From: Xu Kuohai When the bpf ring buffer is full, new events can not be recorded util the consumer consumes some events to free space. This may cause critical events to be discarded, such as in fault diagnostic, where recent events are more critical than older ones. So add ovewrite mode for bpf ring buffer. In this mode, the new event overwrites the oldest event when the buffer is full. The scheme is as follows: 1. producer_pos tracks the next position to write new data. When there is enough free space, producer simply moves producer_pos forward to make space for the new event. 2. To avoid waiting for consumer to free space when the buffer is full, a new variable overwrite_pos is introduced for producer. overwrite_pos tracks the next event to be overwritten (the oldest event committed) in the buffer. producer moves it forward to discard the oldest events when the buffer is full. 3. pending_pos tracks the oldest event under committing. producer ensures producers_pos never passes pending_pos when making space for new events. So multiple producers never write to the same position at the same time. 4. producer wakes up consumer every half a round ahead to give it a chance to retrieve data. However, for an overwrite-mode ring buffer, users typically only cares about the ring buffer snapshot before a fault occurs. In this case, the producer should commit data with BPF_RB_NO_WAKEUP flag to avoid unnecessary wakeups. The performance data for overwrite mode will be provided in a follow-up patch that adds overwrite mode benchs. A sample of performance data for non-overwrite mode on an x86_64 and arm64 CPU, before and after this patch, is shown below. As we can see, no obvious performance regression occurs. - x86_64 (AMD EPYC 9654) Before: Ringbuf, multi-producer contention ================================== rb-libbpf nr_prod 1 13.218 ± 0.039M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 15.684 ± 0.015M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 7.771 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 6.281 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 2.842 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 2.001 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 1.833 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 1.508 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 1.421 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 1.309 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 1.265 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 1.198 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 1.174 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 1.113 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 1.097 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 1.070 ± 0.002M/s (drops 0.000 ± 0.000M/s) After: Ringbuf, multi-producer contention ================================== rb-libbpf nr_prod 1 13.751 ± 0.673M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 15.592 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 7.776 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 6.463 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 2.883 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 2.017 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 1.816 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 1.512 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 1.396 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 1.303 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 1.267 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 1.210 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 1.181 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 1.136 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 1.090 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 1.091 ± 0.002M/s (drops 0.000 ± 0.000M/s) - arm64 (HiSilicon Kunpeng 920) Before: Ringbuf, multi-producer contention ================================== rb-libbpf nr_prod 1 11.602 ± 0.423M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 9.599 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 6.669 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 4.806 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 3.856 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 3.368 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 3.210 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 3.003 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 2.944 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 2.863 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 2.819 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 2.887 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 2.837 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 2.787 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 2.738 ± 0.010M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 2.700 ± 0.007M/s (drops 0.000 ± 0.000M/s) After: Ringbuf, multi-producer contention ================================== rb-libbpf nr_prod 1 11.614 ± 0.268M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 9.917 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 6.920 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 4.803 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 3.898 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 3.426 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 3.320 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 3.029 ± 0.013M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 3.068 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 2.890 ± 0.009M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 2.950 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 2.812 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 2.834 ± 0.009M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 2.803 ± 0.010M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 2.766 ± 0.010M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 2.754 ± 0.009M/s (drops 0.000 ± 0.000M/s) Signed-off-by: Xu Kuohai --- include/uapi/linux/bpf.h | 4 + kernel/bpf/ringbuf.c | 159 +++++++++++++++++++++++++++------ tools/include/uapi/linux/bpf.h | 4 + 3 files changed, 141 insertions(+), 26 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 233de8677382..d3b2fd2ae527 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1430,6 +1430,9 @@ enum { /* Do not translate kernel bpf_arena pointers to user pointers */ BPF_F_NO_USER_CONV = (1U << 18), + +/* bpf ringbuf works in overwrite mode? */ + BPF_F_OVERWRITE = (1U << 19), }; /* Flags for BPF_PROG_QUERY. */ @@ -6215,6 +6218,7 @@ enum { BPF_RB_RING_SIZE = 1, BPF_RB_CONS_POS = 2, BPF_RB_PROD_POS = 3, + BPF_RB_OVER_POS = 4, }; /* BPF ring buffer constants */ diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 719d73299397..6ca41d01f187 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -13,7 +13,7 @@ #include #include -#define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) +#define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE | BPF_F_OVERWRITE) /* non-mmap()'able part of bpf_ringbuf (everything up to consumer page) */ #define RINGBUF_PGOFF \ @@ -27,7 +27,8 @@ struct bpf_ringbuf { wait_queue_head_t waitq; struct irq_work work; - u64 mask; + u64 mask:48; + u64 overwrite_mode:1; struct page **pages; int nr_pages; rqspinlock_t spinlock ____cacheline_aligned_in_smp; @@ -72,6 +73,7 @@ struct bpf_ringbuf { */ unsigned long consumer_pos __aligned(PAGE_SIZE); unsigned long producer_pos __aligned(PAGE_SIZE); + unsigned long overwrite_pos; /* to be overwritten in overwrite mode */ unsigned long pending_pos; char data[] __aligned(PAGE_SIZE); }; @@ -166,7 +168,8 @@ static void bpf_ringbuf_notify(struct irq_work *work) * considering that the maximum value of data_sz is (4GB - 1), there * will be no overflow, so just note the size limit in the comments. */ -static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) +static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node, + int overwrite_mode) { struct bpf_ringbuf *rb; @@ -183,17 +186,25 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) rb->consumer_pos = 0; rb->producer_pos = 0; rb->pending_pos = 0; + rb->overwrite_mode = overwrite_mode; return rb; } static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) { + int overwrite_mode = 0; struct bpf_ringbuf_map *rb_map; if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); + if (attr->map_flags & BPF_F_OVERWRITE) { + if (attr->map_type == BPF_MAP_TYPE_USER_RINGBUF) + return ERR_PTR(-EINVAL); + overwrite_mode = 1; + } + if (attr->key_size || attr->value_size || !is_power_of_2(attr->max_entries) || !PAGE_ALIGNED(attr->max_entries)) @@ -205,7 +216,8 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) bpf_map_init_from_attr(&rb_map->map, attr); - rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); + rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node, + overwrite_mode); if (!rb_map->rb) { bpf_map_area_free(rb_map); return ERR_PTR(-ENOMEM); @@ -295,11 +307,16 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb) { - unsigned long cons_pos, prod_pos; + unsigned long cons_pos, prod_pos, over_pos; cons_pos = smp_load_acquire(&rb->consumer_pos); prod_pos = smp_load_acquire(&rb->producer_pos); - return prod_pos - cons_pos; + + if (likely(!rb->overwrite_mode)) + return prod_pos - cons_pos; + + over_pos = READ_ONCE(rb->overwrite_pos); + return min(prod_pos - max(cons_pos, over_pos), rb->mask + 1); } static u32 ringbuf_total_data_sz(const struct bpf_ringbuf *rb) @@ -402,11 +419,43 @@ bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) return (void*)((addr & PAGE_MASK) - off); } + +static bool bpf_ringbuf_has_space(const struct bpf_ringbuf *rb, + unsigned long new_prod_pos, + unsigned long cons_pos, + unsigned long pend_pos) +{ + /* no space if oldest not yet committed record until the newest + * record span more than (ringbuf_size - 1) + */ + if (new_prod_pos - pend_pos > rb->mask) + return false; + + /* ok, we have space in ovewrite mode */ + if (unlikely(rb->overwrite_mode)) + return true; + + /* no space if producer position advances more than (ringbuf_size - 1) + * ahead than consumer position when not in overwrite mode + */ + if (new_prod_pos - cons_pos > rb->mask) + return false; + + return true; +} + +static u32 ringbuf_round_up_hdr_len(u32 hdr_len) +{ + hdr_len &= ~BPF_RINGBUF_DISCARD_BIT; + return round_up(hdr_len + BPF_RINGBUF_HDR_SZ, 8); +} + static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) { - unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, flags; + unsigned long flags; struct bpf_ringbuf_hdr *hdr; - u32 len, pg_off, tmp_size, hdr_len; + u32 len, pg_off, hdr_len; + unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, over_pos; if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) return NULL; @@ -429,24 +478,39 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) hdr_len = READ_ONCE(hdr->len); if (hdr_len & BPF_RINGBUF_BUSY_BIT) break; - tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT; - tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8); - pend_pos += tmp_size; + pend_pos += ringbuf_round_up_hdr_len(hdr_len); } rb->pending_pos = pend_pos; - /* check for out of ringbuf space: - * - by ensuring producer position doesn't advance more than - * (ringbuf_size - 1) ahead - * - by ensuring oldest not yet committed record until newest - * record does not span more than (ringbuf_size - 1) - */ - if (new_prod_pos - cons_pos > rb->mask || - new_prod_pos - pend_pos > rb->mask) { + if (!bpf_ringbuf_has_space(rb, new_prod_pos, cons_pos, pend_pos)) { raw_res_spin_unlock_irqrestore(&rb->spinlock, flags); return NULL; } + /* In overwrite mode, move overwrite_pos to the next record to be + * overwritten if the ring buffer is full + */ + if (unlikely(rb->overwrite_mode)) { + over_pos = rb->overwrite_pos; + while (new_prod_pos - over_pos > rb->mask) { + hdr = (void *)rb->data + (over_pos & rb->mask); + hdr_len = READ_ONCE(hdr->len); + /* since pending_pos is the first record with BUSY + * bit set and overwrite_pos is never bigger than + * pending_pos, no need to check BUSY bit here. + */ + over_pos += ringbuf_round_up_hdr_len(hdr_len); + } + /* smp_store_release(&rb->producer_pos, new_prod_pos) at + * the end of the function ensures that when consumer sees + * the updated rb->producer_pos, it always sees the updated + * rb->overwrite_pos, so when consumer reads overwrite_pos + * after smp_load_acquire(r->producer_pos), the overwrite_pos + * will always be valid. + */ + WRITE_ONCE(rb->overwrite_pos, over_pos); + } + hdr = (void *)rb->data + (prod_pos & rb->mask); pg_off = bpf_ringbuf_rec_pg_off(rb, hdr); hdr->len = size | BPF_RINGBUF_BUSY_BIT; @@ -479,7 +543,50 @@ const struct bpf_func_proto bpf_ringbuf_reserve_proto = { .arg3_type = ARG_ANYTHING, }; -static void bpf_ringbuf_commit(void *sample, u64 flags, bool discard) +static __always_inline +bool ringbuf_should_wakeup(const struct bpf_ringbuf *rb, + unsigned long rec_pos, + unsigned long cons_pos, + u32 len, u64 flags) +{ + unsigned long rec_end; + + if (flags & BPF_RB_FORCE_WAKEUP) + return true; + + if (flags & BPF_RB_NO_WAKEUP) + return false; + + /* for non-overwrite mode, if consumer caught up and is waiting for + * our record, notify about new data availability + */ + if (likely(!rb->overwrite_mode)) + return cons_pos == rec_pos; + + /* for overwrite mode, to give the consumer a chance to catch up + * before being overwritten, wake up consumer every half a round + * ahead. + */ + rec_end = rec_pos + ringbuf_round_up_hdr_len(len); + + cons_pos &= (rb->mask >> 1); + rec_pos &= (rb->mask >> 1); + rec_end &= (rb->mask >> 1); + + if (cons_pos == rec_pos) + return true; + + if (rec_pos < cons_pos && cons_pos < rec_end) + return true; + + if (rec_end < rec_pos && (cons_pos > rec_pos || cons_pos < rec_end)) + return true; + + return false; +} + +static __always_inline +void bpf_ringbuf_commit(void *sample, u64 flags, bool discard) { unsigned long rec_pos, cons_pos; struct bpf_ringbuf_hdr *hdr; @@ -495,15 +602,10 @@ static void bpf_ringbuf_commit(void *sample, u64 flags, bool discard) /* update record header with correct final size prefix */ xchg(&hdr->len, new_len); - /* if consumer caught up and is waiting for our record, notify about - * new data availability - */ rec_pos = (void *)hdr - (void *)rb->data; cons_pos = smp_load_acquire(&rb->consumer_pos) & rb->mask; - if (flags & BPF_RB_FORCE_WAKEUP) - irq_work_queue(&rb->work); - else if (cons_pos == rec_pos && !(flags & BPF_RB_NO_WAKEUP)) + if (ringbuf_should_wakeup(rb, rec_pos, cons_pos, new_len, flags)) irq_work_queue(&rb->work); } @@ -576,6 +678,8 @@ BPF_CALL_2(bpf_ringbuf_query, struct bpf_map *, map, u64, flags) return smp_load_acquire(&rb->consumer_pos); case BPF_RB_PROD_POS: return smp_load_acquire(&rb->producer_pos); + case BPF_RB_OVER_POS: + return READ_ONCE(rb->overwrite_pos); default: return 0; } @@ -749,6 +853,9 @@ BPF_CALL_4(bpf_user_ringbuf_drain, struct bpf_map *, map, rb = container_of(map, struct bpf_ringbuf_map, map)->rb; + if (unlikely(rb->overwrite_mode)) + return -EOPNOTSUPP; + /* If another consumer is already consuming a sample, wait for them to finish. */ if (!atomic_try_cmpxchg(&rb->busy, &busy, 1)) return -EBUSY; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 233de8677382..d3b2fd2ae527 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1430,6 +1430,9 @@ enum { /* Do not translate kernel bpf_arena pointers to user pointers */ BPF_F_NO_USER_CONV = (1U << 18), + +/* bpf ringbuf works in overwrite mode? */ + BPF_F_OVERWRITE = (1U << 19), }; /* Flags for BPF_PROG_QUERY. */ @@ -6215,6 +6218,7 @@ enum { BPF_RB_RING_SIZE = 1, BPF_RB_CONS_POS = 2, BPF_RB_PROD_POS = 3, + BPF_RB_OVER_POS = 4, }; /* BPF ring buffer constants */ -- 2.43.0 From: Xu Kuohai In overwrite mode, the producer does not wait for the consumer, so the consumer is responsible for handling conflicts. An optimistic method is used to resolve the conflicts: the consumer first reads consumer_pos, producer_pos and overwrite_pos, then calculates a read window and copies data in the window from the ring buffer. After copying, it checks the positions to decide if the data in the copy window have been overwritten by be the producer. If so, it discards the copy and tries again. Once success, the consumer processes the events in the copy. Signed-off-by: Xu Kuohai --- tools/lib/bpf/ringbuf.c | 103 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 102 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 9702b70da444..9c072af675ff 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -27,10 +27,13 @@ struct ring { ring_buffer_sample_fn sample_cb; void *ctx; void *data; + void *read_buffer; unsigned long *consumer_pos; unsigned long *producer_pos; + unsigned long *overwrite_pos; unsigned long mask; int map_fd; + bool overwrite_mode; }; struct ring_buffer { @@ -69,6 +72,9 @@ static void ringbuf_free_ring(struct ring_buffer *rb, struct ring *r) r->producer_pos = NULL; } + if (r->read_buffer) + free(r->read_buffer); + free(r); } @@ -119,6 +125,14 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, r->sample_cb = sample_cb; r->ctx = ctx; r->mask = info.max_entries - 1; + r->overwrite_mode = info.map_flags & BPF_F_OVERWRITE; + if (unlikely(r->overwrite_mode)) { + r->read_buffer = malloc(info.max_entries); + if (!r->read_buffer) { + err = -ENOMEM; + goto err_out; + } + } /* Map writable consumer page */ tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0); @@ -148,6 +162,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, goto err_out; } r->producer_pos = tmp; + r->overwrite_pos = r->producer_pos + 1; /* overwrite_pos is next to producer_pos */ r->data = tmp + rb->page_size; e = &rb->events[rb->ring_cnt]; @@ -232,7 +247,7 @@ static inline int roundup_len(__u32 len) return (len + 7) / 8 * 8; } -static int64_t ringbuf_process_ring(struct ring *r, size_t n) +static int64_t ringbuf_process_normal_ring(struct ring *r, size_t n) { int *len_ptr, len, err; /* 64-bit to avoid overflow in case of extreme application behavior */ @@ -278,6 +293,92 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n) return cnt; } +static int64_t ringbuf_process_overwrite_ring(struct ring *r, size_t n) +{ + + int err; + uint32_t *len_ptr, len; + /* 64-bit to avoid overflow in case of extreme application behavior */ + int64_t cnt = 0; + size_t size, offset; + unsigned long cons_pos, prod_pos, over_pos, tmp_pos; + bool got_new_data; + void *sample; + bool copied; + + size = r->mask + 1; + + cons_pos = smp_load_acquire(r->consumer_pos); + do { + got_new_data = false; + + /* grab a copy of data */ + prod_pos = smp_load_acquire(r->producer_pos); + do { + over_pos = READ_ONCE(*r->overwrite_pos); + /* prod_pos may be outdated now */ + if (over_pos < prod_pos) { + tmp_pos = max(cons_pos, over_pos); + /* smp_load_acquire(r->producer_pos) before + * READ_ONCE(*r->overwrite_pos) ensures that + * over_pos + r->mask < prod_pos never occurs, + * so size is never larger than r->mask + */ + size = prod_pos - tmp_pos; + if (!size) + goto done; + memcpy(r->read_buffer, + r->data + (tmp_pos & r->mask), size); + copied = true; + } else { + copied = false; + } + prod_pos = smp_load_acquire(r->producer_pos); + /* retry if data is overwritten by producer */ + } while (!copied || prod_pos - tmp_pos > r->mask); + + cons_pos = tmp_pos; + + for (offset = 0; offset < size; offset += roundup_len(len)) { + len_ptr = r->read_buffer + (offset & r->mask); + len = *len_ptr; + + if (len & BPF_RINGBUF_BUSY_BIT) + goto done; + + got_new_data = true; + cons_pos += roundup_len(len); + + if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) { + sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ; + err = r->sample_cb(r->ctx, sample, len); + if (err < 0) { + /* update consumer pos and bail out */ + smp_store_release(r->consumer_pos, + cons_pos); + return err; + } + cnt++; + } + + if (cnt >= n) + goto done; + } + } while (got_new_data); + +done: + smp_store_release(r->consumer_pos, cons_pos); + return cnt; +} + +static int64_t ringbuf_process_ring(struct ring *r, size_t n) +{ + if (likely(!r->overwrite_mode)) + return ringbuf_process_normal_ring(r, n); + else + return ringbuf_process_overwrite_ring(r, n); +} + /* Consume available ring buffer(s) data without event polling, up to n * records. * -- 2.43.0 From: Xu Kuohai Add test for overwiret mode ring buffer. Signed-off-by: Xu Kuohai --- tools/testing/selftests/bpf/Makefile | 3 +- .../selftests/bpf/prog_tests/ringbuf.c | 74 ++++++++++++++ .../bpf/progs/test_ringbuf_overwrite.c | 98 +++++++++++++++++++ 3 files changed, 174 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 4863106034df..8a3796a2e5f5 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -499,7 +499,8 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c \ trace_printk.c trace_vprintk.c map_ptr_kern.c \ core_kern.c core_kern_overflow.c test_ringbuf.c \ - test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c + test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c \ + test_ringbuf_overwrite.c # Generate both light skeleton and libbpf skeleton for these LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \ diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index d1e4cb28a72c..205a51c725a7 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -17,6 +17,7 @@ #include "test_ringbuf_n.lskel.h" #include "test_ringbuf_map_key.lskel.h" #include "test_ringbuf_write.lskel.h" +#include "test_ringbuf_overwrite.lskel.h" #define EDONE 7777 @@ -497,6 +498,77 @@ static void ringbuf_map_key_subtest(void) test_ringbuf_map_key_lskel__destroy(skel_map_key); } +static void ringbuf_overwrite_mode_subtest(void) +{ + unsigned long size, len1, len2, len3, len4, len5; + unsigned long expect_avail_data, expect_prod_pos, expect_over_pos; + struct test_ringbuf_overwrite_lskel *skel; + int err; + + skel = test_ringbuf_overwrite_lskel__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + size = 0x1000; + len1 = 0x800; + len2 = 0x400; + len3 = size - len1 - len2 - BPF_RINGBUF_HDR_SZ * 3; /* 0x3e8 */ + len4 = len3 - 8; /* 0x3e0 */ + len5 = len3; /* retry with len3 */ + + skel->maps.ringbuf.max_entries = size; + skel->rodata->LEN1 = len1; + skel->rodata->LEN2 = len2; + skel->rodata->LEN3 = len3; + skel->rodata->LEN4 = len4; + skel->rodata->LEN5 = len5; + + skel->bss->pid = getpid(); + + err = test_ringbuf_overwrite_lskel__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + err = test_ringbuf_overwrite_lskel__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + syscall(__NR_getpgid); + + ASSERT_EQ(skel->bss->reserve1_fail, 0, "reserve 1"); + ASSERT_EQ(skel->bss->reserve2_fail, 0, "reserve 2"); + ASSERT_EQ(skel->bss->reserve3_fail, 1, "reserve 3"); + ASSERT_EQ(skel->bss->reserve4_fail, 0, "reserve 4"); + ASSERT_EQ(skel->bss->reserve5_fail, 0, "reserve 5"); + + CHECK(skel->bss->ring_size != size, + "check_ring_size", "exp %lu, got %lu\n", + size, skel->bss->ring_size); + + expect_avail_data = len2 + len4 + len5 + 3 * BPF_RINGBUF_HDR_SZ; + CHECK(skel->bss->avail_data != expect_avail_data, + "check_avail_size", "exp %lu, got %lu\n", + expect_avail_data, skel->bss->avail_data); + + CHECK(skel->bss->cons_pos != 0, + "check_cons_pos", "exp 0, got %lu\n", + skel->bss->cons_pos); + + expect_prod_pos = len1 + len2 + len4 + len5 + 4 * BPF_RINGBUF_HDR_SZ; + CHECK(skel->bss->prod_pos != expect_prod_pos, + "check_prod_pos", "exp %lu, got %lu\n", + expect_prod_pos, skel->bss->prod_pos); + + expect_over_pos = len1 + BPF_RINGBUF_HDR_SZ; + CHECK(skel->bss->over_pos != expect_over_pos, + "check_over_pos", "exp %lu, got %lu\n", + (unsigned long)expect_over_pos, skel->bss->over_pos); + + test_ringbuf_overwrite_lskel__detach(skel); +cleanup: + test_ringbuf_overwrite_lskel__destroy(skel); +} + void test_ringbuf(void) { if (test__start_subtest("ringbuf")) @@ -507,4 +579,6 @@ void test_ringbuf(void) ringbuf_map_key_subtest(); if (test__start_subtest("ringbuf_write")) ringbuf_write_subtest(); + if (test__start_subtest("ringbuf_overwrite_mode")) + ringbuf_overwrite_mode_subtest(); } diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c b/tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c new file mode 100644 index 000000000000..da89ba12a75c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025. Huawei Technologies Co., Ltd */ + +#include +#include +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(map_flags, BPF_F_OVERWRITE); +} ringbuf SEC(".maps"); + +int pid; + +const volatile unsigned long LEN1; +const volatile unsigned long LEN2; +const volatile unsigned long LEN3; +const volatile unsigned long LEN4; +const volatile unsigned long LEN5; + +long reserve1_fail = 0; +long reserve2_fail = 0; +long reserve3_fail = 0; +long reserve4_fail = 0; +long reserve5_fail = 0; + +unsigned long avail_data = 0; +unsigned long ring_size = 0; +unsigned long cons_pos = 0; +unsigned long prod_pos = 0; +unsigned long over_pos = 0; + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int test_overwrite_ringbuf(void *ctx) +{ + char *rec1, *rec2, *rec3, *rec4, *rec5; + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + if (cur_pid != pid) + return 0; + + rec1 = bpf_ringbuf_reserve(&ringbuf, LEN1, 0); + if (!rec1) { + reserve1_fail = 1; + return 0; + } + + rec2 = bpf_ringbuf_reserve(&ringbuf, LEN2, 0); + if (!rec2) { + bpf_ringbuf_discard(rec1, 0); + reserve2_fail = 1; + return 0; + } + + rec3 = bpf_ringbuf_reserve(&ringbuf, LEN3, 0); + /* expect failure */ + if (!rec3) { + reserve3_fail = 1; + } else { + bpf_ringbuf_discard(rec1, 0); + bpf_ringbuf_discard(rec2, 0); + bpf_ringbuf_discard(rec3, 0); + return 0; + } + + rec4 = bpf_ringbuf_reserve(&ringbuf, LEN4, 0); + if (!rec4) { + reserve4_fail = 1; + bpf_ringbuf_discard(rec1, 0); + bpf_ringbuf_discard(rec2, 0); + return 0; + } + + bpf_ringbuf_submit(rec1, 0); + bpf_ringbuf_submit(rec2, 0); + bpf_ringbuf_submit(rec4, 0); + + rec5 = bpf_ringbuf_reserve(&ringbuf, LEN5, 0); + if (!rec5) { + reserve5_fail = 1; + return 0; + } + + for (int i = 0; i < LEN3; i++) + rec5[i] = 0xdd; + + bpf_ringbuf_submit(rec5, 0); + + ring_size = bpf_ringbuf_query(&ringbuf, BPF_RB_RING_SIZE); + avail_data = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA); + cons_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_CONS_POS); + prod_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_PROD_POS); + over_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_OVER_POS); + + return 0; +} -- 2.43.0 From: Xu Kuohai Add overwrite mode bench for ring buffer. For reference, below are bench numbers collected from x86_64 and arm64. - x86_64 (AMD EPYC 9654) Ringbuf, multi-producer contention, overwrite mode ================================================== rb-libbpf nr_prod 1 14.970 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 14.064 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 7.493 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 6.575 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 3.696 ± 0.011M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 2.612 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 2.335 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 2.079 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 1.965 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 1.846 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 1.790 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 1.735 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 1.701 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 1.669 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 1.749 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 1.709 ± 0.001M/s (drops 0.000 ± 0.000M/s) - arm64 (HiSilicon Kunpeng 920) Ringbuf, multi-producer contention, overwrite mode ================================================== rb-libbpf nr_prod 1 10.319 ± 0.231M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 9.219 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 6.699 ± 0.013M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 4.608 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 3.905 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 3.282 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 3.182 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 3.029 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 3.116 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 2.869 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 3.075 ± 0.010M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 2.795 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 2.947 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 2.748 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 2.767 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 2.858 ± 0.002M/s (drops 0.000 ± 0.000M/s) Signed-off-by: Xu Kuohai --- .../selftests/bpf/benchs/bench_ringbufs.c | 22 ++++++++++++++++++- .../bpf/benchs/run_bench_ringbufs.sh | 4 ++++ 2 files changed, 25 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index e1ee979e6acc..6fdfc61c721b 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -19,6 +19,7 @@ static struct { int ringbuf_sz; /* per-ringbuf, in bytes */ bool ringbuf_use_output; /* use slower output API */ int perfbuf_sz; /* per-CPU size, in pages */ + bool overwrite_mode; } args = { .back2back = false, .batch_cnt = 500, @@ -27,6 +28,7 @@ static struct { .ringbuf_sz = 512 * 1024, .ringbuf_use_output = false, .perfbuf_sz = 128, + .overwrite_mode = false, }; enum { @@ -35,6 +37,7 @@ enum { ARG_RB_BATCH_CNT = 2002, ARG_RB_SAMPLED = 2003, ARG_RB_SAMPLE_RATE = 2004, + ARG_RB_OVERWRITE = 2005, }; static const struct argp_option opts[] = { @@ -43,6 +46,7 @@ static const struct argp_option opts[] = { { "rb-batch-cnt", ARG_RB_BATCH_CNT, "CNT", 0, "Set BPF-side record batch count"}, { "rb-sampled", ARG_RB_SAMPLED, NULL, 0, "Notification sampling"}, { "rb-sample-rate", ARG_RB_SAMPLE_RATE, "RATE", 0, "Notification sample rate"}, + { "rb-overwrite", ARG_RB_OVERWRITE, NULL, 0, "overwrite mode"}, {}, }; @@ -72,6 +76,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) argp_usage(state); } break; + case ARG_RB_OVERWRITE: + args.overwrite_mode = true; + break; default: return ARGP_ERR_UNKNOWN; } @@ -104,6 +111,11 @@ static void bufs_validate(void) fprintf(stderr, "back-to-back mode makes sense only for single-producer case!\n"); exit(1); } + + if (args.overwrite_mode && strcmp(env.bench_name, "rb-libbpf") != 0) { + fprintf(stderr, "rb-overwrite mode only supports rb-libbpf!\n"); + exit(1); + } } static void *bufs_sample_producer(void *input) @@ -134,6 +146,8 @@ static void ringbuf_libbpf_measure(struct bench_res *res) static struct ringbuf_bench *ringbuf_setup_skeleton(void) { + __u32 flags; + struct bpf_map *ringbuf; struct ringbuf_bench *skel; setup_libbpf(); @@ -151,7 +165,13 @@ static struct ringbuf_bench *ringbuf_setup_skeleton(void) /* record data + header take 16 bytes */ skel->rodata->wakeup_data_size = args.sample_rate * 16; - bpf_map__set_max_entries(skel->maps.ringbuf, args.ringbuf_sz); + ringbuf = skel->maps.ringbuf; + if (args.overwrite_mode) { + flags = bpf_map__map_flags(ringbuf) | BPF_F_OVERWRITE; + bpf_map__set_map_flags(ringbuf, flags); + } + + bpf_map__set_max_entries(ringbuf, args.ringbuf_sz); if (ringbuf_bench__load(skel)) { fprintf(stderr, "failed to load skeleton\n"); diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh index 91e3567962ff..4e758bc52b73 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh @@ -49,3 +49,7 @@ for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do summarize "rb-libbpf nr_prod $b" "$($RUN_RB_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)" done +header "Ringbuf, multi-producer contention, overwrite mode" +for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do + summarize "rb-libbpf nr_prod $b" "$($RUN_RB_BENCH -p$b --rb-overwrite --rb-batch-cnt 50 rb-libbpf)" +done -- 2.43.0