summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-06-04 02:27:18 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-06-04 02:27:18 +0300
commitcb8e59cc87201af93dfbb6c3dccc8fcad72a09c2 (patch)
treea334db9022f89654b777bbce8c4c6632e65b9031 /drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
parent2e63f6ce7ed2c4ff83ba30ad9ccad422289a6c63 (diff)
parent065fcfd49763ec71ae345bb5c5a74f961031e70e (diff)
downloadlinux-cb8e59cc87201af93dfbb6c3dccc8fcad72a09c2.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller: 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz Augusto von Dentz. 2) Add GSO partial support to igc, from Sasha Neftin. 3) Several cleanups and improvements to r8169 from Heiner Kallweit. 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a device self-test. From Andrew Lunn. 5) Start moving away from custom driver versions, use the globally defined kernel version instead, from Leon Romanovsky. 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin. 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet. 8) Add sriov and vf support to hinic, from Luo bin. 9) Support Media Redundancy Protocol (MRP) in the bridging code, from Horatiu Vultur. 10) Support netmap in the nft_nat code, from Pablo Neira Ayuso. 11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina Dubroca. Also add ipv6 support for espintcp. 12) Lots of ReST conversions of the networking documentation, from Mauro Carvalho Chehab. 13) Support configuration of ethtool rxnfc flows in bcmgenet driver, from Doug Berger. 14) Allow to dump cgroup id and filter by it in inet_diag code, from Dmitry Yakunin. 15) Add infrastructure to export netlink attribute policies to userspace, from Johannes Berg. 16) Several optimizations to sch_fq scheduler, from Eric Dumazet. 17) Fallback to the default qdisc if qdisc init fails because otherwise a packet scheduler init failure will make a device inoperative. From Jesper Dangaard Brouer. 18) Several RISCV bpf jit optimizations, from Luke Nelson. 19) Correct the return type of the ->ndo_start_xmit() method in several drivers, it's netdev_tx_t but many drivers were using 'int'. From Yunjian Wang. 20) Add an ethtool interface for PHY master/slave config, from Oleksij Rempel. 21) Add BPF iterators, from Yonghang Song. 22) Add cable test infrastructure, including ethool interfaces, from Andrew Lunn. Marvell PHY driver is the first to support this facility. 23) Remove zero-length arrays all over, from Gustavo A. R. Silva. 24) Calculate and maintain an explicit frame size in XDP, from Jesper Dangaard Brouer. 25) Add CAP_BPF, from Alexei Starovoitov. 26) Support terse dumps in the packet scheduler, from Vlad Buslov. 27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei. 28) Add devm_register_netdev(), from Bartosz Golaszewski. 29) Minimize qdisc resets, from Cong Wang. 30) Get rid of kernel_getsockopt and kernel_setsockopt in order to eliminate set_fs/get_fs calls. From Christoph Hellwig. * git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits) selftests: net: ip_defrag: ignore EPERM net_failover: fixed rollback in net_failover_open() Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv" Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv" vmxnet3: allow rx flow hash ops only when rss is enabled hinic: add set_channels ethtool_ops support selftests/bpf: Add a default $(CXX) value tools/bpf: Don't use $(COMPILE.c) bpf, selftests: Use bpf_probe_read_kernel s390/bpf: Use bcr 0,%0 as tail call nop filler s390/bpf: Maintain 8-byte stack alignment selftests/bpf: Fix verifier test selftests/bpf: Fix sample_cnt shared between two threads bpf, selftests: Adapt cls_redirect to call csum_level helper bpf: Add csum_level helper for fixing up csum levels bpf: Fix up bpf_skb_adjust_room helper's skb csum setting sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf() crypto/chtls: IPv6 support for inline TLS Crypto/chcr: Fixes a coccinile check error Crypto/chcr: Fixes compilations warnings ...
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c')
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c113
1 files changed, 21 insertions, 92 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index 62fc8a128a8d..a33a1f762c70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -3,71 +3,10 @@
#include "rx.h"
#include "en/xdp.h"
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
/* RX data path */
-bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count)
-{
- /* Check in advance that we have enough frames, instead of allocating
- * one-by-one, failing and moving frames to the Reuse Ring.
- */
- return xsk_umem_has_addrs_rq(rq->umem, count);
-}
-
-int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
- struct mlx5e_dma_info *dma_info)
-{
- struct xdp_umem *umem = rq->umem;
- u64 handle;
-
- if (!xsk_umem_peek_addr_rq(umem, &handle))
- return -ENOMEM;
-
- dma_info->xsk.handle = xsk_umem_adjust_offset(umem, handle,
- rq->buff.umem_headroom);
- dma_info->xsk.data = xdp_umem_get_data(umem, dma_info->xsk.handle);
-
- /* No need to add headroom to the DMA address. In striding RQ case, we
- * just provide pages for UMR, and headroom is counted at the setup
- * stage when creating a WQE. In non-striding RQ case, headroom is
- * accounted in mlx5e_alloc_rx_wqe.
- */
- dma_info->addr = xdp_umem_get_dma(umem, handle);
-
- xsk_umem_release_addr_rq(umem);
-
- dma_sync_single_for_device(rq->pdev, dma_info->addr, PAGE_SIZE,
- DMA_BIDIRECTIONAL);
-
- return 0;
-}
-
-static inline void mlx5e_xsk_recycle_frame(struct mlx5e_rq *rq, u64 handle)
-{
- xsk_umem_fq_reuse(rq->umem, handle & rq->umem->chunk_mask);
-}
-
-/* XSKRQ uses pages from UMEM, they must not be released. They are returned to
- * the userspace if possible, and if not, this function is called to reuse them
- * in the driver.
- */
-void mlx5e_xsk_page_release(struct mlx5e_rq *rq,
- struct mlx5e_dma_info *dma_info)
-{
- mlx5e_xsk_recycle_frame(rq, dma_info->xsk.handle);
-}
-
-/* Return a frame back to the hardware to fill in again. It is used by XDP when
- * the XDP program returns XDP_TX or XDP_REDIRECT not to an XSKMAP.
- */
-void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle)
-{
- struct mlx5e_rq *rq = container_of(zca, struct mlx5e_rq, zca);
-
- mlx5e_xsk_recycle_frame(rq, handle);
-}
-
static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, void *data,
u32 cqe_bcnt)
{
@@ -90,11 +29,8 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
u32 head_offset,
u32 page_idx)
{
- struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
- u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom;
+ struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk;
u32 cqe_bcnt32 = cqe_bcnt;
- void *va, *data;
- u32 frag_size;
bool consumed;
/* Check packet size. Note LRO doesn't use linear SKB */
@@ -103,22 +39,20 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
return NULL;
}
- /* head_offset is not used in this function, because di->xsk.data and
- * di->addr point directly to the necessary place. Furthermore, in the
- * current implementation, UMR pages are mapped to XSK frames, so
+ /* head_offset is not used in this function, because xdp->data and the
+ * DMA address point directly to the necessary place. Furthermore, in
+ * the current implementation, UMR pages are mapped to XSK frames, so
* head_offset should always be 0.
*/
WARN_ON_ONCE(head_offset);
- va = di->xsk.data;
- data = va + rx_headroom;
- frag_size = rq->buff.headroom + cqe_bcnt32;
-
- dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL);
- prefetch(data);
+ xdp->data_end = xdp->data + cqe_bcnt32;
+ xdp_set_data_meta_invalid(xdp);
+ xsk_buff_dma_sync_for_cpu(xdp);
+ prefetch(xdp->data);
rcu_read_lock();
- consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, true);
+ consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp);
rcu_read_unlock();
/* Possible flows:
@@ -145,7 +79,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
/* XDP_PASS: copy the data from the UMEM to a new SKB and reuse the
* frame. On SKB allocation failure, NULL is returned.
*/
- return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt32);
+ return mlx5e_xsk_construct_skb(rq, xdp->data, cqe_bcnt32);
}
struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
@@ -153,25 +87,20 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
struct mlx5e_wqe_frag_info *wi,
u32 cqe_bcnt)
{
- struct mlx5e_dma_info *di = wi->di;
- u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom;
- void *va, *data;
+ struct xdp_buff *xdp = wi->di->xsk;
bool consumed;
- u32 frag_size;
- /* wi->offset is not used in this function, because di->xsk.data and
- * di->addr point directly to the necessary place. Furthermore, in the
- * current implementation, one page = one packet = one frame, so
+ /* wi->offset is not used in this function, because xdp->data and the
+ * DMA address point directly to the necessary place. Furthermore, the
+ * XSK allocator allocates frames per packet, instead of pages, so
* wi->offset should always be 0.
*/
WARN_ON_ONCE(wi->offset);
- va = di->xsk.data;
- data = va + rx_headroom;
- frag_size = rq->buff.headroom + cqe_bcnt;
-
- dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL);
- prefetch(data);
+ xdp->data_end = xdp->data + cqe_bcnt;
+ xdp_set_data_meta_invalid(xdp);
+ xsk_buff_dma_sync_for_cpu(xdp);
+ prefetch(xdp->data);
if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
rq->stats->wqe_err++;
@@ -179,7 +108,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
}
rcu_read_lock();
- consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, true);
+ consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp);
rcu_read_unlock();
if (likely(consumed))
@@ -189,5 +118,5 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
* will be handled by mlx5e_put_rx_frag.
* On SKB allocation failure, NULL is returned.
*/
- return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt);
+ return mlx5e_xsk_construct_skb(rq, xdp->data, cqe_bcnt);
}