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/crypto/cavium/cpt/cptvf_reqmanager.c | 575 +++++++++++++++++++++++++++ 1 file changed, 575 insertions(+) create mode 100644 drivers/crypto/cavium/cpt/cptvf_reqmanager.c (limited to 'drivers/crypto/cavium/cpt/cptvf_reqmanager.c') diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c new file mode 100644 index 000000000..153004bdf --- /dev/null +++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c @@ -0,0 +1,575 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2016 Cavium, Inc. + */ + +#include "cptvf.h" +#include "cptvf_algs.h" +#include "request_manager.h" + +/** + * get_free_pending_entry - get free entry from pending queue + * @q: pending queue + * @qlen: queue length + */ +static struct pending_entry *get_free_pending_entry(struct pending_queue *q, + int qlen) +{ + struct pending_entry *ent = NULL; + + ent = &q->head[q->rear]; + if (unlikely(ent->busy)) { + ent = NULL; + goto no_free_entry; + } + + q->rear++; + if (unlikely(q->rear == qlen)) + q->rear = 0; + +no_free_entry: + return ent; +} + +static inline void pending_queue_inc_front(struct pending_qinfo *pqinfo, + int qno) +{ + struct pending_queue *queue = &pqinfo->queue[qno]; + + queue->front++; + if (unlikely(queue->front == pqinfo->qlen)) + queue->front = 0; +} + +static int setup_sgio_components(struct cpt_vf *cptvf, struct buf_ptr *list, + int buf_count, u8 *buffer) +{ + int ret = 0, i, j; + int components; + struct sglist_component *sg_ptr = NULL; + struct pci_dev *pdev = cptvf->pdev; + + if (unlikely(!list)) { + dev_err(&pdev->dev, "Input List pointer is NULL\n"); + return -EFAULT; + } + + for (i = 0; i < buf_count; i++) { + if (likely(list[i].vptr)) { + list[i].dma_addr = dma_map_single(&pdev->dev, + list[i].vptr, + list[i].size, + DMA_BIDIRECTIONAL); + if (unlikely(dma_mapping_error(&pdev->dev, + list[i].dma_addr))) { + dev_err(&pdev->dev, "DMA map kernel buffer failed for component: %d\n", + i); + ret = -EIO; + goto sg_cleanup; + } + } + } + + components = buf_count / 4; + sg_ptr = (struct sglist_component *)buffer; + for (i = 0; i < components; i++) { + sg_ptr->u.s.len0 = cpu_to_be16(list[i * 4 + 0].size); + sg_ptr->u.s.len1 = cpu_to_be16(list[i * 4 + 1].size); + sg_ptr->u.s.len2 = cpu_to_be16(list[i * 4 + 2].size); + sg_ptr->u.s.len3 = cpu_to_be16(list[i * 4 + 3].size); + sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr); + sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr); + sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr); + sg_ptr->ptr3 = cpu_to_be64(list[i * 4 + 3].dma_addr); + sg_ptr++; + } + + components = buf_count % 4; + + switch (components) { + case 3: + sg_ptr->u.s.len2 = cpu_to_be16(list[i * 4 + 2].size); + sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr); + fallthrough; + case 2: + sg_ptr->u.s.len1 = cpu_to_be16(list[i * 4 + 1].size); + sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr); + fallthrough; + case 1: + sg_ptr->u.s.len0 = cpu_to_be16(list[i * 4 + 0].size); + sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr); + break; + default: + break; + } + + return ret; + +sg_cleanup: + for (j = 0; j < i; j++) { + if (list[j].dma_addr) { + dma_unmap_single(&pdev->dev, list[i].dma_addr, + list[i].size, DMA_BIDIRECTIONAL); + } + + list[j].dma_addr = 0; + } + + return ret; +} + +static inline int setup_sgio_list(struct cpt_vf *cptvf, + struct cpt_info_buffer *info, + struct cpt_request_info *req) +{ + u16 g_sz_bytes = 0, s_sz_bytes = 0; + int ret = 0; + struct pci_dev *pdev = cptvf->pdev; + + if (req->incnt > MAX_SG_IN_CNT || req->outcnt > MAX_SG_OUT_CNT) { + dev_err(&pdev->dev, "Request SG components are higher than supported\n"); + ret = -EINVAL; + goto scatter_gather_clean; + } + + /* Setup gather (input) components */ + g_sz_bytes = ((req->incnt + 3) / 4) * sizeof(struct sglist_component); + info->gather_components = kzalloc(g_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); + if (!info->gather_components) { + ret = -ENOMEM; + goto scatter_gather_clean; + } + + ret = setup_sgio_components(cptvf, req->in, + req->incnt, + info->gather_components); + if (ret) { + dev_err(&pdev->dev, "Failed to setup gather list\n"); + ret = -EFAULT; + goto scatter_gather_clean; + } + + /* Setup scatter (output) components */ + s_sz_bytes = ((req->outcnt + 3) / 4) * sizeof(struct sglist_component); + info->scatter_components = kzalloc(s_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); + if (!info->scatter_components) { + ret = -ENOMEM; + goto scatter_gather_clean; + } + + ret = setup_sgio_components(cptvf, req->out, + req->outcnt, + info->scatter_components); + if (ret) { + dev_err(&pdev->dev, "Failed to setup gather list\n"); + ret = -EFAULT; + goto scatter_gather_clean; + } + + /* Create and initialize DPTR */ + info->dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE; + info->in_buffer = kzalloc(info->dlen, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); + if (!info->in_buffer) { + ret = -ENOMEM; + goto scatter_gather_clean; + } + + ((__be16 *)info->in_buffer)[0] = cpu_to_be16(req->outcnt); + ((__be16 *)info->in_buffer)[1] = cpu_to_be16(req->incnt); + ((__be16 *)info->in_buffer)[2] = 0; + ((__be16 *)info->in_buffer)[3] = 0; + + memcpy(&info->in_buffer[8], info->gather_components, + g_sz_bytes); + memcpy(&info->in_buffer[8 + g_sz_bytes], + info->scatter_components, s_sz_bytes); + + info->dptr_baddr = dma_map_single(&pdev->dev, + (void *)info->in_buffer, + info->dlen, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(&pdev->dev, info->dptr_baddr)) { + dev_err(&pdev->dev, "Mapping DPTR Failed %d\n", info->dlen); + ret = -EIO; + goto scatter_gather_clean; + } + + /* Create and initialize RPTR */ + info->out_buffer = kzalloc(COMPLETION_CODE_SIZE, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); + if (!info->out_buffer) { + ret = -ENOMEM; + goto scatter_gather_clean; + } + + *((u64 *)info->out_buffer) = ~((u64)COMPLETION_CODE_INIT); + info->alternate_caddr = (u64 *)info->out_buffer; + info->rptr_baddr = dma_map_single(&pdev->dev, + (void *)info->out_buffer, + COMPLETION_CODE_SIZE, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(&pdev->dev, info->rptr_baddr)) { + dev_err(&pdev->dev, "Mapping RPTR Failed %d\n", + COMPLETION_CODE_SIZE); + ret = -EIO; + goto scatter_gather_clean; + } + + return 0; + +scatter_gather_clean: + return ret; +} + +static int send_cpt_command(struct cpt_vf *cptvf, union cpt_inst_s *cmd, + u32 qno) +{ + struct pci_dev *pdev = cptvf->pdev; + struct command_qinfo *qinfo = NULL; + struct command_queue *queue; + struct command_chunk *chunk; + u8 *ent; + int ret = 0; + + if (unlikely(qno >= cptvf->nr_queues)) { + dev_err(&pdev->dev, "Invalid queue (qno: %d, nr_queues: %d)\n", + qno, cptvf->nr_queues); + return -EINVAL; + } + + qinfo = &cptvf->cqinfo; + queue = &qinfo->queue[qno]; + /* lock commad queue */ + spin_lock(&queue->lock); + ent = &queue->qhead->head[queue->idx * qinfo->cmd_size]; + memcpy(ent, (void *)cmd, qinfo->cmd_size); + + if (++queue->idx >= queue->qhead->size / 64) { + hlist_for_each_entry(chunk, &queue->chead, nextchunk) { + if (chunk == queue->qhead) { + continue; + } else { + queue->qhead = chunk; + break; + } + } + queue->idx = 0; + } + /* make sure all memory stores are done before ringing doorbell */ + smp_wmb(); + cptvf_write_vq_doorbell(cptvf, 1); + /* unlock command queue */ + spin_unlock(&queue->lock); + + return ret; +} + +static void do_request_cleanup(struct cpt_vf *cptvf, + struct cpt_info_buffer *info) +{ + int i; + struct pci_dev *pdev = cptvf->pdev; + struct cpt_request_info *req; + + if (info->dptr_baddr) + dma_unmap_single(&pdev->dev, info->dptr_baddr, + info->dlen, DMA_BIDIRECTIONAL); + + if (info->rptr_baddr) + dma_unmap_single(&pdev->dev, info->rptr_baddr, + COMPLETION_CODE_SIZE, DMA_BIDIRECTIONAL); + + if (info->comp_baddr) + dma_unmap_single(&pdev->dev, info->comp_baddr, + sizeof(union cpt_res_s), DMA_BIDIRECTIONAL); + + if (info->req) { + req = info->req; + for (i = 0; i < req->outcnt; i++) { + if (req->out[i].dma_addr) + dma_unmap_single(&pdev->dev, + req->out[i].dma_addr, + req->out[i].size, + DMA_BIDIRECTIONAL); + } + + for (i = 0; i < req->incnt; i++) { + if (req->in[i].dma_addr) + dma_unmap_single(&pdev->dev, + req->in[i].dma_addr, + req->in[i].size, + DMA_BIDIRECTIONAL); + } + } + + kfree_sensitive(info->scatter_components); + kfree_sensitive(info->gather_components); + kfree_sensitive(info->out_buffer); + kfree_sensitive(info->in_buffer); + kfree_sensitive((void *)info->completion_addr); + kfree_sensitive(info); +} + +static void do_post_process(struct cpt_vf *cptvf, struct cpt_info_buffer *info) +{ + struct pci_dev *pdev = cptvf->pdev; + + if (!info) { + dev_err(&pdev->dev, "incorrect cpt_info_buffer for post processing\n"); + return; + } + + do_request_cleanup(cptvf, info); +} + +static inline void process_pending_queue(struct cpt_vf *cptvf, + struct pending_qinfo *pqinfo, + int qno) +{ + struct pci_dev *pdev = cptvf->pdev; + struct pending_queue *pqueue = &pqinfo->queue[qno]; + struct pending_entry *pentry = NULL; + struct cpt_info_buffer *info = NULL; + union cpt_res_s *status = NULL; + unsigned char ccode; + + while (1) { + spin_lock_bh(&pqueue->lock); + pentry = &pqueue->head[pqueue->front]; + if (unlikely(!pentry->busy)) { + spin_unlock_bh(&pqueue->lock); + break; + } + + info = (struct cpt_info_buffer *)pentry->post_arg; + if (unlikely(!info)) { + dev_err(&pdev->dev, "Pending Entry post arg NULL\n"); + pending_queue_inc_front(pqinfo, qno); + spin_unlock_bh(&pqueue->lock); + continue; + } + + status = (union cpt_res_s *)pentry->completion_addr; + ccode = status->s.compcode; + if ((status->s.compcode == CPT_COMP_E_FAULT) || + (status->s.compcode == CPT_COMP_E_SWERR)) { + dev_err(&pdev->dev, "Request failed with %s\n", + (status->s.compcode == CPT_COMP_E_FAULT) ? + "DMA Fault" : "Software error"); + pentry->completion_addr = NULL; + pentry->busy = false; + atomic64_dec((&pqueue->pending_count)); + pentry->post_arg = NULL; + pending_queue_inc_front(pqinfo, qno); + do_request_cleanup(cptvf, info); + spin_unlock_bh(&pqueue->lock); + break; + } else if (status->s.compcode == COMPLETION_CODE_INIT) { + /* check for timeout */ + if (time_after_eq(jiffies, + (info->time_in + + (CPT_COMMAND_TIMEOUT * HZ)))) { + dev_err(&pdev->dev, "Request timed out"); + pentry->completion_addr = NULL; + pentry->busy = false; + atomic64_dec((&pqueue->pending_count)); + pentry->post_arg = NULL; + pending_queue_inc_front(pqinfo, qno); + do_request_cleanup(cptvf, info); + spin_unlock_bh(&pqueue->lock); + break; + } else if ((*info->alternate_caddr == + (~COMPLETION_CODE_INIT)) && + (info->extra_time < TIME_IN_RESET_COUNT)) { + info->time_in = jiffies; + info->extra_time++; + spin_unlock_bh(&pqueue->lock); + break; + } + } + + pentry->completion_addr = NULL; + pentry->busy = false; + pentry->post_arg = NULL; + atomic64_dec((&pqueue->pending_count)); + pending_queue_inc_front(pqinfo, qno); + spin_unlock_bh(&pqueue->lock); + + do_post_process(info->cptvf, info); + /* + * Calling callback after we find + * that the request has been serviced + */ + pentry->callback(ccode, pentry->callback_arg); + } +} + +int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req) +{ + int ret = 0, clear = 0, queue = 0; + struct cpt_info_buffer *info = NULL; + struct cptvf_request *cpt_req = NULL; + union ctrl_info *ctrl = NULL; + union cpt_res_s *result = NULL; + struct pending_entry *pentry = NULL; + struct pending_queue *pqueue = NULL; + struct pci_dev *pdev = cptvf->pdev; + u8 group = 0; + struct cpt_vq_command vq_cmd; + union cpt_inst_s cptinst; + + info = kzalloc(sizeof(*info), req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); + if (unlikely(!info)) { + dev_err(&pdev->dev, "Unable to allocate memory for info_buffer\n"); + return -ENOMEM; + } + + cpt_req = (struct cptvf_request *)&req->req; + ctrl = (union ctrl_info *)&req->ctrl; + + info->cptvf = cptvf; + group = ctrl->s.grp; + ret = setup_sgio_list(cptvf, info, req); + if (ret) { + dev_err(&pdev->dev, "Setting up SG list failed"); + goto request_cleanup; + } + + cpt_req->dlen = info->dlen; + /* + * Get buffer for union cpt_res_s response + * structure and its physical address + */ + info->completion_addr = kzalloc(sizeof(union cpt_res_s), req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); + if (unlikely(!info->completion_addr)) { + dev_err(&pdev->dev, "Unable to allocate memory for completion_addr\n"); + ret = -ENOMEM; + goto request_cleanup; + } + + result = (union cpt_res_s *)info->completion_addr; + result->s.compcode = COMPLETION_CODE_INIT; + info->comp_baddr = dma_map_single(&pdev->dev, + (void *)info->completion_addr, + sizeof(union cpt_res_s), + DMA_BIDIRECTIONAL); + if (dma_mapping_error(&pdev->dev, info->comp_baddr)) { + dev_err(&pdev->dev, "mapping compptr Failed %lu\n", + sizeof(union cpt_res_s)); + ret = -EFAULT; + goto request_cleanup; + } + + /* Fill the VQ command */ + vq_cmd.cmd.u64 = 0; + vq_cmd.cmd.s.opcode = cpu_to_be16(cpt_req->opcode.flags); + vq_cmd.cmd.s.param1 = cpu_to_be16(cpt_req->param1); + vq_cmd.cmd.s.param2 = cpu_to_be16(cpt_req->param2); + vq_cmd.cmd.s.dlen = cpu_to_be16(cpt_req->dlen); + + vq_cmd.dptr = info->dptr_baddr; + vq_cmd.rptr = info->rptr_baddr; + vq_cmd.cptr.u64 = 0; + vq_cmd.cptr.s.grp = group; + /* Get Pending Entry to submit command */ + /* Always queue 0, because 1 queue per VF */ + queue = 0; + pqueue = &cptvf->pqinfo.queue[queue]; + + if (atomic64_read(&pqueue->pending_count) > PENDING_THOLD) { + dev_err(&pdev->dev, "pending threshold reached\n"); + process_pending_queue(cptvf, &cptvf->pqinfo, queue); + } + +get_pending_entry: + spin_lock_bh(&pqueue->lock); + pentry = get_free_pending_entry(pqueue, cptvf->pqinfo.qlen); + if (unlikely(!pentry)) { + spin_unlock_bh(&pqueue->lock); + if (clear == 0) { + process_pending_queue(cptvf, &cptvf->pqinfo, queue); + clear = 1; + goto get_pending_entry; + } + dev_err(&pdev->dev, "Get free entry failed\n"); + dev_err(&pdev->dev, "queue: %d, rear: %d, front: %d\n", + queue, pqueue->rear, pqueue->front); + ret = -EFAULT; + goto request_cleanup; + } + + pentry->completion_addr = info->completion_addr; + pentry->post_arg = (void *)info; + pentry->callback = req->callback; + pentry->callback_arg = req->callback_arg; + info->pentry = pentry; + pentry->busy = true; + atomic64_inc(&pqueue->pending_count); + + /* Send CPT command */ + info->pentry = pentry; + info->time_in = jiffies; + info->req = req; + + /* Create the CPT_INST_S type command for HW intrepretation */ + cptinst.s.doneint = true; + cptinst.s.res_addr = (u64)info->comp_baddr; + cptinst.s.tag = 0; + cptinst.s.grp = 0; + cptinst.s.wq_ptr = 0; + cptinst.s.ei0 = vq_cmd.cmd.u64; + cptinst.s.ei1 = vq_cmd.dptr; + cptinst.s.ei2 = vq_cmd.rptr; + cptinst.s.ei3 = vq_cmd.cptr.u64; + + ret = send_cpt_command(cptvf, &cptinst, queue); + spin_unlock_bh(&pqueue->lock); + if (unlikely(ret)) { + dev_err(&pdev->dev, "Send command failed for AE\n"); + ret = -EFAULT; + goto request_cleanup; + } + + return 0; + +request_cleanup: + dev_dbg(&pdev->dev, "Failed to submit CPT command\n"); + do_request_cleanup(cptvf, info); + + return ret; +} + +void vq_post_process(struct cpt_vf *cptvf, u32 qno) +{ + struct pci_dev *pdev = cptvf->pdev; + + if (unlikely(qno > cptvf->nr_queues)) { + dev_err(&pdev->dev, "Request for post processing on invalid pending queue: %u\n", + qno); + return; + } + + process_pending_queue(cptvf, &cptvf->pqinfo, qno); +} + +int cptvf_do_request(void *vfdev, struct cpt_request_info *req) +{ + struct cpt_vf *cptvf = (struct cpt_vf *)vfdev; + struct pci_dev *pdev = cptvf->pdev; + + if (!cpt_device_ready(cptvf)) { + dev_err(&pdev->dev, "CPT Device is not ready"); + return -ENODEV; + } + + if ((cptvf->vftype == SE_TYPES) && (!req->ctrl.s.se_req)) { + dev_err(&pdev->dev, "CPTVF-%d of SE TYPE got AE request", + cptvf->vfid); + return -EINVAL; + } else if ((cptvf->vftype == AE_TYPES) && (req->ctrl.s.se_req)) { + dev_err(&pdev->dev, "CPTVF-%d of AE TYPE got SE request", + cptvf->vfid); + return -EINVAL; + } + + return process_request(cptvf, req); +} -- cgit v1.2.3