* [PATCH v3 bpf-next 4/4] tools/bpftool: switch map event_pipe to libbpf's perf_buffer
From: Andrii Nakryiko @ 2019-06-29 5:53 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, kernel-team,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629055309.1594755-1-andriin@fb.com>
Switch event_pipe implementation to rely on new libbpf perf buffer API
(it's raw low-level variant).
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
tools/bpf/bpftool/map_perf_ring.c | 207 ++++++++++--------------------
1 file changed, 68 insertions(+), 139 deletions(-)
diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
index 0507dfaf7a8f..4b048a53f8be 100644
--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@@ -28,7 +28,7 @@
#define MMAP_PAGE_CNT 16
-static bool stop;
+static volatile bool stop;
struct event_ring_info {
int fd;
@@ -44,32 +44,44 @@ struct perf_event_sample {
unsigned char data[];
};
+struct perf_event_lost {
+ struct perf_event_header header;
+ __u64 id;
+ __u64 lost;
+};
+
static void int_exit(int signo)
{
fprintf(stderr, "Stopping...\n");
stop = true;
}
+struct event_pipe_ctx {
+ bool all_cpus;
+ int cpu;
+ int idx;
+};
+
static enum bpf_perf_event_ret
-print_bpf_output(struct perf_event_header *event, void *private_data)
+print_bpf_output(void *private_data, int cpu, struct perf_event_header *event)
{
- struct perf_event_sample *e = container_of(event, struct perf_event_sample,
+ struct perf_event_sample *e = container_of(event,
+ struct perf_event_sample,
header);
- struct event_ring_info *ring = private_data;
- struct {
- struct perf_event_header header;
- __u64 id;
- __u64 lost;
- } *lost = (typeof(lost))event;
+ struct perf_event_lost *lost = container_of(event,
+ struct perf_event_lost,
+ header);
+ struct event_pipe_ctx *ctx = private_data;
+ int idx = ctx->all_cpus ? cpu : ctx->idx;
if (json_output) {
jsonw_start_object(json_wtr);
jsonw_name(json_wtr, "type");
jsonw_uint(json_wtr, e->header.type);
jsonw_name(json_wtr, "cpu");
- jsonw_uint(json_wtr, ring->cpu);
+ jsonw_uint(json_wtr, cpu);
jsonw_name(json_wtr, "index");
- jsonw_uint(json_wtr, ring->key);
+ jsonw_uint(json_wtr, idx);
if (e->header.type == PERF_RECORD_SAMPLE) {
jsonw_name(json_wtr, "timestamp");
jsonw_uint(json_wtr, e->time);
@@ -89,7 +101,7 @@ print_bpf_output(struct perf_event_header *event, void *private_data)
if (e->header.type == PERF_RECORD_SAMPLE) {
printf("== @%lld.%09lld CPU: %d index: %d =====\n",
e->time / 1000000000ULL, e->time % 1000000000ULL,
- ring->cpu, ring->key);
+ cpu, idx);
fprint_hex(stdout, e->data, e->size, " ");
printf("\n");
} else if (e->header.type == PERF_RECORD_LOST) {
@@ -103,92 +115,32 @@ print_bpf_output(struct perf_event_header *event, void *private_data)
return LIBBPF_PERF_EVENT_CONT;
}
-static void
-perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len)
-{
- enum bpf_perf_event_ret ret;
-
- ret = bpf_perf_event_read_simple(ring->mem,
- MMAP_PAGE_CNT * get_page_size(),
- get_page_size(), buf, buf_len,
- print_bpf_output, ring);
- if (ret != LIBBPF_PERF_EVENT_CONT) {
- fprintf(stderr, "perf read loop failed with %d\n", ret);
- stop = true;
- }
-}
-
-static int perf_mmap_size(void)
-{
- return get_page_size() * (MMAP_PAGE_CNT + 1);
-}
-
-static void *perf_event_mmap(int fd)
-{
- int mmap_size = perf_mmap_size();
- void *base;
-
- base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
- if (base == MAP_FAILED) {
- p_err("event mmap failed: %s\n", strerror(errno));
- return NULL;
- }
-
- return base;
-}
-
-static void perf_event_unmap(void *mem)
-{
- if (munmap(mem, perf_mmap_size()))
- fprintf(stderr, "Can't unmap ring memory!\n");
-}
-
-static int bpf_perf_event_open(int map_fd, int key, int cpu)
+int do_event_pipe(int argc, char **argv)
{
- struct perf_event_attr attr = {
+ struct perf_event_attr perf_attr = {
.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME,
.type = PERF_TYPE_SOFTWARE,
.config = PERF_COUNT_SW_BPF_OUTPUT,
+ .sample_period = 1,
+ .wakeup_events = 1,
};
- int pmu_fd;
-
- pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
- if (pmu_fd < 0) {
- p_err("failed to open perf event %d for CPU %d", key, cpu);
- return -1;
- }
-
- if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) {
- p_err("failed to update map for event %d for CPU %d", key, cpu);
- goto err_close;
- }
- if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) {
- p_err("failed to enable event %d for CPU %d", key, cpu);
- goto err_close;
- }
-
- return pmu_fd;
-
-err_close:
- close(pmu_fd);
- return -1;
-}
-
-int do_event_pipe(int argc, char **argv)
-{
- int i, nfds, map_fd, index = -1, cpu = -1;
struct bpf_map_info map_info = {};
- struct event_ring_info *rings;
- size_t tmp_buf_sz = 0;
- void *tmp_buf = NULL;
- struct pollfd *pfds;
+ struct perf_buffer_raw_opts opts;
+ struct event_pipe_ctx ctx = {
+ .all_cpus = true,
+ .cpu = -1,
+ .idx = -1,
+ };
+ struct perf_buffer *pb;
__u32 map_info_len;
- bool do_all = true;
+ int err, map_fd;
map_info_len = sizeof(map_info);
map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len);
- if (map_fd < 0)
+ if (map_fd < 0) {
+ p_err("failed to get map info");
return -1;
+ }
if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
p_err("map is not a perf event array");
@@ -205,7 +157,7 @@ int do_event_pipe(int argc, char **argv)
char *endptr;
NEXT_ARG();
- cpu = strtoul(*argv, &endptr, 0);
+ ctx.cpu = strtoul(*argv, &endptr, 0);
if (*endptr) {
p_err("can't parse %s as CPU ID", **argv);
goto err_close_map;
@@ -216,7 +168,7 @@ int do_event_pipe(int argc, char **argv)
char *endptr;
NEXT_ARG();
- index = strtoul(*argv, &endptr, 0);
+ ctx.idx = strtoul(*argv, &endptr, 0);
if (*endptr) {
p_err("can't parse %s as index", **argv);
goto err_close_map;
@@ -228,45 +180,32 @@ int do_event_pipe(int argc, char **argv)
goto err_close_map;
}
- do_all = false;
+ ctx.all_cpus = false;
}
- if (!do_all) {
- if (index == -1 || cpu == -1) {
+ if (!ctx.all_cpus) {
+ if (ctx.idx == -1 || ctx.cpu == -1) {
p_err("cpu and index must be specified together");
goto err_close_map;
}
-
- nfds = 1;
} else {
- nfds = min(get_possible_cpus(), map_info.max_entries);
- cpu = 0;
- index = 0;
+ ctx.cpu = 0;
+ ctx.idx = 0;
}
- rings = calloc(nfds, sizeof(rings[0]));
- if (!rings)
+ opts.attr = &perf_attr;
+ opts.event_cb = print_bpf_output;
+ opts.ctx = &ctx;
+ opts.cpu_cnt = ctx.all_cpus ? 0 : 1;
+ opts.cpus = &ctx.cpu;
+ opts.map_keys = &ctx.idx;
+
+ pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &opts);
+ err = libbpf_get_error(pb);
+ if (err) {
+ p_err("failed to create perf buffer: %s (%d)",
+ strerror(err), err);
goto err_close_map;
-
- pfds = calloc(nfds, sizeof(pfds[0]));
- if (!pfds)
- goto err_free_rings;
-
- for (i = 0; i < nfds; i++) {
- rings[i].cpu = cpu + i;
- rings[i].key = index + i;
-
- rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key,
- rings[i].cpu);
- if (rings[i].fd < 0)
- goto err_close_fds_prev;
-
- rings[i].mem = perf_event_mmap(rings[i].fd);
- if (!rings[i].mem)
- goto err_close_fds_current;
-
- pfds[i].fd = rings[i].fd;
- pfds[i].events = POLLIN;
}
signal(SIGINT, int_exit);
@@ -277,35 +216,25 @@ int do_event_pipe(int argc, char **argv)
jsonw_start_array(json_wtr);
while (!stop) {
- poll(pfds, nfds, 200);
- for (i = 0; i < nfds; i++)
- perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz);
+ err = perf_buffer__poll(pb, 200);
+ if (err < 0 && err != -EINTR) {
+ p_err("perf buffer polling failed: %s (%d)",
+ strerror(err), err);
+ goto err_close_pb;
+ }
}
- free(tmp_buf);
if (json_output)
jsonw_end_array(json_wtr);
- for (i = 0; i < nfds; i++) {
- perf_event_unmap(rings[i].mem);
- close(rings[i].fd);
- }
- free(pfds);
- free(rings);
+ perf_buffer__free(pb);
close(map_fd);
return 0;
-err_close_fds_prev:
- while (i--) {
- perf_event_unmap(rings[i].mem);
-err_close_fds_current:
- close(rings[i].fd);
- }
- free(pfds);
-err_free_rings:
- free(rings);
+err_close_pb:
+ perf_buffer__free(pb);
err_close_map:
close(map_fd);
- return -1;
+ return err ? -1 : 0;
}
--
2.17.1
^ permalink raw reply related
* [PATCH v3 bpf-next 2/4] libbpf: auto-set PERF_EVENT_ARRAY size to number of CPUs
From: Andrii Nakryiko @ 2019-06-29 5:53 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, kernel-team,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629055309.1594755-1-andriin@fb.com>
For BPF_MAP_TYPE_PERF_EVENT_ARRAY typically correct size is number of
possible CPUs. This is impossible to specify at compilation time. This
change adds automatic setting of PERF_EVENT_ARRAY size to number of
system CPUs, unless non-zero size is specified explicitly. This allows
to adjust size for advanced specific cases, while providing convenient
and logical defaults.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
tools/lib/bpf/libbpf.c | 31 ++++++++++++++++++++++++-------
1 file changed, 24 insertions(+), 7 deletions(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e2bf3eedd0ae..a5ae7207d19a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2118,6 +2118,7 @@ static int
bpf_object__create_maps(struct bpf_object *obj)
{
struct bpf_create_map_attr create_attr = {};
+ int nr_cpus = 0;
unsigned int i;
int err;
@@ -2140,7 +2141,22 @@ bpf_object__create_maps(struct bpf_object *obj)
create_attr.map_flags = def->map_flags;
create_attr.key_size = def->key_size;
create_attr.value_size = def->value_size;
- create_attr.max_entries = def->max_entries;
+ if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
+ !def->max_entries) {
+ if (!nr_cpus)
+ nr_cpus = libbpf_num_possible_cpus();
+ if (nr_cpus < 0) {
+ pr_warning("failed to determine number of system CPUs: %d\n",
+ nr_cpus);
+ err = nr_cpus;
+ goto err_out;
+ }
+ pr_debug("map '%s': setting size to %d\n",
+ map->name, nr_cpus);
+ create_attr.max_entries = nr_cpus;
+ } else {
+ create_attr.max_entries = def->max_entries;
+ }
create_attr.btf_fd = 0;
create_attr.btf_key_type_id = 0;
create_attr.btf_value_type_id = 0;
@@ -2157,9 +2173,10 @@ bpf_object__create_maps(struct bpf_object *obj)
*pfd = bpf_create_map_xattr(&create_attr);
if (*pfd < 0 && (create_attr.btf_key_type_id ||
create_attr.btf_value_type_id)) {
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+ err = -errno;
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
- map->name, cp, errno);
+ map->name, cp, err);
create_attr.btf_fd = 0;
create_attr.btf_key_type_id = 0;
create_attr.btf_value_type_id = 0;
@@ -2171,11 +2188,11 @@ bpf_object__create_maps(struct bpf_object *obj)
if (*pfd < 0) {
size_t j;
- err = *pfd;
+ err = -errno;
err_out:
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warning("failed to create map (name: '%s'): %s\n",
- map->name, cp);
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
+ pr_warning("failed to create map (name: '%s'): %s(%d)\n",
+ map->name, cp, err);
for (j = 0; j < i; j++)
zclose(obj->maps[j].fd);
return err;
--
2.17.1
^ permalink raw reply related
* [PATCH v3 bpf-next 1/4] libbpf: add perf buffer API
From: Andrii Nakryiko @ 2019-06-29 5:53 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, kernel-team,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629055309.1594755-1-andriin@fb.com>
BPF_MAP_TYPE_PERF_EVENT_ARRAY map is often used to send data from BPF program
to user space for additional processing. libbpf already has very low-level API
to read single CPU perf buffer, bpf_perf_event_read_simple(), but it's hard to
use and requires a lot of code to set everything up. This patch adds
perf_buffer abstraction on top of it, abstracting setting up and polling
per-CPU logic into simple and convenient API, similar to what BCC provides.
perf_buffer__new() sets up per-CPU ring buffers and updates corresponding BPF
map entries. It accepts two user-provided callbacks: one for handling raw
samples and one for get notifications of lost samples due to buffer overflow.
perf_buffer__new_raw() is similar, but provides more control over how
perf events are set up (by accepting user-provided perf_event_attr), how
they are handled (perf_event_header pointer is passed directly to
user-provided callback), and on which CPUs ring buffers are created
(it's possible to provide a list of CPUs and corresponding map keys to
update). This API allows advanced users fuller control.
perf_buffer__poll() is used to fetch ring buffer data across all CPUs,
utilizing epoll instance.
perf_buffer__free() does corresponding clean up and unsets FDs from BPF map.
All APIs are not thread-safe. User should ensure proper locking/coordination if
used in multi-threaded set up.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
tools/lib/bpf/libbpf.c | 366 +++++++++++++++++++++++++++++++++++++++
tools/lib/bpf/libbpf.h | 49 ++++++
tools/lib/bpf/libbpf.map | 4 +
3 files changed, 419 insertions(+)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f8c7a7ecb35e..e2bf3eedd0ae 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -32,7 +32,9 @@
#include <linux/limits.h>
#include <linux/perf_event.h>
#include <linux/ring_buffer.h>
+#include <sys/epoll.h>
#include <sys/ioctl.h>
+#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
@@ -4348,6 +4350,370 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
return ret;
}
+struct perf_buffer;
+
+struct perf_buffer_params {
+ struct perf_event_attr *attr;
+ /* if event_cb is specified, it takes precendence */
+ perf_buffer_event_fn event_cb;
+ /* sample_cb and lost_cb are higher-level common-case callbacks */
+ perf_buffer_sample_fn sample_cb;
+ perf_buffer_lost_fn lost_cb;
+ void *ctx;
+ int cpu_cnt;
+ int *cpus;
+ int *map_keys;
+};
+
+struct perf_cpu_buf {
+ struct perf_buffer *pb;
+ void *base; /* mmap()'ed memory */
+ void *buf; /* for reconstructing segmented data */
+ size_t buf_size;
+ int fd;
+ int cpu;
+ int map_key;
+};
+
+struct perf_buffer {
+ perf_buffer_event_fn event_cb;
+ perf_buffer_sample_fn sample_cb;
+ perf_buffer_lost_fn lost_cb;
+ void *ctx; /* passed into callbacks */
+
+ size_t page_size;
+ size_t mmap_size;
+ struct perf_cpu_buf **cpu_bufs;
+ struct epoll_event *events;
+ int cpu_cnt;
+ int epoll_fd; /* perf event FD */
+ int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */
+};
+
+static void perf_buffer__free_cpu_buf(struct perf_buffer *pb,
+ struct perf_cpu_buf *cpu_buf)
+{
+ if (!cpu_buf)
+ return;
+ if (cpu_buf->base &&
+ munmap(cpu_buf->base, pb->mmap_size + pb->page_size))
+ pr_warning("failed to munmap cpu_buf #%d\n", cpu_buf->cpu);
+ if (cpu_buf->fd >= 0) {
+ ioctl(cpu_buf->fd, PERF_EVENT_IOC_DISABLE, 0);
+ close(cpu_buf->fd);
+ }
+ free(cpu_buf->buf);
+ free(cpu_buf);
+}
+
+void perf_buffer__free(struct perf_buffer *pb)
+{
+ int i;
+
+ if (!pb)
+ return;
+ if (pb->cpu_bufs) {
+ for (i = 0; i < pb->cpu_cnt && pb->cpu_bufs[i]; i++) {
+ struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i];
+
+ bpf_map_delete_elem(pb->map_fd, &cpu_buf->map_key);
+ perf_buffer__free_cpu_buf(pb, cpu_buf);
+ }
+ free(pb->cpu_bufs);
+ }
+ if (pb->epoll_fd >= 0)
+ close(pb->epoll_fd);
+ free(pb->events);
+ free(pb);
+}
+
+static struct perf_cpu_buf *
+perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr,
+ int cpu, int map_key)
+{
+ struct perf_cpu_buf *cpu_buf;
+ char msg[STRERR_BUFSIZE];
+ int err;
+
+ cpu_buf = calloc(1, sizeof(*cpu_buf));
+ if (!cpu_buf)
+ return ERR_PTR(-ENOMEM);
+
+ cpu_buf->pb = pb;
+ cpu_buf->cpu = cpu;
+ cpu_buf->map_key = map_key;
+
+ cpu_buf->fd = syscall(__NR_perf_event_open, attr, -1 /* pid */, cpu,
+ -1, PERF_FLAG_FD_CLOEXEC);
+ if (cpu_buf->fd < 0) {
+ err = -errno;
+ pr_warning("failed to open perf buffer event on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ cpu_buf->base = mmap(NULL, pb->mmap_size + pb->page_size,
+ PROT_READ | PROT_WRITE, MAP_SHARED,
+ cpu_buf->fd, 0);
+ if (cpu_buf->base == MAP_FAILED) {
+ cpu_buf->base = NULL;
+ err = -errno;
+ pr_warning("failed to mmap perf buffer on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
+ err = -errno;
+ pr_warning("failed to enable perf buffer event on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ return cpu_buf;
+
+error:
+ perf_buffer__free_cpu_buf(pb, cpu_buf);
+ return (struct perf_cpu_buf *)ERR_PTR(err);
+}
+
+static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
+ struct perf_buffer_params *p);
+
+struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt,
+ const struct perf_buffer_opts *opts)
+{
+ struct perf_buffer_params p = {};
+ struct perf_event_attr attr = {
+ .config = PERF_COUNT_SW_BPF_OUTPUT,
+ .type = PERF_TYPE_SOFTWARE,
+ .sample_type = PERF_SAMPLE_RAW,
+ .sample_period = 1,
+ .wakeup_events = 1,
+ };
+
+ p.attr = &attr;
+ p.sample_cb = opts ? opts->sample_cb : NULL;
+ p.lost_cb = opts ? opts->lost_cb : NULL;
+ p.ctx = opts ? opts->ctx : NULL;
+
+ return __perf_buffer__new(map_fd, page_cnt, &p);
+}
+
+struct perf_buffer *
+perf_buffer__new_raw(int map_fd, size_t page_cnt,
+ const struct perf_buffer_raw_opts *opts)
+{
+ struct perf_buffer_params p = {};
+
+ p.attr = opts->attr;
+ p.event_cb = opts->event_cb;
+ p.ctx = opts->ctx;
+ p.cpu_cnt = opts->cpu_cnt;
+ p.cpus = opts->cpus;
+ p.map_keys = opts->map_keys;
+
+ return __perf_buffer__new(map_fd, page_cnt, &p);
+}
+
+static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
+ struct perf_buffer_params *p)
+{
+ struct bpf_map_info map = {};
+ char msg[STRERR_BUFSIZE];
+ struct perf_buffer *pb;
+ __u32 map_info_len;
+ int err, i;
+
+ if (page_cnt & (page_cnt - 1)) {
+ pr_warning("page count should be power of two, but is %zu\n",
+ page_cnt);
+ return ERR_PTR(-EINVAL);
+ }
+
+ map_info_len = sizeof(map);
+ err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len);
+ if (err) {
+ err = -errno;
+ pr_warning("failed to get map info for map FD %d: %s\n",
+ map_fd, libbpf_strerror_r(err, msg, sizeof(msg)));
+ return ERR_PTR(err);
+ }
+
+ if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+ pr_warning("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
+ map.name);
+ return ERR_PTR(-EINVAL);
+ }
+
+ pb = calloc(1, sizeof(*pb));
+ if (!pb)
+ return ERR_PTR(-ENOMEM);
+
+ pb->event_cb = p->event_cb;
+ pb->sample_cb = p->sample_cb;
+ pb->lost_cb = p->lost_cb;
+ pb->ctx = p->ctx;
+
+ pb->page_size = getpagesize();
+ pb->mmap_size = pb->page_size * page_cnt;
+ pb->map_fd = map_fd;
+
+ pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+ if (pb->epoll_fd < 0) {
+ err = -errno;
+ pr_warning("failed to create epoll instance: %s\n",
+ libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ if (p->cpu_cnt > 0) {
+ pb->cpu_cnt = p->cpu_cnt;
+ } else {
+ pb->cpu_cnt = libbpf_num_possible_cpus();
+ if (pb->cpu_cnt < 0) {
+ err = pb->cpu_cnt;
+ goto error;
+ }
+ if (map.max_entries < pb->cpu_cnt)
+ pb->cpu_cnt = map.max_entries;
+ }
+
+ pb->events = calloc(pb->cpu_cnt, sizeof(*pb->events));
+ if (!pb->events) {
+ err = -ENOMEM;
+ pr_warning("failed to allocate events: out of memory\n");
+ goto error;
+ }
+ pb->cpu_bufs = calloc(pb->cpu_cnt, sizeof(*pb->cpu_bufs));
+ if (!pb->cpu_bufs) {
+ err = -ENOMEM;
+ pr_warning("failed to allocate buffers: out of memory\n");
+ goto error;
+ }
+
+ for (i = 0; i < pb->cpu_cnt; i++) {
+ struct perf_cpu_buf *cpu_buf;
+ int cpu, map_key;
+
+ cpu = p->cpu_cnt > 0 ? p->cpus[i] : i;
+ map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i;
+
+ cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key);
+ if (IS_ERR(cpu_buf)) {
+ err = PTR_ERR(cpu_buf);
+ goto error;
+ }
+
+ pb->cpu_bufs[i] = cpu_buf;
+
+ err = bpf_map_update_elem(pb->map_fd, &map_key,
+ &cpu_buf->fd, 0);
+ if (err) {
+ err = -errno;
+ pr_warning("failed to set cpu #%d, key %d -> perf FD %d: %s\n",
+ cpu, map_key, cpu_buf->fd,
+ libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ pb->events[i].events = EPOLLIN;
+ pb->events[i].data.ptr = cpu_buf;
+ if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd,
+ &pb->events[i]) < 0) {
+ err = -errno;
+ pr_warning("failed to epoll_ctl cpu #%d perf FD %d: %s\n",
+ cpu, cpu_buf->fd,
+ libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+ }
+
+ return pb;
+
+error:
+ if (pb)
+ perf_buffer__free(pb);
+ return ERR_PTR(err);
+}
+
+struct perf_sample_raw {
+ struct perf_event_header header;
+ uint32_t size;
+ char data[0];
+};
+
+struct perf_sample_lost {
+ struct perf_event_header header;
+ uint64_t id;
+ uint64_t lost;
+ uint64_t sample_id;
+};
+
+static enum bpf_perf_event_ret
+perf_buffer__process_record(struct perf_event_header *e, void *ctx)
+{
+ struct perf_cpu_buf *cpu_buf = ctx;
+ struct perf_buffer *pb = cpu_buf->pb;
+ void *data = e;
+
+ /* user wants full control over parsing perf event */
+ if (pb->event_cb)
+ return pb->event_cb(pb->ctx, cpu_buf->cpu, e);
+
+ switch (e->type) {
+ case PERF_RECORD_SAMPLE: {
+ struct perf_sample_raw *s = data;
+
+ if (pb->sample_cb)
+ pb->sample_cb(pb->ctx, cpu_buf->cpu, s->data, s->size);
+ break;
+ }
+ case PERF_RECORD_LOST: {
+ struct perf_sample_lost *s = data;
+
+ if (pb->lost_cb)
+ pb->lost_cb(pb->ctx, cpu_buf->cpu, s->lost);
+ break;
+ }
+ default:
+ pr_warning("unknown perf sample type %d\n", e->type);
+ return LIBBPF_PERF_EVENT_ERROR;
+ }
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+static int perf_buffer__process_records(struct perf_buffer *pb,
+ struct perf_cpu_buf *cpu_buf)
+{
+ enum bpf_perf_event_ret ret;
+
+ ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size,
+ pb->page_size, &cpu_buf->buf,
+ &cpu_buf->buf_size,
+ perf_buffer__process_record, cpu_buf);
+ if (ret != LIBBPF_PERF_EVENT_CONT)
+ return ret;
+ return 0;
+}
+
+int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms)
+{
+ int cnt, err;
+
+ cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms);
+ for (int i = 0; i < cnt; i++) {
+ struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr;
+
+ err = perf_buffer__process_records(pb, cpu_buf);
+ if (err) {
+ pr_warning("error while processing records: %d\n", err);
+ return err;
+ }
+ }
+ return cnt < 0 ? -errno : cnt;
+}
+
struct bpf_prog_info_array_desc {
int array_offset; /* e.g. offset of jited_prog_insns */
int count_offset; /* e.g. offset of jited_prog_len */
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index f55933784f95..5cbf459ece0b 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -358,6 +358,26 @@ LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
+struct perf_buffer;
+
+typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu,
+ void *data, __u32 size);
+typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt);
+
+/* common use perf buffer options */
+struct perf_buffer_opts {
+ /* if specified, sample_cb is called for each sample */
+ perf_buffer_sample_fn sample_cb;
+ /* if specified, lost_cb is called for each batch of lost samples */
+ perf_buffer_lost_fn lost_cb;
+ /* ctx is provided to sample_cb and lost_cb */
+ void *ctx;
+};
+
+LIBBPF_API struct perf_buffer *
+perf_buffer__new(int map_fd, size_t page_cnt,
+ const struct perf_buffer_opts *opts);
+
enum bpf_perf_event_ret {
LIBBPF_PERF_EVENT_DONE = 0,
LIBBPF_PERF_EVENT_ERROR = -1,
@@ -365,6 +385,35 @@ enum bpf_perf_event_ret {
};
struct perf_event_header;
+
+typedef enum bpf_perf_event_ret
+(*perf_buffer_event_fn)(void *ctx, int cpu, struct perf_event_header *event);
+
+/* raw perf buffer options, giving most power and control */
+struct perf_buffer_raw_opts {
+ /* perf event attrs passed directly into perf_event_open() */
+ struct perf_event_attr *attr;
+ /* raw event callback */
+ perf_buffer_event_fn event_cb;
+ /* ctx is provided to event_cb */
+ void *ctx;
+ /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of
+ * max_entries of given PERF_EVENT_ARRAY map)
+ */
+ int cpu_cnt;
+ /* if cpu_cnt > 0, cpus is an array of CPUs to open ring buffers on */
+ int *cpus;
+ /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */
+ int *map_keys;
+};
+
+LIBBPF_API struct perf_buffer *
+perf_buffer__new_raw(int map_fd, size_t page_cnt,
+ const struct perf_buffer_raw_opts *opts);
+
+LIBBPF_API void perf_buffer__free(struct perf_buffer *pb);
+LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms);
+
typedef enum bpf_perf_event_ret
(*bpf_perf_event_print_t)(struct perf_event_header *hdr,
void *private_data);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index e6b7d4edbc93..f9d316e873d8 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -179,4 +179,8 @@ LIBBPF_0.0.4 {
btf_dump__new;
btf__parse_elf;
libbpf_num_possible_cpus;
+ perf_buffer__free;
+ perf_buffer__new;
+ perf_buffer__new_raw;
+ perf_buffer__poll;
} LIBBPF_0.0.3;
--
2.17.1
^ permalink raw reply related
* [PATCH v3 bpf-next 3/4] selftests/bpf: test perf buffer API
From: Andrii Nakryiko @ 2019-06-29 5:53 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, kernel-team,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629055309.1594755-1-andriin@fb.com>
Add test verifying perf buffer API functionality.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
---
.../selftests/bpf/prog_tests/perf_buffer.c | 94 +++++++++++++++++++
.../selftests/bpf/progs/test_perf_buffer.c | 29 ++++++
2 files changed, 123 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/perf_buffer.c
create mode 100644 tools/testing/selftests/bpf/progs/test_perf_buffer.c
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
new file mode 100644
index 000000000000..64556ab0d1a9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sched.h>
+#include <sys/socket.h>
+#include <test_progs.h>
+
+static void on_sample(void *ctx, int cpu, void *data, __u32 size)
+{
+ int cpu_data = *(int *)data, duration = 0;
+ cpu_set_t *cpu_seen = ctx;
+
+ if (cpu_data != cpu)
+ CHECK(cpu_data != cpu, "check_cpu_data",
+ "cpu_data %d != cpu %d\n", cpu_data, cpu);
+
+ CPU_SET(cpu, cpu_seen);
+}
+
+void test_perf_buffer(void)
+{
+ int err, prog_fd, nr_cpus, i, duration = 0;
+ const char *prog_name = "kprobe/sys_nanosleep";
+ const char *file = "./test_perf_buffer.o";
+ struct perf_buffer_opts pb_opts = {};
+ struct bpf_map *perf_buf_map;
+ cpu_set_t cpu_set, cpu_seen;
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ struct perf_buffer *pb;
+ struct bpf_link *link;
+
+ nr_cpus = libbpf_num_possible_cpus();
+ if (CHECK(nr_cpus < 0, "nr_cpus", "err %d\n", nr_cpus))
+ return;
+
+ /* load program */
+ err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd);
+ if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
+ return;
+
+ prog = bpf_object__find_program_by_title(obj, prog_name);
+ if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name))
+ goto out_close;
+
+ /* load map */
+ perf_buf_map = bpf_object__find_map_by_name(obj, "perf_buf_map");
+ if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n"))
+ goto out_close;
+
+ /* attach kprobe */
+ link = bpf_program__attach_kprobe(prog, false /* retprobe */,
+ "sys_nanosleep");
+ if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link)))
+ goto out_close;
+
+ /* set up perf buffer */
+ pb_opts.sample_cb = on_sample;
+ pb_opts.ctx = &cpu_seen;
+ pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, &pb_opts);
+ if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
+ goto out_detach;
+
+ /* trigger kprobe on every CPU */
+ CPU_ZERO(&cpu_seen);
+ for (i = 0; i < nr_cpus; i++) {
+ CPU_ZERO(&cpu_set);
+ CPU_SET(i, &cpu_set);
+
+ err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set),
+ &cpu_set);
+ if (err && CHECK(err, "set_affinity", "cpu #%d, err %d\n",
+ i, err))
+ goto out_detach;
+
+ usleep(1);
+ }
+
+ /* read perf buffer */
+ err = perf_buffer__poll(pb, 100);
+ if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err))
+ goto out_free_pb;
+
+ if (CHECK(CPU_COUNT(&cpu_seen) != nr_cpus, "seen_cpu_cnt",
+ "expect %d, seen %d\n", nr_cpus, CPU_COUNT(&cpu_seen)))
+ goto out_free_pb;
+
+out_free_pb:
+ perf_buffer__free(pb);
+out_detach:
+ bpf_link__destroy(link);
+out_close:
+ bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
new file mode 100644
index 000000000000..8609f0031bc0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct {
+ int type;
+ int key_size;
+ int value_size;
+} perf_buf_map SEC(".maps") = {
+ .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+};
+
+SEC("kprobe/sys_nanosleep")
+int handle_sys_nanosleep_entry(struct pt_regs *ctx)
+{
+ int cpu = bpf_get_smp_processor_id();
+
+ bpf_perf_event_output(ctx, &perf_buf_map, BPF_F_CURRENT_CPU,
+ &cpu, sizeof(cpu));
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1;
--
2.17.1
^ permalink raw reply related
* [PATCH v3 bpf-next 0/4] libbpf: add perf buffer abstraction and API
From: Andrii Nakryiko @ 2019-06-29 5:53 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, kernel-team,
songliubraving
Cc: Andrii Nakryiko
This patchset adds a high-level API for setting up and polling perf buffers
associated with BPF_MAP_TYPE_PERF_EVENT_ARRAY map. Details of APIs are
described in corresponding commit.
Patch #1 adds a set of APIs to set up and work with perf buffer.
Patch #2 enhances libbpf to support auto-setting PERF_EVENT_ARRAY map size.
Patch #3 adds test.
Patch #4 converts bpftool map event_pipe to new API.
v2->v3:
- added perf_buffer__new_raw for more low-level control;
- converted bpftool map event_pipe to new API (Daniel);
- fixed bug with error handling in create_maps (Song);
v1->v2:
- add auto-sizing of PERF_EVENT_ARRAY maps;
Andrii Nakryiko (4):
libbpf: add perf buffer API
libbpf: auto-set PERF_EVENT_ARRAY size to number of CPUs
selftests/bpf: test perf buffer API
tools/bpftool: switch map event_pipe to libbpf's perf_buffer
tools/bpf/bpftool/map_perf_ring.c | 207 +++------
tools/lib/bpf/libbpf.c | 397 +++++++++++++++++-
tools/lib/bpf/libbpf.h | 49 +++
tools/lib/bpf/libbpf.map | 4 +
.../selftests/bpf/prog_tests/perf_buffer.c | 94 +++++
.../selftests/bpf/progs/test_perf_buffer.c | 29 ++
6 files changed, 634 insertions(+), 146 deletions(-)
create mode 100644 tools/testing/selftests/bpf/prog_tests/perf_buffer.c
create mode 100644 tools/testing/selftests/bpf/progs/test_perf_buffer.c
--
2.17.1
^ permalink raw reply
* [net-next, PATCH 3/3, v2] net: netsec: add XDP support
From: Ilias Apalodimas @ 2019-06-29 5:23 UTC (permalink / raw)
To: netdev, jaswinder.singh
Cc: ard.biesheuvel, bjorn.topel, magnus.karlsson, brouer, daniel, ast,
makita.toshiaki, jakub.kicinski, john.fastabend, davem,
maciejromanfijalkowski, Ilias Apalodimas
In-Reply-To: <1561785805-21647-1-git-send-email-ilias.apalodimas@linaro.org>
The interface only supports 1 Tx queue so locking is introduced on
the Tx queue if XDP is enabled to make sure .ndo_start_xmit and
.ndo_xdp_xmit won't corrupt Tx ring
- Performance (SMMU off)
Benchmark XDP_SKB XDP_DRV
xdp1 291kpps 344kpps
rxdrop 282kpps 342kpps
- Performance (SMMU on)
Benchmark XDP_SKB XDP_DRV
xdp1 167kpps 324kpps
rxdrop 164kpps 323kpps
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
---
drivers/net/ethernet/socionext/netsec.c | 361 ++++++++++++++++++++++--
1 file changed, 334 insertions(+), 27 deletions(-)
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 7791bff2f2af..5544a722543f 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -9,6 +9,9 @@
#include <linux/etherdevice.h>
#include <linux/interrupt.h>
#include <linux/io.h>
+#include <linux/netlink.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
#include <net/tcp.h>
#include <net/page_pool.h>
@@ -236,23 +239,41 @@
#define DESC_NUM 256
#define NETSEC_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
-#define NETSEC_RX_BUF_NON_DATA (NETSEC_SKB_PAD + \
+#define NETSEC_RXBUF_HEADROOM (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + \
+ NET_IP_ALIGN)
+#define NETSEC_RX_BUF_NON_DATA (NETSEC_RXBUF_HEADROOM + \
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
#define DESC_SZ sizeof(struct netsec_de)
#define NETSEC_F_NETSEC_VER_MAJOR_NUM(x) ((x) & 0xffff0000)
+#define NETSEC_XDP_PASS 0
+#define NETSEC_XDP_CONSUMED BIT(0)
+#define NETSEC_XDP_TX BIT(1)
+#define NETSEC_XDP_REDIR BIT(2)
+#define NETSEC_XDP_RX_OK (NETSEC_XDP_PASS | NETSEC_XDP_TX | NETSEC_XDP_REDIR)
+
enum ring_id {
NETSEC_RING_TX = 0,
NETSEC_RING_RX
};
+enum buf_type {
+ TYPE_NETSEC_SKB = 0,
+ TYPE_NETSEC_XDP_TX,
+ TYPE_NETSEC_XDP_NDO,
+};
+
struct netsec_desc {
- struct sk_buff *skb;
+ union {
+ struct sk_buff *skb;
+ struct xdp_frame *xdpf;
+ };
dma_addr_t dma_addr;
void *addr;
u16 len;
+ u8 buf_type;
};
struct netsec_desc_ring {
@@ -260,13 +281,17 @@ struct netsec_desc_ring {
struct netsec_desc *desc;
void *vaddr;
u16 head, tail;
+ u16 xdp_xmit; /* netsec_xdp_xmit packets */
+ bool is_xdp;
struct page_pool *page_pool;
struct xdp_rxq_info xdp_rxq;
+ spinlock_t lock; /* XDP tx queue locking */
};
struct netsec_priv {
struct netsec_desc_ring desc_ring[NETSEC_RING_MAX];
struct ethtool_coalesce et_coalesce;
+ struct bpf_prog *xdp_prog;
spinlock_t reglock; /* protect reg access */
struct napi_struct napi;
phy_interface_t phy_interface;
@@ -303,6 +328,11 @@ struct netsec_rx_pkt_info {
bool err_flag;
};
+static void netsec_set_tx_de(struct netsec_priv *priv,
+ struct netsec_desc_ring *dring,
+ const struct netsec_tx_pkt_ctrl *tx_ctrl,
+ const struct netsec_desc *desc, void *buf);
+
static void netsec_write(struct netsec_priv *priv, u32 reg_addr, u32 val)
{
writel(val, priv->ioaddr + reg_addr);
@@ -609,6 +639,9 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv)
int tail = dring->tail;
int cnt = 0;
+ if (dring->is_xdp)
+ spin_lock(&dring->lock);
+
pkts = 0;
bytes = 0;
entry = dring->vaddr + DESC_SZ * tail;
@@ -622,13 +655,23 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv)
eop = (entry->attr >> NETSEC_TX_LAST) & 1;
dma_rmb();
- dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
- DMA_TO_DEVICE);
- if (eop) {
- pkts++;
+ if (desc->buf_type == TYPE_NETSEC_SKB)
+ dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
+ DMA_TO_DEVICE);
+ else if (desc->buf_type == TYPE_NETSEC_XDP_NDO)
+ dma_unmap_single(priv->dev, desc->dma_addr,
+ desc->len, DMA_TO_DEVICE);
+
+ if (!eop)
+ goto next;
+
+ if (desc->buf_type == TYPE_NETSEC_SKB) {
bytes += desc->skb->len;
dev_kfree_skb(desc->skb);
+ } else {
+ xdp_return_frame(desc->xdpf);
}
+next:
/* clean up so netsec_uninit_pkt_dring() won't free the skb
* again
*/
@@ -645,6 +688,8 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv)
entry = dring->vaddr + DESC_SZ * tail;
cnt++;
}
+ if (dring->is_xdp)
+ spin_unlock(&dring->lock);
if (!cnt)
return false;
@@ -688,12 +733,13 @@ static void *netsec_alloc_rx_data(struct netsec_priv *priv,
if (!page)
return NULL;
- /* page_pool API will map the whole page, skip
- * NET_SKB_PAD + NET_IP_ALIGN for the payload
+ /* We allocate the same buffer length for XDP and non-XDP cases.
+ * page_pool API will map the whole page, skip what's needed for
+ * network payloads and/or XDP
*/
- *dma_handle = page_pool_get_dma_addr(page) + NETSEC_SKB_PAD;
- /* make sure the incoming payload fits in the page with the needed
- * NET_SKB_PAD + NET_IP_ALIGN + skb_shared_info
+ *dma_handle = page_pool_get_dma_addr(page) + NETSEC_RXBUF_HEADROOM;
+ /* Make sure the incoming payload fits in the page for XDP and non-XDP
+ * cases and reserve enough space for headroom + skb_shared_info
*/
*desc_len = PAGE_SIZE - NETSEC_RX_BUF_NON_DATA;
@@ -714,21 +760,159 @@ static void netsec_rx_fill(struct netsec_priv *priv, u16 from, u16 num)
}
}
+static void netsec_xdp_ring_tx_db(struct netsec_priv *priv, u16 pkts)
+{
+ if (likely(pkts))
+ netsec_write(priv, NETSEC_REG_NRM_TX_PKTCNT, pkts);
+}
+
+static void netsec_finalize_xdp_rx(struct netsec_priv *priv, u32 xdp_res,
+ u16 pkts)
+{
+ if (xdp_res & NETSEC_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_res & NETSEC_XDP_TX)
+ netsec_xdp_ring_tx_db(priv, pkts);
+}
+
+/* The current driver only supports 1 Txq, this should run under spin_lock() */
+static u32 netsec_xdp_queue_one(struct netsec_priv *priv,
+ struct xdp_frame *xdpf, bool is_ndo)
+
+{
+ struct netsec_desc_ring *tx_ring = &priv->desc_ring[NETSEC_RING_TX];
+ struct page *page = virt_to_page(xdpf->data);
+ struct netsec_tx_pkt_ctrl tx_ctrl = {};
+ struct netsec_desc tx_desc;
+ dma_addr_t dma_handle;
+ u16 filled;
+
+ if (tx_ring->head >= tx_ring->tail)
+ filled = tx_ring->head - tx_ring->tail;
+ else
+ filled = tx_ring->head + DESC_NUM - tx_ring->tail;
+
+ if (DESC_NUM - filled <= 1)
+ return NETSEC_XDP_CONSUMED;
+
+ if (is_ndo) {
+ /* this is for ndo_xdp_xmit, the buffer needs mapping before
+ * sending
+ */
+ dma_handle = dma_map_single(priv->dev, xdpf->data, xdpf->len,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(priv->dev, dma_handle))
+ return NETSEC_XDP_CONSUMED;
+ tx_desc.buf_type = TYPE_NETSEC_XDP_NDO;
+ } else {
+ /* This is the device Rx buffer from page_pool. No need to remap
+ * just sync and send it
+ */
+ struct netsec_desc_ring *rx_ring =
+ &priv->desc_ring[NETSEC_RING_RX];
+ enum dma_data_direction dma_dir =
+ page_pool_get_dma_dir(rx_ring->page_pool);
+
+ dma_handle = page_pool_get_dma_addr(page) +
+ NETSEC_RXBUF_HEADROOM;
+ dma_sync_single_for_device(priv->dev, dma_handle, xdpf->len,
+ dma_dir);
+ tx_desc.buf_type = TYPE_NETSEC_XDP_TX;
+ }
+
+ tx_desc.dma_addr = dma_handle;
+ tx_desc.addr = xdpf->data;
+ tx_desc.len = xdpf->len;
+
+ netsec_set_tx_de(priv, tx_ring, &tx_ctrl, &tx_desc, xdpf);
+
+ return NETSEC_XDP_TX;
+}
+
+static u32 netsec_xdp_xmit_back(struct netsec_priv *priv, struct xdp_buff *xdp)
+{
+ struct netsec_desc_ring *tx_ring = &priv->desc_ring[NETSEC_RING_TX];
+ struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
+ u32 ret;
+
+ if (unlikely(!xdpf))
+ return NETSEC_XDP_CONSUMED;
+
+ spin_lock(&tx_ring->lock);
+ ret = netsec_xdp_queue_one(priv, xdpf, false);
+ spin_unlock(&tx_ring->lock);
+
+ return ret;
+}
+
+static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
+ struct xdp_buff *xdp)
+{
+ u32 ret = NETSEC_XDP_PASS;
+ int err;
+ u32 act;
+
+ act = bpf_prog_run_xdp(prog, xdp);
+
+ switch (act) {
+ case XDP_PASS:
+ ret = NETSEC_XDP_PASS;
+ break;
+ case XDP_TX:
+ ret = netsec_xdp_xmit_back(priv, xdp);
+ if (ret != NETSEC_XDP_TX)
+ xdp_return_buff(xdp);
+ break;
+ case XDP_REDIRECT:
+ err = xdp_do_redirect(priv->ndev, xdp, prog);
+ if (!err) {
+ ret = NETSEC_XDP_REDIR;
+ } else {
+ ret = NETSEC_XDP_CONSUMED;
+ xdp_return_buff(xdp);
+ }
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ /* fall through */
+ case XDP_ABORTED:
+ trace_xdp_exception(priv->ndev, prog, act);
+ /* fall through -- handle aborts by dropping packet */
+ case XDP_DROP:
+ ret = NETSEC_XDP_CONSUMED;
+ xdp_return_buff(xdp);
+ break;
+ }
+
+ return ret;
+}
+
static int netsec_process_rx(struct netsec_priv *priv, int budget)
{
struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
struct net_device *ndev = priv->ndev;
struct netsec_rx_pkt_info rx_info;
- struct sk_buff *skb;
+ enum dma_data_direction dma_dir;
+ struct bpf_prog *xdp_prog;
+ struct sk_buff *skb = NULL;
+ u16 xdp_xmit = 0;
+ u32 xdp_act = 0;
int done = 0;
+ rcu_read_lock();
+ xdp_prog = READ_ONCE(priv->xdp_prog);
+ dma_dir = page_pool_get_dma_dir(dring->page_pool);
+
while (done < budget) {
u16 idx = dring->tail;
struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
struct netsec_desc *desc = &dring->desc[idx];
struct page *page = virt_to_page(desc->addr);
+ u32 xdp_result = XDP_PASS;
u16 pkt_len, desc_len;
dma_addr_t dma_handle;
+ struct xdp_buff xdp;
void *buf_addr;
if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD)) {
@@ -770,10 +954,26 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
break;
dma_sync_single_for_cpu(priv->dev, desc->dma_addr, pkt_len,
- DMA_FROM_DEVICE);
+ dma_dir);
prefetch(desc->addr);
+ xdp.data_hard_start = desc->addr;
+ xdp.data = desc->addr + NETSEC_RXBUF_HEADROOM;
+ xdp_set_data_meta_invalid(&xdp);
+ xdp.data_end = xdp.data + pkt_len;
+ xdp.rxq = &dring->xdp_rxq;
+
+ if (xdp_prog) {
+ xdp_result = netsec_run_xdp(priv, xdp_prog, &xdp);
+ if (xdp_result != NETSEC_XDP_PASS) {
+ xdp_act |= xdp_result;
+ if (xdp_result == NETSEC_XDP_TX)
+ xdp_xmit++;
+ goto next;
+ }
+ }
skb = build_skb(desc->addr, desc->len + NETSEC_RX_BUF_NON_DATA);
+
if (unlikely(!skb)) {
/* If skb fails recycle_direct will either unmap and
* free the page or refill the cache depending on the
@@ -787,27 +987,32 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
}
page_pool_release_page(dring->page_pool, page);
- /* Update the descriptor with the new buffer we allocated */
- desc->len = desc_len;
- desc->dma_addr = dma_handle;
- desc->addr = buf_addr;
-
- skb_reserve(skb, NETSEC_SKB_PAD);
- skb_put(skb, pkt_len);
+ skb_reserve(skb, xdp.data - xdp.data_hard_start);
+ skb_put(skb, xdp.data_end - xdp.data);
skb->protocol = eth_type_trans(skb, priv->ndev);
if (priv->rx_cksum_offload_flag &&
rx_info.rx_cksum_result == NETSEC_RX_CKSUM_OK)
skb->ip_summed = CHECKSUM_UNNECESSARY;
- if (napi_gro_receive(&priv->napi, skb) != GRO_DROP) {
+next:
+ if ((skb && napi_gro_receive(&priv->napi, skb) != GRO_DROP) ||
+ xdp_result & NETSEC_XDP_RX_OK) {
ndev->stats.rx_packets++;
- ndev->stats.rx_bytes += pkt_len;
+ ndev->stats.rx_bytes += xdp.data_end - xdp.data;
}
+ /* Update the descriptor with fresh buffers */
+ desc->len = desc_len;
+ desc->dma_addr = dma_handle;
+ desc->addr = buf_addr;
+
netsec_rx_fill(priv, idx, 1);
dring->tail = (dring->tail + 1) % DESC_NUM;
}
+ netsec_finalize_xdp_rx(priv, xdp_act, xdp_xmit);
+
+ rcu_read_unlock();
return done;
}
@@ -837,8 +1042,7 @@ static int netsec_napi_poll(struct napi_struct *napi, int budget)
static void netsec_set_tx_de(struct netsec_priv *priv,
struct netsec_desc_ring *dring,
const struct netsec_tx_pkt_ctrl *tx_ctrl,
- const struct netsec_desc *desc,
- struct sk_buff *skb)
+ const struct netsec_desc *desc, void *buf)
{
int idx = dring->head;
struct netsec_de *de;
@@ -861,10 +1065,16 @@ static void netsec_set_tx_de(struct netsec_priv *priv,
de->data_buf_addr_lw = lower_32_bits(desc->dma_addr);
de->buf_len_info = (tx_ctrl->tcp_seg_len << 16) | desc->len;
de->attr = attr;
- dma_wmb();
+ /* under spin_lock if using XDP */
+ if (!dring->is_xdp)
+ dma_wmb();
dring->desc[idx] = *desc;
- dring->desc[idx].skb = skb;
+ if (desc->buf_type == TYPE_NETSEC_SKB)
+ dring->desc[idx].skb = buf;
+ else if (desc->buf_type == TYPE_NETSEC_XDP_TX ||
+ desc->buf_type == TYPE_NETSEC_XDP_NDO)
+ dring->desc[idx].xdpf = buf;
/* move head ahead */
dring->head = (dring->head + 1) % DESC_NUM;
@@ -915,8 +1125,12 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
u16 tso_seg_len = 0;
int filled;
+ if (dring->is_xdp)
+ spin_lock_bh(&dring->lock);
filled = netsec_desc_used(dring);
if (netsec_check_stop_tx(priv, filled)) {
+ if (dring->is_xdp)
+ spin_unlock_bh(&dring->lock);
net_warn_ratelimited("%s %s Tx queue full\n",
dev_name(priv->dev), ndev->name);
return NETDEV_TX_BUSY;
@@ -949,6 +1163,8 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
tx_desc.dma_addr = dma_map_single(priv->dev, skb->data,
skb_headlen(skb), DMA_TO_DEVICE);
if (dma_mapping_error(priv->dev, tx_desc.dma_addr)) {
+ if (dring->is_xdp)
+ spin_unlock_bh(&dring->lock);
netif_err(priv, drv, priv->ndev,
"%s: DMA mapping failed\n", __func__);
ndev->stats.tx_dropped++;
@@ -957,11 +1173,14 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
}
tx_desc.addr = skb->data;
tx_desc.len = skb_headlen(skb);
+ tx_desc.buf_type = TYPE_NETSEC_SKB;
skb_tx_timestamp(skb);
netdev_sent_queue(priv->ndev, skb->len);
netsec_set_tx_de(priv, dring, &tx_ctrl, &tx_desc, skb);
+ if (dring->is_xdp)
+ spin_unlock_bh(&dring->lock);
netsec_write(priv, NETSEC_REG_NRM_TX_PKTCNT, 1); /* submit another tx */
return NETDEV_TX_OK;
@@ -1049,6 +1268,7 @@ static int netsec_alloc_dring(struct netsec_priv *priv, enum ring_id id)
static void netsec_setup_tx_dring(struct netsec_priv *priv)
{
struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
+ struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog);
int i;
for (i = 0; i < DESC_NUM; i++) {
@@ -1061,11 +1281,18 @@ static void netsec_setup_tx_dring(struct netsec_priv *priv)
*/
de->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD;
}
+
+ if (xdp_prog)
+ dring->is_xdp = true;
+ else
+ dring->is_xdp = false;
+
}
static int netsec_setup_rx_dring(struct netsec_priv *priv)
{
struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
+ struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog);
struct page_pool_params pp_params = { 0 };
int i, err;
@@ -1075,7 +1302,7 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
pp_params.pool_size = DESC_NUM;
pp_params.nid = cpu_to_node(0);
pp_params.dev = priv->dev;
- pp_params.dma_dir = DMA_FROM_DEVICE;
+ pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
dring->page_pool = page_pool_create(&pp_params);
if (IS_ERR(dring->page_pool)) {
@@ -1495,6 +1722,9 @@ static int netsec_netdev_init(struct net_device *ndev)
if (ret)
goto err2;
+ spin_lock_init(&priv->desc_ring[NETSEC_RING_TX].lock);
+ spin_lock_init(&priv->desc_ring[NETSEC_RING_RX].lock);
+
return 0;
err2:
netsec_free_dring(priv, NETSEC_RING_RX);
@@ -1527,6 +1757,81 @@ static int netsec_netdev_ioctl(struct net_device *ndev, struct ifreq *ifr,
return phy_mii_ioctl(ndev->phydev, ifr, cmd);
}
+static int netsec_xdp_xmit(struct net_device *ndev, int n,
+ struct xdp_frame **frames, u32 flags)
+{
+ struct netsec_priv *priv = netdev_priv(ndev);
+ struct netsec_desc_ring *tx_ring = &priv->desc_ring[NETSEC_RING_TX];
+ int drops = 0;
+ int i;
+
+ if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+ return -EINVAL;
+
+ spin_lock(&tx_ring->lock);
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdpf = frames[i];
+ int err;
+
+ err = netsec_xdp_queue_one(priv, xdpf, true);
+ if (err != NETSEC_XDP_TX) {
+ xdp_return_frame_rx_napi(xdpf);
+ drops++;
+ } else {
+ tx_ring->xdp_xmit++;
+ }
+ }
+ spin_unlock(&tx_ring->lock);
+
+ if (unlikely(flags & XDP_XMIT_FLUSH)) {
+ netsec_xdp_ring_tx_db(priv, tx_ring->xdp_xmit);
+ tx_ring->xdp_xmit = 0;
+ }
+
+ return n - drops;
+}
+
+static int netsec_xdp_setup(struct netsec_priv *priv, struct bpf_prog *prog,
+ struct netlink_ext_ack *extack)
+{
+ struct net_device *dev = priv->ndev;
+ struct bpf_prog *old_prog;
+
+ /* For now just support only the usual MTU sized frames */
+ if (prog && dev->mtu > 1500) {
+ NL_SET_ERR_MSG_MOD(extack, "Jumbo frames not supported on XDP");
+ return -EOPNOTSUPP;
+ }
+
+ if (netif_running(dev))
+ netsec_netdev_stop(dev);
+
+ /* Detach old prog, if any */
+ old_prog = xchg(&priv->xdp_prog, prog);
+ if (old_prog)
+ bpf_prog_put(old_prog);
+
+ if (netif_running(dev))
+ netsec_netdev_open(dev);
+
+ return 0;
+}
+
+static int netsec_xdp(struct net_device *ndev, struct netdev_bpf *xdp)
+{
+ struct netsec_priv *priv = netdev_priv(ndev);
+
+ switch (xdp->command) {
+ case XDP_SETUP_PROG:
+ return netsec_xdp_setup(priv, xdp->prog, xdp->extack);
+ case XDP_QUERY_PROG:
+ xdp->prog_id = priv->xdp_prog ? priv->xdp_prog->aux->id : 0;
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
static const struct net_device_ops netsec_netdev_ops = {
.ndo_init = netsec_netdev_init,
.ndo_uninit = netsec_netdev_uninit,
@@ -1537,6 +1842,8 @@ static const struct net_device_ops netsec_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = netsec_netdev_ioctl,
+ .ndo_xdp_xmit = netsec_xdp_xmit,
+ .ndo_bpf = netsec_xdp,
};
static int netsec_of_probe(struct platform_device *pdev,
--
2.20.1
^ permalink raw reply related
* [net-next, PATCH 2/3, v2] net: page_pool: add helper function for retrieving dma direction
From: Ilias Apalodimas @ 2019-06-29 5:23 UTC (permalink / raw)
To: netdev, jaswinder.singh
Cc: ard.biesheuvel, bjorn.topel, magnus.karlsson, brouer, daniel, ast,
makita.toshiaki, jakub.kicinski, john.fastabend, davem,
maciejromanfijalkowski, Ilias Apalodimas
In-Reply-To: <1561785805-21647-1-git-send-email-ilias.apalodimas@linaro.org>
Since the dma direction is stored in page pool params, offer an API
helper for driver that choose not to keep track of it locally
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
include/net/page_pool.h | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index f07c518ef8a5..ee9c871d2043 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -112,6 +112,15 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool)
return page_pool_alloc_pages(pool, gfp);
}
+/* get the stored dma direction. A driver might decide to treat this locally and
+ * avoid the extra cache line from page_pool to determine the direction
+ */
+static
+inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
+{
+ return pool->p.dma_dir;
+}
+
struct page_pool *page_pool_create(const struct page_pool_params *params);
void __page_pool_free(struct page_pool *pool);
--
2.20.1
^ permalink raw reply related
* [net-next, PATCH 1/3, v2] net: netsec: Use page_pool API
From: Ilias Apalodimas @ 2019-06-29 5:23 UTC (permalink / raw)
To: netdev, jaswinder.singh
Cc: ard.biesheuvel, bjorn.topel, magnus.karlsson, brouer, daniel, ast,
makita.toshiaki, jakub.kicinski, john.fastabend, davem,
maciejromanfijalkowski, Ilias Apalodimas
In-Reply-To: <1561785805-21647-1-git-send-email-ilias.apalodimas@linaro.org>
Use page_pool and it's DMA mapping capabilities for Rx buffers instead
of netdev/napi_alloc_frag()
Although this will result in a slight performance penalty on small sized
packets (~10%) the use of the API will allow to easily add XDP support.
The penalty won't be visible in network testing i.e ipef/netperf etc, it
only happens during raw packet drops.
Furthermore we intend to add recycling capabilities on the API
in the future. Once the recycling is added the performance penalty will
go away.
The only 'real' penalty is the slightly increased memory usage, since we
now allocate a page per packet instead of the amount of bytes we need +
skb metadata (difference is roughly 2kb per packet).
With a minimum of 4BG of RAM on the only SoC that has this NIC the
extra memory usage is negligible (a bit more on 64K pages)
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
drivers/net/ethernet/socionext/Kconfig | 1 +
drivers/net/ethernet/socionext/netsec.c | 126 +++++++++++++++---------
2 files changed, 80 insertions(+), 47 deletions(-)
diff --git a/drivers/net/ethernet/socionext/Kconfig b/drivers/net/ethernet/socionext/Kconfig
index 25f18be27423..95e99baf3f45 100644
--- a/drivers/net/ethernet/socionext/Kconfig
+++ b/drivers/net/ethernet/socionext/Kconfig
@@ -26,6 +26,7 @@ config SNI_NETSEC
tristate "Socionext NETSEC ethernet support"
depends on (ARCH_SYNQUACER || COMPILE_TEST) && OF
select PHYLIB
+ select PAGE_POOL
select MII
---help---
Enable to add support for the SocioNext NetSec Gigabit Ethernet
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 48fd7448b513..7791bff2f2af 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -11,6 +11,7 @@
#include <linux/io.h>
#include <net/tcp.h>
+#include <net/page_pool.h>
#include <net/ip6_checksum.h>
#define NETSEC_REG_SOFT_RST 0x104
@@ -235,7 +236,8 @@
#define DESC_NUM 256
#define NETSEC_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
-#define NETSEC_RX_BUF_SZ 1536
+#define NETSEC_RX_BUF_NON_DATA (NETSEC_SKB_PAD + \
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
#define DESC_SZ sizeof(struct netsec_de)
@@ -258,6 +260,8 @@ struct netsec_desc_ring {
struct netsec_desc *desc;
void *vaddr;
u16 head, tail;
+ struct page_pool *page_pool;
+ struct xdp_rxq_info xdp_rxq;
};
struct netsec_priv {
@@ -673,33 +677,27 @@ static void netsec_process_tx(struct netsec_priv *priv)
}
static void *netsec_alloc_rx_data(struct netsec_priv *priv,
- dma_addr_t *dma_handle, u16 *desc_len,
- bool napi)
+ dma_addr_t *dma_handle, u16 *desc_len)
+
{
- size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- size_t payload_len = NETSEC_RX_BUF_SZ;
- dma_addr_t mapping;
- void *buf;
- total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD);
+ struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
+ struct page *page;
- buf = napi ? napi_alloc_frag(total_len) : netdev_alloc_frag(total_len);
- if (!buf)
+ page = page_pool_dev_alloc_pages(dring->page_pool);
+ if (!page)
return NULL;
- mapping = dma_map_single(priv->dev, buf + NETSEC_SKB_PAD, payload_len,
- DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(priv->dev, mapping)))
- goto err_out;
-
- *dma_handle = mapping;
- *desc_len = payload_len;
-
- return buf;
+ /* page_pool API will map the whole page, skip
+ * NET_SKB_PAD + NET_IP_ALIGN for the payload
+ */
+ *dma_handle = page_pool_get_dma_addr(page) + NETSEC_SKB_PAD;
+ /* make sure the incoming payload fits in the page with the needed
+ * NET_SKB_PAD + NET_IP_ALIGN + skb_shared_info
+ */
+ *desc_len = PAGE_SIZE - NETSEC_RX_BUF_NON_DATA;
-err_out:
- skb_free_frag(buf);
- return NULL;
+ return page_address(page);
}
static void netsec_rx_fill(struct netsec_priv *priv, u16 from, u16 num)
@@ -728,10 +726,10 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
u16 idx = dring->tail;
struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
struct netsec_desc *desc = &dring->desc[idx];
+ struct page *page = virt_to_page(desc->addr);
u16 pkt_len, desc_len;
dma_addr_t dma_handle;
void *buf_addr;
- u32 truesize;
if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD)) {
/* reading the register clears the irq */
@@ -766,8 +764,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
/* allocate a fresh buffer and map it to the hardware.
* This will eventually replace the old buffer in the hardware
*/
- buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len,
- true);
+ buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len);
+
if (unlikely(!buf_addr))
break;
@@ -775,22 +773,19 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
DMA_FROM_DEVICE);
prefetch(desc->addr);
- truesize = SKB_DATA_ALIGN(desc->len + NETSEC_SKB_PAD) +
- SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- skb = build_skb(desc->addr, truesize);
+ skb = build_skb(desc->addr, desc->len + NETSEC_RX_BUF_NON_DATA);
if (unlikely(!skb)) {
- /* free the newly allocated buffer, we are not going to
- * use it
+ /* If skb fails recycle_direct will either unmap and
+ * free the page or refill the cache depending on the
+ * cache state. Since we paid the allocation cost if
+ * building an skb fails try to put the page into cache
*/
- dma_unmap_single(priv->dev, dma_handle, desc_len,
- DMA_FROM_DEVICE);
- skb_free_frag(buf_addr);
+ page_pool_recycle_direct(dring->page_pool, page);
netif_err(priv, drv, priv->ndev,
"rx failed to build skb\n");
break;
}
- dma_unmap_single_attrs(priv->dev, desc->dma_addr, desc->len,
- DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+ page_pool_release_page(dring->page_pool, page);
/* Update the descriptor with the new buffer we allocated */
desc->len = desc_len;
@@ -980,19 +975,31 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id)
if (!dring->vaddr || !dring->desc)
return;
-
for (idx = 0; idx < DESC_NUM; idx++) {
desc = &dring->desc[idx];
if (!desc->addr)
continue;
- dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
- id == NETSEC_RING_RX ? DMA_FROM_DEVICE :
- DMA_TO_DEVICE);
- if (id == NETSEC_RING_RX)
- skb_free_frag(desc->addr);
- else if (id == NETSEC_RING_TX)
+ if (id == NETSEC_RING_RX) {
+ struct page *page = virt_to_page(desc->addr);
+
+ page_pool_put_page(dring->page_pool, page, false);
+ } else if (id == NETSEC_RING_TX) {
+ dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
+ DMA_TO_DEVICE);
dev_kfree_skb(desc->skb);
+ }
+ }
+
+ /* Rx is currently using page_pool
+ * since the pool is created during netsec_setup_rx_dring(), we need to
+ * free the pool manually if the registration failed
+ */
+ if (id == NETSEC_RING_RX) {
+ if (xdp_rxq_info_is_reg(&dring->xdp_rxq))
+ xdp_rxq_info_unreg(&dring->xdp_rxq);
+ else
+ page_pool_free(dring->page_pool);
}
memset(dring->desc, 0, sizeof(struct netsec_desc) * DESC_NUM);
@@ -1059,7 +1066,23 @@ static void netsec_setup_tx_dring(struct netsec_priv *priv)
static int netsec_setup_rx_dring(struct netsec_priv *priv)
{
struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
- int i;
+ struct page_pool_params pp_params = { 0 };
+ int i, err;
+
+ pp_params.order = 0;
+ /* internal DMA mapping in page_pool */
+ pp_params.flags = PP_FLAG_DMA_MAP;
+ pp_params.pool_size = DESC_NUM;
+ pp_params.nid = cpu_to_node(0);
+ pp_params.dev = priv->dev;
+ pp_params.dma_dir = DMA_FROM_DEVICE;
+
+ dring->page_pool = page_pool_create(&pp_params);
+ if (IS_ERR(dring->page_pool)) {
+ err = PTR_ERR(dring->page_pool);
+ dring->page_pool = NULL;
+ goto err_out;
+ }
for (i = 0; i < DESC_NUM; i++) {
struct netsec_desc *desc = &dring->desc[i];
@@ -1067,10 +1090,10 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
void *buf;
u16 len;
- buf = netsec_alloc_rx_data(priv, &dma_handle, &len,
- false);
+ buf = netsec_alloc_rx_data(priv, &dma_handle, &len);
+
if (!buf) {
- netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
+ err = -ENOMEM;
goto err_out;
}
desc->dma_addr = dma_handle;
@@ -1079,11 +1102,20 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
}
netsec_rx_fill(priv, 0, DESC_NUM);
+ err = xdp_rxq_info_reg(&dring->xdp_rxq, priv->ndev, 0);
+ if (err)
+ goto err_out;
+
+ err = xdp_rxq_info_reg_mem_model(&dring->xdp_rxq, MEM_TYPE_PAGE_POOL,
+ dring->page_pool);
+ if (err)
+ goto err_out;
return 0;
err_out:
- return -ENOMEM;
+ netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
+ return err;
}
static int netsec_netdev_load_ucode_region(struct netsec_priv *priv, u32 reg,
--
2.20.1
^ permalink raw reply related
* [PATCH 0/3, net-next, v2] net: netsec: Add XDP Support
From: Ilias Apalodimas @ 2019-06-29 5:23 UTC (permalink / raw)
To: netdev, jaswinder.singh
Cc: ard.biesheuvel, bjorn.topel, magnus.karlsson, brouer, daniel, ast,
makita.toshiaki, jakub.kicinski, john.fastabend, davem,
maciejromanfijalkowski, Ilias Apalodimas
This is a respin of https://www.spinics.net/lists/netdev/msg526066.html
Since page_pool API fixes are merged into net-next we can now safely use
it's DMA mapping capabilities.
First patch changes the buffer allocation from napi/netdev_alloc_frag()
to page_pool API. Although this will lead to slightly reduced performance
(on raw packet drops only) we can use the API for XDP buffer recycling.
Another side effect is a slight increase in memory usage, due to using a
single page per packet.
The second patch adds XDP support on the driver.
There's a bunch of interesting options that come up due to the single
Tx queue.
Locking is needed(to avoid messing up the Tx queues since ndo_xdp_xmit
and the normal stack can co-exist). We also need to track down the
'buffer type' for TX and properly free or recycle the packet depending
on it's nature.
Changes since RFC:
- Bug fixes from Jesper and Maciej
- Added page pool API to retrieve the DMA direction
Changes since v1:
- Use page_pool_free correctly if xdp_rxq_info_reg() failed
Ilias Apalodimas (3):
net: netsec: Use page_pool API
net: page_pool: add helper function for retrieving dma direction
net: netsec: add XDP support
drivers/net/ethernet/socionext/Kconfig | 1 +
drivers/net/ethernet/socionext/netsec.c | 473 ++++++++++++++++++++----
include/net/page_pool.h | 9 +
3 files changed, 416 insertions(+), 67 deletions(-)
--
2.20.1
^ permalink raw reply
* Re: [net-next 2/4] gve: Add transmit and receive support
From: kbuild test robot @ 2019-06-29 4:13 UTC (permalink / raw)
To: Catherine Sullivan
Cc: kbuild-all, netdev, Catherine Sullivan, Sagi Shahar, Jon Olson,
Willem de Bruijn, Luigi Rizzo
In-Reply-To: <20190626185251.205687-3-csully@google.com>
Hi Catherine,
I love your patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
url: https://github.com/0day-ci/linux/commits/Catherine-Sullivan/Add-gve-driver/20190629-070444
reproduce:
# apt-get install sparse
# sparse version: v0.6.1-rc1-7-g2b96cd8-dirty
make ARCH=x86_64 allmodconfig
make C=1 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__'
If you fix the issue, kindly add following tag
Reported-by: kbuild test robot <lkp@intel.com>
sparse warnings: (new ones prefixed by >>)
drivers/net/ethernet/google/gve/gve_main.c:25:12: sparse: sparse: symbol 'gve_version_str' was not declared. Should it be static?
drivers/net/ethernet/google/gve/gve_main.c:26:12: sparse: sparse: symbol 'gve_version_prefix' was not declared. Should it be static?
>> drivers/net/ethernet/google/gve/gve_main.c:79:16: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
>> drivers/net/ethernet/google/gve/gve_main.c:79:16: sparse: expected unsigned int val
>> drivers/net/ethernet/google/gve/gve_main.c:79:16: sparse: got restricted __be32 [usertype]
drivers/net/ethernet/google/gve/gve_main.c:104:16: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
drivers/net/ethernet/google/gve/gve_main.c:104:16: sparse: expected unsigned int val
drivers/net/ethernet/google/gve/gve_main.c:104:16: sparse: got restricted __be32 [usertype]
drivers/net/ethernet/google/gve/gve_main.c:115:24: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
drivers/net/ethernet/google/gve/gve_main.c:115:24: sparse: expected unsigned int val
drivers/net/ethernet/google/gve/gve_main.c:115:24: sparse: got restricted __be32 [usertype]
>> drivers/net/ethernet/google/gve/gve_main.c:84:5: sparse: sparse: symbol 'gve_napi_poll' was not declared. Should it be static?
>> drivers/net/ethernet/google/gve/gve_main.c:297:6: sparse: sparse: symbol 'gve_add_napi' was not declared. Should it be static?
>> drivers/net/ethernet/google/gve/gve_main.c:305:6: sparse: sparse: symbol 'gve_remove_napi' was not declared. Should it be static?
drivers/net/ethernet/google/gve/gve_main.c:726:24: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
drivers/net/ethernet/google/gve/gve_main.c:726:24: sparse: expected unsigned int val
drivers/net/ethernet/google/gve/gve_main.c:726:24: sparse: got restricted __be32 [usertype]
drivers/net/ethernet/google/gve/gve_main.c:733:24: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
drivers/net/ethernet/google/gve/gve_main.c:733:24: sparse: expected unsigned int val
drivers/net/ethernet/google/gve/gve_main.c:733:24: sparse: got restricted __be32 [usertype]
drivers/net/ethernet/google/gve/gve_main.c:907:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:907:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:907:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:907:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:907:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:907:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:908:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:908:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:908:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:908:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:908:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:908:25: sparse: sparse: cast to restricted __be32
--
>> drivers/net/ethernet/google/gve/gve_tx.c:145:6: sparse: sparse: symbol 'gve_tx_free_ring' was not declared. Should it be static?
>> drivers/net/ethernet/google/gve/gve_tx.c:18:16: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
>> drivers/net/ethernet/google/gve/gve_tx.c:18:16: sparse: expected unsigned int val
>> drivers/net/ethernet/google/gve/gve_tx.c:18:16: sparse: got restricted __be32 [usertype] val
>> drivers/net/ethernet/google/gve/gve_tx.c:18:16: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
>> drivers/net/ethernet/google/gve/gve_tx.c:18:16: sparse: expected unsigned int val
>> drivers/net/ethernet/google/gve/gve_tx.c:18:16: sparse: got restricted __be32 [usertype] val
--
>> drivers/net/ethernet/google/gve/gve_rx.c:11:6: sparse: sparse: symbol 'gve_rx_remove_from_block' was not declared. Should it be static?
>> drivers/net/ethernet/google/gve/gve_rx.c:217:16: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
>> drivers/net/ethernet/google/gve/gve_rx.c:217:16: sparse: expected unsigned int val
>> drivers/net/ethernet/google/gve/gve_rx.c:217:16: sparse: got restricted __be32 [usertype]
>> drivers/net/ethernet/google/gve/gve_rx.c:349:27: sparse: sparse: incorrect type in assignment (different base types) @@ expected restricted __wsum [usertype] csum @@ got restricted __wsum [usertype] csum @@
>> drivers/net/ethernet/google/gve/gve_rx.c:349:27: sparse: expected restricted __wsum [usertype] csum
>> drivers/net/ethernet/google/gve/gve_rx.c:349:27: sparse: got restricted __be16 [usertype] csum
>> drivers/net/ethernet/google/gve/gve_rx.c:374:19: sparse: sparse: incorrect type in assignment (different base types) @@ expected unsigned short [usertype] flags_seq @@ got resunsigned short [usertype] flags_seq @@
>> drivers/net/ethernet/google/gve/gve_rx.c:374:19: sparse: expected unsigned short [usertype] flags_seq
>> drivers/net/ethernet/google/gve/gve_rx.c:374:19: sparse: got restricted __be16 [usertype] flags_seq
Please review and possibly fold the followup patch.
vim +79 drivers/net/ethernet/google/gve/gve_main.c
24
> 25 const char gve_version_str[] = GVE_VERSION;
26 const char gve_version_prefix[] = GVE_VERSION_PREFIX;
27
28 static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
29 {
30 struct gve_priv *priv = netdev_priv(dev);
31 int ring;
32
33 if (priv->rx) {
34 for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
35 s->rx_packets += priv->rx[ring].rpackets;
36 s->rx_bytes += priv->rx[ring].rbytes;
37 }
38 }
39 if (priv->tx) {
40 for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) {
41 s->tx_packets += priv->tx[ring].pkt_done;
42 s->tx_bytes += priv->tx[ring].bytes_done;
43 }
44 }
45 }
46
47 static int gve_alloc_counter_array(struct gve_priv *priv)
48 {
49 priv->counter_array =
50 dma_alloc_coherent(&priv->pdev->dev,
51 priv->num_event_counters *
52 sizeof(*priv->counter_array),
53 &priv->counter_array_bus, GFP_KERNEL);
54 if (!priv->counter_array)
55 return -ENOMEM;
56
57 return 0;
58 }
59
60 static void gve_free_counter_array(struct gve_priv *priv)
61 {
62 dma_free_coherent(&priv->pdev->dev,
63 priv->num_event_counters *
64 sizeof(*priv->counter_array),
65 priv->counter_array, priv->counter_array_bus);
66 priv->counter_array = NULL;
67 }
68
69 static irqreturn_t gve_mgmnt_intr(int irq, void *arg)
70 {
71 return IRQ_HANDLED;
72 }
73
74 static irqreturn_t gve_intr(int irq, void *arg)
75 {
76 struct gve_notify_block *block = arg;
77 struct gve_priv *priv = block->priv;
78
> 79 writel(cpu_to_be32(GVE_IRQ_MASK), gve_irq_doorbell(priv, block));
80 napi_schedule_irqoff(&block->napi);
81 return IRQ_HANDLED;
82 }
83
> 84 int gve_napi_poll(struct napi_struct *napi, int budget)
85 {
86 struct gve_notify_block *block;
87 __be32 __iomem *irq_doorbell;
88 bool reschedule = false;
89 struct gve_priv *priv;
90
91 block = container_of(napi, struct gve_notify_block, napi);
92 priv = block->priv;
93
94 if (block->tx)
95 reschedule |= gve_tx_poll(block, budget);
96 if (block->rx)
97 reschedule |= gve_rx_poll(block, budget);
98
99 if (reschedule)
100 return budget;
101
102 napi_complete(napi);
103 irq_doorbell = gve_irq_doorbell(priv, block);
104 writel(cpu_to_be32(GVE_IRQ_ACK | GVE_IRQ_EVENT), irq_doorbell);
105
106 /* Double check we have no extra work.
107 * Ensure unmask synchronizes with checking for work.
108 */
109 dma_rmb();
110 if (block->tx)
111 reschedule |= gve_tx_poll(block, -1);
112 if (block->rx)
113 reschedule |= gve_rx_poll(block, -1);
114 if (reschedule && napi_reschedule(napi))
115 writel(cpu_to_be32(GVE_IRQ_MASK), irq_doorbell);
116
117 return 0;
118 }
119
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
^ permalink raw reply
* [RFC PATCH] gve: gve_napi_poll() can be static
From: kbuild test robot @ 2019-06-29 4:13 UTC (permalink / raw)
To: Catherine Sullivan
Cc: kbuild-all, netdev, Catherine Sullivan, Sagi Shahar, Jon Olson,
Willem de Bruijn, Luigi Rizzo
In-Reply-To: <20190626185251.205687-3-csully@google.com>
Fixes: fa090987329c ("gve: Add transmit and receive support")
Signed-off-by: kbuild test robot <lkp@intel.com>
---
gve_main.c | 6 +++---
gve_rx.c | 2 +-
gve_tx.c | 2 +-
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 966bcee..f226a18 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -81,7 +81,7 @@ static irqreturn_t gve_intr(int irq, void *arg)
return IRQ_HANDLED;
}
-int gve_napi_poll(struct napi_struct *napi, int budget)
+static int gve_napi_poll(struct napi_struct *napi, int budget)
{
struct gve_notify_block *block;
__be32 __iomem *irq_doorbell;
@@ -294,7 +294,7 @@ static void gve_teardown_device_resources(struct gve_priv *priv)
gve_clear_device_resources_ok(priv);
}
-void gve_add_napi(struct gve_priv *priv, int ntfy_idx)
+static void gve_add_napi(struct gve_priv *priv, int ntfy_idx)
{
struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
@@ -302,7 +302,7 @@ void gve_add_napi(struct gve_priv *priv, int ntfy_idx)
NAPI_POLL_WEIGHT);
}
-void gve_remove_napi(struct gve_priv *priv, int ntfy_idx)
+static void gve_remove_napi(struct gve_priv *priv, int ntfy_idx)
{
struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 5bcf250..37d6fef 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -8,7 +8,7 @@
#include "gve_adminq.h"
#include <linux/etherdevice.h>
-void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx)
+static void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx)
{
struct gve_notify_block *block =
&priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_idx)];
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index 221a2e7..c7b5c6d 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -142,7 +142,7 @@ static void gve_tx_remove_from_block(struct gve_priv *priv, int queue_idx)
static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
u32 to_do, bool try_to_wake);
-void gve_tx_free_ring(struct gve_priv *priv, int idx)
+static void gve_tx_free_ring(struct gve_priv *priv, int idx)
{
struct gve_tx_ring *tx = &priv->tx[idx];
struct device *hdev = &priv->pdev->dev;
^ permalink raw reply related
* [PATCH v4 bpf-next 9/9] selftests/bpf: convert existing tracepoint tests to new APIs
From: Andrii Nakryiko @ 2019-06-29 3:49 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629034906.1209916-1-andriin@fb.com>
Convert some existing tests that attach to tracepoints to use
bpf_program__attach_tracepoint API instead.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
---
.../bpf/prog_tests/stacktrace_build_id.c | 50 ++++---------------
.../selftests/bpf/prog_tests/stacktrace_map.c | 43 ++++------------
.../bpf/prog_tests/stacktrace_map_raw_tp.c | 15 ++++--
3 files changed, 31 insertions(+), 77 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
index 3aab2b083c71..768883d838ea 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
@@ -4,11 +4,13 @@
void test_stacktrace_build_id(void)
{
int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
+ const char *prog_name = "tracepoint/random/urandom_read";
const char *file = "./test_stacktrace_build_id.o";
- int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len;
- struct perf_event_attr attr = {};
+ int err, prog_fd, stack_trace_len;
__u32 key, previous_key, val, duration = 0;
+ struct bpf_program *prog;
struct bpf_object *obj;
+ struct bpf_link *link = NULL;
char buf[256];
int i, j;
struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
@@ -20,42 +22,14 @@ void test_stacktrace_build_id(void)
if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
goto out;
- /* Get the ID for the sched/sched_switch tracepoint */
- snprintf(buf, sizeof(buf),
- "/sys/kernel/debug/tracing/events/random/urandom_read/id");
- efd = open(buf, O_RDONLY, 0);
- if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
+ prog = bpf_object__find_program_by_title(obj, prog_name);
+ if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
goto close_prog;
- bytes = read(efd, buf, sizeof(buf));
- close(efd);
- if (CHECK(bytes <= 0 || bytes >= sizeof(buf),
- "read", "bytes %d errno %d\n", bytes, errno))
+ link = bpf_program__attach_tracepoint(prog, "random", "urandom_read");
+ if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link)))
goto close_prog;
- /* Open the perf event and attach bpf progrram */
- attr.config = strtol(buf, NULL, 0);
- attr.type = PERF_TYPE_TRACEPOINT;
- attr.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN;
- attr.sample_period = 1;
- attr.wakeup_events = 1;
- pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
- 0 /* cpu 0 */, -1 /* group id */,
- 0 /* flags */);
- if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
- pmu_fd, errno))
- goto close_prog;
-
- err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
- if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
- err, errno))
- goto close_pmu;
-
- err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
- if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
- err, errno))
- goto disable_pmu;
-
/* find map fds */
control_map_fd = bpf_find_map(__func__, obj, "control_map");
if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
@@ -133,8 +107,7 @@ void test_stacktrace_build_id(void)
* try it one more time.
*/
if (build_id_matches < 1 && retry--) {
- ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
- close(pmu_fd);
+ bpf_link__destroy(link);
bpf_object__close(obj);
printf("%s:WARN:Didn't find expected build ID from the map, retrying\n",
__func__);
@@ -152,10 +125,7 @@ void test_stacktrace_build_id(void)
"err %d errno %d\n", err, errno);
disable_pmu:
- ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
-
-close_pmu:
- close(pmu_fd);
+ bpf_link__destroy(link);
close_prog:
bpf_object__close(obj);
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
index 2bfd50a0d6d1..fc539335c5b3 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
@@ -4,50 +4,26 @@
void test_stacktrace_map(void)
{
int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
+ const char *prog_name = "tracepoint/sched/sched_switch";
+ int err, prog_fd, stack_trace_len;
const char *file = "./test_stacktrace_map.o";
- int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len;
- struct perf_event_attr attr = {};
__u32 key, val, duration = 0;
+ struct bpf_program *prog;
struct bpf_object *obj;
- char buf[256];
+ struct bpf_link *link;
err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
return;
- /* Get the ID for the sched/sched_switch tracepoint */
- snprintf(buf, sizeof(buf),
- "/sys/kernel/debug/tracing/events/sched/sched_switch/id");
- efd = open(buf, O_RDONLY, 0);
- if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
+ prog = bpf_object__find_program_by_title(obj, prog_name);
+ if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
goto close_prog;
- bytes = read(efd, buf, sizeof(buf));
- close(efd);
- if (bytes <= 0 || bytes >= sizeof(buf))
+ link = bpf_program__attach_tracepoint(prog, "sched", "sched_switch");
+ if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link)))
goto close_prog;
- /* Open the perf event and attach bpf progrram */
- attr.config = strtol(buf, NULL, 0);
- attr.type = PERF_TYPE_TRACEPOINT;
- attr.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN;
- attr.sample_period = 1;
- attr.wakeup_events = 1;
- pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
- 0 /* cpu 0 */, -1 /* group id */,
- 0 /* flags */);
- if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
- pmu_fd, errno))
- goto close_prog;
-
- err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
- if (err)
- goto disable_pmu;
-
- err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
- if (err)
- goto disable_pmu;
-
/* find map fds */
control_map_fd = bpf_find_map(__func__, obj, "control_map");
if (control_map_fd < 0)
@@ -96,8 +72,7 @@ void test_stacktrace_map(void)
disable_pmu:
error_cnt++;
disable_pmu_noerr:
- ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
- close(pmu_fd);
+ bpf_link__destroy(link);
close_prog:
bpf_object__close(obj);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
index 1f8387d80fd7..fbfa8e76cf63 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
@@ -3,18 +3,25 @@
void test_stacktrace_map_raw_tp(void)
{
+ const char *prog_name = "tracepoint/sched/sched_switch";
int control_map_fd, stackid_hmap_fd, stackmap_fd;
const char *file = "./test_stacktrace_map.o";
- int efd, err, prog_fd;
__u32 key, val, duration = 0;
+ int err, prog_fd;
+ struct bpf_program *prog;
struct bpf_object *obj;
+ struct bpf_link *link = NULL;
err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
return;
- efd = bpf_raw_tracepoint_open("sched_switch", prog_fd);
- if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+ prog = bpf_object__find_program_by_title(obj, prog_name);
+ if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
+ goto close_prog;
+
+ link = bpf_program__attach_raw_tracepoint(prog, "sched_switch");
+ if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
goto close_prog;
/* find map fds */
@@ -55,5 +62,7 @@ void test_stacktrace_map_raw_tp(void)
close_prog:
error_cnt++;
close_prog_noerr:
+ if (!IS_ERR_OR_NULL(link))
+ bpf_link__destroy(link);
bpf_object__close(obj);
}
--
2.17.1
^ permalink raw reply related
* [PATCH v4 bpf-next 7/9] selftests/bpf: switch test to new attach_perf_event API
From: Andrii Nakryiko @ 2019-06-29 3:49 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629034906.1209916-1-andriin@fb.com>
Use new bpf_program__attach_perf_event() in test previously relying on
direct ioctl manipulations.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
---
.../bpf/prog_tests/stacktrace_build_id_nmi.c | 31 +++++++++----------
1 file changed, 15 insertions(+), 16 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index 1c1a2f75f3d8..9557b7dfb782 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -17,6 +17,7 @@ static __u64 read_perf_max_sample_freq(void)
void test_stacktrace_build_id_nmi(void)
{
int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
+ const char *prog_name = "tracepoint/random/urandom_read";
const char *file = "./test_stacktrace_build_id.o";
int err, pmu_fd, prog_fd;
struct perf_event_attr attr = {
@@ -25,7 +26,9 @@ void test_stacktrace_build_id_nmi(void)
.config = PERF_COUNT_HW_CPU_CYCLES,
};
__u32 key, previous_key, val, duration = 0;
+ struct bpf_program *prog;
struct bpf_object *obj;
+ struct bpf_link *link;
char buf[256];
int i, j;
struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
@@ -39,6 +42,10 @@ void test_stacktrace_build_id_nmi(void)
if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
return;
+ prog = bpf_object__find_program_by_title(obj, prog_name);
+ if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
+ goto close_prog;
+
pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
0 /* cpu 0 */, -1 /* group id */,
0 /* flags */);
@@ -47,15 +54,12 @@ void test_stacktrace_build_id_nmi(void)
pmu_fd, errno))
goto close_prog;
- err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
- if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
- err, errno))
- goto close_pmu;
-
- err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
- if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
- err, errno))
- goto disable_pmu;
+ link = bpf_program__attach_perf_event(prog, pmu_fd);
+ if (CHECK(IS_ERR(link), "attach_perf_event",
+ "err %ld\n", PTR_ERR(link))) {
+ close(pmu_fd);
+ goto close_prog;
+ }
/* find map fds */
control_map_fd = bpf_find_map(__func__, obj, "control_map");
@@ -134,8 +138,7 @@ void test_stacktrace_build_id_nmi(void)
* try it one more time.
*/
if (build_id_matches < 1 && retry--) {
- ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
- close(pmu_fd);
+ bpf_link__destroy(link);
bpf_object__close(obj);
printf("%s:WARN:Didn't find expected build ID from the map, retrying\n",
__func__);
@@ -154,11 +157,7 @@ void test_stacktrace_build_id_nmi(void)
*/
disable_pmu:
- ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
-
-close_pmu:
- close(pmu_fd);
-
+ bpf_link__destroy(link);
close_prog:
bpf_object__close(obj);
}
--
2.17.1
^ permalink raw reply related
* [PATCH v4 bpf-next 8/9] selftests/bpf: add kprobe/uprobe selftests
From: Andrii Nakryiko @ 2019-06-29 3:49 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629034906.1209916-1-andriin@fb.com>
Add tests verifying kprobe/kretprobe/uprobe/uretprobe APIs work as
expected.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
---
.../selftests/bpf/prog_tests/attach_probe.c | 155 ++++++++++++++++++
.../selftests/bpf/progs/test_attach_probe.c | 55 +++++++
2 files changed, 210 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/attach_probe.c
create mode 100644 tools/testing/selftests/bpf/progs/test_attach_probe.c
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
new file mode 100644
index 000000000000..f22929063c58
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+ssize_t get_base_addr() {
+ size_t start;
+ char buf[256];
+ FILE *f;
+
+ f = fopen("/proc/self/maps", "r");
+ if (!f)
+ return -errno;
+
+ while (fscanf(f, "%zx-%*x %s %*s\n", &start, buf) == 2) {
+ if (strcmp(buf, "r-xp") == 0) {
+ fclose(f);
+ return start;
+ }
+ }
+
+ fclose(f);
+ return -EINVAL;
+}
+
+void test_attach_probe(void)
+{
+ const char *kprobe_name = "kprobe/sys_nanosleep";
+ const char *kretprobe_name = "kretprobe/sys_nanosleep";
+ const char *uprobe_name = "uprobe/trigger_func";
+ const char *uretprobe_name = "uretprobe/trigger_func";
+ const int kprobe_idx = 0, kretprobe_idx = 1;
+ const int uprobe_idx = 2, uretprobe_idx = 3;
+ const char *file = "./test_attach_probe.o";
+ struct bpf_program *kprobe_prog, *kretprobe_prog;
+ struct bpf_program *uprobe_prog, *uretprobe_prog;
+ struct bpf_object *obj;
+ int err, prog_fd, duration = 0, res;
+ struct bpf_link *kprobe_link = NULL;
+ struct bpf_link *kretprobe_link = NULL;
+ struct bpf_link *uprobe_link = NULL;
+ struct bpf_link *uretprobe_link = NULL;
+ int results_map_fd;
+ size_t uprobe_offset;
+ ssize_t base_addr;
+
+ base_addr = get_base_addr();
+ if (CHECK(base_addr < 0, "get_base_addr",
+ "failed to find base addr: %zd", base_addr))
+ return;
+ uprobe_offset = (size_t)&get_base_addr - base_addr;
+
+ /* load programs */
+ err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd);
+ if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
+ return;
+
+ kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name);
+ if (CHECK(!kprobe_prog, "find_probe",
+ "prog '%s' not found\n", kprobe_name))
+ goto cleanup;
+ kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name);
+ if (CHECK(!kretprobe_prog, "find_probe",
+ "prog '%s' not found\n", kretprobe_name))
+ goto cleanup;
+ uprobe_prog = bpf_object__find_program_by_title(obj, uprobe_name);
+ if (CHECK(!uprobe_prog, "find_probe",
+ "prog '%s' not found\n", uprobe_name))
+ goto cleanup;
+ uretprobe_prog = bpf_object__find_program_by_title(obj, uretprobe_name);
+ if (CHECK(!uretprobe_prog, "find_probe",
+ "prog '%s' not found\n", uretprobe_name))
+ goto cleanup;
+
+ /* load maps */
+ results_map_fd = bpf_find_map(__func__, obj, "results_map");
+ if (CHECK(results_map_fd < 0, "find_results_map",
+ "err %d\n", results_map_fd))
+ goto cleanup;
+
+ kprobe_link = bpf_program__attach_kprobe(kprobe_prog,
+ false /* retprobe */,
+ "sys_nanosleep");
+ if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
+ "err %ld\n", PTR_ERR(kprobe_link)))
+ goto cleanup;
+
+ kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog,
+ true /* retprobe */,
+ "sys_nanosleep");
+ if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe",
+ "err %ld\n", PTR_ERR(kretprobe_link)))
+ goto cleanup;
+
+ uprobe_link = bpf_program__attach_uprobe(uprobe_prog,
+ false /* retprobe */,
+ 0 /* self pid */,
+ "/proc/self/exe",
+ uprobe_offset);
+ if (CHECK(IS_ERR(uprobe_link), "attach_uprobe",
+ "err %ld\n", PTR_ERR(uprobe_link)))
+ goto cleanup;
+
+ uretprobe_link = bpf_program__attach_uprobe(uretprobe_prog,
+ true /* retprobe */,
+ -1 /* any pid */,
+ "/proc/self/exe",
+ uprobe_offset);
+ if (CHECK(IS_ERR(uretprobe_link), "attach_uretprobe",
+ "err %ld\n", PTR_ERR(uretprobe_link)))
+ goto cleanup;
+
+ /* trigger & validate kprobe && kretprobe */
+ usleep(1);
+
+ err = bpf_map_lookup_elem(results_map_fd, &kprobe_idx, &res);
+ if (CHECK(err, "get_kprobe_res",
+ "failed to get kprobe res: %d\n", err))
+ goto cleanup;
+ if (CHECK(res != kprobe_idx + 1, "check_kprobe_res",
+ "wrong kprobe res: %d\n", res))
+ goto cleanup;
+
+ err = bpf_map_lookup_elem(results_map_fd, &kretprobe_idx, &res);
+ if (CHECK(err, "get_kretprobe_res",
+ "failed to get kretprobe res: %d\n", err))
+ goto cleanup;
+ if (CHECK(res != kretprobe_idx + 1, "check_kretprobe_res",
+ "wrong kretprobe res: %d\n", res))
+ goto cleanup;
+
+ /* trigger & validate uprobe & uretprobe */
+ get_base_addr();
+
+ err = bpf_map_lookup_elem(results_map_fd, &uprobe_idx, &res);
+ if (CHECK(err, "get_uprobe_res",
+ "failed to get uprobe res: %d\n", err))
+ goto cleanup;
+ if (CHECK(res != uprobe_idx + 1, "check_uprobe_res",
+ "wrong uprobe res: %d\n", res))
+ goto cleanup;
+
+ err = bpf_map_lookup_elem(results_map_fd, &uretprobe_idx, &res);
+ if (CHECK(err, "get_uretprobe_res",
+ "failed to get uretprobe res: %d\n", err))
+ goto cleanup;
+ if (CHECK(res != uretprobe_idx + 1, "check_uretprobe_res",
+ "wrong uretprobe res: %d\n", res))
+ goto cleanup;
+
+cleanup:
+ bpf_link__destroy(kprobe_link);
+ bpf_link__destroy(kretprobe_link);
+ bpf_link__destroy(uprobe_link);
+ bpf_link__destroy(uretprobe_link);
+ bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
new file mode 100644
index 000000000000..7a7c5cd728c8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct {
+ int type;
+ int max_entries;
+ int *key;
+ int *value;
+} results_map SEC(".maps") = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .max_entries = 4,
+};
+
+SEC("kprobe/sys_nanosleep")
+int handle_sys_nanosleep_entry(struct pt_regs *ctx)
+{
+ const int key = 0, value = 1;
+
+ bpf_map_update_elem(&results_map, &key, &value, 0);
+ return 0;
+}
+
+SEC("kretprobe/sys_nanosleep")
+int handle_sys_getpid_return(struct pt_regs *ctx)
+{
+ const int key = 1, value = 2;
+
+ bpf_map_update_elem(&results_map, &key, &value, 0);
+ return 0;
+}
+
+SEC("uprobe/trigger_func")
+int handle_uprobe_entry(struct pt_regs *ctx)
+{
+ const int key = 2, value = 3;
+
+ bpf_map_update_elem(&results_map, &key, &value, 0);
+ return 0;
+}
+
+SEC("uretprobe/trigger_func")
+int handle_uprobe_return(struct pt_regs *ctx)
+{
+ const int key = 3, value = 4;
+
+ bpf_map_update_elem(&results_map, &key, &value, 0);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 bpf-next 6/9] libbpf: add raw tracepoint attach API
From: Andrii Nakryiko @ 2019-06-29 3:49 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629034906.1209916-1-andriin@fb.com>
Add a wrapper utilizing bpf_link "infrastructure" to allow attaching BPF
programs to raw tracepoints.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
---
tools/lib/bpf/libbpf.c | 37 +++++++++++++++++++++++++++++++++++++
tools/lib/bpf/libbpf.h | 3 +++
tools/lib/bpf/libbpf.map | 1 +
3 files changed, 41 insertions(+)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 8ad4f915df38..f8c7a7ecb35e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4263,6 +4263,43 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
return link;
}
+static int bpf_link__destroy_fd(struct bpf_link *link)
+{
+ struct bpf_link_fd *l = (void *)link;
+
+ return close(l->fd);
+}
+
+struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+ const char *tp_name)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link_fd *link;
+ int prog_fd, pfd;
+
+ prog_fd = bpf_program__fd(prog);
+ if (prog_fd < 0) {
+ pr_warning("program '%s': can't attach before loaded\n",
+ bpf_program__title(prog, false));
+ return ERR_PTR(-EINVAL);
+ }
+
+ link = malloc(sizeof(*link));
+ link->link.destroy = &bpf_link__destroy_fd;
+
+ pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
+ if (pfd < 0) {
+ pfd = -errno;
+ free(link);
+ pr_warning("program '%s': failed to attach to raw tracepoint '%s': %s\n",
+ bpf_program__title(prog, false), tp_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link->fd = pfd;
+ return (struct bpf_link *)link;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 60611f4b4e1d..f55933784f95 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -182,6 +182,9 @@ LIBBPF_API struct bpf_link *
bpf_program__attach_tracepoint(struct bpf_program *prog,
const char *tp_category,
const char *tp_name);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+ const char *tp_name);
struct bpf_insn;
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 3c618b75ef65..e6b7d4edbc93 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -171,6 +171,7 @@ LIBBPF_0.0.4 {
bpf_object__load_xattr;
bpf_program__attach_kprobe;
bpf_program__attach_perf_event;
+ bpf_program__attach_raw_tracepoint;
bpf_program__attach_tracepoint;
bpf_program__attach_uprobe;
btf_dump__dump_type;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 bpf-next 5/9] libbpf: add tracepoint attach API
From: Andrii Nakryiko @ 2019-06-29 3:49 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629034906.1209916-1-andriin@fb.com>
Allow attaching BPF programs to kernel tracepoint BPF hooks specified by
category and name.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
---
tools/lib/bpf/libbpf.c | 79 ++++++++++++++++++++++++++++++++++++++++
tools/lib/bpf/libbpf.h | 4 ++
tools/lib/bpf/libbpf.map | 1 +
3 files changed, 84 insertions(+)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2f79e9563db9..8ad4f915df38 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4184,6 +4184,85 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
return link;
}
+static int determine_tracepoint_id(const char *tp_category,
+ const char *tp_name)
+{
+ char file[PATH_MAX];
+ int ret;
+
+ ret = snprintf(file, sizeof(file),
+ "/sys/kernel/debug/tracing/events/%s/%s/id",
+ tp_category, tp_name);
+ if (ret < 0)
+ return -errno;
+ if (ret >= sizeof(file)) {
+ pr_debug("tracepoint %s/%s path is too long\n",
+ tp_category, tp_name);
+ return -E2BIG;
+ }
+ return parse_value_from_file(file, "%d\n");
+}
+
+static int perf_event_open_tracepoint(const char *tp_category,
+ const char *tp_name)
+{
+ struct perf_event_attr attr = {};
+ char errmsg[STRERR_BUFSIZE];
+ int tp_id, pfd, err;
+
+ tp_id = determine_tracepoint_id(tp_category, tp_name);
+ if (tp_id < 0) {
+ pr_warning("failed to determine tracepoint '%s/%s' perf ID: %s\n",
+ tp_category, tp_name,
+ libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg)));
+ return tp_id;
+ }
+
+ attr.type = PERF_TYPE_TRACEPOINT;
+ attr.size = sizeof(attr);
+ attr.config = tp_id;
+
+ pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */,
+ -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC);
+ if (pfd < 0) {
+ err = -errno;
+ pr_warning("tracepoint '%s/%s' perf_event_open() failed: %s\n",
+ tp_category, tp_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return err;
+ }
+ return pfd;
+}
+
+struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
+ const char *tp_category,
+ const char *tp_name)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int pfd, err;
+
+ pfd = perf_event_open_tracepoint(tp_category, tp_name);
+ if (pfd < 0) {
+ pr_warning("program '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
+ bpf_program__title(prog, false),
+ tp_category, tp_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link = bpf_program__attach_perf_event(prog, pfd);
+ if (IS_ERR(link)) {
+ close(pfd);
+ err = PTR_ERR(link);
+ pr_warning("program '%s': failed to attach to tracepoint '%s/%s': %s\n",
+ bpf_program__title(prog, false),
+ tp_category, tp_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return link;
+ }
+ return link;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index bd767cc11967..60611f4b4e1d 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -178,6 +178,10 @@ LIBBPF_API struct bpf_link *
bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe,
pid_t pid, const char *binary_path,
size_t func_offset);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_tracepoint(struct bpf_program *prog,
+ const char *tp_category,
+ const char *tp_name);
struct bpf_insn;
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 57a40fb60718..3c618b75ef65 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -171,6 +171,7 @@ LIBBPF_0.0.4 {
bpf_object__load_xattr;
bpf_program__attach_kprobe;
bpf_program__attach_perf_event;
+ bpf_program__attach_tracepoint;
bpf_program__attach_uprobe;
btf_dump__dump_type;
btf_dump__free;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 bpf-next 4/9] libbpf: add kprobe/uprobe attach API
From: Andrii Nakryiko @ 2019-06-29 3:49 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629034906.1209916-1-andriin@fb.com>
Add ability to attach to kernel and user probes and retprobes.
Implementation depends on perf event support for kprobes/uprobes.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
tools/lib/bpf/libbpf.c | 165 +++++++++++++++++++++++++++++++++++++++
tools/lib/bpf/libbpf.h | 7 ++
tools/lib/bpf/libbpf.map | 2 +
3 files changed, 174 insertions(+)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 98c155ec3bfa..2f79e9563db9 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4019,6 +4019,171 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
return (struct bpf_link *)link;
}
+static int parse_value_from_file(const char *file, const char *fmt)
+{
+ char buf[STRERR_BUFSIZE];
+ int err, ret;
+ FILE *f;
+
+ f = fopen(file, "r");
+ if (!f) {
+ err = -errno;
+ pr_debug("failed to open '%s': %s\n", file,
+ libbpf_strerror_r(err, buf, sizeof(buf)));
+ fclose(f);
+ return err;
+ }
+ err = fscanf(f, fmt, &ret);
+ if (err != 1) {
+ err = err == EOF ? -EIO : -errno;
+ pr_debug("failed to parse '%s': %s\n", file,
+ libbpf_strerror_r(err, buf, sizeof(buf)));
+ fclose(f);
+ return err;
+ }
+ fclose(f);
+ return ret;
+}
+
+static int determine_kprobe_perf_type(void)
+{
+ const char *file = "/sys/bus/event_source/devices/kprobe/type";
+
+ return parse_value_from_file(file, "%d\n");
+}
+
+static int determine_uprobe_perf_type(void)
+{
+ const char *file = "/sys/bus/event_source/devices/uprobe/type";
+
+ return parse_value_from_file(file, "%d\n");
+}
+
+static int determine_kprobe_retprobe_bit(void)
+{
+ const char *file = "/sys/bus/event_source/devices/kprobe/format/retprobe";
+
+ return parse_value_from_file(file, "config:%d\n");
+}
+
+static int determine_uprobe_retprobe_bit(void)
+{
+ const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe";
+
+ return parse_value_from_file(file, "config:%d\n");
+}
+
+static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
+ uint64_t offset, int pid)
+{
+ struct perf_event_attr attr = {};
+ char errmsg[STRERR_BUFSIZE];
+ int type, pfd, err;
+
+ type = uprobe ? determine_uprobe_perf_type()
+ : determine_kprobe_perf_type();
+ if (type < 0) {
+ pr_warning("failed to determine %s perf type: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(type, errmsg, sizeof(errmsg)));
+ return type;
+ }
+ if (retprobe) {
+ int bit = uprobe ? determine_uprobe_retprobe_bit()
+ : determine_kprobe_retprobe_bit();
+
+ if (bit < 0) {
+ pr_warning("failed to determine %s retprobe bit: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(bit, errmsg,
+ sizeof(errmsg)));
+ return bit;
+ }
+ attr.config |= 1 << bit;
+ }
+ attr.size = sizeof(attr);
+ attr.type = type;
+ attr.config1 = (uint64_t)(void *)name; /* kprobe_func or uprobe_path */
+ attr.config2 = offset; /* kprobe_addr or probe_offset */
+
+ /* pid filter is meaningful only for uprobes */
+ pfd = syscall(__NR_perf_event_open, &attr,
+ pid < 0 ? -1 : pid /* pid */,
+ pid == -1 ? 0 : -1 /* cpu */,
+ -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC);
+ if (pfd < 0) {
+ err = -errno;
+ pr_warning("%s perf_event_open() failed: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return err;
+ }
+ return pfd;
+}
+
+struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
+ bool retprobe,
+ const char *func_name)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int pfd, err;
+
+ pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
+ 0 /* offset */, -1 /* pid */);
+ if (pfd < 0) {
+ pr_warning("program '%s': failed to create %s '%s' perf event: %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "kretprobe" : "kprobe", func_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link = bpf_program__attach_perf_event(prog, pfd);
+ if (IS_ERR(link)) {
+ close(pfd);
+ err = PTR_ERR(link);
+ pr_warning("program '%s': failed to attach to %s '%s': %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "kretprobe" : "kprobe", func_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return link;
+ }
+ return link;
+}
+
+struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
+ bool retprobe, pid_t pid,
+ const char *binary_path,
+ size_t func_offset)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int pfd, err;
+
+ pfd = perf_event_open_probe(true /* uprobe */, retprobe,
+ binary_path, func_offset, pid);
+ if (pfd < 0) {
+ pr_warning("program '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "uretprobe" : "uprobe",
+ binary_path, func_offset,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link = bpf_program__attach_perf_event(prog, pfd);
+ if (IS_ERR(link)) {
+ close(pfd);
+ err = PTR_ERR(link);
+ pr_warning("program '%s': failed to attach to %s '%s:0x%zx': %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "uretprobe" : "uprobe",
+ binary_path, func_offset,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return link;
+ }
+ return link;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1bf66c4a9330..bd767cc11967 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -171,6 +171,13 @@ LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
LIBBPF_API struct bpf_link *
bpf_program__attach_perf_event(struct bpf_program *prog, int pfd);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe,
+ const char *func_name);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe,
+ pid_t pid, const char *binary_path,
+ size_t func_offset);
struct bpf_insn;
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 756f5aa802e9..57a40fb60718 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -169,7 +169,9 @@ LIBBPF_0.0.4 {
global:
bpf_link__destroy;
bpf_object__load_xattr;
+ bpf_program__attach_kprobe;
bpf_program__attach_perf_event;
+ bpf_program__attach_uprobe;
btf_dump__dump_type;
btf_dump__free;
btf_dump__new;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 bpf-next 3/9] libbpf: add ability to attach/detach BPF program to perf event
From: Andrii Nakryiko @ 2019-06-29 3:49 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629034906.1209916-1-andriin@fb.com>
bpf_program__attach_perf_event allows to attach BPF program to existing
perf event hook, providing most generic and most low-level way to attach BPF
programs. It returns struct bpf_link, which should be passed to
bpf_link__destroy to detach and free resources, associated with a link.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
tools/lib/bpf/libbpf.c | 61 ++++++++++++++++++++++++++++++++++++++++
tools/lib/bpf/libbpf.h | 3 ++
tools/lib/bpf/libbpf.map | 1 +
3 files changed, 65 insertions(+)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 455795e6f8af..98c155ec3bfa 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -32,6 +32,7 @@
#include <linux/limits.h>
#include <linux/perf_event.h>
#include <linux/ring_buffer.h>
+#include <sys/ioctl.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
@@ -3958,6 +3959,66 @@ int bpf_link__destroy(struct bpf_link *link)
return err;
}
+struct bpf_link_fd {
+ struct bpf_link link; /* has to be at the top of struct */
+ int fd; /* hook FD */
+};
+
+static int bpf_link__destroy_perf_event(struct bpf_link *link)
+{
+ struct bpf_link_fd *l = (void *)link;
+ int err;
+
+ if (l->fd < 0)
+ return 0;
+
+ err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0);
+ if (err)
+ err = -errno;
+
+ close(l->fd);
+ return err;
+}
+
+struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
+ int pfd)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link_fd *link;
+ int prog_fd, err;
+
+ prog_fd = bpf_program__fd(prog);
+ if (prog_fd < 0) {
+ pr_warning("program '%s': can't attach before loaded\n",
+ bpf_program__title(prog, false));
+ return ERR_PTR(-EINVAL);
+ }
+
+ link = malloc(sizeof(*link));
+ if (!link)
+ return ERR_PTR(-ENOMEM);
+ link->link.destroy = &bpf_link__destroy_perf_event;
+ link->fd = pfd;
+
+ if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
+ err = -errno;
+ free(link);
+ pr_warning("program '%s': failed to attach to pfd %d: %s\n",
+ bpf_program__title(prog, false), pfd,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return ERR_PTR(err);
+ }
+ if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
+ err = -errno;
+ free(link);
+ pr_warning("program '%s': failed to enable pfd %d: %s\n",
+ bpf_program__title(prog, false), pfd,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return ERR_PTR(err);
+ }
+ return (struct bpf_link *)link;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 5082a5ebb0c2..1bf66c4a9330 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -169,6 +169,9 @@ struct bpf_link;
LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_perf_event(struct bpf_program *prog, int pfd);
+
struct bpf_insn;
/*
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 3cde850fc8da..756f5aa802e9 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -169,6 +169,7 @@ LIBBPF_0.0.4 {
global:
bpf_link__destroy;
bpf_object__load_xattr;
+ bpf_program__attach_perf_event;
btf_dump__dump_type;
btf_dump__free;
btf_dump__new;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 bpf-next 2/9] libbpf: introduce concept of bpf_link
From: Andrii Nakryiko @ 2019-06-29 3:48 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629034906.1209916-1-andriin@fb.com>
bpf_link is and abstraction of an association of a BPF program and one
of many possible BPF attachment points (hooks). This allows to have
uniform interface for detaching BPF programs regardless of the nature of
link and how it was created. Details of creation and setting up of
a specific bpf_link is handled by corresponding attachment methods
(bpf_program__attach_xxx) added in subsequent commits. Once successfully
created, bpf_link has to be eventually destroyed with
bpf_link__destroy(), at which point BPF program is disassociated from
a hook and all the relevant resources are freed.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
---
tools/lib/bpf/libbpf.c | 17 +++++++++++++++++
tools/lib/bpf/libbpf.h | 4 ++++
tools/lib/bpf/libbpf.map | 3 ++-
3 files changed, 23 insertions(+), 1 deletion(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6e6ebef11ba3..455795e6f8af 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3941,6 +3941,23 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
return 0;
}
+struct bpf_link {
+ int (*destroy)(struct bpf_link *link);
+};
+
+int bpf_link__destroy(struct bpf_link *link)
+{
+ int err;
+
+ if (!link)
+ return 0;
+
+ err = link->destroy(link);
+ free(link);
+
+ return err;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index d639f47e3110..5082a5ebb0c2 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -165,6 +165,10 @@ LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
+struct bpf_link;
+
+LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
+
struct bpf_insn;
/*
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 2c6d835620d2..3cde850fc8da 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -167,10 +167,11 @@ LIBBPF_0.0.3 {
LIBBPF_0.0.4 {
global:
+ bpf_link__destroy;
+ bpf_object__load_xattr;
btf_dump__dump_type;
btf_dump__free;
btf_dump__new;
btf__parse_elf;
- bpf_object__load_xattr;
libbpf_num_possible_cpus;
} LIBBPF_0.0.3;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 bpf-next 1/9] libbpf: make libbpf_strerror_r agnostic to sign of error
From: Andrii Nakryiko @ 2019-06-29 3:48 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
In-Reply-To: <20190629034906.1209916-1-andriin@fb.com>
It's often inconvenient to switch sign of error when passing it into
libbpf_strerror_r. It's better for it to handle that automatically.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
---
tools/lib/bpf/str_error.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index 00e48ac5b806..b8064eedc177 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -11,7 +11,7 @@
*/
char *libbpf_strerror_r(int err, char *dst, int len)
{
- int ret = strerror_r(err, dst, len);
+ int ret = strerror_r(err < 0 ? -err : err, dst, len);
if (ret)
snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
return dst;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 bpf-next 0/9] libbpf: add bpf_link and tracing attach APIs
From: Andrii Nakryiko @ 2019-06-29 3:48 UTC (permalink / raw)
To: andrii.nakryiko, bpf, netdev, ast, daniel, kernel-team, sdf,
songliubraving
Cc: Andrii Nakryiko
This patchset adds the following APIs to allow attaching BPF programs to
tracing entities:
- bpf_program__attach_perf_event for attaching to any opened perf event FD,
allowing users full control;
- bpf_program__attach_kprobe for attaching to kernel probes (both entry and
return probes);
- bpf_program__attach_uprobe for attaching to user probes (both entry/return);
- bpf_program__attach_tracepoint for attaching to kernel tracepoints;
- bpf_program__attach_raw_tracepoint for attaching to raw kernel tracepoint
(wrapper around bpf_raw_tracepoint_open);
This set of APIs makes libbpf more useful for tracing applications.
All attach APIs return abstract struct bpf_link that encapsulates logic of
detaching BPF program. See patch #2 for details. bpf_assoc was considered as
an alternative name for this opaque "handle", but bpf_link seems to be
appropriate semantically and is nice and short.
Pre-patch #1 makes internal libbpf_strerror_r helper function work w/ negative
error codes, lifting the burder off callers to keep track of error sign.
Patch #2 adds bpf_link abstraction.
Patch #3 adds attach_perf_event, which is the base for all other APIs.
Patch #4 adds kprobe/uprobe APIs.
Patch #5 adds tracepoint API.
Patch #6 adds raw_tracepoint API.
Patch #7 converts one existing test to use attach_perf_event.
Patch #8 adds new kprobe/uprobe tests.
Patch #9 converts some selftests currently using tracepoint to new APIs.
v3->v4:
- proper errno handling (Stanislav);
- bpf_fd -> prog_fd (Stanislav);
- switch to fprintf (Song);
v2->v3:
- added bpf_link concept (Daniel);
- didn't add generic bpf_link__attach_program for reasons described in [0];
- dropped Stanislav's Reviewed-by from patches #2-#6, in case he doesn't like
the change;
v1->v2:
- preserve errno before close() call (Stanislav);
- use libbpf_perf_event_disable_and_close in selftest (Stanislav);
- remove unnecessary memset (Stanislav);
[0] https://lore.kernel.org/bpf/CAEf4BzZ7EM5eP2eaZn7T2Yb5QgVRiwAs+epeLR1g01TTx-6m6Q@mail.gmail.com/
Andrii Nakryiko (9):
libbpf: make libbpf_strerror_r agnostic to sign of error
libbpf: introduce concept of bpf_link
libbpf: add ability to attach/detach BPF program to perf event
libbpf: add kprobe/uprobe attach API
libbpf: add tracepoint attach API
libbpf: add raw tracepoint attach API
selftests/bpf: switch test to new attach_perf_event API
selftests/bpf: add kprobe/uprobe selftests
selftests/bpf: convert existing tracepoint tests to new APIs
tools/lib/bpf/libbpf.c | 359 ++++++++++++++++++
tools/lib/bpf/libbpf.h | 21 +
tools/lib/bpf/libbpf.map | 8 +-
tools/lib/bpf/str_error.c | 2 +-
.../selftests/bpf/prog_tests/attach_probe.c | 155 ++++++++
.../bpf/prog_tests/stacktrace_build_id.c | 50 +--
.../bpf/prog_tests/stacktrace_build_id_nmi.c | 31 +-
.../selftests/bpf/prog_tests/stacktrace_map.c | 43 +--
.../bpf/prog_tests/stacktrace_map_raw_tp.c | 15 +-
.../selftests/bpf/progs/test_attach_probe.c | 55 +++
10 files changed, 644 insertions(+), 95 deletions(-)
create mode 100644 tools/testing/selftests/bpf/prog_tests/attach_probe.c
create mode 100644 tools/testing/selftests/bpf/progs/test_attach_probe.c
--
2.17.1
^ permalink raw reply
* Re: [PATCH 1/2] tls: remove close callback sock unlock/lock and flush_sync
From: Jakub Kicinski @ 2019-06-29 3:46 UTC (permalink / raw)
To: John Fastabend; +Cc: daniel, ast, netdev, edumazet, bpf
In-Reply-To: <20190628175925.79a763f5@cakuba.netronome.com>
On Fri, 28 Jun 2019 17:59:25 -0700, Jakub Kicinski wrote:
> > > Sorry for all the questions, I'm not really able to fully wrap my head
> > > around this. I also feel like I'm missing the sockmap piece that may
> > > be why you prefer unhash over disconnect.
> >
> > Yep, if we try to support listening sockets we need a some more
> > core infrastructure to push around ulp and user_data portions of
> > sockets. Its not going to be nice for stable. Also at least in TLS
> > and sockmap case its not really needed for any use case I know
> > of.
>
> IIUC we can't go from ESTABLISHED to LISTEN without calling close()
> or disconnect() so I'm not clear on why are we hooking into unhash() 😕
Ah, disconnect() is also called with the socket already locked.
So no BH, but still not great..
^ permalink raw reply
* Re: [net-next 4/4] gve: Add ethtool support
From: Florian Fainelli @ 2019-06-29 2:44 UTC (permalink / raw)
To: Catherine Sullivan, netdev
Cc: Sagi Shahar, Jon Olson, Willem de Bruijn, Luigi Rizzo
In-Reply-To: <20190626185251.205687-5-csully@google.com>
On 6/26/2019 11:52 AM, Catherine Sullivan wrote:
[snip]
> +static void
> +gve_get_ethtool_stats(struct net_device *netdev,
> + struct ethtool_stats *stats, u64 *data)
> +{
> + struct gve_priv *priv = netdev_priv(netdev);
> + u64 rx_pkts, rx_bytes, tx_pkts, tx_bytes;
> + int ring;
> + int i;
> +
> + ASSERT_RTNL();
> +
> + if (!netif_carrier_ok(netdev))
> + return;
> +
> + for (rx_pkts = 0, rx_bytes = 0, ring = 0;
> + ring < priv->rx_cfg.num_queues; ring++) {
> + rx_pkts += priv->rx[ring].rpackets;
> + rx_bytes += priv->rx[ring].rbytes;
> + }
> + for (tx_pkts = 0, tx_bytes = 0, ring = 0;
> + ring < priv->tx_cfg.num_queues; ring++) {
> + tx_pkts += priv->tx[ring].pkt_done;
> + tx_bytes += priv->tx[ring].bytes_done;
> + }
Maybe you do not need to support 32-bit guests with that driver, but you
might as well be correct and use the include/linux/u64_stats_sync.h
primitives to help return consistent 64-bit stats on 32-bit machines.
[snip]
> +int gve_adjust_queues(struct gve_priv *priv,
> + struct gve_queue_config new_rx_config,
> + struct gve_queue_config new_tx_config)
> +{
> + int err;
> +
> + if (netif_carrier_ok(priv->dev)) {
Should not that be netif_running()?
--
Florian
^ permalink raw reply
* Re: [net-next 1/4] gve: Add basic driver framework for Compute Engine Virtual NIC
From: kbuild test robot @ 2019-06-29 2:21 UTC (permalink / raw)
To: Catherine Sullivan
Cc: kbuild-all, netdev, Catherine Sullivan, Sagi Shahar, Jon Olson,
Willem de Bruijn, Luigi Rizzo
In-Reply-To: <20190626185251.205687-2-csully@google.com>
Hi Catherine,
I love your patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
url: https://github.com/0day-ci/linux/commits/Catherine-Sullivan/Add-gve-driver/20190629-070444
reproduce:
# apt-get install sparse
# sparse version: v0.6.1-rc1-7-g2b96cd8-dirty
make ARCH=x86_64 allmodconfig
make C=1 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__'
If you fix the issue, kindly add following tag
Reported-by: kbuild test robot <lkp@intel.com>
sparse warnings: (new ones prefixed by >>)
drivers/net/ethernet/google/gve/gve_main.c:23:12: sparse: sparse: symbol 'gve_version_str' was not declared. Should it be static?
>> drivers/net/ethernet/google/gve/gve_main.c:24:12: sparse: sparse: symbol 'gve_version_prefix' was not declared. Should it be static?
>> drivers/net/ethernet/google/gve/gve_main.c:352:25: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_main.c:352:25: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_main.c:352:25: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_main.c:352:25: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_main.c:352:25: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_main.c:352:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:353:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:353:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:353:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:353:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:353:25: sparse: sparse: cast to restricted __be32
drivers/net/ethernet/google/gve/gve_main.c:353:25: sparse: sparse: cast to restricted __be32
--
>> drivers/net/ethernet/google/gve/gve_adminq.c:28:16: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
>> drivers/net/ethernet/google/gve/gve_adminq.c:28:16: sparse: expected unsigned int val
>> drivers/net/ethernet/google/gve/gve_adminq.c:28:16: sparse: got restricted __be32 [usertype]
drivers/net/ethernet/google/gve/gve_adminq.c:68:16: sparse: sparse: incorrect type in argument 1 (different base types) @@ expected unsigned int val @@ got restricted __be3unsigned int val @@
drivers/net/ethernet/google/gve/gve_adminq.c:68:16: sparse: expected unsigned int val
drivers/net/ethernet/google/gve/gve_adminq.c:68:16: sparse: got restricted __be32 [usertype]
>> drivers/net/ethernet/google/gve/gve_adminq.c:77:21: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_adminq.c:77:21: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_adminq.c:77:21: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_adminq.c:77:21: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_adminq.c:77:21: sparse: sparse: cast to restricted __be32
>> drivers/net/ethernet/google/gve/gve_adminq.c:77:21: sparse: sparse: cast to restricted __be32
Please review and possibly fold the followup patch.
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
^ permalink raw reply
* [RFC PATCH] gve: gve_version_prefix[] can be static
From: kbuild test robot @ 2019-06-29 2:21 UTC (permalink / raw)
To: Catherine Sullivan
Cc: kbuild-all, netdev, Catherine Sullivan, Sagi Shahar, Jon Olson,
Willem de Bruijn, Luigi Rizzo
In-Reply-To: <20190626185251.205687-2-csully@google.com>
Fixes: ac22601d5bb7 ("gve: Add basic driver framework for Compute Engine Virtual NIC")
Signed-off-by: kbuild test robot <lkp@intel.com>
---
gve_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index aa0428ef..505ca2c 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -21,7 +21,7 @@
#define GVE_VERSION_PREFIX "GVE-"
const char gve_version_str[] = GVE_VERSION;
-const char gve_version_prefix[] = GVE_VERSION_PREFIX;
+static const char gve_version_prefix[] = GVE_VERSION_PREFIX;
static int gve_alloc_counter_array(struct gve_priv *priv)
{
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox