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/vfio/pci/vfio_pci_core.c | 2572 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 2572 insertions(+) create mode 100644 drivers/vfio/pci/vfio_pci_core.c (limited to 'drivers/vfio/pci/vfio_pci_core.c') diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c new file mode 100644 index 000000000..26a541cc6 --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -0,0 +1,2572 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson + * + * Derived from original vfio: + * Copyright 2010 Cisco Systems, Inc. All rights reserved. + * Author: Tom Lyon, pugs@cisco.com + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#if IS_ENABLED(CONFIG_EEH) +#include +#endif + +#include "vfio_pci_priv.h" + +#define DRIVER_AUTHOR "Alex Williamson " +#define DRIVER_DESC "core driver for VFIO based PCI devices" + +static bool nointxmask; +static bool disable_vga; +static bool disable_idle_d3; + +/* List of PF's that vfio_pci_core_sriov_configure() has been called on */ +static DEFINE_MUTEX(vfio_pci_sriov_pfs_mutex); +static LIST_HEAD(vfio_pci_sriov_pfs); + +struct vfio_pci_dummy_resource { + struct resource resource; + int index; + struct list_head res_next; +}; + +struct vfio_pci_vf_token { + struct mutex lock; + uuid_t uuid; + int users; +}; + +struct vfio_pci_mmap_vma { + struct vm_area_struct *vma; + struct list_head vma_next; +}; + +static inline bool vfio_vga_disabled(void) +{ +#ifdef CONFIG_VFIO_PCI_VGA + return disable_vga; +#else + return true; +#endif +} + +/* + * Our VGA arbiter participation is limited since we don't know anything + * about the device itself. However, if the device is the only VGA device + * downstream of a bridge and VFIO VGA support is disabled, then we can + * safely return legacy VGA IO and memory as not decoded since the user + * has no way to get to it and routing can be disabled externally at the + * bridge. + */ +static unsigned int vfio_pci_set_decode(struct pci_dev *pdev, bool single_vga) +{ + struct pci_dev *tmp = NULL; + unsigned char max_busnr; + unsigned int decodes; + + if (single_vga || !vfio_vga_disabled() || pci_is_root_bus(pdev->bus)) + return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM | + VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; + + max_busnr = pci_bus_max_busnr(pdev->bus); + decodes = VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM; + + while ((tmp = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, tmp)) != NULL) { + if (tmp == pdev || + pci_domain_nr(tmp->bus) != pci_domain_nr(pdev->bus) || + pci_is_root_bus(tmp->bus)) + continue; + + if (tmp->bus->number >= pdev->bus->number && + tmp->bus->number <= max_busnr) { + pci_dev_put(tmp); + decodes |= VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; + break; + } + } + + return decodes; +} + +static void vfio_pci_probe_mmaps(struct vfio_pci_core_device *vdev) +{ + struct resource *res; + int i; + struct vfio_pci_dummy_resource *dummy_res; + + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + int bar = i + PCI_STD_RESOURCES; + + res = &vdev->pdev->resource[bar]; + + if (!IS_ENABLED(CONFIG_VFIO_PCI_MMAP)) + goto no_mmap; + + if (!(res->flags & IORESOURCE_MEM)) + goto no_mmap; + + /* + * The PCI core shouldn't set up a resource with a + * type but zero size. But there may be bugs that + * cause us to do that. + */ + if (!resource_size(res)) + goto no_mmap; + + if (resource_size(res) >= PAGE_SIZE) { + vdev->bar_mmap_supported[bar] = true; + continue; + } + + if (!(res->start & ~PAGE_MASK)) { + /* + * Add a dummy resource to reserve the remainder + * of the exclusive page in case that hot-add + * device's bar is assigned into it. + */ + dummy_res = kzalloc(sizeof(*dummy_res), GFP_KERNEL); + if (dummy_res == NULL) + goto no_mmap; + + dummy_res->resource.name = "vfio sub-page reserved"; + dummy_res->resource.start = res->end + 1; + dummy_res->resource.end = res->start + PAGE_SIZE - 1; + dummy_res->resource.flags = res->flags; + if (request_resource(res->parent, + &dummy_res->resource)) { + kfree(dummy_res); + goto no_mmap; + } + dummy_res->index = bar; + list_add(&dummy_res->res_next, + &vdev->dummy_resources_list); + vdev->bar_mmap_supported[bar] = true; + continue; + } + /* + * Here we don't handle the case when the BAR is not page + * aligned because we can't expect the BAR will be + * assigned into the same location in a page in guest + * when we passthrough the BAR. And it's hard to access + * this BAR in userspace because we have no way to get + * the BAR's location in a page. + */ +no_mmap: + vdev->bar_mmap_supported[bar] = false; + } +} + +struct vfio_pci_group_info; +static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set); +static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, + struct vfio_pci_group_info *groups); + +/* + * INTx masking requires the ability to disable INTx signaling via PCI_COMMAND + * _and_ the ability detect when the device is asserting INTx via PCI_STATUS. + * If a device implements the former but not the latter we would typically + * expect broken_intx_masking be set and require an exclusive interrupt. + * However since we do have control of the device's ability to assert INTx, + * we can instead pretend that the device does not implement INTx, virtualizing + * the pin register to report zero and maintaining DisINTx set on the host. + */ +static bool vfio_pci_nointx(struct pci_dev *pdev) +{ + switch (pdev->vendor) { + case PCI_VENDOR_ID_INTEL: + switch (pdev->device) { + /* All i40e (XL710/X710/XXV710) 10/20/25/40GbE NICs */ + case 0x1572: + case 0x1574: + case 0x1580 ... 0x1581: + case 0x1583 ... 0x158b: + case 0x37d0 ... 0x37d2: + /* X550 */ + case 0x1563: + return true; + default: + return false; + } + } + + return false; +} + +static void vfio_pci_probe_power_state(struct vfio_pci_core_device *vdev) +{ + struct pci_dev *pdev = vdev->pdev; + u16 pmcsr; + + if (!pdev->pm_cap) + return; + + pci_read_config_word(pdev, pdev->pm_cap + PCI_PM_CTRL, &pmcsr); + + vdev->needs_pm_restore = !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET); +} + +/* + * pci_set_power_state() wrapper handling devices which perform a soft reset on + * D3->D0 transition. Save state prior to D0/1/2->D3, stash it on the vdev, + * restore when returned to D0. Saved separately from pci_saved_state for use + * by PM capability emulation and separately from pci_dev internal saved state + * to avoid it being overwritten and consumed around other resets. + */ +int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t state) +{ + struct pci_dev *pdev = vdev->pdev; + bool needs_restore = false, needs_save = false; + int ret; + + /* Prevent changing power state for PFs with VFs enabled */ + if (pci_num_vf(pdev) && state > PCI_D0) + return -EBUSY; + + if (vdev->needs_pm_restore) { + if (pdev->current_state < PCI_D3hot && state >= PCI_D3hot) { + pci_save_state(pdev); + needs_save = true; + } + + if (pdev->current_state >= PCI_D3hot && state <= PCI_D0) + needs_restore = true; + } + + ret = pci_set_power_state(pdev, state); + + if (!ret) { + /* D3 might be unsupported via quirk, skip unless in D3 */ + if (needs_save && pdev->current_state >= PCI_D3hot) { + /* + * The current PCI state will be saved locally in + * 'pm_save' during the D3hot transition. When the + * device state is changed to D0 again with the current + * function, then pci_store_saved_state() will restore + * the state and will free the memory pointed by + * 'pm_save'. There are few cases where the PCI power + * state can be changed to D0 without the involvement + * of the driver. For these cases, free the earlier + * allocated memory first before overwriting 'pm_save' + * to prevent the memory leak. + */ + kfree(vdev->pm_save); + vdev->pm_save = pci_store_saved_state(pdev); + } else if (needs_restore) { + pci_load_and_free_saved_state(pdev, &vdev->pm_save); + pci_restore_state(pdev); + } + } + + return ret; +} + +static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev, + struct eventfd_ctx *efdctx) +{ + /* + * The vdev power related flags are protected with 'memory_lock' + * semaphore. + */ + vfio_pci_zap_and_down_write_memory_lock(vdev); + if (vdev->pm_runtime_engaged) { + up_write(&vdev->memory_lock); + return -EINVAL; + } + + vdev->pm_runtime_engaged = true; + vdev->pm_wake_eventfd_ctx = efdctx; + pm_runtime_put_noidle(&vdev->pdev->dev); + up_write(&vdev->memory_lock); + + return 0; +} + +static int vfio_pci_core_pm_entry(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz) +{ + struct vfio_pci_core_device *vdev = + container_of(device, struct vfio_pci_core_device, vdev); + int ret; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0); + if (ret != 1) + return ret; + + /* + * Inside vfio_pci_runtime_pm_entry(), only the runtime PM usage count + * will be decremented. The pm_runtime_put() will be invoked again + * while returning from the ioctl and then the device can go into + * runtime suspended state. + */ + return vfio_pci_runtime_pm_entry(vdev, NULL); +} + +static int vfio_pci_core_pm_entry_with_wakeup( + struct vfio_device *device, u32 flags, + struct vfio_device_low_power_entry_with_wakeup __user *arg, + size_t argsz) +{ + struct vfio_pci_core_device *vdev = + container_of(device, struct vfio_pci_core_device, vdev); + struct vfio_device_low_power_entry_with_wakeup entry; + struct eventfd_ctx *efdctx; + int ret; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, + sizeof(entry)); + if (ret != 1) + return ret; + + if (copy_from_user(&entry, arg, sizeof(entry))) + return -EFAULT; + + if (entry.wakeup_eventfd < 0) + return -EINVAL; + + efdctx = eventfd_ctx_fdget(entry.wakeup_eventfd); + if (IS_ERR(efdctx)) + return PTR_ERR(efdctx); + + ret = vfio_pci_runtime_pm_entry(vdev, efdctx); + if (ret) + eventfd_ctx_put(efdctx); + + return ret; +} + +static void __vfio_pci_runtime_pm_exit(struct vfio_pci_core_device *vdev) +{ + if (vdev->pm_runtime_engaged) { + vdev->pm_runtime_engaged = false; + pm_runtime_get_noresume(&vdev->pdev->dev); + + if (vdev->pm_wake_eventfd_ctx) { + eventfd_ctx_put(vdev->pm_wake_eventfd_ctx); + vdev->pm_wake_eventfd_ctx = NULL; + } + } +} + +static void vfio_pci_runtime_pm_exit(struct vfio_pci_core_device *vdev) +{ + /* + * The vdev power related flags are protected with 'memory_lock' + * semaphore. + */ + down_write(&vdev->memory_lock); + __vfio_pci_runtime_pm_exit(vdev); + up_write(&vdev->memory_lock); +} + +static int vfio_pci_core_pm_exit(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz) +{ + struct vfio_pci_core_device *vdev = + container_of(device, struct vfio_pci_core_device, vdev); + int ret; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0); + if (ret != 1) + return ret; + + /* + * The device is always in the active state here due to pm wrappers + * around ioctls. If the device had entered a low power state and + * pm_wake_eventfd_ctx is valid, vfio_pci_core_runtime_resume() has + * already signaled the eventfd and exited low power mode itself. + * pm_runtime_engaged protects the redundant call here. + */ + vfio_pci_runtime_pm_exit(vdev); + return 0; +} + +#ifdef CONFIG_PM +static int vfio_pci_core_runtime_suspend(struct device *dev) +{ + struct vfio_pci_core_device *vdev = dev_get_drvdata(dev); + + down_write(&vdev->memory_lock); + /* + * The user can move the device into D3hot state before invoking + * power management IOCTL. Move the device into D0 state here and then + * the pci-driver core runtime PM suspend function will move the device + * into the low power state. Also, for the devices which have + * NoSoftRst-, it will help in restoring the original state + * (saved locally in 'vdev->pm_save'). + */ + vfio_pci_set_power_state(vdev, PCI_D0); + up_write(&vdev->memory_lock); + + /* + * If INTx is enabled, then mask INTx before going into the runtime + * suspended state and unmask the same in the runtime resume. + * If INTx has already been masked by the user, then + * vfio_pci_intx_mask() will return false and in that case, INTx + * should not be unmasked in the runtime resume. + */ + vdev->pm_intx_masked = ((vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) && + vfio_pci_intx_mask(vdev)); + + return 0; +} + +static int vfio_pci_core_runtime_resume(struct device *dev) +{ + struct vfio_pci_core_device *vdev = dev_get_drvdata(dev); + + /* + * Resume with a pm_wake_eventfd_ctx signals the eventfd and exit + * low power mode. + */ + down_write(&vdev->memory_lock); + if (vdev->pm_wake_eventfd_ctx) { + eventfd_signal(vdev->pm_wake_eventfd_ctx, 1); + __vfio_pci_runtime_pm_exit(vdev); + } + up_write(&vdev->memory_lock); + + if (vdev->pm_intx_masked) + vfio_pci_intx_unmask(vdev); + + return 0; +} +#endif /* CONFIG_PM */ + +/* + * The pci-driver core runtime PM routines always save the device state + * before going into suspended state. If the device is going into low power + * state with only with runtime PM ops, then no explicit handling is needed + * for the devices which have NoSoftRst-. + */ +static const struct dev_pm_ops vfio_pci_core_pm_ops = { + SET_RUNTIME_PM_OPS(vfio_pci_core_runtime_suspend, + vfio_pci_core_runtime_resume, + NULL) +}; + +int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) +{ + struct pci_dev *pdev = vdev->pdev; + int ret; + u16 cmd; + u8 msix_pos; + + if (!disable_idle_d3) { + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret < 0) + return ret; + } + + /* Don't allow our initial saved state to include busmaster */ + pci_clear_master(pdev); + + ret = pci_enable_device(pdev); + if (ret) + goto out_power; + + /* If reset fails because of the device lock, fail this path entirely */ + ret = pci_try_reset_function(pdev); + if (ret == -EAGAIN) + goto out_disable_device; + + vdev->reset_works = !ret; + pci_save_state(pdev); + vdev->pci_saved_state = pci_store_saved_state(pdev); + if (!vdev->pci_saved_state) + pci_dbg(pdev, "%s: Couldn't store saved state\n", __func__); + + if (likely(!nointxmask)) { + if (vfio_pci_nointx(pdev)) { + pci_info(pdev, "Masking broken INTx support\n"); + vdev->nointx = true; + pci_intx(pdev, 0); + } else + vdev->pci_2_3 = pci_intx_mask_supported(pdev); + } + + pci_read_config_word(pdev, PCI_COMMAND, &cmd); + if (vdev->pci_2_3 && (cmd & PCI_COMMAND_INTX_DISABLE)) { + cmd &= ~PCI_COMMAND_INTX_DISABLE; + pci_write_config_word(pdev, PCI_COMMAND, cmd); + } + + ret = vfio_pci_zdev_open_device(vdev); + if (ret) + goto out_free_state; + + ret = vfio_config_init(vdev); + if (ret) + goto out_free_zdev; + + msix_pos = pdev->msix_cap; + if (msix_pos) { + u16 flags; + u32 table; + + pci_read_config_word(pdev, msix_pos + PCI_MSIX_FLAGS, &flags); + pci_read_config_dword(pdev, msix_pos + PCI_MSIX_TABLE, &table); + + vdev->msix_bar = table & PCI_MSIX_TABLE_BIR; + vdev->msix_offset = table & PCI_MSIX_TABLE_OFFSET; + vdev->msix_size = ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) * 16; + } else + vdev->msix_bar = 0xFF; + + if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev)) + vdev->has_vga = true; + + + return 0; + +out_free_zdev: + vfio_pci_zdev_close_device(vdev); +out_free_state: + kfree(vdev->pci_saved_state); + vdev->pci_saved_state = NULL; +out_disable_device: + pci_disable_device(pdev); +out_power: + if (!disable_idle_d3) + pm_runtime_put(&pdev->dev); + return ret; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_enable); + +void vfio_pci_core_disable(struct vfio_pci_core_device *vdev) +{ + struct pci_dev *pdev = vdev->pdev; + struct vfio_pci_dummy_resource *dummy_res, *tmp; + struct vfio_pci_ioeventfd *ioeventfd, *ioeventfd_tmp; + int i, bar; + + /* For needs_reset */ + lockdep_assert_held(&vdev->vdev.dev_set->lock); + + /* + * This function can be invoked while the power state is non-D0. + * This non-D0 power state can be with or without runtime PM. + * vfio_pci_runtime_pm_exit() will internally increment the usage + * count corresponding to pm_runtime_put() called during low power + * feature entry and then pm_runtime_resume() will wake up the device, + * if the device has already gone into the suspended state. Otherwise, + * the vfio_pci_set_power_state() will change the device power state + * to D0. + */ + vfio_pci_runtime_pm_exit(vdev); + pm_runtime_resume(&pdev->dev); + + /* + * This function calls __pci_reset_function_locked() which internally + * can use pci_pm_reset() for the function reset. pci_pm_reset() will + * fail if the power state is non-D0. Also, for the devices which + * have NoSoftRst-, the reset function can cause the PCI config space + * reset without restoring the original state (saved locally in + * 'vdev->pm_save'). + */ + vfio_pci_set_power_state(vdev, PCI_D0); + + /* Stop the device from further DMA */ + pci_clear_master(pdev); + + vfio_pci_set_irqs_ioctl(vdev, VFIO_IRQ_SET_DATA_NONE | + VFIO_IRQ_SET_ACTION_TRIGGER, + vdev->irq_type, 0, 0, NULL); + + /* Device closed, don't need mutex here */ + list_for_each_entry_safe(ioeventfd, ioeventfd_tmp, + &vdev->ioeventfds_list, next) { + vfio_virqfd_disable(&ioeventfd->virqfd); + list_del(&ioeventfd->next); + kfree(ioeventfd); + } + vdev->ioeventfds_nr = 0; + + vdev->virq_disabled = false; + + for (i = 0; i < vdev->num_regions; i++) + vdev->region[i].ops->release(vdev, &vdev->region[i]); + + vdev->num_regions = 0; + kfree(vdev->region); + vdev->region = NULL; /* don't krealloc a freed pointer */ + + vfio_config_free(vdev); + + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + bar = i + PCI_STD_RESOURCES; + if (!vdev->barmap[bar]) + continue; + pci_iounmap(pdev, vdev->barmap[bar]); + pci_release_selected_regions(pdev, 1 << bar); + vdev->barmap[bar] = NULL; + } + + list_for_each_entry_safe(dummy_res, tmp, + &vdev->dummy_resources_list, res_next) { + list_del(&dummy_res->res_next); + release_resource(&dummy_res->resource); + kfree(dummy_res); + } + + vdev->needs_reset = true; + + vfio_pci_zdev_close_device(vdev); + + /* + * If we have saved state, restore it. If we can reset the device, + * even better. Resetting with current state seems better than + * nothing, but saving and restoring current state without reset + * is just busy work. + */ + if (pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state)) { + pci_info(pdev, "%s: Couldn't reload saved state\n", __func__); + + if (!vdev->reset_works) + goto out; + + pci_save_state(pdev); + } + + /* + * Disable INTx and MSI, presumably to avoid spurious interrupts + * during reset. Stolen from pci_reset_function() + */ + pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE); + + /* + * Try to get the locks ourselves to prevent a deadlock. The + * success of this is dependent on being able to lock the device, + * which is not always possible. + * We can not use the "try" reset interface here, which will + * overwrite the previously restored configuration information. + */ + if (vdev->reset_works && pci_dev_trylock(pdev)) { + if (!__pci_reset_function_locked(pdev)) + vdev->needs_reset = false; + pci_dev_unlock(pdev); + } + + pci_restore_state(pdev); +out: + pci_disable_device(pdev); + + vfio_pci_dev_set_try_reset(vdev->vdev.dev_set); + + /* Put the pm-runtime usage counter acquired during enable */ + if (!disable_idle_d3) + pm_runtime_put(&pdev->dev); +} +EXPORT_SYMBOL_GPL(vfio_pci_core_disable); + +void vfio_pci_core_close_device(struct vfio_device *core_vdev) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + WARN_ON(!vdev->sriov_pf_core_dev->vf_token->users); + vdev->sriov_pf_core_dev->vf_token->users--; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } +#if IS_ENABLED(CONFIG_EEH) + eeh_dev_release(vdev->pdev); +#endif + vfio_pci_core_disable(vdev); + + mutex_lock(&vdev->igate); + if (vdev->err_trigger) { + eventfd_ctx_put(vdev->err_trigger); + vdev->err_trigger = NULL; + } + if (vdev->req_trigger) { + eventfd_ctx_put(vdev->req_trigger); + vdev->req_trigger = NULL; + } + mutex_unlock(&vdev->igate); +} +EXPORT_SYMBOL_GPL(vfio_pci_core_close_device); + +void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev) +{ + vfio_pci_probe_mmaps(vdev); +#if IS_ENABLED(CONFIG_EEH) + eeh_dev_open(vdev->pdev); +#endif + + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + vdev->sriov_pf_core_dev->vf_token->users++; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } +} +EXPORT_SYMBOL_GPL(vfio_pci_core_finish_enable); + +static int vfio_pci_get_irq_count(struct vfio_pci_core_device *vdev, int irq_type) +{ + if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) { + u8 pin; + + if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || + vdev->nointx || vdev->pdev->is_virtfn) + return 0; + + pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin); + + return pin ? 1 : 0; + } else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) { + u8 pos; + u16 flags; + + pos = vdev->pdev->msi_cap; + if (pos) { + pci_read_config_word(vdev->pdev, + pos + PCI_MSI_FLAGS, &flags); + return 1 << ((flags & PCI_MSI_FLAGS_QMASK) >> 1); + } + } else if (irq_type == VFIO_PCI_MSIX_IRQ_INDEX) { + u8 pos; + u16 flags; + + pos = vdev->pdev->msix_cap; + if (pos) { + pci_read_config_word(vdev->pdev, + pos + PCI_MSIX_FLAGS, &flags); + + return (flags & PCI_MSIX_FLAGS_QSIZE) + 1; + } + } else if (irq_type == VFIO_PCI_ERR_IRQ_INDEX) { + if (pci_is_pcie(vdev->pdev)) + return 1; + } else if (irq_type == VFIO_PCI_REQ_IRQ_INDEX) { + return 1; + } + + return 0; +} + +static int vfio_pci_count_devs(struct pci_dev *pdev, void *data) +{ + (*(int *)data)++; + return 0; +} + +struct vfio_pci_fill_info { + int max; + int cur; + struct vfio_pci_dependent_device *devices; +}; + +static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data) +{ + struct vfio_pci_fill_info *fill = data; + struct iommu_group *iommu_group; + + if (fill->cur == fill->max) + return -EAGAIN; /* Something changed, try again */ + + iommu_group = iommu_group_get(&pdev->dev); + if (!iommu_group) + return -EPERM; /* Cannot reset non-isolated devices */ + + fill->devices[fill->cur].group_id = iommu_group_id(iommu_group); + fill->devices[fill->cur].segment = pci_domain_nr(pdev->bus); + fill->devices[fill->cur].bus = pdev->bus->number; + fill->devices[fill->cur].devfn = pdev->devfn; + fill->cur++; + iommu_group_put(iommu_group); + return 0; +} + +struct vfio_pci_group_info { + int count; + struct file **files; +}; + +static bool vfio_pci_dev_below_slot(struct pci_dev *pdev, struct pci_slot *slot) +{ + for (; pdev; pdev = pdev->bus->self) + if (pdev->bus == slot->bus) + return (pdev->slot == slot); + return false; +} + +struct vfio_pci_walk_info { + int (*fn)(struct pci_dev *pdev, void *data); + void *data; + struct pci_dev *pdev; + bool slot; + int ret; +}; + +static int vfio_pci_walk_wrapper(struct pci_dev *pdev, void *data) +{ + struct vfio_pci_walk_info *walk = data; + + if (!walk->slot || vfio_pci_dev_below_slot(pdev, walk->pdev->slot)) + walk->ret = walk->fn(pdev, walk->data); + + return walk->ret; +} + +static int vfio_pci_for_each_slot_or_bus(struct pci_dev *pdev, + int (*fn)(struct pci_dev *, + void *data), void *data, + bool slot) +{ + struct vfio_pci_walk_info walk = { + .fn = fn, .data = data, .pdev = pdev, .slot = slot, .ret = 0, + }; + + pci_walk_bus(pdev->bus, vfio_pci_walk_wrapper, &walk); + + return walk.ret; +} + +static int msix_mmappable_cap(struct vfio_pci_core_device *vdev, + struct vfio_info_cap *caps) +{ + struct vfio_info_cap_header header = { + .id = VFIO_REGION_INFO_CAP_MSIX_MAPPABLE, + .version = 1 + }; + + return vfio_info_add_capability(caps, &header, sizeof(header)); +} + +int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, + unsigned int type, unsigned int subtype, + const struct vfio_pci_regops *ops, + size_t size, u32 flags, void *data) +{ + struct vfio_pci_region *region; + + region = krealloc(vdev->region, + (vdev->num_regions + 1) * sizeof(*region), + GFP_KERNEL); + if (!region) + return -ENOMEM; + + vdev->region = region; + vdev->region[vdev->num_regions].type = type; + vdev->region[vdev->num_regions].subtype = subtype; + vdev->region[vdev->num_regions].ops = ops; + vdev->region[vdev->num_regions].size = size; + vdev->region[vdev->num_regions].flags = flags; + vdev->region[vdev->num_regions].data = data; + + vdev->num_regions++; + + return 0; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_register_dev_region); + +static int vfio_pci_ioctl_get_info(struct vfio_pci_core_device *vdev, + struct vfio_device_info __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_device_info, num_irqs); + struct vfio_device_info info; + struct vfio_info_cap caps = { .buf = NULL, .size = 0 }; + unsigned long capsz; + int ret; + + /* For backward compatibility, cannot require this */ + capsz = offsetofend(struct vfio_iommu_type1_info, cap_offset); + + if (copy_from_user(&info, arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + + if (info.argsz >= capsz) { + minsz = capsz; + info.cap_offset = 0; + } + + info.flags = VFIO_DEVICE_FLAGS_PCI; + + if (vdev->reset_works) + info.flags |= VFIO_DEVICE_FLAGS_RESET; + + info.num_regions = VFIO_PCI_NUM_REGIONS + vdev->num_regions; + info.num_irqs = VFIO_PCI_NUM_IRQS; + + ret = vfio_pci_info_zdev_add_caps(vdev, &caps); + if (ret && ret != -ENODEV) { + pci_warn(vdev->pdev, + "Failed to setup zPCI info capabilities\n"); + return ret; + } + + if (caps.size) { + info.flags |= VFIO_DEVICE_FLAGS_CAPS; + if (info.argsz < sizeof(info) + caps.size) { + info.argsz = sizeof(info) + caps.size; + } else { + vfio_info_cap_shift(&caps, sizeof(info)); + if (copy_to_user(arg + 1, caps.buf, caps.size)) { + kfree(caps.buf); + return -EFAULT; + } + info.cap_offset = sizeof(*arg); + } + + kfree(caps.buf); + } + + return copy_to_user(arg, &info, minsz) ? -EFAULT : 0; +} + +static int vfio_pci_ioctl_get_region_info(struct vfio_pci_core_device *vdev, + struct vfio_region_info __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_region_info, offset); + struct pci_dev *pdev = vdev->pdev; + struct vfio_region_info info; + struct vfio_info_cap caps = { .buf = NULL, .size = 0 }; + int i, ret; + + if (copy_from_user(&info, arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + + switch (info.index) { + case VFIO_PCI_CONFIG_REGION_INDEX: + info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); + info.size = pdev->cfg_size; + info.flags = VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE; + break; + case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX: + info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); + info.size = pci_resource_len(pdev, info.index); + if (!info.size) { + info.flags = 0; + break; + } + + info.flags = VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE; + if (vdev->bar_mmap_supported[info.index]) { + info.flags |= VFIO_REGION_INFO_FLAG_MMAP; + if (info.index == vdev->msix_bar) { + ret = msix_mmappable_cap(vdev, &caps); + if (ret) + return ret; + } + } + + break; + case VFIO_PCI_ROM_REGION_INDEX: { + void __iomem *io; + size_t size; + u16 cmd; + + info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); + info.flags = 0; + + /* Report the BAR size, not the ROM size */ + info.size = pci_resource_len(pdev, info.index); + if (!info.size) { + /* Shadow ROMs appear as PCI option ROMs */ + if (pdev->resource[PCI_ROM_RESOURCE].flags & + IORESOURCE_ROM_SHADOW) + info.size = 0x20000; + else + break; + } + + /* + * Is it really there? Enable memory decode for implicit access + * in pci_map_rom(). + */ + cmd = vfio_pci_memory_lock_and_enable(vdev); + io = pci_map_rom(pdev, &size); + if (io) { + info.flags = VFIO_REGION_INFO_FLAG_READ; + pci_unmap_rom(pdev, io); + } else { + info.size = 0; + } + vfio_pci_memory_unlock_and_restore(vdev, cmd); + + break; + } + case VFIO_PCI_VGA_REGION_INDEX: + if (!vdev->has_vga) + return -EINVAL; + + info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); + info.size = 0xc0000; + info.flags = VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE; + + break; + default: { + struct vfio_region_info_cap_type cap_type = { + .header.id = VFIO_REGION_INFO_CAP_TYPE, + .header.version = 1 + }; + + if (info.index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions) + return -EINVAL; + info.index = array_index_nospec( + info.index, VFIO_PCI_NUM_REGIONS + vdev->num_regions); + + i = info.index - VFIO_PCI_NUM_REGIONS; + + info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); + info.size = vdev->region[i].size; + info.flags = vdev->region[i].flags; + + cap_type.type = vdev->region[i].type; + cap_type.subtype = vdev->region[i].subtype; + + ret = vfio_info_add_capability(&caps, &cap_type.header, + sizeof(cap_type)); + if (ret) + return ret; + + if (vdev->region[i].ops->add_capability) { + ret = vdev->region[i].ops->add_capability( + vdev, &vdev->region[i], &caps); + if (ret) + return ret; + } + } + } + + if (caps.size) { + info.flags |= VFIO_REGION_INFO_FLAG_CAPS; + if (info.argsz < sizeof(info) + caps.size) { + info.argsz = sizeof(info) + caps.size; + info.cap_offset = 0; + } else { + vfio_info_cap_shift(&caps, sizeof(info)); + if (copy_to_user(arg + 1, caps.buf, caps.size)) { + kfree(caps.buf); + return -EFAULT; + } + info.cap_offset = sizeof(*arg); + } + + kfree(caps.buf); + } + + return copy_to_user(arg, &info, minsz) ? -EFAULT : 0; +} + +static int vfio_pci_ioctl_get_irq_info(struct vfio_pci_core_device *vdev, + struct vfio_irq_info __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_irq_info, count); + struct vfio_irq_info info; + + if (copy_from_user(&info, arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz || info.index >= VFIO_PCI_NUM_IRQS) + return -EINVAL; + + switch (info.index) { + case VFIO_PCI_INTX_IRQ_INDEX ... VFIO_PCI_MSIX_IRQ_INDEX: + case VFIO_PCI_REQ_IRQ_INDEX: + break; + case VFIO_PCI_ERR_IRQ_INDEX: + if (pci_is_pcie(vdev->pdev)) + break; + fallthrough; + default: + return -EINVAL; + } + + info.flags = VFIO_IRQ_INFO_EVENTFD; + + info.count = vfio_pci_get_irq_count(vdev, info.index); + + if (info.index == VFIO_PCI_INTX_IRQ_INDEX) + info.flags |= + (VFIO_IRQ_INFO_MASKABLE | VFIO_IRQ_INFO_AUTOMASKED); + else + info.flags |= VFIO_IRQ_INFO_NORESIZE; + + return copy_to_user(arg, &info, minsz) ? -EFAULT : 0; +} + +static int vfio_pci_ioctl_set_irqs(struct vfio_pci_core_device *vdev, + struct vfio_irq_set __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_irq_set, count); + struct vfio_irq_set hdr; + u8 *data = NULL; + int max, ret = 0; + size_t data_size = 0; + + if (copy_from_user(&hdr, arg, minsz)) + return -EFAULT; + + max = vfio_pci_get_irq_count(vdev, hdr.index); + + ret = vfio_set_irqs_validate_and_prepare(&hdr, max, VFIO_PCI_NUM_IRQS, + &data_size); + if (ret) + return ret; + + if (data_size) { + data = memdup_user(&arg->data, data_size); + if (IS_ERR(data)) + return PTR_ERR(data); + } + + mutex_lock(&vdev->igate); + + ret = vfio_pci_set_irqs_ioctl(vdev, hdr.flags, hdr.index, hdr.start, + hdr.count, data); + + mutex_unlock(&vdev->igate); + kfree(data); + + return ret; +} + +static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev, + void __user *arg) +{ + int ret; + + if (!vdev->reset_works) + return -EINVAL; + + vfio_pci_zap_and_down_write_memory_lock(vdev); + + /* + * This function can be invoked while the power state is non-D0. If + * pci_try_reset_function() has been called while the power state is + * non-D0, then pci_try_reset_function() will internally set the power + * state to D0 without vfio driver involvement. For the devices which + * have NoSoftRst-, the reset function can cause the PCI config space + * reset without restoring the original state (saved locally in + * 'vdev->pm_save'). + */ + vfio_pci_set_power_state(vdev, PCI_D0); + + ret = pci_try_reset_function(vdev->pdev); + up_write(&vdev->memory_lock); + + return ret; +} + +static int vfio_pci_ioctl_get_pci_hot_reset_info( + struct vfio_pci_core_device *vdev, + struct vfio_pci_hot_reset_info __user *arg) +{ + unsigned long minsz = + offsetofend(struct vfio_pci_hot_reset_info, count); + struct vfio_pci_hot_reset_info hdr; + struct vfio_pci_fill_info fill = { 0 }; + struct vfio_pci_dependent_device *devices = NULL; + bool slot = false; + int ret = 0; + + if (copy_from_user(&hdr, arg, minsz)) + return -EFAULT; + + if (hdr.argsz < minsz) + return -EINVAL; + + hdr.flags = 0; + + /* Can we do a slot or bus reset or neither? */ + if (!pci_probe_reset_slot(vdev->pdev->slot)) + slot = true; + else if (pci_probe_reset_bus(vdev->pdev->bus)) + return -ENODEV; + + /* How many devices are affected? */ + ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs, + &fill.max, slot); + if (ret) + return ret; + + WARN_ON(!fill.max); /* Should always be at least one */ + + /* + * If there's enough space, fill it now, otherwise return -ENOSPC and + * the number of devices affected. + */ + if (hdr.argsz < sizeof(hdr) + (fill.max * sizeof(*devices))) { + ret = -ENOSPC; + hdr.count = fill.max; + goto reset_info_exit; + } + + devices = kcalloc(fill.max, sizeof(*devices), GFP_KERNEL); + if (!devices) + return -ENOMEM; + + fill.devices = devices; + + ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_fill_devs, + &fill, slot); + + /* + * If a device was removed between counting and filling, we may come up + * short of fill.max. If a device was added, we'll have a return of + * -EAGAIN above. + */ + if (!ret) + hdr.count = fill.cur; + +reset_info_exit: + if (copy_to_user(arg, &hdr, minsz)) + ret = -EFAULT; + + if (!ret) { + if (copy_to_user(&arg->devices, devices, + hdr.count * sizeof(*devices))) + ret = -EFAULT; + } + + kfree(devices); + return ret; +} + +static int vfio_pci_ioctl_pci_hot_reset(struct vfio_pci_core_device *vdev, + struct vfio_pci_hot_reset __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_pci_hot_reset, count); + struct vfio_pci_hot_reset hdr; + int32_t *group_fds; + struct file **files; + struct vfio_pci_group_info info; + bool slot = false; + int file_idx, count = 0, ret = 0; + + if (copy_from_user(&hdr, arg, minsz)) + return -EFAULT; + + if (hdr.argsz < minsz || hdr.flags) + return -EINVAL; + + /* Can we do a slot or bus reset or neither? */ + if (!pci_probe_reset_slot(vdev->pdev->slot)) + slot = true; + else if (pci_probe_reset_bus(vdev->pdev->bus)) + return -ENODEV; + + /* + * We can't let userspace give us an arbitrarily large buffer to copy, + * so verify how many we think there could be. Note groups can have + * multiple devices so one group per device is the max. + */ + ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs, + &count, slot); + if (ret) + return ret; + + /* Somewhere between 1 and count is OK */ + if (!hdr.count || hdr.count > count) + return -EINVAL; + + group_fds = kcalloc(hdr.count, sizeof(*group_fds), GFP_KERNEL); + files = kcalloc(hdr.count, sizeof(*files), GFP_KERNEL); + if (!group_fds || !files) { + kfree(group_fds); + kfree(files); + return -ENOMEM; + } + + if (copy_from_user(group_fds, arg->group_fds, + hdr.count * sizeof(*group_fds))) { + kfree(group_fds); + kfree(files); + return -EFAULT; + } + + /* + * For each group_fd, get the group through the vfio external user + * interface and store the group and iommu ID. This ensures the group + * is held across the reset. + */ + for (file_idx = 0; file_idx < hdr.count; file_idx++) { + struct file *file = fget(group_fds[file_idx]); + + if (!file) { + ret = -EBADF; + break; + } + + /* Ensure the FD is a vfio group FD.*/ + if (!vfio_file_is_group(file)) { + fput(file); + ret = -EINVAL; + break; + } + + files[file_idx] = file; + } + + kfree(group_fds); + + /* release reference to groups on error */ + if (ret) + goto hot_reset_release; + + info.count = hdr.count; + info.files = files; + + ret = vfio_pci_dev_set_hot_reset(vdev->vdev.dev_set, &info); + +hot_reset_release: + for (file_idx--; file_idx >= 0; file_idx--) + fput(files[file_idx]); + + kfree(files); + return ret; +} + +static int vfio_pci_ioctl_ioeventfd(struct vfio_pci_core_device *vdev, + struct vfio_device_ioeventfd __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_device_ioeventfd, fd); + struct vfio_device_ioeventfd ioeventfd; + int count; + + if (copy_from_user(&ioeventfd, arg, minsz)) + return -EFAULT; + + if (ioeventfd.argsz < minsz) + return -EINVAL; + + if (ioeventfd.flags & ~VFIO_DEVICE_IOEVENTFD_SIZE_MASK) + return -EINVAL; + + count = ioeventfd.flags & VFIO_DEVICE_IOEVENTFD_SIZE_MASK; + + if (hweight8(count) != 1 || ioeventfd.fd < -1) + return -EINVAL; + + return vfio_pci_ioeventfd(vdev, ioeventfd.offset, ioeventfd.data, count, + ioeventfd.fd); +} + +long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, + unsigned long arg) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + void __user *uarg = (void __user *)arg; + + switch (cmd) { + case VFIO_DEVICE_GET_INFO: + return vfio_pci_ioctl_get_info(vdev, uarg); + case VFIO_DEVICE_GET_IRQ_INFO: + return vfio_pci_ioctl_get_irq_info(vdev, uarg); + case VFIO_DEVICE_GET_PCI_HOT_RESET_INFO: + return vfio_pci_ioctl_get_pci_hot_reset_info(vdev, uarg); + case VFIO_DEVICE_GET_REGION_INFO: + return vfio_pci_ioctl_get_region_info(vdev, uarg); + case VFIO_DEVICE_IOEVENTFD: + return vfio_pci_ioctl_ioeventfd(vdev, uarg); + case VFIO_DEVICE_PCI_HOT_RESET: + return vfio_pci_ioctl_pci_hot_reset(vdev, uarg); + case VFIO_DEVICE_RESET: + return vfio_pci_ioctl_reset(vdev, uarg); + case VFIO_DEVICE_SET_IRQS: + return vfio_pci_ioctl_set_irqs(vdev, uarg); + default: + return -ENOTTY; + } +} +EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl); + +static int vfio_pci_core_feature_token(struct vfio_device *device, u32 flags, + uuid_t __user *arg, size_t argsz) +{ + struct vfio_pci_core_device *vdev = + container_of(device, struct vfio_pci_core_device, vdev); + uuid_t uuid; + int ret; + + if (!vdev->vf_token) + return -ENOTTY; + /* + * We do not support GET of the VF Token UUID as this could + * expose the token of the previous device user. + */ + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, + sizeof(uuid)); + if (ret != 1) + return ret; + + if (copy_from_user(&uuid, arg, sizeof(uuid))) + return -EFAULT; + + mutex_lock(&vdev->vf_token->lock); + uuid_copy(&vdev->vf_token->uuid, &uuid); + mutex_unlock(&vdev->vf_token->lock); + return 0; +} + +int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz) +{ + switch (flags & VFIO_DEVICE_FEATURE_MASK) { + case VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY: + return vfio_pci_core_pm_entry(device, flags, arg, argsz); + case VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP: + return vfio_pci_core_pm_entry_with_wakeup(device, flags, + arg, argsz); + case VFIO_DEVICE_FEATURE_LOW_POWER_EXIT: + return vfio_pci_core_pm_exit(device, flags, arg, argsz); + case VFIO_DEVICE_FEATURE_PCI_VF_TOKEN: + return vfio_pci_core_feature_token(device, flags, arg, argsz); + default: + return -ENOTTY; + } +} +EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl_feature); + +static ssize_t vfio_pci_rw(struct vfio_pci_core_device *vdev, char __user *buf, + size_t count, loff_t *ppos, bool iswrite) +{ + unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos); + int ret; + + if (index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions) + return -EINVAL; + + ret = pm_runtime_resume_and_get(&vdev->pdev->dev); + if (ret) { + pci_info_ratelimited(vdev->pdev, "runtime resume failed %d\n", + ret); + return -EIO; + } + + switch (index) { + case VFIO_PCI_CONFIG_REGION_INDEX: + ret = vfio_pci_config_rw(vdev, buf, count, ppos, iswrite); + break; + + case VFIO_PCI_ROM_REGION_INDEX: + if (iswrite) + ret = -EINVAL; + else + ret = vfio_pci_bar_rw(vdev, buf, count, ppos, false); + break; + + case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX: + ret = vfio_pci_bar_rw(vdev, buf, count, ppos, iswrite); + break; + + case VFIO_PCI_VGA_REGION_INDEX: + ret = vfio_pci_vga_rw(vdev, buf, count, ppos, iswrite); + break; + + default: + index -= VFIO_PCI_NUM_REGIONS; + ret = vdev->region[index].ops->rw(vdev, buf, + count, ppos, iswrite); + break; + } + + pm_runtime_put(&vdev->pdev->dev); + return ret; +} + +ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, + size_t count, loff_t *ppos) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + + if (!count) + return 0; + + return vfio_pci_rw(vdev, buf, count, ppos, false); +} +EXPORT_SYMBOL_GPL(vfio_pci_core_read); + +ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + + if (!count) + return 0; + + return vfio_pci_rw(vdev, (char __user *)buf, count, ppos, true); +} +EXPORT_SYMBOL_GPL(vfio_pci_core_write); + +/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */ +static int vfio_pci_zap_and_vma_lock(struct vfio_pci_core_device *vdev, bool try) +{ + struct vfio_pci_mmap_vma *mmap_vma, *tmp; + + /* + * Lock ordering: + * vma_lock is nested under mmap_lock for vm_ops callback paths. + * The memory_lock semaphore is used by both code paths calling + * into this function to zap vmas and the vm_ops.fault callback + * to protect the memory enable state of the device. + * + * When zapping vmas we need to maintain the mmap_lock => vma_lock + * ordering, which requires using vma_lock to walk vma_list to + * acquire an mm, then dropping vma_lock to get the mmap_lock and + * reacquiring vma_lock. This logic is derived from similar + * requirements in uverbs_user_mmap_disassociate(). + * + * mmap_lock must always be the top-level lock when it is taken. + * Therefore we can only hold the memory_lock write lock when + * vma_list is empty, as we'd need to take mmap_lock to clear + * entries. vma_list can only be guaranteed empty when holding + * vma_lock, thus memory_lock is nested under vma_lock. + * + * This enables the vm_ops.fault callback to acquire vma_lock, + * followed by memory_lock read lock, while already holding + * mmap_lock without risk of deadlock. + */ + while (1) { + struct mm_struct *mm = NULL; + + if (try) { + if (!mutex_trylock(&vdev->vma_lock)) + return 0; + } else { + mutex_lock(&vdev->vma_lock); + } + while (!list_empty(&vdev->vma_list)) { + mmap_vma = list_first_entry(&vdev->vma_list, + struct vfio_pci_mmap_vma, + vma_next); + mm = mmap_vma->vma->vm_mm; + if (mmget_not_zero(mm)) + break; + + list_del(&mmap_vma->vma_next); + kfree(mmap_vma); + mm = NULL; + } + if (!mm) + return 1; + mutex_unlock(&vdev->vma_lock); + + if (try) { + if (!mmap_read_trylock(mm)) { + mmput(mm); + return 0; + } + } else { + mmap_read_lock(mm); + } + if (try) { + if (!mutex_trylock(&vdev->vma_lock)) { + mmap_read_unlock(mm); + mmput(mm); + return 0; + } + } else { + mutex_lock(&vdev->vma_lock); + } + list_for_each_entry_safe(mmap_vma, tmp, + &vdev->vma_list, vma_next) { + struct vm_area_struct *vma = mmap_vma->vma; + + if (vma->vm_mm != mm) + continue; + + list_del(&mmap_vma->vma_next); + kfree(mmap_vma); + + zap_vma_ptes(vma, vma->vm_start, + vma->vm_end - vma->vm_start); + } + mutex_unlock(&vdev->vma_lock); + mmap_read_unlock(mm); + mmput(mm); + } +} + +void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev) +{ + vfio_pci_zap_and_vma_lock(vdev, false); + down_write(&vdev->memory_lock); + mutex_unlock(&vdev->vma_lock); +} + +u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev) +{ + u16 cmd; + + down_write(&vdev->memory_lock); + pci_read_config_word(vdev->pdev, PCI_COMMAND, &cmd); + if (!(cmd & PCI_COMMAND_MEMORY)) + pci_write_config_word(vdev->pdev, PCI_COMMAND, + cmd | PCI_COMMAND_MEMORY); + + return cmd; +} + +void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, u16 cmd) +{ + pci_write_config_word(vdev->pdev, PCI_COMMAND, cmd); + up_write(&vdev->memory_lock); +} + +/* Caller holds vma_lock */ +static int __vfio_pci_add_vma(struct vfio_pci_core_device *vdev, + struct vm_area_struct *vma) +{ + struct vfio_pci_mmap_vma *mmap_vma; + + mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL); + if (!mmap_vma) + return -ENOMEM; + + mmap_vma->vma = vma; + list_add(&mmap_vma->vma_next, &vdev->vma_list); + + return 0; +} + +/* + * Zap mmaps on open so that we can fault them in on access and therefore + * our vma_list only tracks mappings accessed since last zap. + */ +static void vfio_pci_mmap_open(struct vm_area_struct *vma) +{ + zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); +} + +static void vfio_pci_mmap_close(struct vm_area_struct *vma) +{ + struct vfio_pci_core_device *vdev = vma->vm_private_data; + struct vfio_pci_mmap_vma *mmap_vma; + + mutex_lock(&vdev->vma_lock); + list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { + if (mmap_vma->vma == vma) { + list_del(&mmap_vma->vma_next); + kfree(mmap_vma); + break; + } + } + mutex_unlock(&vdev->vma_lock); +} + +static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct vfio_pci_core_device *vdev = vma->vm_private_data; + struct vfio_pci_mmap_vma *mmap_vma; + vm_fault_t ret = VM_FAULT_NOPAGE; + + mutex_lock(&vdev->vma_lock); + down_read(&vdev->memory_lock); + + /* + * Memory region cannot be accessed if the low power feature is engaged + * or memory access is disabled. + */ + if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) { + ret = VM_FAULT_SIGBUS; + goto up_out; + } + + /* + * We populate the whole vma on fault, so we need to test whether + * the vma has already been mapped, such as for concurrent faults + * to the same vma. io_remap_pfn_range() will trigger a BUG_ON if + * we ask it to fill the same range again. + */ + list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { + if (mmap_vma->vma == vma) + goto up_out; + } + + if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + vma->vm_end - vma->vm_start, + vma->vm_page_prot)) { + ret = VM_FAULT_SIGBUS; + zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); + goto up_out; + } + + if (__vfio_pci_add_vma(vdev, vma)) { + ret = VM_FAULT_OOM; + zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); + } + +up_out: + up_read(&vdev->memory_lock); + mutex_unlock(&vdev->vma_lock); + return ret; +} + +static const struct vm_operations_struct vfio_pci_mmap_ops = { + .open = vfio_pci_mmap_open, + .close = vfio_pci_mmap_close, + .fault = vfio_pci_mmap_fault, +}; + +int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + struct pci_dev *pdev = vdev->pdev; + unsigned int index; + u64 phys_len, req_len, pgoff, req_start; + int ret; + + index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT); + + if (index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions) + return -EINVAL; + if (vma->vm_end < vma->vm_start) + return -EINVAL; + if ((vma->vm_flags & VM_SHARED) == 0) + return -EINVAL; + if (index >= VFIO_PCI_NUM_REGIONS) { + int regnum = index - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_region *region = vdev->region + regnum; + + if (region->ops && region->ops->mmap && + (region->flags & VFIO_REGION_INFO_FLAG_MMAP)) + return region->ops->mmap(vdev, region, vma); + return -EINVAL; + } + if (index >= VFIO_PCI_ROM_REGION_INDEX) + return -EINVAL; + if (!vdev->bar_mmap_supported[index]) + return -EINVAL; + + phys_len = PAGE_ALIGN(pci_resource_len(pdev, index)); + req_len = vma->vm_end - vma->vm_start; + pgoff = vma->vm_pgoff & + ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1); + req_start = pgoff << PAGE_SHIFT; + + if (req_start + req_len > phys_len) + return -EINVAL; + + /* + * Even though we don't make use of the barmap for the mmap, + * we need to request the region and the barmap tracks that. + */ + if (!vdev->barmap[index]) { + ret = pci_request_selected_regions(pdev, + 1 << index, "vfio-pci"); + if (ret) + return ret; + + vdev->barmap[index] = pci_iomap(pdev, index, 0); + if (!vdev->barmap[index]) { + pci_release_selected_regions(pdev, 1 << index); + return -ENOMEM; + } + } + + vma->vm_private_data = vdev; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff; + + /* + * See remap_pfn_range(), called from vfio_pci_fault() but we can't + * change vm_flags within the fault handler. Set them now. + */ + vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_ops = &vfio_pci_mmap_ops; + + return 0; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_mmap); + +void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + struct pci_dev *pdev = vdev->pdev; + + mutex_lock(&vdev->igate); + + if (vdev->req_trigger) { + if (!(count % 10)) + pci_notice_ratelimited(pdev, + "Relaying device request to user (#%u)\n", + count); + eventfd_signal(vdev->req_trigger, 1); + } else if (count == 0) { + pci_warn(pdev, + "No device request channel registered, blocked until released by user\n"); + } + + mutex_unlock(&vdev->igate); +} +EXPORT_SYMBOL_GPL(vfio_pci_core_request); + +static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, + bool vf_token, uuid_t *uuid) +{ + /* + * There's always some degree of trust or collaboration between SR-IOV + * PF and VFs, even if just that the PF hosts the SR-IOV capability and + * can disrupt VFs with a reset, but often the PF has more explicit + * access to deny service to the VF or access data passed through the + * VF. We therefore require an opt-in via a shared VF token (UUID) to + * represent this trust. This both prevents that a VF driver might + * assume the PF driver is a trusted, in-kernel driver, and also that + * a PF driver might be replaced with a rogue driver, unknown to in-use + * VF drivers. + * + * Therefore when presented with a VF, if the PF is a vfio device and + * it is bound to the vfio-pci driver, the user needs to provide a VF + * token to access the device, in the form of appending a vf_token to + * the device name, for example: + * + * "0000:04:10.0 vf_token=bd8d9d2b-5a5f-4f5a-a211-f591514ba1f3" + * + * When presented with a PF which has VFs in use, the user must also + * provide the current VF token to prove collaboration with existing + * VF users. If VFs are not in use, the VF token provided for the PF + * device will act to set the VF token. + * + * If the VF token is provided but unused, an error is generated. + */ + if (vdev->pdev->is_virtfn) { + struct vfio_pci_core_device *pf_vdev = vdev->sriov_pf_core_dev; + bool match; + + if (!pf_vdev) { + if (!vf_token) + return 0; /* PF is not vfio-pci, no VF token */ + + pci_info_ratelimited(vdev->pdev, + "VF token incorrectly provided, PF not bound to vfio-pci\n"); + return -EINVAL; + } + + if (!vf_token) { + pci_info_ratelimited(vdev->pdev, + "VF token required to access device\n"); + return -EACCES; + } + + mutex_lock(&pf_vdev->vf_token->lock); + match = uuid_equal(uuid, &pf_vdev->vf_token->uuid); + mutex_unlock(&pf_vdev->vf_token->lock); + + if (!match) { + pci_info_ratelimited(vdev->pdev, + "Incorrect VF token provided for device\n"); + return -EACCES; + } + } else if (vdev->vf_token) { + mutex_lock(&vdev->vf_token->lock); + if (vdev->vf_token->users) { + if (!vf_token) { + mutex_unlock(&vdev->vf_token->lock); + pci_info_ratelimited(vdev->pdev, + "VF token required to access device\n"); + return -EACCES; + } + + if (!uuid_equal(uuid, &vdev->vf_token->uuid)) { + mutex_unlock(&vdev->vf_token->lock); + pci_info_ratelimited(vdev->pdev, + "Incorrect VF token provided for device\n"); + return -EACCES; + } + } else if (vf_token) { + uuid_copy(&vdev->vf_token->uuid, uuid); + } + + mutex_unlock(&vdev->vf_token->lock); + } else if (vf_token) { + pci_info_ratelimited(vdev->pdev, + "VF token incorrectly provided, not a PF or VF\n"); + return -EINVAL; + } + + return 0; +} + +#define VF_TOKEN_ARG "vf_token=" + +int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + bool vf_token = false; + uuid_t uuid; + int ret; + + if (strncmp(pci_name(vdev->pdev), buf, strlen(pci_name(vdev->pdev)))) + return 0; /* No match */ + + if (strlen(buf) > strlen(pci_name(vdev->pdev))) { + buf += strlen(pci_name(vdev->pdev)); + + if (*buf != ' ') + return 0; /* No match: non-whitespace after name */ + + while (*buf) { + if (*buf == ' ') { + buf++; + continue; + } + + if (!vf_token && !strncmp(buf, VF_TOKEN_ARG, + strlen(VF_TOKEN_ARG))) { + buf += strlen(VF_TOKEN_ARG); + + if (strlen(buf) < UUID_STRING_LEN) + return -EINVAL; + + ret = uuid_parse(buf, &uuid); + if (ret) + return ret; + + vf_token = true; + buf += UUID_STRING_LEN; + } else { + /* Unknown/duplicate option */ + return -EINVAL; + } + } + } + + ret = vfio_pci_validate_vf_token(vdev, vf_token, &uuid); + if (ret) + return ret; + + return 1; /* Match */ +} +EXPORT_SYMBOL_GPL(vfio_pci_core_match); + +static int vfio_pci_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct vfio_pci_core_device *vdev = container_of(nb, + struct vfio_pci_core_device, nb); + struct device *dev = data; + struct pci_dev *pdev = to_pci_dev(dev); + struct pci_dev *physfn = pci_physfn(pdev); + + if (action == BUS_NOTIFY_ADD_DEVICE && + pdev->is_virtfn && physfn == vdev->pdev) { + pci_info(vdev->pdev, "Captured SR-IOV VF %s driver_override\n", + pci_name(pdev)); + pdev->driver_override = kasprintf(GFP_KERNEL, "%s", + vdev->vdev.ops->name); + } else if (action == BUS_NOTIFY_BOUND_DRIVER && + pdev->is_virtfn && physfn == vdev->pdev) { + struct pci_driver *drv = pci_dev_driver(pdev); + + if (drv && drv != pci_dev_driver(vdev->pdev)) + pci_warn(vdev->pdev, + "VF %s bound to driver %s while PF bound to driver %s\n", + pci_name(pdev), drv->name, + pci_dev_driver(vdev->pdev)->name); + } + + return 0; +} + +static int vfio_pci_vf_init(struct vfio_pci_core_device *vdev) +{ + struct pci_dev *pdev = vdev->pdev; + struct vfio_pci_core_device *cur; + struct pci_dev *physfn; + int ret; + + if (pdev->is_virtfn) { + /* + * If this VF was created by our vfio_pci_core_sriov_configure() + * then we can find the PF vfio_pci_core_device now, and due to + * the locking in pci_disable_sriov() it cannot change until + * this VF device driver is removed. + */ + physfn = pci_physfn(vdev->pdev); + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_for_each_entry(cur, &vfio_pci_sriov_pfs, sriov_pfs_item) { + if (cur->pdev == physfn) { + vdev->sriov_pf_core_dev = cur; + break; + } + } + mutex_unlock(&vfio_pci_sriov_pfs_mutex); + return 0; + } + + /* Not a SRIOV PF */ + if (!pdev->is_physfn) + return 0; + + vdev->vf_token = kzalloc(sizeof(*vdev->vf_token), GFP_KERNEL); + if (!vdev->vf_token) + return -ENOMEM; + + mutex_init(&vdev->vf_token->lock); + uuid_gen(&vdev->vf_token->uuid); + + vdev->nb.notifier_call = vfio_pci_bus_notifier; + ret = bus_register_notifier(&pci_bus_type, &vdev->nb); + if (ret) { + kfree(vdev->vf_token); + return ret; + } + return 0; +} + +static void vfio_pci_vf_uninit(struct vfio_pci_core_device *vdev) +{ + if (!vdev->vf_token) + return; + + bus_unregister_notifier(&pci_bus_type, &vdev->nb); + WARN_ON(vdev->vf_token->users); + mutex_destroy(&vdev->vf_token->lock); + kfree(vdev->vf_token); +} + +static int vfio_pci_vga_init(struct vfio_pci_core_device *vdev) +{ + struct pci_dev *pdev = vdev->pdev; + int ret; + + if (!vfio_pci_is_vga(pdev)) + return 0; + + ret = aperture_remove_conflicting_pci_devices(pdev, vdev->vdev.ops->name); + if (ret) + return ret; + + ret = vga_client_register(pdev, vfio_pci_set_decode); + if (ret) + return ret; + vga_set_legacy_decoding(pdev, vfio_pci_set_decode(pdev, false)); + return 0; +} + +static void vfio_pci_vga_uninit(struct vfio_pci_core_device *vdev) +{ + struct pci_dev *pdev = vdev->pdev; + + if (!vfio_pci_is_vga(pdev)) + return; + vga_client_unregister(pdev); + vga_set_legacy_decoding(pdev, VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM | + VGA_RSRC_LEGACY_IO | + VGA_RSRC_LEGACY_MEM); +} + +int vfio_pci_core_init_dev(struct vfio_device *core_vdev) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + + vdev->pdev = to_pci_dev(core_vdev->dev); + vdev->irq_type = VFIO_PCI_NUM_IRQS; + mutex_init(&vdev->igate); + spin_lock_init(&vdev->irqlock); + mutex_init(&vdev->ioeventfds_lock); + INIT_LIST_HEAD(&vdev->dummy_resources_list); + INIT_LIST_HEAD(&vdev->ioeventfds_list); + mutex_init(&vdev->vma_lock); + INIT_LIST_HEAD(&vdev->vma_list); + INIT_LIST_HEAD(&vdev->sriov_pfs_item); + init_rwsem(&vdev->memory_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_init_dev); + +void vfio_pci_core_release_dev(struct vfio_device *core_vdev) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + + mutex_destroy(&vdev->igate); + mutex_destroy(&vdev->ioeventfds_lock); + mutex_destroy(&vdev->vma_lock); + kfree(vdev->region); + kfree(vdev->pm_save); +} +EXPORT_SYMBOL_GPL(vfio_pci_core_release_dev); + +int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) +{ + struct pci_dev *pdev = vdev->pdev; + struct device *dev = &pdev->dev; + int ret; + + /* Drivers must set the vfio_pci_core_device to their drvdata */ + if (WARN_ON(vdev != dev_get_drvdata(dev))) + return -EINVAL; + + if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) + return -EINVAL; + + if (vdev->vdev.mig_ops) { + if (!(vdev->vdev.mig_ops->migration_get_state && + vdev->vdev.mig_ops->migration_set_state && + vdev->vdev.mig_ops->migration_get_data_size) || + !(vdev->vdev.migration_flags & VFIO_MIGRATION_STOP_COPY)) + return -EINVAL; + } + + if (vdev->vdev.log_ops && !(vdev->vdev.log_ops->log_start && + vdev->vdev.log_ops->log_stop && + vdev->vdev.log_ops->log_read_and_clear)) + return -EINVAL; + + /* + * Prevent binding to PFs with VFs enabled, the VFs might be in use + * by the host or other users. We cannot capture the VFs if they + * already exist, nor can we track VF users. Disabling SR-IOV here + * would initiate removing the VFs, which would unbind the driver, + * which is prone to blocking if that VF is also in use by vfio-pci. + * Just reject these PFs and let the user sort it out. + */ + if (pci_num_vf(pdev)) { + pci_warn(pdev, "Cannot bind to PF with SR-IOV enabled\n"); + return -EBUSY; + } + + if (pci_is_root_bus(pdev->bus)) { + ret = vfio_assign_device_set(&vdev->vdev, vdev); + } else if (!pci_probe_reset_slot(pdev->slot)) { + ret = vfio_assign_device_set(&vdev->vdev, pdev->slot); + } else { + /* + * If there is no slot reset support for this device, the whole + * bus needs to be grouped together to support bus-wide resets. + */ + ret = vfio_assign_device_set(&vdev->vdev, pdev->bus); + } + + if (ret) + return ret; + ret = vfio_pci_vf_init(vdev); + if (ret) + return ret; + ret = vfio_pci_vga_init(vdev); + if (ret) + goto out_vf; + + vfio_pci_probe_power_state(vdev); + + /* + * pci-core sets the device power state to an unknown value at + * bootup and after being removed from a driver. The only + * transition it allows from this unknown state is to D0, which + * typically happens when a driver calls pci_enable_device(). + * We're not ready to enable the device yet, but we do want to + * be able to get to D3. Therefore first do a D0 transition + * before enabling runtime PM. + */ + vfio_pci_set_power_state(vdev, PCI_D0); + + dev->driver->pm = &vfio_pci_core_pm_ops; + pm_runtime_allow(dev); + if (!disable_idle_d3) + pm_runtime_put(dev); + + ret = vfio_register_group_dev(&vdev->vdev); + if (ret) + goto out_power; + return 0; + +out_power: + if (!disable_idle_d3) + pm_runtime_get_noresume(dev); + + pm_runtime_forbid(dev); +out_vf: + vfio_pci_vf_uninit(vdev); + return ret; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_register_device); + +void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) +{ + vfio_pci_core_sriov_configure(vdev, 0); + + vfio_unregister_group_dev(&vdev->vdev); + + vfio_pci_vf_uninit(vdev); + vfio_pci_vga_uninit(vdev); + + if (!disable_idle_d3) + pm_runtime_get_noresume(&vdev->pdev->dev); + + pm_runtime_forbid(&vdev->pdev->dev); +} +EXPORT_SYMBOL_GPL(vfio_pci_core_unregister_device); + +pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct vfio_pci_core_device *vdev = dev_get_drvdata(&pdev->dev); + + mutex_lock(&vdev->igate); + + if (vdev->err_trigger) + eventfd_signal(vdev->err_trigger, 1); + + mutex_unlock(&vdev->igate); + + return PCI_ERS_RESULT_CAN_RECOVER; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_aer_err_detected); + +int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, + int nr_virtfn) +{ + struct pci_dev *pdev = vdev->pdev; + int ret = 0; + + device_lock_assert(&pdev->dev); + + if (nr_virtfn) { + mutex_lock(&vfio_pci_sriov_pfs_mutex); + /* + * The thread that adds the vdev to the list is the only thread + * that gets to call pci_enable_sriov() and we will only allow + * it to be called once without going through + * pci_disable_sriov() + */ + if (!list_empty(&vdev->sriov_pfs_item)) { + ret = -EINVAL; + goto out_unlock; + } + list_add_tail(&vdev->sriov_pfs_item, &vfio_pci_sriov_pfs); + mutex_unlock(&vfio_pci_sriov_pfs_mutex); + + /* + * The PF power state should always be higher than the VF power + * state. The PF can be in low power state either with runtime + * power management (when there is no user) or PCI_PM_CTRL + * register write by the user. If PF is in the low power state, + * then change the power state to D0 first before enabling + * SR-IOV. Also, this function can be called at any time, and + * userspace PCI_PM_CTRL write can race against this code path, + * so protect the same with 'memory_lock'. + */ + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) + goto out_del; + + down_write(&vdev->memory_lock); + vfio_pci_set_power_state(vdev, PCI_D0); + ret = pci_enable_sriov(pdev, nr_virtfn); + up_write(&vdev->memory_lock); + if (ret) { + pm_runtime_put(&pdev->dev); + goto out_del; + } + return nr_virtfn; + } + + if (pci_num_vf(pdev)) { + pci_disable_sriov(pdev); + pm_runtime_put(&pdev->dev); + } + +out_del: + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_del_init(&vdev->sriov_pfs_item); +out_unlock: + mutex_unlock(&vfio_pci_sriov_pfs_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure); + +const struct pci_error_handlers vfio_pci_core_err_handlers = { + .error_detected = vfio_pci_core_aer_err_detected, +}; +EXPORT_SYMBOL_GPL(vfio_pci_core_err_handlers); + +static bool vfio_dev_in_groups(struct vfio_pci_core_device *vdev, + struct vfio_pci_group_info *groups) +{ + unsigned int i; + + for (i = 0; i < groups->count; i++) + if (vfio_file_has_dev(groups->files[i], &vdev->vdev)) + return true; + return false; +} + +static int vfio_pci_is_device_in_set(struct pci_dev *pdev, void *data) +{ + struct vfio_device_set *dev_set = data; + struct vfio_device *cur; + + list_for_each_entry(cur, &dev_set->device_list, dev_set_list) + if (cur->dev == &pdev->dev) + return 0; + return -EBUSY; +} + +/* + * vfio-core considers a group to be viable and will create a vfio_device even + * if some devices are bound to drivers like pci-stub or pcieport. Here we + * require all PCI devices to be inside our dev_set since that ensures they stay + * put and that every driver controlling the device can co-ordinate with the + * device reset. + * + * Returns the pci_dev to pass to pci_reset_bus() if every PCI device to be + * reset is inside the dev_set, and pci_reset_bus() can succeed. NULL otherwise. + */ +static struct pci_dev * +vfio_pci_dev_set_resettable(struct vfio_device_set *dev_set) +{ + struct pci_dev *pdev; + + lockdep_assert_held(&dev_set->lock); + + /* + * By definition all PCI devices in the dev_set share the same PCI + * reset, so any pci_dev will have the same outcomes for + * pci_probe_reset_*() and pci_reset_bus(). + */ + pdev = list_first_entry(&dev_set->device_list, + struct vfio_pci_core_device, + vdev.dev_set_list)->pdev; + + /* pci_reset_bus() is supported */ + if (pci_probe_reset_slot(pdev->slot) && pci_probe_reset_bus(pdev->bus)) + return NULL; + + if (vfio_pci_for_each_slot_or_bus(pdev, vfio_pci_is_device_in_set, + dev_set, + !pci_probe_reset_slot(pdev->slot))) + return NULL; + return pdev; +} + +static int vfio_pci_dev_set_pm_runtime_get(struct vfio_device_set *dev_set) +{ + struct vfio_pci_core_device *cur; + int ret; + + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) { + ret = pm_runtime_resume_and_get(&cur->pdev->dev); + if (ret) + goto unwind; + } + + return 0; + +unwind: + list_for_each_entry_continue_reverse(cur, &dev_set->device_list, + vdev.dev_set_list) + pm_runtime_put(&cur->pdev->dev); + + return ret; +} + +/* + * We need to get memory_lock for each device, but devices can share mmap_lock, + * therefore we need to zap and hold the vma_lock for each device, and only then + * get each memory_lock. + */ +static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, + struct vfio_pci_group_info *groups) +{ + struct vfio_pci_core_device *cur_mem; + struct vfio_pci_core_device *cur_vma; + struct vfio_pci_core_device *cur; + struct pci_dev *pdev; + bool is_mem = true; + int ret; + + mutex_lock(&dev_set->lock); + cur_mem = list_first_entry(&dev_set->device_list, + struct vfio_pci_core_device, + vdev.dev_set_list); + + pdev = vfio_pci_dev_set_resettable(dev_set); + if (!pdev) { + ret = -EINVAL; + goto err_unlock; + } + + /* + * Some of the devices in the dev_set can be in the runtime suspended + * state. Increment the usage count for all the devices in the dev_set + * before reset and decrement the same after reset. + */ + ret = vfio_pci_dev_set_pm_runtime_get(dev_set); + if (ret) + goto err_unlock; + + list_for_each_entry(cur_vma, &dev_set->device_list, vdev.dev_set_list) { + /* + * Test whether all the affected devices are contained by the + * set of groups provided by the user. + */ + if (!vfio_dev_in_groups(cur_vma, groups)) { + ret = -EINVAL; + goto err_undo; + } + + /* + * Locking multiple devices is prone to deadlock, runaway and + * unwind if we hit contention. + */ + if (!vfio_pci_zap_and_vma_lock(cur_vma, true)) { + ret = -EBUSY; + goto err_undo; + } + } + cur_vma = NULL; + + list_for_each_entry(cur_mem, &dev_set->device_list, vdev.dev_set_list) { + if (!down_write_trylock(&cur_mem->memory_lock)) { + ret = -EBUSY; + goto err_undo; + } + mutex_unlock(&cur_mem->vma_lock); + } + cur_mem = NULL; + + /* + * The pci_reset_bus() will reset all the devices in the bus. + * The power state can be non-D0 for some of the devices in the bus. + * For these devices, the pci_reset_bus() will internally set + * the power state to D0 without vfio driver involvement. + * For the devices which have NoSoftRst-, the reset function can + * cause the PCI config space reset without restoring the original + * state (saved locally in 'vdev->pm_save'). + */ + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) + vfio_pci_set_power_state(cur, PCI_D0); + + ret = pci_reset_bus(pdev); + +err_undo: + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) { + if (cur == cur_mem) + is_mem = false; + if (cur == cur_vma) + break; + if (is_mem) + up_write(&cur->memory_lock); + else + mutex_unlock(&cur->vma_lock); + } + + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) + pm_runtime_put(&cur->pdev->dev); +err_unlock: + mutex_unlock(&dev_set->lock); + return ret; +} + +static bool vfio_pci_dev_set_needs_reset(struct vfio_device_set *dev_set) +{ + struct vfio_pci_core_device *cur; + bool needs_reset = false; + + /* No other VFIO device in the set can be open. */ + if (vfio_device_set_open_count(dev_set) > 1) + return false; + + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) + needs_reset |= cur->needs_reset; + return needs_reset; +} + +/* + * If a bus or slot reset is available for the provided dev_set and: + * - All of the devices affected by that bus or slot reset are unused + * - At least one of the affected devices is marked dirty via + * needs_reset (such as by lack of FLR support) + * Then attempt to perform that bus or slot reset. + */ +static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set) +{ + struct vfio_pci_core_device *cur; + struct pci_dev *pdev; + bool reset_done = false; + + if (!vfio_pci_dev_set_needs_reset(dev_set)) + return; + + pdev = vfio_pci_dev_set_resettable(dev_set); + if (!pdev) + return; + + /* + * Some of the devices in the bus can be in the runtime suspended + * state. Increment the usage count for all the devices in the dev_set + * before reset and decrement the same after reset. + */ + if (!disable_idle_d3 && vfio_pci_dev_set_pm_runtime_get(dev_set)) + return; + + if (!pci_reset_bus(pdev)) + reset_done = true; + + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) { + if (reset_done) + cur->needs_reset = false; + + if (!disable_idle_d3) + pm_runtime_put(&cur->pdev->dev); + } +} + +void vfio_pci_core_set_params(bool is_nointxmask, bool is_disable_vga, + bool is_disable_idle_d3) +{ + nointxmask = is_nointxmask; + disable_vga = is_disable_vga; + disable_idle_d3 = is_disable_idle_d3; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_set_params); + +static void vfio_pci_core_cleanup(void) +{ + vfio_pci_uninit_perm_bits(); +} + +static int __init vfio_pci_core_init(void) +{ + /* Allocate shared config space permission data used by all devices */ + return vfio_pci_init_perm_bits(); +} + +module_init(vfio_pci_core_init); +module_exit(vfio_pci_core_cleanup); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR(DRIVER_AUTHOR); +MODULE_DESCRIPTION(DRIVER_DESC); -- cgit v1.2.3