From c40f2f8ff833eddc02cb599ef6e5a162223449ba Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 17 Sep 2014 14:56:18 -0700 Subject: arm/arm64: KVM: add 'writable' parameter to kvm_phys_addr_ioremap Add support for read-only MMIO passthrough mappings by adding a 'writable' parameter to kvm_phys_addr_ioremap. For the moment, mappings will be read-write even if 'writable' is false, but once the definition of PAGE_S2_DEVICE gets changed, those mappings will be created read-only. Acked-by: Marc Zyngier Signed-off-by: Ard Biesheuvel Signed-off-by: Christoffer Dall --- arch/arm64/include/asm/kvm_mmu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index a030d163840b..e36171974d6a 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -77,7 +77,7 @@ void free_hyp_pgds(void); 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, - phys_addr_t pa, unsigned long size); + phys_addr_t pa, unsigned long size, bool writable); int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run); -- cgit v1.2.3 From 4a513fb009b96cf3d86491e00565367ceec29073 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 17 Sep 2014 14:56:20 -0700 Subject: arm64: kvm: define PAGE_S2_DEVICE as read-only by default Now that we support read-only memslots, we need to make sure that pass-through device mappings are not mapped writable if the guest has requested them to be read-only. The existing implementation already honours this by calling kvm_set_s2pte_writable() on the new pte in case of writable mappings, so all we need to do is define the default pgprot_t value used for devices to be PTE_S2_RDONLY. Acked-by: Marc Zyngier Signed-off-by: Ard Biesheuvel Signed-off-by: Christoffer Dall --- arch/arm64/include/asm/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index ffe1ba0506d1..51f6f5284ce5 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -79,7 +79,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) #define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) -#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN) +#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) #define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) -- cgit v1.2.3 From 38f791a4e499792eeb2a3c0572dd5133511c5bbb Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Fri, 10 Oct 2014 12:14:28 +0200 Subject: arm64: KVM: Implement 48 VA support for KVM EL2 and Stage-2 This patch adds the necessary support for all host kernel PGSIZE and VA_SPACE configuration options for both EL2 and the Stage-2 page tables. However, for 40bit and 42bit PARange systems, the architecture mandates that VTCR_EL2.SL0 is maximum 1, resulting in fewer levels of stage-2 pagge tables than levels of host kernel page tables. At the same time, systems with a PARange > 42bit, we limit the IPA range by always setting VTCR_EL2.T0SZ to 24. To solve the situation with different levels of page tables for Stage-2 translation than the host kernel page tables, we allocate a dummy PGD with pointers to our actual inital level Stage-2 page table, in order for us to reuse the kernel pgtable manipulation primitives. Reproducing all these in KVM does not look pretty and unnecessarily complicates the 32-bit side. Systems with a PARange < 40bits are not yet supported. [ I have reworked this patch from its original form submitted by Jungseok to take the architecture constraints into consideration. There were too many changes from the original patch for me to preserve the authorship. Thanks to Catalin Marinas for his help in figuring out a good solution to this challenge. I have also fixed various bugs and missing error code handling from the original patch. - Christoffer ] Reviewed-by: Catalin Marinas Acked-by: Marc Zyngier Signed-off-by: Jungseok Lee Signed-off-by: Christoffer Dall --- arch/arm/include/asm/kvm_mmu.h | 29 ++++++++- arch/arm/kvm/arm.c | 2 +- arch/arm/kvm/mmu.c | 133 +++++++++++++++++++++++++++++++-------- arch/arm64/include/asm/kvm_mmu.h | 125 +++++++++++++++++++++++++++++++++--- 4 files changed, 249 insertions(+), 40 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index eaa6deac97b2..acb0d5712716 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -37,6 +37,11 @@ */ #define TRAMPOLINE_VA UL(CONFIG_VECTORS_BASE) +/* + * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels. + */ +#define KVM_MMU_CACHE_MIN_PAGES 2 + #ifndef __ASSEMBLY__ #include @@ -83,6 +88,11 @@ static inline void kvm_clean_pgd(pgd_t *pgd) clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t)); } +static inline void kvm_clean_pmd(pmd_t *pmd) +{ + clean_dcache_area(pmd, PTRS_PER_PMD * sizeof(pmd_t)); +} + static inline void kvm_clean_pmd_entry(pmd_t *pmd) { clean_pmd_entry(pmd); @@ -123,10 +133,23 @@ static inline bool kvm_page_empty(void *ptr) } -#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep) -#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp) -#define kvm_pud_table_empty(pudp) (0) +#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) +{ + return 0; +} + +static inline void kvm_free_hwpgd(struct kvm *kvm) { } + +static inline void *kvm_get_hwpgd(struct kvm *kvm) +{ + return kvm->arch.pgd; +} struct kvm; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 45e5f67e63b1..9e193c8a959e 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -409,7 +409,7 @@ static void update_vttbr(struct kvm *kvm) kvm_next_vmid++; /* update vttbr to be used with the new vmid */ - pgd_phys = virt_to_phys(kvm->arch.pgd); + pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm)); BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK); vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK; kvm->arch.vttbr = pgd_phys | vmid; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 6038027ab1d6..ee142edcca84 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -42,7 +42,7 @@ static unsigned long hyp_idmap_start; static unsigned long hyp_idmap_end; static phys_addr_t hyp_idmap_vector; -#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t)) +#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t)) #define kvm_pmd_huge(_x) (pmd_huge(_x) || pmd_trans_huge(_x)) @@ -134,7 +134,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, } } while (pte++, addr += PAGE_SIZE, addr != end); - if (kvm_pte_table_empty(start_pte)) + if (kvm_pte_table_empty(kvm, start_pte)) clear_pmd_entry(kvm, pmd, start_addr); } @@ -158,7 +158,7 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud, } } while (pmd++, addr = next, addr != end); - if (kvm_pmd_table_empty(start_pmd)) + if (kvm_pmd_table_empty(kvm, start_pmd)) clear_pud_entry(kvm, pud, start_addr); } @@ -182,7 +182,7 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd, } } while (pud++, addr = next, addr != end); - if (kvm_pud_table_empty(start_pud)) + if (kvm_pud_table_empty(kvm, start_pud)) clear_pgd_entry(kvm, pgd, start_addr); } @@ -306,7 +306,7 @@ void free_boot_hyp_pgd(void) if (boot_hyp_pgd) { unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE); unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE); - free_pages((unsigned long)boot_hyp_pgd, pgd_order); + free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order); boot_hyp_pgd = NULL; } @@ -343,7 +343,7 @@ void free_hyp_pgds(void) for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE) unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE); - free_pages((unsigned long)hyp_pgd, pgd_order); + free_pages((unsigned long)hyp_pgd, hyp_pgd_order); hyp_pgd = NULL; } @@ -401,13 +401,46 @@ static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start, return 0; } +static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start, + unsigned long end, unsigned long pfn, + pgprot_t prot) +{ + pud_t *pud; + pmd_t *pmd; + unsigned long addr, next; + int ret; + + addr = start; + do { + pud = pud_offset(pgd, addr); + + if (pud_none_or_clear_bad(pud)) { + pmd = pmd_alloc_one(NULL, addr); + if (!pmd) { + kvm_err("Cannot allocate Hyp pmd\n"); + return -ENOMEM; + } + pud_populate(NULL, pud, pmd); + get_page(virt_to_page(pud)); + kvm_flush_dcache_to_poc(pud, sizeof(*pud)); + } + + next = pud_addr_end(addr, end); + ret = create_hyp_pmd_mappings(pud, addr, next, pfn, prot); + if (ret) + return ret; + pfn += (next - addr) >> PAGE_SHIFT; + } while (addr = next, addr != end); + + return 0; +} + static int __create_hyp_mappings(pgd_t *pgdp, unsigned long start, unsigned long end, unsigned long pfn, pgprot_t prot) { pgd_t *pgd; pud_t *pud; - pmd_t *pmd; unsigned long addr, next; int err = 0; @@ -416,22 +449,21 @@ static int __create_hyp_mappings(pgd_t *pgdp, end = PAGE_ALIGN(end); do { pgd = pgdp + pgd_index(addr); - pud = pud_offset(pgd, addr); - if (pud_none_or_clear_bad(pud)) { - pmd = pmd_alloc_one(NULL, addr); - if (!pmd) { - kvm_err("Cannot allocate Hyp pmd\n"); + if (pgd_none(*pgd)) { + pud = pud_alloc_one(NULL, addr); + if (!pud) { + kvm_err("Cannot allocate Hyp pud\n"); err = -ENOMEM; goto out; } - pud_populate(NULL, pud, pmd); - get_page(virt_to_page(pud)); - kvm_flush_dcache_to_poc(pud, sizeof(*pud)); + pgd_populate(NULL, pgd, pud); + get_page(virt_to_page(pgd)); + kvm_flush_dcache_to_poc(pgd, sizeof(*pgd)); } next = pgd_addr_end(addr, end); - err = create_hyp_pmd_mappings(pud, addr, next, pfn, prot); + err = create_hyp_pud_mappings(pgd, addr, next, pfn, prot); if (err) goto out; pfn += (next - addr) >> PAGE_SHIFT; @@ -521,6 +553,7 @@ 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; if (kvm->arch.pgd != NULL) { @@ -528,14 +561,38 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) return -EINVAL; } - pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER); + if (KVM_PREALLOC_LEVEL > 0) { + /* + * Allocate fake pgd for the page table manipulation macros to + * work. This is not used by the hardware and we have no + * alignment requirement for this allocation. + */ + pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), + GFP_KERNEL | __GFP_ZERO); + } 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); + } + 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; } /** @@ -571,19 +628,39 @@ void kvm_free_stage2_pgd(struct kvm *kvm) return; unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); - free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER); + kvm_free_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; } -static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, +static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, phys_addr_t addr) { pgd_t *pgd; pud_t *pud; - pmd_t *pmd; pgd = kvm->arch.pgd + pgd_index(addr); - pud = pud_offset(pgd, addr); + if (WARN_ON(pgd_none(*pgd))) { + if (!cache) + return NULL; + pud = mmu_memory_cache_alloc(cache); + pgd_populate(NULL, pgd, pud); + get_page(virt_to_page(pgd)); + } + + return pud_offset(pgd, addr); +} + +static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr) +{ + pud_t *pud; + pmd_t *pmd; + + pud = stage2_get_pud(kvm, cache, addr); if (pud_none(*pud)) { if (!cache) return NULL; @@ -629,7 +706,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, pmd_t *pmd; pte_t *pte, old_pte; - /* Create stage-2 page table mapping - Level 1 */ + /* Create stage-2 page table mapping - Levels 0 and 1 */ pmd = stage2_get_pmd(kvm, cache, addr); if (!pmd) { /* @@ -690,7 +767,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, if (writable) kvm_set_s2pte_writable(&pte); - ret = mmu_topup_memory_cache(&cache, 2, 2); + ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES, + KVM_NR_MEM_OBJS); if (ret) goto out; spin_lock(&kvm->mmu_lock); @@ -805,7 +883,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, up_read(¤t->mm->mmap_sem); /* We need minimum second+third level pages */ - ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS); + ret = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES, + KVM_NR_MEM_OBJS); if (ret) return ret; @@ -1080,8 +1159,8 @@ int kvm_mmu_init(void) (unsigned long)phys_base); } - hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order); - boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order); + hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order); + boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order); if (!hyp_pgd || !boot_hyp_pgd) { kvm_err("Hyp mode PGD not allocated\n"); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index e36171974d6a..0caf7a59f6a1 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -41,6 +41,18 @@ */ #define TRAMPOLINE_VA (HYP_PAGE_OFFSET_MASK & PAGE_MASK) +/* + * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation + * levels in addition to the PGD and potentially the PUD which are + * pre-allocated (we pre-allocate the fake PGD and the PUD when the Stage-2 + * tables use one level of tables less than the kernel. + */ +#ifdef CONFIG_ARM64_64K_PAGES +#define KVM_MMU_CACHE_MIN_PAGES 1 +#else +#define KVM_MMU_CACHE_MIN_PAGES 2 +#endif + #ifdef __ASSEMBLY__ /* @@ -53,6 +65,7 @@ #else +#include #include #include @@ -65,10 +78,6 @@ #define KVM_PHYS_SIZE (1UL << KVM_PHYS_SHIFT) #define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1UL) -/* Make sure we get the right size, and thus the right alignment */ -#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - PGDIR_SHIFT)) -#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) - int create_hyp_mappings(void *from, void *to); int create_hyp_io_mappings(void *from, void *to, phys_addr_t); void free_boot_hyp_pgd(void); @@ -93,6 +102,7 @@ void kvm_clear_hyp_idmap(void); #define kvm_set_pmd(pmdp, pmd) set_pmd(pmdp, pmd) static inline void kvm_clean_pgd(pgd_t *pgd) {} +static inline void kvm_clean_pmd(pmd_t *pmd) {} static inline void kvm_clean_pmd_entry(pmd_t *pmd) {} static inline void kvm_clean_pte(pte_t *pte) {} static inline void kvm_clean_pte_entry(pte_t *pte) {} @@ -111,19 +121,116 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) #define kvm_pud_addr_end(addr, end) pud_addr_end(addr, end) #define kvm_pmd_addr_end(addr, end) pmd_addr_end(addr, end) +/* + * In the case where PGDIR_SHIFT is larger than KVM_PHYS_SHIFT, we can address + * the entire IPA input range with a single pgd entry, and we would only need + * one pgd entry. Note that in this case, the pgd is actually not used by + * the MMU for Stage-2 translations, but is merely a fake pgd used as a data + * structure for the kernel pgtable macros to work. + */ +#if PGDIR_SHIFT > KVM_PHYS_SHIFT +#define PTRS_PER_S2_PGD_SHIFT 0 +#else +#define PTRS_PER_S2_PGD_SHIFT (KVM_PHYS_SHIFT - PGDIR_SHIFT) +#endif +#define PTRS_PER_S2_PGD (1 << PTRS_PER_S2_PGD_SHIFT) +#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) + +/* + * If we are concatenating first level stage-2 page tables, we would have less + * than or equal to 16 pointers in the fake PGD, because that's what the + * architecture allows. In this case, (4 - CONFIG_ARM64_PGTABLE_LEVELS) + * represents the first level for the host, and we add 1 to go to the next + * level (which uses contatenation) for the stage-2 tables. + */ +#if PTRS_PER_S2_PGD <= 16 +#define KVM_PREALLOC_LEVEL (4 - CONFIG_ARM64_PGTABLE_LEVELS + 1) +#else +#define KVM_PREALLOC_LEVEL (0) +#endif + +/** + * kvm_prealloc_hwpgd - allocate inital table for VTTBR + * @kvm: The KVM struct pointer for the VM. + * @pgd: The kernel pseudo pgd + * + * 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. + */ +static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd) +{ + unsigned int i; + unsigned long hwpgd; + + if (KVM_PREALLOC_LEVEL == 0) + return 0; + + hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT); + if (!hwpgd) + return -ENOMEM; + + 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); + } + + return 0; +} + +static inline void *kvm_get_hwpgd(struct kvm *kvm) +{ + pgd_t *pgd = kvm->arch.pgd; + pud_t *pud; + + if (KVM_PREALLOC_LEVEL == 0) + return pgd; + + pud = pud_offset(pgd, 0); + if (KVM_PREALLOC_LEVEL == 1) + return pud; + + BUG_ON(KVM_PREALLOC_LEVEL != 2); + return pmd_offset(pud, 0); +} + +static inline void kvm_free_hwpgd(struct kvm *kvm) +{ + if (KVM_PREALLOC_LEVEL > 0) { + unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm); + free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT); + } +} + 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(ptep) kvm_page_empty(ptep) -#ifndef CONFIG_ARM64_64K_PAGES -#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp) +#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) + +#ifdef __PAGETABLE_PMD_FOLDED +#define kvm_pmd_table_empty(kvm, pmdp) (0) +#else +#define kvm_pmd_table_empty(kvm, pmdp) \ + (kvm_page_empty(pmdp) && (!(kvm) || KVM_PREALLOC_LEVEL < 2)) +#endif + +#ifdef __PAGETABLE_PUD_FOLDED +#define kvm_pud_table_empty(kvm, pudp) (0) #else -#define kvm_pmd_table_empty(pmdp) (0) +#define kvm_pud_table_empty(kvm, pudp) \ + (kvm_page_empty(pudp) && (!(kvm) || KVM_PREALLOC_LEVEL < 1)) #endif -#define kvm_pud_table_empty(pudp) (0) struct kvm; -- cgit v1.2.3 From 2df36a5dd6792870bef48f63bfca42055ea5b79c Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Sun, 28 Sep 2014 16:04:26 +0200 Subject: arm/arm64: KVM: Fix BE accesses to GICv2 EISR and ELRSR regs The EIRSR and ELRSR registers are 32-bit registers on GICv2, and we store these as an array of two such registers on the vgic vcpu struct. However, we access them as a single 64-bit value or as a bitmap pointer in the generic vgic code, which breaks BE support. Instead, store them as u64 values on the vgic structure and do the word-swapping in the assembly code, which already handles the byte order for BE systems. Tested-by: Victor Kamensky Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- arch/arm/kvm/interrupts_head.S | 7 +++++++ arch/arm64/kvm/vgic-v2-switch.S | 12 ++++++++---- include/kvm/arm_vgic.h | 4 ++-- virt/kvm/arm/vgic-v2.c | 24 +++--------------------- virt/kvm/arm/vgic.c | 18 ++++++++++++++++-- 5 files changed, 36 insertions(+), 29 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 98c8c5b9a87f..14d488388480 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -433,10 +433,17 @@ ARM_BE8(rev r10, r10 ) str r3, [r11, #VGIC_V2_CPU_HCR] str r4, [r11, #VGIC_V2_CPU_VMCR] str r5, [r11, #VGIC_V2_CPU_MISR] +#ifdef CONFIG_CPU_ENDIAN_BE8 + str r6, [r11, #(VGIC_V2_CPU_EISR + 4)] + str r7, [r11, #VGIC_V2_CPU_EISR] + str r8, [r11, #(VGIC_V2_CPU_ELRSR + 4)] + str r9, [r11, #VGIC_V2_CPU_ELRSR] +#else str r6, [r11, #VGIC_V2_CPU_EISR] str r7, [r11, #(VGIC_V2_CPU_EISR + 4)] str r8, [r11, #VGIC_V2_CPU_ELRSR] str r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)] +#endif str r10, [r11, #VGIC_V2_CPU_APR] /* Clear GICH_HCR */ diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S index ae211772f991..f002fe1c3700 100644 --- a/arch/arm64/kvm/vgic-v2-switch.S +++ b/arch/arm64/kvm/vgic-v2-switch.S @@ -67,10 +67,14 @@ CPU_BE( rev w11, w11 ) str w4, [x3, #VGIC_V2_CPU_HCR] str w5, [x3, #VGIC_V2_CPU_VMCR] str w6, [x3, #VGIC_V2_CPU_MISR] - str w7, [x3, #VGIC_V2_CPU_EISR] - str w8, [x3, #(VGIC_V2_CPU_EISR + 4)] - str w9, [x3, #VGIC_V2_CPU_ELRSR] - str w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)] +CPU_LE( str w7, [x3, #VGIC_V2_CPU_EISR] ) +CPU_LE( str w8, [x3, #(VGIC_V2_CPU_EISR + 4)] ) +CPU_LE( str w9, [x3, #VGIC_V2_CPU_ELRSR] ) +CPU_LE( str w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)] ) +CPU_BE( str w7, [x3, #(VGIC_V2_CPU_EISR + 4)] ) +CPU_BE( str w8, [x3, #VGIC_V2_CPU_EISR] ) +CPU_BE( str w9, [x3, #(VGIC_V2_CPU_ELRSR + 4)] ) +CPU_BE( str w10, [x3, #VGIC_V2_CPU_ELRSR] ) str w11, [x3, #VGIC_V2_CPU_APR] /* Clear GICH_HCR */ diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index ec559d3264cc..206dcc3b3f7a 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -219,8 +219,8 @@ struct vgic_v2_cpu_if { u32 vgic_hcr; u32 vgic_vmcr; u32 vgic_misr; /* Saved only */ - u32 vgic_eisr[2]; /* Saved only */ - u32 vgic_elrsr[2]; /* Saved only */ + u64 vgic_eisr; /* Saved only */ + u64 vgic_elrsr; /* Saved only */ u32 vgic_apr; u32 vgic_lr[VGIC_V2_MAX_LRS]; }; diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c index 01124ef3690a..2935405ad22f 100644 --- a/virt/kvm/arm/vgic-v2.c +++ b/virt/kvm/arm/vgic-v2.c @@ -71,35 +71,17 @@ static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc) { if (!(lr_desc.state & LR_STATE_MASK)) - set_bit(lr, (unsigned long *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr); + vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr); } static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu) { - u64 val; - -#if BITS_PER_LONG == 64 - val = vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[1]; - val <<= 32; - val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[0]; -#else - val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr; -#endif - return val; + return vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr; } static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu) { - u64 val; - -#if BITS_PER_LONG == 64 - val = vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[1]; - val <<= 32; - val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[0]; -#else - val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr; -#endif - return val; + return vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr; } static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu) diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 382fb5a88b9c..3aaca49de325 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -145,6 +145,20 @@ static void vgic_free_bitmap(struct vgic_bitmap *b) b->shared = NULL; } +/* + * Call this function to convert a u64 value to an unsigned long * bitmask + * in a way that works on both 32-bit and 64-bit LE and BE platforms. + * + * Warning: Calling this function may modify *val. + */ +static unsigned long *u64_to_bitmask(u64 *val) +{ +#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 32 + *val = (*val >> 32) | (*val << 32); +#endif + return (unsigned long *)val; +} + static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, int cpuid, u32 offset) { @@ -1442,7 +1456,7 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) * active bit. */ u64 eisr = vgic_get_eisr(vcpu); - unsigned long *eisr_ptr = (unsigned long *)&eisr; + unsigned long *eisr_ptr = u64_to_bitmask(&eisr); int lr; for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) { @@ -1505,7 +1519,7 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) level_pending = vgic_process_maintenance(vcpu); elrsr = vgic_get_elrsr(vcpu); - elrsr_ptr = (unsigned long *)&elrsr; + elrsr_ptr = u64_to_bitmask(&elrsr); /* Clear mappings for empty LRs */ for_each_set_bit(lr, elrsr_ptr, vgic->nr_lr) { -- cgit v1.2.3