From a987370f8e7a1677ae385042644326d9cd145a20 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 10 Mar 2015 19:06:59 +0000 Subject: [PATCH] arm64: KVM: Fix stage-2 PGD allocation to have per-page refcounting We're using __get_free_pages with to allocate the guest's stage-2 PGD. The standard behaviour of this function is to return a set of pages where only the head page has a valid refcount. This behaviour gets us into trouble when we're trying to increment the refcount on a non-head page: page:ffff7c00cfb693c0 count:0 mapcount:0 mapping: (null) index:0x0 flags: 0x4000000000000000() page dumped because: VM_BUG_ON_PAGE((*({ __attribute__((unused)) typeof((&page->_count)->counter) __var = ( typeof((&page->_count)->counter)) 0; (volatile typeof((&page->_count)->counter) *)&((&page->_count)->counter); })) <= 0) BUG: failure at include/linux/mm.h:548/get_page()! Kernel panic - not syncing: BUG! CPU: 1 PID: 1695 Comm: kvm-vcpu-0 Not tainted 4.0.0-rc1+ #3825 Hardware name: APM X-Gene Mustang board (DT) Call trace: [] dump_backtrace+0x0/0x13c [] show_stack+0x10/0x1c [] dump_stack+0x74/0x94 [] panic+0x100/0x240 [] stage2_get_pmd+0x17c/0x2bc [] kvm_handle_guest_abort+0x4b4/0x6b0 [] handle_exit+0x58/0x180 [] kvm_arch_vcpu_ioctl_run+0x114/0x45c [] kvm_vcpu_ioctl+0x2e0/0x754 [] do_vfs_ioctl+0x424/0x5c8 [] SyS_ioctl+0x40/0x78 CPU0: stopping A possible approach for this is to split the compound page using split_page() at allocation time, and change the teardown path to free one page at a time. It turns out that alloc_pages_exact() and free_pages_exact() does exactly that. While we're at it, the PGD allocation code is reworked to reduce duplication. This has been tested on an X-Gene platform with a 4kB/48bit-VA host kernel, and kvmtool hacked to place memory in the second page of the hardware PGD (PUD for the host kernel). Also regression-tested on a Cubietruck (Cortex-A7). [ Reworked to use alloc_pages_exact() and free_pages_exact() and to return pointers directly instead of by reference as arguments - Christoffer ] Reported-by: Mark Rutland Signed-off-by: Marc Zyngier Signed-off-by: Christoffer Dall --- arch/arm/include/asm/kvm_mmu.h | 12 +++--- arch/arm/kvm/mmu.c | 67 +++++++++++++++++++++++--------- arch/arm64/include/asm/kvm_mmu.h | 46 ++-------------------- 3 files changed, 58 insertions(+), 67 deletions(-) diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index bf0fe99e8ca9..c57c41dc7e87 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -162,18 +162,16 @@ static inline bool kvm_page_empty(void *ptr) #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; } +static inline unsigned int kvm_get_hwpgd_size(void) +{ + return PTRS_PER_S2_PGD * sizeof(pgd_t); +} + struct kvm; #define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l)) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 3e6859bc3e11..a48a73c6b866 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -632,6 +632,20 @@ 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. @@ -645,15 +659,31 @@ 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 @@ -661,30 +691,32 @@ 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; } /** @@ -785,11 +817,10 @@ 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; } diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 6458b5373142..a099cd9cdef8 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -171,43 +171,6 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) #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; @@ -224,12 +187,11 @@ static inline void *kvm_get_hwpgd(struct kvm *kvm) return pmd_offset(pud, 0); } -static inline void kvm_free_hwpgd(struct kvm *kvm) +static inline unsigned int kvm_get_hwpgd_size(void) { - if (KVM_PREALLOC_LEVEL > 0) { - unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm); - free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT); - } + if (KVM_PREALLOC_LEVEL > 0) + return PTRS_PER_S2_PGD * PAGE_SIZE; + return PTRS_PER_S2_PGD * sizeof(pgd_t); } static inline bool kvm_page_empty(void *ptr)