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/xen/privcmd.c | 1009 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1009 insertions(+) create mode 100644 drivers/xen/privcmd.c (limited to 'drivers/xen/privcmd.c') diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c new file mode 100644 index 000000000..1edf45ee9 --- /dev/null +++ b/drivers/xen/privcmd.c @@ -0,0 +1,1009 @@ +// SPDX-License-Identifier: GPL-2.0-only +/****************************************************************************** + * privcmd.c + * + * Interface to privileged domain-0 commands. + * + * Copyright (c) 2002-2004, K A Fraser, B Dragovic + */ + +#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "privcmd.h" + +MODULE_LICENSE("GPL"); + +#define PRIV_VMA_LOCKED ((void *)1) + +static unsigned int privcmd_dm_op_max_num = 16; +module_param_named(dm_op_max_nr_bufs, privcmd_dm_op_max_num, uint, 0644); +MODULE_PARM_DESC(dm_op_max_nr_bufs, + "Maximum number of buffers per dm_op hypercall"); + +static unsigned int privcmd_dm_op_buf_max_size = 4096; +module_param_named(dm_op_buf_max_size, privcmd_dm_op_buf_max_size, uint, + 0644); +MODULE_PARM_DESC(dm_op_buf_max_size, + "Maximum size of a dm_op hypercall buffer"); + +struct privcmd_data { + domid_t domid; +}; + +static int privcmd_vma_range_is_mapped( + struct vm_area_struct *vma, + unsigned long addr, + unsigned long nr_pages); + +static long privcmd_ioctl_hypercall(struct file *file, void __user *udata) +{ + struct privcmd_data *data = file->private_data; + struct privcmd_hypercall hypercall; + long ret; + + /* Disallow arbitrary hypercalls if restricted */ + if (data->domid != DOMID_INVALID) + return -EPERM; + + if (copy_from_user(&hypercall, udata, sizeof(hypercall))) + return -EFAULT; + + xen_preemptible_hcall_begin(); + ret = privcmd_call(hypercall.op, + hypercall.arg[0], hypercall.arg[1], + hypercall.arg[2], hypercall.arg[3], + hypercall.arg[4]); + xen_preemptible_hcall_end(); + + return ret; +} + +static void free_page_list(struct list_head *pages) +{ + struct page *p, *n; + + list_for_each_entry_safe(p, n, pages, lru) + __free_page(p); + + INIT_LIST_HEAD(pages); +} + +/* + * Given an array of items in userspace, return a list of pages + * containing the data. If copying fails, either because of memory + * allocation failure or a problem reading user memory, return an + * error code; its up to the caller to dispose of any partial list. + */ +static int gather_array(struct list_head *pagelist, + unsigned nelem, size_t size, + const void __user *data) +{ + unsigned pageidx; + void *pagedata; + int ret; + + if (size > PAGE_SIZE) + return 0; + + pageidx = PAGE_SIZE; + pagedata = NULL; /* quiet, gcc */ + while (nelem--) { + if (pageidx > PAGE_SIZE-size) { + struct page *page = alloc_page(GFP_KERNEL); + + ret = -ENOMEM; + if (page == NULL) + goto fail; + + pagedata = page_address(page); + + list_add_tail(&page->lru, pagelist); + pageidx = 0; + } + + ret = -EFAULT; + if (copy_from_user(pagedata + pageidx, data, size)) + goto fail; + + data += size; + pageidx += size; + } + + ret = 0; + +fail: + return ret; +} + +/* + * Call function "fn" on each element of the array fragmented + * over a list of pages. + */ +static int traverse_pages(unsigned nelem, size_t size, + struct list_head *pos, + int (*fn)(void *data, void *state), + void *state) +{ + void *pagedata; + unsigned pageidx; + int ret = 0; + + BUG_ON(size > PAGE_SIZE); + + pageidx = PAGE_SIZE; + pagedata = NULL; /* hush, gcc */ + + while (nelem--) { + if (pageidx > PAGE_SIZE-size) { + struct page *page; + pos = pos->next; + page = list_entry(pos, struct page, lru); + pagedata = page_address(page); + pageidx = 0; + } + + ret = (*fn)(pagedata + pageidx, state); + if (ret) + break; + pageidx += size; + } + + return ret; +} + +/* + * Similar to traverse_pages, but use each page as a "block" of + * data to be processed as one unit. + */ +static int traverse_pages_block(unsigned nelem, size_t size, + struct list_head *pos, + int (*fn)(void *data, int nr, void *state), + void *state) +{ + void *pagedata; + int ret = 0; + + BUG_ON(size > PAGE_SIZE); + + while (nelem) { + int nr = (PAGE_SIZE/size); + struct page *page; + if (nr > nelem) + nr = nelem; + pos = pos->next; + page = list_entry(pos, struct page, lru); + pagedata = page_address(page); + ret = (*fn)(pagedata, nr, state); + if (ret) + break; + nelem -= nr; + } + + return ret; +} + +struct mmap_gfn_state { + unsigned long va; + struct vm_area_struct *vma; + domid_t domain; +}; + +static int mmap_gfn_range(void *data, void *state) +{ + struct privcmd_mmap_entry *msg = data; + struct mmap_gfn_state *st = state; + struct vm_area_struct *vma = st->vma; + int rc; + + /* Do not allow range to wrap the address space. */ + if ((msg->npages > (LONG_MAX >> PAGE_SHIFT)) || + ((unsigned long)(msg->npages << PAGE_SHIFT) >= -st->va)) + return -EINVAL; + + /* Range chunks must be contiguous in va space. */ + if ((msg->va != st->va) || + ((msg->va+(msg->npages< vma->vm_end)) + return -EINVAL; + + rc = xen_remap_domain_gfn_range(vma, + msg->va & PAGE_MASK, + msg->mfn, msg->npages, + vma->vm_page_prot, + st->domain, NULL); + if (rc < 0) + return rc; + + st->va += msg->npages << PAGE_SHIFT; + + return 0; +} + +static long privcmd_ioctl_mmap(struct file *file, void __user *udata) +{ + struct privcmd_data *data = file->private_data; + struct privcmd_mmap mmapcmd; + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int rc; + LIST_HEAD(pagelist); + struct mmap_gfn_state state; + + /* We only support privcmd_ioctl_mmap_batch for non-auto-translated. */ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return -ENOSYS; + + if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd))) + return -EFAULT; + + /* If restriction is in place, check the domid matches */ + if (data->domid != DOMID_INVALID && data->domid != mmapcmd.dom) + return -EPERM; + + rc = gather_array(&pagelist, + mmapcmd.num, sizeof(struct privcmd_mmap_entry), + mmapcmd.entry); + + if (rc || list_empty(&pagelist)) + goto out; + + mmap_write_lock(mm); + + { + struct page *page = list_first_entry(&pagelist, + struct page, lru); + struct privcmd_mmap_entry *msg = page_address(page); + + vma = vma_lookup(mm, msg->va); + rc = -EINVAL; + + if (!vma || (msg->va != vma->vm_start) || vma->vm_private_data) + goto out_up; + vma->vm_private_data = PRIV_VMA_LOCKED; + } + + state.va = vma->vm_start; + state.vma = vma; + state.domain = mmapcmd.dom; + + rc = traverse_pages(mmapcmd.num, sizeof(struct privcmd_mmap_entry), + &pagelist, + mmap_gfn_range, &state); + + +out_up: + mmap_write_unlock(mm); + +out: + free_page_list(&pagelist); + + return rc; +} + +struct mmap_batch_state { + domid_t domain; + unsigned long va; + struct vm_area_struct *vma; + int index; + /* A tristate: + * 0 for no errors + * 1 if at least one error has happened (and no + * -ENOENT errors have happened) + * -ENOENT if at least 1 -ENOENT has happened. + */ + int global_error; + int version; + + /* User-space gfn array to store errors in the second pass for V1. */ + xen_pfn_t __user *user_gfn; + /* User-space int array to store errors in the second pass for V2. */ + int __user *user_err; +}; + +/* auto translated dom0 note: if domU being created is PV, then gfn is + * mfn(addr on bus). If it's auto xlated, then gfn is pfn (input to HAP). + */ +static int mmap_batch_fn(void *data, int nr, void *state) +{ + xen_pfn_t *gfnp = data; + struct mmap_batch_state *st = state; + struct vm_area_struct *vma = st->vma; + struct page **pages = vma->vm_private_data; + struct page **cur_pages = NULL; + int ret; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + cur_pages = &pages[st->index]; + + BUG_ON(nr < 0); + ret = xen_remap_domain_gfn_array(st->vma, st->va & PAGE_MASK, gfnp, nr, + (int *)gfnp, st->vma->vm_page_prot, + st->domain, cur_pages); + + /* Adjust the global_error? */ + if (ret != nr) { + if (ret == -ENOENT) + st->global_error = -ENOENT; + else { + /* Record that at least one error has happened. */ + if (st->global_error == 0) + st->global_error = 1; + } + } + st->va += XEN_PAGE_SIZE * nr; + st->index += nr / XEN_PFN_PER_PAGE; + + return 0; +} + +static int mmap_return_error(int err, struct mmap_batch_state *st) +{ + int ret; + + if (st->version == 1) { + if (err) { + xen_pfn_t gfn; + + ret = get_user(gfn, st->user_gfn); + if (ret < 0) + return ret; + /* + * V1 encodes the error codes in the 32bit top + * nibble of the gfn (with its known + * limitations vis-a-vis 64 bit callers). + */ + gfn |= (err == -ENOENT) ? + PRIVCMD_MMAPBATCH_PAGED_ERROR : + PRIVCMD_MMAPBATCH_MFN_ERROR; + return __put_user(gfn, st->user_gfn++); + } else + st->user_gfn++; + } else { /* st->version == 2 */ + if (err) + return __put_user(err, st->user_err++); + else + st->user_err++; + } + + return 0; +} + +static int mmap_return_errors(void *data, int nr, void *state) +{ + struct mmap_batch_state *st = state; + int *errs = data; + int i; + int ret; + + for (i = 0; i < nr; i++) { + ret = mmap_return_error(errs[i], st); + if (ret < 0) + return ret; + } + return 0; +} + +/* Allocate pfns that are then mapped with gfns from foreign domid. Update + * the vma with the page info to use later. + * Returns: 0 if success, otherwise -errno + */ +static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs) +{ + int rc; + struct page **pages; + + pages = kvcalloc(numpgs, sizeof(pages[0]), GFP_KERNEL); + if (pages == NULL) + return -ENOMEM; + + rc = xen_alloc_unpopulated_pages(numpgs, pages); + if (rc != 0) { + pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__, + numpgs, rc); + kvfree(pages); + return -ENOMEM; + } + BUG_ON(vma->vm_private_data != NULL); + vma->vm_private_data = pages; + + return 0; +} + +static const struct vm_operations_struct privcmd_vm_ops; + +static long privcmd_ioctl_mmap_batch( + struct file *file, void __user *udata, int version) +{ + struct privcmd_data *data = file->private_data; + int ret; + struct privcmd_mmapbatch_v2 m; + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long nr_pages; + LIST_HEAD(pagelist); + struct mmap_batch_state state; + + switch (version) { + case 1: + if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch))) + return -EFAULT; + /* Returns per-frame error in m.arr. */ + m.err = NULL; + if (!access_ok(m.arr, m.num * sizeof(*m.arr))) + return -EFAULT; + break; + case 2: + if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch_v2))) + return -EFAULT; + /* Returns per-frame error code in m.err. */ + if (!access_ok(m.err, m.num * (sizeof(*m.err)))) + return -EFAULT; + break; + default: + return -EINVAL; + } + + /* If restriction is in place, check the domid matches */ + if (data->domid != DOMID_INVALID && data->domid != m.dom) + return -EPERM; + + nr_pages = DIV_ROUND_UP(m.num, XEN_PFN_PER_PAGE); + if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT))) + return -EINVAL; + + ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t), m.arr); + + if (ret) + goto out; + if (list_empty(&pagelist)) { + ret = -EINVAL; + goto out; + } + + if (version == 2) { + /* Zero error array now to only copy back actual errors. */ + if (clear_user(m.err, sizeof(int) * m.num)) { + ret = -EFAULT; + goto out; + } + } + + mmap_write_lock(mm); + + vma = find_vma(mm, m.addr); + if (!vma || + vma->vm_ops != &privcmd_vm_ops) { + ret = -EINVAL; + goto out_unlock; + } + + /* + * Caller must either: + * + * Map the whole VMA range, which will also allocate all the + * pages required for the auto_translated_physmap case. + * + * Or + * + * Map unmapped holes left from a previous map attempt (e.g., + * because those foreign frames were previously paged out). + */ + if (vma->vm_private_data == NULL) { + if (m.addr != vma->vm_start || + m.addr + (nr_pages << PAGE_SHIFT) != vma->vm_end) { + ret = -EINVAL; + goto out_unlock; + } + if (xen_feature(XENFEAT_auto_translated_physmap)) { + ret = alloc_empty_pages(vma, nr_pages); + if (ret < 0) + goto out_unlock; + } else + vma->vm_private_data = PRIV_VMA_LOCKED; + } else { + if (m.addr < vma->vm_start || + m.addr + (nr_pages << PAGE_SHIFT) > vma->vm_end) { + ret = -EINVAL; + goto out_unlock; + } + if (privcmd_vma_range_is_mapped(vma, m.addr, nr_pages)) { + ret = -EINVAL; + goto out_unlock; + } + } + + state.domain = m.dom; + state.vma = vma; + state.va = m.addr; + state.index = 0; + state.global_error = 0; + state.version = version; + + BUILD_BUG_ON(((PAGE_SIZE / sizeof(xen_pfn_t)) % XEN_PFN_PER_PAGE) != 0); + /* mmap_batch_fn guarantees ret == 0 */ + BUG_ON(traverse_pages_block(m.num, sizeof(xen_pfn_t), + &pagelist, mmap_batch_fn, &state)); + + mmap_write_unlock(mm); + + if (state.global_error) { + /* Write back errors in second pass. */ + state.user_gfn = (xen_pfn_t *)m.arr; + state.user_err = m.err; + ret = traverse_pages_block(m.num, sizeof(xen_pfn_t), + &pagelist, mmap_return_errors, &state); + } else + ret = 0; + + /* If we have not had any EFAULT-like global errors then set the global + * error to -ENOENT if necessary. */ + if ((ret == 0) && (state.global_error == -ENOENT)) + ret = -ENOENT; + +out: + free_page_list(&pagelist); + return ret; + +out_unlock: + mmap_write_unlock(mm); + goto out; +} + +static int lock_pages( + struct privcmd_dm_op_buf kbufs[], unsigned int num, + struct page *pages[], unsigned int nr_pages, unsigned int *pinned) +{ + unsigned int i, off = 0; + + for (i = 0; i < num; ) { + unsigned int requested; + int page_count; + + requested = DIV_ROUND_UP( + offset_in_page(kbufs[i].uptr) + kbufs[i].size, + PAGE_SIZE) - off; + if (requested > nr_pages) + return -ENOSPC; + + page_count = pin_user_pages_fast( + (unsigned long)kbufs[i].uptr + off * PAGE_SIZE, + requested, FOLL_WRITE, pages); + if (page_count <= 0) + return page_count ? : -EFAULT; + + *pinned += page_count; + nr_pages -= page_count; + pages += page_count; + + off = (requested == page_count) ? 0 : off + page_count; + i += !off; + } + + return 0; +} + +static void unlock_pages(struct page *pages[], unsigned int nr_pages) +{ + unpin_user_pages_dirty_lock(pages, nr_pages, true); +} + +static long privcmd_ioctl_dm_op(struct file *file, void __user *udata) +{ + struct privcmd_data *data = file->private_data; + struct privcmd_dm_op kdata; + struct privcmd_dm_op_buf *kbufs; + unsigned int nr_pages = 0; + struct page **pages = NULL; + struct xen_dm_op_buf *xbufs = NULL; + unsigned int i; + long rc; + unsigned int pinned = 0; + + if (copy_from_user(&kdata, udata, sizeof(kdata))) + return -EFAULT; + + /* If restriction is in place, check the domid matches */ + if (data->domid != DOMID_INVALID && data->domid != kdata.dom) + return -EPERM; + + if (kdata.num == 0) + return 0; + + if (kdata.num > privcmd_dm_op_max_num) + return -E2BIG; + + kbufs = kcalloc(kdata.num, sizeof(*kbufs), GFP_KERNEL); + if (!kbufs) + return -ENOMEM; + + if (copy_from_user(kbufs, kdata.ubufs, + sizeof(*kbufs) * kdata.num)) { + rc = -EFAULT; + goto out; + } + + for (i = 0; i < kdata.num; i++) { + if (kbufs[i].size > privcmd_dm_op_buf_max_size) { + rc = -E2BIG; + goto out; + } + + if (!access_ok(kbufs[i].uptr, + kbufs[i].size)) { + rc = -EFAULT; + goto out; + } + + nr_pages += DIV_ROUND_UP( + offset_in_page(kbufs[i].uptr) + kbufs[i].size, + PAGE_SIZE); + } + + pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) { + rc = -ENOMEM; + goto out; + } + + xbufs = kcalloc(kdata.num, sizeof(*xbufs), GFP_KERNEL); + if (!xbufs) { + rc = -ENOMEM; + goto out; + } + + rc = lock_pages(kbufs, kdata.num, pages, nr_pages, &pinned); + if (rc < 0) + goto out; + + for (i = 0; i < kdata.num; i++) { + set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr); + xbufs[i].size = kbufs[i].size; + } + + xen_preemptible_hcall_begin(); + rc = HYPERVISOR_dm_op(kdata.dom, kdata.num, xbufs); + xen_preemptible_hcall_end(); + +out: + unlock_pages(pages, pinned); + kfree(xbufs); + kfree(pages); + kfree(kbufs); + + return rc; +} + +static long privcmd_ioctl_restrict(struct file *file, void __user *udata) +{ + struct privcmd_data *data = file->private_data; + domid_t dom; + + if (copy_from_user(&dom, udata, sizeof(dom))) + return -EFAULT; + + /* Set restriction to the specified domain, or check it matches */ + if (data->domid == DOMID_INVALID) + data->domid = dom; + else if (data->domid != dom) + return -EINVAL; + + return 0; +} + +static long privcmd_ioctl_mmap_resource(struct file *file, + struct privcmd_mmap_resource __user *udata) +{ + struct privcmd_data *data = file->private_data; + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + struct privcmd_mmap_resource kdata; + xen_pfn_t *pfns = NULL; + struct xen_mem_acquire_resource xdata = { }; + int rc; + + if (copy_from_user(&kdata, udata, sizeof(kdata))) + return -EFAULT; + + /* If restriction is in place, check the domid matches */ + if (data->domid != DOMID_INVALID && data->domid != kdata.dom) + return -EPERM; + + /* Both fields must be set or unset */ + if (!!kdata.addr != !!kdata.num) + return -EINVAL; + + xdata.domid = kdata.dom; + xdata.type = kdata.type; + xdata.id = kdata.id; + + if (!kdata.addr && !kdata.num) { + /* Query the size of the resource. */ + rc = HYPERVISOR_memory_op(XENMEM_acquire_resource, &xdata); + if (rc) + return rc; + return __put_user(xdata.nr_frames, &udata->num); + } + + mmap_write_lock(mm); + + vma = find_vma(mm, kdata.addr); + if (!vma || vma->vm_ops != &privcmd_vm_ops) { + rc = -EINVAL; + goto out; + } + + pfns = kcalloc(kdata.num, sizeof(*pfns), GFP_KERNEL | __GFP_NOWARN); + if (!pfns) { + rc = -ENOMEM; + goto out; + } + + if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && + xen_feature(XENFEAT_auto_translated_physmap)) { + unsigned int nr = DIV_ROUND_UP(kdata.num, XEN_PFN_PER_PAGE); + struct page **pages; + unsigned int i; + + rc = alloc_empty_pages(vma, nr); + if (rc < 0) + goto out; + + pages = vma->vm_private_data; + for (i = 0; i < kdata.num; i++) { + xen_pfn_t pfn = + page_to_xen_pfn(pages[i / XEN_PFN_PER_PAGE]); + + pfns[i] = pfn + (i % XEN_PFN_PER_PAGE); + } + } else + vma->vm_private_data = PRIV_VMA_LOCKED; + + xdata.frame = kdata.idx; + xdata.nr_frames = kdata.num; + set_xen_guest_handle(xdata.frame_list, pfns); + + xen_preemptible_hcall_begin(); + rc = HYPERVISOR_memory_op(XENMEM_acquire_resource, &xdata); + xen_preemptible_hcall_end(); + + if (rc) + goto out; + + if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && + xen_feature(XENFEAT_auto_translated_physmap)) { + rc = xen_remap_vma_range(vma, kdata.addr, kdata.num << PAGE_SHIFT); + } else { + unsigned int domid = + (xdata.flags & XENMEM_rsrc_acq_caller_owned) ? + DOMID_SELF : kdata.dom; + int num, *errs = (int *)pfns; + + BUILD_BUG_ON(sizeof(*errs) > sizeof(*pfns)); + num = xen_remap_domain_mfn_array(vma, + kdata.addr & PAGE_MASK, + pfns, kdata.num, errs, + vma->vm_page_prot, + domid); + if (num < 0) + rc = num; + else if (num != kdata.num) { + unsigned int i; + + for (i = 0; i < num; i++) { + rc = errs[i]; + if (rc < 0) + break; + } + } else + rc = 0; + } + +out: + mmap_write_unlock(mm); + kfree(pfns); + + return rc; +} + +static long privcmd_ioctl(struct file *file, + unsigned int cmd, unsigned long data) +{ + int ret = -ENOTTY; + void __user *udata = (void __user *) data; + + switch (cmd) { + case IOCTL_PRIVCMD_HYPERCALL: + ret = privcmd_ioctl_hypercall(file, udata); + break; + + case IOCTL_PRIVCMD_MMAP: + ret = privcmd_ioctl_mmap(file, udata); + break; + + case IOCTL_PRIVCMD_MMAPBATCH: + ret = privcmd_ioctl_mmap_batch(file, udata, 1); + break; + + case IOCTL_PRIVCMD_MMAPBATCH_V2: + ret = privcmd_ioctl_mmap_batch(file, udata, 2); + break; + + case IOCTL_PRIVCMD_DM_OP: + ret = privcmd_ioctl_dm_op(file, udata); + break; + + case IOCTL_PRIVCMD_RESTRICT: + ret = privcmd_ioctl_restrict(file, udata); + break; + + case IOCTL_PRIVCMD_MMAP_RESOURCE: + ret = privcmd_ioctl_mmap_resource(file, udata); + break; + + default: + break; + } + + return ret; +} + +static int privcmd_open(struct inode *ino, struct file *file) +{ + struct privcmd_data *data = kzalloc(sizeof(*data), GFP_KERNEL); + + if (!data) + return -ENOMEM; + + /* DOMID_INVALID implies no restriction */ + data->domid = DOMID_INVALID; + + file->private_data = data; + return 0; +} + +static int privcmd_release(struct inode *ino, struct file *file) +{ + struct privcmd_data *data = file->private_data; + + kfree(data); + return 0; +} + +static void privcmd_close(struct vm_area_struct *vma) +{ + struct page **pages = vma->vm_private_data; + int numpgs = vma_pages(vma); + int numgfns = (vma->vm_end - vma->vm_start) >> XEN_PAGE_SHIFT; + int rc; + + if (!xen_feature(XENFEAT_auto_translated_physmap) || !numpgs || !pages) + return; + + rc = xen_unmap_domain_gfn_range(vma, numgfns, pages); + if (rc == 0) + xen_free_unpopulated_pages(numpgs, pages); + else + pr_crit("unable to unmap MFN range: leaking %d pages. rc=%d\n", + numpgs, rc); + kvfree(pages); +} + +static vm_fault_t privcmd_fault(struct vm_fault *vmf) +{ + printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n", + vmf->vma, vmf->vma->vm_start, vmf->vma->vm_end, + vmf->pgoff, (void *)vmf->address); + + return VM_FAULT_SIGBUS; +} + +static const struct vm_operations_struct privcmd_vm_ops = { + .close = privcmd_close, + .fault = privcmd_fault +}; + +static int privcmd_mmap(struct file *file, struct vm_area_struct *vma) +{ + /* DONTCOPY is essential for Xen because copy_page_range doesn't know + * how to recreate these mappings */ + vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTCOPY | + VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_ops = &privcmd_vm_ops; + vma->vm_private_data = NULL; + + return 0; +} + +/* + * For MMAPBATCH*. This allows asserting the singleshot mapping + * on a per pfn/pte basis. Mapping calls that fail with ENOENT + * can be then retried until success. + */ +static int is_mapped_fn(pte_t *pte, unsigned long addr, void *data) +{ + return pte_none(*pte) ? 0 : -EBUSY; +} + +static int privcmd_vma_range_is_mapped( + struct vm_area_struct *vma, + unsigned long addr, + unsigned long nr_pages) +{ + return apply_to_page_range(vma->vm_mm, addr, nr_pages << PAGE_SHIFT, + is_mapped_fn, NULL) != 0; +} + +const struct file_operations xen_privcmd_fops = { + .owner = THIS_MODULE, + .unlocked_ioctl = privcmd_ioctl, + .open = privcmd_open, + .release = privcmd_release, + .mmap = privcmd_mmap, +}; +EXPORT_SYMBOL_GPL(xen_privcmd_fops); + +static struct miscdevice privcmd_dev = { + .minor = MISC_DYNAMIC_MINOR, + .name = "xen/privcmd", + .fops = &xen_privcmd_fops, +}; + +static int __init privcmd_init(void) +{ + int err; + + if (!xen_domain()) + return -ENODEV; + + err = misc_register(&privcmd_dev); + if (err != 0) { + pr_err("Could not register Xen privcmd device\n"); + return err; + } + + err = misc_register(&xen_privcmdbuf_dev); + if (err != 0) { + pr_err("Could not register Xen hypercall-buf device\n"); + misc_deregister(&privcmd_dev); + return err; + } + + return 0; +} + +static void __exit privcmd_exit(void) +{ + misc_deregister(&privcmd_dev); + misc_deregister(&xen_privcmdbuf_dev); +} + +module_init(privcmd_init); +module_exit(privcmd_exit); -- cgit v1.2.3