From 5379260852b013902abbca691926b3ac1cac36d5 Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Mon, 3 May 2021 09:28:00 +0200 Subject: [PATCH 1/8] igb: Fix XDP with PTP enabled When using native XDP with the igb driver, the XDP frame data doesn't point to the beginning of the packet. It's off by 16 bytes. Everything works as expected with XDP skb mode. Actually these 16 bytes are used to store the packet timestamps. Therefore, pull the timestamp before executing any XDP operations and adjust all other code accordingly. The igc driver does it like that as well. Tested with Intel i210 card and AF_XDP sockets. Fixes: 9cbc948b5a20 ("igb: add XDP support") Signed-off-by: Kurt Kanzenbach Acked-by: Jesper Dangaard Brouer Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb.h | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 45 +++++++++++++---------- drivers/net/ethernet/intel/igb/igb_ptp.c | 23 +++++------- 3 files changed, 37 insertions(+), 33 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 7bda8c5edea5..2d3daf022651 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -749,7 +749,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter); void igb_ptp_tx_hang(struct igb_adapter *adapter); void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, - struct sk_buff *skb); + ktime_t *timestamp); int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); void igb_set_flag_queue_pairs(struct igb_adapter *, const u32); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 038a9fd1af44..0123285029fa 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8280,7 +8280,7 @@ static void igb_add_rx_frag(struct igb_ring *rx_ring, static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, struct xdp_buff *xdp, - union e1000_adv_rx_desc *rx_desc) + ktime_t timestamp) { #if (PAGE_SIZE < 8192) unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; @@ -8300,12 +8300,8 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, if (unlikely(!skb)) return NULL; - if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { - if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) { - xdp->data += IGB_TS_HDR_LEN; - size -= IGB_TS_HDR_LEN; - } - } + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; /* Determine available headroom for copy */ headlen = size; @@ -8336,7 +8332,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, struct xdp_buff *xdp, - union e1000_adv_rx_desc *rx_desc) + ktime_t timestamp) { #if (PAGE_SIZE < 8192) unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; @@ -8363,11 +8359,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, if (metasize) skb_metadata_set(skb, metasize); - /* pull timestamp out of packet data */ - if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb)) - __skb_pull(skb, IGB_TS_HDR_LEN); - } + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; /* update buffer offset */ #if (PAGE_SIZE < 8192) @@ -8682,7 +8675,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) while (likely(total_packets < budget)) { union e1000_adv_rx_desc *rx_desc; struct igb_rx_buffer *rx_buffer; + ktime_t timestamp = 0; + int pkt_offset = 0; unsigned int size; + void *pktbuf; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGB_RX_BUFFER_WRITE) { @@ -8702,14 +8698,24 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) dma_rmb(); rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt); + pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset; + + /* pull rx packet timestamp if available and valid */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + int ts_hdr_len; + + ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector, + pktbuf, ×tamp); + + pkt_offset += ts_hdr_len; + size -= ts_hdr_len; + } /* retrieve a buffer from the ring */ if (!skb) { - unsigned int offset = igb_rx_offset(rx_ring); - unsigned char *hard_start; + unsigned char *hard_start = pktbuf - igb_rx_offset(rx_ring); + unsigned int offset = pkt_offset + igb_rx_offset(rx_ring); - hard_start = page_address(rx_buffer->page) + - rx_buffer->page_offset - offset; xdp_prepare_buff(&xdp, hard_start, offset, size, true); #if (PAGE_SIZE > 4096) /* At larger PAGE_SIZE, frame_sz depend on len size */ @@ -8732,10 +8738,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) } else if (skb) igb_add_rx_frag(rx_ring, rx_buffer, skb, size); else if (ring_uses_build_skb(rx_ring)) - skb = igb_build_skb(rx_ring, rx_buffer, &xdp, rx_desc); + skb = igb_build_skb(rx_ring, rx_buffer, &xdp, + timestamp); else skb = igb_construct_skb(rx_ring, rx_buffer, - &xdp, rx_desc); + &xdp, timestamp); /* exit if we failed to retrieve a buffer */ if (!skb) { diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index ba61fe9bfaf4..d68cd4466a54 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -856,30 +856,28 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) dev_kfree_skb_any(skb); } -#define IGB_RET_PTP_DISABLED 1 -#define IGB_RET_PTP_INVALID 2 - /** * igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp * @q_vector: Pointer to interrupt specific structure * @va: Pointer to address containing Rx buffer - * @skb: Buffer containing timestamp and packet + * @timestamp: Pointer where timestamp will be stored * * This function is meant to retrieve a timestamp from the first buffer of an * incoming frame. The value is stored in little endian format starting on * byte 8 * - * Returns: 0 if success, nonzero if failure + * Returns: The timestamp header length or 0 if not available **/ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, - struct sk_buff *skb) + ktime_t *timestamp) { struct igb_adapter *adapter = q_vector->adapter; + struct skb_shared_hwtstamps ts; __le64 *regval = (__le64 *)va; int adjust = 0; if (!(adapter->ptp_flags & IGB_PTP_ENABLED)) - return IGB_RET_PTP_DISABLED; + return 0; /* The timestamp is recorded in little endian format. * DWORD: 0 1 2 3 @@ -888,10 +886,9 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, /* check reserved dwords are zero, be/le doesn't matter for zero */ if (regval[0]) - return IGB_RET_PTP_INVALID; + return 0; - igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), - le64_to_cpu(regval[1])); + igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1])); /* adjust timestamp for the RX latency based on link speed */ if (adapter->hw.mac.type == e1000_i210) { @@ -907,10 +904,10 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, break; } } - skb_hwtstamps(skb)->hwtstamp = - ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); - return 0; + *timestamp = ktime_sub_ns(ts.hwtstamp, adjust); + + return IGB_TS_HDR_LEN; } /** From f6c10b48f8c8da44adaff730d8e700b6272add2b Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 10 May 2021 11:38:49 +0200 Subject: [PATCH 2/8] i40e: add correct exception tracing for XDP Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared. Fixes: 74608d17fe29 ("i40e: add support for XDP_TX action") Fixes: 0a714186d3c0 ("i40e: add AF_XDP zero-copy Rx support") Reported-by: Jesper Dangaard Brouer Signed-off-by: Magnus Karlsson Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 7 ++++++- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 8 ++++++-- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index de70c16ef619..b883ab809df3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2313,15 +2313,20 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp) case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); + if (result == I40E_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; + if (err) + goto out_failure; + result = I40E_XDP_REDIR; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 46d884417c63..68f177a86403 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -162,9 +162,10 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; + if (err) + goto out_failure; rcu_read_unlock(); - return result; + return I40E_XDP_REDIR; } switch (act) { @@ -173,11 +174,14 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); + if (result == I40E_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: From 89d65df024c59988291f643b4e45d1528c51aef9 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 10 May 2021 11:38:50 +0200 Subject: [PATCH 3/8] ice: add correct exception tracing for XDP Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared. Fixes: efc2214b6047 ("ice: Add support for XDP") Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reported-by: Jesper Dangaard Brouer Signed-off-by: Magnus Karlsson Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_txrx.c | 12 +++++++++--- drivers/net/ethernet/intel/ice/ice_xsk.c | 8 ++++++-- 2 files changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index e2b4b29ea207..93e5d9ebfd74 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -523,7 +523,7 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct ice_ring *xdp_ring; - int err; + int err, result; u32 act; act = bpf_prog_run_xdp(xdp_prog, xdp); @@ -532,14 +532,20 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, return ICE_XDP_PASS; case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[smp_processor_id()]; - return ice_xmit_xdp_buff(xdp, xdp_ring); + result = ice_xmit_xdp_buff(xdp, xdp_ring); + if (result == ICE_XDP_CONSUMED) + goto out_failure; + return result; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - return !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED; + if (err) + goto out_failure; + return ICE_XDP_REDIR; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index faa7b8d96adb..7228e4d427bc 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -473,9 +473,10 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED; + if (err) + goto out_failure; rcu_read_unlock(); - return result; + return ICE_XDP_REDIR; } switch (act) { @@ -484,11 +485,14 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index]; result = ice_xmit_xdp_buff(xdp, xdp_ring); + if (result == ICE_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: From 8281356b1cab1cccc71412eb4cf28b99d6bb2c19 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 10 May 2021 11:38:51 +0200 Subject: [PATCH 4/8] ixgbe: add correct exception tracing for XDP Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared. Fixes: 33fdc82f0883 ("ixgbe: add support for XDP_TX action") Fixes: d0bcacd0a130 ("ixgbe: add AF_XDP zero-copy Rx support") Reported-by: Jesper Dangaard Brouer Signed-off-by: Magnus Karlsson Tested-by: Vishakha Jambekar Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 16 ++++++++-------- drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 14 ++++++++------ 2 files changed, 16 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index c5ec17d19c59..2ac5b82676f3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2213,23 +2213,23 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, break; case XDP_TX: xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) { - result = IXGBE_XDP_CONSUMED; - break; - } + if (unlikely(!xdpf)) + goto out_failure; result = ixgbe_xmit_xdp_ring(adapter, xdpf); + if (result == IXGBE_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); - if (!err) - result = IXGBE_XDP_REDIR; - else - result = IXGBE_XDP_CONSUMED; + if (err) + goto out_failure; + result = IXGBE_XDP_REDIR; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 91ad5b902673..f72d2978263b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -106,9 +106,10 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED; + if (err) + goto out_failure; rcu_read_unlock(); - return result; + return IXGBE_XDP_REDIR; } switch (act) { @@ -116,16 +117,17 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, break; case XDP_TX: xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) { - result = IXGBE_XDP_CONSUMED; - break; - } + if (unlikely(!xdpf)) + goto out_failure; result = ixgbe_xmit_xdp_ring(adapter, xdpf); + if (result == IXGBE_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: From 74431c40b9c5fa673fff83ec157a76a69efd5c72 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 10 May 2021 11:38:52 +0200 Subject: [PATCH 5/8] igb: add correct exception tracing for XDP Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared. Fixes: 9cbc948b5a20 ("igb: add XDP support") Reported-by: Jesper Dangaard Brouer Signed-off-by: Magnus Karlsson Tested-by: Vishakha Jambekar Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 0123285029fa..b2a042f825ff 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8394,18 +8394,20 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, break; case XDP_TX: result = igb_xdp_xmit_back(adapter, xdp); + if (result == IGB_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); - if (!err) - result = IGB_XDP_REDIR; - else - result = IGB_XDP_CONSUMED; + if (err) + goto out_failure; + result = IGB_XDP_REDIR; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: From faae81420d162551b6ef2d804aafc00f4cd68e0e Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 10 May 2021 11:38:53 +0200 Subject: [PATCH 6/8] ixgbevf: add correct exception tracing for XDP Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared. Fixes: 21092e9ce8b1 ("ixgbevf: Add support for XDP_TX action") Reported-by: Jesper Dangaard Brouer Signed-off-by: Magnus Karlsson Tested-by: Vishakha Jambekar Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index ba2ed8a43d2d..0e733cc15c58 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1067,11 +1067,14 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, case XDP_TX: xdp_ring = adapter->xdp_ring[rx_ring->queue_index]; result = ixgbevf_xmit_xdp_ring(xdp_ring, xdp); + if (result == IXGBEVF_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: From 45ce08594ec3a9f81a6dedeccd1ec785e6907405 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 10 May 2021 11:38:54 +0200 Subject: [PATCH 7/8] igc: add correct exception tracing for XDP Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared. Fixes: 73f1071c1d29 ("igc: Add support for XDP_TX action") Fixes: 4ff320361092 ("igc: Add support for XDP_REDIRECT action") Reported-by: Jesper Dangaard Brouer Signed-off-by: Magnus Karlsson Tested-by: Dvora Fuxbrumer Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_main.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 069471b7ffb0..f1adf154ec4a 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2047,20 +2047,19 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, break; case XDP_TX: if (igc_xdp_xmit_back(adapter, xdp) < 0) - res = IGC_XDP_CONSUMED; - else - res = IGC_XDP_TX; + goto out_failure; + res = IGC_XDP_TX; break; case XDP_REDIRECT: if (xdp_do_redirect(adapter->netdev, xdp, prog) < 0) - res = IGC_XDP_CONSUMED; - else - res = IGC_XDP_REDIRECT; + goto out_failure; + res = IGC_XDP_REDIRECT; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(adapter->netdev, prog, act); fallthrough; case XDP_DROP: From e102db780e1c14f10c70dafa7684af22a745b51d Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Tue, 27 Apr 2021 21:52:09 +0200 Subject: [PATCH 8/8] ice: track AF_XDP ZC enabled queues in bitmap Commit c7a219048e45 ("ice: Remove xsk_buff_pool from VSI structure") silently introduced a regression and broke the Tx side of AF_XDP in copy mode. xsk_pool on ice_ring is set only based on the existence of the XDP prog on the VSI which in turn picks ice_clean_tx_irq_zc to be executed. That is not something that should happen for copy mode as it should use the regular data path ice_clean_tx_irq. This results in a following splat when xdpsock is run in txonly or l2fwd scenarios in copy mode: [ 106.050195] BUG: kernel NULL pointer dereference, address: 0000000000000030 [ 106.057269] #PF: supervisor read access in kernel mode [ 106.062493] #PF: error_code(0x0000) - not-present page [ 106.067709] PGD 0 P4D 0 [ 106.070293] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 106.074721] CPU: 61 PID: 0 Comm: swapper/61 Not tainted 5.12.0-rc2+ #45 [ 106.081436] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [ 106.092027] RIP: 0010:xp_raw_get_dma+0x36/0x50 [ 106.096551] Code: 74 14 48 b8 ff ff ff ff ff ff 00 00 48 21 f0 48 c1 ee 30 48 01 c6 48 8b 87 90 00 00 00 48 89 f2 81 e6 ff 0f 00 00 48 c1 ea 0c <48> 8b 04 d0 48 83 e0 fe 48 01 f0 c3 66 66 2e 0f 1f 84 00 00 00 00 [ 106.115588] RSP: 0018:ffffc9000d694e50 EFLAGS: 00010206 [ 106.120893] RAX: 0000000000000000 RBX: ffff88984b8c8a00 RCX: ffff889852581800 [ 106.128137] RDX: 0000000000000006 RSI: 0000000000000000 RDI: ffff88984cd8b800 [ 106.135383] RBP: ffff888123b50001 R08: ffff889896800000 R09: 0000000000000800 [ 106.142628] R10: 0000000000000000 R11: ffffffff826060c0 R12: 00000000000000ff [ 106.149872] R13: 0000000000000000 R14: 0000000000000040 R15: ffff888123b50018 [ 106.157117] FS: 0000000000000000(0000) GS:ffff8897e0f40000(0000) knlGS:0000000000000000 [ 106.165332] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 106.171163] CR2: 0000000000000030 CR3: 000000000560a004 CR4: 00000000007706e0 [ 106.178408] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 106.185653] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 106.192898] PKRU: 55555554 [ 106.195653] Call Trace: [ 106.198143] [ 106.200196] ice_clean_tx_irq_zc+0x183/0x2a0 [ice] [ 106.205087] ice_napi_poll+0x3e/0x590 [ice] [ 106.209356] __napi_poll+0x2a/0x160 [ 106.212911] net_rx_action+0xd6/0x200 [ 106.216634] __do_softirq+0xbf/0x29b [ 106.220274] irq_exit_rcu+0x88/0xc0 [ 106.223819] common_interrupt+0x7b/0xa0 [ 106.227719] [ 106.229857] asm_common_interrupt+0x1e/0x40 Fix this by introducing the bitmap of queues that are zero-copy enabled, where each bit, corresponding to a queue id that xsk pool is being configured on, will be set/cleared within ice_xsk_pool_{en,dis}able and checked within ice_xsk_pool(). The latter is a function used for deciding which napi poll routine is executed. Idea is being taken from our other drivers such as i40e and ixgbe. Fixes: c7a219048e45 ("ice: Remove xsk_buff_pool from VSI structure") Signed-off-by: Maciej Fijalkowski Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice.h | 8 +++++--- drivers/net/ethernet/intel/ice/ice_lib.c | 10 ++++++++++ drivers/net/ethernet/intel/ice/ice_xsk.c | 3 +++ 3 files changed, 18 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index e35db3ff583b..2924c67567b8 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -335,6 +335,7 @@ struct ice_vsi { struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; struct ice_ring **xdp_rings; /* XDP ring array */ + unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ @@ -547,15 +548,16 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring) */ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring) { + struct ice_vsi *vsi = ring->vsi; u16 qid = ring->q_index; if (ice_ring_is_xdp(ring)) - qid -= ring->vsi->num_xdp_txq; + qid -= vsi->num_xdp_txq; - if (!ice_is_xdp_ena_vsi(ring->vsi)) + if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) return NULL; - return xsk_get_pool_from_qid(ring->vsi->netdev, qid); + return xsk_get_pool_from_qid(vsi->netdev, qid); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 82e2ce23df3d..7f7653906fce 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -105,8 +105,14 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->q_vectors) goto err_vectors; + vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL); + if (!vsi->af_xdp_zc_qps) + goto err_zc_qps; + return 0; +err_zc_qps: + devm_kfree(dev, vsi->q_vectors); err_vectors: devm_kfree(dev, vsi->rxq_map); err_rxq_map: @@ -288,6 +294,10 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); + if (vsi->af_xdp_zc_qps) { + bitmap_free(vsi->af_xdp_zc_qps); + vsi->af_xdp_zc_qps = NULL; + } /* free the ring and vector containers */ if (vsi->q_vectors) { devm_kfree(dev, vsi->q_vectors); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 7228e4d427bc..a1f89ea3c2bd 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -270,6 +270,7 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid) if (!pool) return -EINVAL; + clear_bit(qid, vsi->af_xdp_zc_qps); xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR); return 0; @@ -300,6 +301,8 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) if (err) return err; + set_bit(qid, vsi->af_xdp_zc_qps); + return 0; }