* Re: [PATCH net-next v2 3/5] virtio_ring: add packed ring support
From: Michael S. Tsirkin @ 2018-11-07 17:48 UTC (permalink / raw)
To: Tiwei Bie
Cc: jasowang, virtualization, linux-kernel, netdev, virtio-dev, wexu,
jfreimann
In-Reply-To: <20180711022711.7090-4-tiwei.bie@intel.com>
On Wed, Jul 11, 2018 at 10:27:09AM +0800, Tiwei Bie wrote:
> This commit introduces the support (without EVENT_IDX) for
> packed ring.
>
> Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
> ---
> drivers/virtio/virtio_ring.c | 495 ++++++++++++++++++++++++++++++++++-
> 1 file changed, 487 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
> index c4f8abc7445a..f317b485ba54 100644
> --- a/drivers/virtio/virtio_ring.c
> +++ b/drivers/virtio/virtio_ring.c
> @@ -55,12 +55,21 @@
> #define END_USE(vq)
> #endif
>
> +#define _VRING_DESC_F_AVAIL(b) ((__u16)(b) << 7)
> +#define _VRING_DESC_F_USED(b) ((__u16)(b) << 15)
> +
> struct vring_desc_state {
> void *data; /* Data for callback. */
> struct vring_desc *indir_desc; /* Indirect descriptor, if any. */
> };
>
> struct vring_desc_state_packed {
> + void *data; /* Data for callback. */
> + struct vring_packed_desc *indir_desc; /* Indirect descriptor, if any. */
> + int num; /* Descriptor list length. */
> + dma_addr_t addr; /* Buffer DMA addr. */
> + u32 len; /* Buffer length. */
> + u16 flags; /* Descriptor flags. */
> int next; /* The next desc state. */
> };
>
> @@ -660,7 +669,6 @@ static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
> {
> struct vring_virtqueue *vq = to_vvq(_vq);
>
> - virtio_mb(vq->weak_barriers);
> return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
> }
>
> @@ -757,6 +765,72 @@ static inline unsigned vring_size_packed(unsigned int num, unsigned long align)
> & ~(align - 1)) + sizeof(struct vring_packed_desc_event) * 2;
> }
>
> +static void vring_unmap_state_packed(const struct vring_virtqueue *vq,
> + struct vring_desc_state_packed *state)
> +{
> + u16 flags;
> +
> + if (!vring_use_dma_api(vq->vq.vdev))
> + return;
> +
> + flags = state->flags;
> +
> + if (flags & VRING_DESC_F_INDIRECT) {
> + dma_unmap_single(vring_dma_dev(vq),
> + state->addr, state->len,
> + (flags & VRING_DESC_F_WRITE) ?
> + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> + } else {
> + dma_unmap_page(vring_dma_dev(vq),
> + state->addr, state->len,
> + (flags & VRING_DESC_F_WRITE) ?
> + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> + }
> +}
> +
> +static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
> + struct vring_packed_desc *desc)
> +{
> + u16 flags;
> +
> + if (!vring_use_dma_api(vq->vq.vdev))
> + return;
> +
> + flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);
BTW this stuff is only used on error etc. Is there a way to
reuse vring_unmap_state_packed?
> +
> + if (flags & VRING_DESC_F_INDIRECT) {
> + dma_unmap_single(vring_dma_dev(vq),
> + virtio64_to_cpu(vq->vq.vdev, desc->addr),
> + virtio32_to_cpu(vq->vq.vdev, desc->len),
> + (flags & VRING_DESC_F_WRITE) ?
> + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> + } else {
> + dma_unmap_page(vring_dma_dev(vq),
> + virtio64_to_cpu(vq->vq.vdev, desc->addr),
> + virtio32_to_cpu(vq->vq.vdev, desc->len),
> + (flags & VRING_DESC_F_WRITE) ?
> + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> + }
> +}
> +
> +static struct vring_packed_desc *alloc_indirect_packed(struct virtqueue *_vq,
> + unsigned int total_sg,
> + gfp_t gfp)
> +{
> + struct vring_packed_desc *desc;
> +
> + /*
> + * We require lowmem mappings for the descriptors because
> + * otherwise virt_to_phys will give us bogus addresses in the
> + * virtqueue.
> + */
> + gfp &= ~__GFP_HIGHMEM;
> +
> + desc = kmalloc(total_sg * sizeof(struct vring_packed_desc), gfp);
> +
> + return desc;
> +}
> +
> static inline int virtqueue_add_packed(struct virtqueue *_vq,
> struct scatterlist *sgs[],
> unsigned int total_sg,
> @@ -766,47 +840,449 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
> void *ctx,
> gfp_t gfp)
> {
> + struct vring_virtqueue *vq = to_vvq(_vq);
> + struct vring_packed_desc *desc;
> + struct scatterlist *sg;
> + unsigned int i, n, descs_used, uninitialized_var(prev), err_idx;
> + __virtio16 uninitialized_var(head_flags), flags;
> + u16 head, avail_wrap_counter, id, curr;
> + bool indirect;
> +
> + START_USE(vq);
> +
> + BUG_ON(data == NULL);
> + BUG_ON(ctx && vq->indirect);
> +
> + if (unlikely(vq->broken)) {
> + END_USE(vq);
> + return -EIO;
> + }
> +
> +#ifdef DEBUG
> + {
> + ktime_t now = ktime_get();
> +
> + /* No kick or get, with .1 second between? Warn. */
> + if (vq->last_add_time_valid)
> + WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time))
> + > 100);
> + vq->last_add_time = now;
> + vq->last_add_time_valid = true;
> + }
> +#endif
> +
> + BUG_ON(total_sg == 0);
> +
> + head = vq->next_avail_idx;
> + avail_wrap_counter = vq->avail_wrap_counter;
> +
> + if (virtqueue_use_indirect(_vq, total_sg))
> + desc = alloc_indirect_packed(_vq, total_sg, gfp);
> + else {
> + desc = NULL;
> + WARN_ON_ONCE(total_sg > vq->vring_packed.num && !vq->indirect);
> + }
> +
> + if (desc) {
> + /* Use a single buffer which doesn't continue */
> + indirect = true;
> + /* Set up rest to use this indirect table. */
> + i = 0;
> + descs_used = 1;
> + } else {
> + indirect = false;
> + desc = vq->vring_packed.desc;
> + i = head;
> + descs_used = total_sg;
> + }
> +
> + if (vq->vq.num_free < descs_used) {
> + pr_debug("Can't add buf len %i - avail = %i\n",
> + descs_used, vq->vq.num_free);
> + /* FIXME: for historical reasons, we force a notify here if
> + * there are outgoing parts to the buffer. Presumably the
> + * host should service the ring ASAP. */
I don't think we have a reason to do this for packed ring.
No historical baggage there, right?
> + if (out_sgs)
> + vq->notify(&vq->vq);
> + if (indirect)
> + kfree(desc);
> + END_USE(vq);
> + return -ENOSPC;
> + }
> +
> + id = vq->free_head;
> + BUG_ON(id == vq->vring_packed.num);
> +
> + curr = id;
> + for (n = 0; n < out_sgs + in_sgs; n++) {
> + for (sg = sgs[n]; sg; sg = sg_next(sg)) {
> + dma_addr_t addr = vring_map_one_sg(vq, sg, n < out_sgs ?
> + DMA_TO_DEVICE : DMA_FROM_DEVICE);
> + if (vring_mapping_error(vq, addr))
> + goto unmap_release;
> +
> + flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT |
> + (n < out_sgs ? 0 : VRING_DESC_F_WRITE) |
> + _VRING_DESC_F_AVAIL(vq->avail_wrap_counter) |
> + _VRING_DESC_F_USED(!vq->avail_wrap_counter));
> + if (!indirect && i == head)
> + head_flags = flags;
> + else
> + desc[i].flags = flags;
> +
> + desc[i].addr = cpu_to_virtio64(_vq->vdev, addr);
> + desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
> + i++;
> + if (!indirect) {
> + if (vring_use_dma_api(_vq->vdev)) {
> + vq->desc_state_packed[curr].addr = addr;
> + vq->desc_state_packed[curr].len =
> + sg->length;
> + vq->desc_state_packed[curr].flags =
> + virtio16_to_cpu(_vq->vdev,
> + flags);
> + }
> + curr = vq->desc_state_packed[curr].next;
> +
> + if (i >= vq->vring_packed.num) {
> + i = 0;
> + vq->avail_wrap_counter ^= 1;
> + }
> + }
> + }
> + }
> +
> + prev = (i > 0 ? i : vq->vring_packed.num) - 1;
> + desc[prev].id = cpu_to_virtio16(_vq->vdev, id);
> +
> + /* Last one doesn't continue. */
> + if (total_sg == 1)
> + head_flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);
> + else
> + desc[prev].flags &= cpu_to_virtio16(_vq->vdev,
> + ~VRING_DESC_F_NEXT);
> +
> + if (indirect) {
> + /* Now that the indirect table is filled in, map it. */
> + dma_addr_t addr = vring_map_single(
> + vq, desc, total_sg * sizeof(struct vring_packed_desc),
> + DMA_TO_DEVICE);
> + if (vring_mapping_error(vq, addr))
> + goto unmap_release;
> +
> + head_flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT |
> + _VRING_DESC_F_AVAIL(avail_wrap_counter) |
> + _VRING_DESC_F_USED(!avail_wrap_counter));
> + vq->vring_packed.desc[head].addr = cpu_to_virtio64(_vq->vdev,
> + addr);
> + vq->vring_packed.desc[head].len = cpu_to_virtio32(_vq->vdev,
> + total_sg * sizeof(struct vring_packed_desc));
> + vq->vring_packed.desc[head].id = cpu_to_virtio16(_vq->vdev, id);
> +
> + if (vring_use_dma_api(_vq->vdev)) {
> + vq->desc_state_packed[id].addr = addr;
> + vq->desc_state_packed[id].len = total_sg *
> + sizeof(struct vring_packed_desc);
> + vq->desc_state_packed[id].flags =
> + virtio16_to_cpu(_vq->vdev, head_flags);
> + }
> + }
> +
> + /* We're using some buffers from the free list. */
> + vq->vq.num_free -= descs_used;
> +
> + /* Update free pointer */
> + if (indirect) {
> + n = head + 1;
> + if (n >= vq->vring_packed.num) {
> + n = 0;
> + vq->avail_wrap_counter ^= 1;
> + }
> + vq->next_avail_idx = n;
> + vq->free_head = vq->desc_state_packed[id].next;
> + } else {
> + vq->next_avail_idx = i;
> + vq->free_head = curr;
> + }
> +
> + /* Store token and indirect buffer state. */
> + vq->desc_state_packed[id].num = descs_used;
> + vq->desc_state_packed[id].data = data;
> + if (indirect)
> + vq->desc_state_packed[id].indir_desc = desc;
> + else
> + vq->desc_state_packed[id].indir_desc = ctx;
> +
> + /* A driver MUST NOT make the first descriptor in the list
> + * available before all subsequent descriptors comprising
> + * the list are made available. */
> + virtio_wmb(vq->weak_barriers);
> + vq->vring_packed.desc[head].flags = head_flags;
> + vq->num_added += descs_used;
> +
> + pr_debug("Added buffer head %i to %p\n", head, vq);
> + END_USE(vq);
> +
> + return 0;
> +
> +unmap_release:
> + err_idx = i;
> + i = head;
> +
> + for (n = 0; n < total_sg; n++) {
> + if (i == err_idx)
> + break;
> + vring_unmap_desc_packed(vq, &desc[i]);
> + i++;
> + if (!indirect && i >= vq->vring_packed.num)
> + i = 0;
> + }
> +
> + vq->avail_wrap_counter = avail_wrap_counter;
> +
> + if (indirect)
> + kfree(desc);
> +
> + END_USE(vq);
> return -EIO;
> }
>
> static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
> {
> - return false;
> + struct vring_virtqueue *vq = to_vvq(_vq);
> + u16 flags;
> + bool needs_kick;
> + u32 snapshot;
> +
> + START_USE(vq);
> + /* We need to expose the new flags value before checking notification
> + * suppressions. */
> + virtio_mb(vq->weak_barriers);
> +
> + snapshot = READ_ONCE(*(u32 *)vq->vring_packed.device);
> + flags = virtio16_to_cpu(_vq->vdev, (__virtio16)(snapshot >> 16)) & 0x3;
> +
> +#ifdef DEBUG
> + if (vq->last_add_time_valid) {
> + WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
> + vq->last_add_time)) > 100);
> + }
> + vq->last_add_time_valid = false;
> +#endif
> +
> + needs_kick = (flags != VRING_EVENT_F_DISABLE);
> + END_USE(vq);
> + return needs_kick;
> +}
> +
> +static void detach_buf_packed(struct vring_virtqueue *vq,
> + unsigned int id, void **ctx)
> +{
> + struct vring_desc_state_packed *state = NULL;
> + struct vring_packed_desc *desc;
> + unsigned int curr, i;
> +
> + /* Clear data ptr. */
> + vq->desc_state_packed[id].data = NULL;
> +
> + curr = id;
> + for (i = 0; i < vq->desc_state_packed[id].num; i++) {
> + state = &vq->desc_state_packed[curr];
> + vring_unmap_state_packed(vq, state);
> + curr = state->next;
> + }
> +
> + BUG_ON(state == NULL);
> + vq->vq.num_free += vq->desc_state_packed[id].num;
> + state->next = vq->free_head;
> + vq->free_head = id;
> +
> + if (vq->indirect) {
> + u32 len;
> +
> + /* Free the indirect table, if any, now that it's unmapped. */
> + desc = vq->desc_state_packed[id].indir_desc;
> + if (!desc)
> + return;
> +
> + if (vring_use_dma_api(vq->vq.vdev)) {
> + len = vq->desc_state_packed[id].len;
> + for (i = 0; i < len / sizeof(struct vring_packed_desc);
> + i++)
> + vring_unmap_desc_packed(vq, &desc[i]);
> + }
> + kfree(desc);
> + vq->desc_state_packed[id].indir_desc = NULL;
> + } else if (ctx) {
> + *ctx = vq->desc_state_packed[id].indir_desc;
> + }
> +}
> +
> +static inline bool is_used_desc_packed(const struct vring_virtqueue *vq,
> + u16 idx, bool used_wrap_counter)
> +{
> + u16 flags;
> + bool avail, used;
> +
> + flags = virtio16_to_cpu(vq->vq.vdev,
> + vq->vring_packed.desc[idx].flags);
> + avail = !!(flags & VRING_DESC_F_AVAIL);
> + used = !!(flags & VRING_DESC_F_USED);
> +
> + return avail == used && used == used_wrap_counter;
> }
>
> static inline bool more_used_packed(const struct vring_virtqueue *vq)
> {
> - return false;
> + return is_used_desc_packed(vq, vq->last_used_idx,
> + vq->used_wrap_counter);
> }
>
> static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
> unsigned int *len,
> void **ctx)
> {
> - return NULL;
> + struct vring_virtqueue *vq = to_vvq(_vq);
> + u16 last_used, id;
> + void *ret;
> +
> + START_USE(vq);
> +
> + if (unlikely(vq->broken)) {
> + END_USE(vq);
> + return NULL;
> + }
> +
> + if (!more_used_packed(vq)) {
> + pr_debug("No more buffers in queue\n");
> + END_USE(vq);
> + return NULL;
> + }
> +
> + /* Only get used elements after they have been exposed by host. */
> + virtio_rmb(vq->weak_barriers);
> +
> + last_used = vq->last_used_idx;
> + id = virtio16_to_cpu(_vq->vdev, vq->vring_packed.desc[last_used].id);
> + *len = virtio32_to_cpu(_vq->vdev, vq->vring_packed.desc[last_used].len);
> +
> + if (unlikely(id >= vq->vring_packed.num)) {
> + BAD_RING(vq, "id %u out of range\n", id);
> + return NULL;
> + }
> + if (unlikely(!vq->desc_state_packed[id].data)) {
> + BAD_RING(vq, "id %u is not a head!\n", id);
> + return NULL;
> + }
> +
> + vq->last_used_idx += vq->desc_state_packed[id].num;
> + if (vq->last_used_idx >= vq->vring_packed.num) {
> + vq->last_used_idx -= vq->vring_packed.num;
> + vq->used_wrap_counter ^= 1;
> + }
> +
> + /* detach_buf_packed clears data, so grab it now. */
> + ret = vq->desc_state_packed[id].data;
> + detach_buf_packed(vq, id, ctx);
> +
> +#ifdef DEBUG
> + vq->last_add_time_valid = false;
> +#endif
> +
> + END_USE(vq);
> + return ret;
> }
>
> static void virtqueue_disable_cb_packed(struct virtqueue *_vq)
> {
> + struct vring_virtqueue *vq = to_vvq(_vq);
> +
> + if (vq->event_flags_shadow != VRING_EVENT_F_DISABLE) {
> + vq->event_flags_shadow = VRING_EVENT_F_DISABLE;
> + vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev,
> + vq->event_flags_shadow);
> + }
> }
>
> static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq)
> {
> - return 0;
> + struct vring_virtqueue *vq = to_vvq(_vq);
> +
> + START_USE(vq);
> +
> + /* We optimistically turn back on interrupts, then check if there was
> + * more to do. */
> +
> + if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) {
> + vq->event_flags_shadow = VRING_EVENT_F_ENABLE;
> + vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev,
> + vq->event_flags_shadow);
> + }
> +
> + END_USE(vq);
> + return vq->last_used_idx | ((u16)vq->used_wrap_counter << 15);
> }
>
> -static bool virtqueue_poll_packed(struct virtqueue *_vq, unsigned last_used_idx)
> +static bool virtqueue_poll_packed(struct virtqueue *_vq, unsigned off_wrap)
> {
> - return false;
> + struct vring_virtqueue *vq = to_vvq(_vq);
> + bool wrap_counter;
> + u16 used_idx;
> +
> + wrap_counter = off_wrap >> 15;
> + used_idx = off_wrap & ~(1 << 15);
> +
> + return is_used_desc_packed(vq, used_idx, wrap_counter);
> }
>
> static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
> {
> - return false;
> + struct vring_virtqueue *vq = to_vvq(_vq);
> +
> + START_USE(vq);
> +
> + /* We optimistically turn back on interrupts, then check if there was
> + * more to do. */
> +
> + if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) {
> + vq->event_flags_shadow = VRING_EVENT_F_ENABLE;
> + vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev,
> + vq->event_flags_shadow);
> + /* We need to enable interrupts first before re-checking
> + * for more used buffers. */
> + virtio_mb(vq->weak_barriers);
> + }
> +
> + if (more_used_packed(vq)) {
> + END_USE(vq);
> + return false;
> + }
> +
> + END_USE(vq);
> + return true;
> }
>
> static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq)
> {
> + struct vring_virtqueue *vq = to_vvq(_vq);
> + unsigned int i;
> + void *buf;
> +
> + START_USE(vq);
> +
> + for (i = 0; i < vq->vring_packed.num; i++) {
> + if (!vq->desc_state_packed[i].data)
> + continue;
> + /* detach_buf clears data, so grab it now. */
> + buf = vq->desc_state_packed[i].data;
> + detach_buf_packed(vq, i, NULL);
> + END_USE(vq);
> + return buf;
> + }
> + /* That should have freed everything. */
> + BUG_ON(vq->vq.num_free != vq->vring_packed.num);
> +
> + END_USE(vq);
> return NULL;
> }
>
> @@ -1083,6 +1559,9 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
> {
> struct vring_virtqueue *vq = to_vvq(_vq);
>
> + /* We need to enable interrupts first before re-checking
> + * for more used buffers. */
> + virtio_mb(vq->weak_barriers);
> return vq->packed ? virtqueue_poll_packed(_vq, last_used_idx) :
> virtqueue_poll_split(_vq, last_used_idx);
> }
> --
> 2.18.0
^ permalink raw reply
* Re: [PATCH net-next] inet: minor optimization for backlog setting in listen(2)
From: Eric Dumazet @ 2018-11-07 18:03 UTC (permalink / raw)
To: Yafang Shao, davem, edumazet; +Cc: netdev, linux-kernel
In-Reply-To: <1541589617-1607-1-git-send-email-laoar.shao@gmail.com>
On 11/07/2018 03:20 AM, Yafang Shao wrote:
> Set the backlog earlier in inet_dccp_listen() and inet_listen(),
> then we can avoid the redundant setting.
>
> Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
> ---
>
Reviewed-by: Eric Dumazet <edumazet@google.com>
^ permalink raw reply
* Re: [RFC perf,bpf 5/5] perf util: generate bpf_prog_info_event for short living bpf programs
From: David Ahern @ 2018-11-07 18:12 UTC (permalink / raw)
To: Alexei Starovoitov, David Ahern, David Miller
Cc: Song Liu, netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
Kernel Team, ast@kernel.org, daniel@iogearbox.net,
peterz@infradead.org, acme@kernel.org
In-Reply-To: <edda462f-a32c-bc25-94c8-8d06a47bd480@fb.com>
On 11/6/18 6:09 PM, Alexei Starovoitov wrote:
> On 11/6/18 4:44 PM, David Ahern wrote:
>>
>> So one use case is profiling bpf programs. I was also considering the
>> auditing discussion from some weeks ago which I thought the events are
>> also targeting.
>
> yes. there should be separate mode for 're: audit discussion' where
> only bpf events are collected. This patch set doesn't add that to
> perf user space side.
> The kernel side is common though. It can be used for bpf load/unload
> only and for different use case in this set. Which is making
> bpf program appear in normal 'perf report'.
It would be good for perf-script to work in the next version. Users
should be able to dump the event from the kernel and the synthesized
events. Should be trivial to add and allows a review of both
perspectives -- profiling and monitoring events.
^ permalink raw reply
* Re: [RFC perf,bpf 1/5] perf, bpf: Introduce PERF_RECORD_BPF_EVENT
From: Song Liu @ 2018-11-07 18:25 UTC (permalink / raw)
To: Peter Zijlstra
Cc: Netdev, lkml, Kernel Team, ast@kernel.org, daniel@iogearbox.net,
acme@kernel.org
In-Reply-To: <20181107084057.GG9781@hirez.programming.kicks-ass.net>
> On Nov 7, 2018, at 12:40 AM, Peter Zijlstra <peterz@infradead.org> wrote:
>
> On Tue, Nov 06, 2018 at 12:52:42PM -0800, Song Liu wrote:
>> For better performance analysis of BPF programs, this patch introduces
>> PERF_RECORD_BPF_EVENT, a new perf_event_type that exposes BPF program
>> load/unload information to user space.
>>
>> /*
>> * Record different types of bpf events:
>> * enum perf_bpf_event_type {
>> * PERF_BPF_EVENT_UNKNOWN = 0,
>> * PERF_BPF_EVENT_PROG_LOAD = 1,
>> * PERF_BPF_EVENT_PROG_UNLOAD = 2,
>> * };
>> *
>> * struct {
>> * struct perf_event_header header;
>> * u16 type;
>> * u16 flags;
>> * u32 id; // prog_id or map_id
>> * };
>> */
>> PERF_RECORD_BPF_EVENT = 17,
>>
>> PERF_RECORD_BPF_EVENT contains minimal information about the BPF program.
>> Perf utility (or other user space tools) should listen to this event and
>> fetch more details about the event via BPF syscalls
>> (BPF_PROG_GET_FD_BY_ID, BPF_OBJ_GET_INFO_BY_FD, etc.).
>
> Why !? You're failing to explain why it cannot provide the full
> information there.
Aha, I missed this part. I will add the following to next version. Please
let me know if anything is not clear.
Thanks,
Song
This design decision is picked for the following reasons. First, BPF
programs could be loaded-and-jited and/or unloaded before/during/after
perf-record run. Once a BPF programs is unloaded, it is impossible to
recover details of the program. It is impossible to provide the
information through a simple key (like the build ID). Second, BPF prog
annotation is under fast developments. Multiple informations will be
added to bpf_prog_info in the next few releases. Including all the
information of a BPF program in the perf ring buffer requires frequent
changes to the perf ABI, and thus makes it very difficult to manage
compatibility of perf utility.
For more information on this topic, please refer to the following
discussions:
https://www.spinics.net/lists/netdev/msg524230.html
^ permalink raw reply
* Re: [RFC perf,bpf 5/5] perf util: generate bpf_prog_info_event for short living bpf programs
From: Song Liu @ 2018-11-07 18:28 UTC (permalink / raw)
To: David Ahern
Cc: Alexei Starovoitov, David Miller, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org, Kernel Team, ast@kernel.org,
daniel@iogearbox.net, peterz@infradead.org, acme@kernel.org
In-Reply-To: <c1355a46-77b7-f340-855e-6237b223e43a@gmail.com>
> On Nov 7, 2018, at 10:12 AM, David Ahern <dsahern@gmail.com> wrote:
>
> On 11/6/18 6:09 PM, Alexei Starovoitov wrote:
>> On 11/6/18 4:44 PM, David Ahern wrote:
>>>
>>> So one use case is profiling bpf programs. I was also considering the
>>> auditing discussion from some weeks ago which I thought the events are
>>> also targeting.
>>
>> yes. there should be separate mode for 're: audit discussion' where
>> only bpf events are collected. This patch set doesn't add that to
>> perf user space side.
>> The kernel side is common though. It can be used for bpf load/unload
>> only and for different use case in this set. Which is making
>> bpf program appear in normal 'perf report'.
>
> It would be good for perf-script to work in the next version. Users
> should be able to dump the event from the kernel and the synthesized
> events. Should be trivial to add and allows a review of both
> perspectives -- profiling and monitoring events.
Yes, we do plan to include these information in other perf commands,
including perf-script, perf-top, perf-annotate, etc.
Thanks,
Song
^ permalink raw reply
* WARNING in rollback_registered_many (2)
From: syzbot @ 2018-11-07 19:00 UTC (permalink / raw)
To: avagin, davem, ebiederm, edumazet, ktkhai, linux-kernel, netdev,
syzkaller-bugs, tyhicks, willy
Hello,
syzbot found the following crash on:
HEAD commit: 042cb5647815 net: phy: Allow BCM54616S PHY to setup intern..
git tree: net
console output: https://syzkaller.appspot.com/x/log.txt?x=15c0102b400000
kernel config: https://syzkaller.appspot.com/x/.config?x=8f559fee2fc3375a
dashboard link: https://syzkaller.appspot.com/bug?extid=40918e4d826fb2ff9b96
compiler: gcc (GCC) 8.0.1 20180413 (experimental)
Unfortunately, I don't have any reproducer for this crash yet.
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+40918e4d826fb2ff9b96@syzkaller.appspotmail.com
device bridge_slave_0 left promiscuous mode
��: port 1(bridge_slave_0) entered disabled state
bond2 (unregistering): Released all slaves
bond1 (unregistering): Released all slaves
bond0 (unregistering): Released all slaves
WARNING: CPU: 1 PID: 9748 at net/core/dev.c:8022
rollback_registered_many+0xeca/0x1250 net/core/dev.c:8022
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 9748 Comm: kworker/u4:5 Not tainted 4.20.0-rc1+ #174
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Workqueue: netns cleanup_net
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x244/0x39d lib/dump_stack.c:113
panic+0x2ad/0x55c kernel/panic.c:188
__warn.cold.8+0x20/0x45 kernel/panic.c:540
report_bug+0x254/0x2d0 lib/bug.c:186
fixup_bug arch/x86/kernel/traps.c:178 [inline]
do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271
do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290
invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:969
RIP: 0010:rollback_registered_many+0xeca/0x1250 net/core/dev.c:8022
Code: 57 19 00 00 48 c7 c6 e0 01 bb 88 48 c7 c7 20 02 bb 88 c6 05 ea 2e ed
03 01 e8 e2 c0 24 fb 0f 0b e9 a6 f9 ff ff e8 06 5f 5b fb <0f> 0b e9 7b f9
ff ff e8 fa 5e 5b fb 0f 0b e9 ea f9 ff ff e8 ee 5e
RSP: 0018:ffff8801bbc17058 EFLAGS: 00010293
RAX: ffff880187848280 RBX: ffff880192c31240 RCX: ffffffff86242533
RDX: 0000000000000000 RSI: ffffffff86242bba RDI: 0000000000000001
RBP: ffff8801bbc172a0 R08: ffff880187848280 R09: fffffbfff13dee60
R10: fffffbfff13dee60 R11: ffffffff89ef7307 R12: dffffc0000000000
R13: 0000000000000001 R14: ffffffff84889300 R15: ffff8801bbc17138
unregister_netdevice_many+0xfa/0x4c0 net/core/dev.c:9107
default_device_exit_batch+0x43a/0x540 net/core/dev.c:9576
ops_exit_list.isra.5+0x105/0x160 net/core/net_namespace.c:156
cleanup_net+0x555/0xb10 net/core/net_namespace.c:551
process_one_work+0xc90/0x1c40 kernel/workqueue.c:2153
worker_thread+0x17f/0x1390 kernel/workqueue.c:2296
kthread+0x35a/0x440 kernel/kthread.c:246
ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352
Kernel Offset: disabled
Rebooting in 86400 seconds..
---
This bug is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#bug-status-tracking for how to communicate with
syzbot.
^ permalink raw reply
* [PATCH net-next] tun: compute the RFS hash only if needed.
From: Paolo Abeni @ 2018-11-07 9:34 UTC (permalink / raw)
To: netdev; +Cc: Jason Wang, David S. Miller
The tun XDP sendmsg code path, unconditionally computes the symmetric
hash of each packet for RFS's sake, even when we could skip it. e.g.
when the device has a single queue.
This change adds the check already in-place for the skb sendmsg path
to avoid unneeded hashing.
The above gives small, but measurable, performance gain for VM xmit
path when zerocopy is not enabled.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/tun.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 060135ceaf0e..a65779c6d72f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2448,7 +2448,8 @@ static int tun_xdp_one(struct tun_struct *tun,
goto out;
}
- if (!rcu_dereference(tun->steering_prog))
+ if (!rcu_dereference(tun->steering_prog) && tun->numqueues > 1 &&
+ !tfile->detached)
rxhash = __skb_get_hash_symmetric(skb);
netif_receive_skb(skb);
--
2.17.2
^ permalink raw reply related
* Re: [PATCH net-next 1/3] devlink: Add fw_version_check generic parameter
From: Ido Schimmel @ 2018-11-07 10:11 UTC (permalink / raw)
To: Jakub Kicinski
Cc: Ido Schimmel, netdev@vger.kernel.org, davem@davemloft.net,
Jiri Pirko, Shalom Toledo, Moshe Shemesh, dsahern@gmail.com,
andrew@lunn.ch, f.fainelli@gmail.com, mlxsw
In-Reply-To: <20181106144713.1d3eb9f5@cakuba.netronome.com>
On Tue, Nov 06, 2018 at 02:47:13PM -0800, Jakub Kicinski wrote:
> On Tue, 6 Nov 2018 22:37:51 +0200, Ido Schimmel wrote:
> > On Tue, Nov 06, 2018 at 12:19:13PM -0800, Jakub Kicinski wrote:
> > > On Tue, 6 Nov 2018 20:05:00 +0000, Ido Schimmel wrote:
> > > > From: Shalom Toledo <shalomt@mellanox.com>
> > > >
> > > > Many drivers checking the device's firmware version during the
> > > > initialization flow and flashing a compatible version if the current
> > > > version is not.
> > > >
> > > > fw_version_check gives the ability to skip this check which allows to run
> > > > the device with a different firmware version than required by the driver
> > > > for testing and/or debugging purposes.
> > > >
> > > > Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
> > > > Reviewed-by: Jiri Pirko <jiri@mellanox.com>
> > > > Signed-off-by: Ido Schimmel <idosch@mellanox.com>
> > >
> > > The documentation is missing, so it's hard to comment on the definition
> > > of the parameter...
> >
> > I assume you mean Documentation/networking/devlink-params.txt ?
>
> Yes
>
> > > We have a FW loading policy for NFP, too, so it'd be good to see if we
> > > can find a common ground.
> >
> > If the parameter is set, then device runs with whatever firmware version
> > was last flashed (via ethtool, for example). Otherwise, the driver will
> > flash a version according to its policy. In mlxsw, it is a specific
> > version.
> >
> > Will that work for you?
>
> Our FW is always backward compatible so there is no need to downgrade.
>
> What we have is this more along these lines: there are two images one
> on disk and second in the flash. The FW loading policy can decide
> which of those should be preferred, or should the versions be compared
> and the newer one win (default). But we don't flash the newer FW, just
> potentially load it from disk today.
Not sure I understand. You have a currently flashed firmware and another
firmware image on disk. You potentially load the firmware from the disk,
but never flash it? If so, why load it?
> I'm not sure whether 'fw_version_check' describes the general behaviour
> of not updating the FW in flash. The policy of updating the FW in the
> flash if the one on disk is newer seems to be something we could adopt
> as well. Can we come up with a more general parameter which could
> select FW loading policy that'd for both cases?
>
> Would values like these make any sense to you?
> - driver preferred (your default behaviour, we don't support since
> driver doesn't care);
> - newest (our default, device compares images and picks newer);
> - always disk (always run with what's on the disk, regardless of
> versions);
> - always flash (always run with what's already in flash, don't look at
> disk);
>
> Separate bool parameter 'fw_flash_auto_update' would decide whether the
> selected FW should be flashed to the device (always true for you AFAIU).
>
> Let me know if that makes sense, it would be nice if we could converge
> on a common solution, or at least name our parameters sufficiently
> distinctly to avoid confusion :)
I think that the above scheme is a bit too complicated and I'm not sure
this is warranted. I'll try to better explain the motivation for this
parameter and where we are coming from.
We want to keep things as simple as possible. This means we don't want
users to fiddle with devlink parameter unless they have to. Things
should just work. This parameter should only be used in exceptional
cases.
For example, when user reports a problem with current firmware version
enforced by the driver. Assuming we have a new firmware version with a
fix, we would like the user to try it and confirm bug was fixed.
Ideally, the user would do something like this:
1. Flash new firmware via ethtool
2. Perform a reset via devlink to have changes take effect
Problem is that after the reset the driver's init sequence will run and
overwrite the new firmware version with the one specified in its source
as a compatible version. The driver needs to enforce a specific version
because newer versions are not necessarily backward compatible.
Therefore, we added this new parameter that gives the user the ability
to explicitly run with a different version than what was specified as
compatible. New sequence is therefore:
1. Flash new firmware via ethtool
2. Toggle devlink parameter
3. Perform a reset via devlink to have changes take effect
Firmware loading policy is basically always go with what the driver is
enforcing (it knows best), unless user specified he/she knows better.
I think this is both generic and simple, but I possibly didn't
understand the full scope of your use cases.
^ permalink raw reply
* Re: [Patch net-next 00/12] provide new interfaces & bugfixes & code optimization
From: David Miller @ 2018-11-07 19:42 UTC (permalink / raw)
To: tanhuazhong; +Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
In-Reply-To: <1541563578-28973-1-git-send-email-tanhuazhong@huawei.com>
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:06 +0800
> This patchset provides some reset interfaces for RAS & RoCE, also
> some bugfixes and optimization related to reset.
Series applied, thank you.
^ permalink raw reply
* Re: [PATCH net-next] net: hns3: Remove set but not used variable 'reset_level'
From: David Miller @ 2018-11-07 19:46 UTC (permalink / raw)
To: yuehaibing
Cc: yisen.zhuang, salil.mehta, shiju.jose, colin.king, netdev,
linux-kernel, kernel-janitors
In-Reply-To: <1541558033-100068-1-git-send-email-yuehaibing@huawei.com>
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 7 Nov 2018 02:33:53 +0000
> Fixes gcc '-Wunused-but-set-variable' warning:
>
> drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c: In function 'hclge_log_and_clear_ppp_error':
> drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c:821:24: warning:
> variable 'reset_level' set but not used [-Wunused-but-set-variable]
> enum hnae3_reset_type reset_level = HNAE3_NONE_RESET;
>
> It never used since introduction in commit
> 01865a50d78f ("net: hns3: Add enable and process hw errors of TM scheduler")
>
> Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Applied, thanks.
^ permalink raw reply
* [PATCH net-next] net: vlan: add support for tunnel offload
From: Davide Caratti @ 2018-11-07 10:28 UTC (permalink / raw)
To: David S. Miller, Cong Wang, netdev, Flavio Leitner,
Florian Westphal
GSO tunneled packets are always segmented in software before they are
transmitted by a VLAN, even when the lower device can offload tunnel
encapsulation and VLAN together (i.e., some bits in NETIF_F_GSO_ENCAP_ALL
mask are set in the lower device 'vlan_features'). If we let VLANs have
the same tunnel offload capabilities as their lower device, throughput
can improve significantly when CPU is limited on the transmitter side.
- set NETIF_F_GSO_ENCAP_ALL bits in the VLAN 'hw_features', to ensure
that 'features' will have those bits zeroed only when the lower device
has no hardware support for tunnel encapsulation.
- for the same reason, copy GSO-related bits of 'hw_enc_features' from
lower device to VLAN, and ensure to update that value when the lower
device changes its features.
- set NETIF_F_HW_CSUM bit in the VLAN 'hw_enc_features' if 'real_dev'
is able to compute checksums at least for a kind of packets, like done
with commit 8403debeead8 ("vlan: Keep NETIF_F_HW_CSUM similar to other
software devices"). This avoids software segmentation due to mismatching
checksum capabilities between VLAN's 'features' and 'hw_enc_features'.
Reported-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
---
net/8021q/vlan.c | 1 +
net/8021q/vlan.h | 12 ++++++++++++
net/8021q/vlan_dev.c | 2 ++
3 files changed, 15 insertions(+)
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 5e9950453955..1b7a375c6616 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -330,6 +330,7 @@ static void vlan_transfer_features(struct net_device *dev,
vlandev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
vlandev->priv_flags |= (vlan->real_dev->priv_flags & IFF_XMIT_DST_RELEASE);
+ vlandev->hw_enc_features = vlan_tnl_features(vlan->real_dev);
netdev_update_features(vlandev);
}
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 44df1c3df02d..c46daf09a501 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -92,6 +92,18 @@ static inline struct net_device *vlan_find_dev(struct net_device *real_dev,
return NULL;
}
+static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev)
+{
+ netdev_features_t ret;
+
+ ret = real_dev->hw_enc_features &
+ (NETIF_F_CSUM_MASK | NETIF_F_ALL_TSO | NETIF_F_GSO_ENCAP_ALL);
+
+ if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK))
+ return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM;
+ return 0;
+}
+
#define vlan_group_for_each_dev(grp, i, dev) \
for ((i) = 0; i < VLAN_PROTO_NUM * VLAN_N_VID; i++) \
if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index ff720f1ebf73..b2d9c8f27cd7 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -562,6 +562,7 @@ static int vlan_dev_init(struct net_device *dev)
dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG |
NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE |
+ NETIF_F_GSO_ENCAP_ALL |
NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC |
NETIF_F_ALL_FCOE;
@@ -572,6 +573,7 @@ static int vlan_dev_init(struct net_device *dev)
netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n");
dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE;
+ dev->hw_enc_features = vlan_tnl_features(real_dev);
/* ipv6 shared card related stuff */
dev->dev_id = real_dev->dev_id;
--
2.19.1
^ permalink raw reply related
* [PATCH net-next] dpaa2-eth: Introduce TX congestion management
From: Ioana Ciocoi Radulescu @ 2018-11-07 10:31 UTC (permalink / raw)
To: netdev@vger.kernel.org, davem@davemloft.net; +Cc: Ioana Ciornei
DPAA2 hardware can be configured to signal when a set of queues
become congested (i.e., they accumulate a number of frames/bytes
larger than a configurable threshold).
Add the firmware API to control the congestion settings and use it
to enable congestion management on the TX path.
DPAA2 ethernet devices use a set of TX queues to transmit frames and
another set of queues to receive confirmation that the transmission
was successful. Congestion is reached when the cumulated amount of
pending bytes on all frames of one type (either Tx or Tx conf)
is higher than the threshold.
When congestion is detected, all netdev Tx queues on the interface
are stopped until state changes back to uncongested.
Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
---
We chose this mechanism over BQL (to which it is conceptually
very similar) because a) we can take advantage of the hardware
offloading and b) BQL doesn't match well with our driver fastpath
(we process ingress (Rx or Tx conf) frames in batches of up to 16,
which in certain scenarios confuses the BQL adaptive algorithm,
resulting in too low values of the limit and low performance).
drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 89 ++++++++++++++++++++++
drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h | 15 ++++
.../net/ethernet/freescale/dpaa2/dpaa2-ethtool.c | 2 +
drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h | 23 ++++++
drivers/net/ethernet/freescale/dpaa2/dpni.c | 44 +++++++++++
drivers/net/ethernet/freescale/dpaa2/dpni.h | 85 +++++++++++++++++++++
6 files changed, 258 insertions(+)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 88f7acc..c51cd79 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -564,6 +564,18 @@ static void free_tx_fd(const struct dpaa2_eth_priv *priv,
dev_kfree_skb(skb);
}
+bool dpaa2_eth_tx_congested(struct dpaa2_eth_priv *priv)
+{
+ struct device *dev = priv->net_dev->dev.parent;
+
+ dma_sync_single_for_cpu(dev, priv->cscn_dma, DPAA2_CSCN_SIZE * 2,
+ DMA_FROM_DEVICE);
+
+ /* Check the congestion state of both queue groups (Tx and Tx conf) */
+ return (dpaa2_cscn_state_congested(priv->cscn_mem) ||
+ dpaa2_cscn_state_congested(priv->cscn_mem + DPAA2_CSCN_SIZE));
+}
+
static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
{
struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
@@ -575,6 +587,12 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
unsigned int needed_headroom;
int err, i;
+ /* If we're congested, stop the software queues; transmission
+ * of the current skb happens regardless of congestion state
+ */
+ if (dpaa2_eth_tx_congested(priv))
+ netif_tx_stop_all_queues(net_dev);
+
percpu_stats = this_cpu_ptr(priv->percpu_stats);
percpu_extras = this_cpu_ptr(priv->percpu_extras);
@@ -675,6 +693,10 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv,
percpu_extras->tx_conf_frames++;
percpu_extras->tx_conf_bytes += dpaa2_fd_get_len(fd);
+ /* Check congestion state and wake all queues if necessary */
+ if (netif_queue_stopped(priv->net_dev) && !dpaa2_eth_tx_congested(priv))
+ netif_tx_wake_all_queues(priv->net_dev);
+
/* Check frame errors in the FD field */
fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK;
free_tx_fd(priv, fd);
@@ -1858,6 +1880,65 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
return 0;
}
+static int set_tx_congestion(struct dpaa2_eth_priv *priv)
+{
+ struct dpni_cong_notif_cfg cfg = {0};
+ struct device *dev = priv->net_dev->dev.parent;
+ void *tmp;
+ int err;
+
+ /* We need two congestion state buffers, one for Tx queue group
+ * and one for Tx confirmation queue group
+ */
+ tmp = devm_kzalloc(dev, DPAA2_CSCN_SIZE * 2 + DPAA2_CSCN_ALIGN,
+ GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
+
+ priv->cscn_mem = PTR_ALIGN(tmp, DPAA2_CSCN_ALIGN);
+ priv->cscn_dma = dma_map_single(dev, priv->cscn_mem,
+ DPAA2_CSCN_SIZE * 2, DMA_FROM_DEVICE);
+ if (dma_mapping_error(dev, priv->cscn_dma)) {
+ dev_err(dev, "Error mapping CSCN memory area\n");
+ err = -ENOMEM;
+ goto free;
+ }
+
+ cfg.units = DPNI_CONGESTION_UNIT_BYTES;
+ cfg.threshold_entry = DPAA2_ETH_TXCONG_ENTRY_THRESH;
+ cfg.threshold_exit = DPAA2_ETH_TXCONG_EXIT_THRESH;
+ cfg.message_ctx = (u64)priv;
+ cfg.message_iova = priv->cscn_dma;
+ cfg.notification_mode = DPNI_CONG_OPT_WRITE_MEM_ON_ENTER |
+ DPNI_CONG_OPT_WRITE_MEM_ON_EXIT |
+ DPNI_CONG_OPT_COHERENT_WRITE;
+
+ err = dpni_set_congestion_notification(priv->mc_io, 0, priv->mc_token,
+ DPNI_QUEUE_TX, 0, &cfg);
+ if (err) {
+ dev_err(dev, "dpni_set_congestion_notification(TX) failed\n");
+ goto unmap;
+ }
+
+ cfg.message_iova = priv->cscn_dma + DPAA2_CSCN_SIZE;
+ err = dpni_set_congestion_notification(priv->mc_io, 0, priv->mc_token,
+ DPNI_QUEUE_TX_CONFIRM, 0, &cfg);
+ if (err) {
+ dev_err(dev, "dpni_set_congestion_notification(TX_CONF) failed\n");
+ goto unmap;
+ }
+
+ return 0;
+
+unmap:
+ dma_unmap_single(dev, priv->cscn_dma, DPAA2_CSCN_SIZE * 2,
+ DMA_FROM_DEVICE);
+free:
+ devm_kfree(dev, tmp);
+
+ return err;
+}
+
/* Configure the DPNI object this interface is associated with */
static int setup_dpni(struct fsl_mc_device *ls_dev)
{
@@ -1926,6 +2007,7 @@ static int setup_dpni(struct fsl_mc_device *ls_dev)
static void free_dpni(struct dpaa2_eth_priv *priv)
{
+ struct device *dev = priv->net_dev->dev.parent;
int err;
err = dpni_reset(priv->mc_io, 0, priv->mc_token);
@@ -1934,6 +2016,9 @@ static void free_dpni(struct dpaa2_eth_priv *priv)
err);
dpni_close(priv->mc_io, 0, priv->mc_token);
+
+ dma_unmap_single(dev, priv->cscn_dma, DPAA2_CSCN_SIZE * 2,
+ DMA_FROM_DEVICE);
}
static int setup_rx_flow(struct dpaa2_eth_priv *priv,
@@ -2347,6 +2432,10 @@ static int bind_dpni(struct dpaa2_eth_priv *priv)
return err;
}
+ err = set_tx_congestion(priv);
+ if (err)
+ return err;
+
err = dpni_get_qdid(priv->mc_io, 0, priv->mc_token,
DPNI_QUEUE_TX, &priv->tx_qdid);
if (err) {
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 452a8e9..f91133b 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -40,6 +40,16 @@
*/
#define DPAA2_ETH_TAILDROP_THRESH (64 * 1024)
+/* Tx congestion entry and exit thresholds, in number of bytes.
+ * Allow a maximum of 512KB worth of pending egress frames.
+ * Congestion is reached when the cumulated amount of pending bytes
+ * on all frames of one type (either Tx or Tx conf) is higher
+ * than the threshold.
+ */
+#define DPAA2_ETH_TXCONG_ENTRY_THRESH (512 * 1024)
+#define DPAA2_ETH_TXCONG_EXIT_THRESH \
+ (DPAA2_ETH_TXCONG_ENTRY_THRESH * 7 / 8)
+
/* Maximum number of Tx confirmation frames to be processed
* in a single NAPI call
*/
@@ -352,6 +362,10 @@ struct dpaa2_eth_priv {
u64 rx_hash_fields;
struct dpaa2_eth_cls_rule *cls_rules;
u8 rx_cls_enabled;
+
+ /* Tx congestion status is written here by hardware */
+ void *cscn_mem;
+ dma_addr_t cscn_dma;
};
#define DPAA2_RXH_SUPPORTED (RXH_L2DA | RXH_VLAN | RXH_L3_PROTO \
@@ -442,5 +456,6 @@ static int dpaa2_eth_queue_count(struct dpaa2_eth_priv *priv)
int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags);
int dpaa2_eth_cls_key_size(void);
int dpaa2_eth_cls_fld_off(int prot, int field);
+bool dpaa2_eth_tx_congested(struct dpaa2_eth_priv *priv);
#endif /* __DPAA2_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 26bd5a2..8e1835c 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -45,6 +45,7 @@ static char dpaa2_ethtool_extras[][ETH_GSTRING_LEN] = {
"[drv] dequeue portal busy",
"[drv] channel pull errors",
"[drv] cdan",
+ "[drv] tx congestion state",
};
#define DPAA2_ETH_NUM_EXTRA_STATS ARRAY_SIZE(dpaa2_ethtool_extras)
@@ -222,6 +223,7 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
*(data + i++) = portal_busy;
*(data + i++) = pull_err;
*(data + i++) = cdan;
+ *(data + i++) = dpaa2_eth_tx_congested(priv);
}
static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask,
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
index 7b44d7d..26e0338 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
@@ -566,4 +566,27 @@ struct dpni_cmd_remove_fs_entry {
__le64 mask_iova;
};
+#define DPNI_CONG_UNITS_SHIFT 4
+#define DPNI_CONG_UNITS_SIZE 2
+
+struct dpni_cmd_set_congestion_notification {
+ /* cmd word 0 */
+ u8 qtype;
+ u8 tc;
+ u8 pad[6];
+ /* cmd word 1 */
+ __le32 dest_id;
+ __le16 notification_mode;
+ u8 dest_priority;
+ /* from LSB: dest_type:4, units:2 */
+ u8 type_units;
+ /* cmd word 2 */
+ __le64 message_iova;
+ /* cmd word 3 */
+ __le64 message_ctx;
+ /* cmd word 4 */
+ __le32 threshold_entry;
+ __le32 threshold_exit;
+};
+
#endif /* _FSL_DPNI_CMD_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.c b/drivers/net/ethernet/freescale/dpaa2/dpni.c
index 220dfc8..046ae19 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.c
@@ -1750,3 +1750,47 @@ int dpni_remove_fs_entry(struct fsl_mc_io *mc_io,
/* send command to mc*/
return mc_send_command(mc_io, &cmd);
}
+
+/**
+ * dpni_set_congestion_notification() - Set congestion notification config
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPNI object
+ * @qtype: Type of queue - Rx, Tx and Tx confirm types are supported
+ * @tc_id: Traffic class selection (0-7)
+ * @cfg: Congestion notification configuration
+ *
+ * Return: '0' on Success; error code otherwise.
+ */
+int dpni_set_congestion_notification(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ enum dpni_queue_type qtype,
+ u8 tc_id,
+ const struct dpni_cong_notif_cfg *cfg)
+{
+ struct dpni_cmd_set_congestion_notification *cmd_params;
+ struct fsl_mc_command cmd = { 0 };
+
+ /* prepare command */
+ cmd.header =
+ mc_encode_cmd_header(DPNI_CMDID_SET_CONGESTION_NOTIFICATION,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpni_cmd_set_congestion_notification *)cmd.params;
+ cmd_params->qtype = qtype;
+ cmd_params->tc = tc_id;
+ cmd_params->dest_id = cpu_to_le32(cfg->dest_cfg.dest_id);
+ cmd_params->notification_mode = cpu_to_le16(cfg->notification_mode);
+ cmd_params->dest_priority = cfg->dest_cfg.priority;
+ dpni_set_field(cmd_params->type_units, DEST_TYPE,
+ cfg->dest_cfg.dest_type);
+ dpni_set_field(cmd_params->type_units, CONG_UNITS, cfg->units);
+ cmd_params->message_iova = cpu_to_le64(cfg->message_iova);
+ cmd_params->message_ctx = cpu_to_le64(cfg->message_ctx);
+ cmd_params->threshold_entry = cpu_to_le32(cfg->threshold_entry);
+ cmd_params->threshold_exit = cpu_to_le32(cfg->threshold_exit);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h
index a521242..63d337c 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h
@@ -810,6 +810,91 @@ enum dpni_congestion_point {
};
/**
+ * struct dpni_dest_cfg - Structure representing DPNI destination parameters
+ * @dest_type: Destination type
+ * @dest_id: Either DPIO ID or DPCON ID, depending on the destination type
+ * @priority: Priority selection within the DPIO or DPCON channel; valid
+ * values are 0-1 or 0-7, depending on the number of priorities
+ * in that channel; not relevant for 'DPNI_DEST_NONE' option
+ */
+struct dpni_dest_cfg {
+ enum dpni_dest dest_type;
+ int dest_id;
+ u8 priority;
+};
+
+/* DPNI congestion options */
+
+/**
+ * CSCN message is written to message_iova once entering a
+ * congestion state (see 'threshold_entry')
+ */
+#define DPNI_CONG_OPT_WRITE_MEM_ON_ENTER 0x00000001
+/**
+ * CSCN message is written to message_iova once exiting a
+ * congestion state (see 'threshold_exit')
+ */
+#define DPNI_CONG_OPT_WRITE_MEM_ON_EXIT 0x00000002
+/**
+ * CSCN write will attempt to allocate into a cache (coherent write);
+ * valid only if 'DPNI_CONG_OPT_WRITE_MEM_<X>' is selected
+ */
+#define DPNI_CONG_OPT_COHERENT_WRITE 0x00000004
+/**
+ * if 'dest_cfg.dest_type != DPNI_DEST_NONE' CSCN message is sent to
+ * DPIO/DPCON's WQ channel once entering a congestion state
+ * (see 'threshold_entry')
+ */
+#define DPNI_CONG_OPT_NOTIFY_DEST_ON_ENTER 0x00000008
+/**
+ * if 'dest_cfg.dest_type != DPNI_DEST_NONE' CSCN message is sent to
+ * DPIO/DPCON's WQ channel once exiting a congestion state
+ * (see 'threshold_exit')
+ */
+#define DPNI_CONG_OPT_NOTIFY_DEST_ON_EXIT 0x00000010
+/**
+ * if 'dest_cfg.dest_type != DPNI_DEST_NONE' when the CSCN is written to the
+ * sw-portal's DQRR, the DQRI interrupt is asserted immediately (if enabled)
+ */
+#define DPNI_CONG_OPT_INTR_COALESCING_DISABLED 0x00000020
+/**
+ * This congestion will trigger flow control or priority flow control.
+ * This will have effect only if flow control is enabled with
+ * dpni_set_link_cfg().
+ */
+#define DPNI_CONG_OPT_FLOW_CONTROL 0x00000040
+
+/**
+ * struct dpni_cong_notif_cfg - configuration for congestion notifications
+ * @units: Units type
+ * @threshold_entry: Above this threshold we enter a congestion state.
+ * set it to '0' to disable it
+ * @threshold_exit: Below this threshold we exit the congestion state.
+ * @message_ctx: The context that will be part of the CSCN message
+ * @message_iova: I/O virtual address (must be in DMA-able memory),
+ * must be 16B aligned; valid only if 'DPNI_CONG_OPT_WRITE_MEM_<X>'
+ * is contained in 'options'
+ * @dest_cfg: CSCN can be send to either DPIO or DPCON WQ channel
+ * @notification_mode: Mask of available options; use 'DPNI_CONG_OPT_<X>' values
+ */
+struct dpni_cong_notif_cfg {
+ enum dpni_congestion_unit units;
+ u32 threshold_entry;
+ u32 threshold_exit;
+ u64 message_ctx;
+ u64 message_iova;
+ struct dpni_dest_cfg dest_cfg;
+ u16 notification_mode;
+};
+
+int dpni_set_congestion_notification(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ enum dpni_queue_type qtype,
+ u8 tc_id,
+ const struct dpni_cong_notif_cfg *cfg);
+
+/**
* struct dpni_taildrop - Structure representing the taildrop
* @enable: Indicates whether the taildrop is active or not.
* @units: Indicates the unit of THRESHOLD. Queue taildrop only supports
--
2.7.4
^ permalink raw reply related
* Re: [PATCH net-next 03/11] vxlan: Allow configuration of DF behaviour
From: Stefano Brivio @ 2018-11-07 10:35 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: David S. Miller, Sabrina Dubroca, Xin Long, netdev
In-Reply-To: <20181106210018.08f45eb0@shemminger-XPS-13-9360>
Stephen, thanks for reviewing this.
On Tue, 6 Nov 2018 21:00:18 -0800
Stephen Hemminger <stephen@networkplumber.org> wrote:
> On Tue, 6 Nov 2018 22:38:59 +0100
> Stefano Brivio <sbrivio@redhat.com> wrote:
>
> > df = htons(IP_DF);
> > }
> >
> > + if (!df) {
> > + if (vxlan->cfg.df == VXLAN_DF_SET) {
> > + df = htons(IP_DF);
>
> I am confused, this looks like this new flag is duplicating the exiting tunnel DF flag.
> (in info->key.tun.flags). Why is another flag needed?
The reason is that for non-lwt tunnels the tunnel key is not used in
VXLAN, and this patch is intended for non-lwt tunnels only, as external
control planes already have a way to set the DF bit.
But now I see that the way I wrote this is misleading: this should
really be in an if (rdst) or if (!info) clause. I'll place this into
the if (!info) block just above. TTL and TOS are handled in a similar
way, using the if (rdst) clause above.
Functionally, it's equivalent, because external control planes will
never set non-default values for vxlan->cfg.df, but still not a good
reason to write it this way.
Similar story for GENEVE, I will place that under if
(!geneve->collect_md) instead.
With a notable difference, though: GENEVE already uses struct
ip_tunnel_key for some of its interface configuration, so I had already
thought about adding a TUNNEL_DONT_FRAGMENT_INHERIT flag that could be
used in tun_flags.
However, I would use the last available bit there, and this wouldn't be
terribly useful: an external control plane already has access to the
inner DF bit, and would most likely decide on its own whether to set DF
or not, by setting that in tun_flags. So I'd rather keep that in struct
geneve_dev.
--
Stefano
^ permalink raw reply
* Re: Application of f8b39039cbf2a15f ("net: fs_enet: do not call phy_stop() in interrupts") to 4.9 and 4.14 stable
From: Christophe LEROY @ 2018-11-07 20:18 UTC (permalink / raw)
To: David Miller, netdev@vger.kernel.org; +Cc: Greg KH, stable@vger.kernel.org
In-Reply-To: <f22dfae5-df25-ca45-7991-0a5b3b31eb23@c-s.fr>
ping ?
Le 17/10/2018 à 14:08, Christophe LEROY a écrit :
> Hi,
>
> Could you please apply f8b39039cbf2a15f2b8c9f081e1cbd5dee00aaf5 to 4.9
> and 4.14 ?
>
> It fixes an Oops when Ethernet transmission times out.
>
> As you can observe in the commit log, the Oops what initially observed
> in 4.9.
>
> The fix has been in mainline since 4.15
>
> Thanks
> Christophe
^ permalink raw reply
* Re: [PATCH net-next 00/11] ICMP error handling for UDP tunnels
From: Jiri Benc @ 2018-11-07 11:09 UTC (permalink / raw)
To: Stefano Brivio; +Cc: David S. Miller, Sabrina Dubroca, Xin Long, netdev
In-Reply-To: <cover.1541533786.git.sbrivio@redhat.com>
On Tue, 6 Nov 2018 22:38:56 +0100, Stefano Brivio wrote:
> - patch 1/11 adds a socket lookup for UDP tunnels that use, by design,
> the same destination port on both endpoints -- i.e. VxLAN and GENEVE
This is not necessarily true with lwtunnels (collect_md mode of VXLAN
and GENEVE). While any sane setup will use the same dst ports, there's
really nothing that enforces it. Of course, in that case we have no way
to map the ICMP error back to the tunnel.
Generally speaking, I'm not sure how ICMP error handling should work
for external control planes. Are we sure they want PMTU discovery and
route redirection done by the kernel? (I am not sure, neither way.)
Jiri
^ permalink raw reply
* [PATCH net-next 00/10] udp: implement GRO support
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
This series implements GRO support for UDP sockets, as the RX counterpart
of commit bec1f6f69736 ("udp: generate gso with UDP_SEGMENT").
The core functionality is implemented by the second patch, introducing a new
sockopt to enable UDP_GRO, while patch 3 implements support for passing the
segment size to the user space via a new cmsg.
UDP GRO performs a socket lookup for each ingress packets and aggregate datagram
directed to UDP GRO enabled sockets with constant l4 tuple.
UDP GRO packets can land on non GRO-enabled sockets, e.g. due to iptables NAT
rules, and that could potentially confuse existing applications.
The solution adopted here is to de-segment the GRO packet before enqueuing
as needed. Since we must cope with packet reinsertion after de-segmentation,
the relevant code is factored-out in ipv4 and ipv6 specific helpers and exposed
to UDP usage.
While the current code can probably be improved, this safeguard ,implemented in
the patches 4-7, allows future enachements to enable UDP GSO offload on more
virtual devices eventually even on forwarded packets.
The last 4 for patches implement some performance and functional self-tests,
re-using the existing udpgso infrastructure. The problematic scenario described
above is explicitly tested.
This revision of the series try to address the feedback provided by Willem and
Subash on previous iteration.
Paolo Abeni (10):
udp: implement complete book-keeping for encap_needed
udp: implement GRO for plain UDP sockets.
udp: add support for UDP_GRO cmsg
ip: factor out protocol delivery helper
ipv6: factor out protocol delivery helper
udp: cope with UDP GRO packet misdirection
selftests: add GRO support to udp bench rx program
selftests: add dummy xdp test helper
selftests: add some benchmark for UDP GRO
selftests: add functionals test for UDP GRO
include/linux/udp.h | 25 ++-
include/net/ip.h | 1 +
include/net/ipv6.h | 2 +
include/net/udp.h | 45 ++++-
include/net/udp_tunnel.h | 6 +
include/uapi/linux/udp.h | 1 +
net/ipv4/ip_input.c | 73 ++++----
net/ipv4/udp.c | 54 +++++-
net/ipv4/udp_offload.c | 109 +++++++++---
net/ipv6/ip6_input.c | 28 ++--
net/ipv6/udp.c | 41 ++++-
net/ipv6/udp_offload.c | 6 +-
tools/testing/selftests/bpf/Makefile | 3 +-
tools/testing/selftests/bpf/xdp_dummy.c | 13 ++
tools/testing/selftests/net/Makefile | 1 +
tools/testing/selftests/net/udpgro.sh | 148 +++++++++++++++++
tools/testing/selftests/net/udpgro_bench.sh | 95 +++++++++++
tools/testing/selftests/net/udpgso_bench.sh | 2 +-
tools/testing/selftests/net/udpgso_bench_rx.c | 156 ++++++++++++++++--
tools/testing/selftests/net/udpgso_bench_tx.c | 22 ++-
20 files changed, 708 insertions(+), 123 deletions(-)
create mode 100644 tools/testing/selftests/bpf/xdp_dummy.c
create mode 100755 tools/testing/selftests/net/udpgro.sh
create mode 100755 tools/testing/selftests/net/udpgro_bench.sh
--
2.17.2
^ permalink raw reply
* [PATCH net-next 01/10] udp: implement complete book-keeping for encap_needed
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
In-Reply-To: <cover.1541588248.git.pabeni@redhat.com>
The *encap_needed static keys are enabled by UDP tunnels
and several UDP encapsulations type, but they are never
turned off. This can cause unneeded overall performance
degradation for systems where such features are used
transiently.
This patch introduces complete book-keeping for such keys,
decreasing the usage at socket destruction time, if needed,
and avoiding that the same socket could increase the key
usage multiple times.
rfc v3 -> v1:
- add socket lock around udp_tunnel_encap_enable()
rfc v2 -> rfc v3:
- use udp_tunnel_encap_enable() in setsockopt()
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
include/linux/udp.h | 7 ++++++-
include/net/udp_tunnel.h | 6 ++++++
net/ipv4/udp.c | 19 +++++++++++++------
net/ipv6/udp.c | 14 +++++++++-----
4 files changed, 34 insertions(+), 12 deletions(-)
diff --git a/include/linux/udp.h b/include/linux/udp.h
index 320d49d85484..a4dafff407fb 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -49,7 +49,12 @@ struct udp_sock {
unsigned int corkflag; /* Cork is required */
__u8 encap_type; /* Is this an Encapsulation socket? */
unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
- no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */
+ no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
+ encap_enabled:1; /* This socket enabled encap
+ * processing; UDP tunnels and
+ * different encapsulation layer set
+ * this
+ */
/*
* Following member retains the information to create a UDP header
* when the socket is uncorked.
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index fe680ab6b15a..3fbe56430e3b 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -165,6 +165,12 @@ static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum)
static inline void udp_tunnel_encap_enable(struct socket *sock)
{
+ struct udp_sock *up = udp_sk(sock->sk);
+
+ if (up->encap_enabled)
+ return;
+
+ up->encap_enabled = 1;
#if IS_ENABLED(CONFIG_IPV6)
if (sock->sk->sk_family == PF_INET6)
ipv6_stub->udpv6_encap_enable();
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1976fddb9e00..0ed715a72249 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -115,6 +115,7 @@
#include "udp_impl.h"
#include <net/sock_reuseport.h>
#include <net/addrconf.h>
+#include <net/udp_tunnel.h>
struct udp_table udp_table __read_mostly;
EXPORT_SYMBOL(udp_table);
@@ -2398,11 +2399,15 @@ void udp_destroy_sock(struct sock *sk)
bool slow = lock_sock_fast(sk);
udp_flush_pending_frames(sk);
unlock_sock_fast(sk, slow);
- if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) {
- void (*encap_destroy)(struct sock *sk);
- encap_destroy = READ_ONCE(up->encap_destroy);
- if (encap_destroy)
- encap_destroy(sk);
+ if (static_branch_unlikely(&udp_encap_needed_key)) {
+ if (up->encap_type) {
+ void (*encap_destroy)(struct sock *sk);
+ encap_destroy = READ_ONCE(up->encap_destroy);
+ if (encap_destroy)
+ encap_destroy(sk);
+ }
+ if (up->encap_enabled)
+ static_branch_disable(&udp_encap_needed_key);
}
}
@@ -2447,7 +2452,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
/* FALLTHROUGH */
case UDP_ENCAP_L2TPINUDP:
up->encap_type = val;
- udp_encap_enable();
+ lock_sock(sk);
+ udp_tunnel_encap_enable(sk->sk_socket);
+ release_sock(sk);
break;
default:
err = -ENOPROTOOPT;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d2d97d07ef27..fc0ce6c59ebb 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1458,11 +1458,15 @@ void udpv6_destroy_sock(struct sock *sk)
udp_v6_flush_pending_frames(sk);
release_sock(sk);
- if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) {
- void (*encap_destroy)(struct sock *sk);
- encap_destroy = READ_ONCE(up->encap_destroy);
- if (encap_destroy)
- encap_destroy(sk);
+ if (static_branch_unlikely(&udpv6_encap_needed_key)) {
+ if (up->encap_type) {
+ void (*encap_destroy)(struct sock *sk);
+ encap_destroy = READ_ONCE(up->encap_destroy);
+ if (encap_destroy)
+ encap_destroy(sk);
+ }
+ if (up->encap_enabled)
+ static_branch_disable(&udpv6_encap_needed_key);
}
inet6_destroy_sock(sk);
--
2.17.2
^ permalink raw reply related
* [PATCH net-next 02/10] udp: implement GRO for plain UDP sockets.
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
In-Reply-To: <cover.1541588248.git.pabeni@redhat.com>
This is the RX counterpart of commit bec1f6f69736 ("udp: generate gso
with UDP_SEGMENT"). When UDP_GRO is enabled, such socket is also
eligible for GRO in the rx path: UDP segments directed to such socket
are assembled into a larger GSO_UDP_L4 packet.
The core UDP GRO support is enabled with setsockopt(UDP_GRO).
Initial benchmark numbers:
Before:
udp rx: 1079 MB/s 769065 calls/s
After:
udp rx: 1466 MB/s 24877 calls/s
This change introduces a side effect in respect to UDP tunnels:
after a UDP tunnel creation, now the kernel performs a lookup per ingress
UDP packet, while before such lookup happened only if the ingress packet
carried a valid internal header csum.
rfc v2 -> rfc v3:
- fixed typos in macro name and comments
- really enforce UDP_GRO_CNT_MAX, instead of UDP_GRO_CNT_MAX + 1
- acquire socket lock in UDP_GRO setsockopt
rfc v1 -> rfc v2:
- use a new option to enable UDP GRO
- use static keys to protect the UDP GRO socket lookup
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
--
Note: I opted for acquiring the socket lock only for the newly introduced
setsockopt instead for every value, despite the previous conversation on
this topic, to avoid introducing somewhat larger and unrelated changes.
---
include/linux/udp.h | 3 +-
include/uapi/linux/udp.h | 1 +
net/ipv4/udp.c | 8 +++
net/ipv4/udp_offload.c | 109 +++++++++++++++++++++++++++++++--------
net/ipv6/udp_offload.c | 6 +--
5 files changed, 99 insertions(+), 28 deletions(-)
diff --git a/include/linux/udp.h b/include/linux/udp.h
index a4dafff407fb..f613b329852e 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -50,11 +50,12 @@ struct udp_sock {
__u8 encap_type; /* Is this an Encapsulation socket? */
unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
- encap_enabled:1; /* This socket enabled encap
+ encap_enabled:1, /* This socket enabled encap
* processing; UDP tunnels and
* different encapsulation layer set
* this
*/
+ gro_enabled:1; /* Can accept GRO packets */
/*
* Following member retains the information to create a UDP header
* when the socket is uncorked.
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index 09502de447f5..30baccb6c9c4 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -33,6 +33,7 @@ struct udphdr {
#define UDP_NO_CHECK6_TX 101 /* Disable sending checksum for UDP6X */
#define UDP_NO_CHECK6_RX 102 /* Disable accpeting checksum for UDP6 */
#define UDP_SEGMENT 103 /* Set GSO segmentation size */
+#define UDP_GRO 104 /* This socket can receive UDP GRO packets */
/* UDP encapsulation types */
#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0ed715a72249..0d447fd194c5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2476,6 +2476,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
up->gso_size = val;
break;
+ case UDP_GRO:
+ lock_sock(sk);
+ if (valbool)
+ udp_tunnel_encap_enable(sk->sk_socket);
+ up->gro_enabled = valbool;
+ release_sock(sk);
+ break;
+
/*
* UDP-Lite's partial checksum coverage (RFC 3828).
*/
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 802f2bc00d69..0646d61f4fa8 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -343,6 +343,54 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
return segs;
}
+#define UDP_GRO_CNT_MAX 64
+static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
+ struct sk_buff *skb)
+{
+ struct udphdr *uh = udp_hdr(skb);
+ struct sk_buff *pp = NULL;
+ struct udphdr *uh2;
+ struct sk_buff *p;
+
+ /* requires non zero csum, for symmetry with GSO */
+ if (!uh->check) {
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+ }
+
+ /* pull encapsulating udp header */
+ skb_gro_pull(skb, sizeof(struct udphdr));
+ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
+
+ list_for_each_entry(p, head, list) {
+ if (!NAPI_GRO_CB(p)->same_flow)
+ continue;
+
+ uh2 = udp_hdr(p);
+
+ /* Match ports only, as csum is always non zero */
+ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
+ NAPI_GRO_CB(p)->same_flow = 0;
+ continue;
+ }
+
+ /* Terminate the flow on len mismatch or if it grow "too much".
+ * Under small packet flood GRO count could elsewhere grow a lot
+ * leading to execessive truesize values
+ */
+ if (!skb_gro_receive(p, skb) &&
+ NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
+ pp = p;
+ else if (uh->len != uh2->len)
+ pp = p;
+
+ return pp;
+ }
+
+ /* mismatch, but we never need to flush */
+ return NULL;
+}
+
struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
struct udphdr *uh, udp_lookup_t lookup)
{
@@ -353,23 +401,27 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
int flush = 1;
struct sock *sk;
+ rcu_read_lock();
+ sk = (*lookup)(skb, uh->source, uh->dest);
+ if (!sk)
+ goto out_unlock;
+
+ if (udp_sk(sk)->gro_enabled) {
+ pp = call_gro_receive(udp_gro_receive_segment, head, skb);
+ rcu_read_unlock();
+ return pp;
+ }
+
if (NAPI_GRO_CB(skb)->encap_mark ||
(skb->ip_summed != CHECKSUM_PARTIAL &&
NAPI_GRO_CB(skb)->csum_cnt == 0 &&
- !NAPI_GRO_CB(skb)->csum_valid))
- goto out;
+ !NAPI_GRO_CB(skb)->csum_valid) ||
+ !udp_sk(sk)->gro_receive)
+ goto out_unlock;
/* mark that this skb passed once through the tunnel gro layer */
NAPI_GRO_CB(skb)->encap_mark = 1;
- rcu_read_lock();
- sk = (*lookup)(skb, uh->source, uh->dest);
-
- if (sk && udp_sk(sk)->gro_receive)
- goto unflush;
- goto out_unlock;
-
-unflush:
flush = 0;
list_for_each_entry(p, head, list) {
@@ -394,7 +446,6 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
out_unlock:
rcu_read_unlock();
-out:
skb_gro_flush_final(skb, pp, flush);
return pp;
}
@@ -427,6 +478,19 @@ static struct sk_buff *udp4_gro_receive(struct list_head *head,
return NULL;
}
+static int udp_gro_complete_segment(struct sk_buff *skb)
+{
+ struct udphdr *uh = udp_hdr(skb);
+
+ skb->csum_start = (unsigned char *)uh - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+
+ skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
+ return 0;
+}
+
int udp_gro_complete(struct sk_buff *skb, int nhoff,
udp_lookup_t lookup)
{
@@ -437,16 +501,21 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
uh->len = newlen;
- /* Set encapsulation before calling into inner gro_complete() functions
- * to make them set up the inner offsets.
- */
- skb->encapsulation = 1;
-
rcu_read_lock();
sk = (*lookup)(skb, uh->source, uh->dest);
- if (sk && udp_sk(sk)->gro_complete)
+ if (sk && udp_sk(sk)->gro_enabled) {
+ err = udp_gro_complete_segment(skb);
+ } else if (sk && udp_sk(sk)->gro_complete) {
+ skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM
+ : SKB_GSO_UDP_TUNNEL;
+
+ /* Set encapsulation before calling into inner gro_complete()
+ * functions to make them set up the inner offsets.
+ */
+ skb->encapsulation = 1;
err = udp_sk(sk)->gro_complete(sk, skb,
nhoff + sizeof(struct udphdr));
+ }
rcu_read_unlock();
if (skb->remcsum_offload)
@@ -461,13 +530,9 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
const struct iphdr *iph = ip_hdr(skb);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
- if (uh->check) {
- skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+ if (uh->check)
uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
iph->daddr, 0);
- } else {
- skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
- }
return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
}
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 1b8e161ac527..828b2457f97b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -147,13 +147,9 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
- if (uh->check) {
- skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+ if (uh->check)
uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr,
&ipv6h->daddr, 0);
- } else {
- skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
- }
return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb);
}
--
2.17.2
^ permalink raw reply related
* [PATCH net-next 03/10] udp: add support for UDP_GRO cmsg
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
In-Reply-To: <cover.1541588248.git.pabeni@redhat.com>
When UDP GRO is enabled, the UDP_GRO cmsg will carry the ingress
datagram size. User-space can use such info to compute the original
packets layout.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
include/linux/udp.h | 11 +++++++++++
net/ipv4/udp.c | 4 ++++
net/ipv6/udp.c | 3 +++
3 files changed, 18 insertions(+)
diff --git a/include/linux/udp.h b/include/linux/udp.h
index f613b329852e..e23d5024f42f 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -121,6 +121,17 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
return udp_sk(sk)->no_check6_rx;
}
+static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb)
+{
+ int gso_size;
+
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+ gso_size = skb_shinfo(skb)->gso_size;
+ put_cmsg(msg, SOL_UDP, UDP_GRO, sizeof(gso_size), &gso_size);
+ }
+}
+
#define udp_portaddr_for_each_entry(__sk, list) \
hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0d447fd194c5..725ece9d78af 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1714,6 +1714,10 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
*addr_len = sizeof(*sin);
}
+
+ if (udp_sk(sk)->gro_enabled)
+ udp_cmsg_recv(msg, sk, skb);
+
if (inet->cmsg_flags)
ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index fc0ce6c59ebb..8e76e719305c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -421,6 +421,9 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
*addr_len = sizeof(*sin6);
}
+ if (udp_sk(sk)->gro_enabled)
+ udp_cmsg_recv(msg, sk, skb);
+
if (np->rxopt.all)
ip6_datagram_recv_common_ctl(sk, msg, skb);
--
2.17.2
^ permalink raw reply related
* [PATCH net-next 04/10] ip: factor out protocol delivery helper
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
In-Reply-To: <cover.1541588248.git.pabeni@redhat.com>
So that we can re-use it at the UDP level in a later patch
rfc v3 -> v1
- add the helper declaration into the ip header
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
include/net/ip.h | 1 +
net/ipv4/ip_input.c | 73 ++++++++++++++++++++++-----------------------
2 files changed, 37 insertions(+), 37 deletions(-)
diff --git a/include/net/ip.h b/include/net/ip.h
index 72593e171d14..cece69b5c531 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -155,6 +155,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
void ip_list_rcv(struct list_head *head, struct packet_type *pt,
struct net_device *orig_dev);
int ip_local_deliver(struct sk_buff *skb);
+void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto);
int ip_mr_input(struct sk_buff *skb);
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 35a786c0aaa0..72250b4e466d 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -188,51 +188,50 @@ bool ip_call_ra_chain(struct sk_buff *skb)
return false;
}
-static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
{
- __skb_pull(skb, skb_network_header_len(skb));
-
- rcu_read_lock();
- {
- int protocol = ip_hdr(skb)->protocol;
- const struct net_protocol *ipprot;
- int raw;
+ const struct net_protocol *ipprot;
+ int raw, ret;
- resubmit:
- raw = raw_local_deliver(skb, protocol);
+resubmit:
+ raw = raw_local_deliver(skb, protocol);
- ipprot = rcu_dereference(inet_protos[protocol]);
- if (ipprot) {
- int ret;
-
- if (!ipprot->no_policy) {
- if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- kfree_skb(skb);
- goto out;
- }
- nf_reset(skb);
+ ipprot = rcu_dereference(inet_protos[protocol]);
+ if (ipprot) {
+ if (!ipprot->no_policy) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+ kfree_skb(skb);
+ return;
}
- ret = ipprot->handler(skb);
- if (ret < 0) {
- protocol = -ret;
- goto resubmit;
+ nf_reset(skb);
+ }
+ ret = ipprot->handler(skb);
+ if (ret < 0) {
+ protocol = -ret;
+ goto resubmit;
+ }
+ __IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
+ } else {
+ if (!raw) {
+ if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+ __IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS);
+ icmp_send(skb, ICMP_DEST_UNREACH,
+ ICMP_PROT_UNREACH, 0);
}
- __IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
+ kfree_skb(skb);
} else {
- if (!raw) {
- if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- __IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS);
- icmp_send(skb, ICMP_DEST_UNREACH,
- ICMP_PROT_UNREACH, 0);
- }
- kfree_skb(skb);
- } else {
- __IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
- consume_skb(skb);
- }
+ __IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
+ consume_skb(skb);
}
}
- out:
+}
+
+static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ __skb_pull(skb, skb_network_header_len(skb));
+
+ rcu_read_lock();
+ ip_protocol_deliver_rcu(net, skb, ip_hdr(skb)->protocol);
rcu_read_unlock();
return 0;
--
2.17.2
^ permalink raw reply related
* [PATCH net-next 05/10] ipv6: factor out protocol delivery helper
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
In-Reply-To: <cover.1541588248.git.pabeni@redhat.com>
So that we can re-use it at the UDP level in the next patch
rfc v3 -> v1:
- add the helper declaration into the ipv6 header
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
include/net/ipv6.h | 2 ++
net/ipv6/ip6_input.c | 28 ++++++++++++++++------------
2 files changed, 18 insertions(+), 12 deletions(-)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 829650540780..daf80863d3a5 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -975,6 +975,8 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip6_forward(struct sk_buff *skb);
int ip6_input(struct sk_buff *skb);
int ip6_mc_input(struct sk_buff *skb);
+void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
+ bool have_final);
int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 96577e742afd..3065226bdc57 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -319,28 +319,26 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
/*
* Deliver the packet to the host
*/
-
-
-static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
+ bool have_final)
{
const struct inet6_protocol *ipprot;
struct inet6_dev *idev;
unsigned int nhoff;
- int nexthdr;
bool raw;
- bool have_final = false;
/*
* Parse extension headers
*/
- rcu_read_lock();
resubmit:
idev = ip6_dst_idev(skb_dst(skb));
- if (!pskb_pull(skb, skb_transport_offset(skb)))
- goto discard;
nhoff = IP6CB(skb)->nhoff;
- nexthdr = skb_network_header(skb)[nhoff];
+ if (!have_final) {
+ if (!pskb_pull(skb, skb_transport_offset(skb)))
+ goto discard;
+ nexthdr = skb_network_header(skb)[nhoff];
+ }
resubmit_final:
raw = raw6_local_deliver(skb, nexthdr);
@@ -411,13 +409,19 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
consume_skb(skb);
}
}
- rcu_read_unlock();
- return 0;
+ return;
discard:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
- rcu_read_unlock();
kfree_skb(skb);
+}
+
+static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ rcu_read_lock();
+ ip6_protocol_deliver_rcu(net, skb, 0, false);
+ rcu_read_unlock();
+
return 0;
}
--
2.17.2
^ permalink raw reply related
* [PATCH net-next 06/10] udp: cope with UDP GRO packet misdirection
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
In-Reply-To: <cover.1541588248.git.pabeni@redhat.com>
In some scenarios, the GRO engine can assemble an UDP GRO packet
that ultimately lands on a non GRO-enabled socket.
This patch tries to address the issue explicitly checking for the UDP
socket features before enqueuing the packet, and eventually segmenting
the unexpected GRO packet, as needed.
We must also cope with re-insertion requests: after segmentation the
UDP code calls the helper introduced by the previous patches, as needed.
Segmentation is performed by a common helper, which takes care of
updating socket and protocol stats is case of failure.
rfc v3 -> v1
- fix compile issues with rxrpc
- when gso_segment returns NULL, treat is as an error
- added 'ipv4' argument to udp_rcv_segment()
rfc v2 -> rfc v3
- moved udp_rcv_segment() into net/udp.h, account errors to socket
and ns, always return NULL or segs list
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
include/linux/udp.h | 6 ++++++
include/net/udp.h | 45 +++++++++++++++++++++++++++++++++++++--------
net/ipv4/udp.c | 23 ++++++++++++++++++++++-
net/ipv6/udp.c | 24 +++++++++++++++++++++++-
4 files changed, 88 insertions(+), 10 deletions(-)
diff --git a/include/linux/udp.h b/include/linux/udp.h
index e23d5024f42f..0a9c54e76305 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -132,6 +132,12 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk,
}
}
+static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb)
+{
+ return !udp_sk(sk)->gro_enabled && skb_is_gso(skb) &&
+ skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4;
+}
+
#define udp_portaddr_for_each_entry(__sk, list) \
hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node)
diff --git a/include/net/udp.h b/include/net/udp.h
index 9e82cb391dea..90a2954962eb 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -406,17 +406,24 @@ static inline int copy_linear_skb(struct sk_buff *skb, int len, int off,
} while(0)
#if IS_ENABLED(CONFIG_IPV6)
-#define __UDPX_INC_STATS(sk, field) \
-do { \
- if ((sk)->sk_family == AF_INET) \
- __UDP_INC_STATS(sock_net(sk), field, 0); \
- else \
- __UDP6_INC_STATS(sock_net(sk), field, 0); \
-} while (0)
+#define __UDPX_MIB(sk, ipv4) \
+({ \
+ ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \
+ sock_net(sk)->mib.udp_statistics) : \
+ (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 : \
+ sock_net(sk)->mib.udp_stats_in6); \
+})
#else
-#define __UDPX_INC_STATS(sk, field) __UDP_INC_STATS(sock_net(sk), field, 0)
+#define __UDPX_MIB(sk, ipv4) \
+({ \
+ IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \
+ sock_net(sk)->mib.udp_statistics; \
+})
#endif
+#define __UDPX_INC_STATS(sk, field) \
+ __SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field)
+
#ifdef CONFIG_PROC_FS
struct udp_seq_afinfo {
sa_family_t family;
@@ -450,4 +457,26 @@ DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
void udpv6_encap_enable(void);
#endif
+static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
+ struct sk_buff *skb, bool ipv4)
+{
+ struct sk_buff *segs;
+
+ /* the GSO CB lays after the UDP one, no need to save and restore any
+ * CB fragment
+ */
+ segs = __skb_gso_segment(skb, NETIF_F_SG, false);
+ if (unlikely(IS_ERR_OR_NULL(segs))) {
+ int segs_nr = skb_shinfo(skb)->gso_segs;
+
+ atomic_add(segs_nr, &sk->sk_drops);
+ SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr);
+ kfree_skb(skb);
+ return NULL;
+ }
+
+ consume_skb(skb);
+ return segs;
+}
+
#endif /* _UDP_H */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 725ece9d78af..73926352960c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1909,7 +1909,7 @@ EXPORT_SYMBOL(udp_encap_enable);
* Note that in the success and error cases, the skb is assumed to
* have either been requeued or freed.
*/
-static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
int is_udplite = IS_UDPLITE(sk);
@@ -2012,6 +2012,27 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
return -1;
}
+static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ struct sk_buff *next, *segs;
+ int ret;
+
+ if (likely(!udp_unexpected_gso(sk, skb)))
+ return udp_queue_rcv_one_skb(sk, skb);
+
+ BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET);
+ __skb_push(skb, -skb_mac_offset(skb));
+ segs = udp_rcv_segment(sk, skb, true);
+ for (skb = segs; skb; skb = next) {
+ next = skb->next;
+ __skb_pull(skb, skb_transport_offset(skb));
+ ret = udp_queue_rcv_one_skb(sk, skb);
+ if (ret > 0)
+ ip_protocol_deliver_rcu(dev_net(skb->dev), skb, -ret);
+ }
+ return 0;
+}
+
/* For TCP sockets, sk_rx_dst is protected by socket lock
* For UDP, we use xchg() to guard against concurrent changes.
*/
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 8e76e719305c..f7666e34fec9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -558,7 +558,7 @@ void udpv6_encap_enable(void)
}
EXPORT_SYMBOL(udpv6_encap_enable);
-static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
int is_udplite = IS_UDPLITE(sk);
@@ -641,6 +641,28 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
return -1;
}
+static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ struct sk_buff *next, *segs;
+ int ret;
+
+ if (likely(!udp_unexpected_gso(sk, skb)))
+ return udpv6_queue_rcv_one_skb(sk, skb);
+
+ __skb_push(skb, -skb_mac_offset(skb));
+ segs = udp_rcv_segment(sk, skb, false);
+ for (skb = segs; skb; skb = next) {
+ next = skb->next;
+ __skb_pull(skb, skb_transport_offset(skb));
+
+ ret = udpv6_queue_rcv_one_skb(sk, skb);
+ if (ret > 0)
+ ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret,
+ true);
+ }
+ return 0;
+}
+
static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
__be16 loc_port, const struct in6_addr *loc_addr,
__be16 rmt_port, const struct in6_addr *rmt_addr,
--
2.17.2
^ permalink raw reply related
* [PATCH net-next 07/10] selftests: add GRO support to udp bench rx program
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
In-Reply-To: <cover.1541588248.git.pabeni@redhat.com>
And fix a couple of buglets (port option processing,
clean termination on SIGINT). This is preparatory work
for GRO tests.
rfc v2 -> rfc v3:
- use ETH_MAX_MTU
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
tools/testing/selftests/net/udpgso_bench_rx.c | 37 +++++++++++++++----
1 file changed, 30 insertions(+), 7 deletions(-)
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 727cf67a3f75..8f48d7fb32cf 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -31,9 +31,15 @@
#include <sys/wait.h>
#include <unistd.h>
+#ifndef UDP_GRO
+#define UDP_GRO 104
+#endif
+
static int cfg_port = 8000;
static bool cfg_tcp;
static bool cfg_verify;
+static bool cfg_read_all;
+static bool cfg_gro_segment;
static bool interrupted;
static unsigned long packets, bytes;
@@ -63,6 +69,8 @@ static void do_poll(int fd)
do {
ret = poll(&pfd, 1, 10);
+ if (interrupted)
+ break;
if (ret == -1)
error(1, errno, "poll");
if (ret == 0)
@@ -70,7 +78,7 @@ static void do_poll(int fd)
if (pfd.revents != POLLIN)
error(1, errno, "poll: 0x%x expected 0x%x\n",
pfd.revents, POLLIN);
- } while (!ret && !interrupted);
+ } while (!ret);
}
static int do_socket(bool do_tcp)
@@ -102,6 +110,8 @@ static int do_socket(bool do_tcp)
error(1, errno, "listen");
do_poll(accept_fd);
+ if (interrupted)
+ exit(0);
fd = accept(accept_fd, NULL, NULL);
if (fd == -1)
@@ -167,10 +177,10 @@ static void do_verify_udp(const char *data, int len)
/* Flush all outstanding datagrams. Verify first few bytes of each. */
static void do_flush_udp(int fd)
{
- static char rbuf[ETH_DATA_LEN];
+ static char rbuf[ETH_MAX_MTU];
int ret, len, budget = 256;
- len = cfg_verify ? sizeof(rbuf) : 0;
+ len = cfg_read_all ? sizeof(rbuf) : 0;
while (budget--) {
/* MSG_TRUNC will make return value full datagram length */
ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
@@ -178,7 +188,7 @@ static void do_flush_udp(int fd)
return;
if (ret == -1)
error(1, errno, "recv");
- if (len) {
+ if (len && cfg_verify) {
if (ret == 0)
error(1, errno, "recv: 0 byte datagram\n");
@@ -192,23 +202,30 @@ static void do_flush_udp(int fd)
static void usage(const char *filepath)
{
- error(1, 0, "Usage: %s [-tv] [-p port]", filepath);
+ error(1, 0, "Usage: %s [-Grtv] [-p port]", filepath);
}
static void parse_opts(int argc, char **argv)
{
int c;
- while ((c = getopt(argc, argv, "ptv")) != -1) {
+ while ((c = getopt(argc, argv, "Gp:rtv")) != -1) {
switch (c) {
+ case 'G':
+ cfg_gro_segment = true;
+ break;
case 'p':
- cfg_port = htons(strtoul(optarg, NULL, 0));
+ cfg_port = strtoul(optarg, NULL, 0);
+ break;
+ case 'r':
+ cfg_read_all = true;
break;
case 't':
cfg_tcp = true;
break;
case 'v':
cfg_verify = true;
+ cfg_read_all = true;
break;
}
}
@@ -227,6 +244,12 @@ static void do_recv(void)
fd = do_socket(cfg_tcp);
+ if (cfg_gro_segment && !cfg_tcp) {
+ int val = 1;
+ if (setsockopt(fd, IPPROTO_UDP, UDP_GRO, &val, sizeof(val)))
+ error(1, errno, "setsockopt UDP_GRO");
+ }
+
treport = gettimeofday_ms() + 1000;
do {
do_poll(fd);
--
2.17.2
^ permalink raw reply related
* [PATCH net-next 08/10] selftests: add dummy xdp test helper
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
In-Reply-To: <cover.1541588248.git.pabeni@redhat.com>
This trivial XDP program does nothing, but will be used by the
next patch to test the GRO path in a net namespace, leveraging
the veth XDP implementation.
It's added here, despite its 'net' usage, to avoid the duplication
of the llc-related makefile boilerplate.
rfc v3 -> v1:
- move the helper implementation into the bpf directory, don't
touch udpgso_bench_rx
rfc v2 -> rfc v3:
- move 'x' option handling here
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
tools/testing/selftests/bpf/Makefile | 3 ++-
tools/testing/selftests/bpf/xdp_dummy.c | 13 +++++++++++++
2 files changed, 15 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/xdp_dummy.c
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e39dfb4e7970..4a54236475ae 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -37,7 +37,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
- test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o
+ test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o \
+ xdp_dummy.o
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
diff --git a/tools/testing/selftests/bpf/xdp_dummy.c b/tools/testing/selftests/bpf/xdp_dummy.c
new file mode 100644
index 000000000000..43b0ef1001ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_dummy.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+SEC("xdp_dummy")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
--
2.17.2
^ permalink raw reply related
* [PATCH net-next 09/10] selftests: add some benchmark for UDP GRO
From: Paolo Abeni @ 2018-11-07 11:38 UTC (permalink / raw)
To: netdev
Cc: David S. Miller, Willem de Bruijn, Steffen Klassert,
Subash Abhinov Kasiviswanathan
In-Reply-To: <cover.1541588248.git.pabeni@redhat.com>
Run on top of veth pair, using a dummy XDP program to enable the GRO.
rfc v3 -> v1:
- use ip route to attach the xdp helper to the veth
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
tools/testing/selftests/net/Makefile | 1 +
tools/testing/selftests/net/udpgro_bench.sh | 93 +++++++++++++++++++++
2 files changed, 94 insertions(+)
create mode 100755 tools/testing/selftests/net/udpgro_bench.sh
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 256d82d5fa87..b1bba2f60467 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,6 +7,7 @@ CFLAGS += -I../../../../usr/include/
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
+TEST_PROGS += udpgro_bench.sh
TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
new file mode 100755
index 000000000000..9ef4b1ee0f76
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -0,0 +1,93 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgro benchmarks
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+cleanup() {
+ local -r jobs="$(jobs -p)"
+ local -r ns="$(ip netns list|grep $PEER_NS)"
+
+ [ -n "${jobs}" ] && kill -INT ${jobs} 2>/dev/null
+ [ -n "$ns" ] && ip netns del $ns 2>/dev/null
+}
+trap cleanup EXIT
+
+run_one() {
+ # use 'rx' as separator between sender args and receiver args
+ local -r all="$@"
+ local -r tx_args=${all%rx*}
+ local -r rx_args=${all#*rx}
+
+ ip netns add "${PEER_NS}"
+ ip -netns "${PEER_NS}" link set lo up
+ ip link add type veth
+ ip link set dev veth0 up
+ ip addr add dev veth0 192.168.1.2/24
+ ip addr add dev veth0 2001:db8::2/64 nodad
+
+ ip link set dev veth1 netns "${PEER_NS}"
+ ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+ ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+ ip -netns "${PEER_NS}" link set dev veth1 up
+
+ ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r &
+
+ # Hack: let bg programs complete the startup
+ sleep 0.1
+ ./udpgso_bench_tx ${tx_args}
+}
+
+run_in_netns() {
+ local -r args=$@
+
+ ./in_netns.sh $0 __subprocess ${args}
+}
+
+run_udp() {
+ local -r args=$@
+
+ echo "udp gso - over veth touching data"
+ run_in_netns ${args} -S rx
+
+ echo "udp gso and gro - over veth touching data"
+ run_in_netns ${args} -S rx -G
+}
+
+run_tcp() {
+ local -r args=$@
+
+ echo "tcp - over veth touching data"
+ run_in_netns ${args} -t rx
+}
+
+run_all() {
+ local -r core_args="-l 4"
+ local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
+ local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+
+ echo "ipv4"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv4_args}"
+
+ echo "ipv6"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv6_args}"
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+ echo "Missing xdp_dummy helper. Build bpf selftest first"
+ exit -1
+fi
+
+if [[ $# -eq 0 ]]; then
+ run_all
+elif [[ $1 == "__subprocess" ]]; then
+ shift
+ run_one $@
+else
+ run_in_netns $@
+fi
--
2.17.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox