Commit e5158d98 authored by Yonghong Song's avatar Yonghong Song Committed by Alexei Starovoitov
Browse files

bpf: Implement common macros/helpers for target iterators 



Macro DEFINE_BPF_ITER_FUNC is implemented so target
can define an init function to capture the BTF type
which represents the target.

The bpf_iter_meta is a structure holding meta data, common
to all targets in the bpf program.

Additional marker functions are called before or after
bpf_seq_read() show()/next()/stop() callback functions
to help calculate precise seq_num and whether call bpf_prog
inside stop().

Two functions, bpf_iter_get_info() and bpf_iter_run_prog(),
are implemented so target can get needed information from
bpf_iter infrastructure and can run the program.

Signed-off-by: default avatarYonghong Song <yhs@fb.com>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarAndrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175907.2475956-1-yhs@fb.com
parent 367ec3e4

include/linux/bpf.h

+11 −0
Original line number Diff line number Diff line
@@ -1129,6 +1129,9 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname); 
int bpf_obj_get_user(const char __user *pathname, int flags);



#define BPF_ITER_FUNC_PREFIX "__bpf_iter__"

#define DEFINE_BPF_ITER_FUNC(target, args...)			\

	extern int __bpf_iter__ ## target(args);		\

	int __init __bpf_iter__ ## target(args) { return 0; }



typedef int (*bpf_iter_init_seq_priv_t)(void *private_data);

typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
@@ -1141,12 +1144,20 @@ struct bpf_iter_reg { 
	u32 seq_priv_size;

};



struct bpf_iter_meta {

	__bpf_md_ptr(struct seq_file *, seq);

	u64 session_id;

	u64 seq_num;

};



int bpf_iter_reg_target(struct bpf_iter_reg *reg_info);

void bpf_iter_unreg_target(const char *target);

bool bpf_iter_prog_supported(struct bpf_prog *prog);

int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);

int bpf_iter_new_fd(struct bpf_link *link);

bool bpf_link_is_iter(struct bpf_link *link);

struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop);

int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);



int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);

int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);

kernel/bpf/bpf_iter.c

+80 −5
Original line number Diff line number Diff line
@@ -41,6 +41,33 @@ static atomic64_t session_id; 


static int prepare_seq_file(struct file *file, struct bpf_iter_link *link);



static void bpf_iter_inc_seq_num(struct seq_file *seq)

{

	struct bpf_iter_priv_data *iter_priv;



	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,

				 target_private);

	iter_priv->seq_num++;

}



static void bpf_iter_dec_seq_num(struct seq_file *seq)

{

	struct bpf_iter_priv_data *iter_priv;



	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,

				 target_private);

	iter_priv->seq_num--;

}



static void bpf_iter_done_stop(struct seq_file *seq)

{

	struct bpf_iter_priv_data *iter_priv;



	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,

				 target_private);

	iter_priv->done_stop = true;

}



/* bpf_seq_read, a customized and simpler version for bpf iterator.

 * no_llseek is assumed for this file.

 * The following are differences from seq_read():
@@ -93,6 +120,10 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, 


	err = seq->op->show(seq, p);

	if (err > 0) {

		/* object is skipped, decrease seq_num, so next

		 * valid object can reuse the same seq_num.

		 */

		bpf_iter_dec_seq_num(seq);

		seq->count = 0;

	} else if (err < 0 || seq_has_overflowed(seq)) {

		if (!err)
@@ -117,11 +148,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, 
		if (IS_ERR_OR_NULL(p))

			break;



		/* got a valid next object, increase seq_num */

		bpf_iter_inc_seq_num(seq);



		if (seq->count >= size)

			break;



		err = seq->op->show(seq, p);

		if (err > 0) {

			bpf_iter_dec_seq_num(seq);

			seq->count = offs;

		} else if (err < 0 || seq_has_overflowed(seq)) {

			seq->count = offs;
@@ -138,13 +173,17 @@ stop: 
	offs = seq->count;

	/* bpf program called if !p */

	seq->op->stop(seq, p);

	if (!p && seq_has_overflowed(seq)) {

	if (!p) {

		if (!seq_has_overflowed(seq)) {

			bpf_iter_done_stop(seq);

		} else {

			seq->count = offs;

			if (offs == 0) {

				err = -E2BIG;

				goto done;

			}

		}

	}



	n = min(seq->count, size);

	err = copy_to_user(buf, seq->buf, n);
@@ -453,3 +492,39 @@ free_fd: 
	put_unused_fd(fd);

	return err;

}



struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop)

{

	struct bpf_iter_priv_data *iter_priv;

	struct seq_file *seq;

	void *seq_priv;



	seq = meta->seq;

	if (seq->file->f_op != &bpf_iter_fops)

		return NULL;



	seq_priv = seq->private;

	iter_priv = container_of(seq_priv, struct bpf_iter_priv_data,

				 target_private);



	if (in_stop && iter_priv->done_stop)

		return NULL;



	meta->session_id = iter_priv->session_id;

	meta->seq_num = iter_priv->seq_num;



	return iter_priv->prog;

}



int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx)

{

	int ret;



	rcu_read_lock();

	migrate_disable();

	ret = BPF_PROG_RUN(prog, ctx);

	migrate_enable();

	rcu_read_unlock();



	return ret == 0 ? 0 : -EAGAIN;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE