| Message ID | 20250116153908.515848-2-maciej.fijalkowski@intel.com (mailing list archive) |
|---|---|
| State | New |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | ice: fix Rx data path for heavy 9k MTU traffic | expand |
On 16. 01. 25 16:39, Maciej Fijalkowski wrote: > Introduce a new helper ice_put_rx_mbuf() that will go through gathered > frags from current frame and will call ice_put_rx_buf() on them. Current > logic that was supposed to simplify and optimize the driver where we go > through a batch of all buffers processed in current NAPI instance turned > out to be broken for jumbo frames and very heavy load that was coming > from both multi-thread iperf and nginx/wrk pair between server and > client. The delay introduced by approach that we are dropping is simply > too big and we need to take the decision regarding page > recycling/releasing as quick as we can. > > While at it, address an error path of ice_add_xdp_frag() - we were > missing buffer putting from day 1 there. > > As a nice side effect we get rid of annoying and repetetive three-liner: > > xdp->data = NULL; > rx_ring->first_desc = ntc; > rx_ring->nr_frags = 0; > > by embedding it within introduced routine. > > Fixes: 1dc1a7e7f410 ("ice: Centrallize Rx buffer recycling") > Reported-and-tested-by: Xu Du <xudu@redhat.com> > Co-developed-by: Jacob Keller <jacob.e.keller@intel.com> > Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> > Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> > --- > drivers/net/ethernet/intel/ice/ice_txrx.c | 67 +++++++++++++---------- > 1 file changed, 38 insertions(+), 29 deletions(-) > > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c > index 5d2d7736fd5f..501df1bc881d 100644 > --- a/drivers/net/ethernet/intel/ice/ice_txrx.c > +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c > @@ -1103,6 +1103,37 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) > rx_buf->page = NULL; > } > > +static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, > + u32 *xdp_xmit) > +{ > + u32 nr_frags = rx_ring->nr_frags + 1; > + u32 idx = rx_ring->first_desc; > + u32 cnt = rx_ring->count; > + struct ice_rx_buf *buf; > + > + for (int i = 0; i < nr_frags; i++) { > + buf = &rx_ring->rx_buf[idx]; > + > + if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { > + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); > + *xdp_xmit |= buf->act; > + } else if (buf->act & ICE_XDP_CONSUMED) { > + buf->pagecnt_bias++; > + } else if (buf->act == ICE_XDP_PASS) { > + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); > + } > + > + ice_put_rx_buf(rx_ring, buf); > + > + if (++idx == cnt) > + idx = 0; > + } > + > + xdp->data = NULL; > + rx_ring->first_desc = ntc; ntc is not delared in this scope > + rx_ring->nr_frags = 0; > +} > + > /** > * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf > * @rx_ring: Rx descriptor ring to transact packets on > @@ -1120,7 +1151,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > unsigned int total_rx_bytes = 0, total_rx_pkts = 0; > unsigned int offset = rx_ring->rx_offset; > struct xdp_buff *xdp = &rx_ring->xdp; > - u32 cached_ntc = rx_ring->first_desc; > struct ice_tx_ring *xdp_ring = NULL; > struct bpf_prog *xdp_prog = NULL; > u32 ntc = rx_ring->next_to_clean; > @@ -1128,7 +1158,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > u32 xdp_xmit = 0; > u32 cached_ntu; > bool failure; > - u32 first; > > xdp_prog = READ_ONCE(rx_ring->xdp_prog); > if (xdp_prog) { > @@ -1190,6 +1219,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); > xdp_buff_clear_frags_flag(xdp); > } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { > + ice_put_rx_mbuf(rx_ring, xdp, NULL); > break; > } > if (++ntc == cnt) > @@ -1205,9 +1235,8 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > total_rx_bytes += xdp_get_buff_len(xdp); > total_rx_pkts++; > > - xdp->data = NULL; > - rx_ring->first_desc = ntc; > - rx_ring->nr_frags = 0; > + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit); > + > continue; > construct_skb: > if (likely(ice_ring_uses_build_skb(rx_ring))) > @@ -1221,14 +1250,11 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > if (unlikely(xdp_buff_has_frags(xdp))) > ice_set_rx_bufs_act(xdp, rx_ring, > ICE_XDP_CONSUMED); > - xdp->data = NULL; > - rx_ring->first_desc = ntc; > - rx_ring->nr_frags = 0; > - break; > } > - xdp->data = NULL; > - rx_ring->first_desc = ntc; > - rx_ring->nr_frags = 0; > + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit); > + > + if (!skb) > + break; > > stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); > if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, > @@ -1257,23 +1283,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > total_rx_pkts++; > } > > - first = rx_ring->first_desc; > - while (cached_ntc != first) { > - struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc]; > - > - if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { > - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); > - xdp_xmit |= buf->act; > - } else if (buf->act & ICE_XDP_CONSUMED) { > - buf->pagecnt_bias++; > - } else if (buf->act == ICE_XDP_PASS) { > - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); > - } > - > - ice_put_rx_buf(rx_ring, buf); > - if (++cached_ntc >= cnt) > - cached_ntc = 0; > - } > rx_ring->next_to_clean = ntc; > /* return up to cleaned_count buffers to hardware */ > failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
On Thu, Jan 16, 2025 at 06:10:38PM +0100, Petr Oros wrote: > > On 16. 01. 25 16:39, Maciej Fijalkowski wrote: > > Introduce a new helper ice_put_rx_mbuf() that will go through gathered > > frags from current frame and will call ice_put_rx_buf() on them. Current > > logic that was supposed to simplify and optimize the driver where we go > > through a batch of all buffers processed in current NAPI instance turned > > out to be broken for jumbo frames and very heavy load that was coming > > from both multi-thread iperf and nginx/wrk pair between server and > > client. The delay introduced by approach that we are dropping is simply > > too big and we need to take the decision regarding page > > recycling/releasing as quick as we can. > > > > While at it, address an error path of ice_add_xdp_frag() - we were > > missing buffer putting from day 1 there. > > > > As a nice side effect we get rid of annoying and repetetive three-liner: > > > > xdp->data = NULL; > > rx_ring->first_desc = ntc; > > rx_ring->nr_frags = 0; > > > > by embedding it within introduced routine. > > > > Fixes: 1dc1a7e7f410 ("ice: Centrallize Rx buffer recycling") > > Reported-and-tested-by: Xu Du <xudu@redhat.com> > > Co-developed-by: Jacob Keller <jacob.e.keller@intel.com> > > Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> > > Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> > > --- > > drivers/net/ethernet/intel/ice/ice_txrx.c | 67 +++++++++++++---------- > > 1 file changed, 38 insertions(+), 29 deletions(-) > > > > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c > > index 5d2d7736fd5f..501df1bc881d 100644 > > --- a/drivers/net/ethernet/intel/ice/ice_txrx.c > > +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c > > @@ -1103,6 +1103,37 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) > > rx_buf->page = NULL; > > } > > +static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, > > + u32 *xdp_xmit) > > +{ > > + u32 nr_frags = rx_ring->nr_frags + 1; > > + u32 idx = rx_ring->first_desc; > > + u32 cnt = rx_ring->count; > > + struct ice_rx_buf *buf; > > + > > + for (int i = 0; i < nr_frags; i++) { > > + buf = &rx_ring->rx_buf[idx]; > > + > > + if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { > > + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); > > + *xdp_xmit |= buf->act; > > + } else if (buf->act & ICE_XDP_CONSUMED) { > > + buf->pagecnt_bias++; > > + } else if (buf->act == ICE_XDP_PASS) { > > + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); > > + } > > + > > + ice_put_rx_buf(rx_ring, buf); > > + > > + if (++idx == cnt) > > + idx = 0; > > + } > > + > > + xdp->data = NULL; > > + rx_ring->first_desc = ntc; > ntc is not delared in this scope Yikes! That happens when you change things right before submission. Thanks for being faster than build bots. I'll wait 24h and send a v2. > > + rx_ring->nr_frags = 0; > > +} > > + > > /** > > * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf > > * @rx_ring: Rx descriptor ring to transact packets on > > @@ -1120,7 +1151,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > > unsigned int total_rx_bytes = 0, total_rx_pkts = 0; > > unsigned int offset = rx_ring->rx_offset; > > struct xdp_buff *xdp = &rx_ring->xdp; > > - u32 cached_ntc = rx_ring->first_desc; > > struct ice_tx_ring *xdp_ring = NULL; > > struct bpf_prog *xdp_prog = NULL; > > u32 ntc = rx_ring->next_to_clean; > > @@ -1128,7 +1158,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > > u32 xdp_xmit = 0; > > u32 cached_ntu; > > bool failure; > > - u32 first; > > xdp_prog = READ_ONCE(rx_ring->xdp_prog); > > if (xdp_prog) { > > @@ -1190,6 +1219,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > > xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); > > xdp_buff_clear_frags_flag(xdp); > > } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { > > + ice_put_rx_mbuf(rx_ring, xdp, NULL); > > break; > > } > > if (++ntc == cnt) > > @@ -1205,9 +1235,8 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > > total_rx_bytes += xdp_get_buff_len(xdp); > > total_rx_pkts++; > > - xdp->data = NULL; > > - rx_ring->first_desc = ntc; > > - rx_ring->nr_frags = 0; > > + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit); > > + > > continue; > > construct_skb: > > if (likely(ice_ring_uses_build_skb(rx_ring))) > > @@ -1221,14 +1250,11 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > > if (unlikely(xdp_buff_has_frags(xdp))) > > ice_set_rx_bufs_act(xdp, rx_ring, > > ICE_XDP_CONSUMED); > > - xdp->data = NULL; > > - rx_ring->first_desc = ntc; > > - rx_ring->nr_frags = 0; > > - break; > > } > > - xdp->data = NULL; > > - rx_ring->first_desc = ntc; > > - rx_ring->nr_frags = 0; > > + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit); > > + > > + if (!skb) > > + break; > > stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); > > if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, > > @@ -1257,23 +1283,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) > > total_rx_pkts++; > > } > > - first = rx_ring->first_desc; > > - while (cached_ntc != first) { > > - struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc]; > > - > > - if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { > > - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); > > - xdp_xmit |= buf->act; > > - } else if (buf->act & ICE_XDP_CONSUMED) { > > - buf->pagecnt_bias++; > > - } else if (buf->act == ICE_XDP_PASS) { > > - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); > > - } > > - > > - ice_put_rx_buf(rx_ring, buf); > > - if (++cached_ntc >= cnt) > > - cached_ntc = 0; > > - } > > rx_ring->next_to_clean = ntc; > > /* return up to cleaned_count buffers to hardware */ > > failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring)); >
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 5d2d7736fd5f..501df1bc881d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1103,6 +1103,37 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) rx_buf->page = NULL; } +static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, + u32 *xdp_xmit) +{ + u32 nr_frags = rx_ring->nr_frags + 1; + u32 idx = rx_ring->first_desc; + u32 cnt = rx_ring->count; + struct ice_rx_buf *buf; + + for (int i = 0; i < nr_frags; i++) { + buf = &rx_ring->rx_buf[idx]; + + if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + *xdp_xmit |= buf->act; + } else if (buf->act & ICE_XDP_CONSUMED) { + buf->pagecnt_bias++; + } else if (buf->act == ICE_XDP_PASS) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + } + + ice_put_rx_buf(rx_ring, buf); + + if (++idx == cnt) + idx = 0; + } + + xdp->data = NULL; + rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; +} + /** * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: Rx descriptor ring to transact packets on @@ -1120,7 +1151,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_pkts = 0; unsigned int offset = rx_ring->rx_offset; struct xdp_buff *xdp = &rx_ring->xdp; - u32 cached_ntc = rx_ring->first_desc; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; @@ -1128,7 +1158,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) u32 xdp_xmit = 0; u32 cached_ntu; bool failure; - u32 first; xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { @@ -1190,6 +1219,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { + ice_put_rx_mbuf(rx_ring, xdp, NULL); break; } if (++ntc == cnt) @@ -1205,9 +1235,8 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) total_rx_bytes += xdp_get_buff_len(xdp); total_rx_pkts++; - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit); + continue; construct_skb: if (likely(ice_ring_uses_build_skb(rx_ring))) @@ -1221,14 +1250,11 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) if (unlikely(xdp_buff_has_frags(xdp))) ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED); - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; - break; } - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit); + + if (!skb) + break; stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, @@ -1257,23 +1283,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) total_rx_pkts++; } - first = rx_ring->first_desc; - while (cached_ntc != first) { - struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc]; - - if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - xdp_xmit |= buf->act; - } else if (buf->act & ICE_XDP_CONSUMED) { - buf->pagecnt_bias++; - } else if (buf->act == ICE_XDP_PASS) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - } - - ice_put_rx_buf(rx_ring, buf); - if (++cached_ntc >= cnt) - cached_ntc = 0; - } rx_ring->next_to_clean = ntc; /* return up to cleaned_count buffers to hardware */ failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
Introduce a new helper ice_put_rx_mbuf() that will go through gathered frags from current frame and will call ice_put_rx_buf() on them. Current logic that was supposed to simplify and optimize the driver where we go through a batch of all buffers processed in current NAPI instance turned out to be broken for jumbo frames and very heavy load that was coming from both multi-thread iperf and nginx/wrk pair between server and client. The delay introduced by approach that we are dropping is simply too big and we need to take the decision regarding page recycling/releasing as quick as we can. While at it, address an error path of ice_add_xdp_frag() - we were missing buffer putting from day 1 there. As a nice side effect we get rid of annoying and repetetive three-liner: xdp->data = NULL; rx_ring->first_desc = ntc; rx_ring->nr_frags = 0; by embedding it within introduced routine. Fixes: 1dc1a7e7f410 ("ice: Centrallize Rx buffer recycling") Reported-and-tested-by: Xu Du <xudu@redhat.com> Co-developed-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> --- drivers/net/ethernet/intel/ice/ice_txrx.c | 67 +++++++++++++---------- 1 file changed, 38 insertions(+), 29 deletions(-)