From f17bedcd29517739a6491c1c51cc6a593f6a0332 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 25 Sep 2026 06:55:28 +0200 Subject: [PATCH 1/5] bpf: Skip zero-length stream writes A stream write whose formatted output is empty still allocates a stream element and links it into the stream log. Capacity accounting only counts payload bytes, so such elements never count against the stream limit, and a program that keeps producing empty output allocates elements without bound until a reader drains them. Return success without allocating anything when there is nothing to write, for both bpf_stream_vprintk() and staged writes. Every element in a stream log then carries at least one byte, which later changes rely on when they derive read readiness from published byte counts. Fixes: 5ab154f1463a ("bpf: Introduce BPF standard streams") Suggested-by: Emil Tsalapatis Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://patch.msgid.link/20260925045536.1480933-2-memxor@gmail.com --- kernel/bpf/stream.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/stream.c b/kernel/bpf/stream.c index 2b80a0599865..9829d1ebce70 100644 --- a/kernel/bpf/stream.c +++ b/kernel/bpf/stream.c @@ -75,8 +75,13 @@ static void bpf_stream_release_capacity(struct bpf_stream *stream, int len) static int bpf_stream_push_str(struct bpf_stream *stream, const char *str, int len) { - int ret = bpf_stream_consume_capacity(stream, len); + int ret; + /* Nothing to publish; do not allocate an element for it. */ + if (!len) + return 0; + + ret = bpf_stream_consume_capacity(stream, len); if (ret) return ret; @@ -333,8 +338,8 @@ int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...) va_start(args, fmt); len = vscnprintf(buf->buf, ARRAY_SIZE(buf->buf), fmt, args); va_end(args); - /* Exclude NULL byte during push. */ - ret = __bpf_stream_push_str(&ss->log, buf->buf, len); + /* Exclude NULL byte during push; skip empty output entirely. */ + ret = len ? __bpf_stream_push_str(&ss->log, buf->buf, len) : 0; if (!ret) ss->len += len; bpf_put_buffers(); From e831ff570908c572d7ee5389a7e03a8637d1d8ee Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 25 Sep 2026 06:55:29 +0200 Subject: [PATCH 2/5] bpf: Add file descriptor interface for program streams The existing BPF_PROG_STREAM_READ_BY_FD command only supports polling a program stream through repeated bpf() calls. It cannot block for new data or integrate with poll-based event loops. Add BPF_PROG_STREAM_OPEN to return a read-only, close-on-exec file descriptor for a selected program stream. Reads block by default and BPF_F_STREAM_NONBLOCK, the only accepted flag, provides non-blocking behavior. poll reports readable data and reports hangup once the program has been freed. Like pipes and sockets, the descriptor is not seekable and lseek fails with ESPIPE. A stream descriptor deliberately does not retain the program. Move each stream into a separately refcounted allocation so program teardown can mark it dead and wake descriptor users while outstanding descriptors drain buffered data safely. Readers sample the dead flag before looking for data, so EOF is reported only when the stream was already dead before it was found empty; data published right before teardown is never skipped. Only programs loaded through BPF_PROG_LOAD get streams. Classic BPF filters, JIT subprograms and shim programs never write to one, and kernel-side writers already resolve a subprogram to its main program, so those programs no longer carry stream state. Readiness needs its own counter. Stream capacity is charged before allocation and before an element is published to the stream log, so using that reservation as the read and poll condition can report readable data while no element exists: a blocking reader retries instead of sleeping and a lone non-blocking reader can see POLLIN followed by EAGAIN. Publish bytes with release ordering after adding elements to the lockless log, use acquire loads before consuming them or reporting readiness, limit each read to its readable snapshot and subtract only bytes actually copied. This keeps the aggregate count correct even when concurrent publishers update it out of publication order. With several readers on one stream, readiness remains advisory, as it is for pipes. The capacity counter is kept solely for enforcing the stream size limit. Wakeups are always deferred through irq_work. Stream writers run in whatever context the program runs in: NMI context for perf_event programs, sections with interrupts disabled inside bpf_spin_lock or rqspinlock critical sections since bpf_stream_vprintk() is KF_SPINLOCK_SAFE, and tracing programs attached anywhere in the kernel, including inside the wait queue and epoll code itself. Waking waiters directly from there can deadlock, and no cheap context check covers every case: on PREEMPT_RT, spinlock_t sections do not disable interrupts, so in_nmi() or irqs_disabled() cannot tell such a program apart from a benign one. Queue an irq_work item instead, as bpf_ringbuf does. Queue it only when a publication turns an empty stream readable. Readers block and pollers wait only after finding the stream empty, and the readable count never drops below zero because each read is bounded by its snapshot, so the first publication after such an observation is the one that makes the count positive, and it is the one that queues the wakeup. Publications into a stream that already holds data raise no interrupt, so a program that prints while nobody drains its stream pays for a single irq_work until the stream is emptied again. This matches bpf_ringbuf, which notifies only once the consumer has caught up. Blocking readers and level-triggered pollers re-check the readable count before waiting, so they cannot miss data, and edge-triggered epoll consumers drain until EAGAIN before waiting again, as epoll(7) requires. Synchronize pending work before releasing the final stream reference so the callback cannot outlive the stream, but only when the work was ever queued: irq_work_sync() waits for an RCU grace period on PREEMPT_RT and on architectures without an irq_work interrupt. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://patch.msgid.link/20260925045536.1480933-3-memxor@gmail.com --- include/linux/bpf.h | 14 ++- include/uapi/linux/bpf.h | 39 ++++++ kernel/bpf/core.c | 8 +- kernel/bpf/stream.c | 209 ++++++++++++++++++++++++++++++--- kernel/bpf/syscall.c | 29 +++++ tools/include/uapi/linux/bpf.h | 39 ++++++ 6 files changed, 315 insertions(+), 23 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2cf04bba16bb..4bae3796c42f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -1771,12 +1772,18 @@ enum { }; struct bpf_stream { - atomic_t capacity; + refcount_t refcnt; + atomic_t capacity; /* bytes reserved against the stream limit */ + atomic_t readable; /* published bytes available to readers */ struct llist_head log; /* list of in-flight stream elements in LIFO order */ struct mutex lock; /* lock protecting backlog_{head,tail} */ struct llist_node *backlog_head; /* list of in-flight stream elements in FIFO order */ struct llist_node *backlog_tail; /* tail of the list above */ + wait_queue_head_t waitq; + struct irq_work notify_work; + bool notify_used; /* notify_work was queued at least once */ + bool dead; }; struct bpf_stream_stage { @@ -1915,7 +1922,7 @@ struct bpf_prog_aux { struct work_struct work; struct rcu_head rcu; }; - struct bpf_stream stream[2]; + struct bpf_stream *stream[2]; struct mutex st_ops_assoc_mutex; struct bpf_map __rcu *st_ops_assoc; }; @@ -4224,9 +4231,10 @@ void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs); void bpf_put_buffers(void); -void bpf_prog_stream_init(struct bpf_prog *prog); +int bpf_prog_stream_init(struct bpf_prog *prog, gfp_t gfp_extra_flags); void bpf_prog_stream_free(struct bpf_prog *prog); int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, u32 len); +int bpf_prog_stream_new_fd(struct bpf_prog *prog, enum bpf_stream_id stream_id, u32 flags); void bpf_stream_stage_init(struct bpf_stream_stage *ss); void bpf_stream_stage_free(struct bpf_stream_stage *ss); __printf(2, 3) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0aaa54359aeb..4687c3310996 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -936,6 +936,33 @@ union bpf_iter_link_info { * 0 on success or -1 if an error occurred (in which case, * *errno* is set appropriately). * + * BPF_PROG_STREAM_OPEN + * Description + * Open a file descriptor for one of the BPF streams associated + * with the program identified by *prog_fd*. The stream is selected + * by *stream_id*. + * + * The returned file descriptor supports **read**\ (2) and + * **poll**\ (2). Reads block while the stream is empty unless + * **BPF_F_STREAM_NONBLOCK** is specified in *flags*. A non-blocking + * read of an empty stream fails with **EAGAIN**. + * + * **poll**\ (2) reports **POLLIN** when data is available and + * **POLLHUP** once the program has been freed, that is, after every + * reference to it, including links and other file descriptors, has + * been dropped. Hangup may lag the final release because program + * teardown is deferred. Buffered data remains readable after + * **POLLHUP** and a read returns zero after all such data has been + * consumed. + * + * The file descriptor is read-only and has the close-on-exec flag + * set. It is not seekable and **lseek**\ (2) fails with **ESPIPE**. + * *flags* may only contain **BPF_F_STREAM_NONBLOCK**. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -993,6 +1020,7 @@ enum bpf_cmd { BPF_TOKEN_CREATE, BPF_PROG_STREAM_READ_BY_FD, BPF_PROG_ASSOC_STRUCT_OPS, + BPF_PROG_STREAM_OPEN, __MAX_BPF_CMD, BPF_COMMON_ATTRS = 1 << 16, /* Indicate carrying syscall common attrs. */ }; @@ -1524,6 +1552,11 @@ enum { BPF_STREAM_STDERR = 2, }; +/* flags for BPF_PROG_STREAM_OPEN command */ +enum { + BPF_F_STREAM_NONBLOCK = (1U << 0), +}; + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -1950,6 +1983,12 @@ union bpf_attr { __u32 flags; } prog_assoc_struct_ops; + struct { + __u32 prog_fd; + __u32 stream_id; + __u32 flags; + } prog_stream_open; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index aa72ad3ec689..d3b8b626ec0f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -142,10 +142,6 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag mutex_init(&fp->aux->dst_mutex); mutex_init(&fp->aux->st_ops_assoc_mutex); -#ifdef CONFIG_BPF_SYSCALL - bpf_prog_stream_init(fp); -#endif - return fp; } @@ -289,6 +285,9 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, void __bpf_prog_free(struct bpf_prog *fp) { if (fp->aux) { +#ifdef CONFIG_BPF_SYSCALL + bpf_prog_stream_free(fp); +#endif mutex_destroy(&fp->aux->used_maps_mutex); mutex_destroy(&fp->aux->dst_mutex); mutex_destroy(&fp->aux->st_ops_assoc_mutex); @@ -3086,7 +3085,6 @@ static void bpf_prog_free_deferred(struct work_struct *work) aux = container_of(work, struct bpf_prog_aux, work); #ifdef CONFIG_BPF_SYSCALL bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab); - bpf_prog_stream_free(aux->prog); #endif #ifdef CONFIG_CGROUP_BPF if (aux->cgroup_atype != CGROUP_BPF_ATTACH_TYPE_INVALID) diff --git a/kernel/bpf/stream.c b/kernel/bpf/stream.c index 9829d1ebce70..83e803ea54ef 100644 --- a/kernel/bpf/stream.c +++ b/kernel/bpf/stream.c @@ -2,11 +2,15 @@ /* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ #include +#include #include #include #include +#include #include #include +#include +#include static void bpf_stream_elem_init(struct bpf_stream_elem *elem, int len) { @@ -73,6 +77,51 @@ static void bpf_stream_release_capacity(struct bpf_stream *stream, int len) atomic_sub(len, &stream->capacity); } +static void bpf_stream_notify(struct irq_work *work) +{ + struct bpf_stream *stream = container_of(work, struct bpf_stream, notify_work); + + /* + * Writers run in arbitrary program contexts, including NMI and regions + * that already hold wait queue or epoll locks. Wake waiters from + * irq_work instead, where taking those locks is safe. + */ + wake_up_interruptible_poll(&stream->waitq, EPOLLIN | EPOLLRDNORM); +} + +static void bpf_stream_queue_notify(struct bpf_stream *stream) +{ + /* + * Record that the work has been used so that teardown only pays for + * irq_work_sync(), which may wait for an RCU grace period, when a + * callback could actually be in flight. + */ + if (!READ_ONCE(stream->notify_used)) + WRITE_ONCE(stream->notify_used, true); + irq_work_queue(&stream->notify_work); +} + +static int bpf_stream_readable_bytes(struct bpf_stream *stream) +{ + return atomic_read_acquire(&stream->readable); +} + +static void bpf_stream_publish(struct bpf_stream *stream, int len) +{ + /* + * Pairs with atomic_read_acquire() in bpf_stream_readable_bytes(). + * + * Notify only when the stream turns from empty to readable. Readers + * block and pollers wait only after finding it empty, and a read never + * takes the count below zero, so the publication that makes it positive + * is the one they wait for. Publishing into a stream that already holds + * data would only raise an interrupt for waiters that are being woken + * already, or for nobody at all. + */ + if (atomic_add_return_release(len, &stream->readable) == len) + bpf_stream_queue_notify(stream); +} + static int bpf_stream_push_str(struct bpf_stream *stream, const char *str, int len) { int ret; @@ -88,6 +137,8 @@ static int bpf_stream_push_str(struct bpf_stream *stream, const char *str, int l ret = __bpf_stream_push_str(&stream->log, str, len); if (ret) bpf_stream_release_capacity(stream, len); + else + bpf_stream_publish(stream, len); return ret; } @@ -96,7 +147,7 @@ static struct bpf_stream *bpf_stream_get(enum bpf_stream_id stream_id, struct bp { if (stream_id != BPF_STDOUT && stream_id != BPF_STDERR) return NULL; - return &aux->stream[stream_id - 1]; + return aux->stream[stream_id - 1]; } static void bpf_stream_free_elem(struct bpf_stream_elem *elem) @@ -164,14 +215,16 @@ static bool bpf_stream_consume_elem(struct bpf_stream_elem *elem, int *len) static int bpf_stream_read(struct bpf_stream *stream, void __user *buf, int len) { - int rem_len = len, cons_len, ret = 0; + int read_len, rem_len, cons_len, ret = 0; struct bpf_stream_elem *elem = NULL; struct llist_node *node; mutex_lock(&stream->lock); + read_len = min(len, bpf_stream_readable_bytes(stream)); + rem_len = read_len; while (rem_len) { - int pos = len - rem_len; + int pos = read_len - rem_len; int chunk, n; bool cont; @@ -193,7 +246,7 @@ static int bpf_stream_read(struct bpf_stream *stream, void __user *buf, int len) /* Keep any successfully copied bytes; -EFAULT only if none. */ elem->consumed_len -= n; rem_len += n; - ret = (len == rem_len) ? -EFAULT : 0; + ret = (read_len == rem_len) ? -EFAULT : 0; break; } @@ -204,8 +257,9 @@ static int bpf_stream_read(struct bpf_stream *stream, void __user *buf, int len) bpf_stream_free_elem(elem); } + atomic_sub(read_len - rem_len, &stream->readable); mutex_unlock(&stream->lock); - return ret ? ret : len - rem_len; + return ret ? ret : read_len - rem_len; } int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, u32 len) @@ -220,6 +274,111 @@ int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, vo return bpf_stream_read(stream, buf, len); } +static bool bpf_stream_has_data(struct bpf_stream *stream) +{ + return bpf_stream_readable_bytes(stream) > 0; +} + +static void bpf_stream_put(struct bpf_stream *stream) +{ + if (refcount_dec_and_test(&stream->refcnt)) { + struct llist_node *list; + + /* Only a stream that ever queued its work can have a callback in flight. */ + if (READ_ONCE(stream->notify_used)) + irq_work_sync(&stream->notify_work); + list = llist_del_all(&stream->log); + bpf_stream_free_list(list); + bpf_stream_free_list(stream->backlog_head); + mutex_destroy(&stream->lock); + kfree(stream); + } +} + +static int bpf_stream_release(struct inode *inode, struct file *file) +{ + bpf_stream_put(file->private_data); + return 0; +} + +static ssize_t bpf_stream_file_read(struct file *file, char __user *buf, size_t len, + loff_t *ppos) +{ + struct bpf_stream *stream = file->private_data; + bool dead; + int ret; + + if (!len) + return 0; + + for (;;) { + /* + * Sample teardown state before looking for data. Nothing is + * published once the program is gone, so finding the stream + * empty after observing dead means EOF. The opposite order could + * report EOF while data published just before teardown is still + * buffered. + */ + dead = smp_load_acquire(&stream->dead); + ret = bpf_stream_read(stream, buf, len); + if (ret) + return ret; + if (dead) + return 0; + if (file->f_flags & O_NONBLOCK) + return -EAGAIN; + + ret = wait_event_interruptible(stream->waitq, + bpf_stream_has_data(stream) || + READ_ONCE(stream->dead)); + if (ret) + return ret; + } +} + +static __poll_t bpf_stream_poll(struct file *file, struct poll_table_struct *pts) +{ + struct bpf_stream *stream = file->private_data; + __poll_t events = 0; + + /* + * poll_wait() only registers the wait queue callback. Register before + * checking persistent state so a concurrent publication or teardown is + * observed either by the callback or by the checks below. + */ + poll_wait(file, &stream->waitq, pts); + if (bpf_stream_has_data(stream)) + events |= EPOLLIN | EPOLLRDNORM; + if (READ_ONCE(stream->dead)) + events |= EPOLLHUP; + return events; +} + +static const struct file_operations bpf_stream_fops = { + .release = bpf_stream_release, + .read = bpf_stream_file_read, + .poll = bpf_stream_poll, +}; + +int bpf_prog_stream_new_fd(struct bpf_prog *prog, enum bpf_stream_id stream_id, u32 flags) +{ + struct bpf_stream *stream; + int fd_flags = O_RDONLY | O_CLOEXEC; + int fd; + + stream = bpf_stream_get(stream_id, prog->aux); + if (!stream) + return -ENOENT; + if (flags & BPF_F_STREAM_NONBLOCK) + fd_flags |= O_NONBLOCK; + + refcount_inc(&stream->refcnt); + fd = anon_inode_getfd("bpf-stream", &bpf_stream_fops, stream, fd_flags); + if (fd < 0) + bpf_stream_put(stream); + return fd; +} + __bpf_kfunc_start_defs(); /* @@ -287,28 +446,47 @@ __bpf_kfunc_end_defs(); /* Added kfunc to common_btf_ids */ -void bpf_prog_stream_init(struct bpf_prog *prog) +int bpf_prog_stream_init(struct bpf_prog *prog, gfp_t gfp_extra_flags) { int i; for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) { - atomic_set(&prog->aux->stream[i].capacity, 0); - init_llist_head(&prog->aux->stream[i].log); - mutex_init(&prog->aux->stream[i].lock); - prog->aux->stream[i].backlog_head = NULL; - prog->aux->stream[i].backlog_tail = NULL; + struct bpf_stream *stream; + + /* On failure, bpf_prog_stream_free() releases the streams allocated so far. */ + stream = kzalloc_obj(*stream, + bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); + if (!stream) + return -ENOMEM; + + refcount_set(&stream->refcnt, 1); + init_llist_head(&stream->log); + mutex_init(&stream->lock); + init_waitqueue_head(&stream->waitq); + init_irq_work(&stream->notify_work, bpf_stream_notify); + prog->aux->stream[i] = stream; } + return 0; } void bpf_prog_stream_free(struct bpf_prog *prog) { - struct llist_node *list; int i; for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) { - list = llist_del_all(&prog->aux->stream[i].log); - bpf_stream_free_list(list); - bpf_stream_free_list(prog->aux->stream[i].backlog_head); + struct bpf_stream *stream = prog->aux->stream[i]; + + if (!stream) + continue; + /* + * Pairs with smp_load_acquire() in bpf_stream_file_read(): every + * publication precedes the dead flag, so a reader that observes + * it also observes all buffered data. + */ + smp_store_release(&stream->dead, true); + wake_up_interruptible_poll(&stream->waitq, EPOLLHUP); + bpf_stream_put(stream); + prog->aux->stream[i] = NULL; } } @@ -371,6 +549,7 @@ int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog, list = tail; } llist_add_batch(head, tail, &stream->log); + bpf_stream_publish(stream, ss->len); return 0; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e1bcfd43f54f..ac52f4ae414c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3080,6 +3080,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, struct bpf_log_at prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; + err = bpf_prog_stream_init(prog, GFP_USER); + if (err) + goto free_prog; + err = -EFAULT; if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), @@ -6316,6 +6320,28 @@ static int prog_assoc_struct_ops(union bpf_attr *attr) return ret; } +#define BPF_PROG_STREAM_OPEN_LAST_FIELD prog_stream_open.flags + +static int prog_stream_open(union bpf_attr *attr) +{ + struct bpf_prog *prog; + u32 flags = attr->prog_stream_open.flags; + int ret; + + if (CHECK_ATTR(BPF_PROG_STREAM_OPEN)) + return -EINVAL; + if (flags & ~BPF_F_STREAM_NONBLOCK) + return -EINVAL; + + prog = bpf_prog_get(attr->prog_stream_open.prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + ret = bpf_prog_stream_new_fd(prog, attr->prog_stream_open.stream_id, flags); + bpf_prog_put(prog); + return ret; +} + static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size, bpfptr_t uattr_common, unsigned int size_common) { @@ -6488,6 +6514,9 @@ static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size, case BPF_PROG_ASSOC_STRUCT_OPS: err = prog_assoc_struct_ops(&attr); break; + case BPF_PROG_STREAM_OPEN: + err = prog_stream_open(&attr); + break; default: err = -EINVAL; break; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0aaa54359aeb..4687c3310996 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -936,6 +936,33 @@ union bpf_iter_link_info { * 0 on success or -1 if an error occurred (in which case, * *errno* is set appropriately). * + * BPF_PROG_STREAM_OPEN + * Description + * Open a file descriptor for one of the BPF streams associated + * with the program identified by *prog_fd*. The stream is selected + * by *stream_id*. + * + * The returned file descriptor supports **read**\ (2) and + * **poll**\ (2). Reads block while the stream is empty unless + * **BPF_F_STREAM_NONBLOCK** is specified in *flags*. A non-blocking + * read of an empty stream fails with **EAGAIN**. + * + * **poll**\ (2) reports **POLLIN** when data is available and + * **POLLHUP** once the program has been freed, that is, after every + * reference to it, including links and other file descriptors, has + * been dropped. Hangup may lag the final release because program + * teardown is deferred. Buffered data remains readable after + * **POLLHUP** and a read returns zero after all such data has been + * consumed. + * + * The file descriptor is read-only and has the close-on-exec flag + * set. It is not seekable and **lseek**\ (2) fails with **ESPIPE**. + * *flags* may only contain **BPF_F_STREAM_NONBLOCK**. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -993,6 +1020,7 @@ enum bpf_cmd { BPF_TOKEN_CREATE, BPF_PROG_STREAM_READ_BY_FD, BPF_PROG_ASSOC_STRUCT_OPS, + BPF_PROG_STREAM_OPEN, __MAX_BPF_CMD, BPF_COMMON_ATTRS = 1 << 16, /* Indicate carrying syscall common attrs. */ }; @@ -1524,6 +1552,11 @@ enum { BPF_STREAM_STDERR = 2, }; +/* flags for BPF_PROG_STREAM_OPEN command */ +enum { + BPF_F_STREAM_NONBLOCK = (1U << 0), +}; + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -1950,6 +1983,12 @@ union bpf_attr { __u32 flags; } prog_assoc_struct_ops; + struct { + __u32 prog_fd; + __u32 stream_id; + __u32 flags; + } prog_stream_open; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF From 9054903ab51b8e462bd247d6365c11bc4fce90a2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 25 Sep 2026 06:55:30 +0200 Subject: [PATCH 3/5] libbpf: Add bpf_prog_stream_open() Expose the BPF_PROG_STREAM_OPEN command through a low-level libbpf wrapper. The options structure carries stream open flags, including non-blocking mode, while leaving room for future extensions. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Reviewed-by: Emil Tsalapatis Link: https://patch.msgid.link/20260925045536.1480933-4-memxor@gmail.com --- tools/lib/bpf/bpf.c | 19 +++++++++++++++++++ tools/lib/bpf/bpf.h | 24 ++++++++++++++++++++++++ tools/lib/bpf/libbpf.map | 1 + 3 files changed, 44 insertions(+) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index a9de7f107cf7..b49822d212ae 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -1466,6 +1466,25 @@ int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len, return libbpf_err_errno(err); } +int bpf_prog_stream_open(int prog_fd, __u32 stream_id, + const struct bpf_prog_stream_open_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_stream_open); + union bpf_attr attr; + int fd; + + if (!OPTS_VALID(opts, bpf_prog_stream_open_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.prog_stream_open.prog_fd = prog_fd; + attr.prog_stream_open.stream_id = stream_id; + attr.prog_stream_open.flags = OPTS_GET(opts, flags, 0); + + fd = sys_bpf_fd(BPF_PROG_STREAM_OPEN, &attr, attr_sz); + return libbpf_err_errno(fd); +} + int bpf_prog_assoc_struct_ops(int prog_fd, int map_fd, struct bpf_prog_assoc_struct_ops_opts *opts) { diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 490e8cb4ba53..826d9cc9ab65 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -759,10 +759,34 @@ struct bpf_prog_stream_read_opts { * * @return The number of bytes read, on success; negative error code, otherwise * (errno is also set to the error code) + * + * For blocking reads and polling, prefer **bpf_prog_stream_open**. */ LIBBPF_API int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len, struct bpf_prog_stream_read_opts *opts); +struct bpf_prog_stream_open_opts { + size_t sz; + __u32 flags; + size_t :0; +}; +#define bpf_prog_stream_open_opts__last_field flags + +/** + * @brief **bpf_prog_stream_open** opens a file descriptor for a BPF stream of + * a given BPF program. + * + * @param prog_fd FD for the BPF program whose BPF stream is to be opened. + * @param stream_id ID of the BPF stream to be opened. + * @param opts optional options, can be NULL. BPF_F_STREAM_NONBLOCK requests a + * non-blocking descriptor. + * + * @return A new stream FD, on success; negative error code, otherwise (errno + * is also set to the error code) + */ +LIBBPF_API int bpf_prog_stream_open(int prog_fd, __u32 stream_id, + const struct bpf_prog_stream_open_opts *opts); + struct bpf_prog_assoc_struct_ops_opts { size_t sz; __u32 flags; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 18d27d20102e..53b7b591325f 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -459,6 +459,7 @@ LIBBPF_1.7.0 { LIBBPF_1.8.0 { global: bpf_map__attach_cgroup_opts; + bpf_prog_stream_open; bpf_program__add_flags; bpf_program__attach_tracing_multi; bpf_program__clear_flags; From 0abecacb4bfddff99064b855ff28613b786fa435 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 25 Sep 2026 06:55:31 +0200 Subject: [PATCH 4/5] bpftool: Add option to wait for program stream output bpftool prog tracelog { stdout | stderr } PROG dumps the output buffered in a program stream and exits, which is all BPF_PROG_STREAM_READ_BY_FD allows. Waiting for further output means rerunning the command. Add a -w/--wait option that opens the stream with bpf_prog_stream_open() in its default blocking mode and keeps printing output as the program produces it. Flush each chunk as it arrives so redirected output is not held in stdio buffers while the next read blocks. Waiting is opt-in: the default dump keeps using BPF_PROG_STREAM_READ_BY_FD and exits once the buffered output is drained, so existing scripts behave the same on old and new kernels. A stream descriptor does not keep its program alive, so bpftool drops the program descriptor once the stream is open. Waiting then ends with EOF when the program is unloaded and otherwise runs until interrupted, as bpftool prog tracelog already does for the trace pipe. Exit from the SIGINT, SIGHUP and SIGTERM handlers like that command does. A flag set by the handler and checked before each read would miss a signal that lands between the check and the blocking read(), leaving bpftool asleep until the next print. Waiting requires BPF_PROG_STREAM_OPEN. The bpf() syscall fails with EINVAL for an unknown command, which bpftool reports as missing kernel support rather than degrading into a dump. Document the option and offer it in the bash completion. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Acked-by: Quentin Monnet Link: https://patch.msgid.link/20260925045536.1480933-5-memxor@gmail.com --- .../bpftool/Documentation/bpftool-prog.rst | 12 +++- tools/bpf/bpftool/bash-completion/bpftool | 2 +- tools/bpf/bpftool/main.c | 7 ++- tools/bpf/bpftool/main.h | 1 + tools/bpf/bpftool/prog.c | 62 ++++++++++++++++--- 5 files changed, 73 insertions(+), 11 deletions(-) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 90fe8c61bf42..17aa0d560e32 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -18,7 +18,8 @@ SYNOPSIS *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-m** | **--mapcompat** } | { **-n** | **--nomount** } | -{ **-L** | **--use-loader** } | [ { **-S** | **--sign** } **-k** **-i** ] } +{ **-L** | **--use-loader** } | [ { **-S** | **--sign** } **-k** **-i** ] | +{ **-w** | **--wait** } } *COMMANDS* := { **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** | @@ -186,6 +187,11 @@ bpftool prog tracelog { stdout | stderr } *PROG* error messages to the standard error stream. This facility should be used only for debugging purposes. + By default, bpftool prints the output buffered so far and exits. With + **-w** or **--wait**, it keeps printing new output as the program produces + it, until the program is unloaded or is hit. Waiting requires a + kernel that supports opening a stream as a file descriptor. + bpftool prog run *PROG* data_in *FILE* [data_out *FILE* [data_size_out *L*]] [ctx_in *FILE* [ctx_out *FILE* [ctx_size_out *M*]]] [repeat *N*] Run BPF program *PROG* in the kernel testing infrastructure for BPF, meaning that the program works on the data and context provided by the @@ -267,6 +273,10 @@ OPTIONS Path to the X.509 certificate file in PEM or DER format, required when signing. +-w, --wait + When dumping a program stream with **bpftool prog tracelog**, wait for new + output instead of exiting once the buffered output has been printed. + EXAMPLES ======== **# bpftool prog show** diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 9d9ced270685..a28af31937ad 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -269,7 +269,7 @@ _bpftool() # Deal with options if [[ ${words[cword]} == -* ]]; then local c='--version --json --pretty --bpffs --mapcompat --debug \ - --use-loader --base-btf --sign -i -k' + --use-loader --base-btf --sign -i -k --wait' COMPREPLY=( $( compgen -W "$c" -- "$cur" ) ) return 0 fi diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 83884b21e708..d15fec71b64e 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -31,6 +31,7 @@ bool block_mount; bool verifier_logs; bool relaxed_maps; bool use_loader; +bool wait_output; struct btf *base_btf; struct hashmap *refs_table; bool sign_progs; @@ -462,6 +463,7 @@ int main(int argc, char **argv) { "nomount", no_argument, NULL, 'n' }, { "debug", no_argument, NULL, 'd' }, { "use-loader", no_argument, NULL, 'L' }, + { "wait", no_argument, NULL, 'w' }, { "sign", no_argument, NULL, 'S' }, { "base-btf", required_argument, NULL, 'B' }, { 0 } @@ -480,7 +482,7 @@ int main(int argc, char **argv) bin_name = "bpftool"; opterr = 0; - while ((opt = getopt_long(argc, argv, "VhpjfLmndSi:k:B:l", + while ((opt = getopt_long(argc, argv, "VhpjfLmndSi:k:B:lw", options, NULL)) >= 0) { switch (opt) { case 'V': @@ -530,6 +532,9 @@ int main(int argc, char **argv) case 'L': use_loader = true; break; + case 'w': + wait_output = true; + break; case 'S': sign_progs = true; use_loader = true; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 48eedcb9f6c0..fa2c877a3cbf 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -89,6 +89,7 @@ extern bool block_mount; extern bool verifier_logs; extern bool relaxed_maps; extern bool use_loader; +extern bool wait_output; extern struct btf *base_btf; extern struct hashmap *refs_table; extern bool sign_progs; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 24e40dfab469..5e27b22444f2 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1119,21 +1119,66 @@ enum prog_tracelog_mode { TRACE_STDERR, }; +static void exit_stream(int signo) +{ + exit(0); +} + +/* Consumes prog_fd. */ static int prog_tracelog_stream(int prog_fd, enum prog_tracelog_mode mode) { + const struct sigaction act = { .sa_handler = exit_stream }; + const int signals[] = { SIGHUP, SIGINT, SIGTERM }; FILE *file = mode == TRACE_STDOUT ? stdout : stderr; int stream_id = mode == TRACE_STDOUT ? 1 : 2; char buf[512]; - int ret; + unsigned int i; + int fd, ret; - ret = 0; - do { - ret = bpf_prog_stream_read(prog_fd, stream_id, buf, sizeof(buf), NULL); - if (ret > 0) - fwrite(buf, sizeof(buf[0]), ret, file); - } while (ret > 0); + if (!wait_output) { + do { + ret = bpf_prog_stream_read(prog_fd, stream_id, buf, sizeof(buf), NULL); + if (ret > 0) + fwrite(buf, sizeof(buf[0]), ret, file); + } while (ret > 0); + if (ret < 0) + p_err("failed to read stream: %s", strerror(-ret)); + close(prog_fd); + goto out; + } + fd = bpf_prog_stream_open(prog_fd, stream_id, NULL); + /* + * The stream descriptor does not keep the program alive. Drop the + * program reference so that reads return EOF once the program is gone. + */ + close(prog_fd); + if (fd == -EINVAL) { + /* The bpf() syscall rejects unknown commands with EINVAL. */ + p_err("waiting for stream output is not supported by this kernel"); + return -1; + } + if (fd < 0) { + p_err("failed to open stream: %s", strerror(-fd)); + return -1; + } + + /* + * Exit from the handler like the trace pipe variant does. A flag checked + * between reads would miss a signal that lands before read() blocks and + * only end the loop at the next print. + */ + for (i = 0; i < ARRAY_SIZE(signals); i++) + sigaction(signals[i], &act, NULL); + while ((ret = read(fd, buf, sizeof(buf))) > 0) { + fwrite(buf, sizeof(buf[0]), ret, file); + fflush(file); + } + if (ret < 0) + p_err("failed to read stream: %s", strerror(errno)); + close(fd); +out: fflush(file); return ret ? -1 : 0; } @@ -2659,7 +2704,8 @@ static int do_help(int argc, char **argv) " METRIC := { cycles | instructions | l1d_loads | llc_misses | itlb_misses | dtlb_misses }\n" " " HELP_SPEC_OPTIONS " |\n" " {-f|--bpffs} | {-m|--mapcompat} | {-n|--nomount} |\n" - " {-L|--use-loader} | [ {-S|--sign } {-k} {-i} ] \n" + " {-L|--use-loader} | [ {-S|--sign } {-k} {-i} ] |\n" + " {-w|--wait} }\n" "", bin_name, argv[-2]); From 4e1d734651e5a0379defd42c53bd2f985e3e33a6 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 25 Sep 2026 06:55:32 +0200 Subject: [PATCH 5/5] selftests/bpf: Test program stream file descriptors Exercise validation and normal file semantics of BPF_PROG_STREAM_OPEN. Cover read-only and close-on-exec state, write and lseek rejection, non-blocking reads, partial reads, poll readiness, and a blocking reader woken by new stream data. Also check that an empty stream write produces neither readable data nor poll readiness. Register the descriptor with EPOLLET, consume the initial data event without draining buffered output, then release the program. Require a second edge carrying POLLIN and POLLHUP, drain the buffered bytes, and verify that poll continues to report HUP before read returns EOF. This ensures program teardown notifies edge-triggered loops even when readability never transitions. Notifications are only sent when an empty stream turns readable, so also consume the first edge of an edge-triggered descriptor, leave part of the output behind while more arrives, drain the stream and require a new edge for output published afterwards. This covers the transition that re-arms notifications once readers, including partial ones, bring the count back to zero. Also block a reader on an empty live stream, release the program, and verify that it wakes and returns EOF. This directly covers the teardown wait condition and its no-lost-wakeup ordering. Finally, attach a stream-writing program to a hardware perf event and busy-poll its epoll registration until output arrives. This both drives the per-thread event into NMI context and directly verifies that the deferred irq_work notification reaches epoll, without a separate BSS completion handshake. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://patch.msgid.link/20260925045536.1480933-6-memxor@gmail.com --- .../testing/selftests/bpf/prog_tests/stream.c | 486 ++++++++++++++++++ tools/testing/selftests/bpf/progs/stream.c | 20 + 2 files changed, 506 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/stream.c b/tools/testing/selftests/bpf/prog_tests/stream.c index 74bd15c4bfba..ae400dcfbf24 100644 --- a/tools/testing/selftests/bpf/prog_tests/stream.c +++ b/tools/testing/selftests/bpf/prog_tests/stream.c @@ -1,11 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ #include +#include +#include +#include #include +#include #include "stream.skel.h" #include "stream_fail.skel.h" +#define NMI_TIMEOUT_NS (5ULL * 1000 * 1000 * 1000) + void test_stream_failure(void) { RUN_TESTS(stream_fail); @@ -62,6 +68,486 @@ void test_stream_syscall(void) stream__destroy(skel); } +static bool stream_fd_trigger(struct bpf_program *prog) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + int ret; + + ret = bpf_prog_test_run_opts(bpf_program__fd(prog), &opts); + return ASSERT_OK(ret, "test_run") && ASSERT_OK(opts.retval, "retval"); +} + +static void test_stream_fd_open(void) +{ + LIBBPF_OPTS(bpf_prog_stream_open_opts, opts); + struct stream *skel; + int fd, prog_fd; + + skel = stream__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stream__open_and_load")) + return; + + prog_fd = bpf_program__fd(skel->progs.stream_syscall); + fd = bpf_prog_stream_open(0, BPF_STREAM_STDOUT, NULL); + ASSERT_EQ(fd, -EINVAL, "bad_prog_fd"); + + fd = bpf_prog_stream_open(prog_fd, 0, NULL); + ASSERT_EQ(fd, -ENOENT, "bad_stream_id"); + + opts.flags = BPF_F_RDONLY; + fd = bpf_prog_stream_open(prog_fd, BPF_STREAM_STDOUT, &opts); + ASSERT_EQ(fd, -EINVAL, "access_flag"); + + opts.flags = 1U << 31; + fd = bpf_prog_stream_open(prog_fd, BPF_STREAM_STDOUT, &opts); + ASSERT_EQ(fd, -EINVAL, "unknown_flag"); + + fd = bpf_prog_stream_open(prog_fd, BPF_STREAM_STDERR, NULL); + if (ASSERT_OK_FD(fd, "stderr")) + close(fd); + + stream__destroy(skel); +} + +static void test_stream_fd_nonblock(void) +{ + LIBBPF_OPTS(bpf_prog_stream_open_opts, opts, + .flags = BPF_F_STREAM_NONBLOCK, + ); + struct pollfd pfd = { .events = POLLIN | POLLHUP }; + struct stream *skel; + char buf[4] = {}; + int fd, flags, ret; + + skel = stream__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stream__open_and_load")) + return; + + fd = bpf_prog_stream_open(bpf_program__fd(skel->progs.stream_syscall), + BPF_STREAM_STDOUT, &opts); + if (!ASSERT_OK_FD(fd, "stream_open")) + goto out_destroy; + pfd.fd = fd; + + flags = fcntl(fd, F_GETFD); + ASSERT_GE(flags, 0, "getfd"); + ASSERT_NEQ(flags & FD_CLOEXEC, 0, "cloexec"); + flags = fcntl(fd, F_GETFL); + ASSERT_GE(flags, 0, "getfl"); + ASSERT_EQ(flags & O_ACCMODE, O_RDONLY, "readonly"); + ASSERT_NEQ(flags & O_NONBLOCK, 0, "nonblock"); + + ret = write(fd, "x", 1); + ASSERT_EQ(ret, -1, "write"); + ASSERT_EQ(errno, EBADF, "write_errno"); + ret = lseek(fd, 0, SEEK_SET); + ASSERT_EQ(ret, -1, "lseek"); + ASSERT_EQ(errno, ESPIPE, "lseek_errno"); + + ret = poll(&pfd, 1, 0); + ASSERT_EQ(ret, 0, "poll_empty"); + ret = read(fd, buf, sizeof(buf)); + ASSERT_EQ(ret, -1, "read_empty"); + ASSERT_EQ(errno, EAGAIN, "read_empty_errno"); + + if (!stream_fd_trigger(skel->progs.stream_syscall)) + goto out_close; + ret = poll(&pfd, 1, 0); + ASSERT_EQ(ret, 1, "poll_data"); + ASSERT_NEQ(pfd.revents & POLLIN, 0, "pollin"); + ASSERT_EQ(pfd.revents & POLLHUP, 0, "no_pollhup"); + + ret = read(fd, buf, 2); + ASSERT_EQ(ret, 2, "read_first"); + ASSERT_OK(memcmp(buf, "fo", 2), "read_first_data"); + pfd.revents = 0; + ret = poll(&pfd, 1, 0); + ASSERT_EQ(ret, 1, "poll_partial"); + ASSERT_NEQ(pfd.revents & POLLIN, 0, "pollin_partial"); + + ret = read(fd, buf, sizeof(buf)); + ASSERT_EQ(ret, 1, "read_rest"); + ASSERT_EQ(buf[0], 'o', "read_rest_data"); + ret = read(fd, buf, sizeof(buf)); + ASSERT_EQ(ret, -1, "read_drained"); + ASSERT_EQ(errno, EAGAIN, "read_drained_errno"); + +out_close: + close(fd); +out_destroy: + stream__destroy(skel); +} + +static void test_stream_fd_empty(void) +{ + LIBBPF_OPTS(bpf_prog_stream_open_opts, opts, + .flags = BPF_F_STREAM_NONBLOCK, + ); + struct pollfd pfd = { .events = POLLIN | POLLHUP }; + struct stream *skel; + char buf[4]; + int fd, ret; + + skel = stream__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stream__open_and_load")) + return; + + fd = bpf_prog_stream_open(bpf_program__fd(skel->progs.stream_empty), + BPF_STREAM_STDOUT, &opts); + if (!ASSERT_OK_FD(fd, "stream_open")) + goto out_destroy; + pfd.fd = fd; + + /* Empty output produces neither data nor readiness. */ + if (!stream_fd_trigger(skel->progs.stream_empty)) + goto out_close; + ret = poll(&pfd, 1, 0); + ASSERT_EQ(ret, 0, "poll_empty_write"); + ret = read(fd, buf, sizeof(buf)); + ASSERT_EQ(ret, -1, "read_empty_write"); + ASSERT_EQ(errno, EAGAIN, "read_empty_write_errno"); + +out_close: + close(fd); +out_destroy: + stream__destroy(skel); +} + +struct stream_fd_read_ctx { + int fd; + ssize_t ret; + char buf[4]; +}; + +static void *stream_fd_read_thread(void *arg) +{ + struct stream_fd_read_ctx *ctx = arg; + + ctx->ret = read(ctx->fd, ctx->buf, sizeof(ctx->buf)); + return NULL; +} + +static int stream_fd_timed_join(pthread_t thread) +{ + struct timespec timeout; + + clock_gettime(CLOCK_REALTIME, &timeout); + timeout.tv_sec += 5; + return pthread_timedjoin_np(thread, NULL, &timeout); +} + +static void test_stream_fd_blocking(void) +{ + struct stream_fd_read_ctx ctx = {}; + struct stream *skel; + pthread_t thread; + bool thread_live = false; + int fd, flags, ret; + + skel = stream__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stream__open_and_load")) + return; + + fd = bpf_prog_stream_open(bpf_program__fd(skel->progs.stream_syscall), + BPF_STREAM_STDOUT, NULL); + if (!ASSERT_OK_FD(fd, "stream_open")) + goto out_destroy; + ctx.fd = fd; + + flags = fcntl(fd, F_GETFL); + ASSERT_GE(flags, 0, "getfl"); + ASSERT_EQ(flags & O_NONBLOCK, 0, "blocking"); + + ret = pthread_create(&thread, NULL, stream_fd_read_thread, &ctx); + if (!ASSERT_OK(ret, "pthread_create")) + goto out_close; + thread_live = true; + + usleep(50000); + ret = pthread_tryjoin_np(thread, NULL); + if (!ASSERT_EQ(ret, EBUSY, "read_blocks")) { + thread_live = ret != 0; + goto out_thread; + } + if (!stream_fd_trigger(skel->progs.stream_syscall)) + goto out_thread; + + ret = stream_fd_timed_join(thread); + if (!ASSERT_OK(ret, "pthread_join")) + goto out_thread; + thread_live = false; + ASSERT_EQ(ctx.ret, 3, "read_len"); + ASSERT_OK(memcmp(ctx.buf, "foo", 3), "read_data"); + + memset(&ctx, 0, sizeof(ctx)); + ctx.fd = fd; + ret = pthread_create(&thread, NULL, stream_fd_read_thread, &ctx); + if (!ASSERT_OK(ret, "pthread_create_eof")) + goto out_close; + thread_live = true; + + usleep(50000); + ret = pthread_tryjoin_np(thread, NULL); + if (!ASSERT_EQ(ret, EBUSY, "read_eof_blocks")) { + thread_live = ret != 0; + goto out_thread; + } + + stream__destroy(skel); + skel = NULL; + ret = stream_fd_timed_join(thread); + if (!ASSERT_OK(ret, "pthread_join_eof")) + goto out_thread; + thread_live = false; + ASSERT_EQ(ctx.ret, 0, "read_eof"); + +out_thread: + if (thread_live) { + stream__destroy(skel); + skel = NULL; + ret = stream_fd_timed_join(thread); + if (ret) { + pthread_cancel(thread); + pthread_join(thread, NULL); + } + } +out_close: + close(fd); +out_destroy: + stream__destroy(skel); +} + +static void test_stream_fd_hup(void) +{ + LIBBPF_OPTS(bpf_prog_stream_open_opts, opts, + .flags = BPF_F_STREAM_NONBLOCK, + ); + struct epoll_event event = { + .events = EPOLLIN | EPOLLET, + }; + struct pollfd pfd = { .events = POLLIN | POLLHUP }; + struct stream *skel; + char buf[4] = {}; + int epfd = -1, fd, ret; + + skel = stream__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stream__open_and_load")) + return; + + fd = bpf_prog_stream_open(bpf_program__fd(skel->progs.stream_syscall), + BPF_STREAM_STDOUT, &opts); + if (!ASSERT_OK_FD(fd, "stream_open")) + goto out_destroy; + pfd.fd = fd; + epfd = epoll_create1(EPOLL_CLOEXEC); + if (!ASSERT_OK_FD(epfd, "epoll_create")) + goto out_close; + event.data.fd = fd; + ret = epoll_ctl(epfd, EPOLL_CTL_ADD, fd, &event); + if (!ASSERT_OK(ret, "epoll_ctl")) + goto out_close; + + if (!stream_fd_trigger(skel->progs.stream_syscall)) + goto out_close; + ret = epoll_wait(epfd, &event, 1, 5000); + if (!ASSERT_EQ(ret, 1, "epoll_wait_data")) + goto out_close; + ASSERT_NEQ(event.events & EPOLLIN, 0, "epollin"); + ASSERT_EQ(event.events & EPOLLHUP, 0, "no_epollhup"); + + stream__destroy(skel); + skel = NULL; + event.events = 0; + ret = epoll_wait(epfd, &event, 1, 5000); + if (!ASSERT_EQ(ret, 1, "epoll_wait_hup")) + goto out_close; + ASSERT_NEQ(event.events & EPOLLIN, 0, "epollin_with_hup"); + ASSERT_NEQ(event.events & EPOLLHUP, 0, "epollhup"); + + ret = read(fd, buf, sizeof(buf)); + ASSERT_EQ(ret, 3, "read_buffered"); + ASSERT_OK(memcmp(buf, "foo", 3), "read_buffered_data"); + pfd.revents = 0; + ret = poll(&pfd, 1, 0); + ASSERT_EQ(ret, 1, "poll_drained_hup"); + ASSERT_EQ(pfd.revents & POLLIN, 0, "no_pollin_after_drain"); + ASSERT_NEQ(pfd.revents & POLLHUP, 0, "pollhup_after_drain"); + ret = read(fd, buf, sizeof(buf)); + ASSERT_EQ(ret, 0, "read_eof"); + +out_close: + if (epfd >= 0) + close(epfd); + close(fd); +out_destroy: + stream__destroy(skel); +} + +static void test_stream_fd_edge(void) +{ + LIBBPF_OPTS(bpf_prog_stream_open_opts, opts, + .flags = BPF_F_STREAM_NONBLOCK, + ); + struct epoll_event event = { + .events = EPOLLIN | EPOLLET, + }; + struct stream *skel; + char buf[8] = {}; + int epfd = -1, fd, ret; + + skel = stream__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stream__open_and_load")) + return; + + fd = bpf_prog_stream_open(bpf_program__fd(skel->progs.stream_syscall), + BPF_STREAM_STDOUT, &opts); + if (!ASSERT_OK_FD(fd, "stream_open")) + goto out_destroy; + epfd = epoll_create1(EPOLL_CLOEXEC); + if (!ASSERT_OK_FD(epfd, "epoll_create")) + goto out_close; + event.data.fd = fd; + ret = epoll_ctl(epfd, EPOLL_CTL_ADD, fd, &event); + if (!ASSERT_OK(ret, "epoll_ctl")) + goto out_close; + + /* Output into an empty stream raises an edge. */ + if (!stream_fd_trigger(skel->progs.stream_syscall)) + goto out_close; + ret = epoll_wait(epfd, &event, 1, 5000); + if (!ASSERT_EQ(ret, 1, "epoll_wait_first")) + goto out_close; + ASSERT_NEQ(event.events & EPOLLIN, 0, "epollin_first"); + + /* + * Leave data behind, add more, then drain everything. Whether output + * into a non-empty stream raises an edge of its own is not part of the + * contract, so discard any pending event before re-arming the stream. + */ + ret = read(fd, buf, 2); + ASSERT_EQ(ret, 2, "read_partial"); + if (!stream_fd_trigger(skel->progs.stream_syscall)) + goto out_close; + ret = read(fd, buf, sizeof(buf)); + ASSERT_EQ(ret, 4, "read_rest"); + ASSERT_OK(memcmp(buf, "ofoo", 4), "read_rest_data"); + ret = read(fd, buf, sizeof(buf)); + ASSERT_EQ(ret, -1, "read_drained"); + ASSERT_EQ(errno, EAGAIN, "read_drained_errno"); + epoll_wait(epfd, &event, 1, 0); + + /* Output into the drained stream raises an edge again. */ + if (!stream_fd_trigger(skel->progs.stream_syscall)) + goto out_close; + ret = epoll_wait(epfd, &event, 1, 5000); + if (!ASSERT_EQ(ret, 1, "epoll_wait_after_drain")) + goto out_close; + ASSERT_NEQ(event.events & EPOLLIN, 0, "epollin_after_drain"); + +out_close: + if (epfd >= 0) + close(epfd); + close(fd); +out_destroy: + stream__destroy(skel); +} + +static void test_stream_fd_nmi_epoll(void) +{ + LIBBPF_OPTS(bpf_prog_stream_open_opts, opts, + .flags = BPF_F_STREAM_NONBLOCK, + ); + struct perf_event_attr attr = { + .size = sizeof(attr), + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .freq = 1, + .sample_freq = 10, + }; + struct epoll_event event = { + .events = EPOLLIN, + }; + struct bpf_link *link = NULL; + struct stream *skel; + __u64 deadline; + char buf[4] = {}; + int epfd = -1, fd = -1, pmu_fd = -1; + int ret; + + skel = stream__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stream__open_and_load")) + return; + fd = bpf_prog_stream_open(bpf_program__fd(skel->progs.stream_nmi), + BPF_STREAM_STDOUT, &opts); + if (!ASSERT_OK_FD(fd, "stream_open")) + goto out; + + epfd = epoll_create1(EPOLL_CLOEXEC); + if (!ASSERT_OK_FD(epfd, "epoll_create")) + goto out; + event.data.fd = fd; + ret = epoll_ctl(epfd, EPOLL_CTL_ADD, fd, &event); + if (!ASSERT_OK(ret, "epoll_ctl")) + goto out; + + pmu_fd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, + PERF_FLAG_FD_CLOEXEC); + if (pmu_fd < 0 && (errno == ENOENT || errno == EOPNOTSUPP)) { + printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__); + test__skip(); + goto out; + } + if (!ASSERT_GE(pmu_fd, 0, "perf_event_open")) + goto out; + + link = bpf_program__attach_perf_event(skel->progs.stream_nmi, pmu_fd); + if (!ASSERT_OK_PTR(link, "attach_perf_event")) { + link = NULL; + goto out; + } + pmu_fd = -1; + + deadline = get_time_ns() + NMI_TIMEOUT_NS; + do { + ret = epoll_wait(epfd, &event, 1, 0); + } while (ret == 0 && get_time_ns() < deadline); + if (!ASSERT_EQ(ret, 1, "epoll_wait")) + goto out; + ASSERT_NEQ(event.events & EPOLLIN, 0, "epollin"); + + ret = read(fd, buf, sizeof(buf)); + ASSERT_EQ(ret, 3, "read_len"); + ASSERT_OK(memcmp(buf, "nmi", 3), "read_data"); + +out: + bpf_link__destroy(link); + if (pmu_fd >= 0) + close(pmu_fd); + if (epfd >= 0) + close(epfd); + if (fd >= 0) + close(fd); + stream__destroy(skel); +} + +void test_stream_fd(void) +{ + if (test__start_subtest("open")) + test_stream_fd_open(); + if (test__start_subtest("nonblock")) + test_stream_fd_nonblock(); + if (test__start_subtest("empty")) + test_stream_fd_empty(); + if (test__start_subtest("blocking")) + test_stream_fd_blocking(); + if (test__start_subtest("hup")) + test_stream_fd_hup(); + if (test__start_subtest("edge")) + test_stream_fd_edge(); + if (test__start_subtest("nmi_epoll")) + test_stream_fd_nmi_epoll(); +} + void test_stream_oversize(void) { LIBBPF_OPTS(bpf_test_run_opts, opts); diff --git a/tools/testing/selftests/bpf/progs/stream.c b/tools/testing/selftests/bpf/progs/stream.c index 12fc29e45487..1ae015c4e6b4 100644 --- a/tools/testing/selftests/bpf/progs/stream.c +++ b/tools/testing/selftests/bpf/progs/stream.c @@ -44,6 +44,7 @@ struct { _X64 _X64 _X64 _X64 _X64 _X64 _X64 _X64) int size; +int nmi_stream_prints; u64 fault_addr; void *arena_ptr; @@ -124,6 +125,25 @@ int stream_syscall(void *ctx) return 0; } +SEC("syscall") +__success __retval(0) +int stream_empty(void *ctx) +{ + return bpf_stream_printk(BPF_STDOUT, ""); +} + +SEC("perf_event") +int stream_nmi(void *ctx) +{ + if (nmi_stream_prints) + return 0; + /* Retry on a later sample if the write failed, e.g. with -EBUSY. */ + if (bpf_stream_printk(BPF_STDOUT, "nmi")) + return 0; + nmi_stream_prints = 1; + return 0; +} + SEC("syscall") __success __retval(0) int stream_oversize(void *ctx)