diff options
Diffstat (limited to 'arch/x86')
58 files changed, 944 insertions, 574 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3dbb7e7..b3a1a5d 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 a15893d..d8c0d32 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/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 2c82bd1..7d69afd 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1193,6 +1193,10 @@ static efi_status_t setup_e820(struct boot_params *params, unsigned int e820_type = 0; unsigned long m = efi->efi_memmap; +#ifdef CONFIG_X86_64 + m |= (u64)efi->efi_memmap_hi << 32; +#endif + d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size)); switch (d->type) { case EFI_RESERVED_TYPE: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 3bb2c43..8cb3e43 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 bb187a6..a7e257d 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -140,6 +140,7 @@ sysexit_from_sys_call: */ andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) movl RIP(%rsp), %ecx /* User %eip */ + movq RAX(%rsp), %rax RESTORE_RSI_RDI xorl %edx, %edx /* Do not leak kernel information */ xorq %r8, %r8 @@ -205,7 +206,6 @@ 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 @@ -220,7 +220,6 @@ sysexit_from_sys_call: 1: setbe %al /* 1 if error, 0 if not */ movzbl %al, %edi /* zero-extend that into %edi */ call __audit_syscall_exit - movq RAX(%rsp), %rax /* reload syscall return value */ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF @@ -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) @@ -369,6 +368,7 @@ sysretl_from_sys_call: RESTORE_RSI_RDI_RDX movl RIP(%rsp), %ecx movl EFLAGS(%rsp), %r11d + movq RAX(%rsp), %rax xorq %r10, %r10 xorq %r9, %r9 xorq %r8, %r8 @@ -392,7 +392,9 @@ 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 +406,16 @@ 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 +425,7 @@ 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 4dd1f2d..aeac434 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/desc.h b/arch/x86/include/asm/desc.h index a0bf89f..4e10d73 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -280,21 +280,6 @@ static inline void clear_LDT(void) set_ldt(NULL, 0); } -/* - * load one particular LDT into the current CPU - */ -static inline void load_LDT_nolock(mm_context_t *pc) -{ - set_ldt(pc->ldt, pc->size); -} - -static inline void load_LDT(mm_context_t *pc) -{ - preempt_disable(); - load_LDT_nolock(pc); - preempt_enable(); -} - static inline unsigned long get_desc_base(const struct desc_struct *desc) { return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 0637826..c49c517 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 200ec2e..cd0310e 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 2a7f5d7..49ec903 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 4e881a3..0000000 --- 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.h b/arch/x86/include/asm/mmu.h index 09b9620..364d274 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -9,8 +9,7 @@ * we put the segment information here. */ typedef struct { - void *ldt; - int size; + struct ldt_struct *ldt; #ifdef CONFIG_X86_64 /* True if mm supports a task running in 32 bit compatibility mode. */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 5e8daee..984abfe 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 @@ -34,6 +34,50 @@ static inline void load_mm_cr4(struct mm_struct *mm) {} #endif /* + * ldt_structs can be allocated, used, and freed, but they are never + * modified while live. + */ +struct ldt_struct { + /* + * Xen requires page-aligned LDTs with special permissions. This is + * needed to prevent us from installing evil descriptors such as + * call gates. On native, we could merge the ldt_struct and LDT + * allocations, but it's not worth trying to optimize. + */ + struct desc_struct *entries; + int size; +}; + +static inline void load_mm_ldt(struct mm_struct *mm) +{ + struct ldt_struct *ldt; + + /* lockless_dereference synchronizes with smp_store_release */ + ldt = lockless_dereference(mm->context.ldt); + + /* + * Any change to mm->context.ldt is followed by an IPI to all + * CPUs with the mm active. The LDT will not be freed until + * after the IPI is handled by all such CPUs. This means that, + * if the ldt_struct changes before we return, the values we see + * will be safe, and the new values will be loaded before we run + * any user code. + * + * NB: don't try to convert this to use RCU without extreme care. + * We would still need IRQs off, because we don't want to change + * the local LDT after an IPI loaded a newer value than the one + * that we can see. + */ + + if (unlikely(ldt)) + set_ldt(ldt->entries, ldt->size); + else + clear_LDT(); + + DEBUG_LOCKS_WARN_ON(preemptible()); +} + +/* * Used for LDT copy/destruction. */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm); @@ -78,12 +122,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * was called and then modify_ldt changed * prev->context.ldt but suppressed an IPI to this CPU. * In this case, prev->context.ldt != NULL, because we - * never free an LDT while the mm still exists. That - * means that next->context.ldt != prev->context.ldt, - * because mms never share an LDT. + * never set context.ldt to NULL while the mm still + * exists. That means that next->context.ldt != + * prev->context.ldt, because mms never share an LDT. */ if (unlikely(prev->context.ldt != next->context.ldt)) - load_LDT_nolock(&next->context); + load_mm_ldt(next); } #ifdef CONFIG_SMP else { @@ -106,7 +150,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); load_mm_cr4(next); - load_LDT_nolock(&next->context); + load_mm_ldt(next); } } #endif diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 43e6519..944f178 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/sigcontext.h b/arch/x86/include/asm/sigcontext.h index 6fe6b18..9dfce4e 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -57,9 +57,9 @@ struct sigcontext { unsigned long ip; unsigned long flags; unsigned short cs; - unsigned short __pad2; /* Was called gs, but was always zero. */ - unsigned short __pad1; /* Was called fs, but was always zero. */ - unsigned short ss; + unsigned short gs; + unsigned short fs; + unsigned short __pad0; unsigned long err; unsigned long trapno; unsigned long oldmask; diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 751bf4b..d7f3b3b 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -79,12 +79,12 @@ do { \ #else /* CONFIG_X86_32 */ /* frame pointer must be last for get_wchan */ -#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t" -#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t" +#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" +#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t" #define __EXTRA_CLOBBER \ , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ - "r12", "r13", "r14", "r15", "flags" + "r12", "r13", "r14", "r15" #ifdef CONFIG_CC_STACKPROTECTOR #define __switch_canary \ @@ -100,11 +100,7 @@ do { \ #define __switch_canary_iparam #endif /* CC_STACKPROTECTOR */ -/* - * There is no need to save or restore flags, because flags are always - * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL - * has no effect. - */ +/* Save restore flags to clear handle leaking NT */ #define switch_to(prev, next, last) \ asm volatile(SAVE_CONTEXT \ "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 8fba544..f36d56b 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 a4ae82e..cd54147 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/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index 0e8a973..40836a9 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -177,24 +177,9 @@ struct sigcontext { __u64 rip; __u64 eflags; /* RFLAGS */ __u16 cs; - - /* - * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"), - * Linux saved and restored fs and gs in these slots. This - * was counterproductive, as fsbase and gsbase were never - * saved, so arch_prctl was presumably unreliable. - * - * If these slots are ever needed for any other purpose, there - * is some risk that very old 64-bit binaries could get - * confused. I doubt that many such binaries still work, - * though, since the same patch in 2.5.64 also removed the - * 64-bit set_thread_area syscall, so it appears that there is - * no TLS API that works in both pre- and post-2.5.64 kernels. - */ - __u16 __pad2; /* Was gs. */ - __u16 __pad1; /* Was fs. */ - - __u16 ss; + __u16 gs; + __u16 fs; + __u16 __pad0; __u64 err; __u64 trapno; __u64 oldmask; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index dcb5285..cde732c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1424,7 +1424,7 @@ static inline void __x2apic_disable(void) { u64 msr; - if (cpu_has_apic) + if (!cpu_has_apic) return; rdmsrl(MSR_IA32_APICBASE, msr); @@ -1483,10 +1483,13 @@ void x2apic_setup(void) static __init void x2apic_disable(void) { - u32 x2apic_id; + u32 x2apic_id, state = x2apic_state; - if (x2apic_state != X2APIC_ON) - goto out; + x2apic_mode = 0; + x2apic_state = X2APIC_DISABLED; + + if (state != X2APIC_ON) + return; x2apic_id = read_apic_id(); if (x2apic_id >= 255) @@ -1494,9 +1497,6 @@ static __init void x2apic_disable(void) __x2apic_disable(); register_lapic_address(mp_lapic_addr); -out: - x2apic_state = X2APIC_DISABLED; - x2apic_mode = 0; } static __init void x2apic_enable(void) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 845dc0d..206052e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -943,7 +943,7 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) */ if (irq < nr_legacy_irqs() && data->count == 1) { if (info->ioapic_trigger != data->trigger) - mp_register_handler(irq, data->trigger); + mp_register_handler(irq, info->ioapic_trigger); data->entry.trigger = data->trigger = info->ioapic_trigger; data->entry.polarity = data->polarity = info->ioapic_polarity; } diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f813261..2683f36 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -322,7 +322,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irq_data->chip = &lapic_controller; irq_data->chip_data = data; irq_data->hwirq = virq + i; - err = assign_irq_vector_policy(virq, irq_data->node, data, + err = assign_irq_vector_policy(virq + i, irq_data->node, data, info); if (err) goto error; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 922c5e0..cb9e5df 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1410,7 +1410,7 @@ void cpu_init(void) load_sp0(t, ¤t->thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); clear_all_debug_regs(); dbg_restore_debug_regs(); @@ -1459,7 +1459,7 @@ void cpu_init(void) load_sp0(t, thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 3658de4..9469dfa 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -2179,21 +2179,25 @@ static unsigned long get_segment_base(unsigned int segment) int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { + struct ldt_struct *ldt; + if (idx > LDT_ENTRIES) return 0; - if (idx > current->active_mm->context.size) + /* IRQs are off, so this synchronizes with smp_store_release */ + ldt = lockless_dereference(current->active_mm->context.ldt); + if (!ldt || idx > ldt->size) return 0; - desc = current->active_mm->context.ldt; + desc = &ldt->entries[idx]; } else { if (idx > GDT_ENTRIES) return 0; - desc = raw_cpu_ptr(gdt_page.gdt); + desc = raw_cpu_ptr(gdt_page.gdt) + idx; } - return get_desc_base(desc + idx); + return get_desc_base(desc); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index b9826a9..6326ae2 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2534,7 +2534,7 @@ static int intel_pmu_cpu_prepare(int cpu) if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) - return NOTIFY_BAD; + goto err; } if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { @@ -2542,18 +2542,27 @@ static int intel_pmu_cpu_prepare(int cpu) cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); if (!cpuc->constraint_list) - return NOTIFY_BAD; + goto err_shared_regs; cpuc->excl_cntrs = allocate_excl_cntrs(cpu); - if (!cpuc->excl_cntrs) { - kfree(cpuc->constraint_list); - kfree(cpuc->shared_regs); - return NOTIFY_BAD; - } + if (!cpuc->excl_cntrs) + goto err_constraint_list; + cpuc->excl_thread_id = 0; } return NOTIFY_OK; + +err_constraint_list: + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; + +err_shared_regs: + kfree(cpuc->shared_regs); + cpuc->shared_regs = NULL; + +err: + return NOTIFY_BAD; } static void intel_pmu_cpu_starting(int cpu) diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index 1880761..377e8f8 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. @@ -1247,7 +1255,7 @@ static inline void cqm_pick_event_reader(int cpu) cpumask_set_cpu(cpu, &cqm_cpumask); } -static void intel_cqm_cpu_prepare(unsigned int cpu) +static void intel_cqm_cpu_starting(unsigned int cpu) { struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -1288,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb, unsigned int cpu = (unsigned long)hcpu; switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - intel_cqm_cpu_prepare(cpu); - break; case CPU_DOWN_PREPARE: intel_cqm_cpu_exit(cpu); break; case CPU_STARTING: + intel_cqm_cpu_starting(cpu); cqm_pick_event_reader(cpu); break; } @@ -1365,7 +1371,7 @@ static int __init intel_cqm_init(void) goto out; for_each_online_cpu(i) { - intel_cqm_cpu_prepare(i); + intel_cqm_cpu_starting(i); cqm_pick_event_reader(i); } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 79de954..d25097c 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -270,7 +270,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; - if (src_fpu->fpstate_active) + if (src_fpu->fpstate_active && cpu_has_fpu) fpu_copy(dst_fpu, src_fpu); return 0; diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 3282679..d14e9ac 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: @@ -38,7 +40,12 @@ static void fpu__init_cpu_generic(void) write_cr0(cr0); /* Flush out any pending x87 state: */ - asm volatile ("fninit"); +#ifdef CONFIG_MATH_EMULATION + if (!cpu_has_fpu) + fpstate_init_soft(¤t->thread.fpu.state.soft); + else +#endif + asm volatile ("fninit"); } /* @@ -136,6 +143,43 @@ 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 +331,7 @@ 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 +356,15 @@ 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/ldt.c b/arch/x86/kernel/ldt.c index c37886d..2bcc052 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> @@ -20,82 +21,82 @@ #include <asm/mmu_context.h> #include <asm/syscalls.h> -#ifdef CONFIG_SMP +/* context.lock is held for us, so we don't need any locking. */ static void flush_ldt(void *current_mm) { - if (current->active_mm == current_mm) - load_LDT(¤t->active_mm->context); + mm_context_t *pc; + + if (current->active_mm != current_mm) + return; + + pc = ¤t->active_mm->context; + set_ldt(pc->ldt->entries, pc->ldt->size); } -#endif -static int alloc_ldt(mm_context_t *pc, int mincount, int reload) +/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ +static struct ldt_struct *alloc_ldt_struct(int size) { - void *oldldt, *newldt; - int oldsize; - - if (mincount <= pc->size) - return 0; - oldsize = pc->size; - mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) & - (~(PAGE_SIZE / LDT_ENTRY_SIZE - 1)); - if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE) - newldt = vmalloc(mincount * LDT_ENTRY_SIZE); + struct ldt_struct *new_ldt; + int alloc_size; + + if (size > LDT_ENTRIES) + return NULL; + + new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); + if (!new_ldt) + return NULL; + + BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); + alloc_size = size * LDT_ENTRY_SIZE; + + /* + * Xen is very picky: it requires a page-aligned LDT that has no + * trailing nonzero bytes in any page that contains LDT descriptors. + * Keep it simple: zero the whole allocation and never allocate less + * than PAGE_SIZE. + */ + if (alloc_size > PAGE_SIZE) + new_ldt->entries = vzalloc(alloc_size); else - newldt = (void *)__get_free_page(GFP_KERNEL); - - if (!newldt) - return -ENOMEM; + new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (oldsize) - memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE); - oldldt = pc->ldt; - memset(newldt + oldsize * LDT_ENTRY_SIZE, 0, - (mincount - oldsize) * LDT_ENTRY_SIZE); + if (!new_ldt->entries) { + kfree(new_ldt); + return NULL; + } - paravirt_alloc_ldt(newldt, mincount); + new_ldt->size = size; + return new_ldt; +} -#ifdef CONFIG_X86_64 - /* CHECKME: Do we really need this ? */ - wmb(); -#endif - pc->ldt = newldt; - wmb(); - pc->size = mincount; - wmb(); - - if (reload) { -#ifdef CONFIG_SMP - preempt_disable(); - load_LDT(pc); - if (!cpumask_equal(mm_cpumask(current->mm), - cpumask_of(smp_processor_id()))) - smp_call_function(flush_ldt, current->mm, 1); - preempt_enable(); -#else - load_LDT(pc); -#endif - } - if (oldsize) { - paravirt_free_ldt(oldldt, oldsize); - if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(oldldt); - else - put_page(virt_to_page(oldldt)); - } - return 0; +/* After calling this, the LDT is immutable. */ +static void finalize_ldt_struct(struct ldt_struct *ldt) +{ + paravirt_alloc_ldt(ldt->entries, ldt->size); } -static inline int copy_ldt(mm_context_t *new, mm_context_t *old) +/* context.lock is held */ +static void install_ldt(struct mm_struct *current_mm, + struct ldt_struct *ldt) { - int err = alloc_ldt(new, old->size, 0); - int i; + /* Synchronizes with lockless_dereference in load_mm_ldt. */ + smp_store_release(¤t_mm->context.ldt, ldt); + + /* Activate the LDT for all CPUs using current_mm. */ + on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true); +} - if (err < 0) - return err; +static void free_ldt_struct(struct ldt_struct *ldt) +{ + if (likely(!ldt)) + return; - for (i = 0; i < old->size; i++) - write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE); - return 0; + paravirt_free_ldt(ldt->entries, ldt->size); + if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(ldt->entries); + else + kfree(ldt->entries); + kfree(ldt); } /* @@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old) */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + struct ldt_struct *new_ldt; struct mm_struct *old_mm; int retval = 0; mutex_init(&mm->context.lock); - mm->context.size = 0; old_mm = current->mm; - if (old_mm && old_mm->context.size > 0) { - mutex_lock(&old_mm->context.lock); - retval = copy_ldt(&mm->context, &old_mm->context); - mutex_unlock(&old_mm->context.lock); + if (!old_mm) { + mm->context.ldt = NULL; + return 0; } + + mutex_lock(&old_mm->context.lock); + if (!old_mm->context.ldt) { + mm->context.ldt = NULL; + goto out_unlock; + } + + new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + if (!new_ldt) { + retval = -ENOMEM; + goto out_unlock; + } + + memcpy(new_ldt->entries, old_mm->context.ldt->entries, + new_ldt->size * LDT_ENTRY_SIZE); + finalize_ldt_struct(new_ldt); + + mm->context.ldt = new_ldt; + +out_unlock: + mutex_unlock(&old_mm->context.lock); return retval; } @@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) */ void destroy_context(struct mm_struct *mm) { - if (mm->context.size) { -#ifdef CONFIG_X86_32 - /* CHECKME: Can this ever happen ? */ - if (mm == current->active_mm) - clear_LDT(); -#endif - paravirt_free_ldt(mm->context.ldt, mm->context.size); - if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(mm->context.ldt); - else - put_page(virt_to_page(mm->context.ldt)); - mm->context.size = 0; - } + free_ldt_struct(mm->context.ldt); + mm->context.ldt = NULL; } static int read_ldt(void __user *ptr, unsigned long bytecount) { - int err; + int retval; unsigned long size; struct mm_struct *mm = current->mm; - if (!mm->context.size) - return 0; + mutex_lock(&mm->context.lock); + + if (!mm->context.ldt) { + retval = 0; + goto out_unlock; + } + if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - mutex_lock(&mm->context.lock); - size = mm->context.size * LDT_ENTRY_SIZE; + size = mm->context.ldt->size * LDT_ENTRY_SIZE; if (size > bytecount) size = bytecount; - err = 0; - if (copy_to_user(ptr, mm->context.ldt, size)) - err = -EFAULT; - mutex_unlock(&mm->context.lock); - if (err < 0) - goto error_return; + if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + retval = -EFAULT; + goto out_unlock; + } + if (size != bytecount) { - /* zero-fill the rest */ - if (clear_user(ptr + size, bytecount - size) != 0) { - err = -EFAULT; - goto error_return; + /* Zero-fill the rest and pretend we read bytecount bytes. */ + if (clear_user(ptr + size, bytecount - size)) { + retval = -EFAULT; + goto out_unlock; } } - return bytecount; -error_return: - return err; + retval = bytecount; + +out_unlock: + mutex_unlock(&mm->context.lock); + return retval; } static int read_default_ldt(void __user *ptr, unsigned long bytecount) @@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) struct desc_struct ldt; int error; struct user_desc ldt_info; + int oldsize, newsize; + struct ldt_struct *new_ldt, *old_ldt; error = -EINVAL; if (bytecount != sizeof(ldt_info)) @@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) goto out; } - mutex_lock(&mm->context.lock); - if (ldt_info.entry_number >= mm->context.size) { - error = alloc_ldt(¤t->mm->context, - ldt_info.entry_number + 1, 1); - if (error < 0) - goto out_unlock; - } - - /* Allow LDTs to be cleared by the user. */ - if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { - if (oldmode || LDT_empty(&ldt_info)) { - memset(&ldt, 0, sizeof(ldt)); - goto install; + if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) || + LDT_empty(&ldt_info)) { + /* The user wants to clear the entry. */ + memset(&ldt, 0, sizeof(ldt)); + } else { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out; } + + fill_ldt(&ldt, &ldt_info); + if (oldmode) + ldt.avl = 0; } - if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { - error = -EINVAL; + mutex_lock(&mm->context.lock); + + old_ldt = mm->context.ldt; + oldsize = old_ldt ? old_ldt->size : 0; + newsize = max((int)(ldt_info.entry_number + 1), oldsize); + + error = -ENOMEM; + new_ldt = alloc_ldt_struct(newsize); + if (!new_ldt) goto out_unlock; - } - fill_ldt(&ldt, &ldt_info); - if (oldmode) - ldt.avl = 0; + if (old_ldt) + memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; + finalize_ldt_struct(new_ldt); - /* Install the new entry ... */ -install: - write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt); + install_ldt(mm, new_ldt); + free_ldt_struct(old_ldt); error = 0; out_unlock: diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index c3e985d..d05bd2e 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 9cad694..c27cad7 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); } @@ -408,6 +408,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) static void mwait_idle(void) { if (!current_set_polling_and_test()) { + trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { smp_mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); @@ -419,6 +420,7 @@ static void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 71d7849..f6b9163 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -121,11 +121,11 @@ void __show_regs(struct pt_regs *regs, int all) void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { - if (dead_task->mm->context.size) { + if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt, - dead_task->mm->context.size); + dead_task->mm->context.ldt->size); BUG(); } } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 206996c..71820c4 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -93,8 +93,15 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) COPY(r15); #endif /* CONFIG_X86_64 */ +#ifdef CONFIG_X86_32 COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); +#else /* !CONFIG_X86_32 */ + /* Kernel saves and restores only the CS segment register on signals, + * which is the bare minimum needed to allow mixed 32/64-bit code. + * App's signal handler can save/restore other segments if needed. */ + COPY_SEG_CPL3(cs); +#endif /* CONFIG_X86_32 */ get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); @@ -154,9 +161,8 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, #else /* !CONFIG_X86_32 */ put_user_ex(regs->flags, &sc->flags); put_user_ex(regs->cs, &sc->cs); - put_user_ex(0, &sc->__pad2); - put_user_ex(0, &sc->__pad1); - put_user_ex(regs->ss, &sc->ss); + put_user_ex(0, &sc->gs); + put_user_ex(0, &sc->fs); #endif /* CONFIG_X86_32 */ put_user_ex(fpstate, &sc->fpstate); @@ -451,19 +457,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, regs->sp = (unsigned long)frame; - /* - * Set up the CS and SS registers to run signal handlers in - * 64-bit mode, even if the handler happens to be interrupting - * 32-bit or 16-bit code. - * - * SS is subtle. In 64-bit mode, we don't need any particular - * SS descriptor, but we do need SS to be valid. It's possible - * that the old SS is entirely bogus -- this can happen if the - * signal we're trying to deliver is #GP or #SS caused by a bad - * SS value. - */ + /* Set up the CS register to run signal handlers in 64-bit mode, + even if the handler happens to be interrupting 32-bit code. */ regs->cs = __USER_CS; - regs->ss = __USER_DS; return 0; } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index d3010aa..b1f3ed9c 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/kernel/step.c b/arch/x86/kernel/step.c index 9b4d51d..0ccb53a 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -5,6 +5,7 @@ #include <linux/mm.h> #include <linux/ptrace.h> #include <asm/desc.h> +#include <asm/mmu_context.h> unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs) { @@ -27,13 +28,14 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re struct desc_struct *desc; unsigned long base; - seg &= ~7UL; + seg >>= 3; mutex_lock(&child->mm->context.lock); - if (unlikely((seg >> 3) >= child->mm->context.size)) + if (unlikely(!child->mm->context.ldt || + seg >= child->mm->context.ldt->size)) addr = -1L; /* bogus selector, access would fault */ else { - desc = child->mm->context.ldt + seg; + desc = &child->mm->context.ldt->entries[seg]; base = get_desc_base(desc); /* 16-bit code segment? */ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 64dd467..2fbea25 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 7dbced3..5c520eb 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 954e98a..2a5ca97 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 f807496..4417146 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 de1d2d8..9e8bf13 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/svm.c b/arch/x86/kvm/svm.c index 602b974..8e0c084 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 e856dd5..83b7b5c 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 bbaf44e..8f0f6ec 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2105,7 +2105,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (guest_cpuid_has_tsc_adjust(vcpu)) { if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; - kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true); + adjust_tsc_offset_guest(vcpu, adj); } vcpu->arch.ia32_tsc_adjust_msr = data; } @@ -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; } @@ -6328,6 +6327,7 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf) static void process_smi(struct kvm_vcpu *vcpu) { struct kvm_segment cs, ds; + struct desc_ptr dt; char buf[512]; u32 cr0; @@ -6360,6 +6360,10 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_x86_ops->set_cr4(vcpu, 0); + /* Undocumented: IDT limit is set to zero on entry to SMM. */ + dt.address = dt.size = 0; + kvm_x86_ops->set_idt(vcpu, &dt); + __kvm_set_dr(vcpu, 7, DR7_FIXED_1); cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; @@ -7315,11 +7319,6 @@ 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 +8217,24 @@ 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 edc8cdc..0ca2f3e 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/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index f37e84a..3d8f2e4 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -29,7 +29,6 @@ #include <asm/uaccess.h> #include <asm/traps.h> -#include <asm/desc.h> #include <asm/user.h> #include <asm/fpu/internal.h> @@ -181,7 +180,7 @@ void math_emulate(struct math_emu_info *info) math_abort(FPU_info, SIGILL); } - code_descriptor = LDT_DESCRIPTOR(FPU_CS); + code_descriptor = FPU_get_ldt_descriptor(FPU_CS); if (SEG_D_SIZE(code_descriptor)) { /* The above test may be wrong, the book is not clear */ /* Segmented 32 bit protected mode */ diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 9ccecb6..5e044d5 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -16,9 +16,24 @@ #include <linux/kernel.h> #include <linux/mm.h> -/* s is always from a cpu register, and the cpu does bounds checking - * during register load --> no further bounds checks needed */ -#define LDT_DESCRIPTOR(s) (((struct desc_struct *)current->mm->context.ldt)[(s) >> 3]) +#include <asm/desc.h> +#include <asm/mmu_context.h> + +static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) +{ + static struct desc_struct zero_desc; + struct desc_struct ret = zero_desc; + +#ifdef CONFIG_MODIFY_LDT_SYSCALL + seg >>= 3; + mutex_lock(¤t->mm->context.lock); + if (current->mm->context.ldt && seg < current->mm->context.ldt->size) + ret = current->mm->context.ldt->entries[seg]; + mutex_unlock(¤t->mm->context.lock); +#endif + return ret; +} + #define SEG_D_SIZE(x) ((x).b & (3 << 21)) #define SEG_G_BIT(x) ((x).b & (1 << 23)) #define SEG_GRANULARITY(x) (((x).b & (1 << 23)) ? 4096 : 1) diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index 6ef5e99..8300db7 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -20,7 +20,6 @@ #include <linux/stddef.h> #include <asm/uaccess.h> -#include <asm/desc.h> #include "fpu_system.h" #include "exception.h" @@ -158,7 +157,7 @@ static long pm_address(u_char FPU_modrm, u_char segment, addr->selector = PM_REG_(segment); } - descriptor = LDT_DESCRIPTOR(PM_REG_(segment)); + descriptor = FPU_get_ldt_descriptor(addr->selector); base_address = SEG_BASE_ADDR(descriptor); address = base_address + offset; limit = base_address diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index cc5ccc4..b9c78f3 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 9d518d6..844b06d 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 7a657f5..db1b0bc 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 3250f23..90b924a 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); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 579a8fd..be2e7a2 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -269,7 +269,7 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ offsetof(struct bpf_array, map.max_entries)); EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ -#define OFFSET1 44 /* number of bytes to jump */ +#define OFFSET1 47 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; @@ -278,15 +278,15 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 33 +#define OFFSET2 36 EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ /* prog = array->prog[index]; */ - EMIT4(0x48, 0x8D, 0x44, 0xD6); /* lea rax, [rsi + rdx * 8 + 0x50] */ - EMIT1(offsetof(struct bpf_array, prog)); + EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ + offsetof(struct bpf_array, prog)); EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */ /* if (prog == NULL) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index cfba30f..e4308fe 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -972,6 +972,11 @@ u64 efi_mem_attributes(unsigned long phys_addr) static int __init arch_parse_efi_cmdline(char *str) { + if (!str) { + pr_warn("need at least one option\n"); + return -EINVAL; + } + if (parse_option_str(str, "old_map")) set_bit(EFI_OLD_MEMMAP, &efi.flags); if (parse_option_str(str, "debug")) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 0d7dd1f..9ab5279 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -22,6 +22,7 @@ #include <asm/fpu/internal.h> #include <asm/debugreg.h> #include <asm/cpu.h> +#include <asm/mmu_context.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -153,7 +154,7 @@ static void fix_processor_context(void) syscall_init(); /* This sets MSR_*STAR and related */ #endif load_TR_desc(); /* This does ltr */ - load_LDT(¤t->active_mm->context); /* This does lldt */ + load_mm_ldt(current->active_mm); /* This does lldt */ fpu__resume_cpu(); } diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index e88fda8..4841453 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -8,7 +8,7 @@ config XEN select PARAVIRT_CLOCK select XEN_HAVE_PVMMU depends on X86_64 || (X86_32 && X86_PAE) - depends on X86_TSC + depends on X86_LOCAL_APIC && X86_TSC help This is the Linux Xen port. Enabling this will allow the kernel to boot in a paravirtualized environment under the @@ -17,7 +17,7 @@ config XEN config XEN_DOM0 def_bool y depends on XEN && PCI_XEN && SWIOTLB_XEN - depends on X86_LOCAL_APIC && X86_IO_APIC && ACPI && PCI + depends on X86_IO_APIC && ACPI && PCI config XEN_PVHVM def_bool y diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 7322755..4b6e29a 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -13,13 +13,13 @@ CFLAGS_mmu.o := $(nostackp) obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ grant-table.o suspend.o platform-pci-unplug.o \ - p2m.o + p2m.o apic.o obj-$(CONFIG_EVENT_TRACING) += trace.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_DOM0) += apic.o vga.o +obj-$(CONFIG_XEN_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0b95c9b..11d6fb4 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -483,6 +483,7 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte_t pte; unsigned long pfn; struct page *page; + unsigned char dummy; ptep = lookup_address((unsigned long)v, &level); BUG_ON(ptep == NULL); @@ -492,6 +493,32 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte = pfn_pte(pfn, prot); + /* + * Careful: update_va_mapping() will fail if the virtual address + * we're poking isn't populated in the page tables. We don't + * need to worry about the direct map (that's always in the page + * tables), but we need to be careful about vmap space. In + * particular, the top level page table can lazily propagate + * entries between processes, so if we've switched mms since we + * vmapped the target in the first place, we might not have the + * top-level page table entry populated. + * + * We disable preemption because we want the same mm active when + * we probe the target and when we issue the hypercall. We'll + * have the same nominal mm, but if we're a kernel thread, lazy + * mm dropping could change our pgd. + * + * Out of an abundance of caution, this uses __get_user() to fault + * in the target address just in case there's some obscure case + * in which the target address isn't readable. + */ + + preempt_disable(); + + pagefault_disable(); /* Avoid warnings due to being atomic. */ + __get_user(dummy, (unsigned char __user __force *)v); + pagefault_enable(); + if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); @@ -503,6 +530,8 @@ static void set_aliased_prot(void *v, pgprot_t prot) BUG(); } else kmap_flush_unused(); + + preempt_enable(); } static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) @@ -510,6 +539,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE; int i; + /* + * We need to mark the all aliases of the LDT pages RO. We + * don't need to call vm_flush_aliases(), though, since that's + * only responsible for flushing aliases out the TLBs, not the + * page tables, and Xen will flush the TLB for us if needed. + * + * To avoid confusing future readers: none of this is necessary + * to load the LDT. The hypervisor only checks this when the + * LDT is faulted in due to subsequent descriptor access. + */ + for(i = 0; i < entries; i += entries_per_page) set_aliased_prot(ldt + i, PAGE_KERNEL_RO); } diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index c20fe29..2292721 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -101,17 +101,15 @@ struct dom0_vga_console_info; #ifdef CONFIG_XEN_DOM0 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); -void __init xen_init_apic(void); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) { } -static inline void __init xen_init_apic(void) -{ -} #endif +void __init xen_init_apic(void); + #ifdef CONFIG_XEN_EFI extern void xen_efi_init(void); #else |