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/virt/nitro_enclaves/ne_pci_dev.c | 626 +++++++++++++++++++++++++++++++ 1 file changed, 626 insertions(+) create mode 100644 drivers/virt/nitro_enclaves/ne_pci_dev.c (limited to 'drivers/virt/nitro_enclaves/ne_pci_dev.c') diff --git a/drivers/virt/nitro_enclaves/ne_pci_dev.c b/drivers/virt/nitro_enclaves/ne_pci_dev.c new file mode 100644 index 000000000..6b81e8f3a --- /dev/null +++ b/drivers/virt/nitro_enclaves/ne_pci_dev.c @@ -0,0 +1,626 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved. + */ + +/** + * DOC: Nitro Enclaves (NE) PCI device driver. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "ne_misc_dev.h" +#include "ne_pci_dev.h" + +/** + * NE_DEFAULT_TIMEOUT_MSECS - Default timeout to wait for a reply from + * the NE PCI device. + */ +#define NE_DEFAULT_TIMEOUT_MSECS (120000) /* 120 sec */ + +static const struct pci_device_id ne_pci_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, PCI_DEVICE_ID_NE) }, + { 0, } +}; + +MODULE_DEVICE_TABLE(pci, ne_pci_ids); + +/** + * ne_submit_request() - Submit command request to the PCI device based on the + * command type. + * @pdev: PCI device to send the command to. + * @cmd_type: Command type of the request sent to the PCI device. + * @cmd_request: Command request payload. + * @cmd_request_size: Size of the command request payload. + * + * Context: Process context. This function is called with the ne_pci_dev mutex held. + */ +static void ne_submit_request(struct pci_dev *pdev, enum ne_pci_dev_cmd_type cmd_type, + void *cmd_request, size_t cmd_request_size) +{ + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + + memcpy_toio(ne_pci_dev->iomem_base + NE_SEND_DATA, cmd_request, cmd_request_size); + + iowrite32(cmd_type, ne_pci_dev->iomem_base + NE_COMMAND); +} + +/** + * ne_retrieve_reply() - Retrieve reply from the PCI device. + * @pdev: PCI device to receive the reply from. + * @cmd_reply: Command reply payload. + * @cmd_reply_size: Size of the command reply payload. + * + * Context: Process context. This function is called with the ne_pci_dev mutex held. + */ +static void ne_retrieve_reply(struct pci_dev *pdev, struct ne_pci_dev_cmd_reply *cmd_reply, + size_t cmd_reply_size) +{ + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + + memcpy_fromio(cmd_reply, ne_pci_dev->iomem_base + NE_RECV_DATA, cmd_reply_size); +} + +/** + * ne_wait_for_reply() - Wait for a reply of a PCI device command. + * @pdev: PCI device for which a reply is waited. + * + * Context: Process context. This function is called with the ne_pci_dev mutex held. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_wait_for_reply(struct pci_dev *pdev) +{ + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + int rc = -EINVAL; + + /* + * TODO: Update to _interruptible and handle interrupted wait event + * e.g. -ERESTARTSYS, incoming signals + update timeout, if needed. + */ + rc = wait_event_timeout(ne_pci_dev->cmd_reply_wait_q, + atomic_read(&ne_pci_dev->cmd_reply_avail) != 0, + msecs_to_jiffies(NE_DEFAULT_TIMEOUT_MSECS)); + if (!rc) + return -ETIMEDOUT; + + return 0; +} + +int ne_do_request(struct pci_dev *pdev, enum ne_pci_dev_cmd_type cmd_type, + void *cmd_request, size_t cmd_request_size, + struct ne_pci_dev_cmd_reply *cmd_reply, size_t cmd_reply_size) +{ + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + int rc = -EINVAL; + + if (cmd_type <= INVALID_CMD || cmd_type >= MAX_CMD) { + dev_err_ratelimited(&pdev->dev, "Invalid cmd type=%u\n", cmd_type); + + return -EINVAL; + } + + if (!cmd_request) { + dev_err_ratelimited(&pdev->dev, "Null cmd request for cmd type=%u\n", + cmd_type); + + return -EINVAL; + } + + if (cmd_request_size > NE_SEND_DATA_SIZE) { + dev_err_ratelimited(&pdev->dev, "Invalid req size=%zu for cmd type=%u\n", + cmd_request_size, cmd_type); + + return -EINVAL; + } + + if (!cmd_reply) { + dev_err_ratelimited(&pdev->dev, "Null cmd reply for cmd type=%u\n", + cmd_type); + + return -EINVAL; + } + + if (cmd_reply_size > NE_RECV_DATA_SIZE) { + dev_err_ratelimited(&pdev->dev, "Invalid reply size=%zu for cmd type=%u\n", + cmd_reply_size, cmd_type); + + return -EINVAL; + } + + /* + * Use this mutex so that the PCI device handles one command request at + * a time. + */ + mutex_lock(&ne_pci_dev->pci_dev_mutex); + + atomic_set(&ne_pci_dev->cmd_reply_avail, 0); + + ne_submit_request(pdev, cmd_type, cmd_request, cmd_request_size); + + rc = ne_wait_for_reply(pdev); + if (rc < 0) { + dev_err_ratelimited(&pdev->dev, "Error in wait for reply for cmd type=%u [rc=%d]\n", + cmd_type, rc); + + goto unlock_mutex; + } + + ne_retrieve_reply(pdev, cmd_reply, cmd_reply_size); + + atomic_set(&ne_pci_dev->cmd_reply_avail, 0); + + if (cmd_reply->rc < 0) { + rc = cmd_reply->rc; + + dev_err_ratelimited(&pdev->dev, "Error in cmd process logic, cmd type=%u [rc=%d]\n", + cmd_type, rc); + + goto unlock_mutex; + } + + rc = 0; + +unlock_mutex: + mutex_unlock(&ne_pci_dev->pci_dev_mutex); + + return rc; +} + +/** + * ne_reply_handler() - Interrupt handler for retrieving a reply matching a + * request sent to the PCI device for enclave lifetime + * management. + * @irq: Received interrupt for a reply sent by the PCI device. + * @args: PCI device private data structure. + * + * Context: Interrupt context. + * Return: + * * IRQ_HANDLED on handled interrupt. + */ +static irqreturn_t ne_reply_handler(int irq, void *args) +{ + struct ne_pci_dev *ne_pci_dev = (struct ne_pci_dev *)args; + + atomic_set(&ne_pci_dev->cmd_reply_avail, 1); + + /* TODO: Update to _interruptible. */ + wake_up(&ne_pci_dev->cmd_reply_wait_q); + + return IRQ_HANDLED; +} + +/** + * ne_event_work_handler() - Work queue handler for notifying enclaves on a + * state change received by the event interrupt + * handler. + * @work: Item containing the NE PCI device for which an out-of-band event + * was issued. + * + * An out-of-band event is being issued by the Nitro Hypervisor when at least + * one enclave is changing state without client interaction. + * + * Context: Work queue context. + */ +static void ne_event_work_handler(struct work_struct *work) +{ + struct ne_pci_dev_cmd_reply cmd_reply = {}; + struct ne_enclave *ne_enclave = NULL; + struct ne_pci_dev *ne_pci_dev = + container_of(work, struct ne_pci_dev, notify_work); + struct pci_dev *pdev = ne_pci_dev->pdev; + int rc = -EINVAL; + struct slot_info_req slot_info_req = {}; + + mutex_lock(&ne_pci_dev->enclaves_list_mutex); + + /* + * Iterate over all enclaves registered for the Nitro Enclaves + * PCI device and determine for which enclave(s) the out-of-band event + * is corresponding to. + */ + list_for_each_entry(ne_enclave, &ne_pci_dev->enclaves_list, enclave_list_entry) { + mutex_lock(&ne_enclave->enclave_info_mutex); + + /* + * Enclaves that were never started cannot receive out-of-band + * events. + */ + if (ne_enclave->state != NE_STATE_RUNNING) + goto unlock; + + slot_info_req.slot_uid = ne_enclave->slot_uid; + + rc = ne_do_request(pdev, SLOT_INFO, + &slot_info_req, sizeof(slot_info_req), + &cmd_reply, sizeof(cmd_reply)); + if (rc < 0) + dev_err(&pdev->dev, "Error in slot info [rc=%d]\n", rc); + + /* Notify enclave process that the enclave state changed. */ + if (ne_enclave->state != cmd_reply.state) { + ne_enclave->state = cmd_reply.state; + + ne_enclave->has_event = true; + + wake_up_interruptible(&ne_enclave->eventq); + } + +unlock: + mutex_unlock(&ne_enclave->enclave_info_mutex); + } + + mutex_unlock(&ne_pci_dev->enclaves_list_mutex); +} + +/** + * ne_event_handler() - Interrupt handler for PCI device out-of-band events. + * This interrupt does not supply any data in the MMIO + * region. It notifies a change in the state of any of + * the launched enclaves. + * @irq: Received interrupt for an out-of-band event. + * @args: PCI device private data structure. + * + * Context: Interrupt context. + * Return: + * * IRQ_HANDLED on handled interrupt. + */ +static irqreturn_t ne_event_handler(int irq, void *args) +{ + struct ne_pci_dev *ne_pci_dev = (struct ne_pci_dev *)args; + + queue_work(ne_pci_dev->event_wq, &ne_pci_dev->notify_work); + + return IRQ_HANDLED; +} + +/** + * ne_setup_msix() - Setup MSI-X vectors for the PCI device. + * @pdev: PCI device to setup the MSI-X for. + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_setup_msix(struct pci_dev *pdev) +{ + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + int nr_vecs = 0; + int rc = -EINVAL; + + nr_vecs = pci_msix_vec_count(pdev); + if (nr_vecs < 0) { + rc = nr_vecs; + + dev_err(&pdev->dev, "Error in getting vec count [rc=%d]\n", rc); + + return rc; + } + + rc = pci_alloc_irq_vectors(pdev, nr_vecs, nr_vecs, PCI_IRQ_MSIX); + if (rc < 0) { + dev_err(&pdev->dev, "Error in alloc MSI-X vecs [rc=%d]\n", rc); + + return rc; + } + + /* + * This IRQ gets triggered every time the PCI device responds to a + * command request. The reply is then retrieved, reading from the MMIO + * space of the PCI device. + */ + rc = request_irq(pci_irq_vector(pdev, NE_VEC_REPLY), ne_reply_handler, + 0, "enclave_cmd", ne_pci_dev); + if (rc < 0) { + dev_err(&pdev->dev, "Error in request irq reply [rc=%d]\n", rc); + + goto free_irq_vectors; + } + + ne_pci_dev->event_wq = create_singlethread_workqueue("ne_pci_dev_wq"); + if (!ne_pci_dev->event_wq) { + rc = -ENOMEM; + + dev_err(&pdev->dev, "Cannot get wq for dev events [rc=%d]\n", rc); + + goto free_reply_irq_vec; + } + + INIT_WORK(&ne_pci_dev->notify_work, ne_event_work_handler); + + /* + * This IRQ gets triggered every time any enclave's state changes. Its + * handler then scans for the changes and propagates them to the user + * space. + */ + rc = request_irq(pci_irq_vector(pdev, NE_VEC_EVENT), ne_event_handler, + 0, "enclave_evt", ne_pci_dev); + if (rc < 0) { + dev_err(&pdev->dev, "Error in request irq event [rc=%d]\n", rc); + + goto destroy_wq; + } + + return 0; + +destroy_wq: + destroy_workqueue(ne_pci_dev->event_wq); +free_reply_irq_vec: + free_irq(pci_irq_vector(pdev, NE_VEC_REPLY), ne_pci_dev); +free_irq_vectors: + pci_free_irq_vectors(pdev); + + return rc; +} + +/** + * ne_teardown_msix() - Teardown MSI-X vectors for the PCI device. + * @pdev: PCI device to teardown the MSI-X for. + * + * Context: Process context. + */ +static void ne_teardown_msix(struct pci_dev *pdev) +{ + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + + free_irq(pci_irq_vector(pdev, NE_VEC_EVENT), ne_pci_dev); + + flush_work(&ne_pci_dev->notify_work); + destroy_workqueue(ne_pci_dev->event_wq); + + free_irq(pci_irq_vector(pdev, NE_VEC_REPLY), ne_pci_dev); + + pci_free_irq_vectors(pdev); +} + +/** + * ne_pci_dev_enable() - Select the PCI device version and enable it. + * @pdev: PCI device to select version for and then enable. + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_pci_dev_enable(struct pci_dev *pdev) +{ + u8 dev_enable_reply = 0; + u16 dev_version_reply = 0; + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + + iowrite16(NE_VERSION_MAX, ne_pci_dev->iomem_base + NE_VERSION); + + dev_version_reply = ioread16(ne_pci_dev->iomem_base + NE_VERSION); + if (dev_version_reply != NE_VERSION_MAX) { + dev_err(&pdev->dev, "Error in pci dev version cmd\n"); + + return -EIO; + } + + iowrite8(NE_ENABLE_ON, ne_pci_dev->iomem_base + NE_ENABLE); + + dev_enable_reply = ioread8(ne_pci_dev->iomem_base + NE_ENABLE); + if (dev_enable_reply != NE_ENABLE_ON) { + dev_err(&pdev->dev, "Error in pci dev enable cmd\n"); + + return -EIO; + } + + return 0; +} + +/** + * ne_pci_dev_disable() - Disable the PCI device. + * @pdev: PCI device to disable. + * + * Context: Process context. + */ +static void ne_pci_dev_disable(struct pci_dev *pdev) +{ + u8 dev_disable_reply = 0; + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + const unsigned int sleep_time = 10; /* 10 ms */ + unsigned int sleep_time_count = 0; + + iowrite8(NE_ENABLE_OFF, ne_pci_dev->iomem_base + NE_ENABLE); + + /* + * Check for NE_ENABLE_OFF in a loop, to handle cases when the device + * state is not immediately set to disabled and going through a + * transitory state of disabling. + */ + while (sleep_time_count < NE_DEFAULT_TIMEOUT_MSECS) { + dev_disable_reply = ioread8(ne_pci_dev->iomem_base + NE_ENABLE); + if (dev_disable_reply == NE_ENABLE_OFF) + return; + + msleep_interruptible(sleep_time); + sleep_time_count += sleep_time; + } + + dev_disable_reply = ioread8(ne_pci_dev->iomem_base + NE_ENABLE); + if (dev_disable_reply != NE_ENABLE_OFF) + dev_err(&pdev->dev, "Error in pci dev disable cmd\n"); +} + +/** + * ne_pci_probe() - Probe function for the NE PCI device. + * @pdev: PCI device to match with the NE PCI driver. + * @id : PCI device id table associated with the NE PCI driver. + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct ne_pci_dev *ne_pci_dev = NULL; + int rc = -EINVAL; + + ne_pci_dev = kzalloc(sizeof(*ne_pci_dev), GFP_KERNEL); + if (!ne_pci_dev) + return -ENOMEM; + + rc = pci_enable_device(pdev); + if (rc < 0) { + dev_err(&pdev->dev, "Error in pci dev enable [rc=%d]\n", rc); + + goto free_ne_pci_dev; + } + + pci_set_master(pdev); + + rc = pci_request_regions_exclusive(pdev, "nitro_enclaves"); + if (rc < 0) { + dev_err(&pdev->dev, "Error in pci request regions [rc=%d]\n", rc); + + goto disable_pci_dev; + } + + ne_pci_dev->iomem_base = pci_iomap(pdev, PCI_BAR_NE, 0); + if (!ne_pci_dev->iomem_base) { + rc = -ENOMEM; + + dev_err(&pdev->dev, "Error in pci iomap [rc=%d]\n", rc); + + goto release_pci_regions; + } + + pci_set_drvdata(pdev, ne_pci_dev); + + rc = ne_setup_msix(pdev); + if (rc < 0) { + dev_err(&pdev->dev, "Error in pci dev msix setup [rc=%d]\n", rc); + + goto iounmap_pci_bar; + } + + ne_pci_dev_disable(pdev); + + rc = ne_pci_dev_enable(pdev); + if (rc < 0) { + dev_err(&pdev->dev, "Error in ne_pci_dev enable [rc=%d]\n", rc); + + goto teardown_msix; + } + + atomic_set(&ne_pci_dev->cmd_reply_avail, 0); + init_waitqueue_head(&ne_pci_dev->cmd_reply_wait_q); + INIT_LIST_HEAD(&ne_pci_dev->enclaves_list); + mutex_init(&ne_pci_dev->enclaves_list_mutex); + mutex_init(&ne_pci_dev->pci_dev_mutex); + ne_pci_dev->pdev = pdev; + + ne_devs.ne_pci_dev = ne_pci_dev; + + rc = misc_register(ne_devs.ne_misc_dev); + if (rc < 0) { + dev_err(&pdev->dev, "Error in misc dev register [rc=%d]\n", rc); + + goto disable_ne_pci_dev; + } + + return 0; + +disable_ne_pci_dev: + ne_devs.ne_pci_dev = NULL; + ne_pci_dev_disable(pdev); +teardown_msix: + ne_teardown_msix(pdev); +iounmap_pci_bar: + pci_set_drvdata(pdev, NULL); + pci_iounmap(pdev, ne_pci_dev->iomem_base); +release_pci_regions: + pci_release_regions(pdev); +disable_pci_dev: + pci_disable_device(pdev); +free_ne_pci_dev: + kfree(ne_pci_dev); + + return rc; +} + +/** + * ne_pci_remove() - Remove function for the NE PCI device. + * @pdev: PCI device associated with the NE PCI driver. + * + * Context: Process context. + */ +static void ne_pci_remove(struct pci_dev *pdev) +{ + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + + misc_deregister(ne_devs.ne_misc_dev); + + ne_devs.ne_pci_dev = NULL; + + ne_pci_dev_disable(pdev); + + ne_teardown_msix(pdev); + + pci_set_drvdata(pdev, NULL); + + pci_iounmap(pdev, ne_pci_dev->iomem_base); + + pci_release_regions(pdev); + + pci_disable_device(pdev); + + kfree(ne_pci_dev); +} + +/** + * ne_pci_shutdown() - Shutdown function for the NE PCI device. + * @pdev: PCI device associated with the NE PCI driver. + * + * Context: Process context. + */ +static void ne_pci_shutdown(struct pci_dev *pdev) +{ + struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev); + + if (!ne_pci_dev) + return; + + misc_deregister(ne_devs.ne_misc_dev); + + ne_devs.ne_pci_dev = NULL; + + ne_pci_dev_disable(pdev); + + ne_teardown_msix(pdev); + + pci_set_drvdata(pdev, NULL); + + pci_iounmap(pdev, ne_pci_dev->iomem_base); + + pci_release_regions(pdev); + + pci_disable_device(pdev); + + kfree(ne_pci_dev); +} + +/* + * TODO: Add suspend / resume functions for power management w/ CONFIG_PM, if + * needed. + */ +/* NE PCI device driver. */ +struct pci_driver ne_pci_driver = { + .name = "nitro_enclaves", + .id_table = ne_pci_ids, + .probe = ne_pci_probe, + .remove = ne_pci_remove, + .shutdown = ne_pci_shutdown, +}; -- cgit v1.2.3