 +759,18 @@ class DebugfsProvider(Provider): if len(vms) == 0: self.do_read = False - self.paths = filter(lambda x: "{}-".format(pid) in x, vms) + self.paths = list(filter(lambda x: "{}-".format(pid) in x, vms)) else: self.paths = [] self.do_read = True - self.reset() + + def _verify_paths(self): + """Remove invalid paths""" + for path in self.paths: + if not os.path.exists(os.path.join(PATH_DEBUGFS_KVM, path)): + self.paths.remove(path) + continue def read(self, reset=0, by_guest=0): """Returns a dict with format:'file name / field -> current value'. @@ -780,6 +786,7 @@ class DebugfsProvider(Provider): # If no debugfs filtering support is available, then don't read. if not self.do_read: return results + self._verify_paths() paths = self.paths if self._pid == 0: @@ -1096,15 +1103,16 @@ class Tui(object): pid = self.stats.pid_filter self.screen.erase() gname = self.get_gname_from_pid(pid) + self._gname = gname if gname: gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...' if len(gname) > MAX_GUEST_NAME_LEN else gname)) if pid > 0: - self.screen.addstr(0, 0, 'kvm statistics - pid {0} {1}' - .format(pid, gname), curses.A_BOLD) + self._headline = 'kvm statistics - pid {0} {1}'.format(pid, gname) else: - self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD) + self._headline = 'kvm statistics - summary' + self.screen.addstr(0, 0, self._headline, curses.A_BOLD) if self.stats.fields_filter: regex = self.stats.fields_filter if len(regex) > MAX_REGEX_LEN: @@ -1162,6 +1170,19 @@ class Tui(object): return sorted_items + if not self._is_running_guest(self.stats.pid_filter): + if self._gname: + try: # ...to identify the guest by name in case it's back + pids = self.get_pid_from_gname(self._gname) + if len(pids) == 1: + self._refresh_header(pids[0]) + self._update_pid(pids[0]) + return + except: + pass + self._display_guest_dead() + # leave final data on screen + return row = 3 self.screen.move(row, 0) self.screen.clrtobot() @@ -1184,6 +1205,7 @@ class Tui(object): # print events tavg = 0 tcur = 0 + guest_removed = False for key, values in get_sorted_events(self, stats): if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0): break @@ -1191,7 +1213,10 @@ class Tui(object): key = self.get_gname_from_pid(key) if not key: continue - cur = int(round(values.delta / sleeptime)) if values.delta else '' + cur = int(round(values.delta / sleeptime)) if values.delta else 0 + if cur < 0: + guest_removed = True + continue if key[0] != ' ': if values.delta: tcur += values.delta @@ -1204,13 +1229,21 @@ class Tui(object): values.value * 100 / float(ltotal), cur)) row += 1 if row == 3: - self.screen.addstr(4, 1, 'No matching events reported yet') + if guest_removed: + self.screen.addstr(4, 1, 'Guest removed, updating...') + else: + self.screen.addstr(4, 1, 'No matching events reported yet') if row > 4: tavg = int(round(tcur / sleeptime)) if tcur > 0 else '' self.screen.addstr(row, 1, '%-40s %10d %8s' % ('Total', total, tavg), curses.A_BOLD) self.screen.refresh() + def _display_guest_dead(self): + marker = ' Guest is DEAD ' + y = min(len(self._headline), 80 - len(marker)) + self.screen.addstr(0, y, marker, curses.A_BLINK | curses.A_STANDOUT) + def _show_msg(self, text): """Display message centered text and exit on key press""" hint = 'Press any key to continue' @@ -1219,10 +1252,10 @@ class Tui(object): (x, term_width) = self.screen.getmaxyx() row = 2 for line in text: - start = (term_width - len(line)) / 2 + start = (term_width - len(line)) // 2 self.screen.addstr(row, start, line) row += 1 - self.screen.addstr(row + 1, (term_width - len(hint)) / 2, hint, + self.screen.addstr(row + 1, (term_width - len(hint)) // 2, hint, curses.A_STANDOUT) self.screen.getkey() @@ -1319,6 +1352,12 @@ class Tui(object): msg = '"' + str(val) + '": Invalid value' self._refresh_header() + def _is_running_guest(self, pid): + """Check if pid is still a running process.""" + if not pid: + return True + return os.path.isdir(os.path.join('/proc/', str(pid))) + def _show_vm_selection_by_guest(self): """Draws guest selection mask. @@ -1346,7 +1385,7 @@ class Tui(object): if not guest or guest == '0': break if guest.isdigit(): - if not os.path.isdir(os.path.join('/proc/', guest)): + if not self._is_running_guest(guest): msg = '"' + guest + '": Not a running process' continue pid = int(guest) diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 512b2c0ba0d2..7bc31c905018 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1 @@ -libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o netlink.o +libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 9ca8e0e624d8..4f8d43ae20d2 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -50,6 +50,7 @@ #include "libbpf.h" #include "bpf.h" #include "btf.h" +#include "str_error.h" #ifndef EM_BPF #define EM_BPF 247 @@ -469,7 +470,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) obj->efile.fd = open(obj->path, O_RDONLY); if (obj->efile.fd < 0) { char errmsg[STRERR_BUFSIZE]; - char *cp = strerror_r(errno, errmsg, sizeof(errmsg)); + char *cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to open %s: %s\n", obj->path, cp); return -errno; @@ -810,8 +811,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) data->d_size, name, idx); if (err) { char errmsg[STRERR_BUFSIZE]; - char *cp = strerror_r(-err, errmsg, - sizeof(errmsg)); + char *cp = str_error(-err, errmsg, sizeof(errmsg)); pr_warning("failed to alloc program %s (%s): %s", name, obj->path, cp); @@ -1140,7 +1140,7 @@ bpf_object__create_maps(struct bpf_object *obj) *pfd = bpf_create_map_xattr(&create_attr); if (*pfd < 0 && create_attr.btf_key_type_id) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", map->name, cp, errno); create_attr.btf_fd = 0; @@ -1155,7 +1155,7 @@ bpf_object__create_maps(struct bpf_object *obj) size_t j; err = *pfd; - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to create map (name: '%s'): %s\n", map->name, cp); for (j = 0; j < i; j++) @@ -1339,7 +1339,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, } ret = -LIBBPF_ERRNO__LOAD; - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("load bpf program failed: %s\n", cp); if (log_buf && log_buf[0] != '\0') { @@ -1655,7 +1655,7 @@ static int check_path(const char *path) dir = dirname(dname); if (statfs(dir, &st_fs)) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to statfs %s: %s\n", dir, cp); err = -errno; } @@ -1691,7 +1691,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, } if (bpf_obj_pin(prog->instances.fds[instance], path)) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to pin program: %s\n", cp); return -errno; } @@ -1709,7 +1709,7 @@ static int make_dir(const char *path) err = -errno; if (err) { - cp = strerror_r(-err, errmsg, sizeof(errmsg)); + cp = str_error(-err, errmsg, sizeof(errmsg)); pr_warning("failed to mkdir %s: %s\n", path, cp); } return err; @@ -1771,7 +1771,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path) } if (bpf_obj_pin(map->fd, path)) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to pin map: %s\n", cp); return -errno; } diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c new file mode 100644 index 000000000000..b8798114a357 --- /dev/null +++ b/tools/lib/bpf/str_error.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: LGPL-2.1 +#undef _GNU_SOURCE +#include <string.h> +#include <stdio.h> +#include "str_error.h" + +/* + * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl + * libc, while checking strerror_r() return to avoid having to check this in + * all places calling it. + */ +char *str_error(int err, char *dst, int len) +{ + int ret = strerror_r(err, dst, len); + if (ret) + snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); + return dst; +} diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h new file mode 100644 index 000000000000..355b1db571d1 --- /dev/null +++ b/tools/lib/bpf/str_error.h @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: LGPL-2.1 +#ifndef BPF_STR_ERROR +#define BPF_STR_ERROR + +char *str_error(int err, char *dst, int len); +#endif // BPF_STR_ERROR diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 42261a9b280e..ac841bc5c35b 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -280,7 +280,7 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt mv $@+ $@ ifdef USE_ASCIIDOCTOR -$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt +$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ $(ASCIIDOC) -b manpage -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index b3d1b12a5081..5224ade3d5af 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -777,14 +777,12 @@ endif $(call QUIET_INSTALL, libexec) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' ifndef NO_LIBBPF - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, include/bpf) \ - $(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' - $(call QUIET_INSTALL, examples/bpf) \ - $(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-headers) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \ + $(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-examples) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \ + $(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' endif $(call QUIET_INSTALL, perf-archive) \ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index f013b115dc86..dbef716a1913 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -11,7 +11,8 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 out := $(OUTPUT)arch/arm64/include/generated/asm header := $(out)/syscalls.c -sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h +incpath := $(srctree)/tools +sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ systbl := $(sysprf)/mksyscalltbl @@ -19,7 +20,7 @@ systbl := $(sysprf)/mksyscalltbl _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@ + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ clean:: $(call QUIET_CLEAN, arm64) $(RM) $(header) diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl index 52e197317d3e..2dbb8cade048 100755 --- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -11,7 +11,8 @@ gcc=$1 hostcc=$2 -input=$3 +incpath=$3 +input=$4 if ! test -r $input; then echo "Could not read input file" >&2 @@ -28,7 +29,6 @@ create_table_from_c() cat <<-_EoHEADER #include <stdio.h> - #define __ARCH_WANT_RENAMEAT #include "$input" int main(int argc, char *argv[]) { @@ -42,7 +42,7 @@ create_table_from_c() printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);" printf "}\n" - } | $hostcc -o $create_table_exe -x c - + } | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c - $create_table_exe diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 20e7d74d86cd..10a44e946f77 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) #endif -#if !defined(_CALL_ELF) || _CALL_ELF != 2 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { char *sym = syma->name; +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Skip over any initial dot */ if (*sym == '.') sym++; +#endif /* Avoid "SyS" kernel syscall aliases */ if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3)) @@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma, return SYMBOL_A; } +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Allow matching against dot variants */ int arch__compare_symbol_names(const char *namea, const char *nameb) { diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index c1bd979b957b..613709cfbbd0 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -9,6 +9,7 @@ struct test; int test__rdpmc(struct test *test __maybe_unused, int subtest); int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); +int test__bp_modify(struct test *test, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 8e2c5a38c3b9..586849ff83a0 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -5,3 +5,4 @@ libperf-y += arch-tests.o libperf-y += rdpmc.o libperf-y += perf-time-to-tsc.o libperf-$(CONFIG_AUXTRACE) += insn-x86.o +libperf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index cc1802ff5410..d47d3f8e3c8e 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -24,6 +24,12 @@ struct test arch_tests[] = { .func = test__insn_x86, }, #endif +#if defined(__x86_64__) + { + .desc = "x86 bp modify", + .func = test__bp_modify, + }, +#endif { .func = NULL, }, diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c new file mode 100644 index 000000000000..f53e4406709f --- /dev/null +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/user.h> +#include <syscall.h> +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ptrace.h> +#include <asm/ptrace.h> +#include <errno.h> +#include "debug.h" +#include "tests/tests.h" +#include "arch-tests.h" + +static noinline int bp_1(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static noinline int bp_2(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static int spawn_child(void) +{ + int child = fork(); + + if (child == 0) { + /* + * The child sets itself for as tracee and + * waits in signal for parent to trace it, + * then it calls bp_1 and quits. + */ + int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL); + + if (err) { + pr_debug("failed to PTRACE_TRACEME\n"); + exit(1); + } + + raise(SIGCONT); + bp_1(); + exit(0); + } + + return child; +} + +/* + * This tests creates HW breakpoint, tries to + * change it and checks it was properly changed. + */ +static int bp_modify1(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_2 function + * - changes that breakponit to bp_1 function + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_2)) { + pr_debug("failed to set breakpoint, 1st time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint, 2nd time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +/* + * This tests creates HW breakpoint, tries to + * change it to bogus value and checks the original + * breakpoint is hit. + */ +static int bp_modify2(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_1 function + * - tries to change that breakpoint to (-1) address + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (!ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) { + pr_debug("failed, breakpoint set to bogus address\n"); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +int test__bp_modify(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1()); + TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2()); + + return 0; +} diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 20061cf42288..28cd6a17491b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -246,8 +246,14 @@ find_target: indirect_call: tok = strchr(endptr, '*'); - if (tok != NULL) - ops->target.addr = strtoull(tok + 1, NULL, 16); + if (tok != NULL) { + endptr++; + + /* Indirect call can use a non-rip register and offset: callq *0x8(%rbx). + * Do not parse such instruction. */ + if (strstr(endptr, "(%r") == NULL) + ops->target.addr = strtoull(endptr, NULL, 16); + } goto find_target; } @@ -276,7 +282,19 @@ bool ins__is_call(const struct ins *ins) return ins->ops == &call_ops || ins->ops == &s390_call_ops; } -static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms) +/* + * Prevents from matching commas in the comment section, e.g.: + * ffff200008446e70: b.cs ffff2000084470f4 <generic_exec_single+0x314> // b.hs, b.nlast + */ +static inline const char *validate_comma(const char *c, struct ins_operands *ops) +{ + if (ops->raw_comment && c > ops->raw_comment) + return NULL; + + return c; +} + +static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) { struct map *map = ms->map; struct symbol *sym = ms->sym; @@ -285,6 +303,10 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op }; const char *c = strchr(ops->raw, ','); u64 start, end; + + ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char); + c = validate_comma(c, ops); + /* * Examples of lines to parse for the _cpp_lex_token@@Base * function: @@ -304,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op ops->target.addr = strtoull(c, NULL, 16); if (!ops->target.addr) { c = strchr(c, ','); + c = validate_comma(c, ops); if (c++ != NULL) ops->target.addr = strtoull(c, NULL, 16); } @@ -361,9 +384,12 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size, return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name); c = strchr(ops->raw, ','); + c = validate_comma(c, ops); + if (c != NULL) { const char *c2 = strchr(c + 1, ','); + c2 = validate_comma(c2, ops); /* check for 3-op insn */ if (c2 != NULL) c = c2; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 005a5fe8a8c6..5399ba2321bb 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -22,6 +22,7 @@ struct ins { struct ins_operands { char *raw; + char *raw_comment; struct { char *raw; char *name; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c980bbff6353..1a61628a1c12 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -251,8 +251,9 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { struct perf_evsel *evsel = zalloc(perf_evsel__object.size); - if (evsel != NULL) - perf_evsel__init(evsel, attr, idx); + if (!evsel) + return NULL; + perf_evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 36d0763311ef..6a6929f208b4 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -576,6 +576,13 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg, return NULL; } +static bool map__contains_symbol(struct map *map, struct symbol *sym) +{ + u64 ip = map->unmap_ip(map, sym->start); + + return ip >= map->start && ip < map->end; +} + struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { @@ -591,6 +598,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, if (sym == NULL) continue; + if (!map__contains_symbol(pos, sym)) { + sym = NULL; + continue; + } if (mapp != NULL) *mapp = pos; goto out; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index c85d0d1a65ed..7b0ca7cbb7de 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -377,7 +377,7 @@ out: static int record_saved_cmdline(void) { - unsigned int size; + unsigned long long size; char *path; struct stat st; int ret, err = 0; diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 920b1d58a068..e76214f8d596 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -164,16 +164,15 @@ void parse_ftrace_printk(struct tep_handle *pevent, void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size __maybe_unused) { - char *comm; + char comm[17]; /* Max comm length in the kernel is 16. */ char *line; char *next = NULL; int pid; line = strtok_r(file, "\n", &next); while (line) { - sscanf(line, "%d %ms", &pid, &comm); - tep_register_comm(pevent, comm, pid); - free(comm); + if (sscanf(line, "%d %16s", &pid, comm) == 2) + tep_register_comm(pevent, comm, pid); line = strtok_r(NULL, "\n", &next); } } diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile index 72c25a3cb658..d9a725478375 100644 --- a/tools/testing/selftests/android/Makefile +++ b/tools/testing/selftests/android/Makefile @@ -6,7 +6,7 @@ TEST_PROGS := run.sh include ../lib.mk -all: +all: khdr @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ diff --git a/tools/testing/selftests/android/ion/config b/tools/testing/selftests/android/config index b4ad748a9dd9..b4ad748a9dd9 100644 --- a/tools/testing/selftests/android/ion/config +++ b/tools/testing/selftests/android/config diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile index e03695287f76..88cfe88e466f 100644 --- a/tools/testing/selftests/android/ion/Makefile +++ b/tools/testing/selftests/android/ion/Makefile @@ -10,6 +10,8 @@ $(TEST_GEN_FILES): ipcsocket.c ionutils.c TEST_PROGS := ion_test.sh +KSFT_KHDR_INSTALL := 1 +top_srcdir = ../../../../.. include ../../lib.mk $(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 6f54f84144a0..9b552c0fc47d 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -580,7 +580,11 @@ static void test_sockmap(int tasks, void *data) /* Test update without programs */ for (i = 0; i < 6; i++) { err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); - if (err) { + if (i < 2 && !err) { + printf("Allowed update sockmap '%i:%i' not in ESTABLISHED\n", + i, sfd[i]); + goto out_sockmap; + } else if (i >= 2 && err) { printf("Failed noprog update sockmap '%i:%i'\n", i, sfd[i]); goto out_sockmap; @@ -741,7 +745,7 @@ static void test_sockmap(int tasks, void *data) } /* Test map update elem afterwards fd lives in fd and map_fd */ - for (i = 0; i < 6; i++) { + for (i = 2; i < 6; i++) { err = bpf_map_update_elem(map_fd_rx, &i, &sfd[i], BPF_ANY); if (err) { printf("Failed map_fd_rx update sockmap %i '%i:%i'\n", @@ -845,7 +849,7 @@ static void test_sockmap(int tasks, void *data) } /* Delete the elems without programs */ - for (i = 0; i < 6; i++) { + for (i = 2; i < 6; i++) { err = bpf_map_delete_elem(fd, &i); if (err) { printf("Failed delete sockmap %i '%i:%i'\n", diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore index 95eb3a53c381..adacda50a4b2 100644 --- a/tools/testing/selftests/cgroup/.gitignore +++ b/tools/testing/selftests/cgroup/.gitignore @@ -1 +1,2 @@ test_memcontrol +test_core diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 1c5d2b2a583b..14c9fe284806 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -89,17 +89,28 @@ int cg_read(const char *cgroup, const char *control, char *buf, size_t len) int cg_read_strcmp(const char *cgroup, const char *control, const char *expected) { - size_t size = strlen(expected) + 1; + size_t size; char *buf; + int ret; + + /* Handle the case of comparing against empty string */ + if (!expected) + size = 32; + else + size = strlen(expected) + 1; buf = malloc(size); if (!buf) return -1; - if (cg_read(cgroup, control, buf, size)) + if (cg_read(cgroup, control, buf, size)) { + free(buf); return -1; + } - return strcmp(expected, buf); + ret = strcmp(expected, buf); + free(buf); + return ret; } int cg_read_strstr(const char *cgroup, const char *control, const char *needle) @@ -337,3 +348,24 @@ int is_swap_enabled(void) return cnt > 1; } + +int set_oom_adj_score(int pid, int score) +{ + char path[PATH_MAX]; + int fd, len; + + sprintf(path, "/proc/%d/oom_score_adj", pid); + + fd = open(path, O_WRONLY | O_APPEND); + if (fd < 0) + return fd; + + len = dprintf(fd, "%d", score); + if (len < 0) { + close(fd); + return len; + } + + close(fd); + return 0; +} diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 1ff6f9f1abdc..9ac8b7958f83 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -40,3 +40,4 @@ extern int get_temp_fd(void); extern int alloc_pagecache(int fd, size_t size); extern int alloc_anon(const char *cgroup, void *arg); extern int is_swap_enabled(void); +extern int set_oom_adj_score(int pid, int score); diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index cf0bddc9d271..28d321ba311b 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -2,6 +2,7 @@ #define _GNU_SOURCE #include <linux/limits.h> +#include <linux/oom.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> @@ -202,6 +203,36 @@ static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg) return 0; } +static int alloc_anon_noexit(const char *cgroup, void *arg) +{ + int ppid = getppid(); + + if (alloc_anon(cgroup, arg)) + return -1; + + while (getppid() == ppid) + sleep(1); + + return 0; +} + +/* + * Wait until processes are killed asynchronously by the OOM killer + * If we exceed a timeout, fail. + */ +static int cg_test_proc_killed(const char *cgroup) +{ + int limit; + + for (limit = 10; limit > 0; limit--) { + if (cg_read_strcmp(cgroup, "cgroup.procs", "") == 0) + return 0; + + usleep(100000); + } + return -1; +} + /* * First, this test creates the following hierarchy: * A memory.min = 50M, memory.max = 200M @@ -964,6 +995,177 @@ cleanup: return ret; } +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes in the leaf (but not the parent) were killed. + */ +static int test_memcg_oom_group_leaf_events(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child; + + parent = cg_name(root, "memcg_test_0"); + child = cg_name(root, "memcg_test_0/memcg_test_1"); + + if (!parent || !child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + if (cg_write(parent, "cgroup.subtree_control", "+memory")) + goto cleanup; + + if (cg_write(child, "memory.max", "50M")) + goto cleanup; + + if (cg_write(child, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(child, "memory.oom.group", "1")) + goto cleanup; + + cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + if (!cg_run(child, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_test_proc_killed(child)) + goto cleanup; + + if (cg_read_key_long(child, "memory.events", "oom_kill ") <= 0) + goto cleanup; + + if (cg_read_key_long(parent, "memory.events", "oom_kill ") != 0) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + if (parent) + cg_destroy(parent); + free(child); + free(parent); + + return ret; +} + +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes in the parent and leaf were killed. + */ +static int test_memcg_oom_group_parent_events(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child; + + parent = cg_name(root, "memcg_test_0"); + child = cg_name(root, "memcg_test_0/memcg_test_1"); + + if (!parent || !child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + if (cg_write(parent, "memory.max", "80M")) + goto cleanup; + + if (cg_write(parent, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(parent, "memory.oom.group", "1")) + goto cleanup; + + cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + + if (!cg_run(child, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_test_proc_killed(child)) + goto cleanup; + if (cg_test_proc_killed(parent)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + if (parent) + cg_destroy(parent); + free(child); + free(parent); + + return ret; +} + +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes were killed except those set with OOM_SCORE_ADJ_MIN + */ +static int test_memcg_oom_group_score_events(const char *root) +{ + int ret = KSFT_FAIL; + char *memcg; + int safe_pid; + + memcg = cg_name(root, "memcg_test_0"); + + if (!memcg) + goto cleanup; + + if (cg_create(memcg)) + goto cleanup; + + if (cg_write(memcg, "memory.max", "50M")) + goto cleanup; + + if (cg_write(memcg, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(memcg, "memory.oom.group", "1")) + goto cleanup; + + safe_pid = cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1)); + if (set_oom_adj_score(safe_pid, OOM_SCORE_ADJ_MIN)) + goto cleanup; + + cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1)); + if (!cg_run(memcg, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 3) + goto cleanup; + + if (kill(safe_pid, SIGKILL)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (memcg) + cg_destroy(memcg); + free(memcg); + + return ret; +} + + #define T(x) { x, #x } struct memcg_test { int (*fn)(const char *root); @@ -978,6 +1180,9 @@ struct memcg_test { T(test_memcg_oom_events), T(test_memcg_swap_max), T(test_memcg_sock), + T(test_memcg_oom_group_leaf_events), + T(test_memcg_oom_group_parent_events), + T(test_memcg_oom_group_score_events), }; #undef T diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh new file mode 100644 index 000000000000..0150bb2741eb --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh @@ -0,0 +1,347 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# A test for switch behavior under MC overload. An issue in Spectrum chips +# causes throughput of UC traffic to drop severely when a switch is under heavy +# MC load. This issue can be overcome by putting the switch to MC-aware mode. +# This test verifies that UC performance stays intact even as the switch is +# under MC flood, and therefore that the MC-aware mode is enabled and correctly +# configured. +# +# Because mlxsw throttles CPU port, the traffic can't actually reach userspace +# at full speed. That makes it impossible to use iperf3 to simply measure the +# throughput, because many packets (that reach $h3) don't get to the kernel at +# all even in UDP mode (the situation is even worse in TCP mode, where one can't +# hope to see more than a couple Mbps). +# +# So instead we send traffic with mausezahn and use RX ethtool counters at $h3. +# Multicast traffic is untagged, unicast traffic is tagged with PCP 1. Therefore +# each gets a different priority and we can use per-prio ethtool counters to +# measure the throughput. In order to avoid prioritizing unicast traffic, prio +# qdisc is installed on $swp3 and maps all priorities to the same band #7 (and +# thus TC 0). +# +# Mausezahn can't actually saturate the links unless it's using large frames. +# Thus we set MTU to 10K on all involved interfaces. Then both unicast and +# multicast traffic uses 8K frames. +# +# +-----------------------+ +----------------------------------+ +# | H1 | | H2 | +# | | | unicast --> + $h2.111 | +# | | | traffic | 192.0.2.129/28 | +# | multicast | | | e-qos-map 0:1 | +# | traffic | | | | +# | $h1 + <----- | | + $h2 | +# +-----|-----------------+ +--------------|-------------------+ +# | | +# +-----|-------------------------------------------------|-------------------+ +# | + $swp1 + $swp2 | +# | | >1Gbps | >1Gbps | +# | +---|----------------+ +----------|----------------+ | +# | | + $swp1.1 | | + $swp2.111 | | +# | | BR1 | SW | BR111 | | +# | | + $swp3.1 | | + $swp3.111 | | +# | +---|----------------+ +----------|----------------+ | +# | \_________________________________________________/ | +# | | | +# | + $swp3 | +# | | 1Gbps bottleneck | +# | | prio qdisc: {0..7} -> 7 | +# +------------------------------------|--------------------------------------+ +# | +# +--|-----------------+ +# | + $h3 H3 | +# | | | +# | + $h3.111 | +# | 192.0.2.130/28 | +# +--------------------+ + +ALL_TESTS=" + ping_ipv4 + test_mc_aware +" + +lib_dir=$(dirname $0)/../../../net/forwarding + +NUM_NETIFS=6 +source $lib_dir/lib.sh + +h1_create() +{ + simple_if_init $h1 + mtu_set $h1 10000 +} + +h1_destroy() +{ + mtu_restore $h1 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + mtu_set $h2 10000 + + vlan_create $h2 111 v$h2 192.0.2.129/28 + ip link set dev $h2.111 type vlan egress-qos-map 0:1 +} + +h2_destroy() +{ + vlan_destroy $h2 111 + + mtu_restore $h2 + simple_if_fini $h2 +} + +h3_create() +{ + simple_if_init $h3 + mtu_set $h3 10000 + + vlan_create $h3 111 v$h3 192.0.2.130/28 +} + +h3_destroy() +{ + vlan_destroy $h3 111 + + mtu_restore $h3 + simple_if_fini $h3 +} + +switch_create() +{ + ip link set dev $swp1 up + mtu_set $swp1 10000 + + ip link set dev $swp2 up + mtu_set $swp2 10000 + + ip link set dev $swp3 up + mtu_set $swp3 10000 + + vlan_create $swp2 111 + vlan_create $swp3 111 + + ethtool -s $swp3 speed 1000 autoneg off + tc qdisc replace dev $swp3 root handle 3: \ + prio bands 8 priomap 7 7 7 7 7 7 7 7 + + ip link add name br1 type bridge vlan_filtering 0 + ip link set dev br1 up + ip link set dev $swp1 master br1 + ip link set dev $swp3 master br1 + + ip link add name br111 type bridge vlan_filtering 0 + ip link set dev br111 up + ip link set dev $swp2.111 master br111 + ip link set dev $swp3.111 master br111 +} + +switch_destroy() +{ + ip link del dev br111 + ip link del dev br1 + + tc qdisc del dev $swp3 root handle 3: + ethtool -s $swp3 autoneg on + + vlan_destroy $swp3 111 + vlan_destroy $swp2 111 + + mtu_restore $swp3 + ip link set dev $swp3 down + + mtu_restore $swp2 + ip link set dev $swp2 down + + mtu_restore $swp1 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + h3mac=$(mac_get $h3) + + vrf_prepare + + h1_create + h2_create + h3_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h2 192.0.2.130 +} + +humanize() +{ + local speed=$1; shift + + for unit in bps Kbps Mbps Gbps; do + if (($(echo "$speed < 1024" | bc))); then + break + fi + + speed=$(echo "scale=1; $speed / 1024" | bc) + done + + echo "$speed${unit}" +} + +rate() +{ + local t0=$1; shift + local t1=$1; shift + local interval=$1; shift + + echo $((8 * (t1 - t0) / interval)) +} + +check_rate() +{ + local rate=$1; shift + local min=$1; shift + local what=$1; shift + + if ((rate > min)); then + return 0 + fi + + echo "$what $(humanize $ir) < $(humanize $min_ingress)" > /dev/stderr + return 1 +} + +measure_uc_rate() +{ + local what=$1; shift + + local interval=10 + local i + local ret=0 + + # Dips in performance might cause momentary ingress rate to drop below + # 1Gbps. That wouldn't saturate egress and MC would thus get through, + # seemingly winning bandwidth on account of UC. Demand at least 2Gbps + # average ingress rate to somewhat mitigate this. + local min_ingress=2147483648 + + mausezahn $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \ + -a own -b $h3mac -t udp -q & + sleep 1 + + for i in {5..0}; do + local t0=$(ethtool_stats_get $h3 rx_octets_prio_1) + local u0=$(ethtool_stats_get $swp2 rx_octets_prio_1) + sleep $interval + local t1=$(ethtool_stats_get $h3 rx_octets_prio_1) + local u1=$(ethtool_stats_get $swp2 rx_octets_prio_1) + + local ir=$(rate $u0 $u1 $interval) + local er=$(rate $t0 $t1 $interval) + + if check_rate $ir $min_ingress "$what ingress rate"; then + break + fi + + # Fail the test if we can't get the throughput. + if ((i == 0)); then + ret=1 + fi + done + + # Suppress noise from killing mausezahn. + { kill %% && wait; } 2>/dev/null + + echo $ir $er + exit $ret +} + +test_mc_aware() +{ + RET=0 + + local -a uc_rate + uc_rate=($(measure_uc_rate "UC-only")) + check_err $? "Could not get high enough UC-only ingress rate" + local ucth1=${uc_rate[1]} + + mausezahn $h1 -p 8000 -c 0 -a own -b bc -t udp -q & + + local d0=$(date +%s) + local t0=$(ethtool_stats_get $h3 rx_octets_prio_0) + local u0=$(ethtool_stats_get $swp1 rx_octets_prio_0) + + local -a uc_rate_2 + uc_rate_2=($(measure_uc_rate "UC+MC")) + check_err $? "Could not get high enough UC+MC ingress rate" + local ucth2=${uc_rate_2[1]} + + local d1=$(date +%s) + local t1=$(ethtool_stats_get $h3 rx_octets_prio_0) + local u1=$(ethtool_stats_get $swp1 rx_octets_prio_0) + + local deg=$(bc <<< " + scale=2 + ret = 100 * ($ucth1 - $ucth2) / $ucth1 + if (ret > 0) { ret } else { 0 } + ") + check_err $(bc <<< "$deg > 10") + + local interval=$((d1 - d0)) + local mc_ir=$(rate $u0 $u1 $interval) + local mc_er=$(rate $t0 $t1 $interval) + + # Suppress noise from killing mausezahn. + { kill %% && wait; } 2>/dev/null + + log_test "UC performace under MC overload" + + echo "UC-only throughput $(humanize $ucth1)" + echo "UC+MC throughput $(humanize $ucth2)" + echo "Degradation $deg %" + echo + echo "Full report:" + echo " UC only:" + echo " ingress UC throughput $(humanize ${uc_rate[0]})" + echo " egress UC throughput $(humanize ${uc_rate[1]})" + echo " UC+MC:" + echo " ingress UC throughput $(humanize ${uc_rate_2[0]})" + echo " egress UC throughput $(humanize ${uc_rate_2[1]})" + echo " ingress MC throughput $(humanize $mc_ir)" + echo " egress MC throughput $(humanize $mc_er)" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/efivarfs/config b/tools/testing/selftests/efivarfs/config new file mode 100644 index 000000000000..4e151f1005b2 --- /dev/null +++ b/tools/testing/selftests/efivarfs/config @@ -0,0 +1 @@ +CONFIG_EFIVAR_FS=y diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index ff8feca49746..ad1eeb14fda7 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -18,6 +18,7 @@ TEST_GEN_FILES := \ TEST_PROGS := run.sh +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 1bbb47565c55..4665cdbf1a8d 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -21,11 +21,8 @@ endef CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ LDLIBS += -lmount -I/usr/include/libmount -$(BINARIES): ../../../gpio/gpio-utils.o ../../../../usr/include/linux/gpio.h +$(BINARIES):| khdr +$(BINARIES): ../../../gpio/gpio-utils.o ../../../gpio/gpio-utils.o: make ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio - -../../../../usr/include/linux/gpio.h: - make -C ../../../.. headers_install INSTALL_HDR_PATH=$(shell pwd)/../../../../usr/ - diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 15e6b75fc3a5..a3edb2c8e43d 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -19,7 +19,6 @@ #define KSFT_FAIL 1 #define KSFT_XFAIL 2 #define KSFT_XPASS 3 -/* Treat skip as pass */ #define KSFT_SKIP 4 /* counters */ diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 4202139d81d9..5c34752e1cff 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,4 +1,5 @@ cr4_cpuid_sync_test +platform_info_test set_sregs_test sync_regs_test vmx_tsc_adjust_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 03b0f551bedf..ec32dad3c3f0 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -6,7 +6,8 @@ UNAME_M := $(shell uname -m) LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c LIBKVM_x86_64 = lib/x86.c lib/vmx.c -TEST_GEN_PROGS_x86_64 = set_sregs_test +TEST_GEN_PROGS_x86_64 = platform_info_test +TEST_GEN_PROGS_x86_64 += set_sregs_test TEST_GEN_PROGS_x86_64 += sync_regs_test TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += cr4_cpuid_sync_test @@ -20,7 +21,7 @@ INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)tools/include CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I.. -LDFLAGS += -lpthread +LDFLAGS += -pthread # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ @@ -37,9 +38,6 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) $(AR) crs $@ $^ -$(LINUX_HDR_PATH): - make -C $(top_srcdir) headers_install - -all: $(STATIC_LIBS) $(LINUX_HDR_PATH) +all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) -$(TEST_GEN_PROGS) $(LIBKVM_OBJ): | $(LINUX_HDR_PATH) +$(STATIC_LIBS):| khdr diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index bb5a25fb82c6..3acf9a91704c 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -50,6 +50,7 @@ enum vm_mem_backing_src_type { }; int kvm_check_cap(long cap); +int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); void kvm_vm_free(struct kvm_vm *vmp); @@ -108,6 +109,9 @@ void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events); void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events); +uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index); +void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value); const char *exit_reason_str(unsigned int exit_reason); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index e9ba389c48db..6fd8c089cafc 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -63,6 +63,29 @@ int kvm_check_cap(long cap) return ret; } +/* VM Enable Capability + * + * Input Args: + * vm - Virtual Machine + * cap - Capability + * + * Output Args: None + * + * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * + * Enables a capability (KVM_CAP_*) on the VM. + */ +int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) +{ + int ret; + + ret = ioctl(vm->fd, KVM_ENABLE_CAP, cap); + TEST_ASSERT(ret == 0, "KVM_ENABLE_CAP IOCTL failed,\n" + " rc: %i errno: %i", ret, errno); + + return ret; +} + static void vm_open(struct kvm_vm *vm, int perm) { vm->kvm_fd = open(KVM_DEV_PATH, perm); @@ -1220,6 +1243,72 @@ void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, ret, errno); } +/* VCPU Get MSR + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * msr_index - Index of MSR + * + * Output Args: None + * + * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced. + * + * Get value of MSR for VCPU. + */ +uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + struct { + struct kvm_msrs header; + struct kvm_msr_entry entry; + } buffer = {}; + int r; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + buffer.header.nmsrs = 1; + buffer.entry.index = msr_index; + r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header); + TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" + " rc: %i errno: %i", r, errno); + + return buffer.entry.data; +} + +/* VCPU Set MSR + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * msr_index - Index of MSR + * msr_value - New value of MSR + * + * Output Args: None + * + * Return: On success, nothing. On failure a TEST_ASSERT is produced. + * + * Set value of MSR for VCPU. + */ +void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + struct { + struct kvm_msrs header; + struct kvm_msr_entry entry; + } buffer = {}; + int r; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + memset(&buffer, 0, sizeof(buffer)); + buffer.header.nmsrs = 1; + buffer.entry.index = msr_index; + buffer.entry.data = msr_value; + r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header); + TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n" + " rc: %i errno: %i", r, errno); +} + /* VM VCPU Args Set * * Input Args: diff --git a/tools/testing/selftests/kvm/platform_info_test.c b/tools/testing/selftests/kvm/platform_info_test.c new file mode 100644 index 000000000000..3764e7121265 --- /dev/null +++ b/tools/testing/selftests/kvm/platform_info_test.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test for x86 KVM_CAP_MSR_PLATFORM_INFO + * + * Copyright (C) 2018, Google LLC. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Verifies expected behavior of controlling guest access to + * MSR_PLATFORM_INFO. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "x86.h" + +#define VCPU_ID 0 +#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00 + +static void guest_code(void) +{ + uint64_t msr_platform_info; + + for (;;) { + msr_platform_info = rdmsr(MSR_PLATFORM_INFO); + GUEST_SYNC(msr_platform_info); + asm volatile ("inc %r11"); + } +} + +static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable) +{ + struct kvm_enable_cap cap = {}; + + cap.cap = KVM_CAP_MSR_PLATFORM_INFO; + cap.flags = 0; + cap.args[0] = (int)enable; + vm_enable_cap(vm, &cap); +} + +static void test_msr_platform_info_enabled(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct guest_args args; + + set_msr_platform_info_enabled(vm, true); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Exit_reason other than KVM_EXIT_IO: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + guest_args_read(vm, VCPU_ID, &args); + TEST_ASSERT(args.port == GUEST_PORT_SYNC, + "Received IO from port other than PORT_HOST_SYNC: %u\n", + run->io.port); + TEST_ASSERT((args.arg1 & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) == + MSR_PLATFORM_INFO_MAX_TURBO_RATIO, + "Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.", + MSR_PLATFORM_INFO_MAX_TURBO_RATIO); +} + +static void test_msr_platform_info_disabled(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + set_msr_platform_info_enabled(vm, false); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + struct kvm_run *state; + int rv; + uint64_t msr_platform_info; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO); + if (!rv) { + fprintf(stderr, + "KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n"); + exit(KSFT_SKIP); + } + + vm = vm_create_default(VCPU_ID, 0, guest_code); + + 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); + vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 17ab36605a8e..0a8e75886224 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -16,8 +16,20 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) +top_srcdir ?= ../../../.. +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) + all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +.PHONY: khdr +khdr: + make ARCH=$(ARCH) -C $(top_srcdir) headers_install + +ifdef KSFT_KHDR_INSTALL +$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES):| khdr +endif + .ONESHELL: define RUN_TEST_PRINT_RESULT TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST"; \ diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config index 2fde30191a47..a7e8cd5bb265 100644 --- a/tools/testing/selftests/memory-hotplug/config +++ b/tools/testing/selftests/memory-hotplug/config @@ -2,3 +2,4 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTPLUG_SPARSE=y CONFIG_NOTIFIER_ERROR_INJECTION=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m +CONFIG_MEMORY_HOTREMOVE=y diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index cccdb2295567..256d82d5fa87 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -15,6 +15,7 @@ TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls +KSFT_KHDR_INSTALL := 1 include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index ca53b539aa2d..0e73698b2048 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -494,6 +494,14 @@ tc_rule_stats_get() | jq '.[1].options.actions[].stats.packets' } +ethtool_stats_get() +{ + local dev=$1; shift + local stat=$1; shift + + ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2 +} + mac_get() { local if_name=$1 @@ -541,6 +549,23 @@ forwarding_restore() sysctl_restore net.ipv4.conf.all.forwarding } +declare -A MTU_ORIG +mtu_set() +{ + local dev=$1; shift + local mtu=$1; shift + + MTU_ORIG["$dev"]=$(ip -j link show dev $dev | jq -e '.[].mtu') + ip link set dev $dev mtu $mtu +} + +mtu_restore() +{ + local dev=$1; shift + + ip link set dev $dev mtu ${MTU_ORIG["$dev"]} +} + tc_offload_check() { local num_netifs=${1:-$NUM_NETIFS} diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c index 55fdcdc78eef..2366dc6bce71 100644 --- a/tools/testing/selftests/net/ip_defrag.c +++ b/tools/testing/selftests/net/ip_defrag.c @@ -23,21 +23,28 @@ static bool cfg_overlap; static unsigned short cfg_port = 9000; const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) }; +const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT; #define IP4_HLEN (sizeof(struct iphdr)) #define IP6_HLEN (sizeof(struct ip6_hdr)) #define UDP_HLEN (sizeof(struct udphdr)) -static int msg_len; +/* IPv6 fragment header lenth. */ +#define FRAG_HLEN 8 + +static int payload_len; static int max_frag_len; #define MSG_LEN_MAX 60000 /* Max UDP payload length. */ #define IP4_MF (1u << 13) /* IPv4 MF flag. */ +#define IP6_MF (1) /* IPv6 MF flag. */ + +#define CSUM_MANGLED_0 (0xffff) static uint8_t udp_payload[MSG_LEN_MAX]; static uint8_t ip_frame[IP_MAXPACKET]; -static uint16_t ip_id = 0xabcd; +static uint32_t ip_id = 0xabcd; static int msg_counter; static int frag_counter; static unsigned int seed; @@ -48,25 +55,25 @@ static void recv_validate_udp(int fd_udp) ssize_t ret; static uint8_t recv_buff[MSG_LEN_MAX]; - ret = recv(fd_udp, recv_buff, msg_len, 0); + ret = recv(fd_udp, recv_buff, payload_len, 0); msg_counter++; if (cfg_overlap) { if (ret != -1) - error(1, 0, "recv: expected timeout; got %d; seed = %u", - (int)ret, seed); + error(1, 0, "recv: expected timeout; got %d", + (int)ret); if (errno != ETIMEDOUT && errno != EAGAIN) - error(1, errno, "recv: expected timeout: %d; seed = %u", - errno, seed); + error(1, errno, "recv: expected timeout: %d", + errno); return; /* OK */ } if (ret == -1) - error(1, errno, "recv: msg_len = %d max_frag_len = %d", - msg_len, max_frag_len); - if (ret != msg_len) - error(1, 0, "recv: wrong size: %d vs %d", (int)ret, msg_len); - if (memcmp(udp_payload, recv_buff, msg_len)) + error(1, errno, "recv: payload_len = %d max_frag_len = %d", + payload_len, max_frag_len); + if (ret != payload_len) + error(1, 0, "recv: wrong size: %d vs %d", (int)ret, payload_len); + if (memcmp(udp_payload, recv_buff, payload_len)) error(1, 0, "recv: wrong data"); } @@ -92,31 +99,95 @@ static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum) static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr) { uint32_t sum = 0; + uint16_t res; sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src), - IPPROTO_UDP + (uint32_t)(UDP_HLEN + msg_len)); - sum = raw_checksum((uint8_t *)udp_payload, msg_len, sum); + IPPROTO_UDP + (uint32_t)(UDP_HLEN + payload_len)); + sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum); + sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum); + res = 0xffff & ~sum; + if (res) + return htons(res); + else + return CSUM_MANGLED_0; +} + +static uint16_t udp6_checksum(struct ip6_hdr *iphdr, struct udphdr *udphdr) +{ + uint32_t sum = 0; + uint16_t res; + + sum = raw_checksum((uint8_t *)&iphdr->ip6_src, 2 * sizeof(iphdr->ip6_src), + IPPROTO_UDP); + sum = raw_checksum((uint8_t *)&udphdr->len, sizeof(udphdr->len), sum); sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum); - return htons(0xffff & ~sum); + sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum); + res = 0xffff & ~sum; + if (res) + return htons(res); + else + return CSUM_MANGLED_0; } static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen, - struct ip *iphdr, int offset) + int offset, bool ipv6) { int frag_len; int res; + int payload_offset = offset > 0 ? offset - UDP_HLEN : 0; + uint8_t *frag_start = ipv6 ? ip_frame + IP6_HLEN + FRAG_HLEN : + ip_frame + IP4_HLEN; + + if (offset == 0) { + struct udphdr udphdr; + udphdr.source = htons(cfg_port + 1); + udphdr.dest = htons(cfg_port); + udphdr.len = htons(UDP_HLEN + payload_len); + udphdr.check = 0; + if (ipv6) + udphdr.check = udp6_checksum((struct ip6_hdr *)ip_frame, &udphdr); + else + udphdr.check = udp_checksum((struct ip *)ip_frame, &udphdr); + memcpy(frag_start, &udphdr, UDP_HLEN); + } - if (msg_len - offset <= max_frag_len) { - /* This is the last fragment. */ - frag_len = IP4_HLEN + msg_len - offset; - iphdr->ip_off = htons((offset + UDP_HLEN) / 8); + if (ipv6) { + struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame; + struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); + if (payload_len - payload_offset <= max_frag_len && offset > 0) { + /* This is the last fragment. */ + frag_len = FRAG_HLEN + payload_len - payload_offset; + fraghdr->ip6f_offlg = htons(offset); + } else { + frag_len = FRAG_HLEN + max_frag_len; + fraghdr->ip6f_offlg = htons(offset | IP6_MF); + } + ip6hdr->ip6_plen = htons(frag_len); + if (offset == 0) + memcpy(frag_start + UDP_HLEN, udp_payload, + frag_len - FRAG_HLEN - UDP_HLEN); + else + memcpy(frag_start, udp_payload + payload_offset, + frag_len - FRAG_HLEN); + frag_len += IP6_HLEN; } else { - frag_len = IP4_HLEN + max_frag_len; - iphdr->ip_off = htons((offset + UDP_HLEN) / 8 | IP4_MF); + struct ip *iphdr = (struct ip *)ip_frame; + if (payload_len - payload_offset <= max_frag_len && offset > 0) { + /* This is the last fragment. */ + frag_len = IP4_HLEN + payload_len - payload_offset; + iphdr->ip_off = htons(offset / 8); + } else { + frag_len = IP4_HLEN + max_frag_len; + iphdr->ip_off = htons(offset / 8 | IP4_MF); + } + iphdr->ip_len = htons(frag_len); + if (offset == 0) + memcpy(frag_start + UDP_HLEN, udp_payload, + frag_len - IP4_HLEN - UDP_HLEN); + else + memcpy(frag_start, udp_payload + payload_offset, + frag_len - IP4_HLEN); } - iphdr->ip_len = htons(frag_len); - memcpy(ip_frame + IP4_HLEN, udp_payload + offset, - frag_len - IP4_HLEN); res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); if (res < 0) @@ -127,9 +198,11 @@ static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen, frag_counter++; } -static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen) +static void send_udp_frags(int fd_raw, struct sockaddr *addr, + socklen_t alen, bool ipv6) { struct ip *iphdr = (struct ip *)ip_frame; + struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame; struct udphdr udphdr; int res; int offset; @@ -142,31 +215,55 @@ static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen) * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then * even fragments (0th, 2nd, etc.) are sent out. */ - memset(iphdr, 0, sizeof(*iphdr)); - iphdr->ip_hl = 5; - iphdr->ip_v = 4; - iphdr->ip_tos = 0; - iphdr->ip_id = htons(ip_id++); - iphdr->ip_ttl = 0x40; - iphdr->ip_p = IPPROTO_UDP; - iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK); - iphdr->ip_dst = addr4; - iphdr->ip_sum = 0; + if (ipv6) { + struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); + ((struct sockaddr_in6 *)addr)->sin6_port = 0; + memset(ip6hdr, 0, sizeof(*ip6hdr)); + ip6hdr->ip6_flow = htonl(6<<28); /* Version. */ + ip6hdr->ip6_nxt = IPPROTO_FRAGMENT; + ip6hdr->ip6_hops = 255; + ip6hdr->ip6_src = addr6; + ip6hdr->ip6_dst = addr6; + fraghdr->ip6f_nxt = IPPROTO_UDP; + fraghdr->ip6f_reserved = 0; + fraghdr->ip6f_ident = htonl(ip_id++); + } else { + memset(iphdr, 0, sizeof(*iphdr)); + iphdr->ip_hl = 5; + iphdr->ip_v = 4; + iphdr->ip_tos = 0; + iphdr->ip_id = htons(ip_id++); + iphdr->ip_ttl = 0x40; + iphdr->ip_p = IPPROTO_UDP; + iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK); + iphdr->ip_dst = addr4; + iphdr->ip_sum = 0; + } /* Odd fragments. */ - offset = 0; - while (offset < msg_len) { - send_fragment(fd_raw, addr, alen, iphdr, offset); + offset = max_frag_len; + while (offset < (UDP_HLEN + payload_len)) { + send_fragment(fd_raw, addr, alen, offset, ipv6); offset += 2 * max_frag_len; } if (cfg_overlap) { /* Send an extra random fragment. */ - offset = rand() % (UDP_HLEN + msg_len - 1); + offset = rand() % (UDP_HLEN + payload_len - 1); /* sendto() returns EINVAL if offset + frag_len is too small. */ - frag_len = IP4_HLEN + UDP_HLEN + rand() % 256; - iphdr->ip_off = htons(offset / 8 | IP4_MF); - iphdr->ip_len = htons(frag_len); + if (ipv6) { + struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); + frag_len = max_frag_len + rand() % 256; + /* In IPv6 if !!(frag_len % 8), the fragment is dropped. */ + frag_len &= ~0x7; + fraghdr->ip6f_offlg = htons(offset / 8 | IP6_MF); + ip6hdr->ip6_plen = htons(frag_len); + frag_len += IP6_HLEN; + } else { + frag_len = IP4_HLEN + UDP_HLEN + rand() % 256; + iphdr->ip_off = htons(offset / 8 | IP4_MF); + iphdr->ip_len = htons(frag_len); + } res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); if (res < 0) error(1, errno, "sendto overlap"); @@ -175,48 +272,26 @@ static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen) frag_counter++; } - /* Zeroth fragment (UDP header). */ - frag_len = IP4_HLEN + UDP_HLEN; - iphdr->ip_len = htons(frag_len); - iphdr->ip_off = htons(IP4_MF); - - udphdr.source = htons(cfg_port + 1); - udphdr.dest = htons(cfg_port); - udphdr.len = htons(UDP_HLEN + msg_len); - udphdr.check = 0; - udphdr.check = udp_checksum(iphdr, &udphdr); - - memcpy(ip_frame + IP4_HLEN, &udphdr, UDP_HLEN); - res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); - if (res < 0) - error(1, errno, "sendto UDP header"); - if (res != frag_len) - error(1, 0, "sendto UDP header: %d vs %d", (int)res, frag_len); - frag_counter++; - - /* Even fragments. */ - offset = max_frag_len; - while (offset < msg_len) { - send_fragment(fd_raw, addr, alen, iphdr, offset); + /* Event fragments. */ + offset = 0; + while (offset < (UDP_HLEN + payload_len)) { + send_fragment(fd_raw, addr, alen, offset, ipv6); offset += 2 * max_frag_len; } } -static void run_test(struct sockaddr *addr, socklen_t alen) +static void run_test(struct sockaddr *addr, socklen_t alen, bool ipv6) { - int fd_tx_udp, fd_tx_raw, fd_rx_udp; + int fd_tx_raw, fd_rx_udp; struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 }; int idx; + int min_frag_len = ipv6 ? 1280 : 8; /* Initialize the payload. */ for (idx = 0; idx < MSG_LEN_MAX; ++idx) udp_payload[idx] = idx % 256; /* Open sockets. */ - fd_tx_udp = socket(addr->sa_family, SOCK_DGRAM, 0); - if (fd_tx_udp == -1) - error(1, errno, "socket tx_udp"); - fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW); if (fd_tx_raw == -1) error(1, errno, "socket tx_raw"); @@ -230,22 +305,21 @@ static void run_test(struct sockaddr *addr, socklen_t alen) if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) error(1, errno, "setsockopt rcv timeout"); - for (msg_len = 1; msg_len < MSG_LEN_MAX; msg_len += (rand() % 4096)) { + for (payload_len = min_frag_len; payload_len < MSG_LEN_MAX; + payload_len += (rand() % 4096)) { if (cfg_verbose) - printf("msg_len: %d\n", msg_len); - max_frag_len = addr->sa_family == AF_INET ? 8 : 1280; - for (; max_frag_len < 1500 && max_frag_len <= msg_len; - max_frag_len += 8) { - send_udp_frags_v4(fd_tx_raw, addr, alen); + printf("payload_len: %d\n", payload_len); + max_frag_len = min_frag_len; + do { + send_udp_frags(fd_tx_raw, addr, alen, ipv6); recv_validate_udp(fd_rx_udp); - } + max_frag_len += 8 * (rand() % 8); + } while (max_frag_len < (1500 - FRAG_HLEN) && max_frag_len <= payload_len); } /* Cleanup. */ if (close(fd_tx_raw)) error(1, errno, "close tx_raw"); - if (close(fd_tx_udp)) - error(1, errno, "close tx_udp"); if (close(fd_rx_udp)) error(1, errno, "close rx_udp"); @@ -265,13 +339,18 @@ static void run_test_v4(void) addr.sin_port = htons(cfg_port); addr.sin_addr = addr4; - run_test((void *)&addr, sizeof(addr)); + run_test((void *)&addr, sizeof(addr), false /* !ipv6 */); } static void run_test_v6(void) { - fprintf(stderr, "NOT IMPL.\n"); - exit(1); + struct sockaddr_in6 addr = {0}; + + addr.sin6_family = AF_INET6; + addr.sin6_port = htons(cfg_port); + addr.sin6_addr = addr6; + + run_test((void *)&addr, sizeof(addr), true /* ipv6 */); } static void parse_opts(int argc, char **argv) @@ -303,6 +382,8 @@ int main(int argc, char **argv) parse_opts(argc, argv); seed = time(NULL); srand(seed); + /* Print the seed to track/reproduce potential failures. */ + printf("seed = %d\n", seed); if (cfg_do_ipv4) run_test_v4(); diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh index 78743adcca9e..3a4042d918f0 100755 --- a/tools/testing/selftests/net/ip_defrag.sh +++ b/tools/testing/selftests/net/ip_defrag.sh @@ -6,23 +6,34 @@ set +x set -e -echo "ipv4 defrag" +readonly NETNS="ns-$(mktemp -u XXXXXX)" + +setup() { + ip netns add "${NETNS}" + ip -netns "${NETNS}" link set lo up + ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null + ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null + ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 &> /dev/null + ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 &> /dev/null +} -run_v4() { -sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null -sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null -./ip_defrag -4 +cleanup() { + ip netns del "${NETNS}" } -export -f run_v4 -./in_netns.sh "run_v4" +trap cleanup EXIT +setup + +echo "ipv4 defrag" +ip netns exec "${NETNS}" ./ip_defrag -4 + echo "ipv4 defrag with overlaps" -run_v4o() { -sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null -sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null -./ip_defrag -4o -} -export -f run_v4o +ip netns exec "${NETNS}" ./ip_defrag -4o + +echo "ipv6 defrag" +ip netns exec "${NETNS}" ./ip_defrag -6 + +echo "ipv6 defrag with overlaps" +ip netns exec "${NETNS}" ./ip_defrag -6o -./in_netns.sh "run_v4o" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 32a194e3e07a..0ab9423d009f 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -178,8 +178,8 @@ setup() { cleanup() { [ ${cleanup_done} -eq 1 ] && return - ip netns del ${NS_A} 2 > /dev/null - ip netns del ${NS_B} 2 > /dev/null + ip netns del ${NS_A} 2> /dev/null + ip netns del ${NS_B} 2> /dev/null cleanup_done=1 } diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 07daff076ce0..11d54c36ae49 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -121,11 +121,11 @@ TEST_F(tls, send_then_sendfile) buf = (char *)malloc(st.st_size); EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send); - EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send); + EXPECT_EQ(recv(self->cfd, recv_buf, to_send, MSG_WAITALL), to_send); EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0); EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0); - EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size); + EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size); } TEST_F(tls, recv_max) @@ -160,7 +160,7 @@ TEST_F(tls, msg_more) EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1); EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); - EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT), + EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_WAITALL), send_len * 2); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } @@ -180,7 +180,7 @@ TEST_F(tls, sendmsg_single) msg.msg_iov = &vec; msg.msg_iovlen = 1; EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); - EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } @@ -306,7 +306,7 @@ TEST_F(tls, splice_from_pipe2) EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0); EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0); EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0); - EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0); + EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len); EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } @@ -436,7 +436,7 @@ TEST_F(tls, multiple_send_single_recv) EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0); EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0); memset(recv_mem, 0, total_len); - EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len); + EXPECT_EQ(recv(self->cfd, recv_mem, total_len, MSG_WAITALL), total_len); EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0); EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0); @@ -502,6 +502,55 @@ TEST_F(tls, recv_peek_multiple) EXPECT_EQ(memcmp(test_str, buf, send_len), 0); } +TEST_F(tls, recv_peek_multiple_records) +{ + char const *test_str = "test_read_peek_mult_recs"; + char const *test_str_first = "test_read_peek"; + char const *test_str_second = "_mult_recs"; + int len; + char buf[64]; + + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, 0), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + /* MSG_PEEK can only peek into the current record. */ + len = strlen(test_str_first) + 1; + EXPECT_EQ(memcmp(test_str_first, buf, len), 0); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, 0), -1); + + /* Non-MSG_PEEK will advance strparser (and therefore record) + * however. + */ + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); + + /* MSG_MORE will hold current record open, so later MSG_PEEK + * will see everything. + */ + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, MSG_MORE), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); +} + TEST_F(tls, recv_peek_large_buf_mult_recs) { char const *test_str = "test_read_peek_mult_recs"; @@ -524,6 +573,7 @@ TEST_F(tls, recv_peek_large_buf_mult_recs) EXPECT_EQ(memcmp(test_str, buf, len), 0); } + TEST_F(tls, pollin) { char const *test_str = "test_poll"; @@ -537,7 +587,7 @@ TEST_F(tls, pollin) EXPECT_EQ(poll(&fd, 1, 20), 1); EXPECT_EQ(fd.revents & POLLIN, 1); - EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len); /* Test timing out */ EXPECT_EQ(poll(&fd, 1, 20), 0); } @@ -555,7 +605,7 @@ TEST_F(tls, poll_wait) /* Set timeout to inf. secs */ EXPECT_EQ(poll(&fd, 1, -1), 1); EXPECT_EQ(fd.revents & POLLIN, 1); - EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, recv_mem, send_len, MSG_WAITALL), send_len); } TEST_F(tls, blocking) @@ -701,7 +751,7 @@ TEST_F(tls, control_msg) EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); vec.iov_base = buf; - EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len); + EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); cmsg = CMSG_FIRSTHDR(&msg); EXPECT_NE(cmsg, NULL); EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index a728040edbe1..14cfcf006936 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -5,6 +5,7 @@ TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp all: $(TEST_PROGS) +top_srcdir = ../../../../.. include ../../lib.mk clean: diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9881876d2aa0..e94b7b14bcb2 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -26,10 +26,6 @@ TEST_PROGS := run_vmtests include ../lib.mk -$(OUTPUT)/userfaultfd: ../../../../usr/include/linux/kernel.h $(OUTPUT)/userfaultfd: LDLIBS += -lpthread $(OUTPUT)/mlock-random-test: LDLIBS += -lcap - -../../../../usr/include/linux/kernel.h: - make -C ../../../.. headers_install diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 30cb0a0713ff..37908a83ddc2 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -159,12 +159,6 @@ static const char * const page_flag_names[] = { }; -static const char * const debugfs_known_mountpoints[] = { - "/sys/kernel/debug", - "/debug", - 0, -}; - /* * data structures */ diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c index f82c2eaa859d..334b16db0ebb 100644 --- a/tools/vm/slabinfo.c +++ b/tools/vm/slabinfo.c @@ -30,8 +30,8 @@ struct slabinfo { int alias; int refs; int aliases, align, cache_dma, cpu_slabs, destroy_by_rcu; - int hwcache_align, object_size, objs_per_slab; - int sanity_checks, slab_size, store_user, trace; + unsigned int hwcache_align, object_size, objs_per_slab; + unsigned int sanity_checks, slab_size, store_user, trace; int order, poison, reclaim_account, red_zone; unsigned long partial, objects, slabs, objects_partial, objects_total; unsigned long alloc_fastpath, alloc_slowpath; |