bpf: Introduce bpf timers.

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 <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Acked-by: Martin KaFai Lau <[email protected]>
Acked-by: Andrii Nakryiko <[email protected]>
Acked-by: Toke Høiland-Jørgensen <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: Alexei Starovoitov

include/linux/bpf.h

@@ -168,6 +168,7 @@ struct bpf_map {
 	u32 max_entries;
 	u32 map_flags;
 	int spin_lock_off; /* >=0 valid offset, <0 error */
+	int timer_off; /* >=0 valid offset, <0 error */
 	u32 id;
 	int numa_node;
 	u32 btf_key_type_id;
@@ -221,6 +222,7 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
 }
 void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
 			   bool lock_src);
+void bpf_timer_cancel_and_free(void *timer);
 int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size);
 
 struct bpf_offload_dev;
@@ -314,6 +316,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_FUNC,	/* pointer to a bpf program function */
 	ARG_PTR_TO_STACK_OR_NULL,	/* pointer to stack or NULL */
 	ARG_PTR_TO_CONST_STR,	/* pointer to a null terminated read-only string */
+	ARG_PTR_TO_TIMER,	/* pointer to bpf_timer */
 	__BPF_ARG_TYPE_MAX,
 };
 

include/uapi/linux/bpf.h

@@ -4777,6 +4777,70 @@ union bpf_attr {
  * 		Execute close syscall for given FD.
  * 	Return
  * 		A syscall result.
+ *
+ * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags)
+ *	Description
+ *		Initialize the timer.
+ *		First 4 bits of *flags* specify clockid.
+ *		Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed.
+ *		All other bits of *flags* are reserved.
+ *		The verifier will reject the program if *timer* is not from
+ *		the same *map*.
+ *	Return
+ *		0 on success.
+ *		**-EBUSY** if *timer* is already initialized.
+ *		**-EINVAL** if invalid *flags* are passed.
+ *		**-EPERM** if *timer* is in a map that doesn't have any user references.
+ *		The user space should either hold a file descriptor to a map with timers
+ *		or pin such map in bpffs. When map is unpinned or file descriptor is
+ *		closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn)
+ *	Description
+ *		Configure the timer to call *callback_fn* static function.
+ *	Return
+ *		0 on success.
+ *		**-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ *		**-EPERM** if *timer* is in a map that doesn't have any user references.
+ *		The user space should either hold a file descriptor to a map with timers
+ *		or pin such map in bpffs. When map is unpinned or file descriptor is
+ *		closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags)
+ *	Description
+ *		Set timer expiration N nanoseconds from the current time. The
+ *		configured callback will be invoked in soft irq context on some cpu
+ *		and will not repeat unless another bpf_timer_start() is made.
+ *		In such case the next invocation can migrate to a different cpu.
+ *		Since struct bpf_timer is a field inside map element the map
+ *		owns the timer. The bpf_timer_set_callback() will increment refcnt
+ *		of BPF program to make sure that callback_fn code stays valid.
+ *		When user space reference to a map reaches zero all timers
+ *		in a map are cancelled and corresponding program's refcnts are
+ *		decremented. This is done to make sure that Ctrl-C of a user
+ *		process doesn't leave any timers running. If map is pinned in
+ *		bpffs the callback_fn can re-arm itself indefinitely.
+ *		bpf_map_update/delete_elem() helpers and user space sys_bpf commands
+ *		cancel and free the timer in the given map element.
+ *		The map can contain timers that invoke callback_fn-s from different
+ *		programs. The same callback_fn can serve different timers from
+ *		different maps if key/value layout matches across maps.
+ *		Every bpf_timer_set_callback() can have different callback_fn.
+ *
+ *	Return
+ *		0 on success.
+ *		**-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier
+ *		or invalid *flags* are passed.
+ *
+ * long bpf_timer_cancel(struct bpf_timer *timer)
+ *	Description
+ *		Cancel the timer and wait for callback_fn to finish if it was running.
+ *	Return
+ *		0 if the timer was not active.
+ *		1 if the timer was active.
+ *		**-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ *		**-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its
+ *		own timer which would have led to a deadlock otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -4948,6 +5012,10 @@ union bpf_attr {
 	FN(sys_bpf),			\
 	FN(btf_find_by_name_kind),	\
 	FN(sys_close),			\
+	FN(timer_init),			\
+	FN(timer_set_callback),		\
+	FN(timer_start),		\
+	FN(timer_cancel),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -6074,6 +6142,11 @@ struct bpf_spin_lock {
 	__u32	val;
 };
 
+struct bpf_timer {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
 struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.