On 03/07/2018 11:22, Eelco Chaudron wrote:
>
>
> On 28 Jun 2018, at 17:41, Tiago Lam wrote:
>
>> When a dp_packet is from a DPDK source, and it contains multi-segment
>> mbufs, the data_len is not equal to the packet size, pkt_len. Instead,
>> the data_len of each mbuf in the chain should be considered while
>> distributing the new (provided) size.
>>
>> To account for the above dp_packet_set_size() has been changed so
>> that,
>> in the multi-segment mbufs case, only the data_len on the last mbuf of
>> the chain and the total size of the packet, pkt_len, are changed. The
>> data_len on the intermediate mbufs preceeding the last mbuf is not
>> changed by dp_packet_set_size(). Furthermore, in some cases
>> dp_packet_set_size() may be used to set a smaller size than the
>> current
>> packet size, thus effectively trimming the end of the packet. In the
>> multi-segment mbufs case this may lead to lingering mbufs that may
>> need
>> freeing.
>>
>> __dp_packet_set_data() now also updates an mbufs' data_len after
>> setting
>> the data offset. This is so that both fields are always in sync for
>> each
>> mbuf in a chain.
>>
>> Co-authored-by: Michael Qiu <[email protected]>
>> Co-authored-by: Mark Kavanagh <[email protected]>
>> Co-authored-by: Przemyslaw Lal <[email protected]>
>> Co-authored-by: Marcin Ksiadz <[email protected]>
>> Co-authored-by: Yuanhan Liu <[email protected]>
>>
>> Signed-off-by: Michael Qiu <[email protected]>
>> Signed-off-by: Mark Kavanagh <[email protected]>
>> Signed-off-by: Przemyslaw Lal <[email protected]>
>> Signed-off-by: Marcin Ksiadz <[email protected]>
>> Signed-off-by: Yuanhan Liu <[email protected]>
>> Signed-off-by: Tiago Lam <[email protected]>
>> ---
>> lib/dp-packet.h | 67
>> ++++++++++++++++++++++++++++++++++++++++++++++-----------
>> 1 file changed, 55 insertions(+), 12 deletions(-)
>>
>> diff --git a/lib/dp-packet.h b/lib/dp-packet.h
>> index c612ad4..d8cd35c 100644
>> --- a/lib/dp-packet.h
>> +++ b/lib/dp-packet.h
>> @@ -429,17 +429,44 @@ dp_packet_size(const struct dp_packet *b)
>> static inline void
>> dp_packet_set_size(struct dp_packet *b, uint32_t v)
>> {
>> - /* netdev-dpdk does not currently support segmentation;
>> consequently, for
>> - * all intents and purposes, 'data_len' (16 bit) and 'pkt_len'
>> (32 bit) may
>> - * be used interchangably.
>> - *
>> - * On the datapath, it is expected that the size of packets
>> - * (and thus 'v') will always be <= UINT16_MAX; this means that
>> there is no
>> - * loss of accuracy in assigning 'v' to 'data_len'.
>> - */
>> - b->mbuf.data_len = (uint16_t)v; /* Current seg length. */
>> - b->mbuf.pkt_len = v; /* Total length of all segments
>> linked to
>> - * this segment. */
>> + if (b->source == DPBUF_DPDK) {
>> + struct rte_mbuf *mbuf = &b->mbuf;
>> + struct rte_mbuf *fmbuf = mbuf;
>> + uint16_t new_len = v;
>> + uint16_t data_len;
>> + uint16_t nb_segs = 0;
>> + uint16_t pkt_len = 0;
>> +
>> + /* Trim 'v' length bytes from the end of the chained buffers,
>> freeing
>> + any buffers that may be left floating */
>> + while (mbuf) {
>> + data_len = MIN(new_len, mbuf->data_len);
>> + mbuf->data_len = data_len;
>> +
>> + if (new_len - data_len <= 0) {
>> + /* Free the rest of chained mbufs */
>> + free_dpdk_buf(CONTAINER_OF(mbuf->next, struct
>> dp_packet,
>> + mbuf));
>> + mbuf->next = NULL;
>> + } else if (!mbuf->next) {
>> + /* Don't assign more than what we have available */
>> + mbuf->data_len = MIN(new_len,
>> + mbuf->buf_len - mbuf->data_off);
>> + }
>> +
>> + new_len -= data_len;
>> + nb_segs += 1;
>> + pkt_len += mbuf->data_len;
>> + mbuf = mbuf->next;
>> + }
>> +
>> + fmbuf->nb_segs = nb_segs;
>> + fmbuf->pkt_len = pkt_len;
>
> Guess we do not need the extra variable, we can just do b->mbuf.pkt_len
> etc as below. Looks like a left over from the previous revision?
>
Good point, I got rid of it for v2.
> In the increase packet size case we can end up with an b->mbuf.pkt_len <
> v, maybe we should assert on this?
>
Yeah, it can happen if 'v' is bigger than the available tailroom. An
assertion sounds good in this case since dp_packet_set_size() relies on
the caller making sure there is enough space for performing the
operation (like allocating space themselves if not enough space is
available).
>> + } else {
>> + b->mbuf.data_len = v;
>> + /* Total length of all segments linked to this segment. */
>> + b->mbuf.pkt_len = v;
>> + }
>> }
>>
>> static inline uint16_t
>> @@ -451,7 +478,23 @@ __packet_data(const struct dp_packet *b)
>> static inline void
>> __packet_set_data(struct dp_packet *b, uint16_t v)
>> {
>> - b->mbuf.data_off = v;
>> + if (b->source == DPBUF_DPDK) {
>> + uint16_t prev_ofs = b->mbuf.data_off;
>> + b->mbuf.data_off = v;
>> + int16_t ofs_diff = prev_ofs - b->mbuf.data_off;
>> +
>> + /* When dealing with DPDK mbufs, keep data_off and data_len
>> in sync.
>> + * Thus, update data_len if the length changes with the move
>> of
>> + * data_off. However, if data_len is 0, there's no data to
>> move and
>> + * data_Len should remain 0. */
>> +
>
> What if the data offset moves to the second buffer? This would probably
> never happen as all APIs assume a single address space (and they seem to
> calculate the offset like this), but an assert might help to avoid
> problems in the future.
>
I'll use one here as well then, for the same reasons pointed out above.
Thanks for putting the time for reviewing the series, Eelco.
Tiago.
>> + if (b->mbuf.data_len != 0) {
>> + b->mbuf.data_len = MIN(b->mbuf.data_len + ofs_diff,
>> + b->mbuf.buf_len -
>> b->mbuf.data_off);
>> + }
>> + } else {
>> + b->mbuf.data_off = v;
>> + }
>> }
>>
>> static inline uint16_t
>> --
>> 2.7.4
_______________________________________________
dev mailing list
[email protected]
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
