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_rdwr.c | 502 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 502 insertions(+) create mode 100644 drivers/vfio/pci/vfio_pci_rdwr.c (limited to 'drivers/vfio/pci/vfio_pci_rdwr.c') diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c new file mode 100644 index 000000000..e352a033b --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -0,0 +1,502 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VFIO PCI I/O Port & MMIO access + * + * 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 + */ + +#include +#include +#include +#include +#include +#include + +#include "vfio_pci_priv.h" + +#ifdef __LITTLE_ENDIAN +#define vfio_ioread64 ioread64 +#define vfio_iowrite64 iowrite64 +#define vfio_ioread32 ioread32 +#define vfio_iowrite32 iowrite32 +#define vfio_ioread16 ioread16 +#define vfio_iowrite16 iowrite16 +#else +#define vfio_ioread64 ioread64be +#define vfio_iowrite64 iowrite64be +#define vfio_ioread32 ioread32be +#define vfio_iowrite32 iowrite32be +#define vfio_ioread16 ioread16be +#define vfio_iowrite16 iowrite16be +#endif +#define vfio_ioread8 ioread8 +#define vfio_iowrite8 iowrite8 + +#define VFIO_IOWRITE(size) \ +static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev, \ + bool test_mem, u##size val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + vfio_iowrite##size(val, io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOWRITE(8) +VFIO_IOWRITE(16) +VFIO_IOWRITE(32) +#ifdef iowrite64 +VFIO_IOWRITE(64) +#endif + +#define VFIO_IOREAD(size) \ +static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev, \ + bool test_mem, u##size *val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + *val = vfio_ioread##size(io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOREAD(8) +VFIO_IOREAD(16) +VFIO_IOREAD(32) + +/* + * Read or write from an __iomem region (MMIO or I/O port) with an excluded + * range which is inaccessible. The excluded range drops writes and fills + * reads with -1. This is intended for handling MSI-X vector tables and + * leftover space for ROM BARs. + */ +static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, + void __iomem *io, char __user *buf, + loff_t off, size_t count, size_t x_start, + size_t x_end, bool iswrite) +{ + ssize_t done = 0; + int ret; + + while (count) { + size_t fillable, filled; + + if (off < x_start) + fillable = min(count, (size_t)(x_start - off)); + else if (off >= x_end) + fillable = count; + else + fillable = 0; + + if (fillable >= 4 && !(off % 4)) { + u32 val; + + if (iswrite) { + if (copy_from_user(&val, buf, 4)) + return -EFAULT; + + ret = vfio_pci_iowrite32(vdev, test_mem, + val, io + off); + if (ret) + return ret; + } else { + ret = vfio_pci_ioread32(vdev, test_mem, + &val, io + off); + if (ret) + return ret; + + if (copy_to_user(buf, &val, 4)) + return -EFAULT; + } + + filled = 4; + } else if (fillable >= 2 && !(off % 2)) { + u16 val; + + if (iswrite) { + if (copy_from_user(&val, buf, 2)) + return -EFAULT; + + ret = vfio_pci_iowrite16(vdev, test_mem, + val, io + off); + if (ret) + return ret; + } else { + ret = vfio_pci_ioread16(vdev, test_mem, + &val, io + off); + if (ret) + return ret; + + if (copy_to_user(buf, &val, 2)) + return -EFAULT; + } + + filled = 2; + } else if (fillable) { + u8 val; + + if (iswrite) { + if (copy_from_user(&val, buf, 1)) + return -EFAULT; + + ret = vfio_pci_iowrite8(vdev, test_mem, + val, io + off); + if (ret) + return ret; + } else { + ret = vfio_pci_ioread8(vdev, test_mem, + &val, io + off); + if (ret) + return ret; + + if (copy_to_user(buf, &val, 1)) + return -EFAULT; + } + + filled = 1; + } else { + /* Fill reads with -1, drop writes */ + filled = min(count, (size_t)(x_end - off)); + if (!iswrite) { + u8 val = 0xFF; + size_t i; + + for (i = 0; i < filled; i++) + if (copy_to_user(buf + i, &val, 1)) + return -EFAULT; + } + } + + count -= filled; + done += filled; + off += filled; + buf += filled; + } + + return done; +} + +static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar) +{ + struct pci_dev *pdev = vdev->pdev; + int ret; + void __iomem *io; + + if (vdev->barmap[bar]) + return 0; + + ret = pci_request_selected_regions(pdev, 1 << bar, "vfio"); + if (ret) + return ret; + + io = pci_iomap(pdev, bar, 0); + if (!io) { + pci_release_selected_regions(pdev, 1 << bar); + return -ENOMEM; + } + + vdev->barmap[bar] = io; + + return 0; +} + +ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, + size_t count, loff_t *ppos, bool iswrite) +{ + struct pci_dev *pdev = vdev->pdev; + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + int bar = VFIO_PCI_OFFSET_TO_INDEX(*ppos); + size_t x_start = 0, x_end = 0; + resource_size_t end; + void __iomem *io; + struct resource *res = &vdev->pdev->resource[bar]; + ssize_t done; + + if (pci_resource_start(pdev, bar)) + end = pci_resource_len(pdev, bar); + else if (bar == PCI_ROM_RESOURCE && + pdev->resource[bar].flags & IORESOURCE_ROM_SHADOW) + end = 0x20000; + else + return -EINVAL; + + if (pos >= end) + return -EINVAL; + + count = min(count, (size_t)(end - pos)); + + if (bar == PCI_ROM_RESOURCE) { + /* + * The ROM can fill less space than the BAR, so we start the + * excluded range at the end of the actual ROM. This makes + * filling large ROM BARs much faster. + */ + io = pci_map_rom(pdev, &x_start); + if (!io) { + done = -ENOMEM; + goto out; + } + x_end = end; + } else { + int ret = vfio_pci_setup_barmap(vdev, bar); + if (ret) { + done = ret; + goto out; + } + + io = vdev->barmap[bar]; + } + + if (bar == vdev->msix_bar) { + x_start = vdev->msix_offset; + x_end = vdev->msix_offset + vdev->msix_size; + } + + done = do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos, + count, x_start, x_end, iswrite); + + if (done >= 0) + *ppos += done; + + if (bar == PCI_ROM_RESOURCE) + pci_unmap_rom(pdev, io); +out: + return done; +} + +#ifdef CONFIG_VFIO_PCI_VGA +ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, + size_t count, loff_t *ppos, bool iswrite) +{ + int ret; + loff_t off, pos = *ppos & VFIO_PCI_OFFSET_MASK; + void __iomem *iomem = NULL; + unsigned int rsrc; + bool is_ioport; + ssize_t done; + + if (!vdev->has_vga) + return -EINVAL; + + if (pos > 0xbfffful) + return -EINVAL; + + switch ((u32)pos) { + case 0xa0000 ... 0xbffff: + count = min(count, (size_t)(0xc0000 - pos)); + iomem = ioremap(0xa0000, 0xbffff - 0xa0000 + 1); + off = pos - 0xa0000; + rsrc = VGA_RSRC_LEGACY_MEM; + is_ioport = false; + break; + case 0x3b0 ... 0x3bb: + count = min(count, (size_t)(0x3bc - pos)); + iomem = ioport_map(0x3b0, 0x3bb - 0x3b0 + 1); + off = pos - 0x3b0; + rsrc = VGA_RSRC_LEGACY_IO; + is_ioport = true; + break; + case 0x3c0 ... 0x3df: + count = min(count, (size_t)(0x3e0 - pos)); + iomem = ioport_map(0x3c0, 0x3df - 0x3c0 + 1); + off = pos - 0x3c0; + rsrc = VGA_RSRC_LEGACY_IO; + is_ioport = true; + break; + default: + return -EINVAL; + } + + if (!iomem) + return -ENOMEM; + + ret = vga_get_interruptible(vdev->pdev, rsrc); + if (ret) { + is_ioport ? ioport_unmap(iomem) : iounmap(iomem); + return ret; + } + + /* + * VGA MMIO is a legacy, non-BAR resource that hopefully allows + * probing, so we don't currently worry about access in relation + * to the memory enable bit in the command register. + */ + done = do_io_rw(vdev, false, iomem, buf, off, count, 0, 0, iswrite); + + vga_put(vdev->pdev, rsrc); + + is_ioport ? ioport_unmap(iomem) : iounmap(iomem); + + if (done >= 0) + *ppos += done; + + return done; +} +#endif + +static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd, + bool test_mem) +{ + switch (ioeventfd->count) { + case 1: + vfio_pci_iowrite8(ioeventfd->vdev, test_mem, + ioeventfd->data, ioeventfd->addr); + break; + case 2: + vfio_pci_iowrite16(ioeventfd->vdev, test_mem, + ioeventfd->data, ioeventfd->addr); + break; + case 4: + vfio_pci_iowrite32(ioeventfd->vdev, test_mem, + ioeventfd->data, ioeventfd->addr); + break; +#ifdef iowrite64 + case 8: + vfio_pci_iowrite64(ioeventfd->vdev, test_mem, + ioeventfd->data, ioeventfd->addr); + break; +#endif + } +} + +static int vfio_pci_ioeventfd_handler(void *opaque, void *unused) +{ + struct vfio_pci_ioeventfd *ioeventfd = opaque; + struct vfio_pci_core_device *vdev = ioeventfd->vdev; + + if (ioeventfd->test_mem) { + if (!down_read_trylock(&vdev->memory_lock)) + return 1; /* Lock contended, use thread */ + if (!__vfio_pci_memory_enabled(vdev)) { + up_read(&vdev->memory_lock); + return 0; + } + } + + vfio_pci_ioeventfd_do_write(ioeventfd, false); + + if (ioeventfd->test_mem) + up_read(&vdev->memory_lock); + + return 0; +} + +static void vfio_pci_ioeventfd_thread(void *opaque, void *unused) +{ + struct vfio_pci_ioeventfd *ioeventfd = opaque; + + vfio_pci_ioeventfd_do_write(ioeventfd, ioeventfd->test_mem); +} + +int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, + uint64_t data, int count, int fd) +{ + struct pci_dev *pdev = vdev->pdev; + loff_t pos = offset & VFIO_PCI_OFFSET_MASK; + int ret, bar = VFIO_PCI_OFFSET_TO_INDEX(offset); + struct vfio_pci_ioeventfd *ioeventfd; + + /* Only support ioeventfds into BARs */ + if (bar > VFIO_PCI_BAR5_REGION_INDEX) + return -EINVAL; + + if (pos + count > pci_resource_len(pdev, bar)) + return -EINVAL; + + /* Disallow ioeventfds working around MSI-X table writes */ + if (bar == vdev->msix_bar && + !(pos + count <= vdev->msix_offset || + pos >= vdev->msix_offset + vdev->msix_size)) + return -EINVAL; + +#ifndef iowrite64 + if (count == 8) + return -EINVAL; +#endif + + ret = vfio_pci_setup_barmap(vdev, bar); + if (ret) + return ret; + + mutex_lock(&vdev->ioeventfds_lock); + + list_for_each_entry(ioeventfd, &vdev->ioeventfds_list, next) { + if (ioeventfd->pos == pos && ioeventfd->bar == bar && + ioeventfd->data == data && ioeventfd->count == count) { + if (fd == -1) { + vfio_virqfd_disable(&ioeventfd->virqfd); + list_del(&ioeventfd->next); + vdev->ioeventfds_nr--; + kfree(ioeventfd); + ret = 0; + } else + ret = -EEXIST; + + goto out_unlock; + } + } + + if (fd < 0) { + ret = -ENODEV; + goto out_unlock; + } + + if (vdev->ioeventfds_nr >= VFIO_PCI_IOEVENTFD_MAX) { + ret = -ENOSPC; + goto out_unlock; + } + + ioeventfd = kzalloc(sizeof(*ioeventfd), GFP_KERNEL); + if (!ioeventfd) { + ret = -ENOMEM; + goto out_unlock; + } + + ioeventfd->vdev = vdev; + ioeventfd->addr = vdev->barmap[bar] + pos; + ioeventfd->data = data; + ioeventfd->pos = pos; + ioeventfd->bar = bar; + ioeventfd->count = count; + ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM; + + ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler, + vfio_pci_ioeventfd_thread, NULL, + &ioeventfd->virqfd, fd); + if (ret) { + kfree(ioeventfd); + goto out_unlock; + } + + list_add(&ioeventfd->next, &vdev->ioeventfds_list); + vdev->ioeventfds_nr++; + +out_unlock: + mutex_unlock(&vdev->ioeventfds_lock); + + return ret; +} -- cgit v1.2.3