diff options
Diffstat (limited to 'arch')
66 files changed, 721 insertions, 376 deletions
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h index 7f36d00600b4..feb988a7ec37 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 c019949a5189..c4b2ea3fbe42 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 bf65e9f4525d..47f023aa8495 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 df95e050f9dd..05ac4b06876a 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 e7714f367eb8..907d5a620bca 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 027dd570dcc3..d4004557532a 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 9fcbd6ca0090..9c5b48e68a71 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 8bca4dea6dfa..f55fa1044f72 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 1351edc0b26f..13fa536d82e6 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 e34f095e2090..c6844cb9b508 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 2be1ec7c1b41..77b030f5ec09 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 4223d086aa17..241c24a1c18f 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 a420cb949328..315a540c7ce5 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 73c5c2b05f64..7f3c0a2e60cd 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/atomic_mm.h b/arch/m68k/include/asm/atomic_mm.h index 88b7af20a996..d9d2ed647435 100644 --- a/arch/m68k/include/asm/atomic_mm.h +++ b/arch/m68k/include/asm/atomic_mm.h @@ -148,14 +148,18 @@ static inline int atomic_xchg(atomic_t *v, int new) static inline int atomic_sub_and_test(int i, atomic_t *v) { char c; - __asm__ __volatile__("subl %2,%1; seq %0" : "=d" (c), "+m" (*v): "g" (i)); + __asm__ __volatile__("subl %2,%1; seq %0" + : "=d" (c), "+m" (*v) + : "id" (i)); return c != 0; } static inline int atomic_add_negative(int i, atomic_t *v) { char c; - __asm__ __volatile__("addl %2,%1; smi %0" : "=d" (c), "+m" (*v): "g" (i)); + __asm__ __volatile__("addl %2,%1; smi %0" + : "=d" (c), "+m" (*v) + : "id" (i)); return c != 0; } diff --git a/arch/m68k/include/asm/mcfuart.h b/arch/m68k/include/asm/mcfuart.h index ef2293873612..01a8716c5fc5 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/m68k/include/asm/sigcontext.h b/arch/m68k/include/asm/sigcontext.h index 1320eaa4cc2a..a29dd74a17cb 100644 --- a/arch/m68k/include/asm/sigcontext.h +++ b/arch/m68k/include/asm/sigcontext.h @@ -17,13 +17,11 @@ struct sigcontext { #ifndef __uClinux__ # ifdef __mcoldfire__ unsigned long sc_fpregs[2][2]; /* room for two fp registers */ - unsigned long sc_fpcntl[3]; - unsigned char sc_fpstate[16+6*8]; # else unsigned long sc_fpregs[2*3]; /* room for two fp registers */ +# endif unsigned long sc_fpcntl[3]; unsigned char sc_fpstate[216]; -# endif #endif }; diff --git a/arch/m68knommu/Makefile b/arch/m68knommu/Makefile index ce404bc9ccbd..14042574ac21 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 56043ade3941..aff6f57ef8b5 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 1143f77caca4..6f22970d8c20 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 25da07fd9f77..604af29b71ed 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 4a76d9480cce..533f35751aeb 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 08db736dded0..a09408952ed0 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 b354427e03b7..c56d3f56d020 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 fba6dec156bf..d906bf19c14a 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 4a98909a8310..969643954273 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 ad8acfc949fb..2d3633175e3b 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 49106c6e6f88..f40467884a03 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 f873e75634e1..36ee674722ec 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/Kconfig b/arch/sparc/Kconfig index 6db513674050..9908d477ccd9 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -37,6 +37,9 @@ config SPARC64 def_bool 64BIT select ARCH_SUPPORTS_MSI select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FP_TEST + select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_KRETPROBES select HAVE_KPROBES select HAVE_LMB diff --git a/arch/sparc/Kconfig.debug b/arch/sparc/Kconfig.debug index 9d3c889718ac..1b4a831565f9 100644 --- a/arch/sparc/Kconfig.debug +++ b/arch/sparc/Kconfig.debug @@ -19,13 +19,10 @@ config DEBUG_DCFLUSH bool "D-cache flush debugging" depends on SPARC64 && DEBUG_KERNEL -config STACK_DEBUG - bool "Stack Overflow Detection Support" - config MCOUNT bool depends on SPARC64 - depends on STACK_DEBUG || FUNCTION_TRACER + depends on FUNCTION_TRACER default y config FRAME_POINTER diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h index 926397d345ff..050ef35b9dcf 100644 --- a/arch/sparc/include/asm/cpudata_64.h +++ b/arch/sparc/include/asm/cpudata_64.h @@ -17,7 +17,7 @@ typedef struct { unsigned int __nmi_count; unsigned long clock_tick; /* %tick's per second */ unsigned long __pad; - unsigned int __pad1; + unsigned int irq0_irqs; unsigned int __pad2; /* Dcache line 2, rarely used */ diff --git a/arch/sparc/include/asm/irqflags_64.h b/arch/sparc/include/asm/irqflags_64.h index 8b49bf920df3..bfa1ea45b4cd 100644 --- a/arch/sparc/include/asm/irqflags_64.h +++ b/arch/sparc/include/asm/irqflags_64.h @@ -76,9 +76,26 @@ static inline int raw_irqs_disabled(void) */ static inline unsigned long __raw_local_irq_save(void) { - unsigned long flags = __raw_local_save_flags(); - - raw_local_irq_disable(); + unsigned long flags, tmp; + + /* Disable interrupts to PIL_NORMAL_MAX unless we already + * are using PIL_NMI, in which case PIL_NMI is retained. + * + * The only values we ever program into the %pil are 0, + * PIL_NORMAL_MAX and PIL_NMI. + * + * Since PIL_NMI is the largest %pil value and all bits are + * set in it (0xf), it doesn't matter what PIL_NORMAL_MAX + * actually is. + */ + __asm__ __volatile__( + "rdpr %%pil, %0\n\t" + "or %0, %2, %1\n\t" + "wrpr %1, 0x0, %%pil" + : "=r" (flags), "=r" (tmp) + : "i" (PIL_NORMAL_MAX) + : "memory" + ); return flags; } diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h index 9e2d9447f2ad..4827a3aeac7f 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/Makefile b/arch/sparc/kernel/Makefile index c6316142db4e..0c2dc1f24a9a 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -13,6 +13,14 @@ extra-y += init_task.o CPPFLAGS_vmlinux.lds := -Usparc -m$(BITS) extra-y += vmlinux.lds +ifdef CONFIG_FUNCTION_TRACER +# Do not profile debug and lowlevel utilities +CFLAGS_REMOVE_ftrace.o := -pg +CFLAGS_REMOVE_time_$(BITS).o := -pg +CFLAGS_REMOVE_perf_event.o := -pg +CFLAGS_REMOVE_pcr.o := -pg +endif + obj-$(CONFIG_SPARC32) += entry.o wof.o wuf.o obj-$(CONFIG_SPARC32) += etrap_32.o obj-$(CONFIG_SPARC32) += rtrap_32.o @@ -85,7 +93,7 @@ obj-$(CONFIG_KGDB) += kgdb_$(BITS).o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -CFLAGS_REMOVE_ftrace.o := -pg +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_EARLYFB) += btext.o obj-$(CONFIG_STACKTRACE) += stacktrace.o diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c index 9103a56b39e8..03ab022e51c5 100644 --- a/arch/sparc/kernel/ftrace.c +++ b/arch/sparc/kernel/ftrace.c @@ -13,7 +13,7 @@ static const u32 ftrace_nop = 0x01000000; static u32 ftrace_call_replace(unsigned long ip, unsigned long addr) { - static u32 call; + u32 call; s32 off; off = ((s32)addr - (s32)ip); @@ -91,3 +91,61 @@ int __init ftrace_dyn_arch_init(void *data) return 0; } #endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +#ifdef CONFIG_DYNAMIC_FTRACE +extern void ftrace_graph_call(void); + +int ftrace_enable_ftrace_graph_caller(void) +{ + unsigned long ip = (unsigned long)(&ftrace_graph_call); + u32 old, new; + + old = *(u32 *) &ftrace_graph_call; + new = ftrace_call_replace(ip, (unsigned long) &ftrace_graph_caller); + return ftrace_modify_code(ip, old, new); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + unsigned long ip = (unsigned long)(&ftrace_graph_call); + u32 old, new; + + old = *(u32 *) &ftrace_graph_call; + new = ftrace_call_replace(ip, (unsigned long) &ftrace_stub); + + return ftrace_modify_code(ip, old, new); +} + +#endif /* !CONFIG_DYNAMIC_FTRACE */ + +/* + * Hook the return address and push it in the stack of return addrs + * in current thread info. + */ +unsigned long prepare_ftrace_return(unsigned long parent, + unsigned long self_addr, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long) &return_to_handler; + struct ftrace_graph_ent trace; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return parent + 8UL; + + if (ftrace_push_return_trace(parent, self_addr, &trace.depth, + frame_pointer) == -EBUSY) + return parent + 8UL; + + trace.func = self_addr; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) { + current->curr_ret_stack--; + return parent + 8UL; + } + + return return_hooker; +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index e1cbdb94d97b..830d70a3e20b 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -20,7 +20,9 @@ #include <linux/delay.h> #include <linux/proc_fs.h> #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> @@ -45,6 +47,7 @@ #include "entry.h" #include "cpumap.h" +#include "kstack.h" #define NUM_IVECS (IMAP_INR + 1) @@ -647,6 +650,14 @@ unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino) bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC); if (unlikely(!bucket)) return 0; + + /* The only reference we store to the IRQ bucket is + * by physical address which kmemleak can't see, tell + * it that this object explicitly is not a leak and + * should be scanned. + */ + kmemleak_not_leak(bucket); + __flush_dcache_range((unsigned long) bucket, ((unsigned long) bucket + sizeof(struct ino_bucket))); @@ -703,25 +714,7 @@ 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 handler_irq(int irq, struct pt_regs *regs) +void __irq_entry handler_irq(int irq, struct pt_regs *regs) { unsigned long pstate, bucket_pa; struct pt_regs *old_regs; diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c index f5a0fd490b59..0a2bd0f99fc1 100644 --- a/arch/sparc/kernel/kgdb_64.c +++ b/arch/sparc/kernel/kgdb_64.c @@ -5,6 +5,7 @@ #include <linux/kgdb.h> #include <linux/kdebug.h> +#include <linux/ftrace.h> #include <asm/kdebug.h> #include <asm/ptrace.h> @@ -108,7 +109,7 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) } #ifdef CONFIG_SMP -void smp_kgdb_capture_client(int irq, struct pt_regs *regs) +void __irq_entry smp_kgdb_capture_client(int irq, struct pt_regs *regs) { unsigned long flags; diff --git a/arch/sparc/kernel/kstack.h b/arch/sparc/kernel/kstack.h index 5247283d1c03..53dfb92e09fb 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 b287b62c7ea3..a4bd7ba74c89 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. @@ -92,7 +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; - int cpu = smp_processor_id(); + void *orig_sp; clear_softint(1 << irq); @@ -100,13 +102,15 @@ 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; else pcr_ops->write(PCR_PIC_PRIV); - sum = kstat_irqs_cpu(0, cpu); + sum = local_cpu_data().irq0_irqs; if (__get_cpu_var(nmi_touch)) { __get_cpu_var(nmi_touch) = 0; touched = 1; @@ -125,6 +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/pci_common.c b/arch/sparc/kernel/pci_common.c index b775658a927d..8a000583b5cf 100644 --- a/arch/sparc/kernel/pci_common.c +++ b/arch/sparc/kernel/pci_common.c @@ -371,14 +371,19 @@ static void pci_register_iommu_region(struct pci_pbm_info *pbm) struct resource *rp = kzalloc(sizeof(*rp), GFP_KERNEL); if (!rp) { - prom_printf("Cannot allocate IOMMU resource.\n"); - prom_halt(); + pr_info("%s: Cannot allocate IOMMU resource.\n", + pbm->name); + return; } rp->name = "IOMMU"; rp->start = pbm->mem_space.start + (unsigned long) vdma[0]; rp->end = rp->start + (unsigned long) vdma[1] - 1UL; rp->flags = IORESOURCE_BUSY; - request_resource(&pbm->mem_space, rp); + if (request_resource(&pbm->mem_space, rp)) { + pr_info("%s: Unable to request IOMMU resource.\n", + pbm->name); + kfree(rp); + } } } diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index 2d94e7a03af5..c4a6a50b4849 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -8,6 +8,7 @@ #include <linux/irq.h> #include <linux/perf_event.h> +#include <linux/ftrace.h> #include <asm/pil.h> #include <asm/pcr.h> @@ -34,7 +35,7 @@ unsigned int picl_shift; * Therefore in such situations we defer the work by signalling * a lower level cpu IRQ. */ -void deferred_pcr_work_irq(int irq, struct pt_regs *regs) +void __irq_entry deferred_pcr_work_irq(int irq, struct pt_regs *regs) { struct pt_regs *old_regs; diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index 83f1873c6c13..090b9e9ad5e3 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/smp_64.c b/arch/sparc/kernel/smp_64.c index 4c5334528109..b6a2b8f47040 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -22,6 +22,7 @@ #include <linux/profile.h> #include <linux/bootmem.h> #include <linux/vmalloc.h> +#include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/slab.h> @@ -823,13 +824,13 @@ void arch_send_call_function_single_ipi(int cpu) &cpumask_of_cpu(cpu)); } -void smp_call_function_client(int irq, struct pt_regs *regs) +void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); generic_smp_call_function_interrupt(); } -void smp_call_function_single_client(int irq, struct pt_regs *regs) +void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); generic_smp_call_function_single_interrupt(); @@ -965,7 +966,7 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page) put_cpu(); } -void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) +void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) { struct mm_struct *mm; unsigned long flags; @@ -1149,7 +1150,7 @@ void smp_release(void) */ extern void prom_world(int); -void smp_penguin_jailcell(int irq, struct pt_regs *regs) +void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs) { clear_softint(1 << irq); @@ -1365,7 +1366,7 @@ void smp_send_reschedule(int cpu) &cpumask_of_cpu(cpu)); } -void smp_receive_signal_client(int irq, struct pt_regs *regs) +void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); } diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 67e165102885..c7bbe6cf7b85 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -35,6 +35,7 @@ #include <linux/clocksource.h> #include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/ftrace.h> #include <asm/oplib.h> #include <asm/timer.h> @@ -717,7 +718,7 @@ static struct clock_event_device sparc64_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, sparc64_events); -void timer_interrupt(int irq, struct pt_regs *regs) +void __irq_entry timer_interrupt(int irq, struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); unsigned long tick_mask = tick_ops->softint_mask; @@ -728,6 +729,7 @@ void timer_interrupt(int irq, struct pt_regs *regs) irq_enter(); + local_cpu_data().irq0_irqs++; kstat_incr_irqs_this_cpu(0, irq_to_desc(0)); if (unlikely(!evt->event_handler)) { diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 837dfc2390d6..9da57f032983 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2203,27 +2203,6 @@ void dump_stack(void) EXPORT_SYMBOL(dump_stack); -static inline int is_kernel_stack(struct task_struct *task, - struct reg_window *rw) -{ - unsigned long rw_addr = (unsigned long) rw; - unsigned long thread_base, thread_end; - - if (rw_addr < PAGE_OFFSET) { - if (task != &init_task) - return 0; - } - - thread_base = (unsigned long) task_stack_page(task); - thread_end = thread_base + sizeof(union thread_union); - if (rw_addr >= thread_base && - rw_addr < thread_end && - !(rw_addr & 0x7UL)) - return 1; - - return 0; -} - static inline struct reg_window *kernel_stack_up(struct reg_window *rw) { unsigned long fp = rw->ins[6]; @@ -2252,6 +2231,7 @@ void die_if_kernel(char *str, struct pt_regs *regs) show_regs(regs); add_taint(TAINT_DIE); if (regs->tstate & TSTATE_PRIV) { + struct thread_info *tp = current_thread_info(); struct reg_window *rw = (struct reg_window *) (regs->u_regs[UREG_FP] + STACK_BIAS); @@ -2259,8 +2239,8 @@ void die_if_kernel(char *str, struct pt_regs *regs) * find some badly aligned kernel stack. */ while (rw && - count++ < 30&& - is_kernel_stack(current, rw)) { + count++ < 30 && + kstack_valid(tp, (unsigned long) rw)) { printk("Caller[%016lx]: %pS\n", rw->ins[7], (void *) rw->ins[7]); diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c index ebce43018c49..c752c4c479bd 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/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 4e5992593967..0c1e6783657f 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -46,11 +46,16 @@ SECTIONS SCHED_TEXT LOCK_TEXT KPROBES_TEXT + IRQENTRY_TEXT *(.gnu.warning) } = 0 _etext = .; RO_DATA(PAGE_SIZE) + + /* Start of data section */ + _sdata = .; + .data1 : { *(.data1) } diff --git a/arch/sparc/lib/mcount.S b/arch/sparc/lib/mcount.S index 24b8b12deed2..3ad6cbdc2163 100644 --- a/arch/sparc/lib/mcount.S +++ b/arch/sparc/lib/mcount.S @@ -7,26 +7,11 @@ #include <linux/linkage.h> -#include <asm/ptrace.h> -#include <asm/thread_info.h> - /* * This is the main variant and is called by C code. GCC's -pg option * automatically instruments every C function with a call to this. */ -#ifdef CONFIG_STACK_DEBUG - -#define OVSTACKSIZE 4096 /* lets hope this is enough */ - - .data - .align 8 -panicstring: - .asciz "Stack overflow\n" - .align 8 -ovstack: - .skip OVSTACKSIZE -#endif .text .align 32 .globl _mcount @@ -35,84 +20,48 @@ ovstack: .type mcount,#function _mcount: mcount: -#ifdef CONFIG_STACK_DEBUG - /* - * Check whether %sp is dangerously low. - */ - ldub [%g6 + TI_FPDEPTH], %g1 - srl %g1, 1, %g3 - add %g3, 1, %g3 - sllx %g3, 8, %g3 ! each fpregs frame is 256b - add %g3, 192, %g3 - add %g6, %g3, %g3 ! where does task_struct+frame end? - sub %g3, STACK_BIAS, %g3 - cmp %sp, %g3 - bg,pt %xcc, 1f - nop - lduh [%g6 + TI_CPU], %g1 - sethi %hi(hardirq_stack), %g3 - or %g3, %lo(hardirq_stack), %g3 - sllx %g1, 3, %g1 - ldx [%g3 + %g1], %g7 - sub %g7, STACK_BIAS, %g7 - cmp %sp, %g7 - bleu,pt %xcc, 2f - sethi %hi(THREAD_SIZE), %g3 - add %g7, %g3, %g7 - cmp %sp, %g7 - blu,pn %xcc, 1f -2: sethi %hi(softirq_stack), %g3 - or %g3, %lo(softirq_stack), %g3 - ldx [%g3 + %g1], %g7 - sub %g7, STACK_BIAS, %g7 - cmp %sp, %g7 - bleu,pt %xcc, 3f - sethi %hi(THREAD_SIZE), %g3 - add %g7, %g3, %g7 - cmp %sp, %g7 - blu,pn %xcc, 1f - nop - /* If we are already on ovstack, don't hop onto it - * again, we are already trying to output the stack overflow - * message. - */ -3: sethi %hi(ovstack), %g7 ! cant move to panic stack fast enough - or %g7, %lo(ovstack), %g7 - add %g7, OVSTACKSIZE, %g3 - sub %g3, STACK_BIAS + 192, %g3 - sub %g7, STACK_BIAS, %g7 - cmp %sp, %g7 - blu,pn %xcc, 2f - cmp %sp, %g3 - bleu,pn %xcc, 1f - nop -2: mov %g3, %sp - sethi %hi(panicstring), %g3 - call prom_printf - or %g3, %lo(panicstring), %o0 - call prom_halt - nop -1: -#endif #ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE - mov %o7, %o0 - .globl mcount_call -mcount_call: - call ftrace_stub - mov %o0, %o7 + /* Do nothing, the retl/nop below is all we need. */ #else - sethi %hi(ftrace_trace_function), %g1 + sethi %hi(function_trace_stop), %g1 + lduw [%g1 + %lo(function_trace_stop)], %g2 + brnz,pn %g2, 2f + sethi %hi(ftrace_trace_function), %g1 sethi %hi(ftrace_stub), %g2 ldx [%g1 + %lo(ftrace_trace_function)], %g1 or %g2, %lo(ftrace_stub), %g2 cmp %g1, %g2 be,pn %icc, 1f - mov %i7, %o1 - jmpl %g1, %g0 - mov %o7, %o0 + mov %i7, %g3 + save %sp, -176, %sp + mov %g3, %o1 + jmpl %g1, %o7 + mov %i7, %o0 + ret + restore /* not reached */ 1: +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + sethi %hi(ftrace_graph_return), %g1 + ldx [%g1 + %lo(ftrace_graph_return)], %g3 + cmp %g2, %g3 + bne,pn %xcc, 5f + sethi %hi(ftrace_graph_entry_stub), %g2 + sethi %hi(ftrace_graph_entry), %g1 + or %g2, %lo(ftrace_graph_entry_stub), %g2 + ldx [%g1 + %lo(ftrace_graph_entry)], %g1 + cmp %g1, %g2 + be,pt %xcc, 2f + nop +5: mov %i7, %g2 + mov %fp, %g3 + save %sp, -176, %sp + mov %g2, %l0 + ba,pt %xcc, ftrace_graph_caller + mov %g3, %l1 +#endif +2: #endif #endif retl @@ -131,14 +80,50 @@ ftrace_stub: .globl ftrace_caller .type ftrace_caller,#function ftrace_caller: - mov %i7, %o1 - mov %o7, %o0 + sethi %hi(function_trace_stop), %g1 + mov %i7, %g2 + lduw [%g1 + %lo(function_trace_stop)], %g1 + brnz,pn %g1, ftrace_stub + mov %fp, %g3 + save %sp, -176, %sp + mov %g2, %o1 + mov %g2, %l0 + mov %g3, %l1 .globl ftrace_call ftrace_call: call ftrace_stub - mov %o0, %o7 - retl + mov %i7, %o0 +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .globl ftrace_graph_call +ftrace_graph_call: + call ftrace_stub nop +#endif + ret + restore +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .size ftrace_graph_call,.-ftrace_graph_call +#endif + .size ftrace_call,.-ftrace_call .size ftrace_caller,.-ftrace_caller #endif #endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + mov %l0, %o0 + mov %i7, %o1 + call prepare_ftrace_return + mov %l1, %o2 + ret + restore %o0, -8, %i7 +END(ftrace_graph_caller) + +ENTRY(return_to_handler) + save %sp, -176, %sp + call ftrace_return_to_handler + mov %fp, %o0 + jmpl %o0 + 8, %g0 + restore +END(return_to_handler) +#endif diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 64cda95f59ca..7a656bd8bd3c 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -6,6 +6,7 @@ #include "linux/irqreturn.h" #include "linux/kd.h" #include "linux/sched.h" +#include "linux/slab.h" #include "chan_kern.h" #include "irq_kern.h" #include "irq_user.h" diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index 06d6ccf0e444..b6b1096152aa 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -8,7 +8,6 @@ #include <errno.h> #include <sched.h> #include <linux/limits.h> -#include <linux/slab.h> #include <sys/socket.h> #include <sys/wait.h> #include "kern_constants.h" diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 59b4556a5b92..e790bc1fbfa3 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/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index ba19ad4c47d0..86a0ff0aeac7 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -21,6 +21,7 @@ #define _ASM_X86_AMD_IOMMU_TYPES_H #include <linux/types.h> +#include <linux/mutex.h> #include <linux/list.h> #include <linux/spinlock.h> @@ -140,6 +141,7 @@ /* constants to configure the command buffer */ #define CMD_BUFFER_SIZE 8192 +#define CMD_BUFFER_UNINITIALIZED 1 #define CMD_BUFFER_ENTRIES 512 #define MMIO_CMD_SIZE_SHIFT 56 #define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT) @@ -237,6 +239,7 @@ struct protection_domain { struct list_head list; /* for list of all protection domains */ struct list_head dev_list; /* List of all devices in this domain */ spinlock_t lock; /* mostly used to lock the page table*/ + struct mutex api_lock; /* protect page tables in the iommu-api path */ u16 id; /* the domain id written to the device table */ int mode; /* paging mode (0-6 levels) */ u64 *pt_root; /* page table root pointer */ diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index ba0eed8aa1a6..b60f2924c413 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -28,22 +28,39 @@ #ifndef __ASSEMBLY__ #include <asm/hw_irq.h> -#include <asm/kvm_para.h> /*G:030 * But first, how does our Guest contact the Host to ask for privileged * operations? There are two ways: the direct way is to make a "hypercall", * to make requests of the Host Itself. * - * We use the KVM hypercall mechanism, though completely different hypercall - * numbers. Seventeen hypercalls are available: the hypercall number is put in - * the %eax register, and the arguments (when required) are placed in %ebx, - * %ecx, %edx and %esi. If a return value makes sense, it's returned in %eax. + * Our hypercall mechanism uses the highest unused trap code (traps 32 and + * above are used by real hardware interrupts). Seventeen hypercalls are + * available: the hypercall number is put in the %eax register, and the + * arguments (when required) are placed in %ebx, %ecx, %edx and %esi. + * If a return value makes sense, it's returned in %eax. * * Grossly invalid calls result in Sudden Death at the hands of the vengeful * Host, rather than returning failure. This reflects Winston Churchill's * definition of a gentleman: "someone who is only rude intentionally". -:*/ + */ +static inline unsigned long +hcall(unsigned long call, + unsigned long arg1, unsigned long arg2, unsigned long arg3, + unsigned long arg4) +{ + /* "int" is the Intel instruction to trigger a trap. */ + asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY) + /* The call in %eax (aka "a") might be overwritten */ + : "=a"(call) + /* The arguments are in %eax, %ebx, %ecx, %edx & %esi */ + : "a"(call), "b"(arg1), "c"(arg2), "d"(arg3), "S"(arg4) + /* "memory" means this might write somewhere in memory. + * This isn't true for all calls, but it's safe to tell + * gcc that it might happen so it doesn't get clever. */ + : "memory"); + return call; +} /* Can't use our min() macro here: needs to be a constant */ #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32) diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index f3dadb571d9b..f854d89b7edf 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -118,7 +118,7 @@ static bool check_device(struct device *dev) return false; /* No device or no PCI device */ - if (!dev || dev->bus != &pci_bus_type) + if (dev->bus != &pci_bus_type) return false; devid = get_device_id(dev); @@ -392,6 +392,7 @@ static int __iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) u32 tail, head; u8 *target; + WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED); tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); target = iommu->cmd_buf + tail; memcpy_toio(target, cmd, sizeof(*cmd)); @@ -2186,7 +2187,7 @@ static void prealloc_protection_domains(void) struct dma_ops_domain *dma_dom; u16 devid; - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + for_each_pci_dev(dev) { /* Do we handle this device? */ if (!check_device(&dev->dev)) @@ -2298,7 +2299,7 @@ static void cleanup_domain(struct protection_domain *domain) list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) { struct device *dev = dev_data->dev; - do_detach(dev); + __detach_device(dev); atomic_set(&dev_data->bind, 0); } @@ -2327,6 +2328,7 @@ static struct protection_domain *protection_domain_alloc(void) return NULL; spin_lock_init(&domain->lock); + mutex_init(&domain->api_lock); domain->id = domain_id_alloc(); if (!domain->id) goto out_err; @@ -2379,9 +2381,7 @@ static void amd_iommu_domain_destroy(struct iommu_domain *dom) free_pagetable(domain); - domain_id_free(domain->id); - - kfree(domain); + protection_domain_free(domain); dom->priv = NULL; } @@ -2456,6 +2456,8 @@ static int amd_iommu_map_range(struct iommu_domain *dom, iova &= PAGE_MASK; paddr &= PAGE_MASK; + mutex_lock(&domain->api_lock); + for (i = 0; i < npages; ++i) { ret = iommu_map_page(domain, iova, paddr, prot, PM_MAP_4k); if (ret) @@ -2465,6 +2467,8 @@ static int amd_iommu_map_range(struct iommu_domain *dom, paddr += PAGE_SIZE; } + mutex_unlock(&domain->api_lock); + return 0; } @@ -2477,12 +2481,16 @@ static void amd_iommu_unmap_range(struct iommu_domain *dom, iova &= PAGE_MASK; + mutex_lock(&domain->api_lock); + for (i = 0; i < npages; ++i) { iommu_unmap_page(domain, iova, PM_MAP_4k); iova += PAGE_SIZE; } iommu_flush_tlb_pde(domain); + + mutex_unlock(&domain->api_lock); } static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 42f5350b908f..6360abf993d4 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -138,9 +138,9 @@ int amd_iommus_present; bool amd_iommu_np_cache __read_mostly; /* - * Set to true if ACPI table parsing and hardware intialization went properly + * The ACPI table parsing functions set this variable on an error */ -static bool amd_iommu_initialized; +static int __initdata amd_iommu_init_err; /* * List of protection domains - used during resume @@ -391,9 +391,11 @@ static int __init find_last_devid_acpi(struct acpi_table_header *table) */ for (i = 0; i < table->length; ++i) checksum += p[i]; - if (checksum != 0) + if (checksum != 0) { /* ACPI table corrupt */ - return -ENODEV; + amd_iommu_init_err = -ENODEV; + return 0; + } p += IVRS_HEADER_LENGTH; @@ -436,7 +438,7 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu) if (cmd_buf == NULL) return NULL; - iommu->cmd_buf_size = CMD_BUFFER_SIZE; + iommu->cmd_buf_size = CMD_BUFFER_SIZE | CMD_BUFFER_UNINITIALIZED; return cmd_buf; } @@ -472,12 +474,13 @@ static void iommu_enable_command_buffer(struct amd_iommu *iommu) &entry, sizeof(entry)); amd_iommu_reset_cmd_buffer(iommu); + iommu->cmd_buf_size &= ~(CMD_BUFFER_UNINITIALIZED); } static void __init free_command_buffer(struct amd_iommu *iommu) { free_pages((unsigned long)iommu->cmd_buf, - get_order(iommu->cmd_buf_size)); + get_order(iommu->cmd_buf_size & ~(CMD_BUFFER_UNINITIALIZED))); } /* allocates the memory where the IOMMU will log its events to */ @@ -920,11 +923,16 @@ static int __init init_iommu_all(struct acpi_table_header *table) h->mmio_phys); iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL); - if (iommu == NULL) - return -ENOMEM; + if (iommu == NULL) { + amd_iommu_init_err = -ENOMEM; + return 0; + } + ret = init_iommu_one(iommu, h); - if (ret) - return ret; + if (ret) { + amd_iommu_init_err = ret; + return 0; + } break; default: break; @@ -934,8 +942,6 @@ static int __init init_iommu_all(struct acpi_table_header *table) } WARN_ON(p != end); - amd_iommu_initialized = true; - return 0; } @@ -1211,6 +1217,10 @@ static int __init amd_iommu_init(void) if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0) return -ENODEV; + ret = amd_iommu_init_err; + if (ret) + goto out; + dev_table_size = tbl_size(DEV_TABLE_ENTRY_SIZE); alias_table_size = tbl_size(ALIAS_TABLE_ENTRY_SIZE); rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE); @@ -1270,12 +1280,19 @@ static int __init amd_iommu_init(void) if (acpi_table_parse("IVRS", init_iommu_all) != 0) goto free; - if (!amd_iommu_initialized) + if (amd_iommu_init_err) { + ret = amd_iommu_init_err; goto free; + } if (acpi_table_parse("IVRS", init_memory_definitions) != 0) goto free; + if (amd_iommu_init_err) { + ret = amd_iommu_init_err; + goto free; + } + ret = sysdev_class_register(&amd_iommu_sysdev_class); if (ret) goto free; @@ -1288,6 +1305,8 @@ static int __init amd_iommu_init(void) if (ret) goto free; + enable_iommus(); + if (iommu_pass_through) ret = amd_iommu_init_passthrough(); else @@ -1300,8 +1319,6 @@ static int __init amd_iommu_init(void) amd_iommu_init_notifier(); - enable_iommus(); - if (iommu_pass_through) goto out; @@ -1315,6 +1332,7 @@ out: return ret; free: + disable_iommus(); amd_iommu_uninit_devices(); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 3704997e8b25..b5d8b0bcf235 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -393,6 +393,7 @@ void __init gart_iommu_hole_init(void) for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { int bus; int dev_base, dev_limit; + u32 ctl; bus = bus_dev_ranges[i].bus; dev_base = bus_dev_ranges[i].dev_base; @@ -406,7 +407,19 @@ void __init gart_iommu_hole_init(void) gart_iommu_aperture = 1; x86_init.iommu.iommu_init = gart_iommu_init; - aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7; + ctl = read_pci_config(bus, slot, 3, + AMD64_GARTAPERTURECTL); + + /* + * Before we do anything else disable the GART. It may + * still be enabled if we boot into a crash-kernel here. + * Reconfiguring the GART while it is enabled could have + * unknown side-effects. + */ + ctl &= ~GARTEN; + write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl); + + aper_order = (ctl >> 1) & 7; aper_size = (32 * 1024 * 1024) << aper_order; aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff; aper_base <<= 25; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index a4849c10a77e..ebd4c51d096a 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -27,7 +27,6 @@ #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/virtext.h> -#include <asm/x86_init.h> #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) @@ -103,10 +102,5 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif - -#ifdef CONFIG_X86_64 - x86_platform.iommu_shutdown(); -#endif - crash_save_cpu(regs, safe_smp_processor_id()); } diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h index e39e77168a37..e1a93be4fd44 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/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 68cd24f9deae..0f7f130caa67 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -565,6 +565,9 @@ static void enable_gart_translations(void) enable_gart_translation(dev, __pa(agp_gatt_table)); } + + /* Flush the GART-TLB to remove stale entries */ + k8_flush_garts(); } /* diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 48aeee8eefb0..19a8906bcaa2 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 445c59411ed0..2ba58206812a 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 686492ed3079..bc933cfb4e66 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 24cd0ee896e9..3c4ca98ad27f 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; } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 7e59dc1d3fc2..2bdf628066bd 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -115,7 +115,7 @@ static void async_hcall(unsigned long call, unsigned long arg1, local_irq_save(flags); if (lguest_data.hcall_status[next_call] != 0xFF) { /* Table full, so do normal hcall which will flush table. */ - kvm_hypercall4(call, arg1, arg2, arg3, arg4); + hcall(call, arg1, arg2, arg3, arg4); } else { lguest_data.hcalls[next_call].arg0 = call; lguest_data.hcalls[next_call].arg1 = arg1; @@ -145,46 +145,45 @@ static void async_hcall(unsigned long call, unsigned long arg1, * So, when we're in lazy mode, we call async_hcall() to store the call for * future processing: */ -static void lazy_hcall1(unsigned long call, - unsigned long arg1) +static void lazy_hcall1(unsigned long call, unsigned long arg1) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - kvm_hypercall1(call, arg1); + hcall(call, arg1, 0, 0, 0); else async_hcall(call, arg1, 0, 0, 0); } /* You can imagine what lazy_hcall2, 3 and 4 look like. :*/ static void lazy_hcall2(unsigned long call, - unsigned long arg1, - unsigned long arg2) + unsigned long arg1, + unsigned long arg2) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - kvm_hypercall2(call, arg1, arg2); + hcall(call, arg1, arg2, 0, 0); else async_hcall(call, arg1, arg2, 0, 0); } static void lazy_hcall3(unsigned long call, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3) + unsigned long arg1, + unsigned long arg2, + unsigned long arg3) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - kvm_hypercall3(call, arg1, arg2, arg3); + hcall(call, arg1, arg2, arg3, 0); else async_hcall(call, arg1, arg2, arg3, 0); } #ifdef CONFIG_X86_PAE static void lazy_hcall4(unsigned long call, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3, - unsigned long arg4) + unsigned long arg1, + unsigned long arg2, + unsigned long arg3, + unsigned long arg4) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - kvm_hypercall4(call, arg1, arg2, arg3, arg4); + hcall(call, arg1, arg2, arg3, arg4); else async_hcall(call, arg1, arg2, arg3, arg4); } @@ -196,13 +195,13 @@ static void lazy_hcall4(unsigned long call, :*/ static void lguest_leave_lazy_mmu_mode(void) { - kvm_hypercall0(LHCALL_FLUSH_ASYNC); + hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); paravirt_leave_lazy_mmu(); } static void lguest_end_context_switch(struct task_struct *next) { - kvm_hypercall0(LHCALL_FLUSH_ASYNC); + hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); paravirt_end_context_switch(next); } @@ -286,7 +285,7 @@ static void lguest_write_idt_entry(gate_desc *dt, /* Keep the local copy up to date. */ native_write_idt_entry(dt, entrynum, g); /* Tell Host about this new entry. */ - kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]); + hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1], 0); } /* @@ -300,7 +299,7 @@ static void lguest_load_idt(const struct desc_ptr *desc) struct desc_struct *idt = (void *)desc->address; for (i = 0; i < (desc->size+1)/8; i++) - kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b); + hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b, 0); } /* @@ -321,7 +320,7 @@ static void lguest_load_gdt(const struct desc_ptr *desc) struct desc_struct *gdt = (void *)desc->address; for (i = 0; i < (desc->size+1)/8; i++) - kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b); + hcall(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b, 0); } /* @@ -334,8 +333,8 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, { native_write_gdt_entry(dt, entrynum, desc, type); /* Tell Host about this new entry. */ - kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum, - dt[entrynum].a, dt[entrynum].b); + hcall(LHCALL_LOAD_GDT_ENTRY, entrynum, + dt[entrynum].a, dt[entrynum].b, 0); } /* @@ -931,7 +930,7 @@ static int lguest_clockevent_set_next_event(unsigned long delta, } /* Please wake us this far in the future. */ - kvm_hypercall1(LHCALL_SET_CLOCKEVENT, delta); + hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0, 0); return 0; } @@ -942,7 +941,7 @@ static void lguest_clockevent_set_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: /* A 0 argument shuts the clock down. */ - kvm_hypercall0(LHCALL_SET_CLOCKEVENT); + hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0); break; case CLOCK_EVT_MODE_ONESHOT: /* This is what we expect. */ @@ -1100,7 +1099,7 @@ static void set_lguest_basic_apic_ops(void) /* STOP! Until an interrupt comes in. */ static void lguest_safe_halt(void) { - kvm_hypercall0(LHCALL_HALT); + hcall(LHCALL_HALT, 0, 0, 0, 0); } /* @@ -1112,8 +1111,8 @@ static void lguest_safe_halt(void) */ static void lguest_power_off(void) { - kvm_hypercall2(LHCALL_SHUTDOWN, __pa("Power down"), - LGUEST_SHUTDOWN_POWEROFF); + hcall(LHCALL_SHUTDOWN, __pa("Power down"), + LGUEST_SHUTDOWN_POWEROFF, 0, 0); } /* @@ -1123,7 +1122,7 @@ static void lguest_power_off(void) */ static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p) { - kvm_hypercall2(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF); + hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0, 0); /* The hcall won't return, but to keep gcc happy, we're "done". */ return NOTIFY_DONE; } @@ -1162,7 +1161,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) len = sizeof(scratch) - 1; scratch[len] = '\0'; memcpy(scratch, buf, len); - kvm_hypercall1(LHCALL_NOTIFY, __pa(scratch)); + hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0, 0); /* This routine returns the number of bytes actually written. */ return len; @@ -1174,7 +1173,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) */ static void lguest_restart(char *reason) { - kvm_hypercall2(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART); + hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0, 0); } /*G:050 diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S index 27eac0faee48..4f420c2f2d55 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/i386_head.S @@ -32,7 +32,7 @@ ENTRY(lguest_entry) */ movl $LHCALL_LGUEST_INIT, %eax movl $lguest_data - __PAGE_OFFSET, %ebx - .byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */ + int $LGUEST_TRAP_ENTRY /* Set up the initial stack so we can run C code. */ movl $(init_thread_union+THREAD_SIZE),%esp |