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(). ... --- arch/x86/kernel/vm86_32.c | 832 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 832 insertions(+) create mode 100644 arch/x86/kernel/vm86_32.c (limited to 'arch/x86/kernel/vm86_32.c') diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c new file mode 100644 index 000000000..e9e803a4d --- /dev/null +++ b/arch/x86/kernel/vm86_32.c @@ -0,0 +1,832 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 1994 Linus Torvalds + * + * 29 dec 2001 - Fixed oopses caused by unchecked access to the vm86 + * stack - Manfred Spraul + * + * 22 mar 2002 - Manfred detected the stackfaults, but didn't handle + * them correctly. Now the emulation will be in a + * consistent state after stackfaults - Kasper Dupont + * + * + * 22 mar 2002 - Added missing clear_IF in set_vflags_* Kasper Dupont + * + * + * ?? ??? 2002 - Fixed premature returns from handle_vm86_fault + * caused by Kasper Dupont's changes - Stas Sergeev + * + * 4 apr 2002 - Fixed CHECK_IF_IN_TRAP broken by Stas' changes. + * Kasper Dupont + * + * 9 apr 2002 - Changed syntax of macros in handle_vm86_fault. + * Kasper Dupont + * + * 9 apr 2002 - Changed stack access macros to jump to a label + * instead of returning to userspace. This simplifies + * do_int, and is needed by handle_vm6_fault. Kasper + * Dupont + * + */ + +#define pr_fmt(fmt) 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 + +/* + * Known problems: + * + * Interrupt handling is not guaranteed: + * - a real x86 will disable all interrupts for one instruction + * after a "mov ss,xx" to make stack handling atomic even without + * the 'lss' instruction. We can't guarantee this in v86 mode, + * as the next instruction might result in a page fault or similar. + * - a real x86 will have interrupts disabled for one instruction + * past the 'sti' that enables them. We don't bother with all the + * details yet. + * + * Let's hope these problems do not actually matter for anything. + */ + + +/* + * 8- and 16-bit register defines.. + */ +#define AL(regs) (((unsigned char *)&((regs)->pt.ax))[0]) +#define AH(regs) (((unsigned char *)&((regs)->pt.ax))[1]) +#define IP(regs) (*(unsigned short *)&((regs)->pt.ip)) +#define SP(regs) (*(unsigned short *)&((regs)->pt.sp)) + +/* + * virtual flags (16 and 32-bit versions) + */ +#define VFLAGS (*(unsigned short *)&(current->thread.vm86->veflags)) +#define VEFLAGS (current->thread.vm86->veflags) + +#define set_flags(X, new, mask) \ +((X) = ((X) & ~(mask)) | ((new) & (mask))) + +#define SAFE_MASK (0xDD5) +#define RETURN_MASK (0xDFF) + +void save_v86_state(struct kernel_vm86_regs *regs, int retval) +{ + struct task_struct *tsk = current; + struct vm86plus_struct __user *user; + struct vm86 *vm86 = current->thread.vm86; + + /* + * This gets called from entry.S with interrupts disabled, but + * from process context. Enable interrupts here, before trying + * to access user space. + */ + local_irq_enable(); + + BUG_ON(!vm86); + + set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask); + user = vm86->user_vm86; + + if (!user_access_begin(user, vm86->vm86plus.is_vm86pus ? + sizeof(struct vm86plus_struct) : + sizeof(struct vm86_struct))) + goto Efault; + + unsafe_put_user(regs->pt.bx, &user->regs.ebx, Efault_end); + unsafe_put_user(regs->pt.cx, &user->regs.ecx, Efault_end); + unsafe_put_user(regs->pt.dx, &user->regs.edx, Efault_end); + unsafe_put_user(regs->pt.si, &user->regs.esi, Efault_end); + unsafe_put_user(regs->pt.di, &user->regs.edi, Efault_end); + unsafe_put_user(regs->pt.bp, &user->regs.ebp, Efault_end); + unsafe_put_user(regs->pt.ax, &user->regs.eax, Efault_end); + unsafe_put_user(regs->pt.ip, &user->regs.eip, Efault_end); + unsafe_put_user(regs->pt.cs, &user->regs.cs, Efault_end); + unsafe_put_user(regs->pt.flags, &user->regs.eflags, Efault_end); + unsafe_put_user(regs->pt.sp, &user->regs.esp, Efault_end); + unsafe_put_user(regs->pt.ss, &user->regs.ss, Efault_end); + unsafe_put_user(regs->es, &user->regs.es, Efault_end); + unsafe_put_user(regs->ds, &user->regs.ds, Efault_end); + unsafe_put_user(regs->fs, &user->regs.fs, Efault_end); + unsafe_put_user(regs->gs, &user->regs.gs, Efault_end); + + /* + * Don't write screen_bitmap in case some user had a value there + * and expected it to remain unchanged. + */ + + user_access_end(); + +exit_vm86: + preempt_disable(); + tsk->thread.sp0 = vm86->saved_sp0; + tsk->thread.sysenter_cs = __KERNEL_CS; + update_task_stack(tsk); + refresh_sysenter_cs(&tsk->thread); + vm86->saved_sp0 = 0; + preempt_enable(); + + memcpy(®s->pt, &vm86->regs32, sizeof(struct pt_regs)); + + loadsegment(gs, vm86->regs32.gs); + + regs->pt.ax = retval; + return; + +Efault_end: + user_access_end(); +Efault: + pr_alert("could not access userspace vm86 info\n"); + force_exit_sig(SIGSEGV); + goto exit_vm86; +} + +static int do_vm86_irq_handling(int subfunction, int irqnumber); +static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus); + +SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, user_vm86) +{ + return do_sys_vm86((struct vm86plus_struct __user *) user_vm86, false); +} + + +SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) +{ + switch (cmd) { + case VM86_REQUEST_IRQ: + case VM86_FREE_IRQ: + case VM86_GET_IRQ_BITS: + case VM86_GET_AND_RESET_IRQ: + return do_vm86_irq_handling(cmd, (int)arg); + case VM86_PLUS_INSTALL_CHECK: + /* + * NOTE: on old vm86 stuff this will return the error + * from access_ok(), because the subfunction is + * interpreted as (invalid) address to vm86_struct. + * So the installation check works. + */ + return 0; + } + + /* we come here only for functions VM86_ENTER, VM86_ENTER_NO_BYPASS */ + return do_sys_vm86((struct vm86plus_struct __user *) arg, true); +} + + +static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) +{ + struct task_struct *tsk = current; + struct vm86 *vm86 = tsk->thread.vm86; + struct kernel_vm86_regs vm86regs; + struct pt_regs *regs = current_pt_regs(); + unsigned long err = 0; + struct vm86_struct v; + + err = security_mmap_addr(0); + if (err) { + /* + * vm86 cannot virtualize the address space, so vm86 users + * need to manage the low 1MB themselves using mmap. Given + * that BIOS places important data in the first page, vm86 + * is essentially useless if mmap_min_addr != 0. DOSEMU, + * for example, won't even bother trying to use vm86 if it + * can't map a page at virtual address 0. + * + * To reduce the available kernel attack surface, simply + * disallow vm86(old) for users who cannot mmap at va 0. + * + * The implementation of security_mmap_addr will allow + * suitably privileged users to map va 0 even if + * vm.mmap_min_addr is set above 0, and we want this + * behavior for vm86 as well, as it ensures that legacy + * tools like vbetool will not fail just because of + * vm.mmap_min_addr. + */ + pr_info_once("Denied a call to vm86(old) from %s[%d] (uid: %d). Set the vm.mmap_min_addr sysctl to 0 and/or adjust LSM mmap_min_addr policy to enable vm86 if you are using a vm86-based DOS emulator.\n", + current->comm, task_pid_nr(current), + from_kuid_munged(&init_user_ns, current_uid())); + return -EPERM; + } + + if (!vm86) { + if (!(vm86 = kzalloc(sizeof(*vm86), GFP_KERNEL))) + return -ENOMEM; + tsk->thread.vm86 = vm86; + } + if (vm86->saved_sp0) + return -EPERM; + + if (copy_from_user(&v, user_vm86, + offsetof(struct vm86_struct, int_revectored))) + return -EFAULT; + + + /* VM86_SCREEN_BITMAP had numerous bugs and appears to have no users. */ + if (v.flags & VM86_SCREEN_BITMAP) { + char comm[TASK_COMM_LEN]; + + pr_info_once("vm86: '%s' uses VM86_SCREEN_BITMAP, which is no longer supported\n", get_task_comm(comm, current)); + return -EINVAL; + } + + memset(&vm86regs, 0, sizeof(vm86regs)); + + vm86regs.pt.bx = v.regs.ebx; + vm86regs.pt.cx = v.regs.ecx; + vm86regs.pt.dx = v.regs.edx; + vm86regs.pt.si = v.regs.esi; + vm86regs.pt.di = v.regs.edi; + vm86regs.pt.bp = v.regs.ebp; + vm86regs.pt.ax = v.regs.eax; + vm86regs.pt.ip = v.regs.eip; + vm86regs.pt.cs = v.regs.cs; + vm86regs.pt.flags = v.regs.eflags; + vm86regs.pt.sp = v.regs.esp; + vm86regs.pt.ss = v.regs.ss; + vm86regs.es = v.regs.es; + vm86regs.ds = v.regs.ds; + vm86regs.fs = v.regs.fs; + vm86regs.gs = v.regs.gs; + + vm86->flags = v.flags; + vm86->cpu_type = v.cpu_type; + + if (copy_from_user(&vm86->int_revectored, + &user_vm86->int_revectored, + sizeof(struct revectored_struct))) + return -EFAULT; + if (copy_from_user(&vm86->int21_revectored, + &user_vm86->int21_revectored, + sizeof(struct revectored_struct))) + return -EFAULT; + if (plus) { + if (copy_from_user(&vm86->vm86plus, &user_vm86->vm86plus, + sizeof(struct vm86plus_info_struct))) + return -EFAULT; + vm86->vm86plus.is_vm86pus = 1; + } else + memset(&vm86->vm86plus, 0, + sizeof(struct vm86plus_info_struct)); + + memcpy(&vm86->regs32, regs, sizeof(struct pt_regs)); + vm86->user_vm86 = user_vm86; + +/* + * The flags register is also special: we cannot trust that the user + * has set it up safely, so this makes sure interrupt etc flags are + * inherited from protected mode. + */ + VEFLAGS = vm86regs.pt.flags; + vm86regs.pt.flags &= SAFE_MASK; + vm86regs.pt.flags |= regs->flags & ~SAFE_MASK; + vm86regs.pt.flags |= X86_VM_MASK; + + vm86regs.pt.orig_ax = regs->orig_ax; + + switch (vm86->cpu_type) { + case CPU_286: + vm86->veflags_mask = 0; + break; + case CPU_386: + vm86->veflags_mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL; + break; + case CPU_486: + vm86->veflags_mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + break; + default: + vm86->veflags_mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + break; + } + +/* + * Save old state + */ + vm86->saved_sp0 = tsk->thread.sp0; + savesegment(gs, vm86->regs32.gs); + + /* make room for real-mode segments */ + preempt_disable(); + tsk->thread.sp0 += 16; + + if (boot_cpu_has(X86_FEATURE_SEP)) { + tsk->thread.sysenter_cs = 0; + refresh_sysenter_cs(&tsk->thread); + } + + update_task_stack(tsk); + preempt_enable(); + + memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs)); + return regs->ax; +} + +static inline void set_IF(struct kernel_vm86_regs *regs) +{ + VEFLAGS |= X86_EFLAGS_VIF; +} + +static inline void clear_IF(struct kernel_vm86_regs *regs) +{ + VEFLAGS &= ~X86_EFLAGS_VIF; +} + +static inline void clear_TF(struct kernel_vm86_regs *regs) +{ + regs->pt.flags &= ~X86_EFLAGS_TF; +} + +static inline void clear_AC(struct kernel_vm86_regs *regs) +{ + regs->pt.flags &= ~X86_EFLAGS_AC; +} + +/* + * It is correct to call set_IF(regs) from the set_vflags_* + * functions. However someone forgot to call clear_IF(regs) + * in the opposite case. + * After the command sequence CLI PUSHF STI POPF you should + * end up with interrupts disabled, but you ended up with + * interrupts enabled. + * ( I was testing my own changes, but the only bug I + * could find was in a function I had not changed. ) + * [KD] + */ + +static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs *regs) +{ + set_flags(VEFLAGS, flags, current->thread.vm86->veflags_mask); + set_flags(regs->pt.flags, flags, SAFE_MASK); + if (flags & X86_EFLAGS_IF) + set_IF(regs); + else + clear_IF(regs); +} + +static inline void set_vflags_short(unsigned short flags, struct kernel_vm86_regs *regs) +{ + set_flags(VFLAGS, flags, current->thread.vm86->veflags_mask); + set_flags(regs->pt.flags, flags, SAFE_MASK); + if (flags & X86_EFLAGS_IF) + set_IF(regs); + else + clear_IF(regs); +} + +static inline unsigned long get_vflags(struct kernel_vm86_regs *regs) +{ + unsigned long flags = regs->pt.flags & RETURN_MASK; + + if (VEFLAGS & X86_EFLAGS_VIF) + flags |= X86_EFLAGS_IF; + flags |= X86_EFLAGS_IOPL; + return flags | (VEFLAGS & current->thread.vm86->veflags_mask); +} + +static inline int is_revectored(int nr, struct revectored_struct *bitmap) +{ + return test_bit(nr, bitmap->__map); +} + +#define val_byte(val, n) (((__u8 *)&val)[n]) + +#define pushb(base, ptr, val, err_label) \ + do { \ + __u8 __val = val; \ + ptr--; \ + if (put_user(__val, base + ptr) < 0) \ + goto err_label; \ + } while (0) + +#define pushw(base, ptr, val, err_label) \ + do { \ + __u16 __val = val; \ + ptr--; \ + if (put_user(val_byte(__val, 1), base + ptr) < 0) \ + goto err_label; \ + ptr--; \ + if (put_user(val_byte(__val, 0), base + ptr) < 0) \ + goto err_label; \ + } while (0) + +#define pushl(base, ptr, val, err_label) \ + do { \ + __u32 __val = val; \ + ptr--; \ + if (put_user(val_byte(__val, 3), base + ptr) < 0) \ + goto err_label; \ + ptr--; \ + if (put_user(val_byte(__val, 2), base + ptr) < 0) \ + goto err_label; \ + ptr--; \ + if (put_user(val_byte(__val, 1), base + ptr) < 0) \ + goto err_label; \ + ptr--; \ + if (put_user(val_byte(__val, 0), base + ptr) < 0) \ + goto err_label; \ + } while (0) + +#define popb(base, ptr, err_label) \ + ({ \ + __u8 __res; \ + if (get_user(__res, base + ptr) < 0) \ + goto err_label; \ + ptr++; \ + __res; \ + }) + +#define popw(base, ptr, err_label) \ + ({ \ + __u16 __res; \ + if (get_user(val_byte(__res, 0), base + ptr) < 0) \ + goto err_label; \ + ptr++; \ + if (get_user(val_byte(__res, 1), base + ptr) < 0) \ + goto err_label; \ + ptr++; \ + __res; \ + }) + +#define popl(base, ptr, err_label) \ + ({ \ + __u32 __res; \ + if (get_user(val_byte(__res, 0), base + ptr) < 0) \ + goto err_label; \ + ptr++; \ + if (get_user(val_byte(__res, 1), base + ptr) < 0) \ + goto err_label; \ + ptr++; \ + if (get_user(val_byte(__res, 2), base + ptr) < 0) \ + goto err_label; \ + ptr++; \ + if (get_user(val_byte(__res, 3), base + ptr) < 0) \ + goto err_label; \ + ptr++; \ + __res; \ + }) + +/* There are so many possible reasons for this function to return + * VM86_INTx, so adding another doesn't bother me. We can expect + * userspace programs to be able to handle it. (Getting a problem + * in userspace is always better than an Oops anyway.) [KD] + */ +static void do_int(struct kernel_vm86_regs *regs, int i, + unsigned char __user *ssp, unsigned short sp) +{ + unsigned long __user *intr_ptr; + unsigned long segoffs; + struct vm86 *vm86 = current->thread.vm86; + + if (regs->pt.cs == BIOSSEG) + goto cannot_handle; + if (is_revectored(i, &vm86->int_revectored)) + goto cannot_handle; + if (i == 0x21 && is_revectored(AH(regs), &vm86->int21_revectored)) + goto cannot_handle; + intr_ptr = (unsigned long __user *) (i << 2); + if (get_user(segoffs, intr_ptr)) + goto cannot_handle; + if ((segoffs >> 16) == BIOSSEG) + goto cannot_handle; + pushw(ssp, sp, get_vflags(regs), cannot_handle); + pushw(ssp, sp, regs->pt.cs, cannot_handle); + pushw(ssp, sp, IP(regs), cannot_handle); + regs->pt.cs = segoffs >> 16; + SP(regs) -= 6; + IP(regs) = segoffs & 0xffff; + clear_TF(regs); + clear_IF(regs); + clear_AC(regs); + return; + +cannot_handle: + save_v86_state(regs, VM86_INTx + (i << 8)); +} + +int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno) +{ + struct vm86 *vm86 = current->thread.vm86; + + if (vm86->vm86plus.is_vm86pus) { + if ((trapno == 3) || (trapno == 1)) { + save_v86_state(regs, VM86_TRAP + (trapno << 8)); + return 0; + } + do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs)); + return 0; + } + if (trapno != 1) + return 1; /* we let this handle by the calling routine */ + current->thread.trap_nr = trapno; + current->thread.error_code = error_code; + force_sig(SIGTRAP); + return 0; +} + +void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) +{ + unsigned char opcode; + unsigned char __user *csp; + unsigned char __user *ssp; + unsigned short ip, sp, orig_flags; + int data32, pref_done; + struct vm86plus_info_struct *vmpi = ¤t->thread.vm86->vm86plus; + +#define CHECK_IF_IN_TRAP \ + if (vmpi->vm86dbg_active && vmpi->vm86dbg_TFpendig) \ + newflags |= X86_EFLAGS_TF + + orig_flags = *(unsigned short *)®s->pt.flags; + + csp = (unsigned char __user *) (regs->pt.cs << 4); + ssp = (unsigned char __user *) (regs->pt.ss << 4); + sp = SP(regs); + ip = IP(regs); + + data32 = 0; + pref_done = 0; + do { + switch (opcode = popb(csp, ip, simulate_sigsegv)) { + case 0x66: /* 32-bit data */ data32 = 1; break; + case 0x67: /* 32-bit address */ break; + case 0x2e: /* CS */ break; + case 0x3e: /* DS */ break; + case 0x26: /* ES */ break; + case 0x36: /* SS */ break; + case 0x65: /* GS */ break; + case 0x64: /* FS */ break; + case 0xf2: /* repnz */ break; + case 0xf3: /* rep */ break; + default: pref_done = 1; + } + } while (!pref_done); + + switch (opcode) { + + /* pushf */ + case 0x9c: + if (data32) { + pushl(ssp, sp, get_vflags(regs), simulate_sigsegv); + SP(regs) -= 4; + } else { + pushw(ssp, sp, get_vflags(regs), simulate_sigsegv); + SP(regs) -= 2; + } + IP(regs) = ip; + goto vm86_fault_return; + + /* popf */ + case 0x9d: + { + unsigned long newflags; + if (data32) { + newflags = popl(ssp, sp, simulate_sigsegv); + SP(regs) += 4; + } else { + newflags = popw(ssp, sp, simulate_sigsegv); + SP(regs) += 2; + } + IP(regs) = ip; + CHECK_IF_IN_TRAP; + if (data32) + set_vflags_long(newflags, regs); + else + set_vflags_short(newflags, regs); + + goto check_vip; + } + + /* int xx */ + case 0xcd: { + int intno = popb(csp, ip, simulate_sigsegv); + IP(regs) = ip; + if (vmpi->vm86dbg_active) { + if ((1 << (intno & 7)) & vmpi->vm86dbg_intxxtab[intno >> 3]) { + save_v86_state(regs, VM86_INTx + (intno << 8)); + return; + } + } + do_int(regs, intno, ssp, sp); + return; + } + + /* iret */ + case 0xcf: + { + unsigned long newip; + unsigned long newcs; + unsigned long newflags; + if (data32) { + newip = popl(ssp, sp, simulate_sigsegv); + newcs = popl(ssp, sp, simulate_sigsegv); + newflags = popl(ssp, sp, simulate_sigsegv); + SP(regs) += 12; + } else { + newip = popw(ssp, sp, simulate_sigsegv); + newcs = popw(ssp, sp, simulate_sigsegv); + newflags = popw(ssp, sp, simulate_sigsegv); + SP(regs) += 6; + } + IP(regs) = newip; + regs->pt.cs = newcs; + CHECK_IF_IN_TRAP; + if (data32) { + set_vflags_long(newflags, regs); + } else { + set_vflags_short(newflags, regs); + } + goto check_vip; + } + + /* cli */ + case 0xfa: + IP(regs) = ip; + clear_IF(regs); + goto vm86_fault_return; + + /* sti */ + /* + * Damn. This is incorrect: the 'sti' instruction should actually + * enable interrupts after the /next/ instruction. Not good. + * + * Probably needs some horsing around with the TF flag. Aiee.. + */ + case 0xfb: + IP(regs) = ip; + set_IF(regs); + goto check_vip; + + default: + save_v86_state(regs, VM86_UNKNOWN); + } + + return; + +check_vip: + if ((VEFLAGS & (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) == + (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) { + save_v86_state(regs, VM86_STI); + return; + } + +vm86_fault_return: + if (vmpi->force_return_for_pic && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) { + save_v86_state(regs, VM86_PICRETURN); + return; + } + if (orig_flags & X86_EFLAGS_TF) + handle_vm86_trap(regs, 0, X86_TRAP_DB); + return; + +simulate_sigsegv: + /* FIXME: After a long discussion with Stas we finally + * agreed, that this is wrong. Here we should + * really send a SIGSEGV to the user program. + * But how do we create the correct context? We + * are inside a general protection fault handler + * and has just returned from a page fault handler. + * The correct context for the signal handler + * should be a mixture of the two, but how do we + * get the information? [KD] + */ + save_v86_state(regs, VM86_UNKNOWN); +} + +/* ---------------- vm86 special IRQ passing stuff ----------------- */ + +#define VM86_IRQNAME "vm86irq" + +static struct vm86_irqs { + struct task_struct *tsk; + int sig; +} vm86_irqs[16]; + +static DEFINE_SPINLOCK(irqbits_lock); +static int irqbits; + +#define ALLOWED_SIGS (1 /* 0 = don't send a signal */ \ + | (1 << SIGUSR1) | (1 << SIGUSR2) | (1 << SIGIO) | (1 << SIGURG) \ + | (1 << SIGUNUSED)) + +static irqreturn_t irq_handler(int intno, void *dev_id) +{ + int irq_bit; + unsigned long flags; + + spin_lock_irqsave(&irqbits_lock, flags); + irq_bit = 1 << intno; + if ((irqbits & irq_bit) || !vm86_irqs[intno].tsk) + goto out; + irqbits |= irq_bit; + if (vm86_irqs[intno].sig) + send_sig(vm86_irqs[intno].sig, vm86_irqs[intno].tsk, 1); + /* + * IRQ will be re-enabled when user asks for the irq (whether + * polling or as a result of the signal) + */ + disable_irq_nosync(intno); + spin_unlock_irqrestore(&irqbits_lock, flags); + return IRQ_HANDLED; + +out: + spin_unlock_irqrestore(&irqbits_lock, flags); + return IRQ_NONE; +} + +static inline void free_vm86_irq(int irqnumber) +{ + unsigned long flags; + + free_irq(irqnumber, NULL); + vm86_irqs[irqnumber].tsk = NULL; + + spin_lock_irqsave(&irqbits_lock, flags); + irqbits &= ~(1 << irqnumber); + spin_unlock_irqrestore(&irqbits_lock, flags); +} + +void release_vm86_irqs(struct task_struct *task) +{ + int i; + for (i = FIRST_VM86_IRQ ; i <= LAST_VM86_IRQ; i++) + if (vm86_irqs[i].tsk == task) + free_vm86_irq(i); +} + +static inline int get_and_reset_irq(int irqnumber) +{ + int bit; + unsigned long flags; + int ret = 0; + + if (invalid_vm86_irq(irqnumber)) return 0; + if (vm86_irqs[irqnumber].tsk != current) return 0; + spin_lock_irqsave(&irqbits_lock, flags); + bit = irqbits & (1 << irqnumber); + irqbits &= ~bit; + if (bit) { + enable_irq(irqnumber); + ret = 1; + } + + spin_unlock_irqrestore(&irqbits_lock, flags); + return ret; +} + + +static int do_vm86_irq_handling(int subfunction, int irqnumber) +{ + int ret; + switch (subfunction) { + case VM86_GET_AND_RESET_IRQ: { + return get_and_reset_irq(irqnumber); + } + case VM86_GET_IRQ_BITS: { + return irqbits; + } + case VM86_REQUEST_IRQ: { + int sig = irqnumber >> 8; + int irq = irqnumber & 255; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!((1 << sig) & ALLOWED_SIGS)) return -EPERM; + if (invalid_vm86_irq(irq)) return -EPERM; + if (vm86_irqs[irq].tsk) return -EPERM; + ret = request_irq(irq, &irq_handler, 0, VM86_IRQNAME, NULL); + if (ret) return ret; + vm86_irqs[irq].sig = sig; + vm86_irqs[irq].tsk = current; + return irq; + } + case VM86_FREE_IRQ: { + if (invalid_vm86_irq(irqnumber)) return -EPERM; + if (!vm86_irqs[irqnumber].tsk) return 0; + if (vm86_irqs[irqnumber].tsk != current) return -EPERM; + free_vm86_irq(irqnumber); + return 0; + } + } + return -EINVAL; +} + -- cgit v1.2.3