diff options
Diffstat (limited to 'arch/arm')
-rw-r--r-- | arch/arm/boot/dts/dove.dtsi | 4 | ||||
-rw-r--r-- | arch/arm/include/asm/elf.h | 2 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_emulate.h | 5 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_mmu.h | 87 | ||||
-rw-r--r-- | arch/arm/include/uapi/asm/kvm.h | 8 | ||||
-rw-r--r-- | arch/arm/kernel/hibernate.c | 5 | ||||
-rw-r--r-- | arch/arm/kernel/process.c | 10 | ||||
-rw-r--r-- | arch/arm/kernel/reboot.h | 6 | ||||
-rw-r--r-- | arch/arm/kvm/arm.c | 38 | ||||
-rw-r--r-- | arch/arm/kvm/guest.c | 1 | ||||
-rw-r--r-- | arch/arm/kvm/mmu.c | 251 | ||||
-rw-r--r-- | arch/arm/kvm/psci.c | 18 | ||||
-rw-r--r-- | arch/arm/mach-mvebu/pmsu.c | 16 | ||||
-rw-r--r-- | arch/arm/mach-s3c64xx/crag6410.h | 1 | ||||
-rw-r--r-- | arch/arm/mach-s3c64xx/mach-crag6410.c | 1 | ||||
-rw-r--r-- | arch/arm/mm/hugetlbpage.c | 6 |
16 files changed, 379 insertions, 80 deletions
diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi index a5441d5482a6..3cc8b8320345 100644 --- a/arch/arm/boot/dts/dove.dtsi +++ b/arch/arm/boot/dts/dove.dtsi @@ -154,7 +154,7 @@ uart2: serial@12200 { compatible = "ns16550a"; - reg = <0x12000 0x100>; + reg = <0x12200 0x100>; reg-shift = <2>; interrupts = <9>; clocks = <&core_clk 0>; @@ -163,7 +163,7 @@ uart3: serial@12300 { compatible = "ns16550a"; - reg = <0x12100 0x100>; + reg = <0x12300 0x100>; reg-shift = <2>; interrupts = <10>; clocks = <&core_clk 0>; diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index afb9cafd3786..674d03f4ba15 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -115,7 +115,7 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs); the loader. We need to make sure that it is out of the way of the program that it will "exec", and that there is sufficient room for the brk. */ -#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3) +#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) /* When the program starts, a1 contains a pointer to a function to be registered with atexit, as per the SVR4 ABI. A value of 0 means we diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index b9db269c6e61..66ce17655bb9 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -33,6 +33,11 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr = HCR_GUEST_MASK; +} + static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) { return 1; diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index acb0d5712716..16d9d788d0b8 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -44,6 +44,7 @@ #ifndef __ASSEMBLY__ +#include <linux/highmem.h> #include <asm/cacheflush.h> #include <asm/pgalloc.h> @@ -52,6 +53,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t); void free_boot_hyp_pgd(void); void free_hyp_pgds(void); +void stage2_unmap_vm(struct kvm *kvm); int kvm_alloc_stage2_pgd(struct kvm *kvm); void kvm_free_stage2_pgd(struct kvm *kvm); int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, @@ -126,29 +128,28 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) +#define kvm_pgd_index(addr) pgd_index(addr) + static inline bool kvm_page_empty(void *ptr) { struct page *ptr_page = virt_to_page(ptr); return page_count(ptr_page) == 1; } - #define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) #define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp) #define kvm_pud_table_empty(kvm, pudp) (0) #define KVM_PREALLOC_LEVEL 0 -static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd) +static inline void *kvm_get_hwpgd(struct kvm *kvm) { - return 0; + return kvm->arch.pgd; } -static inline void kvm_free_hwpgd(struct kvm *kvm) { } - -static inline void *kvm_get_hwpgd(struct kvm *kvm) +static inline unsigned int kvm_get_hwpgd_size(void) { - return kvm->arch.pgd; + return PTRS_PER_S2_PGD * sizeof(pgd_t); } struct kvm; @@ -160,12 +161,10 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; } -static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, - unsigned long size) +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, + bool ipa_uncached) { - if (!vcpu_has_cache_enabled(vcpu)) - kvm_flush_dcache_to_poc((void *)hva, size); - /* * If we are going to insert an instruction page and the icache is * either VIPT or PIPT, there is a potential problem where the host @@ -177,15 +176,73 @@ static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, * * VIVT caches are tagged using both the ASID and the VMID and doesn't * need any kind of flushing (DDI 0406C.b - Page B3-1392). + * + * We need to do this through a kernel mapping (using the + * user-space mapping has proved to be the wrong + * solution). For that, we need to kmap one page at a time, + * and iterate over the range. */ - if (icache_is_pipt()) { - __cpuc_coherent_user_range(hva, hva + size); - } else if (!icache_is_vivt_asid_tagged()) { + + bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached; + + VM_BUG_ON(size & ~PAGE_MASK); + + if (!need_flush && !icache_is_pipt()) + goto vipt_cache; + + while (size) { + void *va = kmap_atomic_pfn(pfn); + + if (need_flush) + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + if (icache_is_pipt()) + __cpuc_coherent_user_range((unsigned long)va, + (unsigned long)va + PAGE_SIZE); + + size -= PAGE_SIZE; + pfn++; + + kunmap_atomic(va); + } + +vipt_cache: + if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) { /* any kind of VIPT cache */ __flush_icache_all(); } } +static inline void __kvm_flush_dcache_pte(pte_t pte) +{ + void *va = kmap_atomic(pte_page(pte)); + + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + kunmap_atomic(va); +} + +static inline void __kvm_flush_dcache_pmd(pmd_t pmd) +{ + unsigned long size = PMD_SIZE; + pfn_t pfn = pmd_pfn(pmd); + + while (size) { + void *va = kmap_atomic_pfn(pfn); + + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + pfn++; + size -= PAGE_SIZE; + + kunmap_atomic(va); + } +} + +static inline void __kvm_flush_dcache_pud(pud_t pud) +{ +} + #define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x)) void stage2_flush_vm(struct kvm *kvm); diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 09ee408c1a67..b404cf886029 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -193,8 +193,14 @@ struct kvm_arch_memory_slot { #define KVM_ARM_IRQ_CPU_IRQ 0 #define KVM_ARM_IRQ_CPU_FIQ 1 -/* Highest supported SPI, from VGIC_NR_IRQS */ +/* + * This used to hold the highest supported SPI, but it is now obsolete + * and only here to provide source code level compatibility with older + * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS. + */ +#ifndef __KERNEL__ #define KVM_ARM_IRQ_GIC_MAX 127 +#endif /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c index c4cc50e58c13..cfb354ff2a60 100644 --- a/arch/arm/kernel/hibernate.c +++ b/arch/arm/kernel/hibernate.c @@ -22,6 +22,7 @@ #include <asm/suspend.h> #include <asm/memory.h> #include <asm/sections.h> +#include "reboot.h" int pfn_is_nosave(unsigned long pfn) { @@ -61,7 +62,7 @@ static int notrace arch_save_image(unsigned long unused) ret = swsusp_save(); if (ret == 0) - soft_restart(virt_to_phys(cpu_resume)); + _soft_restart(virt_to_phys(cpu_resume), false); return ret; } @@ -86,7 +87,7 @@ static void notrace arch_restore_image(void *unused) for (pbe = restore_pblist; pbe; pbe = pbe->next) copy_page(pbe->orig_address, pbe->address); - soft_restart(virt_to_phys(cpu_resume)); + _soft_restart(virt_to_phys(cpu_resume), false); } static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata; diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index fe972a2f3df3..ecefea4e2929 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -41,6 +41,7 @@ #include <asm/system_misc.h> #include <asm/mach/time.h> #include <asm/tls.h> +#include "reboot.h" #ifdef CONFIG_CC_STACKPROTECTOR #include <linux/stackprotector.h> @@ -95,7 +96,7 @@ static void __soft_restart(void *addr) BUG(); } -void soft_restart(unsigned long addr) +void _soft_restart(unsigned long addr, bool disable_l2) { u64 *stack = soft_restart_stack + ARRAY_SIZE(soft_restart_stack); @@ -104,7 +105,7 @@ void soft_restart(unsigned long addr) local_fiq_disable(); /* Disable the L2 if we're the last man standing. */ - if (num_online_cpus() == 1) + if (disable_l2) outer_disable(); /* Change to the new stack and continue with the reset. */ @@ -114,6 +115,11 @@ void soft_restart(unsigned long addr) BUG(); } +void soft_restart(unsigned long addr) +{ + _soft_restart(addr, num_online_cpus() == 1); +} + /* * Function pointers to optional machine specific functions */ diff --git a/arch/arm/kernel/reboot.h b/arch/arm/kernel/reboot.h new file mode 100644 index 000000000000..c87f05816d6b --- /dev/null +++ b/arch/arm/kernel/reboot.h @@ -0,0 +1,6 @@ +#ifndef REBOOT_H +#define REBOOT_H + +extern void _soft_restart(unsigned long addr, bool disable_l2); + +#endif diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 9e193c8a959e..ed5834e8e2ac 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -213,6 +213,11 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) int err; struct kvm_vcpu *vcpu; + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) { + err = -EBUSY; + goto out; + } + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); if (!vcpu) { err = -ENOMEM; @@ -419,6 +424,7 @@ static void update_vttbr(struct kvm *kvm) static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; int ret; if (likely(vcpu->arch.has_run_once)) @@ -427,15 +433,23 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) vcpu->arch.has_run_once = true; /* - * Initialize the VGIC before running a vcpu the first time on - * this VM. + * Map the VGIC hardware resources before running a vcpu the first + * time on this VM. */ - if (unlikely(!vgic_initialized(vcpu->kvm))) { - ret = kvm_vgic_init(vcpu->kvm); + if (unlikely(!vgic_initialized(kvm))) { + ret = kvm_vgic_map_resources(kvm); if (ret) return ret; } + /* + * Enable the arch timers only if we have an in-kernel VGIC + * and it has been properly initialized, since we cannot handle + * interrupts from the virtual timer with a userspace gic. + */ + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) + kvm_timer_enable(kvm); + return 0; } @@ -639,8 +653,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, if (!irqchip_in_kernel(kvm)) return -ENXIO; - if (irq_num < VGIC_NR_PRIVATE_IRQS || - irq_num > KVM_ARM_IRQ_GIC_MAX) + if (irq_num < VGIC_NR_PRIVATE_IRQS) return -EINVAL; return kvm_vgic_inject_irq(kvm, 0, irq_num, level); @@ -659,10 +672,21 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, return ret; /* + * Ensure a rebooted VM will fault in RAM pages and detect if the + * guest MMU is turned off and flush the caches as needed. + */ + if (vcpu->arch.has_run_once) + stage2_unmap_vm(vcpu->kvm); + + vcpu_reset_hcr(vcpu); + + /* * Handle the "start in power-off" case by marking the VCPU as paused. */ - if (__test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) + if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) vcpu->arch.pause = true; + else + vcpu->arch.pause = false; return 0; } diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index cc0b78769bd8..8c97208b9b97 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { - vcpu->arch.hcr = HCR_GUEST_MASK; return 0; } diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 8664ff17cbbe..cba52cf6ed3f 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -58,6 +58,26 @@ static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa); } +/* + * D-Cache management functions. They take the page table entries by + * value, as they are flushing the cache using the kernel mapping (or + * kmap on 32bit). + */ +static void kvm_flush_dcache_pte(pte_t pte) +{ + __kvm_flush_dcache_pte(pte); +} + +static void kvm_flush_dcache_pmd(pmd_t pmd) +{ + __kvm_flush_dcache_pmd(pmd); +} + +static void kvm_flush_dcache_pud(pud_t pud) +{ + __kvm_flush_dcache_pud(pud); +} + static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, int min, int max) { @@ -119,6 +139,26 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) put_page(virt_to_page(pmd)); } +/* + * Unmapping vs dcache management: + * + * If a guest maps certain memory pages as uncached, all writes will + * bypass the data cache and go directly to RAM. However, the CPUs + * can still speculate reads (not writes) and fill cache lines with + * data. + * + * Those cache lines will be *clean* cache lines though, so a + * clean+invalidate operation is equivalent to an invalidate + * operation, because no cache lines are marked dirty. + * + * Those clean cache lines could be filled prior to an uncached write + * by the guest, and the cache coherent IO subsystem would therefore + * end up writing old data to disk. + * + * This is why right after unmapping a page/section and invalidating + * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure + * the IO subsystem will never hit in the cache. + */ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { @@ -128,9 +168,16 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, start_pte = pte = pte_offset_kernel(pmd, addr); do { if (!pte_none(*pte)) { + pte_t old_pte = *pte; + kvm_set_pte(pte, __pte(0)); - put_page(virt_to_page(pte)); kvm_tlb_flush_vmid_ipa(kvm, addr); + + /* No need to invalidate the cache for device mappings */ + if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(old_pte); + + put_page(virt_to_page(pte)); } } while (pte++, addr += PAGE_SIZE, addr != end); @@ -149,8 +196,13 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud, next = kvm_pmd_addr_end(addr, end); if (!pmd_none(*pmd)) { if (kvm_pmd_huge(*pmd)) { + pmd_t old_pmd = *pmd; + pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pmd(old_pmd); + put_page(virt_to_page(pmd)); } else { unmap_ptes(kvm, pmd, addr, next); @@ -173,8 +225,13 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd, next = kvm_pud_addr_end(addr, end); if (!pud_none(*pud)) { if (pud_huge(*pud)) { + pud_t old_pud = *pud; + pud_clear(pud); kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pud(old_pud); + put_page(virt_to_page(pud)); } else { unmap_pmds(kvm, pud, addr, next); @@ -194,7 +251,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, phys_addr_t addr = start, end = start + size; phys_addr_t next; - pgd = pgdp + pgd_index(addr); + pgd = pgdp + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); if (!pgd_none(*pgd)) @@ -209,10 +266,9 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, pte = pte_offset_kernel(pmd, addr); do { - if (!pte_none(*pte)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE); - } + if (!pte_none(*pte) && + (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(*pte); } while (pte++, addr += PAGE_SIZE, addr != end); } @@ -226,12 +282,10 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, do { next = kvm_pmd_addr_end(addr, end); if (!pmd_none(*pmd)) { - if (kvm_pmd_huge(*pmd)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE); - } else { + if (kvm_pmd_huge(*pmd)) + kvm_flush_dcache_pmd(*pmd); + else stage2_flush_ptes(kvm, pmd, addr, next); - } } } while (pmd++, addr = next, addr != end); } @@ -246,12 +300,10 @@ static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd, do { next = kvm_pud_addr_end(addr, end); if (!pud_none(*pud)) { - if (pud_huge(*pud)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE); - } else { + if (pud_huge(*pud)) + kvm_flush_dcache_pud(*pud); + else stage2_flush_pmds(kvm, pud, addr, next); - } } } while (pud++, addr = next, addr != end); } @@ -264,7 +316,7 @@ static void stage2_flush_memslot(struct kvm *kvm, phys_addr_t next; pgd_t *pgd; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); stage2_flush_puds(kvm, pgd, addr, next); @@ -541,6 +593,20 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr) __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE); } +/* Free the HW pgd, one page at a time */ +static void kvm_free_hwpgd(void *hwpgd) +{ + free_pages_exact(hwpgd, kvm_get_hwpgd_size()); +} + +/* Allocate the HW PGD, making sure that each page gets its own refcount */ +static void *kvm_alloc_hwpgd(void) +{ + unsigned int size = kvm_get_hwpgd_size(); + + return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); +} + /** * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation. * @kvm: The KVM struct pointer for the VM. @@ -554,15 +620,31 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr) */ int kvm_alloc_stage2_pgd(struct kvm *kvm) { - int ret; pgd_t *pgd; + void *hwpgd; if (kvm->arch.pgd != NULL) { kvm_err("kvm_arch already initialized?\n"); return -EINVAL; } + hwpgd = kvm_alloc_hwpgd(); + if (!hwpgd) + return -ENOMEM; + + /* When the kernel uses more levels of page tables than the + * guest, we allocate a fake PGD and pre-populate it to point + * to the next-level page table, which will be the real + * initial page table pointed to by the VTTBR. + * + * When KVM_PREALLOC_LEVEL==2, we allocate a single page for + * the PMD and the kernel will use folded pud. + * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD + * pages. + */ if (KVM_PREALLOC_LEVEL > 0) { + int i; + /* * Allocate fake pgd for the page table manipulation macros to * work. This is not used by the hardware and we have no @@ -570,30 +652,32 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) */ pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), GFP_KERNEL | __GFP_ZERO); + + if (!pgd) { + kvm_free_hwpgd(hwpgd); + return -ENOMEM; + } + + /* Plug the HW PGD into the fake one. */ + for (i = 0; i < PTRS_PER_S2_PGD; i++) { + if (KVM_PREALLOC_LEVEL == 1) + pgd_populate(NULL, pgd + i, + (pud_t *)hwpgd + i * PTRS_PER_PUD); + else if (KVM_PREALLOC_LEVEL == 2) + pud_populate(NULL, pud_offset(pgd, 0) + i, + (pmd_t *)hwpgd + i * PTRS_PER_PMD); + } } else { /* * Allocate actual first-level Stage-2 page table used by the * hardware for Stage-2 page table walks. */ - pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER); + pgd = (pgd_t *)hwpgd; } - if (!pgd) - return -ENOMEM; - - ret = kvm_prealloc_hwpgd(kvm, pgd); - if (ret) - goto out_err; - kvm_clean_pgd(pgd); kvm->arch.pgd = pgd; return 0; -out_err: - if (KVM_PREALLOC_LEVEL > 0) - kfree(pgd); - else - free_pages((unsigned long)pgd, S2_PGD_ORDER); - return ret; } /** @@ -612,6 +696,71 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) unmap_range(kvm, kvm->arch.pgd, start, size); } +static void stage2_unmap_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + hva_t hva = memslot->userspace_addr; + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t size = PAGE_SIZE * memslot->npages; + hva_t reg_end = hva + size; + + /* + * A memory region could potentially cover multiple VMAs, and any holes + * between them, so iterate over all of them to find out if we should + * unmap any of them. + * + * +--------------------------------------------+ + * +---------------+----------------+ +----------------+ + * | : VMA 1 | VMA 2 | | VMA 3 : | + * +---------------+----------------+ +----------------+ + * | memory region | + * +--------------------------------------------+ + */ + do { + struct vm_area_struct *vma = find_vma(current->mm, hva); + hva_t vm_start, vm_end; + + if (!vma || vma->vm_start >= reg_end) + break; + + /* + * Take the intersection of this VMA with the memory region + */ + vm_start = max(hva, vma->vm_start); + vm_end = min(reg_end, vma->vm_end); + + if (!(vma->vm_flags & VM_PFNMAP)) { + gpa_t gpa = addr + (vm_start - memslot->userspace_addr); + unmap_stage2_range(kvm, gpa, vm_end - vm_start); + } + hva = vm_end; + } while (hva < reg_end); +} + +/** + * stage2_unmap_vm - Unmap Stage-2 RAM mappings + * @kvm: The struct kvm pointer + * + * Go through the memregions and unmap any reguler RAM + * backing memory already mapped to the VM. + */ +void stage2_unmap_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_unmap_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); +} + /** * kvm_free_stage2_pgd - free all stage-2 tables * @kvm: The KVM struct pointer for the VM. @@ -629,11 +778,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm) return; unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); - kvm_free_hwpgd(kvm); + kvm_free_hwpgd(kvm_get_hwpgd(kvm)); if (KVM_PREALLOC_LEVEL > 0) kfree(kvm->arch.pgd); - else - free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER); + kvm->arch.pgd = NULL; } @@ -643,7 +791,7 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache pgd_t *pgd; pud_t *pud; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); if (WARN_ON(pgd_none(*pgd))) { if (!cache) return NULL; @@ -840,6 +988,12 @@ static bool kvm_is_device_pfn(unsigned long pfn) return !pfn_valid(pfn); } +static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, bool uncached) +{ + __coherent_cache_guest_page(vcpu, pfn, size, uncached); +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_memory_slot *memslot, unsigned long hva, unsigned long fault_status) @@ -853,6 +1007,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct vm_area_struct *vma; pfn_t pfn; pgprot_t mem_type = PAGE_S2; + bool fault_ipa_uncached; write_fault = kvm_is_write_fault(vcpu); if (fault_status == FSC_PERM && !write_fault) { @@ -919,6 +1074,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (!hugetlb && !force_pte) hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa); + fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT; + if (hugetlb) { pmd_t new_pmd = pfn_pmd(pfn, mem_type); new_pmd = pmd_mkhuge(new_pmd); @@ -926,7 +1083,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pmd_writable(&new_pmd); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE); + coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached); ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); } else { pte_t new_pte = pfn_pte(pfn, mem_type); @@ -934,7 +1091,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pte_writable(&new_pte); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva, PAGE_SIZE); + coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached); ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE)); } @@ -1294,11 +1451,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, hva = vm_end; } while (hva < reg_end); - if (ret) { - spin_lock(&kvm->mmu_lock); + spin_lock(&kvm->mmu_lock); + if (ret) unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size); - spin_unlock(&kvm->mmu_lock); - } + else + stage2_flush_memslot(kvm, memslot); + spin_unlock(&kvm->mmu_lock); return ret; } @@ -1310,6 +1468,15 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages) { + /* + * Readonly memslots are not incoherent with the caches by definition, + * but in practice, they are used mostly to emulate ROMs or NOR flashes + * that the guest may consider devices and hence map as uncached. + * To prevent incoherency issues in these cases, tag all readonly + * regions as incoherent. + */ + if (slot->flags & KVM_MEM_READONLY) + slot->flags |= KVM_MEMSLOT_INCOHERENT; return 0; } diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 09cf37737ee2..58cb3248d277 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -15,6 +15,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/preempt.h> #include <linux/kvm_host.h> #include <linux/wait.h> @@ -166,6 +167,23 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type) { + int i; + struct kvm_vcpu *tmp; + + /* + * The KVM ABI specifies that a system event exit may call KVM_RUN + * again and may perform shutdown/reboot at a later time that when the + * actual request is made. Since we are implementing PSCI and a + * caller of PSCI reboot and shutdown expects that the system shuts + * down or reboots immediately, let's make sure that VCPUs are not run + * after this call is handled and before the VCPUs have been + * re-initialized. + */ + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + tmp->arch.pause = true; + kvm_vcpu_kick(tmp); + } + memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); vcpu->run->system_event.type = type; vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c index bbd8664d1bac..6f8a85c5965c 100644 --- a/arch/arm/mach-mvebu/pmsu.c +++ b/arch/arm/mach-mvebu/pmsu.c @@ -415,6 +415,9 @@ static __init int armada_38x_cpuidle_init(void) void __iomem *mpsoc_base; u32 reg; + pr_warn("CPU idle is currently broken on Armada 38x: disabling"); + return 0; + np = of_find_compatible_node(NULL, NULL, "marvell,armada-380-coherency-fabric"); if (!np) @@ -476,6 +479,16 @@ static int __init mvebu_v7_cpu_pm_init(void) return 0; of_node_put(np); + /* + * Currently the CPU idle support for Armada 38x is broken, as + * the CPU hotplug uses some of the CPU idle functions it is + * broken too, so let's disable it + */ + if (of_machine_is_compatible("marvell,armada380")) { + cpu_hotplug_disable(); + pr_warn("CPU hotplug support is currently broken on Armada 38x: disabling"); + } + if (of_machine_is_compatible("marvell,armadaxp")) ret = armada_xp_cpuidle_init(); else if (of_machine_is_compatible("marvell,armada370")) @@ -489,7 +502,8 @@ static int __init mvebu_v7_cpu_pm_init(void) return ret; mvebu_v7_pmsu_enable_l2_powerdown_onidle(); - platform_device_register(&mvebu_v7_cpuidle_device); + if (mvebu_v7_cpuidle_device.name) + platform_device_register(&mvebu_v7_cpuidle_device); cpu_pm_register_notifier(&mvebu_v7_cpu_pm_notifier); return 0; diff --git a/arch/arm/mach-s3c64xx/crag6410.h b/arch/arm/mach-s3c64xx/crag6410.h index 7bc66682687e..dcbe17f5e5f8 100644 --- a/arch/arm/mach-s3c64xx/crag6410.h +++ b/arch/arm/mach-s3c64xx/crag6410.h @@ -14,6 +14,7 @@ #include <mach/gpio-samsung.h> #define GLENFARCLAS_PMIC_IRQ_BASE IRQ_BOARD_START +#define BANFF_PMIC_IRQ_BASE (IRQ_BOARD_START + 64) #define PCA935X_GPIO_BASE GPIO_BOARD_START #define CODEC_GPIO_BASE (GPIO_BOARD_START + 8) diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c index 10b913baab28..65c426bc45f7 100644 --- a/arch/arm/mach-s3c64xx/mach-crag6410.c +++ b/arch/arm/mach-s3c64xx/mach-crag6410.c @@ -554,6 +554,7 @@ static struct wm831x_touch_pdata touch_pdata = { static struct wm831x_pdata crag_pmic_pdata = { .wm831x_num = 1, + .irq_base = BANFF_PMIC_IRQ_BASE, .gpio_base = BANFF_PMIC_GPIO_BASE, .soft_shutdown = true, diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index 66781bf34077..c72412415093 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -36,12 +36,6 @@ * of type casting from pmd_t * to pte_t *. */ -struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, - int write) -{ - return ERR_PTR(-EINVAL); -} - int pud_huge(pud_t pud) { return 0; |