diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-23 16:49:12 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-23 16:49:12 -0800 |
commit | 00198dab3b825ab264424a052beea5acb859754f (patch) | |
tree | 1afa5fc96a0447bc8049a9992e5d4d047f5f0b38 | |
parent | 9004fda59577d439564d44d6d1db52d262fe3f99 (diff) | |
parent | 3705b97505bcbf6440f38119c0e7d6058f585b54 (diff) |
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Ingo Molnar:
"On the kernel side there's two x86 PMU driver fixes and a uprobes fix,
plus on the tooling side there's a number of fixes and some late
updates"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
perf sched timehist: Fix invalid period calculation
perf sched timehist: Remove hardcoded 'comm_width' check at print_summary
perf sched timehist: Enlarge default 'comm_width'
perf sched timehist: Honour 'comm_width' when aligning the headers
perf/x86: Fix overlap counter scheduling bug
perf/x86/pebs: Fix handling of PEBS buffer overflows
samples/bpf: Move open_raw_sock to separate header
samples/bpf: Remove perf_event_open() declaration
samples/bpf: Be consistent with bpf_load_program bpf_insn parameter
tools lib bpf: Add bpf_prog_{attach,detach}
samples/bpf: Switch over to libbpf
perf diff: Do not overwrite valid build id
perf annotate: Don't throw error for zero length symbols
perf bench futex: Fix lock-pi help string
perf trace: Check if MAP_32BIT is defined (again)
samples/bpf: Make perf_event_read() static
uprobes: Fix uprobes on MIPS, allow for a cache flush after ixol breakpoint creation
samples/bpf: Make samples more libbpf-centric
tools lib bpf: Add flags to bpf_create_map()
tools lib bpf: use __u32 from linux/types.h
...
63 files changed, 1104 insertions, 750 deletions
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index cb8522290e6a..86138267b68a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2110,6 +2110,27 @@ again: GLOBAL_STATUS_LBRS_FROZEN); if (!status) goto done; + /* + * In case multiple PEBS events are sampled at the same time, + * it is possible to have GLOBAL_STATUS bit 62 set indicating + * PEBS buffer overflow and also seeing at most 3 PEBS counters + * having their bits set in the status register. This is a sign + * that there was at least one PEBS record pending at the time + * of the PMU interrupt. PEBS counters must only be processed + * via the drain_pebs() calls and not via the regular sample + * processing loop coming after that the function, otherwise + * phony regular samples may be generated in the sampling buffer + * not marked with the EXACT tag. Another possibility is to have + * one PEBS event and at least one non-PEBS event whic hoverflows + * while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will + * not be set, yet the overflow status bit for the PEBS counter will + * be on Skylake. + * + * To avoid this problem, we systematically ignore the PEBS-enabled + * counters from the GLOBAL_STATUS mask and we always process PEBS + * events via drain_pebs(). + */ + status &= ~cpuc->pebs_enabled; /* * PEBS overflow sets bit 62 in the global status register @@ -2117,15 +2138,6 @@ again: if (__test_and_clear_bit(62, (unsigned long *)&status)) { handled++; x86_pmu.drain_pebs(regs); - /* - * There are cases where, even though, the PEBS ovfl bit is set - * in GLOBAL_OVF_STATUS, the PEBS events may also have their - * overflow bits set for their counters. We must clear them - * here because they have been processed as exact samples in - * the drain_pebs() routine. They must not be processed again - * in the for_each_bit_set() loop for regular samples below. - */ - status &= ~cpuc->pebs_enabled; status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 272427700d48..e6832be714bc 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -669,7 +669,7 @@ static struct event_constraint snbep_uncore_cbox_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), - EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), + UNCORE_EVENT_CONSTRAINT(0x1f, 0xe), UNCORE_EVENT_CONSTRAINT(0x21, 0x3), UNCORE_EVENT_CONSTRAINT(0x23, 0x3), UNCORE_EVENT_CONSTRAINT(0x31, 0x3), diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 215871bda3a2..d416f3baf392 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1194,7 +1194,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr) /* Reserve the 1st slot for get_trampoline_vaddr() */ set_bit(0, area->bitmap); atomic_set(&area->slot_count, 1); - copy_to_page(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE); + arch_uprobe_copy_ixol(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE); if (!xol_add_vma(mm, area)) return area; diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 13315ff1193c..09e9d535bd74 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -35,40 +35,43 @@ hostprogs-y += tc_l2_redirect hostprogs-y += lwt_len_hist hostprogs-y += xdp_tx_iptunnel -test_lru_dist-objs := test_lru_dist.o libbpf.o -sock_example-objs := sock_example.o libbpf.o -fds_example-objs := bpf_load.o libbpf.o fds_example.o -sockex1-objs := bpf_load.o libbpf.o sockex1_user.o -sockex2-objs := bpf_load.o libbpf.o sockex2_user.o -sockex3-objs := bpf_load.o libbpf.o sockex3_user.o -tracex1-objs := bpf_load.o libbpf.o tracex1_user.o -tracex2-objs := bpf_load.o libbpf.o tracex2_user.o -tracex3-objs := bpf_load.o libbpf.o tracex3_user.o -tracex4-objs := bpf_load.o libbpf.o tracex4_user.o -tracex5-objs := bpf_load.o libbpf.o tracex5_user.o -tracex6-objs := bpf_load.o libbpf.o tracex6_user.o -test_probe_write_user-objs := bpf_load.o libbpf.o test_probe_write_user_user.o -trace_output-objs := bpf_load.o libbpf.o trace_output_user.o -lathist-objs := bpf_load.o libbpf.o lathist_user.o -offwaketime-objs := bpf_load.o libbpf.o offwaketime_user.o -spintest-objs := bpf_load.o libbpf.o spintest_user.o -map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o -test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o -test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o -test_cgrp2_attach-objs := libbpf.o test_cgrp2_attach.o -test_cgrp2_attach2-objs := libbpf.o test_cgrp2_attach2.o cgroup_helpers.o -test_cgrp2_sock-objs := libbpf.o test_cgrp2_sock.o -test_cgrp2_sock2-objs := bpf_load.o libbpf.o test_cgrp2_sock2.o -xdp1-objs := bpf_load.o libbpf.o xdp1_user.o +# Libbpf dependencies +LIBBPF := ../../tools/lib/bpf/bpf.o + +test_lru_dist-objs := test_lru_dist.o $(LIBBPF) +sock_example-objs := sock_example.o $(LIBBPF) +fds_example-objs := bpf_load.o $(LIBBPF) fds_example.o +sockex1-objs := bpf_load.o $(LIBBPF) sockex1_user.o +sockex2-objs := bpf_load.o $(LIBBPF) sockex2_user.o +sockex3-objs := bpf_load.o $(LIBBPF) sockex3_user.o +tracex1-objs := bpf_load.o $(LIBBPF) tracex1_user.o +tracex2-objs := bpf_load.o $(LIBBPF) tracex2_user.o +tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o +tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o +tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o +tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o +test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o +trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o +lathist-objs := bpf_load.o $(LIBBPF) lathist_user.o +offwaketime-objs := bpf_load.o $(LIBBPF) offwaketime_user.o +spintest-objs := bpf_load.o $(LIBBPF) spintest_user.o +map_perf_test-objs := bpf_load.o $(LIBBPF) map_perf_test_user.o +test_overhead-objs := bpf_load.o $(LIBBPF) test_overhead_user.o +test_cgrp2_array_pin-objs := $(LIBBPF) test_cgrp2_array_pin.o +test_cgrp2_attach-objs := $(LIBBPF) test_cgrp2_attach.o +test_cgrp2_attach2-objs := $(LIBBPF) test_cgrp2_attach2.o cgroup_helpers.o +test_cgrp2_sock-objs := $(LIBBPF) test_cgrp2_sock.o +test_cgrp2_sock2-objs := bpf_load.o $(LIBBPF) test_cgrp2_sock2.o +xdp1-objs := bpf_load.o $(LIBBPF) xdp1_user.o # reuse xdp1 source intentionally -xdp2-objs := bpf_load.o libbpf.o xdp1_user.o -test_current_task_under_cgroup-objs := bpf_load.o libbpf.o cgroup_helpers.o \ +xdp2-objs := bpf_load.o $(LIBBPF) xdp1_user.o +test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) cgroup_helpers.o \ test_current_task_under_cgroup_user.o -trace_event-objs := bpf_load.o libbpf.o trace_event_user.o -sampleip-objs := bpf_load.o libbpf.o sampleip_user.o -tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o -lwt_len_hist-objs := bpf_load.o libbpf.o lwt_len_hist_user.o -xdp_tx_iptunnel-objs := bpf_load.o libbpf.o xdp_tx_iptunnel_user.o +trace_event-objs := bpf_load.o $(LIBBPF) trace_event_user.o +sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o +tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o +lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o +xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -104,7 +107,10 @@ always += lwt_len_hist_kern.o always += xdp_tx_iptunnel_kern.o HOSTCFLAGS += -I$(objtree)/usr/include +HOSTCFLAGS += -I$(srctree)/tools/lib/ HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ +HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include +HOSTCFLAGS += -I$(srctree)/tools/perf HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable HOSTLOADLIBES_fds_example += -lelf diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst index a43eae3f0551..79f9a58f1872 100644 --- a/samples/bpf/README.rst +++ b/samples/bpf/README.rst @@ -1,8 +1,8 @@ eBPF sample programs ==================== -This directory contains a mini eBPF library, test stubs, verifier -test-suite and examples for using eBPF. +This directory contains a test stubs, verifier test-suite and examples +for using eBPF. The examples use libbpf from tools/lib/bpf. Build dependencies ================== diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index e30b6de94f2e..396e204888b3 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -22,25 +22,34 @@ #include <poll.h> #include <ctype.h> #include "libbpf.h" -#include "bpf_helpers.h" #include "bpf_load.h" +#include "perf-sys.h" #define DEBUGFS "/sys/kernel/debug/tracing/" static char license[128]; static int kern_version; static bool processed_sec[128]; +char bpf_log_buf[BPF_LOG_BUF_SIZE]; int map_fd[MAX_MAPS]; int prog_fd[MAX_PROGS]; int event_fd[MAX_PROGS]; int prog_cnt; int prog_array_fd = -1; +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; +}; + static int populate_prog_array(const char *event, int prog_fd) { int ind = atoi(event), err; - err = bpf_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY); + err = bpf_map_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY); if (err < 0) { printf("failed to store prog_fd in prog_array\n"); return -1; @@ -58,6 +67,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) bool is_perf_event = strncmp(event, "perf_event", 10) == 0; bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0; bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0; + size_t insns_cnt = size / sizeof(struct bpf_insn); enum bpf_prog_type prog_type; char buf[256]; int fd, efd, err, id; @@ -87,9 +97,10 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) return -1; } - fd = bpf_prog_load(prog_type, prog, size, license, kern_version); + fd = bpf_load_program(prog_type, prog, insns_cnt, license, kern_version, + bpf_log_buf, BPF_LOG_BUF_SIZE); if (fd < 0) { - printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf); + printf("bpf_load_program() err=%d\n%s", errno, bpf_log_buf); return -1; } @@ -169,7 +180,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) id = atoi(buf); attr.config = id; - efd = perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0); + efd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0); if (efd < 0) { printf("event %d fd %d err %s\n", id, efd, strerror(errno)); return -1; diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h index fb46a421ab41..c827827299b3 100644 --- a/samples/bpf/bpf_load.h +++ b/samples/bpf/bpf_load.h @@ -1,12 +1,15 @@ #ifndef __BPF_LOAD_H #define __BPF_LOAD_H +#include "libbpf.h" + #define MAX_MAPS 32 #define MAX_PROGS 32 extern int map_fd[MAX_MAPS]; extern int prog_fd[MAX_PROGS]; extern int event_fd[MAX_PROGS]; +extern char bpf_log_buf[BPF_LOG_BUF_SIZE]; extern int prog_cnt; /* parses elf file compiled by llvm .c->.o diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c index 625e797be6ef..e29bd52ff9e8 100644 --- a/samples/bpf/fds_example.c +++ b/samples/bpf/fds_example.c @@ -14,6 +14,7 @@ #include "bpf_load.h" #include "libbpf.h" +#include "sock_example.h" #define BPF_F_PIN (1 << 0) #define BPF_F_GET (1 << 1) @@ -49,17 +50,19 @@ static int bpf_map_create(void) static int bpf_prog_create(const char *object) { - static const struct bpf_insn insns[] = { + static struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }; + size_t insns_cnt = sizeof(insns) / sizeof(struct bpf_insn); if (object) { assert(!load_bpf_file((char *)object)); return prog_fd[0]; } else { - return bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, - insns, sizeof(insns), "GPL", 0); + return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, + insns, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); } } @@ -83,12 +86,12 @@ static int bpf_do_map(const char *file, uint32_t flags, uint32_t key, } if ((flags & BPF_F_KEY_VAL) == BPF_F_KEY_VAL) { - ret = bpf_update_elem(fd, &key, &value, 0); + ret = bpf_map_update_elem(fd, &key, &value, 0); printf("bpf: fd:%d u->(%u:%u) ret:(%d,%s)\n", fd, key, value, ret, strerror(errno)); assert(ret == 0); } else if (flags & BPF_F_KEY) { - ret = bpf_lookup_elem(fd, &key, &value); + ret = bpf_map_lookup_elem(fd, &key, &value); printf("bpf: fd:%d l->(%u):%u ret:(%d,%s)\n", fd, key, value, ret, strerror(errno)); assert(ret == 0); diff --git a/samples/bpf/lathist_user.c b/samples/bpf/lathist_user.c index 65da8c1576de..6477bad5b4e2 100644 --- a/samples/bpf/lathist_user.c +++ b/samples/bpf/lathist_user.c @@ -73,7 +73,7 @@ static void get_data(int fd) for (c = 0; c < MAX_CPU; c++) { for (i = 0; i < MAX_ENTRIES; i++) { key = c * MAX_ENTRIES + i; - bpf_lookup_elem(fd, &key, &value); + bpf_map_lookup_elem(fd, &key, &value); cpu_hist[c].data[i] = value; if (value > cpu_hist[c].max) diff --git a/samples/bpf/libbpf.c b/samples/bpf/libbpf.c deleted file mode 100644 index 9ce707bf02a7..000000000000 --- a/samples/bpf/libbpf.c +++ /dev/null @@ -1,176 +0,0 @@ -/* eBPF mini library */ -#include <stdlib.h> -#include <stdio.h> -#include <linux/unistd.h> -#include <unistd.h> -#include <string.h> -#include <linux/netlink.h> -#include <linux/bpf.h> -#include <errno.h> -#include <net/ethernet.h> -#include <net/if.h> -#include <linux/if_packet.h> -#include <arpa/inet.h> -#include "libbpf.h" - -static __u64 ptr_to_u64(void *ptr) -{ - return (__u64) (unsigned long) ptr; -} - -int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, - int max_entries, int map_flags) -{ - union bpf_attr attr = { - .map_type = map_type, - .key_size = key_size, - .value_size = value_size, - .max_entries = max_entries, - .map_flags = map_flags, - }; - - return syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr)); -} - -int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags) -{ - union bpf_attr attr = { - .map_fd = fd, - .key = ptr_to_u64(key), - .value = ptr_to_u64(value), - .flags = flags, - }; - - return syscall(__NR_bpf, BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); -} - -int bpf_lookup_elem(int fd, void *key, void *value) -{ - union bpf_attr attr = { - .map_fd = fd, - .key = ptr_to_u64(key), - .value = ptr_to_u64(value), - }; - - return syscall(__NR_bpf, BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); -} - -int bpf_delete_elem(int fd, void *key) -{ - union bpf_attr attr = { - .map_fd = fd, - .key = ptr_to_u64(key), - }; - - return syscall(__NR_bpf, BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); -} - -int bpf_get_next_key(int fd, void *key, void *next_key) -{ - union bpf_attr attr = { - .map_fd = fd, - .key = ptr_to_u64(key), - .next_key = ptr_to_u64(next_key), - }; - - return syscall(__NR_bpf, BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); -} - -#define ROUND_UP(x, n) (((x) + (n) - 1u) & ~((n) - 1u)) - -char bpf_log_buf[LOG_BUF_SIZE]; - -int bpf_prog_load(enum bpf_prog_type prog_type, - const struct bpf_insn *insns, int prog_len, - const char *license, int kern_version) -{ - union bpf_attr attr = { - .prog_type = prog_type, - .insns = ptr_to_u64((void *) insns), - .insn_cnt = prog_len / sizeof(struct bpf_insn), - .license = ptr_to_u64((void *) license), - .log_buf = ptr_to_u64(bpf_log_buf), - .log_size = LOG_BUF_SIZE, - .log_level = 1, - }; - - /* assign one field outside of struct init to make sure any - * padding is zero initialized - */ - attr.kern_version = kern_version; - - bpf_log_buf[0] = 0; - - return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); -} - -int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type) -{ - union bpf_attr attr = { - .target_fd = target_fd, - .attach_bpf_fd = prog_fd, - .attach_type = type, - }; - - return syscall(__NR_bpf, BPF_PROG_ATTACH, &attr, sizeof(attr)); -} - -int bpf_prog_detach(int target_fd, enum bpf_attach_type type) -{ - union bpf_attr attr = { - .target_fd = target_fd, - .attach_type = type, - }; - - return syscall(__NR_bpf, BPF_PROG_DETACH, &attr, sizeof(attr)); -} - -int bpf_obj_pin(int fd, const char *pathname) -{ - union bpf_attr attr = { - .pathname = ptr_to_u64((void *)pathname), - .bpf_fd = fd, - }; - - return syscall(__NR_bpf, BPF_OBJ_PIN, &attr, sizeof(attr)); -} - -int bpf_obj_get(const char *pathname) -{ - union bpf_attr attr = { - .pathname = ptr_to_u64((void *)pathname), - }; - - return syscall(__NR_bpf, BPF_OBJ_GET, &attr, sizeof(attr)); -} - -int open_raw_sock(const char *name) -{ - struct sockaddr_ll sll; - int sock; - - sock = socket(PF_PACKET, SOCK_RAW | SOCK_NONBLOCK | SOCK_CLOEXEC, htons(ETH_P_ALL)); - if (sock < 0) { - printf("cannot create raw socket\n"); - return -1; - } - - memset(&sll, 0, sizeof(sll)); - sll.sll_family = AF_PACKET; - sll.sll_ifindex = if_nametoindex(name); - sll.sll_protocol = htons(ETH_P_ALL); - if (bind(sock, (struct sockaddr *)&sll, sizeof(sll)) < 0) { - printf("bind to %s: %s\n", name, strerror(errno)); - close(sock); - return -1; - } - - return sock; -} - -int perf_event_open(struct perf_event_attr *attr, int pid, int cpu, - int group_fd, unsigned l |