diff options
Diffstat (limited to 'arch')
40 files changed, 391 insertions, 174 deletions
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h index 7f36d00600b..feb988a7ec3 100644 --- a/arch/arm/include/asm/highmem.h +++ b/arch/arm/include/asm/highmem.h @@ -11,7 +11,11 @@ #define kmap_prot PAGE_KERNEL -#define flush_cache_kmaps() flush_cache_all() +#define flush_cache_kmaps() \ + do { \ + if (cache_is_vivt()) \ + flush_cache_all(); \ + } while (0) extern pte_t *pkmap_page_table; @@ -21,11 +25,20 @@ extern void *kmap_high(struct page *page); extern void *kmap_high_get(struct page *page); extern void kunmap_high(struct page *page); +extern void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte); +extern void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte); + +/* + * The following functions are already defined by <linux/highmem.h> + * when CONFIG_HIGHMEM is not set. + */ +#ifdef CONFIG_HIGHMEM extern void *kmap(struct page *page); extern void kunmap(struct page *page); extern void *kmap_atomic(struct page *page, enum km_type type); extern void kunmap_atomic(void *kvaddr, enum km_type type); extern void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); extern struct page *kmap_atomic_to_page(const void *ptr); +#endif #endif diff --git a/arch/arm/include/asm/kmap_types.h b/arch/arm/include/asm/kmap_types.h index c019949a518..c4b2ea3fbe4 100644 --- a/arch/arm/include/asm/kmap_types.h +++ b/arch/arm/include/asm/kmap_types.h @@ -18,6 +18,7 @@ enum km_type { KM_IRQ1, KM_SOFTIRQ0, KM_SOFTIRQ1, + KM_L1_CACHE, KM_L2_CACHE, KM_TYPE_NR }; diff --git a/arch/arm/include/asm/ucontext.h b/arch/arm/include/asm/ucontext.h index bf65e9f4525..47f023aa849 100644 --- a/arch/arm/include/asm/ucontext.h +++ b/arch/arm/include/asm/ucontext.h @@ -59,23 +59,22 @@ struct iwmmxt_sigframe { #endif /* CONFIG_IWMMXT */ #ifdef CONFIG_VFP -#if __LINUX_ARM_ARCH__ < 6 -/* For ARM pre-v6, we use fstmiax and fldmiax. This adds one extra - * word after the registers, and a word of padding at the end for - * alignment. */ #define VFP_MAGIC 0x56465001 -#define VFP_STORAGE_SIZE 152 -#else -#define VFP_MAGIC 0x56465002 -#define VFP_STORAGE_SIZE 144 -#endif struct vfp_sigframe { unsigned long magic; unsigned long size; - union vfp_state storage; -}; + struct user_vfp ufp; + struct user_vfp_exc ufp_exc; +} __attribute__((__aligned__(8))); + +/* + * 8 byte for magic and size, 264 byte for ufp, 12 bytes for ufp_exc, + * 4 bytes padding. + */ +#define VFP_STORAGE_SIZE sizeof(struct vfp_sigframe) + #endif /* CONFIG_VFP */ /* @@ -91,7 +90,7 @@ struct aux_sigframe { #ifdef CONFIG_IWMMXT struct iwmmxt_sigframe iwmmxt; #endif -#if 0 && defined CONFIG_VFP /* Not yet saved. */ +#ifdef CONFIG_VFP struct vfp_sigframe vfp; #endif /* Something that isn't a valid magic number for any coprocessor. */ diff --git a/arch/arm/include/asm/user.h b/arch/arm/include/asm/user.h index df95e050f9d..05ac4b06876 100644 --- a/arch/arm/include/asm/user.h +++ b/arch/arm/include/asm/user.h @@ -83,11 +83,21 @@ struct user{ /* * User specific VFP registers. If only VFPv2 is present, registers 16 to 31 - * are ignored by the ptrace system call. + * are ignored by the ptrace system call and the signal handler. */ struct user_vfp { unsigned long long fpregs[32]; unsigned long fpscr; }; +/* + * VFP exception registers exposed to user space during signal delivery. + * Fields not relavant to the current VFP architecture are ignored. + */ +struct user_vfp_exc { + unsigned long fpexc; + unsigned long fpinst; + unsigned long fpinst2; +}; + #endif /* _ARM_USER_H */ diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index e7714f367eb..907d5a620bc 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -18,6 +18,7 @@ #include <asm/cacheflush.h> #include <asm/ucontext.h> #include <asm/unistd.h> +#include <asm/vfp.h> #include "ptrace.h" #include "signal.h" @@ -175,6 +176,90 @@ static int restore_iwmmxt_context(struct iwmmxt_sigframe *frame) #endif +#ifdef CONFIG_VFP + +static int preserve_vfp_context(struct vfp_sigframe __user *frame) +{ + struct thread_info *thread = current_thread_info(); + struct vfp_hard_struct *h = &thread->vfpstate.hard; + const unsigned long magic = VFP_MAGIC; + const unsigned long size = VFP_STORAGE_SIZE; + int err = 0; + + vfp_sync_hwstate(thread); + __put_user_error(magic, &frame->magic, err); + __put_user_error(size, &frame->size, err); + + /* + * Copy the floating point registers. There can be unused + * registers see asm/hwcap.h for details. + */ + err |= __copy_to_user(&frame->ufp.fpregs, &h->fpregs, + sizeof(h->fpregs)); + /* + * Copy the status and control register. + */ + __put_user_error(h->fpscr, &frame->ufp.fpscr, err); + + /* + * Copy the exception registers. + */ + __put_user_error(h->fpexc, &frame->ufp_exc.fpexc, err); + __put_user_error(h->fpinst, &frame->ufp_exc.fpinst, err); + __put_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err); + + return err ? -EFAULT : 0; +} + +static int restore_vfp_context(struct vfp_sigframe __user *frame) +{ + struct thread_info *thread = current_thread_info(); + struct vfp_hard_struct *h = &thread->vfpstate.hard; + unsigned long magic; + unsigned long size; + unsigned long fpexc; + int err = 0; + + __get_user_error(magic, &frame->magic, err); + __get_user_error(size, &frame->size, err); + + if (err) + return -EFAULT; + if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE) + return -EINVAL; + + /* + * Copy the floating point registers. There can be unused + * registers see asm/hwcap.h for details. + */ + err |= __copy_from_user(&h->fpregs, &frame->ufp.fpregs, + sizeof(h->fpregs)); + /* + * Copy the status and control register. + */ + __get_user_error(h->fpscr, &frame->ufp.fpscr, err); + + /* + * Sanitise and restore the exception registers. + */ + __get_user_error(fpexc, &frame->ufp_exc.fpexc, err); + /* Ensure the VFP is enabled. */ + fpexc |= FPEXC_EN; + /* Ensure FPINST2 is invalid and the exception flag is cleared. */ + fpexc &= ~(FPEXC_EX | FPEXC_FP2V); + h->fpexc = fpexc; + + __get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err); + __get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err); + + if (!err) + vfp_flush_hwstate(thread); + + return err ? -EFAULT : 0; +} + +#endif + /* * Do a signal return; undo the signal stack. These are aligned to 64-bit. */ @@ -233,8 +318,8 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf) err |= restore_iwmmxt_context(&aux->iwmmxt); #endif #ifdef CONFIG_VFP -// if (err == 0) -// err |= vfp_restore_state(&sf->aux.vfp); + if (err == 0) + err |= restore_vfp_context(&aux->vfp); #endif return err; @@ -348,8 +433,8 @@ setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs, sigset_t *set) err |= preserve_iwmmxt_context(&aux->iwmmxt); #endif #ifdef CONFIG_VFP -// if (err == 0) -// err |= vfp_save_state(&sf->aux.vfp); + if (err == 0) + err |= preserve_vfp_context(&aux->vfp); #endif __put_user_error(0, &aux->end_magic, err); diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile index 027dd570dcc..d4004557532 100644 --- a/arch/arm/mach-at91/Makefile +++ b/arch/arm/mach-at91/Makefile @@ -16,8 +16,8 @@ obj-$(CONFIG_ARCH_AT91SAM9261) += at91sam9261.o at91sam926x_time.o at91sam9261_d obj-$(CONFIG_ARCH_AT91SAM9G10) += at91sam9261.o at91sam926x_time.o at91sam9261_devices.o sam9_smc.o obj-$(CONFIG_ARCH_AT91SAM9263) += at91sam9263.o at91sam926x_time.o at91sam9263_devices.o sam9_smc.o obj-$(CONFIG_ARCH_AT91SAM9RL) += at91sam9rl.o at91sam926x_time.o at91sam9rl_devices.o sam9_smc.o -obj-$(CONFIG_ARCH_AT91SAM9G20) += at91sam9260.o at91sam926x_time.o at91sam9260_devices.o sam9_smc.o - obj-$(CONFIG_ARCH_AT91SAM9G45) += at91sam9g45.o at91sam926x_time.o at91sam9g45_devices.o sam9_smc.o +obj-$(CONFIG_ARCH_AT91SAM9G20) += at91sam9260.o at91sam926x_time.o at91sam9260_devices.o sam9_smc.o +obj-$(CONFIG_ARCH_AT91SAM9G45) += at91sam9g45.o at91sam926x_time.o at91sam9g45_devices.o sam9_smc.o obj-$(CONFIG_ARCH_AT91CAP9) += at91cap9.o at91sam926x_time.o at91cap9_devices.o sam9_smc.o obj-$(CONFIG_ARCH_AT572D940HF) += at572d940hf.o at91sam926x_time.o at572d940hf_devices.o sam9_smc.o obj-$(CONFIG_ARCH_AT91X40) += at91x40.o at91x40_time.o diff --git a/arch/arm/mach-at91/pm_slowclock.S b/arch/arm/mach-at91/pm_slowclock.S index 9fcbd6ca009..9c5b48e68a7 100644 --- a/arch/arm/mach-at91/pm_slowclock.S +++ b/arch/arm/mach-at91/pm_slowclock.S @@ -175,8 +175,6 @@ ENTRY(at91_slow_clock) orr r3, r3, #(1 << 29) /* bit 29 always set */ str r3, [r1, #(AT91_CKGR_PLLAR - AT91_PMC)] - wait_pllalock - /* Save PLLB setting and disable it */ ldr r3, [r1, #(AT91_CKGR_PLLBR - AT91_PMC)] str r3, .saved_pllbr @@ -184,8 +182,6 @@ ENTRY(at91_slow_clock) mov r3, #AT91_PMC_PLLCOUNT str r3, [r1, #(AT91_CKGR_PLLBR - AT91_PMC)] - wait_pllblock - /* Turn off the main oscillator */ ldr r3, [r1, #(AT91_CKGR_MOR - AT91_PMC)] bic r3, r3, #AT91_PMC_MOSCEN diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c index 8bca4dea6df..f55fa1044f7 100644 --- a/arch/arm/mm/copypage-v6.c +++ b/arch/arm/mm/copypage-v6.c @@ -41,14 +41,7 @@ static void v6_copy_user_highpage_nonaliasing(struct page *to, kfrom = kmap_atomic(from, KM_USER0); kto = kmap_atomic(to, KM_USER1); copy_page(kto, kfrom); -#ifdef CONFIG_HIGHMEM - /* - * kmap_atomic() doesn't set the page virtual address, and - * kunmap_atomic() takes care of cache flushing already. - */ - if (page_address(to) != NULL) -#endif - __cpuc_flush_dcache_area(kto, PAGE_SIZE); + __cpuc_flush_dcache_area(kto, PAGE_SIZE); kunmap_atomic(kto, KM_USER1); kunmap_atomic(kfrom, KM_USER0); } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 1351edc0b26..13fa536d82e 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -464,6 +464,11 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, vaddr += offset; op(vaddr, len, dir); kunmap_high(page); + } else if (cache_is_vipt()) { + pte_t saved_pte; + vaddr = kmap_high_l1_vipt(page, &saved_pte); + op(vaddr + offset, len, dir); + kunmap_high_l1_vipt(page, saved_pte); } } else { vaddr = page_address(page) + offset; diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index e34f095e209..c6844cb9b50 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -13,6 +13,7 @@ #include <asm/cacheflush.h> #include <asm/cachetype.h> +#include <asm/highmem.h> #include <asm/smp_plat.h> #include <asm/system.h> #include <asm/tlbflush.h> @@ -152,21 +153,25 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, void __flush_dcache_page(struct address_space *mapping, struct page *page) { - void *addr = page_address(page); - /* * Writeback any data associated with the kernel mapping of this * page. This ensures that data in the physical page is mutually * coherent with the kernels mapping. */ -#ifdef CONFIG_HIGHMEM - /* - * kmap_atomic() doesn't set the page virtual address, and - * kunmap_atomic() takes care of cache flushing already. - */ - if (addr) -#endif - __cpuc_flush_dcache_area(addr, PAGE_SIZE); + if (!PageHighMem(page)) { + __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE); + } else { + void *addr = kmap_high_get(page); + if (addr) { + __cpuc_flush_dcache_area(addr, PAGE_SIZE); + kunmap_high(page); + } else if (cache_is_vipt()) { + pte_t saved_pte; + addr = kmap_high_l1_vipt(page, &saved_pte); + __cpuc_flush_dcache_area(addr, PAGE_SIZE); + kunmap_high_l1_vipt(page, saved_pte); + } + } /* * If this is a page cache page, and we have an aliasing VIPT cache, diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 2be1ec7c1b4..77b030f5ec0 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -79,7 +79,8 @@ void kunmap_atomic(void *kvaddr, enum km_type type) unsigned int idx = type + KM_TYPE_NR * smp_processor_id(); if (kvaddr >= (void *)FIXADDR_START) { - __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); + if (cache_is_vivt()) + __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); set_pte_ext(TOP_PTE(vaddr), __pte(0), 0); @@ -124,3 +125,87 @@ struct page *kmap_atomic_to_page(const void *ptr) pte = TOP_PTE(vaddr); return pte_page(*pte); } + +#ifdef CONFIG_CPU_CACHE_VIPT + +#include <linux/percpu.h> + +/* + * The VIVT cache of a highmem page is always flushed before the page + * is unmapped. Hence unmapped highmem pages need no cache maintenance + * in that case. + * + * However unmapped pages may still be cached with a VIPT cache, and + * it is not possible to perform cache maintenance on them using physical + * addresses unfortunately. So we have no choice but to set up a temporary + * virtual mapping for that purpose. + * + * Yet this VIPT cache maintenance may be triggered from DMA support + * functions which are possibly called from interrupt context. As we don't + * want to keep interrupt disabled all the time when such maintenance is + * taking place, we therefore allow for some reentrancy by preserving and + * restoring the previous fixmap entry before the interrupted context is + * resumed. If the reentrancy depth is 0 then there is no need to restore + * the previous fixmap, and leaving the current one in place allow it to + * be reused the next time without a TLB flush (common with DMA). + */ + +static DEFINE_PER_CPU(int, kmap_high_l1_vipt_depth); + +void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte) +{ + unsigned int idx, cpu = smp_processor_id(); + int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu); + unsigned long vaddr, flags; + pte_t pte, *ptep; + + idx = KM_L1_CACHE + KM_TYPE_NR * cpu; + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + ptep = TOP_PTE(vaddr); + pte = mk_pte(page, kmap_prot); + + if (!in_interrupt()) + preempt_disable(); + + raw_local_irq_save(flags); + (*depth)++; + if (pte_val(*ptep) == pte_val(pte)) { + *saved_pte = pte; + } else { + *saved_pte = *ptep; + set_pte_ext(ptep, pte, 0); + local_flush_tlb_kernel_page(vaddr); + } + raw_local_irq_restore(flags); + + return (void *)vaddr; +} + +void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte) +{ + unsigned int idx, cpu = smp_processor_id(); + int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu); + unsigned long vaddr, flags; + pte_t pte, *ptep; + + idx = KM_L1_CACHE + KM_TYPE_NR * cpu; + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + ptep = TOP_PTE(vaddr); + pte = mk_pte(page, kmap_prot); + + BUG_ON(pte_val(*ptep) != pte_val(pte)); + BUG_ON(*depth <= 0); + + raw_local_irq_save(flags); + (*depth)--; + if (*depth != 0 && pte_val(pte) != pte_val(saved_pte)) { + set_pte_ext(ptep, saved_pte, 0); + local_flush_tlb_kernel_page(vaddr); + } + raw_local_irq_restore(flags); + + if (!in_interrupt()) + preempt_enable(); +} + +#endif /* CONFIG_CPU_CACHE_VIPT */ diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4223d086aa1..241c24a1c18 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1054,10 +1054,12 @@ void setup_mm_for_reboot(char mode) pgd_t *pgd; int i; - if (current->mm && current->mm->pgd) - pgd = current->mm->pgd; - else - pgd = init_mm.pgd; + /* + * We need to access to user-mode page tables here. For kernel threads + * we don't have any user-mode mappings so we use the context that we + * "borrowed". + */ + pgd = current->active_mm->pgd; base_pmdval = PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | PMD_TYPE_SECT; if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale()) diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index a420cb94932..315a540c7ce 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -428,26 +428,6 @@ static void vfp_pm_init(void) static inline void vfp_pm_init(void) { } #endif /* CONFIG_PM */ -/* - * Synchronise the hardware VFP state of a thread other than current with the - * saved one. This function is used by the ptrace mechanism. - */ -#ifdef CONFIG_SMP -void vfp_sync_hwstate(struct thread_info *thread) -{ -} - -void vfp_flush_hwstate(struct thread_info *thread) -{ - /* - * On SMP systems, the VFP state is automatically saved at every - * context switch. We mark the thread VFP state as belonging to a - * non-existent CPU so that the saved one will be reloaded when - * needed. - */ - thread->vfpstate.hard.cpu = NR_CPUS; -} -#else void vfp_sync_hwstate(struct thread_info *thread) { unsigned int cpu = get_cpu(); @@ -490,9 +470,18 @@ void vfp_flush_hwstate(struct thread_info *thread) last_VFP_context[cpu] = NULL; } +#ifdef CONFIG_SMP + /* + * For SMP we still have to take care of the case where the thread + * migrates to another CPU and then back to the original CPU on which + * the last VFP user is still the same thread. Mark the thread VFP + * state as belonging to a non-existent CPU so that the saved one will + * be reloaded in the above case. + */ + thread->vfpstate.hard.cpu = NR_CPUS; +#endif put_cpu(); } -#endif #include <linux/smp.h> diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 73c5c2b05f6..7f3c0a2e60c 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1802,7 +1802,8 @@ static int kvm_ia64_sync_dirty_log(struct kvm *kvm, { struct kvm_memory_slot *memslot; int r, i; - long n, base; + long base; + unsigned long n; unsigned long *dirty_bitmap = (unsigned long *)(kvm->arch.vm_base + offsetof(struct kvm_vm_data, kvm_mem_dirty_log)); @@ -1815,7 +1816,7 @@ static int kvm_ia64_sync_dirty_log(struct kvm *kvm, if (!memslot->dirty_bitmap) goto out; - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; + n = kvm_dirty_bitmap_bytes(memslot); base = memslot->base_gfn / BITS_PER_LONG; for (i = 0; i < n/sizeof(long); ++i) { @@ -1831,7 +1832,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { int r; - int n; + unsigned long n; struct kvm_memory_slot *memslot; int is_dirty = 0; @@ -1850,7 +1851,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (is_dirty) { kvm_flush_remote_tlbs(kvm); memslot = &kvm->memslots->memslots[log->slot]; - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; + n = kvm_dirty_bitmap_bytes(memslot); memset(memslot->dirty_bitmap, 0, n); } r = 0; diff --git a/arch/m68k/include/asm/mcfuart.h b/arch/m68k/include/asm/mcfuart.h index ef229387361..01a8716c5fc 100644 --- a/arch/m68k/include/asm/mcfuart.h +++ b/arch/m68k/include/asm/mcfuart.h @@ -212,5 +212,10 @@ struct mcf_platform_uart { #define MCFUART_URF_RXS 0xc0 /* Receiver status */ #endif +#if defined(CONFIG_M5272) +#define MCFUART_TXFIFOSIZE 25 +#else +#define MCFUART_TXFIFOSIZE 1 +#endif /****************************************************************************/ #endif /* mcfuart_h */ diff --git a/arch/m68knommu/Makefile b/arch/m68knommu/Makefile index ce404bc9ccb..14042574ac2 100644 --- a/arch/m68knommu/Makefile +++ b/arch/m68knommu/Makefile @@ -94,7 +94,7 @@ cflags-$(CONFIG_M520x) := $(call cc-option,-mcpu=5208,-m5200) cflags-$(CONFIG_M523x) := $(call cc-option,-mcpu=523x,-m5307) cflags-$(CONFIG_M5249) := $(call cc-option,-mcpu=5249,-m5200) cflags-$(CONFIG_M5271) := $(call cc-option,-mcpu=5271,-m5307) -cflags-$(CONFIG_M5272) := $(call cc-option,-mcpu=5271,-m5200) +cflags-$(CONFIG_M5272) := $(call cc-option,-mcpu=5272,-m5307) cflags-$(CONFIG_M5275) := $(call cc-option,-mcpu=5275,-m5307) cflags-$(CONFIG_M528x) := $(call cc-option,-m528x,-m5307) cflags-$(CONFIG_M5307) := $(call cc-option,-m5307,-m5200) diff --git a/arch/m68knommu/kernel/entry.S b/arch/m68knommu/kernel/entry.S index 56043ade394..aff6f57ef8b 100644 --- a/arch/m68knommu/kernel/entry.S +++ b/arch/m68knommu/kernel/entry.S @@ -145,6 +145,6 @@ ENTRY(ret_from_user_signal) trap #0 ENTRY(ret_from_user_rt_signal) - move #__NR_rt_sigreturn,%d0 + movel #__NR_rt_sigreturn,%d0 trap #0 diff --git a/arch/m68knommu/platform/68360/ints.c b/arch/m68knommu/platform/68360/ints.c index 1143f77caca..6f22970d8c2 100644 --- a/arch/m68knommu/platform/68360/ints.c +++ b/arch/m68knommu/platform/68360/ints.c @@ -107,7 +107,6 @@ void init_IRQ(void) _ramvec[vba+CPMVEC_PIO_PC7] = inthandler; /* pio - pc7 */ _ramvec[vba+CPMVEC_PIO_PC6] = inthandler; /* pio - pc6 */ _ramvec[vba+CPMVEC_TIMER3] = inthandler; /* timer 3 */ - _ramvec[vba+CPMVEC_RISCTIMER] = inthandler; /* reserved */ _ramvec[vba+CPMVEC_PIO_PC5] = inthandler; /* pio - pc5 */ _ramvec[vba+CPMVEC_PIO_PC4] = inthandler; /* pio - pc4 */ _ramvec[vba+CPMVEC_RESERVED2] = inthandler; /* reserved */ diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 25da07fd9f7..604af29b71e 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -1004,7 +1004,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_vcpu *vcpu; ulong ga, ga_end; int is_dirty = 0; - int r, n; + int r; + unsigned long n; mutex_lock(&kvm->slots_lock); @@ -1022,7 +1023,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, kvm_for_each_vcpu(n, vcpu, kvm) kvmppc_mmu_pte_pflush(vcpu, ga, ga_end); - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; + n = kvm_dirty_bitmap_bytes(memslot); memset(memslot->dirty_bitmap, 0, n); } diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h index 4a76d9480cc..533f35751ae 100644 --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -29,6 +29,7 @@ struct vdso_data { __u32 tz_minuteswest; /* Minutes west of Greenwich 0x30 */ __u32 tz_dsttime; /* Type of dst correction 0x34 */ __u32 ectg_available; + __u32 ntp_mult; /* NTP adjusted multiplier 0x3C */ }; struct vdso_per_cpu_data { diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 08db736dded..a09408952ed 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -61,6 +61,7 @@ int main(void) DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest)); DEFINE(__VDSO_ECTG_OK, offsetof(struct vdso_data, ectg_available)); + DEFINE(__VDSO_NTP_MULT, offsetof(struct vdso_data, ntp_mult)); DEFINE(__VDSO_ECTG_BASE, offsetof(struct vdso_per_cpu_data, ectg_timer_base)); DEFINE(__VDSO_ECTG_USER, offsetof(struct vdso_per_cpu_data, ectg_user_time)); /* constants used by the vdso */ diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index b354427e03b..c56d3f56d02 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -256,6 +256,9 @@ restore_registers: lghi %r2,0 brasl %r14,arch_set_page_states + /* Reinitialize the channel subsystem */ + brasl %r14,channel_subsystem_reinit + /* Return 0 */ lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) lghi %r2,0 diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index fba6dec156b..d906bf19c14 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -221,6 +221,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock, vdso_data->xtime_clock_nsec = wall_time->tv_nsec; vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec; vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec; + vdso_data->ntp_mult = mult; smp_wmb(); ++vdso_data->tb_update_count; } diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S index 4a98909a831..96964395427 100644 --- a/arch/s390/kernel/vdso32/clock_gettime.S +++ b/arch/s390/kernel/vdso32/clock_gettime.S @@ -38,13 +38,13 @@ __kernel_clock_gettime: sl %r1,__VDSO_XTIME_STAMP+4(%r5) brc 3,2f ahi %r0,-1 -2: mhi %r0,1000 /* cyc2ns(clock,cycle_delta) */ +2: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ lr %r2,%r0 - lhi %r0,1000 + l %r0,__VDSO_NTP_MULT(%r5) ltr %r1,%r1 mr %r0,%r0 jnm 3f - ahi %r0,1000 + a %r0,__VDSO_NTP_MULT(%r5) 3: alr %r0,%r2 srdl %r0,12 al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ @@ -86,13 +86,13 @@ __kernel_clock_gettime: sl %r1,__VDSO_XTIME_STAMP+4(%r5) brc 3,12f ahi %r0,-1 -12: mhi %r0,1000 /* cyc2ns(clock,cycle_delta) */ +12: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ lr %r2,%r0 - lhi %r0,1000 + l %r0,__VDSO_NTP_MULT(%r5) ltr %r1,%r1 mr %r0,%r0 jnm 13f - ahi %r0,1000 + a %r0,__VDSO_NTP_MULT(%r5) 13: alr %r0,%r2 srdl %r0,12 al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S index ad8acfc949f..2d3633175e3 100644 --- a/arch/s390/kernel/vdso32/gettimeofday.S +++ b/arch/s390/kernel/vdso32/gettimeofday.S @@ -35,13 +35,13 @@ __kernel_gettimeofday: sl %r1,__VDSO_XTIME_STAMP+4(%r5) brc 3,3f ahi %r0,-1 -3: mhi %r0,1000 /* cyc2ns(clock,cycle_delta) */ +3: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ st %r0,24(%r15) - lhi %r0,1000 + l %r0,__VDSO_NTP_MULT(%r5) ltr %r1,%r1 mr %r0,%r0 jnm 4f - ahi %r0,1000 + a %r0,__VDSO_NTP_MULT(%r5) 4: al %r0,24(%r15) srdl %r0,12 al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S index 49106c6e6f8..f40467884a0 100644 --- a/arch/s390/kernel/vdso64/clock_gettime.S +++ b/arch/s390/kernel/vdso64/clock_gettime.S @@ -36,7 +36,7 @@ __kernel_clock_gettime: stck 48(%r15) /* Store TOD clock */ lg %r1,48(%r15) sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - mghi %r1,1000 + msgf %r1,__VDSO_NTP_MULT(%r5) /* * NTP adjustment */ srlg %r1,%r1,12 /* cyc2ns(clock,cycle_delta) */ alg %r1,__VDSO_XTIME_NSEC(%r5) /* + xtime */ lg %r0,__VDSO_XTIME_SEC(%r5) @@ -64,7 +64,7 @@ __kernel_clock_gettime: stck 48(%r15) /* Store TOD clock */ lg %r1,48(%r15) sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - mghi %r1,1000 + msgf %r1,__VDSO_NTP_MULT(%r5) /* * NTP adjustment */ srlg %r1,%r1,12 /* cyc2ns(clock,cycle_delta) */ alg %r1,__VDSO_XTIME_NSEC(%r5) /* + xtime */ lg %r0,__VDSO_XTIME_SEC(%r5) diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S index f873e75634e..36ee674722e 100644 --- a/arch/s390/kernel/vdso64/gettimeofday.S +++ b/arch/s390/kernel/vdso64/gettimeofday.S @@ -31,7 +31,7 @@ __kernel_gettimeofday: stck 48(%r15) /* Store TOD clock */ lg %r1,48(%r15) sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - mghi %r1,1000 + msgf %r1,__VDSO_NTP_MULT(%r5) /* * NTP adjustment */ srlg %r1,%r1,12 /* cyc2ns(clock,cycle_delta) */ alg %r1,__VDSO_XTIME_NSEC(%r5) /* + xtime.tv_nsec */ lg %r0,__VDSO_XTIME_SEC(%r5) /* xtime.tv_sec */ diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h index 9e2d9447f2a..4827a3aeac7 100644 --- a/arch/sparc/include/asm/thread_info_64.h +++ b/arch/sparc/include/asm/thread_info_64.h @@ -111,7 +111,7 @@ struct thread_info { #define THREAD_SHIFT PAGE_SHIFT #endif /* PAGE_SHIFT == 13 */ -#define PREEMPT_ACTIVE 0x4000000 +#define PREEMPT_ACTIVE 0x10000000 /* * macros/functions for gaining access to the thread information structure diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 454ce3a2527..830d70a3e20 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -22,6 +22,7 @@ #include <linux/seq_file.h> #include <linux/ftrace.h> #include <linux/irq.h> +#include <linux/kmemleak.h> #include <asm/ptrace.h> #include <asm/processor.h> @@ -46,6 +47,7 @@ #include "entry.h" #include "cpumap.h" +#include "kstack.h" #define NUM_IVECS (IMAP_INR + 1) @@ -712,24 +714,6 @@ void ack_bad_irq(unsigned int virt_irq) void *hardirq_stack[NR_CPUS]; void *softirq_stack[NR_CPUS]; -static __attribute__((always_inline)) void *set_hardirq_stack(void) -{ - void *orig_sp, *sp = hardirq_stack[smp_processor_id()]; - - __asm__ __volatile__("mov %%sp, %0" : "=r" (orig_sp)); - if (orig_sp < sp || - orig_sp > (sp + THREAD_SIZE)) { - sp += THREAD_SIZE - 192 - STACK_BIAS; - __asm__ __volatile__("mov %0, %%sp" : : "r" (sp)); - } - - return orig_sp; -} -static __attribute__((always_inline)) void restore_hardirq_stack(void *orig_sp) -{ - __asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp)); -} - void __irq_entry handler_irq(int irq, struct pt_regs *regs) { unsigned long pstate, bucket_pa; diff --git a/arch/sparc/kernel/kstack.h b/arch/sparc/kernel/kstack.h index 5247283d1c0..53dfb92e09f 100644 --- a/arch/sparc/kernel/kstack.h +++ b/arch/sparc/kernel/kstack.h @@ -61,4 +61,23 @@ check_magic: } +static inline __attribute__((always_inline)) void *set_hardirq_stack(void) +{ + void *orig_sp, *sp = hardirq_stack[smp_processor_id()]; + + __asm__ __volatile__("mov %%sp, %0" : "=r" (orig_sp)); + if (orig_sp < sp || + orig_sp > (sp + THREAD_SIZE)) { + sp += THREAD_SIZE - 192 - STACK_BIAS; + __asm__ __volatile__("mov %0, %%sp" : : "r" (sp)); + } + + return orig_sp; +} + +static inline __attribute__((always_inline)) void restore_hardirq_stack(void *orig_sp) +{ + __asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp)); +} + #endif /* _KSTACK_H */ diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 75a3d1a2535..a4bd7ba74c8 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -23,6 +23,8 @@ #include <asm/ptrace.h> #include <asm/pcr.h> +#include "kstack.h" + /* We don't have a real NMI on sparc64, but we can fake one * up using profiling counter overflow interrupts and interrupt * levels. @@ -92,6 +94,7 @@ static void die_nmi(const char *str, struct pt_regs *regs, int do_panic) notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs) { unsigned int sum, touched = 0; + void *orig_sp; clear_softint(1 << irq); @@ -99,6 +102,8 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs) nmi_enter(); + orig_sp = set_hardirq_stack(); + if (notify_die(DIE_NMI, "nmi", regs, 0, pt_regs_trap_type(regs), SIGINT) == NOTIFY_STOP) touched = 1; @@ -124,6 +129,8 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs) pcr_ops->write(pcr_enable); } + restore_hardirq_stack(orig_sp); + nmi_exit(); } diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index 83f1873c6c1..090b9e9ad5e 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -130,7 +130,17 @@ rtrap_xcall: nop call trace_hardirqs_on nop - wrpr %l4, %pil + /* Do not actually set the %pil here. We will do that + * below after we clear PSTATE_IE in the %pstate register. + * If we re-enable interrupts here, we can recurse down + * the hardirq stack potentially endlessly, causing a + * stack overflow. + * + * It is tempting to put this test and trace_hardirqs_on + * call at the 'rt_continue' label, but that will not work + * as that path hits unconditionally and we do not want to + * execute this in NMI return paths, for example. + */ #endif rtrap_no_irq_enable: andcc %l1, TSTATE_PRIV, %l3 diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c index ebce43018c4..c752c4c479b 100644 --- a/arch/sparc/kernel/unaligned_64.c +++ b/arch/sparc/kernel/unaligned_64.c @@ -50,7 +50,7 @@ static inline enum direction decode_direction(unsigned int insn) } /* 16 = double-word, 8 = extra-word, 4 = word, 2 = half-word */ -static inline int decode_access_size(unsigned int insn) +static inline int decode_access_size(struct pt_regs *regs, unsigned int insn) { unsigned int tmp; @@ -66,7 +66,7 @@ static inline int decode_access_size(unsigned int insn) return 2; else { printk("Impossible unaligned trap. insn=%08x\n", insn); - die_if_kernel("Byte sized unaligned access?!?!", current_thread_info()->kregs); + die_if_kernel("Byte sized unaligned access?!?!", regs); /* GCC should never warn that control reaches the end * of this function without returning a value because @@ -286,7 +286,7 @@ static void log_unaligned(struct pt_regs *regs) asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn) { enum direction dir = decode_direction(insn); - int size = decode_access_size(insn); + int size = decode_access_size(regs, insn); int orig_asi, asi; current_thread_info()->kern_una_regs = regs; diff --git a/arch/sparc/lib/mcount.S b/arch/sparc/lib/mcount.S index 3753e3c6e17..3ad6cbdc216 100644 --- a/arch/sparc/lib/mcount.S +++ b/arch/sparc/lib/mcount.S @@ -34,7 +34,7 @@ mcount: cmp %g1, %g2 be,pn %icc, 1f mov %i7, %g3 - save %sp, -128, %sp + save %sp, -176, %sp mov %g3, %o1 jmpl %g1, %o7 mov %i7, %o0 @@ -56,7 +56,7 @@ mcount: nop 5: mov %i7, %g2 mov %fp, %g3 - save %sp, -128, %sp + save %sp, -176, %sp mov %g2, %l0 ba,pt %xcc, ftrace_graph_caller mov %g3, %l1 @@ -85,7 +85,7 @@ ftrace_caller: lduw [%g1 + %lo(function_trace_stop)], %g1 brnz,pn %g1, ftrace_stub mov %fp, %g3 - save %sp, -128, %sp + save %sp, -176, %sp mov %g2, %o1 mov %g2, %l0 mov %g3, %l1 @@ -120,7 +120,7 @@ ENTRY(ftrace_graph_caller) END(ftrace_graph_caller) ENTRY(return_to_handler) - save %sp, -128, %sp + save %sp, -176, %sp call ftrace_return_to_handler mov %fp, %o0 jmpl %o0 + 8, %g0 diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 59b4556a5b9..e790bc1fbfa 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -626,7 +626,7 @@ ia32_sys_call_table: .quad stub32_sigreturn .quad stub32_clone /* 120 */ .quad sys_setdomainname - .quad sys_uname + .quad sys_newuname .quad sys_modify_ldt .quad compat_sys_adjtimex .quad sys32_mprotect /* 125 */ diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h index e39e77168a3..e1a93be4fd4 100644 --- a/arch/x86/kernel/dumpstack.h +++ b/arch/x86/kernel/dumpstack.h @@ -14,6 +14,8 @@ #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) #endif +#include <linux/uaccess.h> + extern void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, char *log_lvl); @@ -42,8 +44,10 @@ static inline unsigned long rewind_frame_pointer(int n) get_bp(frame); #ifdef CONFIG_FRAME_POINTER - while (n--) - frame = frame->next_frame; + while (n--) { + if (probe_kernel_address(&frame->next_frame, frame)) + break; + } #endif return (unsigned long)frame; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 48aeee8eefb..19a8906bcaa 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1490,8 +1490,8 @@ static int mmu_zap_unsync_children(struct kvm *kvm, for_each_sp(pages, sp, parents, i) { kvm_mmu_zap_page(kvm, sp); mmu_pages_clear_parents(&parents); + zapped++; } - zapped += pages.nr; kvm_mmu_pages_init(parent, &parents, &pages); } @@ -1542,14 +1542,16 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages) */ if (used_pages > kvm_nr_mmu_pages) { - while (used_pages > kvm_nr_mmu_pages) { + while (used_pages > kvm_nr_mmu_pages && + !list_empty(&kvm->arch.active_mmu_pages)) { struct kvm_mmu_page *page; page = container_of(kvm->arch.active_mmu_pages.prev, struct kvm_mmu_page, link); - kvm_mmu_zap_page(kvm, page); + used_pages -= kvm_mmu_zap_page(kvm, page); used_pages--; } + kvm_nr_mmu_pages = used_pages; kvm->arch.n_free_mmu_pages = 0; } else @@ -1596,7 +1598,8 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) && !sp->role.invalid) { pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word); - kvm_mmu_zap_page(kvm, sp); + if (kvm_mmu_zap_page(kvm, sp)) + nn = bucket->first; } } } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 445c59411ed..2ba58206812 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -706,29 +706,28 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) if (err) goto free_svm; + err = -ENOMEM; page = alloc_page(GFP_KERNEL); - if (!page) { - err = -ENOMEM; + if (!page) goto uninit; - } - err = -ENOMEM; msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); if (!msrpm_pages) - goto uninit; + goto free_page1; nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); if (!nested_msrpm_pages) - goto uninit; - - svm->msrpm = page_address(msrpm_pages); - svm_vcpu_init_msrpm(svm->msrpm); + goto free_page2; hsave_page = alloc_page(GFP_KERNEL); if (!hsave_page) - goto uninit; + goto free_page3; + svm->nested.hsave = page_address(hsave_page); + svm->msrpm = page_address(msrpm_pages); + svm_vcpu_init_msrpm(svm->msrpm); + svm->nested.msrpm = page_address(nested_msrpm_pages); svm->vmcb = page_address(page); @@ -744,6 +743,12 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) return &svm->vcpu; +free_page3: + __free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER); +free_page2: + __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER); +free_page1: + __free_page(page); uninit: kvm_vcpu_uninit(&svm->vcpu); free_svm: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 686492ed307..bc933cfb4e6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -77,6 +77,8 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) #define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE) +#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM)) + /* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * ple_gap: upper bound on the amount of time between two successive @@ -131,7 +133,7 @@ struct vcpu_vmx { } host_state; struct { int vm86_active; - u8 save_iopl; + ulong save_rflags; struct kvm_save_segment { u16 selector; unsigned long base; @@ -818,18 +820,23 @@ static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu) static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { - unsigned long rflags; + unsigned long rflags, save_rflags; rflags = vmcs_readl(GUEST_RFLAGS); - if (to_vmx(vcpu)->rmode.vm86_active) - rflags &= ~(unsigned long)(X86_EFLAGS_IOPL | X86_EFLAGS_VM); + if (to_vmx(vcpu)->rmode.vm86_active) { + rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; + save_rflags = to_vmx(vcpu)->rmode.save_rflags; + rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; + } return rflags; } static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { - if (to_vmx(vcpu)->rmode.vm86_active) + if (to_vmx(vcpu)->rmode.vm86_active) { + to_vmx(vcpu)->rmode.save_rflags = rflags; rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; + } vmcs_writel(GUEST_RFLAGS, rflags); } @@ -1483,8 +1490,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar); flags = vmcs_readl(GUEST_RFLAGS); - flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM); - flags |= (vmx->rmode.save_iopl << IOPL_SHIFT); + flags &= RMODE_GUEST_OWNED_EFLAGS_BITS; + flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | @@ -1557,8 +1564,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); flags = vmcs_readl(GUEST_RFLAGS); - vmx->rmode.save_iopl - = (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + vmx->rmode.save_rflags = flags; flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 24cd0ee896e..3c4ca98ad27 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -433,8 +433,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) #ifdef CONFIG_X86_64 if (cr0 & 0xffffffff00000000UL) { - printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n", - cr0, kvm_read_cr0(vcpu)); kvm_inject_gp(vcpu, 0); return; } @@ -443,14 +441,11 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) cr0 &= ~CR0_RESERVED_BITS; if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) { - printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n"); kvm_inject_gp(vcpu, 0); return; } if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) { - printk(KERN_DEBUG "set_cr0: #GP, set PG flag " - "and a clear PE flag\n"); kvm_inject_gp(vcpu, 0); return; } @@ -461,15 +456,11 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) int cs_db, cs_l; if (!is_pae(vcpu)) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while PAE is disabled\n"); kvm_inject_gp(vcpu, 0); return; } kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); if (cs_l) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while CS.L == 1\n"); kvm_inject_gp(vcpu, 0); return; @@ -477,8 +468,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } else #endif if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { - printk(KERN_DEBUG "set_cr0: #GP, pdptrs " - "reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } @@ -505,28 +494,23 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE; if (cr4 & CR4_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) { - printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while " - "in long mode\n"); kvm_inject_gp(vcpu, 0); return; } } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { - printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } if (cr4 & X86_CR4_VMXE) { - printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n"); kvm_inject_gp(vcpu, 0); return; } @@ -547,21 +531,16 @@ void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (is_long_mode(vcpu)) { if (cr3 & CR3_L_MODE_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } } else { if (is_pae(vcpu)) { if (cr3 & CR3_PAE_RESERVED_BITS) { - printk(KERN_DEBUG - "set_cr3: #GP, reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) { - printk(KERN_DEBUG "set_cr3: #GP, pdptrs " - "reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } @@ -593,7 +572,6 @@ EXPORT_SYMBOL_GPL(kvm_set_cr3); void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) { if (cr8 & CR8_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8); kvm_inject_gp(vcpu, 0); return; } @@ -649,15 +627,12 @@ static u32 emulated_msrs[] = { static void set_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) { - printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n", - efer); kvm_inject_gp(vcpu, 0); return; } if (is_paging(vcpu) && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) { - printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n"); kvm_inject_gp(vcpu, 0); return; } @@ -667,7 +642,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer) feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) { - printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n"); kvm_inject_gp(vcpu, 0); return; } @@ -678,7 +652,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer) feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) { - printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n"); kvm_inject_gp(vcpu, 0); return; } @@ -967,9 +940,13 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MC0_CTL + 4 * bank_num) { u32 offset = msr - MSR_IA32_MC0_CTL; - /* only 0 or all 1s can be written to IA32_MCi_CTL */ + /* only 0 or all 1s can be written to IA32_MCi_CTL + * some Linux kernels though clear bit 10 in bank 4 to + * workaround a BIOS/GART TBL issue on AMD K8s, ignore + * this to avoid an uncatched #GP in the guest + */ if ((offset & 0x3) == 0 && - data != 0 && data != ~(u64)0) + data != 0 && (data | (1 << 10)) != ~(u64)0) return -1; vcpu->arch.mce_banks[offset] = data; break; @@ -2635,8 +2612,9 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { - int r, n, i; + int r, i; struct kvm_memory_slot *memslot; + unsigned long n; unsigned long is_dirty = 0; unsigned long *dirty_bitmap = NULL; @@ -2651,7 +2629,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (!memslot->dirty_bitmap) goto out; - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; + n = kvm_dirty_bitmap_bytes(memslot); r = -ENOMEM; dirty_bitmap = vmalloc(n); @@ -4483,7 +4461,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_set_cr8(vcpu, kvm_run->cr8); if (vcpu->arch.pio.cur_count) { + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = complete_pio(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (r) goto out; } @@ -5146,6 +5126,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) int ret = 0; u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR); u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR); + u32 desc_limit; old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL); @@ -5168,7 +5149,10 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) } } - if (!nseg_desc.p || get_desc_limit(&nseg_desc) < 0x67) { + desc_limit = get_desc_limit(&nseg_desc); + if (!nseg_desc.p || + ((desc_limit < 0x67 && (nseg_desc.type & 8)) || + desc_limit < 0x2b)) { kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc); return 1; } |