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(). ... --- drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c | 327 +++++++++++++++++++++++++++ 1 file changed, 327 insertions(+) create mode 100644 drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c (limited to 'drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c') diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c new file mode 100644 index 000000000..e80848bfb --- /dev/null +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c @@ -0,0 +1,327 @@ +/* + * Copyright (c) 2012-2016 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of EITHER the GNU General Public License + * version 2 as published by the Free Software Foundation or the BSD + * 2-Clause License. This program is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; WITHOUT EVEN THE IMPLIED + * WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License version 2 for more details at + * http://www.gnu.org/licenses/old-licenses/gpl-2.0.en.html. + * + * You should have received a copy of the GNU General Public License + * along with this program available in the file COPYING in the main + * directory of this source tree. + * + * The BSD 2-Clause License + * + * 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. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, + * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR + * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, + * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED + * OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include +#include + +#include "pvrdma.h" + +/** + * pvrdma_get_dma_mr - get a DMA memory region + * @pd: protection domain + * @acc: access flags + * + * @return: ib_mr pointer on success, otherwise returns an errno. + */ +struct ib_mr *pvrdma_get_dma_mr(struct ib_pd *pd, int acc) +{ + struct pvrdma_dev *dev = to_vdev(pd->device); + struct pvrdma_user_mr *mr; + union pvrdma_cmd_req req; + union pvrdma_cmd_resp rsp; + struct pvrdma_cmd_create_mr *cmd = &req.create_mr; + struct pvrdma_cmd_create_mr_resp *resp = &rsp.create_mr_resp; + int ret; + + /* Support only LOCAL_WRITE flag for DMA MRs */ + if (acc & ~IB_ACCESS_LOCAL_WRITE) { + dev_warn(&dev->pdev->dev, + "unsupported dma mr access flags %#x\n", acc); + return ERR_PTR(-EOPNOTSUPP); + } + + mr = kzalloc(sizeof(*mr), GFP_KERNEL); + if (!mr) + return ERR_PTR(-ENOMEM); + + memset(cmd, 0, sizeof(*cmd)); + cmd->hdr.cmd = PVRDMA_CMD_CREATE_MR; + cmd->pd_handle = to_vpd(pd)->pd_handle; + cmd->access_flags = acc; + cmd->flags = PVRDMA_MR_FLAG_DMA; + + ret = pvrdma_cmd_post(dev, &req, &rsp, PVRDMA_CMD_CREATE_MR_RESP); + if (ret < 0) { + dev_warn(&dev->pdev->dev, + "could not get DMA mem region, error: %d\n", ret); + kfree(mr); + return ERR_PTR(ret); + } + + mr->mmr.mr_handle = resp->mr_handle; + mr->ibmr.lkey = resp->lkey; + mr->ibmr.rkey = resp->rkey; + + return &mr->ibmr; +} + +/** + * pvrdma_reg_user_mr - register a userspace memory region + * @pd: protection domain + * @start: starting address + * @length: length of region + * @virt_addr: I/O virtual address + * @access_flags: access flags for memory region + * @udata: user data + * + * @return: ib_mr pointer on success, otherwise returns an errno. + */ +struct ib_mr *pvrdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, + u64 virt_addr, int access_flags, + struct ib_udata *udata) +{ + struct pvrdma_dev *dev = to_vdev(pd->device); + struct pvrdma_user_mr *mr = NULL; + struct ib_umem *umem; + union pvrdma_cmd_req req; + union pvrdma_cmd_resp rsp; + struct pvrdma_cmd_create_mr *cmd = &req.create_mr; + struct pvrdma_cmd_create_mr_resp *resp = &rsp.create_mr_resp; + int ret, npages; + + if (length == 0 || length > dev->dsr->caps.max_mr_size) { + dev_warn(&dev->pdev->dev, "invalid mem region length\n"); + return ERR_PTR(-EINVAL); + } + + umem = ib_umem_get(pd->device, start, length, access_flags); + if (IS_ERR(umem)) { + dev_warn(&dev->pdev->dev, + "could not get umem for mem region\n"); + return ERR_CAST(umem); + } + + npages = ib_umem_num_dma_blocks(umem, PAGE_SIZE); + if (npages < 0 || npages > PVRDMA_PAGE_DIR_MAX_PAGES) { + dev_warn(&dev->pdev->dev, "overflow %d pages in mem region\n", + npages); + ret = -EINVAL; + goto err_umem; + } + + mr = kzalloc(sizeof(*mr), GFP_KERNEL); + if (!mr) { + ret = -ENOMEM; + goto err_umem; + } + + mr->mmr.iova = virt_addr; + mr->mmr.size = length; + mr->umem = umem; + + ret = pvrdma_page_dir_init(dev, &mr->pdir, npages, false); + if (ret) { + dev_warn(&dev->pdev->dev, + "could not allocate page directory\n"); + goto err_umem; + } + + ret = pvrdma_page_dir_insert_umem(&mr->pdir, mr->umem, 0); + if (ret) + goto err_pdir; + + memset(cmd, 0, sizeof(*cmd)); + cmd->hdr.cmd = PVRDMA_CMD_CREATE_MR; + cmd->start = start; + cmd->length = length; + cmd->pd_handle = to_vpd(pd)->pd_handle; + cmd->access_flags = access_flags; + cmd->nchunks = npages; + cmd->pdir_dma = mr->pdir.dir_dma; + + ret = pvrdma_cmd_post(dev, &req, &rsp, PVRDMA_CMD_CREATE_MR_RESP); + if (ret < 0) { + dev_warn(&dev->pdev->dev, + "could not register mem region, error: %d\n", ret); + goto err_pdir; + } + + mr->mmr.mr_handle = resp->mr_handle; + mr->ibmr.lkey = resp->lkey; + mr->ibmr.rkey = resp->rkey; + + return &mr->ibmr; + +err_pdir: + pvrdma_page_dir_cleanup(dev, &mr->pdir); +err_umem: + ib_umem_release(umem); + kfree(mr); + + return ERR_PTR(ret); +} + +/** + * pvrdma_alloc_mr - allocate a memory region + * @pd: protection domain + * @mr_type: type of memory region + * @max_num_sg: maximum number of pages + * + * @return: ib_mr pointer on success, otherwise returns an errno. + */ +struct ib_mr *pvrdma_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, + u32 max_num_sg) +{ + struct pvrdma_dev *dev = to_vdev(pd->device); + struct pvrdma_user_mr *mr; + union pvrdma_cmd_req req; + union pvrdma_cmd_resp rsp; + struct pvrdma_cmd_create_mr *cmd = &req.create_mr; + struct pvrdma_cmd_create_mr_resp *resp = &rsp.create_mr_resp; + int size = max_num_sg * sizeof(u64); + int ret; + + if (mr_type != IB_MR_TYPE_MEM_REG || + max_num_sg > PVRDMA_MAX_FAST_REG_PAGES) + return ERR_PTR(-EINVAL); + + mr = kzalloc(sizeof(*mr), GFP_KERNEL); + if (!mr) + return ERR_PTR(-ENOMEM); + + mr->pages = kzalloc(size, GFP_KERNEL); + if (!mr->pages) { + ret = -ENOMEM; + goto freemr; + } + + ret = pvrdma_page_dir_init(dev, &mr->pdir, max_num_sg, false); + if (ret) { + dev_warn(&dev->pdev->dev, + "failed to allocate page dir for mr\n"); + ret = -ENOMEM; + goto freepages; + } + + memset(cmd, 0, sizeof(*cmd)); + cmd->hdr.cmd = PVRDMA_CMD_CREATE_MR; + cmd->pd_handle = to_vpd(pd)->pd_handle; + cmd->access_flags = 0; + cmd->flags = PVRDMA_MR_FLAG_FRMR; + cmd->nchunks = max_num_sg; + + ret = pvrdma_cmd_post(dev, &req, &rsp, PVRDMA_CMD_CREATE_MR_RESP); + if (ret < 0) { + dev_warn(&dev->pdev->dev, + "could not create FR mem region, error: %d\n", ret); + goto freepdir; + } + + mr->max_pages = max_num_sg; + mr->mmr.mr_handle = resp->mr_handle; + mr->ibmr.lkey = resp->lkey; + mr->ibmr.rkey = resp->rkey; + mr->page_shift = PAGE_SHIFT; + mr->umem = NULL; + + return &mr->ibmr; + +freepdir: + pvrdma_page_dir_cleanup(dev, &mr->pdir); +freepages: + kfree(mr->pages); +freemr: + kfree(mr); + return ERR_PTR(ret); +} + +/** + * pvrdma_dereg_mr - deregister a memory region + * @ibmr: memory region + * @udata: pointer to user data + * + * @return: 0 on success. + */ +int pvrdma_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) +{ + struct pvrdma_user_mr *mr = to_vmr(ibmr); + struct pvrdma_dev *dev = to_vdev(ibmr->device); + union pvrdma_cmd_req req; + struct pvrdma_cmd_destroy_mr *cmd = &req.destroy_mr; + int ret; + + memset(cmd, 0, sizeof(*cmd)); + cmd->hdr.cmd = PVRDMA_CMD_DESTROY_MR; + cmd->mr_handle = mr->mmr.mr_handle; + ret = pvrdma_cmd_post(dev, &req, NULL, 0); + if (ret < 0) + dev_warn(&dev->pdev->dev, + "could not deregister mem region, error: %d\n", ret); + + pvrdma_page_dir_cleanup(dev, &mr->pdir); + ib_umem_release(mr->umem); + + kfree(mr->pages); + kfree(mr); + + return 0; +} + +static int pvrdma_set_page(struct ib_mr *ibmr, u64 addr) +{ + struct pvrdma_user_mr *mr = to_vmr(ibmr); + + if (mr->npages == mr->max_pages) + return -ENOMEM; + + mr->pages[mr->npages++] = addr; + return 0; +} + +int pvrdma_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, + unsigned int *sg_offset) +{ + struct pvrdma_user_mr *mr = to_vmr(ibmr); + struct pvrdma_dev *dev = to_vdev(ibmr->device); + int ret; + + mr->npages = 0; + + ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, pvrdma_set_page); + if (ret < 0) + dev_warn(&dev->pdev->dev, "could not map sg to pages\n"); + + return ret; +} -- cgit v1.2.3