diff options
Diffstat (limited to 'arch/x86')
36 files changed, 1352 insertions, 846 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3dbb7e7909ca..b3a1a5d77d92 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -41,6 +41,7 @@ config X86 select ARCH_USE_CMPXCHG_LOCKREF if X86_64 select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS + select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_IPC_PARSE_VERSION if X86_32 select ARCH_WANT_OPTIONAL_GPIOLIB diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index a15893d17c55..d8c0d3266173 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -297,6 +297,18 @@ config OPTIMIZE_INLINING If unsure, say N. +config DEBUG_ENTRY + bool "Debug low-level entry code" + depends on DEBUG_KERNEL + ---help--- + This option enables sanity checks in x86's low-level entry code. + Some of these sanity checks may slow down kernel entries and + exits or otherwise impact performance. + + This is currently used to help test NMI code. + + If unsure, say N. + config DEBUG_NMI_SELFTEST bool "NMI Selftest" depends on DEBUG_KERNEL && X86_LOCAL_APIC diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 3bb2c4302df1..8cb3e438f21e 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1237,11 +1237,12 @@ ENTRY(nmi) * If the variable is not set and the stack is not the NMI * stack then: * o Set the special variable on the stack - * o Copy the interrupt frame into a "saved" location on the stack - * o Copy the interrupt frame into a "copy" location on the stack + * o Copy the interrupt frame into an "outermost" location on the + * stack + * o Copy the interrupt frame into an "iret" location on the stack * o Continue processing the NMI * If the variable is set or the previous stack is the NMI stack: - * o Modify the "copy" location to jump to the repeate_nmi + * o Modify the "iret" location to jump to the repeat_nmi * o return back to the first NMI * * Now on exit of the first NMI, we first clear the stack variable @@ -1250,31 +1251,151 @@ ENTRY(nmi) * a nested NMI that updated the copy interrupt stack frame, a * jump will be made to the repeat_nmi code that will handle the second * NMI. + * + * However, espfix prevents us from directly returning to userspace + * with a single IRET instruction. Similarly, IRET to user mode + * can fault. We therefore handle NMIs from user space like + * other IST entries. */ /* Use %rdx as our temp variable throughout */ pushq %rdx + testb $3, CS-RIP+8(%rsp) + jz .Lnmi_from_kernel + + /* + * NMI from user mode. We need to run on the thread stack, but we + * can't go through the normal entry paths: NMIs are masked, and + * we don't want to enable interrupts, because then we'll end + * up in an awkward situation in which IRQs are on but NMIs + * are off. + */ + + SWAPGS + cld + movq %rsp, %rdx + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + pushq 5*8(%rdx) /* pt_regs->ss */ + pushq 4*8(%rdx) /* pt_regs->rsp */ + pushq 3*8(%rdx) /* pt_regs->flags */ + pushq 2*8(%rdx) /* pt_regs->cs */ + pushq 1*8(%rdx) /* pt_regs->rip */ + pushq $-1 /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq (%rdx) /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq %rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + pushq %r9 /* pt_regs->r9 */ + pushq %r10 /* pt_regs->r10 */ + pushq %r11 /* pt_regs->r11 */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ + + /* + * At this point we no longer need to worry about stack damage + * due to nesting -- we're on the normal thread stack and we're + * done with the NMI stack. + */ + + movq %rsp, %rdi + movq $-1, %rsi + call do_nmi + + /* + * Return back to user mode. We must *not* do the normal exit + * work, because we don't want to enable interrupts. Fortunately, + * do_nmi doesn't modify pt_regs. + */ + SWAPGS + jmp restore_c_regs_and_iret + +.Lnmi_from_kernel: + /* + * Here's what our stack frame will look like: + * +---------------------------------------------------------+ + * | original SS | + * | original Return RSP | + * | original RFLAGS | + * | original CS | + * | original RIP | + * +---------------------------------------------------------+ + * | temp storage for rdx | + * +---------------------------------------------------------+ + * | "NMI executing" variable | + * +---------------------------------------------------------+ + * | iret SS } Copied from "outermost" frame | + * | iret Return RSP } on each loop iteration; overwritten | + * | iret RFLAGS } by a nested NMI to force another | + * | iret CS } iteration if needed. | + * | iret RIP } | + * +---------------------------------------------------------+ + * | outermost SS } initialized in first_nmi; | + * | outermost Return RSP } will not be changed before | + * | outermost RFLAGS } NMI processing is done. | + * | outermost CS } Copied to "iret" frame on each | + * | outermost RIP } iteration. | + * +---------------------------------------------------------+ + * | pt_regs | + * +---------------------------------------------------------+ + * + * The "original" frame is used by hardware. Before re-enabling + * NMIs, we need to be done with it, and we need to leave enough + * space for the asm code here. + * + * We return by executing IRET while RSP points to the "iret" frame. + * That will either return for real or it will loop back into NMI + * processing. + * + * The "outermost" frame is copied to the "iret" frame on each + * iteration of the loop, so each iteration starts with the "iret" + * frame pointing to the final return target. + */ + /* - * If %cs was not the kernel segment, then the NMI triggered in user - * space, which means it is definitely not nested. + * Determine whether we're a nested NMI. + * + * If we interrupted kernel code between repeat_nmi and + * end_repeat_nmi, then we are a nested NMI. We must not + * modify the "iret" frame because it's being written by + * the outer NMI. That's okay; the outer NMI handler is + * about to about to call do_nmi anyway, so we can just + * resume the outer NMI. */ - cmpl $__KERNEL_CS, 16(%rsp) - jne first_nmi + + movq $repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja 1f + movq $end_repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja nested_nmi_out +1: /* - * Check the special variable on the stack to see if NMIs are - * executing. + * Now check "NMI executing". If it's set, then we're nested. + * This will not detect if we interrupted an outer NMI just + * before IRET. */ cmpl $1, -8(%rsp) je nested_nmi /* - * Now test if the previous stack was an NMI stack. - * We need the double check. We check the NMI stack to satisfy the - * race when the first NMI clears the variable before returning. - * We check the variable because the first NMI could be in a - * breakpoint routine using a breakpoint stack. + * Now test if the previous stack was an NMI stack. This covers + * the case where we interrupt an outer NMI after it clears + * "NMI executing" but before IRET. We need to be careful, though: + * there is one case in which RSP could point to the NMI stack + * despite there being no NMI active: naughty userspace controls + * RSP at the very beginning of the SYSCALL targets. We can + * pull a fast one on naughty userspace, though: we program + * SYSCALL to mask DF, so userspace cannot cause DF to be set + * if it controls the kernel's RSP. We set DF before we clear + * "NMI executing". */ lea 6*8(%rsp), %rdx /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */ @@ -1286,25 +1407,20 @@ ENTRY(nmi) cmpq %rdx, 4*8(%rsp) /* If it is below the NMI stack, it is a normal NMI */ jb first_nmi - /* Ah, it is within the NMI stack, treat it as nested */ + + /* Ah, it is within the NMI stack. */ + + testb $(X86_EFLAGS_DF >> 8), (3*8 + 1)(%rsp) + jz first_nmi /* RSP was user controlled. */ + + /* This is a nested NMI. */ nested_nmi: /* - * Do nothing if we interrupted the fixup in repeat_nmi. - * It's about to repeat the NMI handler, so we are fine - * with ignoring this one. + * Modify the "iret" frame to point to repeat_nmi, forcing another + * iteration of NMI handling. */ - movq $repeat_nmi, %rdx - cmpq 8(%rsp), %rdx - ja 1f - movq $end_repeat_nmi, %rdx - cmpq 8(%rsp), %rdx - ja nested_nmi_out - -1: - /* Set up the interrupted NMIs stack to jump to repeat_nmi */ - leaq -1*8(%rsp), %rdx - movq %rdx, %rsp + subq $8, %rsp leaq -10*8(%rsp), %rdx pushq $__KERNEL_DS pushq %rdx @@ -1318,61 +1434,42 @@ nested_nmi: nested_nmi_out: popq %rdx - /* No need to check faults here */ + /* We are returning to kernel mode, so this cannot result in a fault. */ INTERRUPT_RETURN first_nmi: - /* - * Because nested NMIs will use the pushed location that we - * stored in rdx, we must keep that space available. - * Here's what our stack frame will look like: - * +-------------------------+ - * | original SS | - * | original Return RSP | - * | original RFLAGS | - * | original CS | - * | original RIP | - * +-------------------------+ - * | temp storage for rdx | - * +-------------------------+ - * | NMI executing variable | - * +-------------------------+ - * | copied SS | - * | copied Return RSP | - * | copied RFLAGS | - * | copied CS | - * | copied RIP | - * +-------------------------+ - * | Saved SS | - * | Saved Return RSP | - * | Saved RFLAGS | - * | Saved CS | - * | Saved RIP | - * +-------------------------+ - * | pt_regs | - * +-------------------------+ - * - * The saved stack frame is used to fix up the copied stack frame - * that a nested NMI may change to make the interrupted NMI iret jump - * to the repeat_nmi. The original stack frame and the temp storage - * is also used by nested NMIs and can not be trusted on exit. - */ - /* Do not pop rdx, nested NMIs will corrupt that part of the stack */ + /* Restore rdx. */ movq (%rsp), %rdx - /* Set the NMI executing variable on the stack. */ - pushq $1 + /* Make room for "NMI executing". */ + pushq $0 - /* Leave room for the "copied" frame */ + /* Leave room for the "iret" frame */ subq $(5*8), %rsp - /* Copy the stack frame to the Saved frame */ + /* Copy the "original" frame to the "outermost" frame */ .rept 5 pushq 11*8(%rsp) .endr /* Everything up to here is safe from nested NMIs */ +#ifdef CONFIG_DEBUG_ENTRY + /* + * For ease of testing, unmask NMIs right away. Disabled by + * default because IRET is very expensive. + */ + pushq $0 /* SS */ + pushq %rsp /* RSP (minus 8 because of the previous push) */ + addq $8, (%rsp) /* Fix up RSP */ + pushfq /* RFLAGS */ + pushq $__KERNEL_CS /* CS */ + pushq $1f /* RIP */ + INTERRUPT_RETURN /* continues at repeat_nmi below */ +1: +#endif + +repeat_nmi: /* * If there was a nested NMI, the first NMI's iret will return * here. But NMIs are still enabled and we can take another @@ -1381,16 +1478,20 @@ first_nmi: * it will just return, as we are about to repeat an NMI anyway. * This makes it safe to copy to the stack frame that a nested * NMI will update. + * + * RSP is pointing to "outermost RIP". gsbase is unknown, but, if + * we're repeating an NMI, gsbase has the same value that it had on + * the first iteration. paranoid_entry will load the kernel + * gsbase if needed before we call do_nmi. "NMI executing" + * is zero. */ -repeat_nmi: + movq $1, 10*8(%rsp) /* Set "NMI executing". */ + /* - * Update the stack variable to say we are still in NMI (the update - * is benign for the non-repeat case, where 1 was pushed just above - * to this very stack slot). + * Copy the "outermost" frame to the "iret" frame. NMIs that nest + * here must not modify the "iret" frame while we're writing to + * it or it will end up containing garbage. */ - movq $1, 10*8(%rsp) - - /* Make another copy, this one may be modified by nested NMIs */ addq $(10*8), %rsp .rept 5 pushq -6*8(%rsp) @@ -1399,9 +1500,9 @@ repeat_nmi: end_repeat_nmi: /* - * Everything below this point can be preempted by a nested - * NMI if the first NMI took an exception and reset our iret stack - * so that we repeat another NMI. + * Everything below this point can be preempted by a nested NMI. + * If this happens, then the inner NMI will change the "iret" + * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ ALLOC_PT_GPREGS_ON_STACK @@ -1415,28 +1516,11 @@ end_repeat_nmi: */ call paranoid_entry - /* - * Save off the CR2 register. If we take a page fault in the NMI then - * it could corrupt the CR2 value. If the NMI preempts a page fault - * handler before it was able to read the CR2 register, and then the - * NMI itself takes a page fault, the page fault that was preempted - * will read the information from the NMI page fault and not the - * origin fault. Save it off and restore it if it changes. - * Use the r12 callee-saved register. - */ - movq %cr2, %r12 - /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp, %rdi movq $-1, %rsi call do_nmi - /* Did the NMI take a page fault? Restore cr2 if it did */ - movq %cr2, %rcx - cmpq %rcx, %r12 - je 1f - movq %r12, %cr2 -1: testl %ebx, %ebx /* swapgs needed? */ jnz nmi_restore nmi_swapgs: @@ -1444,11 +1528,26 @@ nmi_swapgs: nmi_restore: RESTORE_EXTRA_REGS RESTORE_C_REGS - /* Pop the extra iret frame at once */ + + /* Point RSP at the "iret" frame. */ REMOVE_PT_GPREGS_FROM_STACK 6*8 - /* Clear the NMI executing stack variable */ - movq $0, 5*8(%rsp) + /* + * Clear "NMI executing". Set DF first so that we can easily + * distinguish the remaining code between here and IRET from + * the SYSCALL entry and exit paths. On a native kernel, we + * could just inspect RIP, but, on paravirt kernels, + * INTERRUPT_RETURN can translate into a jump into a + * hypercall page. + */ + std + movq $0, 5*8(%rsp) /* clear "NMI executing" */ + + /* + * INTERRUPT_RETURN reads the "iret" frame and exits the NMI + * stack in a single instruction. We are returning to kernel + * mode, so this cannot result in a fault. + */ INTERRUPT_RETURN END(nmi) diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 4dd1f2d770af..aeac434c9feb 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -9,3 +9,4 @@ generic-y += cputime.h generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h +generic-y += mm-arch-hooks.h diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 0637826292de..c49c5173158e 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -189,6 +189,7 @@ union fpregs_state { struct fxregs_state fxsave; struct swregs_state soft; struct xregs_state xsave; + u8 __padding[PAGE_SIZE]; }; /* @@ -198,40 +199,6 @@ union fpregs_state { */ struct fpu { /* - * @state: - * - * In-memory copy of all FPU registers that we save/restore - * over context switches. If the task is using the FPU then - * the registers in the FPU are more recent than this state - * copy. If the task context-switches away then they get - * saved here and represent the FPU state. - * - * After context switches there may be a (short) time period - * during which the in-FPU hardware registers are unchanged - * and still perfectly match this state, if the tasks - * scheduled afterwards are not using the FPU. - * - * This is the 'lazy restore' window of optimization, which - * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'. - * - * We detect whether a subsequent task uses the FPU via setting - * CR0::TS to 1, which causes any FPU use to raise a #NM fault. - * - * During this window, if the task gets scheduled again, we - * might be able to skip having to do a restore from this - * memory buffer to the hardware registers - at the cost of - * incurring the overhead of #NM fault traps. - * - * Note that on modern CPUs that support the XSAVEOPT (or other - * optimized XSAVE instructions), we don't use #NM traps anymore, - * as the hardware can track whether FPU registers need saving - * or not. On such CPUs we activate the non-lazy ('eagerfpu') - * logic, which unconditionally saves/restores all FPU state - * across context switches. (if FPU state exists.) - */ - union fpregs_state state; - - /* * @last_cpu: * * Records the last CPU on which this context was loaded into @@ -288,6 +255,43 @@ struct fpu { * deal with bursty apps that only use the FPU for a short time: */ unsigned char counter; + /* + * @state: + * + * In-memory copy of all FPU registers that we save/restore + * over context switches. If the task is using the FPU then + * the registers in the FPU are more recent than this state + * copy. If the task context-switches away then they get + * saved here and represent the FPU state. + * + * After context switches there may be a (short) time period + * during which the in-FPU hardware registers are unchanged + * and still perfectly match this state, if the tasks + * scheduled afterwards are not using the FPU. + * + * This is the 'lazy restore' window of optimization, which + * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'. + * + * We detect whether a subsequent task uses the FPU via setting + * CR0::TS to 1, which causes any FPU use to raise a #NM fault. + * + * During this window, if the task gets scheduled again, we + * might be able to skip having to do a restore from this + * memory buffer to the hardware registers - at the cost of + * incurring the overhead of #NM fault traps. + * + * Note that on modern CPUs that support the XSAVEOPT (or other + * optimized XSAVE instructions), we don't use #NM traps anymore, + * as the hardware can track whether FPU registers need saving + * or not. On such CPUs we activate the non-lazy ('eagerfpu') + * logic, which unconditionally saves/restores all FPU state + * across context switches. (if FPU state exists.) + */ + union fpregs_state state; + /* + * WARNING: 'state' is dynamically-sized. Do not put + * anything after it here. + */ }; #endif /* _ASM_X86_FPU_H */ diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h index 200ec2e7821d..cd0310e186f4 100644 --- a/arch/x86/include/asm/intel_pmc_ipc.h +++ b/arch/x86/include/asm/intel_pmc_ipc.h @@ -25,36 +25,9 @@ #if IS_ENABLED(CONFIG_INTEL_PMC_IPC) -/* - * intel_pmc_ipc_simple_command - * @cmd: command - * @sub: sub type - */ int intel_pmc_ipc_simple_command(int cmd, int sub); - -/* - * intel_pmc_ipc_raw_cmd - * @cmd: command - * @sub: sub type - * @in: input data - * @inlen: input length in bytes - * @out: output data - * @outlen: output length in dwords - * @sptr: data writing to SPTR register - * @dptr: data writing to DPTR register - */ int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out, u32 outlen, u32 dptr, u32 sptr); - -/* - * intel_pmc_ipc_command - * @cmd: command - * @sub: sub type - * @in: input data - * @inlen: input length in bytes - * @out: output data - * @outlen: output length in dwords - */ int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out, u32 outlen); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2a7f5d782c33..c12e845f59e6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -252,6 +252,11 @@ struct kvm_pio_request { int size; }; +struct rsvd_bits_validate { + u64 rsvd_bits_mask[2][4]; + u64 bad_mt_xwr; +}; + /* * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level * 32-bit). The kvm_mmu structure abstracts the details of the current mmu @@ -289,8 +294,15 @@ struct kvm_mmu { u64 *pae_root; u64 *lm_root; - u64 rsvd_bits_mask[2][4]; - u64 bad_mt_xwr; + + /* + * check zero bits on shadow page table entries, these + * bits include not only hardware reserved bits but also + * the bits spte never used. + */ + struct rsvd_bits_validate shadow_zero_check; + + struct rsvd_bits_validate guest_rsvd_check; /* * Bitmap: bit set = last pte in walk @@ -358,6 +370,11 @@ struct kvm_mtrr { struct list_head head; }; +/* Hyper-V per vcpu emulation context */ +struct kvm_vcpu_hv { + u64 hv_vapic; +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -514,8 +531,7 @@ struct kvm_vcpu_arch { /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; - /* fields used by HYPER-V emulation */ - u64 hv_vapic; + struct kvm_vcpu_hv hyperv; cpumask_var_t wbinvd_dirty_mask; @@ -586,6 +602,17 @@ struct kvm_apic_map { struct kvm_lapic *logical_map[16][16]; }; +/* Hyper-V emulation context */ +struct kvm_hv { + u64 hv_guest_os_id; + u64 hv_hypercall; + u64 hv_tsc_page; + + /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ + u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; + u64 hv_crash_ctl; +}; + struct kvm_arch { unsigned int n_used_mmu_pages; unsigned int n_requested_mmu_pages; @@ -604,6 +631,8 @@ struct kvm_arch { bool iommu_noncoherent; #define __KVM_HAVE_ARCH_NONCOHERENT_DMA atomic_t noncoherent_dma_count; +#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE + atomic_t assigned_device_count; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; @@ -643,16 +672,14 @@ struct kvm_arch { /* reads protected by irq_srcu, writes by irq_lock */ struct hlist_head mask_notifier_list; - /* fields used by HYPER-V emulation */ - u64 hv_guest_os_id; - u64 hv_hypercall; - u64 hv_tsc_page; + struct kvm_hv hyperv; #ifdef CONFIG_KVM_MMU_AUDIT int audit_point; #endif bool boot_vcpu_runs_old_kvmclock; + u32 bsp_vcpu_id; u64 disabled_quirks; }; @@ -1201,5 +1228,7 @@ int __x86_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem); int x86_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem); +bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); +bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/mm-arch-hooks.h b/arch/x86/include/asm/mm-arch-hooks.h deleted file mode 100644 index 4e881a342236..000000000000 --- a/arch/x86/include/asm/mm-arch-hooks.h +++ /dev/null @@ -1,15 +0,0 @@ -/* - * Architecture specific mm hooks - * - * Copyright (C) 2015, IBM Corporation - * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef _ASM_X86_MM_ARCH_HOOKS_H -#define _ASM_X86_MM_ARCH_HOOKS_H - -#endif /* _ASM_X86_MM_ARCH_HOOKS_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 5e8daee7c5c9..804a3a6030ca 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -23,7 +23,7 @@ extern struct static_key rdpmc_always_available; static inline void load_mm_cr4(struct mm_struct *mm) { - if (static_key_true(&rdpmc_always_available) || + if (static_key_false(&rdpmc_always_available) || atomic_read(&mm->context.perf_rdpmc_allowed)) cr4_set_bits(X86_CR4_PCE); else diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 43e6519df0d5..944f1785ed0d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -390,9 +390,6 @@ struct thread_struct { #endif unsigned long gs; - /* Floating point and extended processor state */ - struct fpu fpu; - /* Save middle states of ptrace breakpoints */ struct perf_event *ptrace_bps[HBP_NUM]; /* Debug status used for traps, single steps, etc... */ @@ -418,6 +415,13 @@ struct thread_struct { unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; + + /* Floating point and extended processor state */ + struct fpu fpu; + /* + * WARNING: 'fpu' is dynamically-sized. It *MUST* be at + * the end. + */ }; /* diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index da772edd19ab..448b7ca61aee 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -47,6 +47,7 @@ #define CPU_BASED_MOV_DR_EXITING 0x00800000 #define CPU_BASED_UNCOND_IO_EXITING 0x01000000 #define CPU_BASED_USE_IO_BITMAPS 0x02000000 +#define CPU_BASED_MONITOR_TRAP_FLAG 0x08000000 #define CPU_BASED_USE_MSR_BITMAPS 0x10000000 #define CPU_BASED_MONITOR_EXITING 0x20000000 #define CPU_BASED_PAUSE_EXITING 0x40000000 @@ -367,29 +368,29 @@ enum vmcs_field { #define TYPE_PHYSICAL_APIC_EVENT (10 << 12) #define TYPE_PHYSICAL_APIC_INST (15 << 12) -/* segment AR */ -#define SEGMENT_AR_L_MASK (1 << 13) - -#define AR_TYPE_ACCESSES_MASK 1 -#define AR_TYPE_READABLE_MASK (1 << 1) -#define AR_TYPE_WRITEABLE_MASK (1 << 2) -#define AR_TYPE_CODE_MASK (1 << 3) -#define AR_TYPE_MASK 0x0f -#define AR_TYPE_BUSY_64_TSS 11 -#define AR_TYPE_BUSY_32_TSS 11 -#define AR_TYPE_BUSY_16_TSS 3 -#define AR_TYPE_LDT 2 - -#define AR_UNUSABLE_MASK (1 << 16) -#define AR_S_MASK (1 << 4) -#define AR_P_MASK (1 << 7) -#define AR_L_MASK (1 << 13) -#define AR_DB_MASK (1 << 14) -#define AR_G_MASK (1 << 15) -#define AR_DPL_SHIFT 5 -#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3) - -#define AR_RESERVD_MASK 0xfffe0f00 +/* segment AR in VMCS -- these are different from what LAR reports */ +#define VMX_SEGMENT_AR_L_MASK (1 << 13) + +#define VMX_AR_TYPE_ACCESSES_MASK 1 +#define VMX_AR_TYPE_READABLE_MASK (1 << 1) +#define VMX_AR_TYPE_WRITEABLE_MASK (1 << 2) +#define VMX_AR_TYPE_CODE_MASK (1 << 3) +#define VMX_AR_TYPE_MASK 0x0f +#define VMX_AR_TYPE_BUSY_64_TSS 11 +#define VMX_AR_TYPE_BUSY_32_TSS 11 +#define VMX_AR_TYPE_BUSY_16_TSS 3 +#define VMX_AR_TYPE_LDT 2 + +#define VMX_AR_UNUSABLE_MASK (1 << 16) +#define VMX_AR_S_MASK (1 << 4) +#define VMX_AR_P_MASK (1 << 7) +#define VMX_AR_L_MASK (1 << 13) +#define VMX_AR_DB_MASK (1 << 14) +#define VMX_AR_G_MASK (1 << 15) +#define VMX_AR_DPL_SHIFT 5 +#define VMX_AR_DPL(ar) (((ar) >> VMX_AR_DPL_SHIFT) & 3) + +#define VMX_AR_RESERVD_MASK 0xfffe0f00 #define TSS_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 0) #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 1) diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 8fba544e9cc4..f36d56bd7632 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -108,6 +108,8 @@ #define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE (1 << 4) /* Support for a virtual guest idle state is available */ #define HV_X64_GUEST_IDLE_STATE_AVAILABLE (1 << 5) +/* Guest crash data handler available */ +#define HV_X64_GUEST_CRASH_MSR_AVAILABLE (1 << 10) /* * Implementation recommendations. Indicates which behaviors the hypervisor diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index a4ae82eb82aa..cd54147cb365 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -354,7 +354,7 @@ struct kvm_xcrs { struct kvm_sync_regs { }; -#define KVM_QUIRK_LINT0_REENABLED (1 << 0) -#define KVM_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) +#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 1fe92181ee9e..37fee272618f 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -58,6 +58,7 @@ #define EXIT_REASON_INVALID_STATE 33 #define EXIT_REASON_MSR_LOAD_FAIL 34 #define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_MONITOR_TRAP_FLAG 37 #define EXIT_REASON_MONITOR_INSTRUCTION 39 #define EXIT_REASON_PAUSE_INSTRUCTION 40 #define EXIT_REASON_MCE_DURING_VMENTRY 41 @@ -106,6 +107,7 @@ { EXIT_REASON_MSR_READ, "MSR_READ" }, \ { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ + { EXIT_REASON_MONITOR_TRAP_FLAG, "MONITOR_TRAP_FLAG" }, \ { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 32826791e675..0b39173dd971 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -4,6 +4,8 @@ #include <asm/fpu/internal.h> #include <asm/tlbflush.h> +#include <linux/sched.h> + /* * Initialize the TS bit in CR0 according to the style of context-switches * we are using: @@ -136,6 +138,43 @@ static void __init fpu__init_system_generic(void) unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); +/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ + BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) + +/* + * We append the 'struct fpu' to the task_struct: + */ +static void __init fpu__init_task_struct_size(void) +{ + int task_size = sizeof(struct task_struct); + + /* + * Subtract off the static size of the register state. + * It potentially has a bunch of padding. + */ + task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state); + + /* + * Add back the dynamically-calculated register state + * size. + */ + task_size += xstate_size; + + /* + * We dynamically size 'struct fpu', so we require that + * it be at the end of 'thread_struct' and that + * 'thread_struct' be at the end of 'task_struct'. If + * you hit a compile error here, check the structure to + * see if something got added to the end. + */ + CHECK_MEMBER_AT_END_OF(struct fpu, state); + CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu); + CHECK_MEMBER_AT_END_OF(struct task_struct, thread); + + arch_task_struct_size = task_size; +} + /* * Set up the xstate_size based on the legacy FPU context size. * @@ -287,6 +326,7 @@ void __init fpu__init_system(struct cpuinfo_x86 *c) fpu__init_system_generic(); fpu__init_system_xstate_size_legacy(); fpu__init_system_xstate(); + fpu__init_task_struct_size(); fpu__init_system_ctx_switch(); } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index c3e985d1751c..d05bd2e2ee91 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -408,15 +408,15 @@ static void default_do_nmi(struct pt_regs *regs) NOKPROBE_SYMBOL(default_do_nmi); /* - * NMIs can hit breakpoints which will cause it to lose its - * NMI context with the CPU when the breakpoint does an iret. - */ -#ifdef CONFIG_X86_32 -/* - * For i386, NMIs use the same stack as the kernel, and we can - * add a workaround to the iret problem in C (preventing nested - * NMIs if an NMI takes a trap). Simply have 3 states the NMI - * can be in: + * NMIs can page fault or hit breakpoints which will cause it to lose + * its NMI context with the CPU when the breakpoint or page fault does an IRET. + * + * As a result, NMIs can nest if NMIs get unmasked due an IRET during + * NMI processing. On x86_64, the asm glue protects us from nested NMIs + * if the outer NMI came from kernel mode, but we can still nest if the + * outer NMI came from user mode. + * + * To handle these nested NMIs, we have three states: * * 1) not running * 2) executing @@ -430,15 +430,14 @@ NOKPROBE_SYMBOL(default_do_nmi); * (Note, the latch is binary, thus multiple NMIs triggering, * when one is running, are ignored. Only one NMI is restarted.) * - * If an NMI hits a breakpoint that executes an iret, another - * NMI can preempt it. We do not want to allow this new NMI - * to run, but we want to execute it when the first one finishes. - * We set the state to "latched", and the exit of the first NMI will - * perform a dec_return, if the result is zero (NOT_RUNNING), then - * it will simply exit the NMI handler. If not, the dec_return - * would have set the state to NMI_EXECUTING (what we want it to - * be when we are running). In this case, we simply jump back - * to rerun the NMI handler again, and restart the 'latched' NMI. + * If an NMI executes an iret, another NMI can preempt it. We do not + * want to allow this new NMI to run, but we want to execute it when the + * first one finishes. We set the state to "latched", and the exit of + * the first NMI will perform a dec_return, if the result is zero + * (NOT_RUNNING), then it will simply exit the NMI handler. If not, the + * dec_return would have set the state to NMI_EXECUTING (what we want it + * to be when we are running). In this case, we simply jump back to + * rerun the NMI handler again, and restart the 'latched' NMI. * * No trap (breakpoint or page fault) should be hit before nmi_restart, * thus there is no race between the first check of state for NOT_RUNNING @@ -461,49 +460,36 @@ enum nmi_states { static DEFINE_PER_CPU(enum nmi_states, nmi_state); static DEFINE_PER_CPU(unsigned long, nmi_cr2); -#define nmi_nesting_preprocess(regs) \ - do { \ - if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { \ - this_cpu_write(nmi_state, NMI_LATCHED); \ - return; \ - } \ - this_cpu_write(nmi_state, NMI_EXECUTING); \ - this_cpu_write(nmi_cr2, read_cr2()); \ - } while (0); \ - nmi_restart: - -#define nmi_nesting_postprocess() \ - do { \ - if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) \ - write_cr2(this_cpu_read(nmi_cr2)); \ - if (this_cpu_dec_return(nmi_state)) \ - goto nmi_restart; \ - } while (0) -#else /* x86_64 */ +#ifdef CONFIG_X86_64 /* - * In x86_64 things are a bit more difficult. This has the same problem - * where an NMI hitting a breakpoint that calls iret will remove the - * NMI context, allowing a nested NMI to enter. What makes this more - * difficult is that both NMIs and breakpoints have their own stack. - * When a new NMI or breakpoint is executed, the stack is set to a fixed - * point. If an NMI is nested, it will have its stack set at that same - * fixed address that the first NMI had, and will start corrupting the - * stack. This is handled in entry_64.S, but the same problem exists with - * the breakpoint stack. + * In x86_64, we need to handle breakpoint -> NMI -> breakpoint. Without + * some care, the inner breakpoint will clobber the outer breakpoint's + * stack. * - * If a breakpoint is being processed, and the debug stack is being used, - * if an NMI comes in and also hits a breakpoint, the stack pointer - * will be set to the same fixed address as the breakpoint that was - * interrupted, causing that stack to be corrupted. To handle this case, - * check if the stack that was interrupted is the debug stack, and if - * so, change the IDT so that new breakpoints will use the current stack - * and not switch to the fixed address. On return of the NMI, switch back - * to the original IDT. + * If a breakpoint is being processed, and the debug stack is being + * used, if an NMI comes in and also hits a breakpoint, the stack + * pointer will be set to the same fixed address as the breakpoint that + * was interrupted, causing that stack to be corrupted. To handle this + * case, check if the stack that was interrupted is the debug stack, and + * if so, change the IDT so that new breakpoints will use the current + * stack and not switch to the fixed address. On return of the NMI, + * switch back to the original IDT. */ static DEFINE_PER_CPU(int, update_debug_stack); +#endif -static inline void nmi_nesting_preprocess(struct pt_regs *regs) +dotraplinkage notrace void +do_nmi(struct pt_regs *regs, long error_code) { + if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { + this_cpu_write(nmi_state, NMI_LATCHED); + return; + } + this_cpu_write(nmi_state, NMI_EXECUTING); + this_cpu_write(nmi_cr2, read_cr2()); +nmi_restart: + +#ifdef CONFIG_X86_64 /* * If we interrupted a breakpoint, it is possible that * the nmi handler will have breakpoints too. We need to @@ -514,22 +500,8 @@ static inline void nmi_nesting_preprocess(struct pt_regs *regs) debug_stack_set_zero(); this_cpu_write(update_debug_stack, 1); } -} - -static inline void nmi_nesting_postprocess(void) -{ - if (unlikely(this_cpu_read(update_debug_stack))) { - debug_stack_reset(); - this_cpu_write(update_debug_stack, 0); - } -} #endif -dotraplinkage notrace void -do_nmi(struct pt_regs *regs, long error_code) -{ - nmi_nesting_preprocess(regs); - nmi_enter(); inc_irq_stat(__nmi_count); @@ -539,8 +511,17 @@ do_nmi(struct pt_regs *regs, long error_code) nmi_exit(); - /* On i386, may loop back to preprocess */ - nmi_nesting_postprocess(); +#ifdef CONFIG_X86_64 + if (unlikely(this_cpu_read(update_debug_stack))) { + debug_stack_reset(); + this_cpu_write(update_debug_stack, 0); + } +#endif + + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) + write_cr2(this_cpu_read(nmi_cr2)); + if (this_cpu_dec_return(nmi_state)) + goto nmi_restart; } NOKPROBE_SYMBOL(do_nmi); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9cad694ed7c4..397688beed4b 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -81,7 +81,7 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister); */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - *dst = *src; + memcpy(dst, src, arch_task_struct_size); return fpu__copy(&dst->thread.fpu, &src->thread.fpu); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index d3010aa79daf..b1f3ed9c7a9e 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -992,8 +992,17 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) common_cpu_up(cpu, tidle); + /* + * We have to walk the irq descriptors to setup the vector + * space for the cpu which comes online. Prevent irq + * alloc/free across the bringup. + */ + irq_lock_sparse(); + err = do_boot_cpu(apicid, cpu, tidle); + if (err) { + irq_unlock_sparse(); pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); return -EIO; } @@ -1011,6 +1020,8 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) touch_nmi_watchdog(); } + irq_unlock_sparse(); + return 0; } diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 67d215cb8953..a1ff508bb423 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -12,7 +12,9 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ - i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o + i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ + hyperv.o + kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o kvm-intel-y += vmx.o pmu_intel.o kvm-amd-y += svm.o pmu_amd.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 64dd46793099..2fbea2544f24 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -98,6 +98,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu); + if (vcpu->arch.eager_fpu) + kvm_x86_ops->fpu_activate(vcpu); /* * The existing code assumes virtual address is 48-bit in the canonical diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c new file mode 100644 index 000000000000..a8160d2ae362 --- /dev/null +++ b/arch/x86/kvm/hyperv.c @@ -0,0 +1,377 @@ +/* + * KVM Microsoft Hyper-V emulation + * + * derived from arch/x86/kvm/x86.c + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright (C) 2008 Qumranet, Inc. + * Copyright IBM Corporation, 2008 + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com> + * + * Authors: + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * Amit Shah <amit.shah@qumranet.com> + * Ben-Ami Yassour <benami@il.ibm.com> + * Andrey Smetanin <asmetanin@virtuozzo.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "x86.h" +#include "lapic.h" +#include "hyperv.h" + +#include <linux/kvm_host.h> +#include <trace/events/kvm.h> + +#include "trace.h" + +static bool kvm_hv_msr_partition_wide(u32 msr) +{ + bool r = false; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + case HV_X64_MSR_HYPERCALL: + case HV_X64_MSR_REFERENCE_TSC: + case HV_X64_MSR_TIME_REF_COUNT: + case HV_X64_MSR_CRASH_CTL: + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + r = true; + break; + } + + return r; +} + +static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, + u32 index, u64 *pdata) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + return -EINVAL; + + *pdata = hv->hv_crash_param[index]; + return 0; +} + +static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + *pdata = hv->hv_crash_ctl; + return 0; +} + +static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + if (host) + hv->hv_crash_ctl = data & HV_X64_MSR_CRASH_CTL_NOTIFY; + + if (!host && (data & HV_X64_MSR_CRASH_CTL_NOTIFY)) { + + vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n", + hv->hv_crash_param[0], + hv->hv_crash_param[1], + hv->hv_crash_param[2], + hv->hv_crash_param[3], + hv->hv_crash_param[4]); + + /* Send notification about crash to user space */ + kvm_make_request(KVM_REQ_HV_CRASH, vcpu); + } + + return 0; +} + +static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, + u32 index, u64 data) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + return -EINVAL; + + hv->hv_crash_param[index] = data; + return 0; +} + +static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, + bool host) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = &kvm->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + hv->hv_guest_os_id = data; + /* setting guest os id to zero disables hypercall page */ + if (!hv->hv_guest_os_id) + hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; + break; + case HV_X64_MSR_HYPERCALL: { + u64 gfn; + unsigned long addr; + u8 instructions[4]; + + /* if guest os id is not set hypercall should remain disabled */ + if (!hv->hv_guest_os_id) + break; + if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { + hv->hv_hypercall = data; + break; + } + gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return 1; + kvm_x86_ops->patch_hypercall(vcpu, instructions); + ((unsigned char *)instructions)[3] = 0xc3; /* ret */ + if (__copy_to_user((void __user *)addr, instructions, 4)) + return 1; + hv->hv_hypercall = data; + mark_page_dirty(kvm, gfn); + break; + } + case HV_X64_MSR_REFERENCE_TSC: { + u64 gfn; + HV_REFERENCE_TSC_PAGE tsc_ref; + + memset(&tsc_ref, 0, sizeof(tsc_ref)); + hv->hv_tsc_page = data; + if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + break; + gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; + if (kvm_write_guest( + kvm, + gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, + &tsc_ref, sizeof(tsc_ref))) + return 1; + mark_page_dirty(kvm, gfn); + break; + } + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + return kvm_hv_msr_set_crash_data(vcpu, + msr - HV_X64_MSR_CRASH_P0, + data); + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_msr_set_crash_ctl(vcpu, data, host); + default: + vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + msr, data); + return 1; + } + return 0; +} + +static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_APIC_ASSIST_PAGE: { + u64 gfn; + unsigned long addr; + + if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { + hv->hv_vapic = data; + if (kvm_lapic_enable_pv_eoi(vcpu, 0)) + return 1; + break; + } + gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; + addr = kvm_vcpu_gfn_to_hva(vcpu, gfn); + if (kvm_is_error_hva(addr)) + return 1; + if (__clear_user((void __user *)addr, PAGE_SIZE)) + return 1; + hv->hv_vapic = data; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + if (kvm_lapic_enable_pv_eoi(vcpu, + gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) + return 1; + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); + default: + vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + msr, data); + return 1; + } + + return 0; +} + +static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = &kvm->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + data = hv->hv_guest_os_id; + break; + case HV_X64_MSR_HYPERCALL: + data = hv->hv_hypercall; + break; + case HV_X64_MSR_TIME_REF_COUNT: { + data = + div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); + break; + } + case HV_X64_MSR_REFERENCE_TSC: + data = hv->hv_tsc_page; + break; + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + return kvm_hv_msr_get_crash_data(vcpu, + msr - HV_X64_MSR_CRASH_P0, + pdata); + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_msr_get_crash_ctl(vcpu, pdata); + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + + *pdata = data; + return 0; +} + +static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_VP_INDEX: { + int r; + struct kvm_vcpu *v; + + kvm_for_each_vcpu(r, v, vcpu->kvm) { + if (v == vcpu) { + data = r; + break; + } + } + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); + case HV_X64_MSR_APIC_ASSIST_PAGE: + data = hv->hv_vapic; + break; + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + *pdata = data; + return 0; +} + +int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) +{ + if (kvm_hv_msr_partition_wide(msr)) { + int r; + + mutex_lock(&vcpu->kvm->lock); + r = kvm_hv_set_msr_pw(vcpu, msr, data, host); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return kvm_hv_set_msr(vcpu, msr, data); +} + +int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + if (kvm_hv_msr_partition_wide(msr)) { + int r; + + mutex_lock(&vcpu->kvm->lock); + r = kvm_hv_get_msr_pw(vcpu, msr, pdata); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return kvm_hv_get_msr(vcpu, msr, pdata); +} + +bool kvm_hv_hypercall_enabled(struct kvm *kvm) +{ + return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; +} + +int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + u64 param, ingpa, outgpa, ret; + uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; + bool fast, longmode; + + /* + * hypercall generates UD from non zero cpl and real mode + * per HYPER-V spec + */ + if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 0; + } + + longmode = is_64_bit_mode(vcpu); + + if (!longmode) { + param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff); + ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff); + outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff); + } +#ifdef CONFIG_X86_64 + else { + param = kvm_register_read(vcpu, VCPU_REGS_RCX); + ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); + outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); + } +#endif + + code = param & 0xffff; + fast = (param >> 16) & 0x1; + rep_cnt = (param >> 32) & 0xfff; + rep_idx = (param >> 48) & 0xfff; + + trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + + switch (code) { + case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: + kvm_vcpu_on_spin(vcpu); + break; + default: + res = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + } + + ret = res | (((u64)rep_done & 0xfff) << 32); + if (longmode) { + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + } else { + kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); + kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); + } + + return 1; +} diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h new file mode 100644 index 000000000000..c7bce559f67b --- /dev/null +++ b/arch/x86/kvm/hyperv.h @@ -0,0 +1,32 @@ +/* + * KVM Microsoft Hyper-V emulation + * + * derived from arch/x86/kvm/x86.c + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright (C) 2008 Qumranet, Inc. + * Copyright IBM Corporation, 2008 + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com> + * + * Authors: + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * Amit Shah <amit.shah@qumranet.com> + * Ben-Ami Yassour <benami@il.ibm.com> + * Andrey Smetanin <asmetanin@virtuozzo.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#ifndef __ARCH_X86_KVM_HYPERV_H__ +#define __ARCH_X86_KVM_HYPERV_H__ + +int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); +int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); +bool kvm_hv_hypercall_enabled(struct kvm *kvm); +int kvm_hv_hypercall(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index fef922ff2635..7cc2360f1848 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -651,15 +651,10 @@ fail_unlock: return NULL; } -void kvm_destroy_pic(struct kvm *kvm) +void kvm_destroy_pic(struct kvm_pic *vpic) { - struct kvm_pic *vpic = kvm->arch.vpic; - - if (vpic) { - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_master); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_slave); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_eclr); - kvm->arch.vpic = NULL; - kfree(vpic); - } + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master); + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave); + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr); + kfree(vpic); } diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 7dbced309ddb..5c520ebf6343 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -200,6 +200,7 @@ int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev) goto out_unmap; } + kvm_arch_start_assignment(kvm); pci_set_dev_assigned(pdev); dev_info(&pdev->dev, "kvm assign device\n"); @@ -224,6 +225,7 @@ int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev) iommu_detach_device(domain, &pdev->dev); pci_clear_dev_assigned(pdev); + kvm_arch_end_assignment(kvm); dev_info(&pdev->dev, "kvm deassign device\n"); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index ad68c73008c5..3d782a2c336a 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -74,7 +74,7 @@ struct kvm_pic { }; struct kvm_pic *kvm_create_pic(struct kvm *kvm); -void kvm_destroy_pic(struct kvm *kvm); +void kvm_destroy_pic(struct kvm_pic *vpic); int kvm_pic_read_irq(struct kvm *kvm); void kvm_pic_update_irq(struct kvm_pic *s); @@ -85,11 +85,11 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) static inline int irqchip_in_kernel(struct kvm *kvm) { - int ret; + struct kvm_pic *vpic = pic_irqchip(kvm); - ret = (pic_irqchip(kvm) != NULL); + /* Read vpic before kvm->irq_routing. */ smp_rmb(); - return ret; + return vpic != NULL; } void kvm_pic_reset(struct kvm_kpic_state *s); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 954e98a8c2e3..9a3e342e3cda 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1595,7 +1595,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) for (i = 0; i < APIC_LVT_NUM; i++) apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); apic_update_lvtt(apic); - if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED)) + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) apic_set_reg(apic, APIC_LVT0, SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0)); @@ -1900,8 +1900,9 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, - sizeof(u32)); + if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32))) + return; apic_set_tpr(vcpu->arch.apic, data & 0xff); } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 71952748222a..764037991d26 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -91,7 +91,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) { - return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE; + return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE; } int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f807496b62c2..fb16a8ea3dee 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -357,12 +357,6 @@ static u64 __get_spte_lockless(u64 *sptep) { return ACCESS_ONCE(*sptep); } - -static bool __check_direct_spte_mmio_pf(u64 spte) -{ - /* It is valid if the spte is zapped. */ - return spte == 0ull; -} #else union split_spte { struct { @@ -478,23 +472,6 @@ retry: return spte.spte; } - -static bool __check_direct_spte_mmio_pf(u64 spte) -{ - union split_spte sspte = (union split_spte)spte; - u32 high_mmio_mask = shadow_mmio_mask >> 32; - - /* It is valid if the spte is zapped. */ - if (spte == 0ull) - return true; - - /* It is valid if the spte is being zapped. */ - if (sspte.spte_low == 0ull && - (sspte.spte_high & high_mmio_mask) == high_mmio_mask) - return true; - - return false; -} #endif static bool spte_is_locklessly_modifiable(u64 spte) @@ -2479,6 +2456,14 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } +static bool kvm_is_mmio_pfn(pfn_t pfn) +{ + if (pfn_valid(pfn)) + return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); + + return true; +} + static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, gfn_t gfn, pfn_t pfn, bool speculative, @@ -2506,7 +2491,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn, - kvm_is_reserved_pfn(pfn)); + kvm_is_mmio_pfn(pfn)); if (host_writable) spte |= SPTE_HOST_WRITEABLE; @@ -3283,54 +3268,89 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception); } -static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) +static bool +__is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level) { - if (direct) - return vcpu_match_mmio_gpa(vcpu, addr); + int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f; - return vcpu_match_mmio_gva(vcpu, addr); + return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) | + ((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0); } +static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) +{ + return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level); +} -/* - * On direct hosts, the last spte is only allows two states - * for mmio page fault: - * - It is the mmio spte - * - It is zapped or it is being zapped. - * - * This function completely checks the spte when the last spte - * is not the mmio spte. - */ -static bool check_direct_spte_mmio_pf(u64 spte) +static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level) { - return __check_direct_spte_mmio_pf(spte); + return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level); } -static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr) +static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) +{ + if (direct) + return vcpu_match_mmio_gpa(vcpu, addr); + + return vcpu_match_mmio_gva(vcpu, addr); +} + +/* return true if reserved bit is detected on spte. */ +static bool +walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { struct kvm_shadow_walk_iterator iterator; - u64 spte = 0ull; + u64 sptes[PT64_ROOT_LEVEL], spte = 0ull; + int root, leaf; + bool reserved = false; if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return spte; + goto exit; walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) + + for (shadow_walk_init(&iterator, vcpu, addr), root = iterator.level; + shadow_walk_okay(&iterator); + __shadow_walk_next(&iterator, spte)) { + leaf = iterator.level; + spte = mmu_spte_get_lockless(iterator.sptep); + + sptes[leaf - 1] = spte; + if (!is_shadow_present_pte(spte)) break; + + reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte, + leaf); + } + walk_shadow_page_lockless_end(vcpu); - return spte; + if (reserved) { + pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n", + __func__, addr); + while (root >= leaf) { + pr_err("------ spte 0x%llx level %d.\n", + sptes[root - 1], root); + root--; + } + } +exit: + *sptep = spte; + return reserved; } int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) { u64 spte; + bool reserved; if (quickly_check_mmio_pf(vcpu, addr, direct)) return RET_MMIO_PF_EMULATE; - spte = walk_shadow_page_get_mmio_spte(vcpu, addr); + reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte); + if (unlikely(reserved)) + return RET_MMIO_PF_BUG; if (is_mmio_spte(spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); @@ -3348,13 +3368,6 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) } /* - * It's ok if the gva is remapped by other cpus on shadow guest, - * it's a BUG if the gfn is not a mmio page. - */ - if (direct && !check_direct_spte_mmio_pf(spte)) - return RET_MMIO_PF_BUG; - - /* * If the page table is zapped by other cpus, let CPU fault again on * the address. */ @@ -3596,19 +3609,21 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp #include "paging_tmpl.h" #undef PTTYPE -static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void +__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, + struct rsvd_bits_validate *rsvd_check, + int maxphyaddr, int level, bool nx, bool gbpages, + bool pse) { - int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; u64 gbpages_bit_rsvd = 0; u64 nonleaf_bit8_rsvd = 0; - context->bad_mt_xwr = 0; + rsvd_check->bad_mt_xwr = 0; - if (!context->nx) + if (!nx) exb_bit_rsvd = rsvd_bits(63, 63); - if (!guest_cpuid_has_gbpages(vcpu)) + if (!gbpages) gbpages_bit_rsvd = rsvd_bits(7, 7); /* @@ -3618,80 +3633,95 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, if (guest_cpuid_is_amd(vcpu)) nonleaf_bit8_rsvd = rsvd_bits(8, 8); - switch (context->root_level) { + switch (level) { case PT32_ROOT_LEVEL: /* no rsvd bits for 2 level 4K page table entries */ - context->rsvd_bits_mask[0][1] = 0; - context->rsvd_bits_mask[0][0] = 0; - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[0][1] = 0; + rsvd_check->rsvd_bits_mask[0][0] = 0; + rsvd_check->rsvd_bits_mask[1][0] = + rsvd_check->rsvd_bits_mask[0][0]; - if (!is_pse(vcpu)) { - context->rsvd_bits_mask[1][1] = 0; + if (!pse) { + rsvd_check->rsvd_bits_mask[1][1] = 0; break; } if (is_cpuid_PSE36()) /* 36bits PSE 4MB page */ - context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21); + rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(17, 21); else /* 32 bits PSE 4MB page */ - context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); + rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); break; case PT32E_ROOT_LEVEL: - context->rsvd_bits_mask[0][2] = + rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(maxphyaddr, 63) | rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */ - context->rsvd_bits_mask[0][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62); /* PDE */ - context->rsvd_bits_mask[0][0] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62); /* PTE */ - context->rsvd_bits_mask[1][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[1][0] = + rsvd_check->rsvd_bits_mask[0][0]; break; case PT64_ROOT_LEVEL: - context->rsvd_bits_mask[0][3] = exb_bit_rsvd | - nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[0][2] = exb_bit_rsvd | - nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[0][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd | + nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[0][0] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | + nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; - context->rsvd_bits_mask[1][2] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | + rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | + rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[1][3] = + rsvd_check->rsvd_bits_mask[0][3]; + rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 29); - context->rsvd_bits_mask[1][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[1][0] = + rsvd_check->rsvd_bits_mask[0][0]; break; } } -static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, bool execonly) +static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) +{ + __reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check, + cpuid_maxphyaddr(vcpu), context->root_level, + context->nx, guest_cpuid_has_gbpages(vcpu), + is_pse(vcpu)); +} + +static void +__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, + int maxphyaddr, bool execonly) { - int maxphyaddr = cpuid_maxphyaddr(vcpu); int pte; - context->rsvd_bits_mask[0][3] = + rsvd_check->rsvd_bits_mask[0][3] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7); - context->rsvd_bits_mask[0][2] = + rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - context->rsvd_bits_mask[0][1] = + rsvd_check->rsvd_bits_mask[0][1] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); /* large page */ - context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; - context->rsvd_bits_mask[1][2] = + rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; + rsvd_check->rsvd_bits_mask[1][2] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29); - context->rsvd_bits_mask[1][1] = + rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20); - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; for (pte = 0; pte < 64; pte++) { int rwx_bits = pte & 7; @@ -3699,10 +3729,64 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, if (mt == 0x2 || mt == 0x3 || mt == 0x7 || rwx_bits == 0x2 || rwx_bits == 0x6 || (rwx_bits == 0x4 && !execonly)) - context->bad_mt_xwr |= (1ull << pte); + rsvd_check->bad_mt_xwr |= (1ull << pte); } } +static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, bool execonly) +{ + __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, + cpuid_maxphyaddr(vcpu), execonly); +} + +/* + * the page table on host is the shadow page table for the page + * table in guest or amd nested guest, its mmu features completely + * follow the features in guest. + */ +void +reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) +{ + __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, + context->shadow_root_level, context->nx, + guest_cpuid_has_gbpages(vcpu), is_pse(vcpu)); +} +EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask); + +/* + * the direct page table on host, use as much mmu features as + * possible, however, kvm currently does not do execution-protection. + */ +static void +reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) +{ + if (guest_cpuid_is_amd(vcpu)) + __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, + context->shadow_root_level, false, + cpu_has_gbpages, true); + else + __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, + false); + +} + +/* + * as the comments in reset_shadow_zero_bits_mask() except it + * is the shadow page table for intel nested guest. + */ +static void +reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, bool execonly) +{ + __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, execonly); +} + static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, bool ept) { @@ -3881,6 +3965,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); + reset_tdp_shadow_zero_bits_mask(vcpu, context); } void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) @@ -3908,6 +3993,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) context->base_role.smap_andnot_wp = smap && !is_write_protection(vcpu); context->base_role.smm = is_smm(vcpu); + reset_shadow_zero_bits_mask(vcpu, context); } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); @@ -3931,6 +4017,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly) update_permission_bitmask(vcpu, context, true); reset_rsvds_bits_mask_ept(vcpu, context, execonly); + reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); @@ -4852,28 +4939,6 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) return nr_mmu_pages; } -int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]) -{ - struct kvm_shadow_walk_iterator iterator; - u64 spte; - int nr_sptes = 0; - - if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return nr_sptes; - - walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { - sptes[iterator.level-1] = spte; - nr_sptes++; - if (!is_shadow_present_pte(spte)) - break; - } - walk_shadow_page_lockless_end(vcpu); - - return nr_sptes; -} -EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy); - void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 398d21c0f6dd..e4202e41d535 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -50,9 +50,11 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask); +void +reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); + /* * Return values of handle_mmio_page_fault_common: * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index de1d2d8062e2..9e8bf13572e6 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -120,6 +120,16 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; } +static u8 mtrr_disabled_type(void) +{ + /* + * Intel SDM 11.11.2.2: all MTRRs are disabled when + * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC + * memory type is applied to all of physical memory. + */ + return MTRR_TYPE_UNCACHABLE; +} + /* * Three terms are used in the following code: * - segment, it indicates the address segments covered by fixed MTRRs. @@ -434,6 +444,8 @@ struct mtrr_iter { /* output fields. */ int mem_type; + /* mtrr is completely disabled? */ + bool mtrr_disabled; /* [start, end) is not fully covered in MTRRs? */ bool partial_map; @@ -549,7 +561,7 @@ static void mtrr_lookup_var_next(struct mtrr_iter *iter) static void mtrr_lookup_start(struct mtrr_iter *iter) { if (!mtrr_is_enabled(iter->mtrr_state)) { - iter->partial_map = true; + iter->mtrr_disabled = true; return; } @@ -563,6 +575,7 @@ static void mtrr_lookup_init(struct mtrr_iter *iter, iter->mtrr_state = mtrr_state; iter->start = start; iter->end = end; + iter->mtrr_disabled = false; iter->partial_map = false; iter->fixed = false; iter->range = NULL; @@ -656,15 +669,19 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) return MTRR_TYPE_WRBACK; } - /* It is not covered by MTRRs. */ - if (iter.partial_map) { - /* - * We just check one page, partially covered by MTRRs is - * impossible. - */ - WARN_ON(type != -1); - type = mtrr_default_type(mtrr_state); - } + if (iter.mtrr_disabled) + return mtrr_disabled_type(); + + /* not contained in any MTRRs. */ + if (type == -1) + return mtrr_default_type(mtrr_state); + + /* + * We just check one page, partially covered by MTRRs is + * impossible. + */ + WARN_ON(iter.partial_map); + return type; } EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type); @@ -689,6 +706,9 @@ bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, return false; } + if (iter.mtrr_disabled) + return true; + if (!iter.partial_map) return true; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 0f67d7e24800..736e6ab8784d 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -128,14 +128,6 @@ static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte) *access &= mask; } -static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level) -{ - int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f; - - return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) | - ((mmu->bad_mt_xwr & (1ull << low6)) != 0); -} - static inline int FNAME(is_present_gpte)(unsigned long pte) { #if PTTYPE != PTTYPE_EPT @@ -172,7 +164,7 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, u64 gpte) { - if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) + if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) goto no_present; if (!FNAME(is_present_gpte)(gpte)) @@ -353,8 +345,7 @@ retry_walk: if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; - if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, - walker->level))) { + if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) { errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK; goto error; } diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index 886aa25a7131..39b91127ef07 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -133,8 +133,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* MSR_K7_PERFCTRn */ pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0); if (pmc) { - if (!msr_info->host_initiated) - data = (s64)data; pmc->counter += data - pmc_read_counter(pmc); return 0; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 602b974a60a6..74d825716f4f 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -865,6 +865,64 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } +#define MTRR_TYPE_UC_MINUS 7 +#define MTRR2PROTVAL_INVALID 0xff + +static u8 mtrr2protval[8]; + +static u8 fallback_mtrr_type(int mtrr) +{ + /* + * WT and WP aren't always available in the host PAT. Treat + * them as UC and UC- respectively. Everything else should be + * there. + */ + switch (mtrr) + { + case MTRR_TYPE_WRTHROUGH: + return MTRR_TYPE_UNCACHABLE; + case MTRR_TYPE_WRPROT: + return MTRR_TYPE_UC_MINUS; + default: + BUG(); + } +} + +static void build_mtrr2protval(void) +{ + int i; + u64 pat; + + for (i = 0; i < 8; i++) + mtrr2protval[i] = MTRR2PROTVAL_INVALID; + + /* Ignore the invalid MTRR types. */ + mtrr2protval[2] = 0; + mtrr2protval[3] = 0; + + /* + * Use host PAT value to figure out the mapping from guest MTRR + * values to nested page table PAT/PCD/PWT values. We do not + * want to change the host PAT value every time we enter the + * guest. + */ + rdmsrl(MSR_IA32_CR_PAT, pat); + for (i = 0; i < 8; i++) { + u8 mtrr = pat >> (8 * i); + + if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID) + mtrr2protval[mtrr] = __cm_idx2pte(i); + } + + for (i = 0; i < 8; i++) { + if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) { + u8 fallback = fallback_mtrr_type(i); + mtrr2protval[i] = mtrr2protval[fallback]; + BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID); + } + } +} + static __init int svm_hardware_setup(void) { int cpu; @@ -931,6 +989,7 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); + build_mtrr2protval(); return 0; err: @@ -1085,6 +1144,43 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) return target_tsc - tsc; } +static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + /* Unlike Intel, AMD takes the guest's CR0.CD into account. + * + * AMD does not have IPAT. To emulate it for the case of guests + * with no assigned devices, just set everything to WB. If guests + * have assigned devices, however, we cannot force WB for RAM + * pages only, so use the guest PAT directly. + */ + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + *g_pat = 0x0606060606060606; + else + *g_pat = vcpu->arch.pat; +} + +static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +{ + u8 mtrr; + + /* + * 1. MMIO: trust guest MTRR, so same as item 3. + * 2. No passthrough: always map as WB, and force guest PAT to WB as well + * 3. Passthrough: can't guarantee the result, try to trust guest. + */ + if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; + + if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) && + kvm_read_cr0(vcpu) & X86_CR0_CD) + return _PAGE_NOCACHE; + + mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + return mtrr2protval[mtrr]; +} + static void init_vmcb(struct vcpu_svm *svm, bool init_event) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -1180,6 +1276,7 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) clr_cr_intercept(svm, INTERCEPT_CR3_READ); clr_cr_intercept(svm, INTERCEPT_CR3_WRITE); save->g_pat = svm->vcpu.arch.pat; + svm_set_guest_pat(svm, &save->g_pat); save->cr3 = 0; save->cr4 = 0; } @@ -1574,13 +1671,10 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!vcpu->fpu_active) cr0 |= X86_CR0_TS; - /* - * re-enable caching here because the QEMU bios - * does not do it - this results in some delay at - * reboot - */ - if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED)) - cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + + /* These are emulated via page tables. */ + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + svm->vmcb->save.cr0 = cr0; mark_dirty(svm->vmcb, VMCB_CR); update_cr0_intercept(svm); @@ -2013,6 +2107,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr; vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit; vcpu->arch.mmu.shadow_root_level = get_npt_level(); + reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; } @@ -3254,6 +3349,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; + case MSR_IA32_CR_PAT: + if (npt_enabled) { + if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) + return 1; + vcpu->arch.pat = data; + svm_set_guest_pat(svm, &svm->vmcb->save.g_pat); + mark_dirty(svm->vmcb, VMCB_NPT); + break; + } + /* fall through */ default: return kvm_set_msr_common(vcpu, msr); } @@ -4088,11 +4193,6 @@ static bool svm_has_high_real_mode_segbase(void) return true; } -static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) -{ - return 0; -} - static void svm_cpuid_update(struct kvm_vcpu *vcpu) { } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e856dd566f4c..da1590ea43fc 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2443,10 +2443,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | #endif CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | - CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING | - CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING | - CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW | - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; + CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG | + CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING | + CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING | + CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the * hardware. For example, L1 can specify an MSR bitmap - and we @@ -3423,12 +3423,12 @@ static void enter_lmode(struct kvm_vcpu *vcpu) vmx_segment_cache_clear(to_vmx(vcpu)); guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); - if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { + if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) { pr_debug_ratelimited("%s: tss fixup for long mode. \n", __func__); vmcs_write32(GUEST_TR_AR_BYTES, - (guest_tr_ar & ~AR_TYPE_MASK) - | AR_TYPE_BUSY_64_TSS); + (guest_tr_ar & ~VMX_AR_TYPE_MASK) + | VMX_AR_TYPE_BUSY_64_TSS); } vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); } @@ -3719,7 +3719,7 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu) return 0; else { int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); - return AR_DPL(ar); + return VMX_AR_DPL(ar); } } @@ -3847,11 +3847,11 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) if (cs.unusable) return false; - if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK)) + if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK)) return false; if (!cs.s) return false; - if (cs.type & AR_TYPE_WRITEABLE_MASK) { + if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) { if (cs.dpl > cs_rpl) return false; } else { @@ -3901,7 +3901,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) return false; if (!var.present) return false; - if (~var.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK)) { + if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) { if (var.dpl < rpl) /* DPL < RPL */ return false; } @@ -5759,73 +5759,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); } -static u64 ept_rsvd_mask(u64 spte, int level) -{ - int i; - u64 mask = 0; - - for (i = 51; i > boot_cpu_data.x86_phys_bits; i--) - mask |= (1ULL << i); - - if (level == 4) - /* bits 7:3 reserved */ - mask |= 0xf8; - else if (spte & (1ULL << 7)) - /* - * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively, - * level == 1 if the hypervisor is using the ignored bit 7. - */ - mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE; - else if (level > 1) - /* bits 6:3 reserved */ - mask |= 0x78; - - return mask; -} - -static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte, - int level) -{ - printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level); - - /* 010b (write-only) */ - WARN_ON((spte & 0x7) == 0x2); - - /* 110b (write/execute) */ - WARN_ON((spte & 0x7) == 0x6); - - /* 100b (execute-only) and value not supported by logical processor */ - if (!cpu_has_vmx_ept_execute_only()) - WARN_ON((spte & 0x7) == 0x4); - - /* not 000b */ - if ((spte & 0x7)) { - u64 rsvd_bits = spte & ept_rsvd_mask(spte, level); - - if (rsvd_bits != 0) { - printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n", - __func__, rsvd_bits); - WARN_ON(1); - } - - /* bits 5:3 are _not_ reserved for large page or leaf page */ - if ((rsvd_bits & 0x38) == 0) { - u64 ept_mem_type = (spte & 0x38) >> 3; - - if (ept_mem_type == 2 || ept_mem_type == 3 || - ept_mem_type == 7) { - printk(KERN_ERR "%s: ept_mem_type=0x%llx\n", - __func__, ept_mem_type); - WARN_ON(1); - } - } - } -} - static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { - u64 sptes[4]; - int nr_sptes, i, ret; + int ret; gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); @@ -5846,13 +5782,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) return 1; /* It is the real ept misconfig */ - printk(KERN_ERR "EPT: Misconfiguration.\n"); - printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa); - - nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes); - - for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i) - ept_misconfig_inspect_spte(vcpu, sptes[i-1], i); + WARN_ON(1); vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; @@ -6246,6 +6176,11 @@ static int handle_mwait(struct kvm_vcpu *vcpu) return handle_nop(vcpu); } +static int handle_monitor_trap(struct kvm_vcpu *vcpu) +{ + return 1; +} + static int handle_monitor(struct kvm_vcpu *vcpu) { printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); @@ -6408,8 +6343,12 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) */ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, - u32 vmx_instruction_info, gva_t *ret) + u32 vmx_instruction_info, bool wr, gva_t *ret) { + gva_t off; + bool exn; + struct kvm_segment s; + /* * According to Vol. 3B, "Information for VM Exits Due to Instruction * Execution", on an exit, vmx_instruction_info holds most of the @@ -6434,22 +6373,63 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Addr = segment_base + offset */ /* offset = base + [index * scale] + displacement */ - *ret = vmx_get_segment_base(vcpu, seg_reg); + off = exit_qualification; /* holds the displacement */ if (base_is_valid) - *ret += kvm_register_read(vcpu, base_reg); + off += kvm_register_read(vcpu, base_reg); if (index_is_valid) - *ret += kvm_register_read(vcpu, index_reg)<<scaling; - *ret += exit_qualification; /* holds the displacement */ + off += kvm_register_read(vcpu, index_reg)<<scaling; + vmx_get_segment(vcpu, &s, seg_reg); + *ret = s.base + off; if (addr_size == 1) /* 32 bit */ *ret &= 0xffffffff; - /* - * TODO: throw #GP (and return 1) in various cases that the VM* - * instructions require it - e.g., offset beyond segment limit, - * unusable or unreadable/unwritable segment, non-canonical 64-bit - * address, and so on. Currently these are not checked. - */ + /* Checks for #GP/#SS exceptions. */ + exn = false; + if (is_protmode(vcpu)) { + /* Protected mode: apply checks for segment validity in the + * following order: + * - segment type check (#GP(0) may be thrown) + * - usability check (#GP(0)/#SS(0)) + * - limit check (#GP(0)/#SS(0)) + */ + if (wr) + /* #GP(0) if the destination operand is located in a + * read-only data segment or any code segment. + */ + exn = ((s.type & 0xa) == 0 || (s.type & 8)); + else + /* #GP(0) if the source operand is located in an + * execute-only code segment + */ + exn = ((s.type & 0xa) == 8); + } + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is an only check for long mode. + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { + /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. + */ + exn = (s.unusable != 0); + /* Protected mode: #GP(0)/#SS(0) if the memory + * operand is outside the segment limit. + */ + exn = exn || (off + sizeof(u64) > s.limit); + } + if (exn) { + kvm_queue_exception_e(vcpu, + seg_reg == VCPU_SREG_SS ? + SS_VECTOR : GP_VECTOR, + 0); + return 1; + } + return 0; } @@ -6471,7 +6451,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, int maxphyaddr = cpuid_maxphyaddr(vcpu); if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) + vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, @@ -6999,7 +6979,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) field_value); } else { if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &gva)) + vmx_instruction_info, true, &gva)) return 1; /* _system ok, as nested_vmx_check_permission verified cpl=0 */ kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva, @@ -7036,7 +7016,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) (((vmx_instruction_info) >> 3) & 0xf)); else { if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &gva)) + vmx_instruction_info, false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) { @@ -7128,7 +7108,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return 1; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &vmcs_gva)) + vmx_instruction_info, true, &vmcs_gva)) return 1; /* ok to use *_system, as nested_vmx_check_permission verified cpl=0 */ if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva, @@ -7184,7 +7164,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) * operand is read even if it isn't needed (e.g., for type==global) */ if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmx_instruction_info, &gva)) + vmx_instruction_info, false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand, sizeof(operand), &e)) { @@ -7282,6 +7262,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, + [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap, [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, [EXIT_REASON_INVEPT] = handle_invept, [EXIT_REASON_INVVPID] = handle_invvpid, @@ -7542,6 +7523,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return true; case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); + case EXIT_REASON_MONITOR_TRAP_FLAG: + return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); case EXIT_REASON_MONITOR_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING); case EXIT_REASON_PAUSE_INSTRUCTION: @@ -8632,22 +8615,17 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) u64 ipat = 0; /* For VT-d and EPT combination - * 1. MMIO: always map as UC + * 1. MMIO: guest may want to apply WC, trust it. * 2. EPT with VT-d: * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. + * result, try to trust guest. So the same as item 1. * b. VT-d with snooping control feature: snooping control feature of * VT-d engine can guarantee the cache correctness. Just set it * to WB to keep consistent with host. So the same as item 3. * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep * consistent with host MTRR */ - if (is_mmio) { - cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } - - if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) { ipat = VMX_EPT_IPAT_BIT; cache = MTRR_TYPE_WRBACK; goto exit; @@ -8655,7 +8633,10 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) if (kvm_read_cr0(vcpu) & X86_CR0_CD) { ipat = VMX_EPT_IPAT_BIT; - cache = MTRR_TYPE_UNCACHABLE; + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + cache = MTRR_TYPE_WRBACK; + else + cache = MTRR_TYPE_UNCACHABLE; goto exit; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bbaf44e8f0d3..c7b6aed998e9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -29,6 +29,7 @@ #include "cpuid.h" #include "assigned-dev.h" #include "pmu.h" +#include "hyperv.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -221,11 +222,9 @@ static void shared_msr_update(unsigned slot, u32 msr) void kvm_define_shared_msr(unsigned slot, u32 msr) { BUG_ON(slot >= KVM_NR_SHARED_MSRS); + shared_msrs_global.msrs[slot] = msr; if (slot >= shared_msrs_global.nr) shared_msrs_global.nr = slot + 1; - shared_msrs_global.msrs[slot] = msr; - /* we need ensured the shared_msr_global have been updated */ - smp_wmb(); } EXPORT_SYMBOL_GPL(kvm_define_shared_msr); @@ -526,7 +525,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if (is_present_gpte(pdpte[i]) && - (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) { + (pdpte[i] & + vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) { ret = 0; goto out; } @@ -949,6 +949,8 @@ static u32 emulated_msrs[] = { MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, + HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, @@ -1217,11 +1219,6 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz, __func__, base_khz, scaled_khz, shift, *pmultiplier); } -static inline u64 get_kernel_ns(void) -{ - return ktime_get_boot_ns(); -} - #ifdef CONFIG_X86_64 static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); #endif @@ -1869,123 +1866,6 @@ out: return r; } -static bool kvm_hv_hypercall_enabled(struct kvm *kvm) -{ - return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; -} - -static bool kvm_hv_msr_partition_wide(u32 msr) -{ - bool r = false; - switch (msr) { - case HV_X64_MSR_GUEST_OS_ID: - case HV_X64_MSR_HYPERCALL: - case HV_X64_MSR_REFERENCE_TSC: - case HV_X64_MSR_TIME_REF_COUNT: - r = true; - break; - } - - return r; -} - -static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - struct kvm *kvm = vcpu->kvm; - - switch (msr) { - case HV_X64_MSR_GUEST_OS_ID: - kvm->arch.hv_guest_os_id = data; - /* setting guest os id to zero disables hypercall page */ - if (!kvm->arch.hv_guest_os_id) - kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; - break; - case HV_X64_MSR_HYPERCALL: { - u64 gfn; - unsigned long addr; - u8 instructions[4]; - - /* if guest os id is not set hypercall should remain disabled */ - if (!kvm->arch.hv_guest_os_id) - break; - if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { - kvm->arch.hv_hypercall = data; - break; - } - gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) - return 1; - kvm_x86_ops->patch_hypercall(vcpu, instructions); - ((unsigned char *)instructions)[3] = 0xc3; /* ret */ - if (__copy_to_user((void __user *)addr, instructions, 4)) - return 1; - kvm->arch.hv_hypercall = data; - mark_page_dirty(kvm, gfn); - break; - } - case HV_X64_MSR_REFERENCE_TSC: { - u64 gfn; - HV_REFERENCE_TSC_PAGE tsc_ref; - memset(&tsc_ref, 0, sizeof(tsc_ref)); - kvm->arch.hv_tsc_page = data; - if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) - break; - gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; - if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, - &tsc_ref, sizeof(tsc_ref))) - return 1; - mark_page_dirty(kvm, gfn); - break; - } - default: - vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); - return 1; - } - return 0; -} - -static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - switch (msr) { - case HV_X64_MSR_APIC_ASSIST_PAGE: { - u64 gfn; - unsigned long addr; - - if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { - vcpu->arch.hv_vapic = data; - if (kvm_lapic_enable_pv_eoi(vcpu, 0)) - return 1; - break; - } - gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; - addr = kvm_vcpu_gfn_to_hva(vcpu, gfn); - if (kvm_is_error_hva(addr)) - return 1; - if (__clear_user((void __user *)addr, PAGE_SIZE)) - return 1; - vcpu->arch.hv_vapic = data; - kvm_vcpu_mark_page_dirty(vcpu, gfn); - if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) - return 1; - break; - } - case HV_X64_MSR_EOI: - return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); - case HV_X64_MSR_ICR: - return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); - case HV_X64_MSR_TPR: - return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); - default: - vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); - return 1; - } - - return 0; -} - static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; @@ -2224,15 +2104,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: - if (kvm_hv_msr_partition_wide(msr)) { - int r; - mutex_lock(&vcpu->kvm->lock); - r = set_msr_hyperv_pw(vcpu, msr, data); - mutex_unlock(&vcpu->kvm->lock); - return r; - } else - return set_msr_hyperv(vcpu, msr, data); - break; + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_set_msr_common(vcpu, msr, data, + msr_info->host_initiated); case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. @@ -2315,68 +2190,6 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } -static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 data = 0; - struct kvm *kvm = vcpu->kvm; - - switch (msr) { - case HV_X64_MSR_GUEST_OS_ID: - data = kvm->arch.hv_guest_os_id; - break; - case HV_X64_MSR_HYPERCALL: - data = kvm->arch.hv_hypercall; - break; - case HV_X64_MSR_TIME_REF_COUNT: { - data = - div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); - break; - } - case HV_X64_MSR_REFERENCE_TSC: - data = kvm->arch.hv_tsc_page; - break; - default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); - return 1; - } - - *pdata = data; - return 0; -} - -static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 data = 0; - - switch (msr) { - case HV_X64_MSR_VP_INDEX: { - int r; - struct kvm_vcpu *v; - kvm_for_each_vcpu(r, v, vcpu->kvm) { - if (v == vcpu) { - data = r; - break; - } - } - break; - } - case HV_X64_MSR_EOI: - return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); - case HV_X64_MSR_ICR: - return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); - case HV_X64_MSR_TPR: - return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); - case HV_X64_MSR_APIC_ASSIST_PAGE: - data = vcpu->arch.hv_vapic; - break; - default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); - return 1; - } - *pdata = data; - return 0; -} - int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { switch (msr_info->index) { @@ -2493,14 +2306,10 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x20000000; break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: - if (kvm_hv_msr_partition_wide(msr_info->index)) { - int r; - mutex_lock(&vcpu->kvm->lock); - r = get_msr_hyperv_pw(vcpu, msr_info->index, &msr_info->data); - mutex_unlock(&vcpu->kvm->lock); - return r; - } else - return get_msr_hyperv(vcpu, msr_info->index, &msr_info->data); + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_get_msr_common(vcpu, + msr_info->index, &msr_info->data); break; case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current @@ -2651,6 +2460,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_TSC_DEADLINE_TIMER: case KVM_CAP_ENABLE_CAP_VM: case KVM_CAP_DISABLE_QUIRKS: + case KVM_CAP_SET_BOOT_CPU_ID: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: @@ -3157,8 +2967,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); memcpy(dest, src + offset, size); - } else - WARN_ON_ONCE(1); + } valid -= feature; } @@ -3818,30 +3627,25 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_ioapic_init(kvm); if (r) { mutex_lock(&kvm->slots_lock); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev_master); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev_slave); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev_eclr); + kvm_destroy_pic(vpic); mutex_unlock(&kvm->slots_lock); - kfree(vpic); goto create_irqchip_unlock; } } else goto create_irqchip_unlock; - smp_wmb(); - kvm->arch.vpic = vpic; - smp_wmb(); r = kvm_setup_default_irq_routing(kvm); if (r) { mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->irq_lock); kvm_ioapic_destroy(kvm); - kvm_destroy_pic(kvm); + kvm_destroy_pic(vpic); mutex_unlock(&kvm->irq_lock); mutex_unlock(&kvm->slots_lock); + goto create_irqchip_unlock; } + /* Write kvm->irq_routing before kvm->arch.vpic. */ + smp_wmb(); + kvm->arch.vpic = vpic; create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -3968,6 +3772,15 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_reinject(kvm, &control); break; } + case KVM_SET_BOOT_CPU_ID: + r = 0; + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus) != 0) + r = -EBUSY; + else + kvm->arch.bsp_vcpu_id = arg; + mutex_unlock(&kvm->lock); + break; case KVM_XEN_HVM_CONFIG: { r = -EFAULT; if (copy_from_user(&kvm->arch.xen_hvm_config, argp, @@ -5883,66 +5696,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); -int kvm_hv_hypercall(struct kvm_vcpu *vcpu) -{ - u64 param, ingpa, outgpa, ret; - uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; - bool fast, longmode; - - /* - * hypercall generates UD from non zero cpl and real mode - * per HYPER-V spec - */ - if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 0; - } - - longmode = is_64_bit_mode(vcpu); - - if (!longmode) { - param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | - (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff); - ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | - (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff); - outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | - (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff); - } -#ifdef CONFIG_X86_64 - else { - param = kvm_register_read(vcpu, VCPU_REGS_RCX); - ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); - outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); - } -#endif - - code = param & 0xffff; - fast = (param >> 16) & 0x1; - rep_cnt = (param >> 32) & 0xfff; - rep_idx = (param >> 48) & 0xfff; - - trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); - - switch (code) { - case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: - kvm_vcpu_on_spin(vcpu); - break; - default: - res = HV_STATUS_INVALID_HYPERCALL_CODE; - break; - } - - ret = res | (((u64)rep_done & 0xfff) << 32); - if (longmode) { - kvm_register_write(vcpu, VCPU_REGS_RAX, ret); - } else { - kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); - kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); - } - - return 1; -} - /* * kvm_pv_kick_cpu_op: Kick a vcpu. * @@ -6514,6 +6267,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu_scan_ioapic(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); + if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; + r = 0; + goto out; + } } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { @@ -7315,11 +7074,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu = kvm_x86_ops->vcpu_create(kvm, id); - /* - * Activate fpu unconditionally in case the guest needs eager FPU. It will be - * deactivated soon if it doesn't. - */ - kvm_x86_ops->fpu_activate(vcpu); return vcpu; } @@ -7541,6 +7295,17 @@ void kvm_arch_check_processor_compat(void *rtn) kvm_x86_ops->check_processor_compatibility(rtn); } +bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp); + +bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; +} + bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL); @@ -8218,6 +7983,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) kvm_x86_ops->interrupt_allowed(vcpu); } +void kvm_arch_start_assignment(struct kvm *kvm) +{ + atomic_inc(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); + +void kvm_arch_end_assignment(struct kvm *kvm) +{ + atomic_dec(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); + +bool kvm_arch_has_assigned_device(struct kvm *kvm) +{ + return atomic_read(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); + void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { atomic_inc(&kvm->arch.noncoherent_dma_count); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index edc8cdcd786b..2f822cd886c2 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -147,6 +147,16 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu, return kvm_register_write(vcpu, reg, val); } +static inline u64 get_kernel_ns(void) +{ + return ktime_get_boot_ns(); +} + +static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) +{ + return !(kvm->arch.disabled_quirks & quirk); +} + void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); void kvm_set_pending_timer(struct kvm_vcpu *vcpu); |