forked from TencentOS/TencentOS-kernel
48710c8137
[upstream commit b00628b1c7d595ae5b544e059c27b1f5828314b4]
Introduce 'struct bpf_timer { __u64 :64; __u64 :64; };' that can be embedded
in hash/array/lru maps as a regular field and helpers to operate on it:
// Initialize the timer.
// First 4 bits of 'flags' specify clockid.
// Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed.
long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, int flags);
// Configure the timer to call 'callback_fn' static function.
long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn);
// Arm the timer to expire 'nsec' nanoseconds from the current time.
long bpf_timer_start(struct bpf_timer *timer, u64 nsec, u64 flags);
// Cancel the timer and wait for callback_fn to finish if it was running.
long bpf_timer_cancel(struct bpf_timer *timer);
Here is how BPF program might look like:
struct map_elem {
int counter;
struct bpf_timer timer;
};
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(max_entries, 1000);
__type(key, int);
__type(value, struct map_elem);
} hmap SEC(".maps");
static int timer_cb(void *map, int *key, struct map_elem *val);
/* val points to particular map element that contains bpf_timer. */
SEC("fentry/bpf_fentry_test1")
int BPF_PROG(test1, int a)
{
struct map_elem *val;
int key = 0;
val = bpf_map_lookup_elem(&hmap, &key);
if (val) {
bpf_timer_init(&val->timer, &hmap, CLOCK_REALTIME);
bpf_timer_set_callback(&val->timer, timer_cb);
bpf_timer_start(&val->timer, 1000 /* call timer_cb2 in 1 usec */, 0);
}
}
This patch adds helper implementations that rely on hrtimers
to call bpf functions as timers expire.
The following patches add necessary safety checks.
Only programs with CAP_BPF are allowed to use bpf_timer.
The amount of timers used by the program is constrained by
the memcg recorded at map creation time.
The bpf_timer_init() helper needs explicit 'map' argument because inner maps
are dynamic and not known at load time. While the bpf_timer_set_callback() is
receiving hidden 'aux->prog' argument supplied by the verifier.
The prog pointer is needed to do refcnting of bpf program to make sure that
program doesn't get freed while the timer is armed. This approach relies on
"user refcnt" scheme used in prog_array that stores bpf programs for
bpf_tail_call. The bpf_timer_set_callback() will increment the prog refcnt which is
paired with bpf_timer_cancel() that will drop the prog refcnt. The
ops->map_release_uref is responsible for cancelling the timers and dropping
prog refcnt when user space reference to a map reaches zero.
This uref approach is done to make sure that Ctrl-C of user space process will
not leave timers running forever unless the user space explicitly pinned a map
that contained timers in bpffs.
bpf_timer_init() and bpf_timer_set_callback() will return -EPERM if map doesn't
have user references (is not held by open file descriptor from user space and
not pinned in bpffs).
The bpf_map_delete_elem() and bpf_map_update_elem() operations cancel
and free the timer if given map element had it allocated.
"bpftool map update" command can be used to cancel timers.
The 'struct bpf_timer' is explicitly __attribute__((aligned(8))) because
'__u64 :64' has 1 byte alignment of 8 byte padding.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210715005417.78572-4-alexei.starovoitov@gmail.com
|
||
|---|---|---|
| .. | ||
| Kconfig | ||
| Makefile | ||
| blktrace.c | ||
| bpf_trace.c | ||
| fgraph.c | ||
| ftrace.c | ||
| ftrace_internal.h | ||
| power-traces.c | ||
| preemptirq_delay_test.c | ||
| ring_buffer.c | ||
| ring_buffer_benchmark.c | ||
| rpm-traces.c | ||
| trace.c | ||
| trace.h | ||
| trace_benchmark.c | ||
| trace_benchmark.h | ||
| trace_branch.c | ||
| trace_clock.c | ||
| trace_dynevent.c | ||
| trace_dynevent.h | ||
| trace_entries.h | ||
| trace_event_perf.c | ||
| trace_events.c | ||
| trace_events_filter.c | ||
| trace_events_filter_test.h | ||
| trace_events_hist.c | ||
| trace_events_trigger.c | ||
| trace_export.c | ||
| trace_functions.c | ||
| trace_functions_graph.c | ||
| trace_hwlat.c | ||
| trace_irqsoff.c | ||
| trace_kdb.c | ||
| trace_kprobe.c | ||
| trace_kprobe_selftest.c | ||
| trace_kprobe_selftest.h | ||
| trace_mmiotrace.c | ||
| trace_nop.c | ||
| trace_output.c | ||
| trace_output.h | ||
| trace_preemptirq.c | ||
| trace_printk.c | ||
| trace_probe.c | ||
| trace_probe.h | ||
| trace_probe_tmpl.h | ||
| trace_sched_switch.c | ||
| trace_sched_wakeup.c | ||
| trace_selftest.c | ||
| trace_selftest_dynamic.c | ||
| trace_seq.c | ||
| trace_stack.c | ||
| trace_stat.c | ||
| trace_stat.h | ||
| trace_syscalls.c | ||
| trace_uprobe.c | ||
| tracing_map.c | ||
| tracing_map.h | ||