diff options
Diffstat (limited to 'arch/x86')
31 files changed, 588 insertions, 332 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/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index bb187a6a877c..5a1844765a7a 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -205,7 +205,6 @@ sysexit_from_sys_call: movl RDX(%rsp), %edx /* arg3 */ movl RSI(%rsp), %ecx /* arg4 */ movl RDI(%rsp), %r8d /* arg5 */ - movl %ebp, %r9d /* arg6 */ .endm .macro auditsys_exit exit @@ -236,6 +235,7 @@ sysexit_from_sys_call: sysenter_auditsys: auditsys_entry_common + movl %ebp, %r9d /* reload 6th syscall arg */ jmp sysenter_dispatch sysexit_audit: @@ -336,7 +336,7 @@ ENTRY(entry_SYSCALL_compat) * 32-bit zero extended: */ ASM_STAC -1: movl (%r8), %ebp +1: movl (%r8), %r9d _ASM_EXTABLE(1b, ia32_badarg) ASM_CLAC orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) @@ -346,7 +346,7 @@ ENTRY(entry_SYSCALL_compat) cstar_do_call: /* 32-bit syscall -> 64-bit C ABI argument conversion */ movl %edi, %r8d /* arg5 */ - movl %ebp, %r9d /* arg6 */ + /* r9 already loaded */ /* arg6 */ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */ movl %ebx, %edi /* arg1 */ movl %edx, %edx /* arg3 (zero extension) */ @@ -358,7 +358,6 @@ cstar_dispatch: call *ia32_sys_call_table(, %rax, 8) movq %rax, RAX(%rsp) 1: - movl RCX(%rsp), %ebp DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) @@ -392,7 +391,9 @@ sysretl_from_sys_call: #ifdef CONFIG_AUDITSYSCALL cstar_auditsys: + movl %r9d, R9(%rsp) /* register to be clobbered by call */ auditsys_entry_common + movl R9(%rsp), %r9d /* reload 6th syscall arg */ jmp cstar_dispatch sysretl_audit: @@ -404,14 +405,16 @@ cstar_tracesys: testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jz cstar_auditsys #endif + xchgl %r9d, %ebp SAVE_EXTRA_REGS xorl %eax, %eax /* Do not leak kernel information */ movq %rax, R11(%rsp) movq %rax, R10(%rsp) - movq %rax, R9(%rsp) + movq %r9, R9(%rsp) movq %rax, R8(%rsp) movq %rsp, %rdi /* &pt_regs -> arg1 */ call syscall_trace_enter + movl R9(%rsp), %r9d /* Reload arg registers from stack. (see sysenter_tracesys) */ movl RCX(%rsp), %ecx @@ -421,6 +424,7 @@ cstar_tracesys: movl %eax, %eax /* zero extension */ RESTORE_EXTRA_REGS + xchgl %ebp, %r9d jmp cstar_do_call END(entry_SYSCALL_compat) 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..49ec9038ec14 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -604,6 +604,8 @@ 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; 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/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/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index 188076161c1b..63eb68b73589 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -952,6 +952,14 @@ static u64 intel_cqm_event_count(struct perf_event *event) return 0; /* + * Getting up-to-date values requires an SMP IPI which is not + * possible if we're being called in interrupt context. Return + * the cached values instead. + */ + if (unlikely(in_interrupt())) + goto out; + + /* * Notice that we don't perform the reading of an RMID * atomically, because we can't hold a spin lock across the * IPIs. diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 32826791e675..1e173f6285c7 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(); } @@ -311,9 +351,15 @@ static int __init x86_noxsave_setup(char *s) setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + setup_clear_cpu_cap(X86_FEATURE_XSAVEC); setup_clear_cpu_cap(X86_FEATURE_XSAVES); setup_clear_cpu_cap(X86_FEATURE_AVX); setup_clear_cpu_cap(X86_FEATURE_AVX2); + setup_clear_cpu_cap(X86_FEATURE_AVX512F); + setup_clear_cpu_cap(X86_FEATURE_AVX512PF); + setup_clear_cpu_cap(X86_FEATURE_AVX512ER); + setup_clear_cpu_cap(X86_FEATURE_AVX512CD); + setup_clear_cpu_cap(X86_FEATURE_MPX); return 1; } 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/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/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/lapic.c b/arch/x86/kvm/lapic.c index 954e98a8c2e3..2a5ca97c263b 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)); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f807496b62c2..44171462bd2a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2479,6 +2479,14 @@ 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 +2514,7 @@ 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; diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index de1d2d8062e2..dc0a84a6f309 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(); + + /* + * We just check one page, partially covered by MTRRs is + * impossible. + */ + WARN_ON(iter.partial_map); + + /* not contained in any MTRRs. */ + if (type == -1) + return mtrr_default_type(mtrr_state); + 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/svm.c b/arch/x86/kvm/svm.c index 602b974a60a6..8e0c0844c6b9 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 +1144,39 @@ 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; + + 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 +1272,7 @@ 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; } @@ -1579,7 +1672,7 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) * does not do it - this results in some delay at * reboot */ - if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED)) + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) cr0 &= ~(X86_CR0_CD | X86_CR0_NW); svm->vmcb->save.cr0 = cr0; mark_dirty(svm->vmcb, VMCB_CR); @@ -3254,6 +3347,16 @@ 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 +4191,6 @@ 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..83b7b5cd75d5 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8632,22 +8632,17 @@ 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 +8650,10 @@ 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..5ef2560075bf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3157,8 +3157,7 @@ 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; } @@ -7315,11 +7314,6 @@ 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; } @@ -8218,6 +8212,24 @@ 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..0ca2f3e4803c 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -147,6 +147,11 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu, return kvm_register_write(vcpu, reg, val); } +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); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index cc5ccc415cc0..b9c78f3bcd67 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -63,8 +63,6 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, !PageReserved(pfn_to_page(start_pfn + i))) return 1; - WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn); - return 0; } @@ -94,7 +92,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, pgprot_t prot; int retval; void __iomem *ret_addr; - int ram_region; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; @@ -117,23 +114,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ - /* First check if whole region can be identified as RAM or not */ - ram_region = region_is_ram(phys_addr, size); - if (ram_region > 0) { - WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n", - (unsigned long int)phys_addr, - (unsigned long int)last_addr); + pfn = phys_addr >> PAGE_SHIFT; + last_pfn = last_addr >> PAGE_SHIFT; + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) { + WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n", + &phys_addr, &last_addr); return NULL; } - /* If could not be identified(-1), check page by page */ - if (ram_region < 0) { - pfn = phys_addr >> PAGE_SHIFT; - last_pfn = last_addr >> PAGE_SHIFT; - if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, - __ioremap_check_ram) == 1) - return NULL; - } /* * Mappings have to be page-aligned */ diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 9d518d693b4b..844b06d67df4 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -126,3 +126,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm) mm->get_unmapped_area = arch_get_unmapped_area_topdown; } } + +const char *arch_vma_name(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_MPX) + return "[mpx]"; + return NULL; +} diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 7a657f58bbea..db1b0bc5017c 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -20,20 +20,6 @@ #define CREATE_TRACE_POINTS #include <asm/trace/mpx.h> -static const char *mpx_mapping_name(struct vm_area_struct *vma) -{ - return "[mpx]"; -} - -static struct vm_operations_struct mpx_vma_ops = { - .name = mpx_mapping_name, -}; - -static int is_mpx_vma(struct vm_area_struct *vma) -{ - return (vma->vm_ops == &mpx_vma_ops); -} - static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm) { if (is_64bit_mm(mm)) @@ -53,9 +39,6 @@ static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm) /* * This is really a simplified "vm_mmap". it only handles MPX * bounds tables (the bounds directory is user-allocated). - * - * Later on, we use the vma->vm_ops to uniquely identify these - * VMAs. */ static unsigned long mpx_mmap(unsigned long len) { @@ -101,7 +84,6 @@ static unsigned long mpx_mmap(unsigned long len) ret = -ENOMEM; goto out; } - vma->vm_ops = &mpx_vma_ops; if (vm_flags & VM_LOCKED) { up_write(&mm->mmap_sem); @@ -812,7 +794,7 @@ static noinline int zap_bt_entries_mapping(struct mm_struct *mm, * so stop immediately and return an error. This * probably results in a SIGSEGV. */ - if (!is_mpx_vma(vma)) + if (!(vma->vm_flags & VM_MPX)) return -EINVAL; len = min(vma->vm_end, end) - addr; @@ -945,9 +927,9 @@ static int try_unmap_single_bt(struct mm_struct *mm, * lots of tables even though we have no actual table * entries in use. */ - while (next && is_mpx_vma(next)) + while (next && (next->vm_flags & VM_MPX)) next = next->vm_next; - while (prev && is_mpx_vma(prev)) + while (prev && (prev->vm_flags & VM_MPX)) prev = prev->vm_prev; /* * We know 'start' and 'end' lie within an area controlled diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 3250f2371aea..90b924acd982 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -117,7 +117,7 @@ static void flush_tlb_func(void *info) } else { unsigned long addr; unsigned long nr_pages = - f->flush_end - f->flush_start / PAGE_SIZE; + (f->flush_end - f->flush_start) / PAGE_SIZE; addr = f->flush_start; while (addr < f->flush_end) { __flush_tlb_single(addr); |
