summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/intel/i40e/i40e_xsk.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-12-15 13:22:29 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2020-12-15 13:22:29 -0800
commitd635a69dd4981cc51f90293f5f64268620ed1565 (patch)
tree5e0a758b402ea7d624c25c3a343545dd29e80f31 /drivers/net/ethernet/intel/i40e/i40e_xsk.c
parentac73e3dc8acd0a3be292755db30388c3580f5674 (diff)
parentefd5a1584537698220578227e6467638307c2a0b (diff)
downloadlinux-d635a69dd4981cc51f90293f5f64268620ed1565.tar.bz2
Merge tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - support "prefer busy polling" NAPI operation mode, where we defer softirq for some time expecting applications to periodically busy poll - AF_XDP: improve efficiency by more batching and hindering the adjacency cache prefetcher - af_packet: make packet_fanout.arr size configurable up to 64K - tcp: optimize TCP zero copy receive in presence of partial or unaligned reads making zero copy a performance win for much smaller messages - XDP: add bulk APIs for returning / freeing frames - sched: support fragmenting IP packets as they come out of conntrack - net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs BPF: - BPF switch from crude rlimit-based to memcg-based memory accounting - BPF type format information for kernel modules and related tracing enhancements - BPF implement task local storage for BPF LSM - allow the FENTRY/FEXIT/RAW_TP tracing programs to use bpf_sk_storage Protocols: - mptcp: improve multiple xmit streams support, memory accounting and many smaller improvements - TLS: support CHACHA20-POLY1305 cipher - seg6: add support for SRv6 End.DT4/DT6 behavior - sctp: Implement RFC 6951: UDP Encapsulation of SCTP - ppp_generic: add ability to bridge channels directly - bridge: Connectivity Fault Management (CFM) support as is defined in IEEE 802.1Q section 12.14. Drivers: - mlx5: make use of the new auxiliary bus to organize the driver internals - mlx5: more accurate port TX timestamping support - mlxsw: - improve the efficiency of offloaded next hop updates by using the new nexthop object API - support blackhole nexthops - support IEEE 802.1ad (Q-in-Q) bridging - rtw88: major bluetooth co-existance improvements - iwlwifi: support new 6 GHz frequency band - ath11k: Fast Initial Link Setup (FILS) - mt7915: dual band concurrent (DBDC) support - net: ipa: add basic support for IPA v4.5 Refactor: - a few pieces of in_interrupt() cleanup work from Sebastian Andrzej Siewior - phy: add support for shared interrupts; get rid of multiple driver APIs and have the drivers write a full IRQ handler, slight growth of driver code should be compensated by the simpler API which also allows shared IRQs - add common code for handling netdev per-cpu counters - move TX packet re-allocation from Ethernet switch tag drivers to a central place - improve efficiency and rename nla_strlcpy - number of W=1 warning cleanups as we now catch those in a patchwork build bot Old code removal: - wan: delete the DLCI / SDLA drivers - wimax: move to staging - wifi: remove old WDS wifi bridging support" * tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1922 commits) net: hns3: fix expression that is currently always true net: fix proc_fs init handling in af_packet and tls nfc: pn533: convert comma to semicolon af_vsock: Assign the vsock transport considering the vsock address flags af_vsock: Set VMADDR_FLAG_TO_HOST flag on the receive path vsock_addr: Check for supported flag values vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag vm_sockets: Add flags field in the vsock address data structure net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit net: mscc: ocelot: install MAC addresses in .ndo_set_rx_mode from process context nfc: s3fwrn5: Release the nfc firmware net: vxget: clean up sparse warnings mlxsw: spectrum_router: Use eXtended mezzanine to offload IPv4 router mlxsw: spectrum: Set KVH XLT cache mode for Spectrum2/3 mlxsw: spectrum_router_xm: Introduce basic XM cache flushing mlxsw: reg: Add Router LPM Cache Enable Register mlxsw: reg: Add Router LPM Cache ML Delete Register mlxsw: spectrum_router_xm: Implement L-value tracking for M-index mlxsw: reg: Add XM Router M Table Register ...
Diffstat (limited to 'drivers/net/ethernet/intel/i40e/i40e_xsk.c')
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_xsk.c124
1 files changed, 84 insertions, 40 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 567fd67e900e..bfa84bfb0488 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -2,6 +2,7 @@
/* Copyright(c) 2018 Intel Corporation. */
#include <linux/bpf_trace.h>
+#include <linux/stringify.h>
#include <net/xdp_sock_drv.h>
#include <net/xdp.h>
@@ -311,7 +312,6 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
continue;
}
- bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
if (!size)
@@ -381,58 +381,102 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
return failure ? budget : (int)total_rx_packets;
}
-/**
- * i40e_xmit_zc - Performs zero-copy Tx AF_XDP
- * @xdp_ring: XDP Tx ring
- * @budget: NAPI budget
- *
- * Returns true if the work is finished.
- **/
-static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
+static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc,
+ unsigned int *total_bytes)
{
- unsigned int sent_frames = 0, total_bytes = 0;
- struct i40e_tx_desc *tx_desc = NULL;
- struct i40e_tx_buffer *tx_bi;
- struct xdp_desc desc;
+ struct i40e_tx_desc *tx_desc;
dma_addr_t dma;
- while (budget-- > 0) {
- if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc))
- break;
+ dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
+ xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
- dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr);
- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma,
- desc.len);
+ tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
+ tx_desc->buffer_addr = cpu_to_le64(dma);
+ tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC | I40E_TX_DESC_CMD_EOP,
+ 0, desc->len, 0);
- tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
- tx_bi->bytecount = desc.len;
+ *total_bytes += desc->len;
+}
- tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use);
- tx_desc->buffer_addr = cpu_to_le64(dma);
- tx_desc->cmd_type_offset_bsz =
- build_ctob(I40E_TX_DESC_CMD_ICRC
- | I40E_TX_DESC_CMD_EOP,
- 0, desc.len, 0);
+static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *desc,
+ unsigned int *total_bytes)
+{
+ u16 ntu = xdp_ring->next_to_use;
+ struct i40e_tx_desc *tx_desc;
+ dma_addr_t dma;
+ u32 i;
- sent_frames++;
- total_bytes += tx_bi->bytecount;
+ loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+ dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr);
+ xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc[i].len);
- xdp_ring->next_to_use++;
- if (xdp_ring->next_to_use == xdp_ring->count)
- xdp_ring->next_to_use = 0;
+ tx_desc = I40E_TX_DESC(xdp_ring, ntu++);
+ tx_desc->buffer_addr = cpu_to_le64(dma);
+ tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC |
+ I40E_TX_DESC_CMD_EOP,
+ 0, desc[i].len, 0);
+
+ *total_bytes += desc[i].len;
}
- if (tx_desc) {
- /* Request an interrupt for the last frame and bump tail ptr. */
- tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS <<
- I40E_TXD_QW1_CMD_SHIFT);
- i40e_xdp_ring_update_tail(xdp_ring);
+ xdp_ring->next_to_use = ntu;
+}
- xsk_tx_release(xdp_ring->xsk_pool);
- i40e_update_tx_stats(xdp_ring, sent_frames, total_bytes);
+static void i40e_fill_tx_hw_ring(struct i40e_ring *xdp_ring, struct xdp_desc *descs, u32 nb_pkts,
+ unsigned int *total_bytes)
+{
+ u32 batched, leftover, i;
+
+ batched = nb_pkts & ~(PKTS_PER_BATCH - 1);
+ leftover = nb_pkts & (PKTS_PER_BATCH - 1);
+ for (i = 0; i < batched; i += PKTS_PER_BATCH)
+ i40e_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+ for (i = batched; i < batched + leftover; i++)
+ i40e_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+}
+
+static void i40e_set_rs_bit(struct i40e_ring *xdp_ring)
+{
+ u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1;
+ struct i40e_tx_desc *tx_desc;
+
+ tx_desc = I40E_TX_DESC(xdp_ring, ntu);
+ tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS << I40E_TXD_QW1_CMD_SHIFT);
+}
+
+/**
+ * i40e_xmit_zc - Performs zero-copy Tx AF_XDP
+ * @xdp_ring: XDP Tx ring
+ * @budget: NAPI budget
+ *
+ * Returns true if the work is finished.
+ **/
+static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
+{
+ struct xdp_desc *descs = xdp_ring->xsk_descs;
+ u32 nb_pkts, nb_processed = 0;
+ unsigned int total_bytes = 0;
+
+ nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, descs, budget);
+ if (!nb_pkts)
+ return false;
+
+ if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
+ nb_processed = xdp_ring->count - xdp_ring->next_to_use;
+ i40e_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+ xdp_ring->next_to_use = 0;
}
- return !!budget;
+ i40e_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
+ &total_bytes);
+
+ /* Request an interrupt for the last frame and bump tail ptr. */
+ i40e_set_rs_bit(xdp_ring);
+ i40e_xdp_ring_update_tail(xdp_ring);
+
+ i40e_update_tx_stats(xdp_ring, nb_pkts, total_bytes);
+
+ return true;
}
/**