From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- net/rds/ib_frmr.c | 446 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 446 insertions(+) create mode 100644 net/rds/ib_frmr.c (limited to 'net/rds/ib_frmr.c') diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c new file mode 100644 index 000000000..28c1b0022 --- /dev/null +++ b/net/rds/ib_frmr.c @@ -0,0 +1,446 @@ +/* + * Copyright (c) 2016 Oracle. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include "ib_mr.h" + +static inline void +rds_transition_frwr_state(struct rds_ib_mr *ibmr, + enum rds_ib_fr_state old_state, + enum rds_ib_fr_state new_state) +{ + if (cmpxchg(&ibmr->u.frmr.fr_state, + old_state, new_state) == old_state && + old_state == FRMR_IS_INUSE) { + /* enforce order of ibmr->u.frmr.fr_state update + * before decrementing i_fastreg_inuse_count + */ + smp_mb__before_atomic(); + atomic_dec(&ibmr->ic->i_fastreg_inuse_count); + if (waitqueue_active(&rds_ib_ring_empty_wait)) + wake_up(&rds_ib_ring_empty_wait); + } +} + +static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev, + int npages) +{ + struct rds_ib_mr_pool *pool; + struct rds_ib_mr *ibmr = NULL; + struct rds_ib_frmr *frmr; + int err = 0; + + if (npages <= RDS_MR_8K_MSG_SIZE) + pool = rds_ibdev->mr_8k_pool; + else + pool = rds_ibdev->mr_1m_pool; + + ibmr = rds_ib_try_reuse_ibmr(pool); + if (ibmr) + return ibmr; + + ibmr = kzalloc_node(sizeof(*ibmr), GFP_KERNEL, + rdsibdev_to_node(rds_ibdev)); + if (!ibmr) { + err = -ENOMEM; + goto out_no_cigar; + } + + frmr = &ibmr->u.frmr; + frmr->mr = ib_alloc_mr(rds_ibdev->pd, IB_MR_TYPE_MEM_REG, + pool->max_pages); + if (IS_ERR(frmr->mr)) { + pr_warn("RDS/IB: %s failed to allocate MR", __func__); + err = PTR_ERR(frmr->mr); + goto out_no_cigar; + } + + ibmr->pool = pool; + if (pool->pool_type == RDS_IB_MR_8K_POOL) + rds_ib_stats_inc(s_ib_rdma_mr_8k_alloc); + else + rds_ib_stats_inc(s_ib_rdma_mr_1m_alloc); + + if (atomic_read(&pool->item_count) > pool->max_items_soft) + pool->max_items_soft = pool->max_items; + + frmr->fr_state = FRMR_IS_FREE; + init_waitqueue_head(&frmr->fr_inv_done); + init_waitqueue_head(&frmr->fr_reg_done); + return ibmr; + +out_no_cigar: + kfree(ibmr); + atomic_dec(&pool->item_count); + return ERR_PTR(err); +} + +static void rds_ib_free_frmr(struct rds_ib_mr *ibmr, bool drop) +{ + struct rds_ib_mr_pool *pool = ibmr->pool; + + if (drop) + llist_add(&ibmr->llnode, &pool->drop_list); + else + llist_add(&ibmr->llnode, &pool->free_list); + atomic_add(ibmr->sg_len, &pool->free_pinned); + atomic_inc(&pool->dirty_count); + + /* If we've pinned too many pages, request a flush */ + if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned || + atomic_read(&pool->dirty_count) >= pool->max_items / 5) + queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); +} + +static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) +{ + struct rds_ib_frmr *frmr = &ibmr->u.frmr; + struct ib_reg_wr reg_wr; + int ret, off = 0; + + while (atomic_dec_return(&ibmr->ic->i_fastreg_wrs) <= 0) { + atomic_inc(&ibmr->ic->i_fastreg_wrs); + cpu_relax(); + } + + ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len, + &off, PAGE_SIZE); + if (unlikely(ret != ibmr->sg_dma_len)) + return ret < 0 ? ret : -EINVAL; + + if (cmpxchg(&frmr->fr_state, + FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE) + return -EBUSY; + + atomic_inc(&ibmr->ic->i_fastreg_inuse_count); + + /* Perform a WR for the fast_reg_mr. Each individual page + * in the sg list is added to the fast reg page list and placed + * inside the fast_reg_mr WR. The key used is a rolling 8bit + * counter, which should guarantee uniqueness. + */ + ib_update_fast_reg_key(frmr->mr, ibmr->remap_count++); + frmr->fr_reg = true; + + memset(®_wr, 0, sizeof(reg_wr)); + reg_wr.wr.wr_id = (unsigned long)(void *)ibmr; + reg_wr.wr.opcode = IB_WR_REG_MR; + reg_wr.wr.num_sge = 0; + reg_wr.mr = frmr->mr; + reg_wr.key = frmr->mr->rkey; + reg_wr.access = IB_ACCESS_LOCAL_WRITE | + IB_ACCESS_REMOTE_READ | + IB_ACCESS_REMOTE_WRITE; + reg_wr.wr.send_flags = IB_SEND_SIGNALED; + + ret = ib_post_send(ibmr->ic->i_cm_id->qp, ®_wr.wr, NULL); + if (unlikely(ret)) { + /* Failure here can be because of -ENOMEM as well */ + rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE); + + atomic_inc(&ibmr->ic->i_fastreg_wrs); + if (printk_ratelimit()) + pr_warn("RDS/IB: %s returned error(%d)\n", + __func__, ret); + goto out; + } + + /* Wait for the registration to complete in order to prevent an invalid + * access error resulting from a race between the memory region already + * being accessed while registration is still pending. + */ + wait_event(frmr->fr_reg_done, !frmr->fr_reg); + +out: + + return ret; +} + +static int rds_ib_map_frmr(struct rds_ib_device *rds_ibdev, + struct rds_ib_mr_pool *pool, + struct rds_ib_mr *ibmr, + struct scatterlist *sg, unsigned int sg_len) +{ + struct ib_device *dev = rds_ibdev->dev; + struct rds_ib_frmr *frmr = &ibmr->u.frmr; + int i; + u32 len; + int ret = 0; + + /* We want to teardown old ibmr values here and fill it up with + * new sg values + */ + rds_ib_teardown_mr(ibmr); + + ibmr->sg = sg; + ibmr->sg_len = sg_len; + ibmr->sg_dma_len = 0; + frmr->sg_byte_len = 0; + WARN_ON(ibmr->sg_dma_len); + ibmr->sg_dma_len = ib_dma_map_sg(dev, ibmr->sg, ibmr->sg_len, + DMA_BIDIRECTIONAL); + if (unlikely(!ibmr->sg_dma_len)) { + pr_warn("RDS/IB: %s failed!\n", __func__); + return -EBUSY; + } + + frmr->sg_byte_len = 0; + frmr->dma_npages = 0; + len = 0; + + ret = -EINVAL; + for (i = 0; i < ibmr->sg_dma_len; ++i) { + unsigned int dma_len = sg_dma_len(&ibmr->sg[i]); + u64 dma_addr = sg_dma_address(&ibmr->sg[i]); + + frmr->sg_byte_len += dma_len; + if (dma_addr & ~PAGE_MASK) { + if (i > 0) + goto out_unmap; + else + ++frmr->dma_npages; + } + + if ((dma_addr + dma_len) & ~PAGE_MASK) { + if (i < ibmr->sg_dma_len - 1) + goto out_unmap; + else + ++frmr->dma_npages; + } + + len += dma_len; + } + frmr->dma_npages += len >> PAGE_SHIFT; + + if (frmr->dma_npages > ibmr->pool->max_pages) { + ret = -EMSGSIZE; + goto out_unmap; + } + + ret = rds_ib_post_reg_frmr(ibmr); + if (ret) + goto out_unmap; + + if (ibmr->pool->pool_type == RDS_IB_MR_8K_POOL) + rds_ib_stats_inc(s_ib_rdma_mr_8k_used); + else + rds_ib_stats_inc(s_ib_rdma_mr_1m_used); + + return ret; + +out_unmap: + ib_dma_unmap_sg(rds_ibdev->dev, ibmr->sg, ibmr->sg_len, + DMA_BIDIRECTIONAL); + ibmr->sg_dma_len = 0; + return ret; +} + +static int rds_ib_post_inv(struct rds_ib_mr *ibmr) +{ + struct ib_send_wr *s_wr; + struct rds_ib_frmr *frmr = &ibmr->u.frmr; + struct rdma_cm_id *i_cm_id = ibmr->ic->i_cm_id; + int ret = -EINVAL; + + if (!i_cm_id || !i_cm_id->qp || !frmr->mr) + goto out; + + if (frmr->fr_state != FRMR_IS_INUSE) + goto out; + + while (atomic_dec_return(&ibmr->ic->i_fastreg_wrs) <= 0) { + atomic_inc(&ibmr->ic->i_fastreg_wrs); + cpu_relax(); + } + + frmr->fr_inv = true; + s_wr = &frmr->fr_wr; + + memset(s_wr, 0, sizeof(*s_wr)); + s_wr->wr_id = (unsigned long)(void *)ibmr; + s_wr->opcode = IB_WR_LOCAL_INV; + s_wr->ex.invalidate_rkey = frmr->mr->rkey; + s_wr->send_flags = IB_SEND_SIGNALED; + + ret = ib_post_send(i_cm_id->qp, s_wr, NULL); + if (unlikely(ret)) { + rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE); + frmr->fr_inv = false; + /* enforce order of frmr->fr_inv update + * before incrementing i_fastreg_wrs + */ + smp_mb__before_atomic(); + atomic_inc(&ibmr->ic->i_fastreg_wrs); + pr_err("RDS/IB: %s returned error(%d)\n", __func__, ret); + goto out; + } + + /* Wait for the FRMR_IS_FREE (or FRMR_IS_STALE) transition in order to + * 1) avoid a silly bouncing between "clean_list" and "drop_list" + * triggered by function "rds_ib_reg_frmr" as it is releases frmr + * regions whose state is not "FRMR_IS_FREE" right away. + * 2) prevents an invalid access error in a race + * from a pending "IB_WR_LOCAL_INV" operation + * with a teardown ("dma_unmap_sg", "put_page") + * and de-registration ("ib_dereg_mr") of the corresponding + * memory region. + */ + wait_event(frmr->fr_inv_done, frmr->fr_state != FRMR_IS_INUSE); + +out: + return ret; +} + +void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc) +{ + struct rds_ib_mr *ibmr = (void *)(unsigned long)wc->wr_id; + struct rds_ib_frmr *frmr = &ibmr->u.frmr; + + if (wc->status != IB_WC_SUCCESS) { + rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE); + if (rds_conn_up(ic->conn)) + rds_ib_conn_error(ic->conn, + "frmr completion <%pI4,%pI4> status %u(%s), vendor_err 0x%x, disconnecting and reconnecting\n", + &ic->conn->c_laddr, + &ic->conn->c_faddr, + wc->status, + ib_wc_status_msg(wc->status), + wc->vendor_err); + } + + if (frmr->fr_inv) { + rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_FREE); + frmr->fr_inv = false; + wake_up(&frmr->fr_inv_done); + } + + if (frmr->fr_reg) { + frmr->fr_reg = false; + wake_up(&frmr->fr_reg_done); + } + + /* enforce order of frmr->{fr_reg,fr_inv} update + * before incrementing i_fastreg_wrs + */ + smp_mb__before_atomic(); + atomic_inc(&ic->i_fastreg_wrs); +} + +void rds_ib_unreg_frmr(struct list_head *list, unsigned int *nfreed, + unsigned long *unpinned, unsigned int goal) +{ + struct rds_ib_mr *ibmr, *next; + struct rds_ib_frmr *frmr; + int ret = 0, ret2; + unsigned int freed = *nfreed; + + /* String all ib_mr's onto one list and hand them to ib_unmap_fmr */ + list_for_each_entry(ibmr, list, unmap_list) { + if (ibmr->sg_dma_len) { + ret2 = rds_ib_post_inv(ibmr); + if (ret2 && !ret) + ret = ret2; + } + } + + if (ret) + pr_warn("RDS/IB: %s failed (err=%d)\n", __func__, ret); + + /* Now we can destroy the DMA mapping and unpin any pages */ + list_for_each_entry_safe(ibmr, next, list, unmap_list) { + *unpinned += ibmr->sg_len; + frmr = &ibmr->u.frmr; + __rds_ib_teardown_mr(ibmr); + if (freed < goal || frmr->fr_state == FRMR_IS_STALE) { + /* Don't de-allocate if the MR is not free yet */ + if (frmr->fr_state == FRMR_IS_INUSE) + continue; + + if (ibmr->pool->pool_type == RDS_IB_MR_8K_POOL) + rds_ib_stats_inc(s_ib_rdma_mr_8k_free); + else + rds_ib_stats_inc(s_ib_rdma_mr_1m_free); + list_del(&ibmr->unmap_list); + if (frmr->mr) + ib_dereg_mr(frmr->mr); + kfree(ibmr); + freed++; + } + } + *nfreed = freed; +} + +struct rds_ib_mr *rds_ib_reg_frmr(struct rds_ib_device *rds_ibdev, + struct rds_ib_connection *ic, + struct scatterlist *sg, + unsigned long nents, u32 *key) +{ + struct rds_ib_mr *ibmr = NULL; + struct rds_ib_frmr *frmr; + int ret; + + if (!ic) { + /* TODO: Add FRWR support for RDS_GET_MR using proxy qp*/ + return ERR_PTR(-EOPNOTSUPP); + } + + do { + if (ibmr) + rds_ib_free_frmr(ibmr, true); + ibmr = rds_ib_alloc_frmr(rds_ibdev, nents); + if (IS_ERR(ibmr)) + return ibmr; + frmr = &ibmr->u.frmr; + } while (frmr->fr_state != FRMR_IS_FREE); + + ibmr->ic = ic; + ibmr->device = rds_ibdev; + ret = rds_ib_map_frmr(rds_ibdev, ibmr->pool, ibmr, sg, nents); + if (ret == 0) { + *key = frmr->mr->rkey; + } else { + rds_ib_free_frmr(ibmr, false); + ibmr = ERR_PTR(ret); + } + + return ibmr; +} + +void rds_ib_free_frmr_list(struct rds_ib_mr *ibmr) +{ + struct rds_ib_mr_pool *pool = ibmr->pool; + struct rds_ib_frmr *frmr = &ibmr->u.frmr; + + if (frmr->fr_state == FRMR_IS_STALE) + llist_add(&ibmr->llnode, &pool->drop_list); + else + llist_add(&ibmr->llnode, &pool->free_list); +} -- cgit v1.2.3