diff options
| -rw-r--r-- | MAINTAINERS | 2 | ||||
| -rw-r--r-- | drivers/infiniband/core/cache.c | 10 | ||||
| -rw-r--r-- | drivers/infiniband/core/device.c | 10 | ||||
| -rw-r--r-- | drivers/infiniband/hw/efa/efa_verbs.c | 118 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe.h | 22 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_comp.c | 4 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_icrc.c | 124 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_loc.h | 61 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_mr.c | 23 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_net.c | 59 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_recv.c | 23 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_req.c | 13 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_resp.c | 33 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_verbs.c | 11 | ||||
| -rw-r--r-- | drivers/infiniband/sw/siw/siw_qp_tx.c | 44 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/rtrs/rtrs-clt.c | 11 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/rtrs/rtrs-clt.h | 1 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/rtrs/rtrs-pri.h | 6 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/rtrs/rtrs-srv.c | 19 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/rtrs/rtrs-srv.h | 2 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/rtrs/rtrs.c | 23 |
21 files changed, 346 insertions, 273 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index a61f4f3b78a9..5b772ea29b0c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8394,7 +8394,7 @@ F: drivers/crypto/hisilicon/sgl.c F: drivers/crypto/hisilicon/zip/ HISILICON ROCE DRIVER -M: Lijun Ou <[email protected]> +M: Wenpeng Liang <[email protected]> M: Weihang Li <[email protected]> S: Maintained diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index c9e9fc81447e..0c98dd3dee67 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -1429,7 +1429,7 @@ int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr, EXPORT_SYMBOL(rdma_read_gid_l2_fields); static int config_non_roce_gid_cache(struct ib_device *device, - u32 port, int gid_tbl_len) + u32 port, struct ib_port_attr *tprops) { struct ib_gid_attr gid_attr = {}; struct ib_gid_table *table; @@ -1441,7 +1441,7 @@ static int config_non_roce_gid_cache(struct ib_device *device, table = rdma_gid_table(device, port); mutex_lock(&table->lock); - for (i = 0; i < gid_tbl_len; ++i) { + for (i = 0; i < tprops->gid_tbl_len; ++i) { if (!device->ops.query_gid) continue; ret = device->ops.query_gid(device, port, i, &gid_attr.gid); @@ -1452,6 +1452,8 @@ static int config_non_roce_gid_cache(struct ib_device *device, goto err; } gid_attr.index = i; + tprops->subnet_prefix = + be64_to_cpu(gid_attr.gid.global.subnet_prefix); add_modify_gid(table, &gid_attr); } err: @@ -1484,7 +1486,7 @@ ib_cache_update(struct ib_device *device, u32 port, bool update_gids, if (!rdma_protocol_roce(device, port) && update_gids) { ret = config_non_roce_gid_cache(device, port, - tprops->gid_tbl_len); + tprops); if (ret) goto err; } @@ -1619,8 +1621,6 @@ int ib_cache_setup_one(struct ib_device *device) u32 p; int err; - rwlock_init(&device->cache_lock); - err = gid_table_setup_one(device); if (err) return err; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index fa20b1824fb8..9056f48bdca6 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -607,6 +607,8 @@ struct ib_device *_ib_alloc_device(size_t size) for (i = 0; i < ARRAY_SIZE(device->cq_pools); i++) INIT_LIST_HEAD(&device->cq_pools[i]); + rwlock_init(&device->cache_lock); + device->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_ALLOC_MW) | BIT_ULL(IB_USER_VERBS_CMD_ALLOC_PD) | @@ -2050,7 +2052,6 @@ static int __ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { - union ib_gid gid = {}; int err; memset(port_attr, 0, sizeof(*port_attr)); @@ -2063,11 +2064,8 @@ static int __ib_query_port(struct ib_device *device, IB_LINK_LAYER_INFINIBAND) return 0; - err = device->ops.query_gid(device, port_num, 0, &gid); - if (err) - return err; - - port_attr->subnet_prefix = be64_to_cpu(gid.global.subnet_prefix); + ib_get_cached_subnet_prefix(device, port_num, + &port_attr->subnet_prefix); return 0; } diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index be6d3ff0f1be..b4cfb656ddd5 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* - * Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved. */ #include <linux/vmalloc.h> @@ -30,7 +30,21 @@ struct efa_user_mmap_entry { u8 mmap_flag; }; -#define EFA_DEFINE_STATS(op) \ +#define EFA_DEFINE_DEVICE_STATS(op) \ + op(EFA_SUBMITTED_CMDS, "submitted_cmds") \ + op(EFA_COMPLETED_CMDS, "completed_cmds") \ + op(EFA_CMDS_ERR, "cmds_err") \ + op(EFA_NO_COMPLETION_CMDS, "no_completion_cmds") \ + op(EFA_KEEP_ALIVE_RCVD, "keep_alive_rcvd") \ + op(EFA_ALLOC_PD_ERR, "alloc_pd_err") \ + op(EFA_CREATE_QP_ERR, "create_qp_err") \ + op(EFA_CREATE_CQ_ERR, "create_cq_err") \ + op(EFA_REG_MR_ERR, "reg_mr_err") \ + op(EFA_ALLOC_UCONTEXT_ERR, "alloc_ucontext_err") \ + op(EFA_CREATE_AH_ERR, "create_ah_err") \ + op(EFA_MMAP_ERR, "mmap_err") + +#define EFA_DEFINE_PORT_STATS(op) \ op(EFA_TX_BYTES, "tx_bytes") \ op(EFA_TX_PKTS, "tx_pkts") \ op(EFA_RX_BYTES, "rx_bytes") \ @@ -44,28 +58,24 @@ struct efa_user_mmap_entry { op(EFA_RDMA_READ_BYTES, "rdma_read_bytes") \ op(EFA_RDMA_READ_WR_ERR, "rdma_read_wr_err") \ op(EFA_RDMA_READ_RESP_BYTES, "rdma_read_resp_bytes") \ - op(EFA_SUBMITTED_CMDS, "submitted_cmds") \ - op(EFA_COMPLETED_CMDS, "completed_cmds") \ - op(EFA_CMDS_ERR, "cmds_err") \ - op(EFA_NO_COMPLETION_CMDS, "no_completion_cmds") \ - op(EFA_KEEP_ALIVE_RCVD, "keep_alive_rcvd") \ - op(EFA_ALLOC_PD_ERR, "alloc_pd_err") \ - op(EFA_CREATE_QP_ERR, "create_qp_err") \ - op(EFA_CREATE_CQ_ERR, "create_cq_err") \ - op(EFA_REG_MR_ERR, "reg_mr_err") \ - op(EFA_ALLOC_UCONTEXT_ERR, "alloc_ucontext_err") \ - op(EFA_CREATE_AH_ERR, "create_ah_err") \ - op(EFA_MMAP_ERR, "mmap_err") #define EFA_STATS_ENUM(ename, name) ename, #define EFA_STATS_STR(ename, name) [ename] = name, -enum efa_hw_stats { - EFA_DEFINE_STATS(EFA_STATS_ENUM) +enum efa_hw_device_stats { + EFA_DEFINE_DEVICE_STATS(EFA_STATS_ENUM) +}; + +static const char *const efa_device_stats_names[] = { + EFA_DEFINE_DEVICE_STATS(EFA_STATS_STR) +}; + +enum efa_hw_port_stats { + EFA_DEFINE_PORT_STATS(EFA_STATS_ENUM) }; -static const char *const efa_stats_names[] = { - EFA_DEFINE_STATS(EFA_STATS_STR) +static const char *const efa_port_stats_names[] = { + EFA_DEFINE_PORT_STATS(EFA_STATS_STR) }; #define EFA_CHUNK_PAYLOAD_SHIFT 12 @@ -1904,33 +1914,53 @@ int efa_destroy_ah(struct ib_ah *ibah, u32 flags) return 0; } -struct rdma_hw_stats *efa_alloc_hw_port_stats(struct ib_device *ibdev, u32 port_num) +struct rdma_hw_stats *efa_alloc_hw_port_stats(struct ib_device *ibdev, + u32 port_num) { - return rdma_alloc_hw_stats_struct(efa_stats_names, - ARRAY_SIZE(efa_stats_names), + return rdma_alloc_hw_stats_struct(efa_port_stats_names, + ARRAY_SIZE(efa_port_stats_names), RDMA_HW_STATS_DEFAULT_LIFESPAN); } struct rdma_hw_stats *efa_alloc_hw_device_stats(struct ib_device *ibdev) { - /* - * It is probably a bug that efa reports its port stats as device - * stats - */ - return efa_alloc_hw_port_stats(ibdev, 0); + return rdma_alloc_hw_stats_struct(efa_device_stats_names, + ARRAY_SIZE(efa_device_stats_names), + RDMA_HW_STATS_DEFAULT_LIFESPAN); } -int efa_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, - u32 port_num, int index) +static int efa_fill_device_stats(struct efa_dev *dev, + struct rdma_hw_stats *stats) +{ + struct efa_com_stats_admin *as = &dev->edev.aq.stats; + struct efa_stats *s = &dev->stats; + + stats->value[EFA_SUBMITTED_CMDS] = atomic64_read(&as->submitted_cmd); + stats->value[EFA_COMPLETED_CMDS] = atomic64_read(&as->completed_cmd); + stats->value[EFA_CMDS_ERR] = atomic64_read(&as->cmd_err); + stats->value[EFA_NO_COMPLETION_CMDS] = atomic64_read(&as->no_completion); + + stats->value[EFA_KEEP_ALIVE_RCVD] = atomic64_read(&s->keep_alive_rcvd); + stats->value[EFA_ALLOC_PD_ERR] = atomic64_read(&s->alloc_pd_err); + stats->value[EFA_CREATE_QP_ERR] = atomic64_read(&s->create_qp_err); + stats->value[EFA_CREATE_CQ_ERR] = atomic64_read(&s->create_cq_err); + stats->value[EFA_REG_MR_ERR] = atomic64_read(&s->reg_mr_err); + stats->value[EFA_ALLOC_UCONTEXT_ERR] = + atomic64_read(&s->alloc_ucontext_err); + stats->value[EFA_CREATE_AH_ERR] = atomic64_read(&s->create_ah_err); + stats->value[EFA_MMAP_ERR] = atomic64_read(&s->mmap_err); + + return ARRAY_SIZE(efa_device_stats_names); +} + +static int efa_fill_port_stats(struct efa_dev *dev, struct rdma_hw_stats *stats, + u32 port_num) { struct efa_com_get_stats_params params = {}; union efa_com_get_stats_result result; - struct efa_dev *dev = to_edev(ibdev); struct efa_com_rdma_read_stats *rrs; struct efa_com_messages_stats *ms; struct efa_com_basic_stats *bs; - struct efa_com_stats_admin *as; - struct efa_stats *s; int err; params.scope = EFA_ADMIN_GET_STATS_SCOPE_ALL; @@ -1969,24 +1999,16 @@ int efa_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, stats->value[EFA_RDMA_READ_WR_ERR] = rrs->read_wr_err; stats->value[EFA_RDMA_READ_RESP_BYTES] = rrs->read_resp_bytes; - as = &dev->edev.aq.stats; - stats->value[EFA_SUBMITTED_CMDS] = atomic64_read(&as->submitted_cmd); - stats->value[EFA_COMPLETED_CMDS] = atomic64_read(&as->completed_cmd); - stats->value[EFA_CMDS_ERR] = atomic64_read(&as->cmd_err); - stats->value[EFA_NO_COMPLETION_CMDS] = atomic64_read(&as->no_completion); - - s = &dev->stats; - stats->value[EFA_KEEP_ALIVE_RCVD] = atomic64_read(&s->keep_alive_rcvd); - stats->value[EFA_ALLOC_PD_ERR] = atomic64_read(&s->alloc_pd_err); - stats->value[EFA_CREATE_QP_ERR] = atomic64_read(&s->create_qp_err); - stats->value[EFA_CREATE_CQ_ERR] = atomic64_read(&s->create_cq_err); - stats->value[EFA_REG_MR_ERR] = atomic64_read(&s->reg_mr_err); - stats->value[EFA_ALLOC_UCONTEXT_ERR] = - atomic64_read(&s->alloc_ucontext_err); - stats->value[EFA_CREATE_AH_ERR] = atomic64_read(&s->create_ah_err); - stats->value[EFA_MMAP_ERR] = atomic64_read(&s->mmap_err); + return ARRAY_SIZE(efa_port_stats_names); +} - return ARRAY_SIZE(efa_stats_names); +int efa_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, + u32 port_num, int index) +{ + if (port_num) + return efa_fill_port_stats(to_edev(ibdev), stats, port_num); + else + return efa_fill_device_stats(to_edev(ibdev), stats); } enum rdma_link_layer efa_port_link_layer(struct ib_device *ibdev, diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index 623fd17df02d..1bb3fb618bf5 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -14,7 +14,6 @@ #include <linux/module.h> #include <linux/skbuff.h> -#include <linux/crc32.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> @@ -42,27 +41,6 @@ extern bool rxe_initialized; -static inline u32 rxe_crc32(struct rxe_dev *rxe, - u32 crc, void *next, size_t len) -{ - u32 retval; - int err; - - SHASH_DESC_ON_STACK(shash, rxe->tfm); - - shash->tfm = rxe->tfm; - *(u32 *)shash_desc_ctx(shash) = crc; - err = crypto_shash_update(shash, next, len); - if (unlikely(err)) { - pr_warn_ratelimited("failed crc calculation, err: %d\n", err); - return crc32_le(crc, next, len); - } - - retval = *(u32 *)shash_desc_ctx(shash); - barrier_data(shash_desc_ctx(shash)); - return retval; -} - void rxe_set_mtu(struct rxe_dev *rxe, unsigned int dev_mtu); int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name); diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 58ad9c2644f3..d2d802c776fd 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -349,7 +349,7 @@ static inline enum comp_state do_read(struct rxe_qp *qp, ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &wqe->dma, payload_addr(pkt), - payload_size(pkt), RXE_TO_MR_OBJ, NULL); + payload_size(pkt), RXE_TO_MR_OBJ); if (ret) { wqe->status = IB_WC_LOC_PROT_ERR; return COMPST_ERROR; @@ -371,7 +371,7 @@ static inline enum comp_state do_atomic(struct rxe_qp *qp, ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &wqe->dma, &atomic_orig, - sizeof(u64), RXE_TO_MR_OBJ, NULL); + sizeof(u64), RXE_TO_MR_OBJ); if (ret) { wqe->status = IB_WC_LOC_PROT_ERR; return COMPST_ERROR; diff --git a/drivers/infiniband/sw/rxe/rxe_icrc.c b/drivers/infiniband/sw/rxe/rxe_icrc.c index 66b2aad54bb7..e03af3012590 100644 --- a/drivers/infiniband/sw/rxe/rxe_icrc.c +++ b/drivers/infiniband/sw/rxe/rxe_icrc.c @@ -4,18 +4,79 @@ * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ +#include <linux/crc32.h> + #include "rxe.h" #include "rxe_loc.h" -/* Compute a partial ICRC for all the IB transport headers. */ -u32 rxe_icrc_hdr(struct rxe_pkt_info *pkt, struct sk_buff *skb) +/** + * rxe_icrc_init() - Initialize crypto function for computing crc32 + * @rxe: rdma_rxe device object + * + * Return: 0 on success else an error + */ +int rxe_icrc_init(struct rxe_dev *rxe) +{ + struct crypto_shash *tfm; + + tfm = crypto_alloc_shash("crc32", 0, 0); + if (IS_ERR(tfm)) { + pr_warn("failed to init crc32 algorithm err:%ld\n", + PTR_ERR(tfm)); + return PTR_ERR(tfm); + } + + rxe->tfm = tfm; + + return 0; +} + +/** + * rxe_crc32() - Compute cumulative crc32 for a contiguous segment + * @rxe: rdma_rxe device object + * @crc: starting crc32 value from previous segments + * @next: starting address of current segment + * @len: length of current segment + * + * Return: the cumulative crc32 checksum + */ +static __be32 rxe_crc32(struct rxe_dev *rxe, __be32 crc, void *next, size_t len) +{ + __be32 icrc; + int err; + + SHASH_DESC_ON_STACK(shash, rxe->tfm); + + shash->tfm = rxe->tfm; + *(__be32 *)shash_desc_ctx(shash) = crc; + err = crypto_shash_update(shash, next, len); + if (unlikely(err)) { + pr_warn_ratelimited("failed crc calculation, err: %d\n", err); + return (__force __be32)crc32_le((__force u32)crc, next, len); + } + + icrc = *(__be32 *)shash_desc_ctx(shash); + barrier_data(shash_desc_ctx(shash)); + + return icrc; +} + +/** + * rxe_icrc_hdr() - Compute the partial ICRC for the network and transport + * headers of a packet. + * @skb: packet buffer + * @pkt: packet information + * + * Return: the partial ICRC + */ +static __be32 rxe_icrc_hdr(struct sk_buff *skb, struct rxe_pkt_info *pkt) { unsigned int bth_offset = 0; struct iphdr *ip4h = NULL; struct ipv6hdr *ip6h = NULL; struct udphdr *udph; struct rxe_bth *bth; - int crc; + __be32 crc; int length; int hdr_size = sizeof(struct udphdr) + (skb->protocol == htons(ETH_P_IP) ? @@ -30,7 +91,7 @@ u32 rxe_icrc_hdr(struct rxe_pkt_info *pkt, struct sk_buff *skb) /* This seed is the result of computing a CRC with a seed of * 0xfffffff and 8 bytes of 0xff representing a masked LRH. */ - crc = 0xdebb20e3; + crc = (__force __be32)0xdebb20e3; if (skb->protocol == htons(ETH_P_IP)) { /* IPv4 */ memcpy(pshdr, ip_hdr(skb), hdr_size); @@ -67,3 +128,58 @@ u32 rxe_icrc_hdr(struct rxe_pkt_info *pkt, struct sk_buff *skb) rxe_opcode[pkt->opcode].length - RXE_BTH_BYTES); return crc; } + +/** + * rxe_icrc_check() - Compute ICRC for a packet and compare to the ICRC + * delivered in the packet. + * @skb: packet buffer + * @pkt: packet information + * + * Return: 0 if the values match else an error + */ +int rxe_icrc_check(struct sk_buff *skb, struct rxe_pkt_info *pkt) +{ + __be32 *icrcp; + __be32 pkt_icrc; + __be32 icrc; + + icrcp = (__be32 *)(pkt->hdr + pkt->paylen - RXE_ICRC_SIZE); + pkt_icrc = *icrcp; + + icrc = rxe_icrc_hdr(skb, pkt); + icrc = rxe_crc32(pkt->rxe, icrc, (u8 *)payload_addr(pkt), + payload_size(pkt) + bth_pad(pkt)); + icrc = ~icrc; + + if (unlikely(icrc != pkt_icrc)) { + if (skb->protocol == htons(ETH_P_IPV6)) + pr_warn_ratelimited("bad ICRC from %pI6c\n", + &ipv6_hdr(skb)->saddr); + else if (skb->protocol == htons(ETH_P_IP)) + pr_warn_ratelimited("bad ICRC from %pI4\n", + &ip_hdr(skb)->saddr); + else + pr_warn_ratelimited("bad ICRC from unknown\n"); + + return -EINVAL; + } + + return 0; +} + +/** + * rxe_icrc_generate() - compute ICRC for a packet. + * @skb: packet buffer + * @pkt: packet information + */ +void rxe_icrc_generate(struct sk_buff *skb, struct rxe_pkt_info *pkt) +{ + __be32 *icrcp; + __be32 icrc; + + icrcp = (__be32 *)(pkt->hdr + pkt->paylen - RXE_ICRC_SIZE); + icrc = rxe_icrc_hdr(skb, pkt); + icrc = rxe_crc32(pkt->rxe, icrc, (u8 *)payload_addr(pkt), + payload_size(pkt) + bth_pad(pkt)); + *icrcp = ~icrc; +} diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h index 1ddb20855dee..f0c954575bde 100644 --- a/drivers/infiniband/sw/rxe/rxe_loc.h +++ b/drivers/infiniband/sw/rxe/rxe_loc.h @@ -77,10 +77,9 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, int access, struct rxe_mr *mr); int rxe_mr_init_fast(struct rxe_pd *pd, int max_pages, struct rxe_mr *mr); int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, - enum rxe_mr_copy_dir dir, u32 *crcp); -int copy_data(struct rxe_pd *pd, int access, - struct rxe_dma_info *dma, void *addr, int length, - enum rxe_mr_copy_dir dir, u32 *crcp); + enum rxe_mr_copy_dir dir); +int copy_data(struct rxe_pd *pd, int access, struct rxe_dma_info *dma, + void *addr, int length, enum rxe_mr_copy_dir dir); void *iova_to_vaddr(struct rxe_mr *mr, u64 iova, int length); struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key, enum rxe_mr_lookup_type type); @@ -99,11 +98,11 @@ struct rxe_mw *rxe_lookup_mw(struct rxe_qp *qp, int access, u32 rkey); void rxe_mw_cleanup(struct rxe_pool_entry *arg); /* rxe_net.c */ -void rxe_loopback(struct sk_buff *skb); -int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb); struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av, int paylen, struct rxe_pkt_info *pkt); -int rxe_prepare(struct rxe_pkt_info *pkt, struct sk_buff *skb, u32 *crc); +int rxe_prepare(struct rxe_pkt_info *pkt, struct sk_buff *skb); +int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, + struct sk_buff *skb); const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num); int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid); int rxe_mcast_delete(struct rxe_dev *rxe, union ib_gid *mgid); @@ -193,7 +192,10 @@ int rxe_completer(void *arg); int rxe_requester(void *arg); int rxe_responder(void *arg); -u32 rxe_icrc_hdr(struct rxe_pkt_info *pkt, struct sk_buff *skb); +/* rxe_icrc.c */ +int rxe_icrc_init(struct rxe_dev *rxe); +int rxe_icrc_check(struct sk_buff *skb, struct rxe_pkt_info *pkt); +void rxe_icrc_generate(struct sk_buff *skb, struct rxe_pkt_info *pkt); void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb); @@ -204,47 +206,4 @@ static inline unsigned int wr_opcode_mask(int opcode, struct rxe_qp *qp) return rxe_wr_opcode_info[opcode].mask[qp->ibqp.qp_type]; } -static inline int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, - struct sk_buff *skb) -{ - int err; - int is_request = pkt->mask & RXE_REQ_MASK; - struct rxe_dev *rxe = to_rdev(qp->ibqp.device); - - if ((is_request && (qp->req.state != QP_STATE_READY)) || - (!is_request && (qp->resp.state != QP_STATE_READY))) { - pr_info("Packet dropped. QP is not in ready state\n"); - goto drop; - } - - if (pkt->mask & RXE_LOOPBACK_MASK) { - memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt)); - rxe_loopback(skb); - err = 0; - } else { - err = rxe_send(pkt, skb); - } - - if (err) { - rxe->xmit_errors++; - rxe_counter_inc(rxe, RXE_CNT_SEND_ERR); - return err; - } - - if ((qp_type(qp) != IB_QPT_RC) && - (pkt->mask & RXE_END_MASK)) { - pkt->wqe->state = wqe_state_done; - rxe_run_task(&qp->comp.task, 1); - } - - rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS); - goto done; - -drop: - kfree_skb(skb); - err = 0; -done: - return err; -} - #endif /* RXE_LOC_H */ diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index 6aabcb4de235..1ee5bd8291e5 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -122,7 +122,6 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, goto err1; } - mr->umem = umem; num_buf = ib_umem_num_pages(umem); rxe_mr_init(access, mr); @@ -279,11 +278,10 @@ out: } /* copy data from a range (vaddr, vaddr+length-1) to or from - * a mr object starting at iova. Compute incremental value of - * crc32 if crcp is not zero. caller must hold a reference to mr + * a mr object starting at iova. */ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, - enum rxe_mr_copy_dir dir, u32 *crcp) + enum rxe_mr_copy_dir dir) { int err; int bytes; @@ -293,7 +291,6 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, int m; int i; size_t offset; - u32 crc = crcp ? (*crcp) : 0; if (length == 0) return 0; @@ -307,10 +304,6 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, memcpy(dest, src, length); - if (crcp) - *crcp = rxe_crc32(to_rdev(mr->ibmr.device), *crcp, dest, - length); - return 0; } @@ -341,10 +334,6 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, memcpy(dest, src, bytes); - if (crcp) - crc = rxe_crc32(to_rdev(mr->ibmr.device), crc, dest, - bytes); - length -= bytes; addr += bytes; @@ -359,9 +348,6 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, } } - if (crcp) - *crcp = crc; - return 0; err1: @@ -377,8 +363,7 @@ int copy_data( struct rxe_dma_info *dma, void *addr, int length, - enum rxe_mr_copy_dir dir, - u32 *crcp) + enum rxe_mr_copy_dir dir) { int bytes; struct rxe_sge *sge = &dma->sge[dma->cur_sge]; @@ -439,7 +424,7 @@ int copy_data( if (bytes > 0) { iova = sge->addr + offset; - err = rxe_mr_copy(mr, iova, addr, bytes, dir, crcp); + err = rxe_mr_copy(mr, iova, addr, bytes, dir); if (err) goto err2; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index dec92928a1cd..10c13dfebcbc 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -343,7 +343,7 @@ static int prepare6(struct rxe_pkt_info *pkt, struct sk_buff *skb) return 0; } -int rxe_prepare(struct rxe_pkt_info *pkt, struct sk_buff *skb, u32 *crc) +int rxe_prepare(struct rxe_pkt_info *pkt, struct sk_buff *skb) { int err = 0; @@ -352,8 +352,6 @@ int rxe_prepare(struct rxe_pkt_info *pkt, struct sk_buff *skb, u32 *crc) else if (skb->protocol == htons(ETH_P_IPV6)) err = prepare6(pkt, skb); - *crc = rxe_icrc_hdr(pkt, skb); - if (ether_addr_equal(skb->dev->dev_addr, rxe_get_av(pkt)->dmac)) pkt->mask |= RXE_LOOPBACK_MASK; @@ -373,7 +371,7 @@ static void rxe_skb_tx_dtor(struct sk_buff *skb) rxe_drop_ref(qp); } -int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb) +static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt) { int err; @@ -406,19 +404,64 @@ int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb) /* fix up a send packet to match the packets * received from UDP before looping them back */ -void rxe_loopback(struct sk_buff *skb) +static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt) { - struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); + memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt)); if (skb->protocol == htons(ETH_P_IP)) skb_pull(skb, sizeof(struct iphdr)); else skb_pull(skb, sizeof(struct ipv6hdr)); - if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) + if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) { kfree_skb(skb); + return -EIO; + } + + rxe_rcv(skb); + + return 0; +} + +int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, + struct sk_buff *skb) +{ + int err; + int is_request = pkt->mask & RXE_REQ_MASK; + struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + + if ((is_request && (qp->req.state != QP_STATE_READY)) || + (!is_request && (qp->resp.state != QP_STATE_READY))) { + pr_info("Packet dropped. QP is not in ready state\n"); + goto drop; + } + + rxe_icrc_generate(skb, pkt); + + if (pkt->mask & RXE_LOOPBACK_MASK) + err = rxe_loopback(skb, pkt); else - rxe_rcv(skb); + err = rxe_send(skb, pkt); + if (err) { + rxe->xmit_errors++; + rxe_counter_inc(rxe, RXE_CNT_SEND_ERR); + return err; + } + + if ((qp_type(qp) != IB_QPT_RC) && + (pkt->mask & RXE_END_MASK)) { + pkt->wqe->state = wqe_state_done; + rxe_run_task(&qp->comp.task, 1); + } + + rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS); + goto done; + +drop: + kfree_skb(skb); + err = 0; +done: + return err; } struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av, diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 7a49e27da23a..6a6cc1fa90e4 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -361,8 +361,6 @@ void rxe_rcv(struct sk_buff *skb) int err; struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); struct rxe_dev *rxe = pkt->rxe; - __be32 *icrcp; - u32 calc_icrc, pack_icrc; if (unlikely(skb->len < RXE_BTH_BYTES)) goto drop; @@ -384,26 +382,9 @@ void rxe_rcv(struct sk_buff *skb) if (unlikely(err)) goto drop; - /* Verify ICRC */ - icrcp = (__be32 *)(pkt->hdr + pkt->paylen - RXE_ICRC_SIZE); - pack_icrc = be32_to_cpu(*icrcp); - - calc_icrc = rxe_icrc_hdr(pkt, skb); - calc_icrc = rxe_crc32(rxe, calc_icrc, (u8 *)payload_addr(pkt), - payload_size(pkt) + bth_pad(pkt)); - calc_icrc = (__force u32)cpu_to_be32(~calc_icrc); - if (unlikely(calc_icrc != pack_icrc)) { - if (skb->protocol == htons(ETH_P_IPV6)) - pr_warn_ratelimited("bad ICRC from %pI6c\n", - &ipv6_hdr(skb)->saddr); - else if (skb->protocol == htons(ETH_P_IP)) - pr_warn_ratelimited("bad ICRC from %pI4\n", - &ip_hdr(skb)->saddr); - else - pr_warn_ratelimited("bad ICRC from unknown\n"); - + err = rxe_icrc_check(skb, pkt); + if (unlikely(err)) goto drop; - } rxe_counter_inc(rxe, RXE_CNT_RCVD_PKTS); diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index c57699cc6578..3894197a82f6 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -466,12 +466,9 @@ static int finish_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe, struct rxe_pkt_info *pkt, struct sk_buff *skb, int paylen) { - struct rxe_dev *rxe = to_rdev(qp->ibqp.device); - u32 crc = 0; - u32 *p; int err; - err = rxe_prepare(pkt, skb, &crc); + err = rxe_prepare(pkt, skb); if (err) return err; @@ -479,7 +476,6 @@ static int finish_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe, if (wqe->wr.send_flags & IB_SEND_INLINE) { u8 *tmp = &wqe->dma.inline_data[wqe->dma.sge_offset]; - crc = rxe_crc32(rxe, crc, tmp, paylen); memcpy(payload_addr(pkt), tmp, paylen); wqe->dma.resid -= paylen; @@ -487,8 +483,7 @@ static int finish_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe, } else { err = copy_data(qp->pd, 0, &wqe->dma, payload_addr(pkt), paylen, - RXE_FROM_MR_OBJ, - &crc); + RXE_FROM_MR_OBJ); if (err) return err; } @@ -496,12 +491,8 @@ static int finish_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe, u8 *pad = payload_addr(pkt) + paylen; memset(pad, 0, bth_pad(pkt)); - crc = rxe_crc32(rxe, crc, pad, bth_pad(pkt)); } } - p = payload_addr(pkt) + paylen + bth_pad(pkt); - - *p = ~crc; return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 3743dc39b60c..685b8aebd627 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -536,7 +536,7 @@ static enum resp_states send_data_in(struct rxe_qp *qp, void *data_addr, int err; err = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &qp->resp.wqe->dma, - data_addr, data_len, RXE_TO_MR_OBJ, NULL); + data_addr, data_len, RXE_TO_MR_OBJ); if (unlikely(err)) return (err == -ENOSPC) ? RESPST_ERR_LENGTH : RESPST_ERR_MALFORMED_WQE; @@ -552,7 +552,7 @@ static enum resp_states write_data_in(struct rxe_qp *qp, int data_len = payload_size(pkt); err = rxe_mr_copy(qp->resp.mr, qp->resp.va + qp->resp.offset, - payload_addr(pkt), data_len, RXE_TO_MR_OBJ, NULL); + payload_addr(pkt), data_len, RXE_TO_MR_OBJ); if (err) { rc = RESPST_ERR_RKEY_VIOLATION; goto out; @@ -613,13 +613,10 @@ static struct sk_buff *prepare_ack_packet(struct rxe_qp *qp, int opcode, int payload, u32 psn, - u8 syndrome, - u32 *crcp) + u8 syndrome) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); struct sk_buff *skb; - u32 crc = 0; - u32 *p; int paylen; int pad; int err; @@ -651,20 +648,12 @@ static struct sk_buff *prepare_ack_packet(struct rxe_qp *qp, if (ack->mask & RXE_ATMACK_MASK) atmack_set_orig(ack, qp->resp.atomic_orig); - err = rxe_prepare(ack, skb, &crc); + err = rxe_prepare(ack, skb); if (err) { kfree_skb(skb); return NULL; } - if (crcp) { - /* CRC computation will be continued by the caller */ - *crcp = crc; - } else { - p = payload_addr(ack) + payload + bth_pad(ack); - *p = ~crc; - } - return skb; } @@ -682,8 +671,6 @@ static enum resp_states read_reply(struct rxe_qp *qp, int opcode; int err; struct resp_res *res = qp->resp.res; - u32 icrc; - u32 *p; if (!res) { /* This is the first time we process that request. Get a @@ -742,24 +729,20 @@ static enum resp_states read_reply(struct rxe_qp *qp, payload = min_t(int, res->read.resid, mtu); skb = prepare_ack_packet(qp, req_pkt, &ack_pkt, opcode, payload, - res->cur_psn, AETH_ACK_UNLIMITED, &icrc); + res->cur_psn, AETH_ACK_UNLIMITED); if (!skb) return RESPST_ERR_RNR; err = rxe_mr_copy(res->read.mr, res->read.va, payload_addr(&ack_pkt), - payload, RXE_FROM_MR_OBJ, &icrc); + payload, RXE_FROM_MR_OBJ); if (err) pr_err("Failed copying memory\n"); if (bth_pad(&ack_pkt)) { - struct rxe_dev *rxe = to_rdev(qp->ibqp.device); u8 *pad = payload_addr(&ack_pkt) + payload; memset(pad, 0, bth_pad(&ack_pkt)); - icrc = rxe_crc32(rxe, icrc, pad, bth_pad(&ack_pkt)); } - p = payload_addr(&ack_pkt) + payload + bth_pad(&ack_pkt); - *p = ~icrc; err = rxe_xmit_packet(qp, &ack_pkt, skb); if (err) { @@ -984,7 +967,7 @@ static int send_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt, struct sk_buff *skb; skb = prepare_ack_packet(qp, pkt, &ack_pkt, IB_OPCODE_RC_ACKNOWLEDGE, - 0, psn, syndrome, NULL); + 0, psn, syndrome); if (!skb) { err = -ENOMEM; goto err1; @@ -1008,7 +991,7 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt, skb = prepare_ack_packet(qp, pkt, &ack_pkt, IB_OPCODE_RC_ATOMIC_ACKNOWLEDGE, 0, pkt->psn, - syndrome, NULL); + syndrome); if (!skb) { rc = -ENOMEM; goto out; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index c223959ac174..f7b1a1f64c13 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1154,7 +1154,6 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) { int err; struct ib_device *dev = &rxe->ib_dev; - struct crypto_shash *tfm; strscpy(dev->node_desc, "rxe", sizeof(dev->node_desc)); @@ -1173,13 +1172,9 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) if (err) return err; - tfm = crypto_alloc_shash("crc32", 0, 0); - if (IS_ERR(tfm)) { - pr_err("failed to allocate crc algorithm err:%ld\n", - PTR_ERR(tfm)); - return PTR_ERR(tfm); - } - rxe->tfm = tfm; + err = rxe_icrc_init(rxe); + if (err) + return err; err = ib_register_device(dev, ibdev_name, NULL); if (err) diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index 7989c4043db4..1f4e60257700 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -76,7 +76,7 @@ static int siw_try_1seg(struct siw_iwarp_tx *c_tx, void *paddr) if (unlikely(!p)) return -EFAULT; - buffer = kmap(p); + buffer = kmap_local_page(p); if (likely(PAGE_SIZE - off >= bytes)) { memcpy(paddr, buffer + off, bytes); @@ -84,7 +84,7 @@ static int siw_try_1seg(struct siw_iwarp_tx *c_tx, void *paddr) unsigned long part = bytes - (PAGE_SIZE - off); memcpy(paddr, buffer + off, part); - kunmap(p); + kunmap_local(buffer); if (!mem->is_pbl) p = siw_get_upage(mem->umem, @@ -96,10 +96,10 @@ static int siw_try_1seg(struct siw_iwarp_tx *c_tx, void *paddr) if (unlikely(!p)) return -EFAULT; - buffer = kmap(p); + buffer = kmap_local_page(p); memcpy(paddr + part, buffer, bytes - part); } - kunmap(p); + kunmap_local(buffer); } } return (int)bytes; @@ -396,13 +396,20 @@ static int siw_0copy_tx(struct socket *s, struct page **page, #define MAX_TRAILER (MPA_CRC_SIZE + 4) -static void siw_unmap_pages(struct page **pp, unsigned long kmap_mask) +static void siw_unmap_pages(struct kvec *iov, unsigned long kmap_mask, int len) { - while (kmap_mask) { - if (kmap_mask & BIT(0)) - kunmap(*pp); - pp++; - kmap_mask >>= 1; + int i; + + /* + * Work backwards through the array to honor the kmap_local_page() + * ordering requirements. + */ + for (i = (len-1); i >= 0; i--) { + if (kmap_mask & BIT(i)) { + unsigned long addr = (unsigned long)iov[i].iov_base; + + kunmap_local((void *)(addr & PAGE_MASK)); + } } } @@ -485,6 +492,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) while (sge_len) { size_t plen = min((int)PAGE_SIZE - fp_off, sge_len); + void *kaddr; if (!is_kva) { struct page *p; @@ -497,7 +505,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) p = siw_get_upage(mem->umem, sge->laddr + sge_off); if (unlikely(!p)) { - siw_unmap_pages(page_array, kmap_mask); + siw_unmap_pages(iov, kmap_mask, seg); wqe->processed -= c_tx->bytes_unsent; rv = -EFAULT; goto done_crc; @@ -505,11 +513,12 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) page_array[seg] = p; if (!c_tx->use_sendpage) { - iov[seg].iov_base = kmap(p) + fp_off; - iov[seg].iov_len = plen; + void *kaddr = kmap_local_page(p); /* Remember for later kunmap() */ kmap_mask |= BIT(seg); + iov[seg].iov_base = kaddr + fp_off; + iov[seg].iov_len = plen; if (do_crc) crypto_shash_update( @@ -517,10 +526,11 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) iov[seg].iov_base, plen); } else if (do_crc) { + kaddr = kmap_local_page(p); crypto_shash_update(c_tx->mpa_crc_hd, - kmap(p) + fp_off, + kaddr + fp_off, plen); - kunmap(p); + kunmap_local(kaddr); } } else { u64 va = sge->laddr + sge_off; @@ -540,7 +550,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) if (++seg > (int)MAX_ARRAY) { siw_dbg_qp(tx_qp(c_tx), "to many fragments\n"); - siw_unmap_pages(page_array, kmap_mask); + siw_unmap_pages(iov, kmap_mask, seg-1); wqe->processed -= c_tx->bytes_unsent; rv = -EMSGSIZE; goto done_crc; @@ -591,7 +601,7 @@ sge_done: } else { rv = kernel_sendmsg(s, &msg, iov, seg + 1, hdr_len + data_len + trl_len); - siw_unmap_pages(page_array, kmap_mask); + siw_unmap_pages(iov, kmap_mask, seg); } if (rv < (int)hdr_len) { /* Not even complete hdr pushed or negative rv */ diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index f2c40e50f25e..ece3205531b8 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -478,7 +478,7 @@ static int rtrs_post_send_rdma(struct rtrs_clt_con *con, * From time to time we have to post signalled sends, * or send queue will fill up and only QP reset can help. */ - flags = atomic_inc_return(&con->io_cnt) % sess->queue_depth ? + flags = atomic_inc_return(&con->c.wr_cnt) % sess->s.signal_interval ? 0 : IB_SEND_SIGNALED; ib_dma_sync_single_for_device(sess->s.dev->ib_dev, req->iu->dma_addr, @@ -680,6 +680,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc) case IB_WC_RDMA_WRITE: /* * post_send() RDMA write completions of IO reqs (read/write) + * and hb. */ break; @@ -1043,7 +1044,7 @@ static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con, * From time to time we have to post signalled sends, * or send queue will fill up and only QP reset can help. */ - flags = atomic_inc_return(&con->io_cnt) % sess->queue_depth ? + flags = atomic_inc_return(&con->c.wr_cnt) % sess->s.signal_interval ? 0 : IB_SEND_SIGNALED; ib_dma_sync_single_for_device(sess->s.dev->ib_dev, req->iu->dma_addr, @@ -1601,7 +1602,8 @@ static int create_con(struct rtrs_clt_sess *sess, unsigned int cid) con->cpu = (cid ? cid - 1 : 0) % nr_cpu_ids; con->c.cid = cid; con->c.sess = &sess->s; - atomic_set(&con->io_cnt, 0); + /* Align with srv, init as 1 */ + atomic_set(&con->c.wr_cnt, 1); mutex_init(&con->con_mutex); sess->s.con[cid] = &con->c; @@ -1678,6 +1680,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con) sess->queue_depth * 3 + 1); max_send_sge = 2; } + atomic_set(&con->c.sq_wr_avail, max_send_wr); cq_num = max_send_wr + max_recv_wr; /* alloc iu to recv new rkey reply when server reports flags set */ if (sess->flags & RTRS_MSG_NEW_RKEY_F || con->c.cid == 0) { @@ -1848,6 +1851,8 @@ static int rtrs_rdma_conn_established(struct rtrs_clt_con *con, return -ENOMEM; } sess->queue_depth = queue_depth; + sess->s.signal_interval = min_not_zero(queue_depth, + (unsigned short) SERVICE_CON_QUEUE_DEPTH); sess->max_hdr_size = le32_to_cpu(msg->max_hdr_size); sess->max_io_size = le32_to_cpu(msg->max_io_size); sess->flags = le32_to_cpu(msg->flags); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h index e276a2dfcf7c..3c3ff094588c 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h @@ -74,7 +74,6 @@ struct rtrs_clt_con { u32 queue_num; unsigned int cpu; struct mutex con_mutex; - atomic_t io_cnt; int cm_err; }; diff --git a/drivers/infiniband/ulp/rtrs/rtrs-pri.h b/drivers/infiniband/ulp/rtrs/rtrs-pri.h index 36f184a3b676..d12ddfa50747 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-pri.h +++ b/drivers/infiniband/ulp/rtrs/rtrs-pri.h @@ -96,6 +96,8 @@ struct rtrs_con { struct rdma_cm_id *cm_id; unsigned int cid; int nr_cqe; + atomic_t wr_cnt; + atomic_t sq_wr_avail; }; struct rtrs_sess { @@ -108,6 +110,7 @@ struct rtrs_sess { unsigned int con_num; unsigned int irq_con_num; unsigned int recon_cnt; + unsigned int signal_interval; struct rtrs_ib_dev *dev; int dev_ref; struct ib_cqe *hb_cqe; @@ -309,9 +312,6 @@ int rtrs_iu_post_rdma_write_imm(struct rtrs_con *con, struct rtrs_iu *iu, struct ib_send_wr *tail); int rtrs_post_recv_empty(struct rtrs_con *con, struct ib_cqe *cqe); -int rtrs_post_rdma_write_imm_empty(struct rtrs_con *con, struct ib_cqe *cqe, - u32 imm_data, enum ib_send_flags flags, - struct ib_send_wr *head); int rtrs_cq_qp_create(struct rtrs_sess *sess, struct rtrs_con *con, u32 max_send_sge, int cq_vector, int nr_cqe, diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index 3df290086169..cd9a4ccf4c28 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -201,7 +201,6 @@ static int rdma_write_sg(struct rtrs_srv_op *id) struct rtrs_srv_sess *sess = to_srv_sess(s); dma_addr_t dma_addr = sess->dma_addr[id->msg_id]; struct rtrs_srv_mr *srv_mr; - struct rtrs_srv *srv = sess->srv; struct ib_send_wr inv_wr; struct ib_rdma_wr imm_wr; struct ib_rdma_wr *wr = NULL; @@ -269,7 +268,7 @@ static int rdma_write_sg(struct rtrs_srv_op *id) * From time to time we have to post signaled sends, * or send queue will fill up and only QP reset can help. */ - flags = (atomic_inc_return(&id->con->wr_cnt) % srv->queue_depth) ? + flags = (atomic_inc_return(&id->con->c.wr_cnt) % s->signal_interval) ? 0 : IB_SEND_SIGNALED; if (need_inval) { @@ -347,7 +346,6 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id, struct ib_send_wr inv_wr, *wr = NULL; struct ib_rdma_wr imm_wr; struct ib_reg_wr rwr; - struct rtrs_srv *srv = sess->srv; struct rtrs_srv_mr *srv_mr; bool need_inval = false; enum ib_send_flags flags; @@ -396,7 +394,7 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id, * From time to time we have to post signalled sends, * or send queue will fill up and only QP reset can help. */ - flags = (atomic_inc_return(&con->wr_cnt) % srv->queue_depth) ? + flags = (atomic_inc_return(&con->c.wr_cnt) % s->signal_interval) ? 0 : IB_SEND_SIGNALED; imm = rtrs_to_io_rsp_imm(id->msg_id, errno, need_inval); imm_wr.wr.next = NULL; @@ -509,11 +507,11 @@ bool rtrs_srv_resp_rdma(struct rtrs_srv_op *id, int status) ib_update_fast_reg_key(mr->mr, ib_inc_rkey(mr->mr->rkey)); } if (unlikely(atomic_sub_return(1, - &con->sq_wr_avail) < 0)) { + &con->c.sq_wr_avail) < 0)) { rtrs_err(s, "IB send queue full: sess=%s cid=%d\n", kobject_name(&sess->kobj), con->c.cid); - atomic_add(1, &con->sq_wr_avail); + atomic_add(1, &con->c.sq_wr_avail); spin_lock(&con->rsp_wr_wait_lock); list_add_tail(&id->wait_list, &con->rsp_wr_wait_list); spin_unlock(&con->rsp_wr_wait_lock); @@ -1268,8 +1266,9 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc) case IB_WC_SEND: /* * post_send() RDMA write completions of IO reqs (read/write) + * and hb. */ - atomic_add(srv->queue_depth, &con->sq_wr_avail); + atomic_add(s->signal_interval, &con->c.sq_wr_avail); if (unlikely(!list_empty_careful(&con->rsp_wr_wait_list))) rtrs_rdma_process_wr_wait_list(con); @@ -1648,7 +1647,7 @@ static int create_con(struct rtrs_srv_sess *sess, con->c.cm_id = cm_id; con->c.sess = &sess->s; con->c.cid = cid; - atomic_set(&con->wr_cnt, 1); + atomic_set(&con->c.wr_cnt, 1); wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr; if (con->c.cid == 0) { @@ -1659,6 +1658,8 @@ static int create_con(struct rtrs_srv_sess *sess, max_send_wr = min_t(int, wr_limit, SERVICE_CON_QUEUE_DEPTH * 2 + 2); max_recv_wr = max_send_wr; + s->signal_interval = min_not_zero(srv->queue_depth, + (size_t)SERVICE_CON_QUEUE_DEPTH); } else { /* when always_invlaidate enalbed, we need linv+rinv+mr+imm */ if (always_invalidate) @@ -1679,7 +1680,7 @@ static int create_con(struct rtrs_srv_sess *sess, */ } cq_num = max_send_wr + max_recv_wr; - atomic_set(&con->sq_wr_avail, max_send_wr); + atomic_set(&con->c.sq_wr_avail, max_send_wr); cq_vector = rtrs_srv_get_next_cq_vector(sess); /* TODO: SOFTIRQ can be faster, but be careful with softirq context */ diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.h b/drivers/infiniband/ulp/rtrs/rtrs-srv.h index f8da2e3f0bda..e81774f5acd3 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.h +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.h @@ -42,8 +42,6 @@ struct rtrs_srv_stats { struct rtrs_srv_con { struct rtrs_con c; - atomic_t wr_cnt; - atomic_t sq_wr_avail; struct list_head rsp_wr_wait_list; spinlock_t rsp_wr_wait_lock; }; diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c index 61919ebd92b2..ca542e477d38 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs.c +++ b/drivers/infiniband/ulp/rtrs/rtrs.c @@ -182,22 +182,28 @@ int rtrs_iu_post_rdma_write_imm(struct rtrs_con *con, struct rtrs_iu *iu, } EXPORT_SYMBOL_GPL(rtrs_iu_post_rdma_write_imm); -int rtrs_post_rdma_write_imm_empty(struct rtrs_con *con, struct ib_cqe *cqe, - u32 imm_data, enum ib_send_flags flags, - struct ib_send_wr *head) +static int rtrs_post_rdma_write_imm_empty(struct rtrs_con *con, + struct ib_cqe *cqe, + u32 imm_data, + struct ib_send_wr *head) { struct ib_rdma_wr wr; + struct rtrs_sess *sess = con->sess; + enum ib_send_flags sflags; + + atomic_dec_if_positive(&con->sq_wr_avail); + sflags = (atomic_inc_return(&con->wr_cnt) % sess->signal_interval) ? + 0 : IB_SEND_SIGNALED; wr = (struct ib_rdma_wr) { .wr.wr_cqe = cqe, - .wr.send_flags = flags, + .wr.send_flags = sflags, .wr.opcode = IB_WR_RDMA_WRITE_WITH_IMM, .wr.ex.imm_data = cpu_to_be32(imm_data), }; return rtrs_post_send(con->qp, head, &wr.wr, NULL); } -EXPORT_SYMBOL_GPL(rtrs_post_rdma_write_imm_empty); static void qp_event_handler(struct ib_event *ev, void *ctx) { @@ -314,8 +320,9 @@ void rtrs_send_hb_ack(struct rtrs_sess *sess) imm = rtrs_to_imm(RTRS_HB_ACK_IMM, 0); err = rtrs_post_rdma_write_imm_empty(usr_con, sess->hb_cqe, imm, - 0, NULL); + NULL); if (err) { + rtrs_err(sess, "send HB ACK failed, errno: %d\n", err); sess->hb_err_handler(usr_con); return; } @@ -333,6 +340,7 @@ static void hb_work(struct work_struct *work) usr_con = sess->con[0]; if (sess->hb_missed_cnt > sess->hb_missed_max) { + rtrs_err(sess, "HB missed max reached.\n"); sess->hb_err_handler(usr_con); return; } @@ -346,8 +354,9 @@ static void hb_work(struct work_struct *work) imm = rtrs_to_imm(RTRS_HB_MSG_IMM, 0); err = rtrs_post_rdma_write_imm_empty(usr_con, sess->hb_cqe, imm, - 0, NULL); + NULL); if (err) { + rtrs_err(sess, "HB send failed, errno: %d\n", err); sess->hb_err_handler(usr_con); return; } |