diff options
author | Shannon Nelson <shannon.nelson@amd.com> | 2023-09-19 01:21:34 +0300 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2023-09-20 12:52:31 +0300 |
commit | 4d9d72200d4c69710e8371c872449c46bcab646f (patch) | |
tree | 5573031c0dff51a8aa904999e1a6cef13defae33 | |
parent | 4fa7011d4f22d5b2e14cba19b524a4f90268b5c1 (diff) | |
download | linux-4d9d72200d4c69710e8371c872449c46bcab646f.tar.xz |
ionic: count SGs in packet to minimize linearize
There are some cases where an skb carries more frags than the
number of SGs that ionic can support per descriptor - this
forces the driver to linearize the skb. However, if this
is a TSO packet that is going to become multiple descriptors
(one per MTU-sized packet) and spread the frags across them,
this time-consuming linearization is likely not necessary.
We scan the frag list and count up the number of SGs that
would be created for each descriptor that would be generated,
and only linearize if we hit the SG limit on a descriptor.
In most cases, we won't even get to the frag list scan, so
this doesn't affect typical traffic.
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r-- | drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 77 |
1 files changed, 68 insertions, 9 deletions
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 26798fc635db..c08a61323066 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -1239,25 +1239,84 @@ static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb) static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) { struct ionic_tx_stats *stats = q_to_tx_stats(q); + bool too_many_frags = false; + skb_frag_t *frag; + int desc_bufs; + int chunk_len; + int frag_rem; + int tso_rem; + int seg_rem; + bool encap; + int hdrlen; int ndescs; int err; /* Each desc is mss long max, so a descriptor for each gso_seg */ - if (skb_is_gso(skb)) + if (skb_is_gso(skb)) { ndescs = skb_shinfo(skb)->gso_segs; - else + } else { ndescs = 1; + if (skb_shinfo(skb)->nr_frags > q->max_sg_elems) { + too_many_frags = true; + goto linearize; + } + } - /* If non-TSO, just need 1 desc and nr_frags sg elems */ - if (skb_shinfo(skb)->nr_frags <= q->max_sg_elems) + /* If non-TSO, or no frags to check, we're done */ + if (!skb_is_gso(skb) || !skb_shinfo(skb)->nr_frags) return ndescs; - /* Too many frags, so linearize */ - err = skb_linearize(skb); - if (err) - return err; + /* We need to scan the skb to be sure that none of the MTU sized + * packets in the TSO will require more sgs per descriptor than we + * can support. We loop through the frags, add up the lengths for + * a packet, and count the number of sgs used per packet. + */ + tso_rem = skb->len; + frag = skb_shinfo(skb)->frags; + encap = skb->encapsulation; + + /* start with just hdr in first part of first descriptor */ + if (encap) + hdrlen = skb_inner_tcp_all_headers(skb); + else + hdrlen = skb_tcp_all_headers(skb); + seg_rem = min_t(int, tso_rem, hdrlen + skb_shinfo(skb)->gso_size); + frag_rem = hdrlen; + + while (tso_rem > 0) { + desc_bufs = 0; + while (seg_rem > 0) { + desc_bufs++; + + /* We add the +1 because we can take buffers for one + * more than we have SGs: one for the initial desc data + * in addition to the SG segments that might follow. + */ + if (desc_bufs > q->max_sg_elems + 1) { + too_many_frags = true; + goto linearize; + } + + if (frag_rem == 0) { + frag_rem = skb_frag_size(frag); + frag++; + } + chunk_len = min(frag_rem, seg_rem); + frag_rem -= chunk_len; + tso_rem -= chunk_len; + seg_rem -= chunk_len; + } + + seg_rem = min_t(int, tso_rem, skb_shinfo(skb)->gso_size); + } - stats->linearize++; +linearize: + if (too_many_frags) { + err = skb_linearize(skb); + if (err) + return err; + stats->linearize++; + } return ndescs; } |