diff options
38 files changed, 1111 insertions, 554 deletions
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 9bb9d11750d7..c4dabba9cfdf 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -657,7 +657,8 @@ static inline bool system_supports_4kb_granule(void) val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN4_SHIFT); - return val == ID_AA64MMFR0_TGRAN4_SUPPORTED; + return (val >= ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN) && + (val <= ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX); } static inline bool system_supports_64kb_granule(void) @@ -669,7 +670,8 @@ static inline bool system_supports_64kb_granule(void) val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN64_SHIFT); - return val == ID_AA64MMFR0_TGRAN64_SUPPORTED; + return (val >= ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN) && + (val <= ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX); } static inline bool system_supports_16kb_granule(void) @@ -681,7 +683,8 @@ static inline bool system_supports_16kb_granule(void) val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN16_SHIFT); - return val == ID_AA64MMFR0_TGRAN16_SUPPORTED; + return (val >= ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN) && + (val <= ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX); } static inline bool system_supports_mixed_endian_el0(void) @@ -781,13 +784,13 @@ extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) { switch (parange) { - case 0: return 32; - case 1: return 36; - case 2: return 40; - case 3: return 42; - case 4: return 44; - case 5: return 48; - case 6: return 52; + case ID_AA64MMFR0_PARANGE_32: return 32; + case ID_AA64MMFR0_PARANGE_36: return 36; + case ID_AA64MMFR0_PARANGE_40: return 40; + case ID_AA64MMFR0_PARANGE_42: return 42; + case ID_AA64MMFR0_PARANGE_44: return 44; + case ID_AA64MMFR0_PARANGE_48: return 48; + case ID_AA64MMFR0_PARANGE_52: return 52; /* * A future PE could use a value unknown to the kernel. * However, by the "D10.1.4 Principles of the ID scheme diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 9f0bf2109be7..aed2aa61766a 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -59,12 +59,11 @@ #define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs 13 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs 14 #define __KVM_HOST_SMCCC_FUNC___pkvm_init 15 -#define __KVM_HOST_SMCCC_FUNC___pkvm_create_mappings 16 +#define __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp 16 #define __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping 17 #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19 -#define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20 -#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 21 +#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 20 #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 41911585ae0c..bdab1754c71f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -66,7 +66,7 @@ DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); extern unsigned int kvm_sve_max_vl; int kvm_arm_init_sve(void); -int __attribute_const__ kvm_target_cpu(void); +u32 __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu); @@ -185,7 +185,6 @@ enum vcpu_sysreg { PMCNTENSET_EL0, /* Count Enable Set Register */ PMINTENSET_EL1, /* Interrupt Enable Set Register */ PMOVSSET_EL0, /* Overflow Flag Status Set Register */ - PMSWINC_EL0, /* Software Increment Register */ PMUSERENR_EL0, /* User Enable Register */ /* Pointer Authentication Registers in a strict increasing order. */ @@ -576,6 +575,7 @@ struct kvm_vcpu_stat { u64 wfi_exit_stat; u64 mmio_exit_user; u64 mmio_exit_kernel; + u64 signal_exits; u64 exits; }; diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index f004c0115d89..027783829584 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -25,6 +25,46 @@ static inline u64 kvm_get_parange(u64 mmfr0) typedef u64 kvm_pte_t; +#define KVM_PTE_VALID BIT(0) + +#define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT) +#define KVM_PTE_ADDR_51_48 GENMASK(15, 12) + +static inline bool kvm_pte_valid(kvm_pte_t pte) +{ + return pte & KVM_PTE_VALID; +} + +static inline u64 kvm_pte_to_phys(kvm_pte_t pte) +{ + u64 pa = pte & KVM_PTE_ADDR_MASK; + + if (PAGE_SHIFT == 16) + pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48; + + return pa; +} + +static inline u64 kvm_granule_shift(u32 level) +{ + /* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */ + return ARM64_HW_PGTABLE_LEVEL_SHIFT(level); +} + +static inline u64 kvm_granule_size(u32 level) +{ + return BIT(kvm_granule_shift(level)); +} + +static inline bool kvm_level_supports_block_mapping(u32 level) +{ + /* + * Reject invalid block mappings and don't bother with 4TB mappings for + * 52-bit PAs. + */ + return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1)); +} + /** * struct kvm_pgtable_mm_ops - Memory management callbacks. * @zalloc_page: Allocate a single zeroed memory page. @@ -76,30 +116,15 @@ enum kvm_pgtable_stage2_flags { }; /** - * struct kvm_pgtable - KVM page-table. - * @ia_bits: Maximum input address size, in bits. - * @start_level: Level at which the page-table walk starts. - * @pgd: Pointer to the first top-level entry of the page-table. - * @mm_ops: Memory management callbacks. - * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables. - */ -struct kvm_pgtable { - u32 ia_bits; - u32 start_level; - kvm_pte_t *pgd; - struct kvm_pgtable_mm_ops *mm_ops; - - /* Stage-2 only */ - struct kvm_s2_mmu *mmu; - enum kvm_pgtable_stage2_flags flags; -}; - -/** * enum kvm_pgtable_prot - Page-table permissions and attributes. * @KVM_PGTABLE_PROT_X: Execute permission. * @KVM_PGTABLE_PROT_W: Write permission. * @KVM_PGTABLE_PROT_R: Read permission. * @KVM_PGTABLE_PROT_DEVICE: Device attributes. + * @KVM_PGTABLE_PROT_SW0: Software bit 0. + * @KVM_PGTABLE_PROT_SW1: Software bit 1. + * @KVM_PGTABLE_PROT_SW2: Software bit 2. + * @KVM_PGTABLE_PROT_SW3: Software bit 3. */ enum kvm_pgtable_prot { KVM_PGTABLE_PROT_X = BIT(0), @@ -107,21 +132,48 @@ enum kvm_pgtable_prot { KVM_PGTABLE_PROT_R = BIT(2), KVM_PGTABLE_PROT_DEVICE = BIT(3), + + KVM_PGTABLE_PROT_SW0 = BIT(55), + KVM_PGTABLE_PROT_SW1 = BIT(56), + KVM_PGTABLE_PROT_SW2 = BIT(57), + KVM_PGTABLE_PROT_SW3 = BIT(58), }; -#define PAGE_HYP (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W) +#define KVM_PGTABLE_PROT_RW (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W) +#define KVM_PGTABLE_PROT_RWX (KVM_PGTABLE_PROT_RW | KVM_PGTABLE_PROT_X) + +#define PKVM_HOST_MEM_PROT KVM_PGTABLE_PROT_RWX +#define PKVM_HOST_MMIO_PROT KVM_PGTABLE_PROT_RW + +#define PAGE_HYP KVM_PGTABLE_PROT_RW #define PAGE_HYP_EXEC (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_X) #define PAGE_HYP_RO (KVM_PGTABLE_PROT_R) #define PAGE_HYP_DEVICE (PAGE_HYP | KVM_PGTABLE_PROT_DEVICE) +typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end, + enum kvm_pgtable_prot prot); + /** - * struct kvm_mem_range - Range of Intermediate Physical Addresses - * @start: Start of the range. - * @end: End of the range. + * struct kvm_pgtable - KVM page-table. + * @ia_bits: Maximum input address size, in bits. + * @start_level: Level at which the page-table walk starts. + * @pgd: Pointer to the first top-level entry of the page-table. + * @mm_ops: Memory management callbacks. + * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables. + * @flags: Stage-2 page-table flags. + * @force_pte_cb: Function that returns true if page level mappings must + * be used instead of block mappings. */ -struct kvm_mem_range { - u64 start; - u64 end; +struct kvm_pgtable { + u32 ia_bits; + u32 start_level; + kvm_pte_t *pgd; + struct kvm_pgtable_mm_ops *mm_ops; + + /* Stage-2 only */ + struct kvm_s2_mmu *mmu; + enum kvm_pgtable_stage2_flags flags; + kvm_pgtable_force_pte_cb_t force_pte_cb; }; /** @@ -216,21 +268,24 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift); /** - * kvm_pgtable_stage2_init_flags() - Initialise a guest stage-2 page-table. + * __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table. * @pgt: Uninitialised page-table structure to initialise. * @arch: Arch-specific KVM structure representing the guest virtual * machine. * @mm_ops: Memory management callbacks. * @flags: Stage-2 configuration flags. + * @force_pte_cb: Function that returns true if page level mappings must + * be used instead of block mappings. * * Return: 0 on success, negative error code on failure. */ -int kvm_pgtable_stage2_init_flags(struct kvm_pgtable *pgt, struct kvm_arch *arch, - struct kvm_pgtable_mm_ops *mm_ops, - enum kvm_pgtable_stage2_flags flags); +int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_arch *arch, + struct kvm_pgtable_mm_ops *mm_ops, + enum kvm_pgtable_stage2_flags flags, + kvm_pgtable_force_pte_cb_t force_pte_cb); #define kvm_pgtable_stage2_init(pgt, arch, mm_ops) \ - kvm_pgtable_stage2_init_flags(pgt, arch, mm_ops, 0) + __kvm_pgtable_stage2_init(pgt, arch, mm_ops, 0, NULL) /** * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table. @@ -374,7 +429,8 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr); * If there is a valid, leaf page-table entry used to translate @addr, then * relax the permissions in that entry according to the read, write and * execute permissions specified by @prot. No permissions are removed, and - * TLB invalidation is performed after updating the entry. + * TLB invalidation is performed after updating the entry. Software bits cannot + * be set or cleared using kvm_pgtable_stage2_relax_perms(). * * Return: 0 on success, negative error code on failure. */ @@ -433,22 +489,42 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker); /** - * kvm_pgtable_stage2_find_range() - Find a range of Intermediate Physical - * Addresses with compatible permission - * attributes. - * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). - * @addr: Address that must be covered by the range. - * @prot: Protection attributes that the range must be compatible with. - * @range: Range structure used to limit the search space at call time and - * that will hold the result. + * kvm_pgtable_get_leaf() - Walk a page-table and retrieve the leaf entry + * with its level. + * @pgt: Page-table structure initialised by kvm_pgtable_*_init() + * or a similar initialiser. + * @addr: Input address for the start of the walk. + * @ptep: Pointer to storage for the retrieved PTE. + * @level: Pointer to storage for the level of the retrieved PTE. + * + * The offset of @addr within a page is ignored. * - * The offset of @addr within a page is ignored. An IPA is compatible with @prot - * iff its corresponding stage-2 page-table entry has default ownership and, if - * valid, is mapped with protection attributes identical to @prot. + * The walker will walk the page-table entries corresponding to the input + * address specified, retrieving the leaf corresponding to this address. + * Invalid entries are treated as leaf entries. * * Return: 0 on success, negative error code on failure. */ -int kvm_pgtable_stage2_find_range(struct kvm_pgtable *pgt, u64 addr, - enum kvm_pgtable_prot prot, - struct kvm_mem_range *range); +int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, + kvm_pte_t *ptep, u32 *level); + +/** + * kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a + * stage-2 Page-Table Entry. + * @pte: Page-table entry + * + * Return: protection attributes of the page-table entry in the enum + * kvm_pgtable_prot format. + */ +enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte); + +/** + * kvm_pgtable_hyp_pte_prot() - Retrieve the protection attributes of a stage-1 + * Page-Table Entry. + * @pte: Page-table entry + * + * Return: protection attributes of the page-table entry in the enum + * kvm_pgtable_prot format. + */ +enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte); #endif /* __ARM64_KVM_PGTABLE_H__ */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 7b9c3acba684..2084b22613e2 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -847,15 +847,26 @@ #define ID_AA64MMFR0_ASID_SHIFT 4 #define ID_AA64MMFR0_PARANGE_SHIFT 0 -#define ID_AA64MMFR0_TGRAN4_NI 0xf -#define ID_AA64MMFR0_TGRAN4_SUPPORTED 0x0 -#define ID_AA64MMFR0_TGRAN64_NI 0xf -#define ID_AA64MMFR0_TGRAN64_SUPPORTED 0x0 -#define ID_AA64MMFR0_TGRAN16_NI 0x0 -#define ID_AA64MMFR0_TGRAN16_SUPPORTED 0x1 +#define ID_AA64MMFR0_TGRAN4_NI 0xf +#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN 0x0 +#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_TGRAN64_NI 0xf +#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN 0x0 +#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_TGRAN16_NI 0x0 +#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN 0x1 +#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX 0xf + +#define ID_AA64MMFR0_PARANGE_32 0x0 +#define ID_AA64MMFR0_PARANGE_36 0x1 +#define ID_AA64MMFR0_PARANGE_40 0x2 +#define ID_AA64MMFR0_PARANGE_42 0x3 +#define ID_AA64MMFR0_PARANGE_44 0x4 #define ID_AA64MMFR0_PARANGE_48 0x5 #define ID_AA64MMFR0_PARANGE_52 0x6 +#define ARM64_MIN_PARANGE_BITS 32 + #define ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT 0x0 #define ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE 0x1 #define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN 0x2 @@ -1028,16 +1039,19 @@ #if defined(CONFIG_ARM64_4K_PAGES) #define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX +#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN4_2_SHIFT #elif defined(CONFIG_ARM64_16K_PAGES) #define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0xF +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX +#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN16_2_SHIFT #elif defined(CONFIG_ARM64_64K_PAGES) #define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX +#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN64_2_SHIFT #endif #define MVFR2_FPMISC_SHIFT 4 diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 709d2c433c5e..f6b1a88245db 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -181,6 +181,8 @@ SECTIONS /* everything from this point to __init_begin will be marked RO NX */ RO_DATA(PAGE_SIZE) + HYPERVISOR_DATA_SECTIONS + idmap_pg_dir = .; . += IDMAP_DIR_SIZE; idmap_pg_end = .; @@ -260,8 +262,6 @@ SECTIONS _sdata = .; RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN) - HYPERVISOR_DATA_SECTIONS - /* * Data written with the MMU off but read with the MMU on requires * cache lines to be invalidated, discarding up to a Cache Writeback diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index a4eba0908bfa..d7eec0b43744 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -26,6 +26,7 @@ menuconfig KVM select HAVE_KVM_ARCH_TLB_FLUSH_ALL select KVM_MMIO select KVM_GENERIC_DIRTYLOG_READ_PROTECT + select KVM_XFER_TO_GUEST_WORK select SRCU select KVM_VFIO select HAVE_KVM_EVENTFD @@ -46,6 +47,15 @@ if KVM source "virt/kvm/Kconfig" +config NVHE_EL2_DEBUG + bool "Debug mode for non-VHE EL2 object" + help + Say Y here to enable the debug mode for the non-VHE KVM EL2 object. + Failure reports will BUG() in the hypervisor. This is intended for + local EL2 hypervisor development. + + If unsure, say N. + endif # KVM endif # VIRTUALIZATION diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 658f76067f46..9ebb99e22ab2 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -6,6 +6,7 @@ #include <linux/bug.h> #include <linux/cpu_pm.h> +#include <linux/entry-kvm.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> @@ -15,6 +16,7 @@ #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> +#include <linux/kmemleak.h> #include <linux/kvm.h> #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> @@ -42,10 +44,6 @@ #include <kvm/arm_pmu.h> #include <kvm/arm_psci.h> -#ifdef REQUIRES_VIRT -__asm__(".arch_extension virt"); -#endif - static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT; DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); @@ -94,10 +92,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, kvm->arch.return_nisv_io_abort_to_user = true; break; case KVM_CAP_ARM_MTE: - if (!system_supports_mte() || kvm->created_vcpus) - return -EINVAL; - r = 0; - kvm->arch.mte_enabled = true; + mutex_lock(&kvm->lock); + if (!system_supports_mte() || kvm->created_vcpus) { + r = -EINVAL; + } else { + r = 0; + kvm->arch.mte_enabled = true; + } + mutex_unlock(&kvm->lock); break; default: r = -EINVAL; @@ -715,6 +717,45 @@ static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu) } /** + * kvm_vcpu_exit_request - returns true if the VCPU should *not* enter the guest + * @vcpu: The VCPU pointer + * @ret: Pointer to write optional return code + * + * Returns: true if the VCPU needs to return to a preemptible + interruptible + * and skip guest entry. + * + * This function disambiguates between two different types of exits: exits to a + * preemptible + interruptible kernel context and exits to userspace. For an + * exit to userspace, this function will write the return code to ret and return + * true. For an exit to preemptible + interruptible kernel context (i.e. check + * for pending work and re-enter), return true without writing to ret. + */ +static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret) +{ + struct kvm_run *run = vcpu->run; + + /* + * If we're using a userspace irqchip, then check if we need + * to tell a userspace irqchip about timer or PMU level + * changes and if so, exit to userspace (the actual level + * state gets updated in kvm_timer_update_run and + * kvm_pmu_update_run below). + */ + if (static_branch_unlikely(&userspace_irqchip_in_use)) { + if (kvm_timer_should_notify_user(vcpu) || + kvm_pmu_should_notify_user(vcpu)) { + *ret = -EINTR; + run->exit_reason = KVM_EXIT_INTR; + return true; + } + } + + return kvm_request_pending(vcpu) || + need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) || + xfer_to_guest_mode_work_pending(); +} + +/** * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code * @vcpu: The VCPU pointer * @@ -757,7 +798,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) /* * Check conditions before entering the guest */ - cond_resched(); + ret = xfer_to_guest_mode_handle_work(vcpu); + if (!ret) + ret = 1; update_vmid(&vcpu->arch.hw_mmu->vmid); @@ -777,30 +820,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_vgic_flush_hwstate(vcpu); /* - * Exit if we have a signal pending so that we can deliver the - * signal to user space. - */ - if (signal_pending(current)) { - ret = -EINTR; - run->exit_reason = KVM_EXIT_INTR; - } - - /* - * If we're using a userspace irqchip, then check if we need - * to tell a userspace irqchip about timer or PMU level - * changes and if so, exit to userspace (the actual level - * state gets updated in kvm_timer_update_run and - * kvm_pmu_update_run below). - */ - if (static_branch_unlikely(&userspace_irqchip_in_use)) { - if (kvm_timer_should_notify_user(vcpu) || - kvm_pmu_should_notify_user(vcpu)) { - ret = -EINTR; - run->exit_reason = KVM_EXIT_INTR; - } - } - - /* * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and @@ -808,8 +827,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); - if (ret <= 0 || need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) || - kvm_request_pending(vcpu)) { + if (ret <= 0 || kvm_vcpu_exit_request(vcpu, &ret)) { vcpu->mode = OUTSIDE_GUEST_MODE; isb(); /* Ensure work in x_flush_hwstate is committed */ kvm_pmu_sync_hwstate(vcpu); @@ -1035,7 +1053,7 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { unsigned int i, ret; - int phys_target = kvm_target_cpu(); + u32 phys_target = kvm_target_cpu(); if (init->target != phys_target) return -EINVAL; @@ -1215,6 +1233,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(®, argp, sizeof(reg))) break; + /* + * We could owe a reset due to PSCI. Handle the pending reset + * here to ensure userspace register accesses are ordered after + * the reset. + */ + if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) + kvm_reset_vcpu(vcpu); + if (ioctl == KVM_SET_ONE_REG) r = kvm_arm_set_reg(vcpu, ®); else @@ -1696,11 +1722,6 @@ static bool init_psci_relay(void) return true; } -static int init_common_resources(void) -{ - return kvm_set_ipa_limit(); -} - static int init_subsystems(void) { int err = 0; @@ -1954,56 +1975,17 @@ static void _kvm_host_prot_finalize(void *discard) WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize)); } -static inline int pkvm_mark_hyp(phys_addr_t start, phys_addr_t end) -{ - return kvm_call_hyp_nvhe(__pkvm_mark_hyp, start, end); -} - -#define pkvm_mark_hyp_section(__section) \ - pkvm_mark_hyp(__pa_symbol(__section##_start), \ - __pa_symbol(__section##_end)) - static int finalize_hyp_mode(void) { - int cpu, ret; - if (!is_protected_kvm_enabled()) return 0; - ret = pkvm_mark_hyp_section(__hyp_idmap_text); - if (ret) - return ret; - - ret = pkvm_mark_hyp_section(__hyp_text); - if (ret) - return ret; - - ret = pkvm_mark_hyp_section(__hyp_rodata); - if (ret) - return ret; - - ret = pkvm_mark_hyp_section(__hyp_bss); - if (ret) - return ret; - - ret = pkvm_mark_hyp(hyp_mem_base, hyp_mem_base + hyp_mem_size); - if (ret) - return ret; - - for_each_possible_cpu(cpu) { - phys_addr_t start = virt_to_phys((void *)kvm_arm_hyp_percpu_base[cpu]); - phys_addr_t end = start + (PAGE_SIZE << nvhe_percpu_order()); - - ret = pkvm_mark_hyp(start, end); - if (ret) - return ret; - - start = virt_to_phys((void *)per_cpu(kvm_arm_hyp_stack_page, cpu)); - end = start + PAGE_SIZE; - ret = pkvm_mark_hyp(start, end); - if (ret) - return ret; - } + /* + * Exclude HYP BSS from kmemleak so that it doesn't get peeked + * at, which would end badly once the section is inaccessible. + * None of other sections should ever be introspected. + */ + kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start); /* * Flip the static key upfront as that may no longer be possible @@ -2015,11 +1997,6 @@ static int finalize_hyp_mode(void) return 0; } -static void check_kvm_target_cpu(void *ret) -{ - *(int *)ret = kvm_target_cpu(); -} - struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) { struct kvm_vcpu *vcpu; @@ -2079,7 +2056,6 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons) int kvm_arch_init(void *opaque) { int err; - int ret, cpu; bool in_hyp_mode; if (!is_hyp_mode_available()) { @@ -2094,15 +2070,7 @@ int kvm_arch_init(void *opaque) kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \ "Only trusted guests should be used on this system.\n"); - for_each_online_cpu(cpu) { - smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); - if (ret < 0) { - kvm_err("Error, CPU %d not supported!\n", cpu); - return -ENODEV; - } - } - - err = init_common_resources(); + err = kvm_set_ipa_limit(); if (err) return err; diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 1dfb83578277..fc86d4f55e97 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -50,6 +50,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, wfi_exit_stat), STATS_DESC_COUNTER(VCPU, mmio_exit_user), STATS_DESC_COUNTER(VCPU, mmio_exit_kernel), + STATS_DESC_COUNTER(VCPU, signal_exits), STATS_DESC_COUNTER(VCPU, exits) }; static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == @@ -842,7 +843,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, return 0; } -int __attribute_const__ kvm_target_cpu(void) +u32 __attribute_const__ kvm_target_cpu(void) { unsigned long implementor = read_cpuid_implementor(); unsigned long part_number = read_cpuid_part_number(); @@ -874,7 +875,7 @@ int __attribute_const__ kvm_target_cpu(void) int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) { - int target = kvm_target_cpu(); + u32 target = kvm_target_cpu(); if (target < 0) return -ENODEV; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 6f48336b1d86..04ebab299aa4 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -292,11 +292,12 @@ void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index) kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu)); } -void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr, +void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, + u64 elr_virt, u64 elr_phys, u64 par, uintptr_t vcpu, u64 far, u64 hpfar) { - u64 elr_in_kimg = __phys_to_kimg(__hyp_pa(elr)); - u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr; + u64 elr_in_kimg = __phys_to_kimg(elr_phys); + u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr_virt; u64 mode = spsr & PSR_MODE_MASK; /* @@ -309,20 +310,24 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr, kvm_err("Invalid host exception to nVHE hyp!\n"); } else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 && (esr & ESR_ELx_BRK64_ISS_COMMENT_MASK) == BUG_BRK_IMM) { - struct bug_entry *bug = find_bug(elr_in_kimg); const char *file = NULL; unsigned int line = 0; /* All hyp bugs, including warnings, are treated as fatal. */ - if (bug) - bug_get_file_line(bug, &file, &line); + if (!is_protected_kvm_enabled() || + IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) { + struct bug_entry *bug = find_bug(elr_in_kimg); + + if (bug) + bug_get_file_line(bug, &file, &line); + } if (file) kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line); else - kvm_err("nVHE hyp BUG at: %016llx!\n", elr + hyp_offset); + kvm_err("nVHE hyp BUG at: %016llx!\n", elr_virt + hyp_offset); } else { - kvm_err("nVHE hyp panic at: %016llx!\n", elr + hyp_offset); + kvm_err("nVHE hyp panic at: %016llx!\n", elr_virt + hyp_offset); } /* @@ -334,5 +339,5 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr, kvm_err("Hyp Offset: 0x%llx\n", hyp_offset); panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%016lx\n", - spsr, elr, esr, far, hpfar, par, vcpu); + spsr, elr_virt, esr, far, hpfar, par, vcpu); } diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h index 8901dc95d7de..b58c910babaf 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h @@ -12,6 +12,32 @@ #include <asm/virt.h> #include <nvhe/spinlock.h> +/* + * SW bits 0-1 are reserved to track the memory ownership state of each page: + * 00: The page is owned exclusively by the page-table owner. + * 01: The page is owned by the page-table owner, but is shared + * with another entity. + * 10: The page is shared with, but not owned by the page-table owner. + * 11: Reserved for future use (lending). + */ +enum pkvm_page_state { + PKVM_PAGE_OWNED = 0ULL, + PKVM_PAGE_SHARED_OWNED = KVM_PGTABLE_PROT_SW0, + PKVM_PAGE_SHARED_BORROWED = KVM_PGTABLE_PROT_SW1, +}; + +#define PKVM_PAGE_STATE_PROT_MASK (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1) +static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot, + enum pkvm_page_state state) +{ + return (prot & ~PKVM_PAGE_STATE_PROT_MASK) | state; +} + +static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot) +{ + return prot & PKVM_PAGE_STATE_PROT_MASK; +} + struct host_kvm { struct kvm_arch arch; struct kvm_pgtable pgt; @@ -20,9 +46,14 @@ struct host_kvm { }; extern struct host_kvm host_kvm; +extern const u8 pkvm_hyp_id; + int __pkvm_prot_finalize(void); -int __pkvm_mark_hyp(phys_addr_t start, phys_addr_t end); +int __pkvm_host_share_hyp(u64 pfn); +bool addr_is_memory(phys_addr_t phys); +int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot); +int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id); int kvm_host_prepare_stage2(void *pgt_pool_base); void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt); diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h index 8ec3a5a7744b..c9a8f535212e 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mm.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h @@ -23,8 +23,7 @@ int hyp_map_vectors(void); int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back); int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot); int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot); -int __pkvm_create_mappings(unsigned long start, unsigned long size, - unsigned long phys, enum kvm_pgtable_prot prot); +int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot); unsigned long __pkvm_create_private_mapping(phys_addr_t phys, size_t size, enum kvm_pgtable_prot prot); diff --git a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h index 76b537f8d1c6..4652fd04bdbe 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h +++ b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h @@ -15,6 +15,7 @@ #include <asm/alternative.h> #include <asm/lse.h> +#include <asm/rwonce.h> typedef union hyp_spinlock { u32 __val; @@ -89,4 +90,28 @@ static inline void hyp_spin_unlock(hyp_spinlock_t *lock) : "memory"); } +static inline bool hyp_spin_is_locked(hyp_spinlock_t *lock) +{ + hyp_spinlock_t lockval = READ_ONCE(*lock); + + return lockval.owner != lockval.next; +} + +#ifdef CONFIG_NVHE_EL2_DEBUG +static inline void hyp_assert_lock_held(hyp_spinlock_t *lock) +{ + /* + * The __pkvm_init() path accesses protected data-structures without + * holding locks as the other CPUs are guaranteed to not enter EL2 + * concurrently at this point in time. The point by which EL2 is + * initialized on all CPUs is reflected in the pkvm static key, so + * wait until it is set before checking the lock state. + */ + if (static_branch_likely(&kvm_protected_mode_initialized)) + BUG_ON(!hyp_spin_is_locked(lock)); +} +#else +static inline void hyp_assert_lock_held(hyp_spinlock_t *lock) { } +#endif + #endif /* __ARM64_KVM_NVHE_SPINLOCK_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 2b23400e0fb3..4b652ffb591d 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -7,6 +7,7 @@ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmu.h> @@ -85,12 +86,24 @@ SYM_FUNC_START(__hyp_do_panic) mov x29, x0 +#ifdef CONFIG_NVHE_EL2_DEBUG + /* Ensure host stage-2 is disabled */ + mrs x0, hcr_el2 + bic x0, x0, #HCR_VM + msr hcr_el2, x0 + isb + tlbi vmalls12e1 + dsb nsh +#endif + /* Load the panic arguments into x0-7 */ mrs x0, esr_el2 - get_vcpu_ptr x4, x5 - mrs x5, far_el2 - mrs x6, hpfar_el2 - mov x7, xzr // Unused argument + mov x4, x3 + mov x3, x2 + hyp_pa x3, x6 + get_vcpu_ptr x5, x6 + mrs x6, far_el2 + mrs x7, hpfar_el2 /* Enter the host, conditionally restoring the host context. */ cbz x29, __host_enter_without_restoring diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 1632f001f4ed..2da6aa8da868 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -140,14 +140,11 @@ static void handle___pkvm_cpu_set_vector(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 1) = pkvm_cpu_set_vector(slot); } -static void handle___pkvm_create_mappings(struct kvm_cpu_context *host_ctxt) +static void handle___pkvm_host_share_hyp(struct kvm_cpu_context *host_ctxt) { - DECLARE_REG(unsigned long, start, host_ctxt, 1); - DECLARE_REG(unsigned long, size, host_ctxt, 2); - DECLARE_REG(unsigned long, phys, host_ctxt, 3); - DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 4); + DECLARE_REG(u64, pfn, host_ctxt, 1); - cpu_reg(host_ctxt, 1) = __pkvm_create_mappings(start, size, phys, prot); + cpu_reg(host_ctxt, 1) = __pkvm_host_share_hyp(pfn); } static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ctxt) @@ -163,14 +160,6 @@ static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt) { cpu_reg(host_ctxt, 1) = __pkvm_prot_finalize(); } - -static void handle___pkvm_mark_hyp(struct kvm_cpu_context *host_ctxt) -{ - DECLARE_REG(phys_addr_t, start, host_ctxt, 1); - DECLARE_REG(phys_addr_t, end, host_ctxt, 2); - - cpu_reg(host_ctxt, 1) = __pkvm_mark_hyp(start, end); -} typedef void (*hcall_t)(struct kvm_cpu_context *); #define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x @@ -193,10 +182,9 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__vgic_v3_restore_aprs), HANDLE_FUNC(__pkvm_init), HANDLE_FUNC(__pkvm_cpu_set_vector), - HANDLE_FUNC(__pkvm_create_mappings), + HANDLE_FUNC(__pkvm_host_share_hyp), HANDLE_FUNC(__pkvm_create_private_mapping), HANDLE_FUNC(__pkvm_prot_finalize), - HANDLE_FUNC(__pkvm_mark_hyp), }; static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 7a0c4af186a0..bacd493a4eac 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -31,7 +31,7 @@ static struct hyp_pool host_s2_pool; u64 id_aa64mmfr0_el1_sys_val; u64 id_aa64mmfr1_el1_sys_val; -static const u8 pkvm_hyp_id = 1; +const u8 pkvm_hyp_id = 1; static void *host_s2_zalloc_pages_exact(size_t size) { @@ -89,6 +89,8 @@ static void prepare_host_vtcr(void) id_aa64mmfr1_el1_sys_val, phys_shift); } +static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot); + int kvm_host_prepare_stage2(void *pgt_pool_base) { struct kvm_s2_mmu *mmu = &host_kvm.arch.mmu; @@ -101,8 +103,9 @@ int kvm_host_prepare_stage2(void *pgt_pool_base) if (ret) return ret; - ret = kvm_pgtable_stage2_init_flags(&host_kvm.pgt, &host_kvm.arch, - &host_kvm.mm_ops, KVM_HOST_S2_FLAGS); + ret = __kvm_pgtable_stage2_init(&host_kvm.pgt, &host_kvm.arch, + &host_kvm.mm_ops, KVM_HOST_S2_FLAGS, + host_stage2_force_pte_cb); if (ret) return ret; @@ -159,6 +162,11 @@ static int host_stage2_unmap_dev_all(void) return kvm_pgtable_stage2_unmap(pgt, addr, BIT(pgt->ia_bits) - addr); } +struct kvm_mem_range { + u64 start; + u64 end; +}; + static bool find_mem_range(phys_addr_t addr, struct kvm_mem_range *range) { int cur, left = 0, right = hyp_memblock_nr; @@ -189,16 +197,26 @@ static bool find_mem_range(phys_addr_t addr, struct kvm_mem_range *range) return false; } +bool addr_is_memory(phys_addr_t phys) +{ + struct kvm_mem_range range; + + return find_mem_range(phys, &range); +} + +static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range) +{ + return range->start <= addr && addr < range->end; +} + static bool range_is_memory(u64 start, u64 end) { - struct kvm_mem_range r1, r2; + struct kvm_mem_range r; - if (!find_mem_range(start, &r1) || !find_mem_range(end, &r2)) - return false; - if (r1.start != r2.start) + if (!find_mem_range(start, &r)) return false; - return true; + return is_in_mem_range(end - 1, &r); } static inline int __host_stage2_idmap(u64 start, u64 end, @@ -208,60 +226,208 @@ static inline int __host_stage2_idmap(u64 start, u64 end, prot, &host_s2_pool); } +/* + * The pool has been provided with enough pages to cover all of memory with + * page granularity, but it is difficult to know how much of the MMIO range + * we will need to cover upfront, so we may need to 'recycle' the pages if we + * run out. + */ +#define host_stage2_try(fn, ...) \ + ({ \ + int __ret; \ + hyp_assert_lock_held(&host_kvm.lock); \ + __ret = fn(__VA_ARGS__); \ + if (__ret == -ENOMEM) { \ + __ret = host_stage2_unmap_dev_all(); \ + if (!__ret) \ + __ret = fn(__VA_ARGS__); \ + } \ + __ret; \ + }) + +static inline bool range_included(struct kvm_mem_range *child, + struct kvm_mem_range *parent) +{ + return parent->start <= child->start && child->end <= parent->end; +} + +static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) +{ + struct kvm_mem_range cur; + kvm_pte_t pte; + u32 level; + int ret; + + hyp_assert_lock_held(&host_kvm.lock); + ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, &level); + if (ret) + return ret; + + if (kvm_pte_valid(pte)) + return -EAGAIN; + + if (pte) + return -EPERM; + + do { + u64 granule = kvm_granule_size(level); + cur.start = ALIGN_DOWN(addr, granule); + cur.end = cur.start + granule; + level++; + } while ((level < KVM_PGTABLE_MAX_LEVELS) && + !(kvm_level_supports_block_mapping(level) && + range_included(&cur, range))); + + *range = cur; + + return 0; +} + +int host_stage2_idmap_locked(phys_addr_t addr, u64 size, + enum kvm_pgtable_prot prot) +{ + hyp_assert_lock_held(&host_kvm.lock); + + return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot); +} + +int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id) +{ + hyp_assert_lock_held(&host_kvm.lock); + + return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_kvm.pgt, + addr, size, &host_s2_pool, owner_id); +} + +static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot) +{ + /* + * Block mappings must be used with care in the host stage-2 as a + * kvm_pgtable_stage2_map() operation targeting a page in the range of + * an existing block will delete the block under the assumption that + * mappings in the rest of the block range can always be rebuilt lazily. + * That assumption is correct for the host stage-2 with RWX mappings + * targeting memory or RW mappings targeting MMIO ranges (see + * host_stage2_idmap() below which implements some of the host memory + * abort logic). However, this is not safe for any other mappings where + * the host stage-2 page-table is in fact the only place where this + * state is stored. In all those cases, it is safer to use page-level + * mappings, hence avoiding to lose the state because of side-effects in + * kvm_pgtable_stage2_map(). + */ + if (range_is_memory(addr, end)) + return prot != PKVM_HOST_MEM_PROT; + else + return prot != PKVM_HOST_MMIO_PROT; +} + static int host_stage2_idmap(u64 addr) { - enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W; struct kvm_mem_range range; bool is_memory = find_mem_range(addr, &range); + enum kvm_pgtable_prot prot; int ret; - if (is_memory) - prot |= KVM_PGTABLE_PROT_X; + prot = is_memory ? PKVM_HOST_MEM_PROT : PKVM_HOST_MMIO_PROT; hyp_spin_lock(&host_kvm.lock); - ret = kvm_pgtable_stage2_find_range(&host_kvm.pgt, addr, prot, &range); + ret = host_stage2_adjust_range(addr, &range); if (ret) goto unlock; - ret = __host_stage2_idmap(range.start, range.end, prot); - if (ret != -ENOMEM) + ret = host_stage2_idmap_locked(range.start, range.end - range.start, prot); +unlock: + hyp_spin_unlock(&host_kvm.lock); + + return ret; +} + +static inline bool check_prot(enum kvm_pgtable_prot prot, + enum kvm_pgtable_prot required, + enum kvm_pgtable_prot denied) +{ + return (prot & (required | denied)) == required; +} + +int __pkvm_host_share_hyp(u64 pfn) +{ + phys_addr_t addr = hyp_pfn_to_phys(pfn); + enum kvm_pgtable_prot prot, cur; + void *virt = __hyp_va(addr); + enum pkvm_page_state state; + kvm_pte_t pte; + int ret; + + if (!addr_is_memory(addr)) + return -EINVAL; + + hyp_spin_lock(&host_kvm.lock); + hyp_spin_lock(&pkvm_pgd_lock); + + ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, NULL); + if (ret) goto unlock; + if (!pte) + goto map_shared; /* - * The pool has been provided with enough pages to cover all of memory - * with page granularity, but it is difficult to know how much of the - * MMIO range we will need to cover upfront, so we may need to 'recycle' - * the pages if we run out. + * Check attributes in the host stage-2 PTE. We need the page to be: + * - mapped RWX as we're sharing memory; + * - not borrowed, as that implies absence of ownership. + * Otherwise, we can't let it got through */ - ret = host_stage2_unmap_dev_all(); - if (ret) + cur = kvm_pgtable_stage2_pte_prot(pte); + prot = pkvm_mkstate(0, PKVM_PAGE_SHARED_BORROWED); + if (!check_prot(cur, PKVM_HOST_MEM_PROT, prot)) { + ret = -EPERM; goto unlock; + } - ret = __host_stage2_idmap(range.start, range.end, prot); + state = pkvm_getstate(cur); + if (state == PKVM_PAGE_OWNED) + goto map_shared; -unlock: - hyp_spin_unlock(&host_kvm.lock); + /* + * Tolerate double-sharing the same page, but this requires + * cross-checking the hypervisor stage-1. + */ + if (state != PKVM_PAGE_SHARED_OWNED) { + ret = -EPERM; + goto unlock; + } - return ret; -} + ret = kvm_pgtable_get_leaf(&pkvm_pgtable, (u64)virt, &pte, NULL); + if (ret) + goto unlock; -int __pkvm_mark_hyp(phys_addr_t start, phys_addr_t end) -{ - int ret; + /* + * If the page has been shared with the hypervisor, it must be + * already mapped as SHARED_BORROWED in its stage-1. + */ + cur = kvm_pgtable_hyp_pte_prot(pte); + prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED); + if (!check_prot(cur, prot, ~prot)) + ret = -EPERM; + goto unlock; +map_shared: /* - * host_stage2_unmap_dev_all() currently relies on MMIO mappings being - * non-persistent, so don't allow changing page ownership in MMIO range. + * If the page is not yet shared, adjust mappings in both page-tables + * while both locks are held. */ - if (!range_is_memory(start, end)) - return -EINVAL; + prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED); + ret = pkvm_create_mappings_locked(virt, virt + PAGE_SIZE, prot); + BUG_ON(ret); - hyp_spin_lock(&host_kvm.lock); - ret = kvm_pgtable_stage2_set_owner(&host_kvm.pgt, start, end - start, - &host_s2_pool, pkvm_hyp_id); + prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_OWNED); + ret = host_stage2_idmap_locked(addr, PAGE_SIZE, prot); + BUG_ON(ret); + +unlock: + hyp_spin_unlock(&pkvm_pgd_lock); hyp_spin_unlock(&host_kvm.lock); - return ret != -EAGAIN ? ret : 0; + return ret; } void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt) diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index a8efdf0f9003..2fabeceb889a 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -23,8 +23,8 @@ u64 __io_map_base; struct memblock_region hyp_memory[HYP_MEMBLOCK_REGIONS]; unsigned int hyp_memblock_nr; -int __pkvm_create_mappings(unsigned long start, unsigned long size, - unsigned long phys, enum kvm_pgtable_prot prot) +static int __pkvm_create_mappings(unsigned long start, unsigned long size, + unsigned long phys, enum kvm_pgtable_prot prot) { int err; @@ -67,13 +67,15 @@ out: return addr; } -int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot) +int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot) { unsigned long start = (unsigned long)from; unsigned long end = (unsigned long)to; unsigned long virt_addr; phys_addr_t phys; + hyp_assert_lock_held(&pkvm_pgd_lock); + start = start & PAGE_MASK; end = PAGE_ALIGN(end); @@ -81,7 +83,8 @@ int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot) int err; phys = hyp_virt_to_phys((void *)virt_addr); - err = __pkvm_create_mappings(virt_addr, PAGE_SIZE, phys, prot); + err = kvm_pgtable_hyp_map(&pkvm_pgtable, virt_addr, PAGE_SIZE, + phys, prot); if (err) return err; } @@ -89,6 +92,17 @@ int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot) return 0; } +int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot) +{ + int ret; + + hyp_spin_lock(&pkvm_pgd_lock); + ret = pkvm_create_mappings_locked(from, to, prot); + hyp_spin_unlock(&pkvm_pgd_lock); + + return ret; +} + int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back) { unsigned long start, end; diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 0b574d106519..57c27846320f 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -58,6 +58,7 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, { void *start, *end, *virt = hyp_phys_to_virt(phys); unsigned long pgt_size = hyp_s1_pgtable_pages() << PAGE_SHIFT; + enum kvm_pgtable_prot prot; int ret, i; /* Recreate the hyp page-table using the early page allocator */ @@ -83,10 +84,6 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, if (ret) return ret; - ret = pkvm_create_mappings(__start_rodata, __end_rodata, PAGE_HYP_RO); - if (ret) - return ret; - ret = pkvm_create_mappings(__hyp_rodata_start, __hyp_rodata_end, PAGE_HYP_RO); if (ret) return ret; @@ -95,10 +92,6 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, if (ret) return ret; - ret = pkvm_create_mappings(__hyp_bss_end, __bss_stop, PAGE_HYP_RO); - if (ret) - return ret; - ret = pkvm_create_mappings(virt, virt + size, PAGE_HYP); if (ret) return ret; @@ -117,6 +110,24 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, return ret; } + /* + * Map the host's .bss and .rodata sections RO in the hypervisor, but + * transfer the ownership from the host to the hypervisor itself to + * make sure it can't be donated or shared with another entity. + * + * The ownership transition requires matching changes in the host + * stage-2. This will be done later (see finalize_host_mappings()) once + * the hyp_vmemmap is addressable. + */ + prot = pkvm_mkstate(PAGE_HYP_RO, PKVM_PAGE_SHARED_OWNED); + ret = pkvm_create_mappings(__start_rodata, __end_rodata, prot); + if (ret) + return ret; + + ret = pkvm_create_mappings(__hyp_bss_end, __bss_stop, prot); + if (ret) + return ret; + return 0; } @@ -148,6 +159,57 @@ static void hpool_put_page(void *addr) hyp_put_page(&hpool, addr); } +static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, + kvm_pte_t *ptep, + enum kvm_pgtable_walk_flags flag, + void * const arg) +{ + enum kvm_pgtable_prot prot; + enum pkvm_page_state state; + kvm_pte_t pte = *ptep; + phys_addr_t phys; + + if (!kvm_pte_valid(pte)) + return 0; + + if (level != (KVM_PGTABLE_MAX_LEVELS - 1)) + return -EINVAL; + + phys = kvm_pte_to_phys(pte); + if (!addr_is_memory(phys)) + return 0; + + /* + * Adjust the host stage-2 mappings to match the ownership attributes + * configured in the hypervisor stage-1. + */ + state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte)); + switch (state) { + case PKVM_PAGE_OWNED: + return host_stage2_set_owner_locked(phys, PAGE_SIZE, pkvm_hyp_id); + case PKVM_PAGE_SHARED_OWNED: + prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_BORROWED); + break; + case PKVM_PAGE_SHARED_BORROWED: + prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_OWNED); + break; + default: + return -EINVAL; + } + + return host_stage2_idmap_locked(phys, PAGE_SIZE, prot); +} + +static int finalize_host_mappings(void) +{ + struct kvm_pgtable_walker walker = { + .cb = finalize_host_mappings_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + }; + + return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits), &walker); +} + void __noreturn __pkvm_init_finalise(void) { struct kvm_host_data *host_data = this_cpu_ptr(&kvm_host_data); @@ -167,6 +229,10 @@ void __noreturn __pkvm_init_finalise(void) if (ret) goto out; + ret = finalize_host_mappings(); + if (ret) + goto out; + pkvm_pgtable_mm_ops = (struct kvm_pgtable_mm_ops) { .zalloc_page = hyp_zalloc_hyp_page, .phys_to_virt = hyp_phys_to_virt, diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 05321f4165e3..f8ceebe4982e 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -11,16 +11,12 @@ #include <asm/kvm_pgtable.h> #include <asm/stage2_pgtable.h> -#define KVM_PTE_VALID BIT(0) #define KVM_PTE_TYPE BIT(1) #define KVM_PTE_TYPE_BLOCK 0 #define KVM_PTE_TYPE_PAGE 1 #define KVM_PTE_TYPE_TABLE 1 -#define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT) -#define KVM_PTE_ADDR_51_48 GENMASK(15, 12) - #define KVM_PTE_LEAF_ATTR_LO GENMASK(11, 2) #define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX GENMASK(4, 2) @@ -40,6 +36,8 @@ #define KVM_PTE_LEAF_ATTR_HI GENMASK(63, 51) +#define KVM_PTE_LEAF_ATTR_HI_SW GENMASK(58, 55) + #define KVM_PTE_LEAF_ATTR_HI_S1_XN BIT(54) #define KVM_PTE_LEAF_ATTR_HI_S2_XN BIT(54) @@ -48,9 +46,7 @@ KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \ KVM_PTE_LEAF_ATTR_HI_S2_XN) -#define KVM_PTE_LEAF_ATTR_S2_IGNORED GENMASK(58, 55) - -#define KVM_INVALID_PTE_OWNER_MASK GENMASK(63, 56) +#define KVM_INVALID_PTE_OWNER_MASK GENMASK(9, 2) #define KVM_MAX_OWNER_ID 1 struct kvm_pgtable_walk_data { @@ -61,17 +57,6 @@ struct kvm_pgtable_walk_data { u64 end; }; -static u64 kvm_granule_shift(u32 level) -{ - /* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */ - return ARM64_HW_PGTABLE_LEVEL_SHIFT(level); -} - -static u64 kvm_granule_size(u32 level) -{ - return BIT(kvm_granule_shift(level)); -} - #define KVM_PHYS_INVALID (-1ULL) static bool kvm_phys_is_valid(u64 phys) @@ -79,15 +64,6 @@ static bool kvm_phys_is_valid(u64 phys) return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_PARANGE_MAX)); } -static bool kvm_level_supports_block_mapping(u32 level) -{ - /* - * Reject invalid block mappings and don't bother with 4TB mappings for - * 52-bit PAs. - */ - return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1)); -} - static bool kvm_block_mapping_supported(u64 addr, u64 end, u64 phys, u32 level) { u64 granule = kvm_granule_size(level); @@ -135,11 +111,6 @@ static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level) return __kvm_pgd_page_idx(&pgt, -1ULL) + 1; } -static bool kvm_pte_valid(kvm_pte_t pte) -{ - return pte & KVM_PTE_VALID; -} - static bool kvm_pte_table(kvm_pte_t pte, u32 level) { if (level == KVM_PGTABLE_MAX_LEVELS - 1) @@ -151,16 +122,6 @@ static bool kvm_pte_table(kvm_pte_t pte, u32 level) return FIELD_GET(KVM_PTE_TYPE, pte) == KVM_PTE_TYPE_TABLE; } -static u64 kvm_pte_to_phys(kvm_pte_t pte) -{ - u64 pa = pte & KVM_PTE_ADDR_MASK; - - if (PAGE_SHIFT == 16) - pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48; - - return pa; -} - static kvm_pte_t kvm_phys_to_pte(u64 pa) { kvm_pte_t pte = pa & KVM_PTE_ADDR_MASK; @@ -326,6 +287,45 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, return _kvm_pgtable_walk(&walk_data); } +struct leaf_walk_data { + kvm_pte_t pte; + u32 level; +}; + +static int leaf_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, + enum kvm_pgtable_walk_flags flag, void * const arg) +{ + struct leaf_walk_data *data = arg; + + data->pte = *ptep; + data->level = level; + + return 0; +} + +int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, + kvm_pte_t *ptep, u32 *level) +{ + struct leaf_walk_data data; + struct kvm_pgtable_walker walker = { + .cb = leaf_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = &data, + }; + int ret; + + ret = kvm_pgtable_walk(pgt, ALIGN_DOWN(addr, PAGE_SIZE), + PAGE_SIZE, &walker); + if (!ret) { + if (ptep) + *ptep = data.pte; + if (level) + *level = data.level; + } + + return ret; +} + struct hyp_map_data { u64 phys; kvm_pte_t attr; @@ -357,11 +357,47 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep) attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap); attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh); attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF; + attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; *ptep = attr; return 0; } +enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) +{ + enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; + u32 ap; + + if (!kvm_pte_valid(pte)) + return prot; + + if (!(pte & KVM_PTE_LEAF_ATTR_HI_S1_XN)) + prot |= KVM_PGTABLE_PROT_X; + + ap = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S1_AP, pte); + if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RO) + prot |= KVM_PGTABLE_PROT_R; + else if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RW) + prot |= KVM_PGTABLE_PROT_RW; + + return prot; +} + +static bool hyp_pte_needs_update(kvm_pte_t old, kvm_pte_t new) +{ + /* + * Tolerate KVM recreating the exact same mapping, or changing software + * bits if the existing mapping was valid. + */ + if (old == new) + return false; + + if (!kvm_pte_valid(old)) + return true; + + return !WARN_ON((old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW); +} + static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, struct hyp_map_data *data) { @@ -371,9 +407,8 @@ static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level, if (!kvm_block_mapping_supported(addr, end, phys, level)) return false; - /* Tolerate KVM recreating the exact same mapping */ new = kvm_init_valid_leaf_pte(phys, data->attr, level); - if (old != new && !WARN_ON(kvm_pte_valid(old))) + if (hyp_pte_needs_update(old, new)) smp_store_release(ptep, new); data->phys += granule; @@ -438,6 +473,8 @@ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, pgt->start_level = KVM_PGTABLE_MAX_LEVELS - levels; pgt->mm_ops = mm_ops; pgt->mmu = NULL; + pgt->force_pte_cb = NULL; + return 0; } @@ -475,6 +512,9 @@ struct stage2_map_data { void *memcache; struct kvm_pgtable_mm_ops *mm_ops; + + /* Force mappings to page granularity */ + bool force_pte; }; u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) @@ -539,11 +579,29 @@ static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot p attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh); attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF; + attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; *ptep = attr; return 0; } +enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte) +{ + enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; + + if (!kvm_pte_valid(pte)) + return prot; + + if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R) + prot |= KVM_PGTABLE_PROT_R; + if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W) + prot |= KVM_PGTABLE_PROT_W; + if (!(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN)) + prot |= KVM_PGTABLE_PROT_X; + + return prot; +} + static bool stage2_pte_needs_update(kvm_pte_t old, kvm_pte_t new) { if (!kvm_pte_valid(old) || !kvm_pte_valid(new)) @@ -588,6 +646,15 @@ static bool stage2_pte_executable(kvm_pte_t pte) return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } +static bool stage2_leaf_mapping_allowed(u64 addr, u64 end, u32 level, + struct stage2_map_data *data) +{ + if (data->force_pte && (level < (KVM_PGTABLE_MAX_LEVELS - 1))) + return false; + + return kvm_block_mapping_supported(addr, end, data->phys, level); +} + static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, struct stage2_map_data *data) @@ -597,7 +664,7 @@ static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, struct kvm_pgtable *pgt = data->mmu->pgt; struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; - if (!kvm_block_mapping_supported(addr, end, phys, level)) + if (!stage2_leaf_mapping_allowed(addr, end, level, data)) return -E2BIG; if (kvm_phys_is_valid(phys)) @@ -641,7 +708,7 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level, if (data->anchor) return 0; - if (!kvm_block_mapping_supported(addr, end, data->phys, level)) + if (!stage2_leaf_mapping_allowed(addr, end, level, data)) return 0; data->childp = kvm_pte_follow(*ptep, data->mm_ops); @@ -771,6 +838,7 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, .mmu = pgt->mmu, .memcache = mc, .mm_ops = pgt->mm_ops, + .force_pte = pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot), }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, @@ -802,6 +870,7 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, .memcache = mc, .mm_ops = pgt->mm_ops, .owner_id = owner_id, + .force_pte = true, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, @@ -995,6 +1064,9 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, u32 level; kvm_pte_t set = 0, clr = 0; + if (prot & KVM_PTE_LEAF_ATTR_HI_SW) + return -EINVAL; + if (prot & KVM_PGTABLE_PROT_R) set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; @@ -1043,9 +1115,11 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size) return kvm_pgtable_walk(pgt, addr, size, &walker); } -int kvm_pgtable_stage2_init_flags(struct kvm_pgtable *pgt, struct kvm_arch *arch, - struct kvm_pgtable_mm_ops *mm_ops, - enum kvm_pgtable_stage2_flags flags) + +int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_arch *arch, + struct kvm_pgtable_mm_ops *mm_ops, + enum kvm_pgtable_stage2_flags flags, + kvm_pgtable_force_pte_cb_t force_pte_cb) { size_t pgd_sz; u64 vtcr = arch->vtcr; @@ -1063,6 +1137,7 @@ int kvm_pgtable_stage2_init_flags(struct kvm_pgtable *pgt, struct kvm_arch *arch pgt->mm_ops = mm_ops; pgt->mmu = &arch->mmu; pgt->flags = flags; + pgt->force_pte_cb = force_pte_cb; /* Ensure zeroed PGD pages are visible to the hardware walker */ dsb(ishst); @@ -1102,77 +1177,3 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) pgt->mm_ops->free_pages_exact(pgt->pgd, pgd_sz); pgt->pgd = NULL; } - -#define KVM_PTE_LEAF_S2_COMPAT_MASK (KVM_PTE_LEAF_ATTR_S2_PERMS | \ - KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR | \ - KVM_PTE_LEAF_ATTR_S2_IGNORED) - -static int stage2_check_permission_walker(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, - void * const arg) -{ - kvm_pte_t old_attr, pte = *ptep, *new_attr = arg; - - /* - * Compatible mappings are either invalid and owned by the page-table - * owner (whose id is 0), or valid with matching permission attributes. - */ - if (kvm_pte_valid(pte)) { - old_attr = pte & KVM_PTE_LEAF_S2_COMPAT_MASK; - if (old_attr != *new_attr) - return -EEXIST; - } else if (pte) { - return -EEXIST; - } - - return 0; -} - -int kvm_pgtable_stage2_find_range(struct kvm_pgtable *pgt, u64 addr, - enum kvm_pgtable_prot prot, - struct kvm_mem_range *range) -{ - kvm_pte_t attr; - struct kvm_pgtable_walker check_perm_walker = { - .cb = stage2_check_permission_walker, - .flags = KVM_PGTABLE_WALK_LEAF, - .arg = &attr, - }; - u64 granule, start, end; - u32 level; - int ret; - - ret = stage2_set_prot_attr(pgt, prot, &attr); - if (ret) - return ret; - attr &= KVM_PTE_LEAF_S2_COMPAT_MASK; - - for (level = pgt->start_level; level < KVM_PGTABLE_MAX_LEVELS; level++) { - granule = kvm_granule_size(level); - start = ALIGN_DOWN(addr, granule); - end = start + granule; - - if (!kvm_level_supports_block_mapping(level)) - continue; - - if (start < range->start || range->end < end) - continue; - - /* - * Check the presence of existing mappings with incompatible - * permissions within the current block range, and try one level - * deeper if one is found. - */ - ret = kvm_pgtable_walk(pgt, start, granule, &check_perm_walker); - if (ret != -EEXIST) - break; - } - - if (!ret) { - range->start = start; - range->end = end; - } - - return ret; -} diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index d9152717cbd9..862bc534e295 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -81,6 +81,7 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot) void kvm_flush_remote_tlbs(struct kvm *kvm) { kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); + ++kvm->stat.generic.remote_tlb_flush; } static bool kvm_is_device_pfn(unsigned long pfn) @@ -259,10 +260,8 @@ static int __create_hyp_mappings(unsigned long start, unsigned long size, { int err; - if (!kvm_host_owns_hyp_mappings()) { - return kvm_call_hyp_nvhe(__pkvm_create_mappings, - start, size, phys, prot); - } + if (WARN_ON(!kvm_host_owns_hyp_mappings())) + return -EINVAL; mutex_lock(&kvm_hyp_pgd_mutex); err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot); @@ -282,6 +281,21 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr) } } +static int pkvm_share_hyp(phys_addr_t start, phys_addr_t end) +{ + phys_addr_t addr; + int ret; + + for (addr = ALIGN_DOWN(start, PAGE_SIZE); addr < end; addr += PAGE_SIZE) { + ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, + __phys_to_pfn(addr)); + if (ret) + return ret; + } + + return 0; +} + /** * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode * @from: The virtual kernel start address of the range @@ -302,6 +316,13 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot) if (is_kernel_in_hyp_mode()) return 0; + if (!kvm_host_owns_hyp_mappings()) { + if (WARN_ON(prot != PAGE_HYP)) + return -EPERM; + return pkvm_share_hyp(kvm_kaddr_to_phys(from), + kvm_kaddr_to_phys(to)); + } + start = start & PAGE_MASK; end = PAGE_ALIGN(end); @@ -433,6 +454,32 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, return 0; } +static struct kvm_pgtable_mm_ops kvm_user_mm_ops = { + /* We shouldn't need any other callback to walk the PT */ + .phys_to_virt = kvm_host_va, +}; + +static int get_user_mapping_size(struct kvm *kvm, u64 addr) +{ + struct kvm_pgtable pgt = { + .pgd = (kvm_pte_t *)kvm->mm->pgd, + .ia_bits = VA_BITS, + .start_level = (KVM_PGTABLE_MAX_LEVELS - + CONFIG_PGTABLE_LEVELS), + .mm_ops = &kvm_user_mm_ops, + }; + kvm_pte_t pte = 0; /* Keep GCC quiet... */ + u32 level = ~0; + int ret; + + ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level); + VM_BUG_ON(ret); + VM_BUG_ON(level >= KVM_PGTABLE_MAX_LEVELS); + VM_BUG_ON(!(pte & PTE_VALID)); + + return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level)); +} + static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .zalloc_page = stage2_memcache_zalloc_page, .zalloc_pages_exact = kvm_host_zalloc_pages_exact, @@ -780,7 +827,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, * Returns the size of the mapping. */ static unsigned long -transparent_hugepage_adjust(struct kvm_memory_slot *memslot, +transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long hva, kvm_pfn_t *pfnp, phys_addr_t *ipap) { @@ -791,8 +838,8 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot, * sure that the HVA and IPA are sufficiently aligned and that the * block map is contained within the memslot. */ - if (kvm_is_transparent_hugepage(pfn) && - fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { + if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) && + get_user_mapping_size(kvm, hva) >= PMD_SIZE) { /* * The address we faulted on is backed by a transparent huge * page. However, because we map the compound huge page and @@ -814,7 +861,7 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot, *ipap &= PMD_MASK; kvm_release_pfn_clean(pfn); pfn &= ~(PTRS_PER_PMD - 1); - kvm_get_pfn(pfn); + get_page(pfn_to_page(pfn)); *pfnp = pfn; return PMD_SIZE; @@ -1050,9 +1097,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * If we are not forced to use page mapping, check if we are * backed by a THP and thus use block mapping if possible. */ - if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) - vma_pagesize = transparent_hugepage_adjust(memslot, hva, - &pfn, &fault_ipa); + if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) { + if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE) + vma_pagesize = fault_granule; + else + vma_pagesize = transparent_hugepage_adjust(kvm, memslot, + hva, &pfn, + &fault_ipa); + } if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) { /* Check the VMM hasn't introduced a new VM_SHARED VMA */ diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c index 151c31fb9860..f9bb3b14130e 100644 --- a/arch/arm64/kvm/perf.c +++ b/arch/arm64/kvm/perf.c @@ -50,7 +50,7 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { int kvm_perf_init(void) { - if (kvm_pmu_probe_pmuver() != 0xf && !is_protected_kvm_enabled()) + if (kvm_pmu_probe_pmuver() != ID_AA64DFR0_PMUVER_IMP_DEF && !is_protected_kvm_enabled()) static_branch_enable(&kvm_arm_pmu_available); return perf_register_guest_info_callbacks(&kvm_guest_cbs); diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index f33825c995cb..f5065f23b413 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -373,7 +373,6 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu) reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1); - reg &= kvm_pmu_valid_counter_mask(vcpu); } return reg; @@ -564,20 +563,21 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) */ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { - unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); int i; if (val & ARMV8_PMU_PMCR_E) { kvm_pmu_enable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask); + __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); } else { - kvm_pmu_disable_counter_mask(vcpu, mask); + kvm_pmu_disable_counter_mask(vcpu, + __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); } if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { + unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); mask &= ~BIT(ARMV8_PMU_CYCLE_IDX); for_each_set_bit(i, &mask, 32) kvm_pmu_set_counter_value(vcpu, i, 0); @@ -745,7 +745,7 @@ int kvm_pmu_probe_pmuver(void) struct perf_event_attr attr = { }; struct perf_event *event; struct arm_pmu *pmu; - int pmuver = 0xf; + int pmuver = ID_AA64DFR0_PMUVER_IMP_DEF; /* * Create a dummy event that only counts user cycles. As we'll never @@ -770,7 +770,7 @@ int kvm_pmu_probe_pmuver(void) if (IS_ERR(event)) { pr_err_once("kvm: pmu event creation failed %ld\n", PTR_ERR(event)); - return 0xf; + return ID_AA64DFR0_PMUVER_IMP_DEF; } if (event->pmu) { @@ -923,7 +923,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) if (!vcpu->kvm->arch.pmuver) vcpu->kvm->arch.pmuver = kvm_pmu_probe_pmuver(); - if (vcpu->kvm->arch.pmuver == 0xf) + if (vcpu->kvm->arch.pmuver == ID_AA64DFR0_PMUVER_IMP_DEF) return -ENODEV; switch (attr->attr) { diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index db4056ecccfd..74c47d420253 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -59,6 +59,12 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu) kvm_vcpu_kick(vcpu); } +static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu, + unsigned long affinity) +{ + return !(affinity & ~MPIDR_HWID_BITMASK); +} + static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) { struct vcpu_reset_state *reset_state; @@ -66,9 +72,9 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) struct kvm_vcpu *vcpu = NULL; unsigned long cpu_id; - cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK; - if (vcpu_mode_is_32bit(source_vcpu)) - cpu_id &= ~((u32) 0); + cpu_id = smccc_get_arg1(source_vcpu); + if (!kvm_psci_valid_affinity(source_vcpu, cpu_id)) + return PSCI_RET_INVALID_PARAMS; vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id); @@ -126,6 +132,9 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) target_affinity = smccc_get_arg1(vcpu); lowest_affinity_level = smccc_get_arg2(vcpu); + if (!kvm_psci_valid_affinity(vcpu, target_affinity)) + return PSCI_RET_INVALID_PARAMS; + /* Determine target affinity mask */ target_affinity_mask = psci_affinity_mask(lowest_affinity_level); if (!target_affinity_mask) diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index cba7872d69a8..5ce36b0a3343 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -210,10 +210,16 @@ static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) */ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { + struct vcpu_reset_state reset_state; int ret; bool loaded; u32 pstate; + mutex_lock(&vcpu->kvm->lock); + reset_state = vcpu->arch.reset_state; + WRITE_ONCE(vcpu->arch.reset_state.reset, false); + mutex_unlock(&vcpu->kvm->lock); + /* Reset PMU outside of the non-preemptible section */ kvm_pmu_vcpu_reset(vcpu); @@ -276,8 +282,8 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) * Additional reset state handling that PSCI may have imposed on us. * Must be done after all the sys_reg reset. */ - if (vcpu->arch.reset_state.reset) { - unsigned long target_pc = vcpu->arch.reset_state.pc; + if (reset_state.reset) { + unsigned long target_pc = reset_state.pc; /* Gracefully handle Thumb2 entry point */ if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { @@ -286,13 +292,11 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } /* Propagate caller endianness */ - if (vcpu->arch.reset_state.be) + if (reset_state.be) kvm_vcpu_set_be(vcpu); *vcpu_pc(vcpu) = target_pc; - vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0); - - vcpu->arch.reset_state.reset = false; + vcpu_set_reg(vcpu, 0, reset_state.r0); } /* Reset timer */ @@ -311,31 +315,26 @@ u32 get_kvm_ipa_limit(void) int kvm_set_ipa_limit(void) { - unsigned int parange, tgran_2; + unsigned int parange; u64 mmfr0; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); parange = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_PARANGE_SHIFT); + /* + * IPA size beyond 48 bits could not be supported + * on either 4K or 16K page size. Hence let's cap + * it to 48 bits, in case it's reported as larger + * on the system. + */ + if (PAGE_SIZE != SZ_64K) + parange = min(parange, (unsigned int)ID_AA64MMFR0_PARANGE_48); /* * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at * Stage-2. If not, things will stop very quickly. */ - switch (PAGE_SIZE) { - default: - case SZ_4K: - tgran_2 = ID_AA64MMFR0_TGRAN4_2_SHIFT; - break; - case SZ_16K: - tgran_2 = ID_AA64MMFR0_TGRAN16_2_SHIFT; - break; - case SZ_64K: - tgran_2 = ID_AA64MMFR0_TGRAN64_2_SHIFT; - break; - } - - switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) { + switch (cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN_2_SHIFT)) { case ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE: kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n"); return -EINVAL; @@ -369,7 +368,7 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type) phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type); if (phys_shift) { if (phys_shift > kvm_ipa_limit || - phys_shift < 32) + phys_shift < ARM64_MIN_PARANGE_BITS) return -EINVAL; } else { phys_shift = KVM_PHYS_SHIFT; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index f6f126eb6ac1..a1f5101f49a3 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -603,6 +603,41 @@ static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu, return REG_HIDDEN; } +static void reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + u64 n, mask = BIT(ARMV8_PMU_CYCLE_IDX); + + /* No PMU available, any PMU reg may UNDEF... */ + if (!kvm_arm_support_pmu_v3()) + return; + + n = read_sysreg(pmcr_el0) >> ARMV8_PMU_PMCR_N_SHIFT; + n &= ARMV8_PMU_PMCR_N_MASK; + if (n) + mask |= GENMASK(n - 1, 0); + + reset_unknown(vcpu, r); + __vcpu_sys_reg(vcpu, r->reg) &= mask; +} + +static void reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + reset_unknown(vcpu, r); + __vcpu_sys_reg(vcpu, r->reg) &= GENMASK(31, 0); +} + +static void reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + reset_unknown(vcpu, r); + __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_EVTYPE_MASK; +} + +static void reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + reset_unknown(vcpu, r); + __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_COUNTER_MASK; +} + static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr, val; @@ -845,7 +880,7 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, kvm_pmu_disable_counter_mask(vcpu, val); } } else { - p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask; + p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); } return true; @@ -869,7 +904,7 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, /* accessing PMINTENCLR_EL1 */ __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val; } else { - p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1) & mask; + p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1); } return true; @@ -891,7 +926,7 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, /* accessing PMOVSCLR_EL0 */ __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask); } else { - p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0) & mask; + p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); } return true; @@ -944,16 +979,18 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr } #define PMU_SYS_REG(r) \ - SYS_DESC(r), .reset = reset_unknown, .visibility = pmu_visibility + SYS_DESC(r), .reset = reset_pmu_reg, .visibility = pmu_visibility /* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ { PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)), \ + .reset = reset_pmevcntr, \ .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), } /* Macro to expand the PMEVTYPERn_EL0 register */ #define PMU_PMEVTYPER_EL0(n) \ { PMU_SYS_REG(SYS_PMEVTYPERn_EL0(n)), \ + .reset = reset_pmevtyper, \ .access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), } static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, @@ -1249,6 +1286,20 @@ static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, return __set_id_reg(vcpu, rd, uaddr, true); } +static int set_wi_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + int err; + u64 val; + + /* Perform the access even if we are going to ignore the value */ + err = reg_from_user(&val, uaddr, sys_reg_to_index(rd)); + if (err) + return err; + + return 0; +} + static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { @@ -1592,16 +1643,21 @@ static const struct sys_reg_desc sys_reg_descs[] = { .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, { PMU_SYS_REG(SYS_PMOVSCLR_EL0), .access = access_pmovs, .reg = PMOVSSET_EL0 }, + /* + * PM_SWINC_EL0 is exposed to userspace as RAZ/WI, as it was + * previously (and pointlessly) advertised in the past... + */ { PMU_SYS_REG(SYS_PMSWINC_EL0), - .access = access_pmswinc, .reg = PMSWINC_EL0 }, + .get_user = get_raz_id_reg, .set_user = set_wi_reg, + .access = access_pmswinc, .reset = NULL }, { PMU_SYS_REG(SYS_PMSELR_EL0), - .access = access_pmselr, .reg = PMSELR_EL0 }, + .access = access_pmselr, .reset = reset_pmselr, .reg = PMSELR_EL0 }, { PMU_SYS_REG(SYS_PMCEID0_EL0), .access = access_pmceid, .reset = NULL }, { PMU_SYS_REG(SYS_PMCEID1_EL0), .access = access_pmceid, .reset = NULL }, { PMU_SYS_REG(SYS_PMCCNTR_EL0), - .access = access_pmu_evcntr, .reg = PMCCNTR_EL0 }, + .access = access_pmu_evcntr, .reset = reset_unknown, .reg = PMCCNTR_EL0 }, { PMU_SYS_REG(SYS_PMXEVTYPER_EL0), .access = access_pmu_evtyper, .reset = NULL }, { PMU_SYS_REG(SYS_PMXEVCNTR_EL0), diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c index a016f07adc28..5f9014ae595b 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c @@ -282,7 +282,7 @@ static unsigned long vgic_mmio_read_vcpuif(struct kvm_vcpu *vcpu, case GIC_CPU_PRIMASK: /* * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the - * the PMR field as GICH_VMCR.VMPriMask rather than + * PMR field as GICH_VMCR.VMPriMask rather than * GICC_PMR.Priority, so we expose the upper five bits of * priority mask to userspace using the lower bits in the * unsigned long. @@ -329,7 +329,7 @@ static void vgic_mmio_write_vcpuif(struct kvm_vcpu *vcpu, case GIC_CPU_PRIMASK: /* * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the - * the PMR field as GICH_VMCR.VMPriMask rather than + * PMR field as GICH_VMCR.VMPriMask rather than * GICC_PMR.Priority, so we expose the upper five bits of * priority mask to userspace using the lower bits in the * unsigned long. diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c index 2c580204f1dc..95a18cec14a3 100644 --- a/arch/arm64/kvm/vgic/vgic-v2.c +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -60,6 +60,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) u32 val = cpuif->vgic_lr[lr]; u32 cpuid, intid = val & GICH_LR_VIRTUALID; struct vgic_irq *irq; + bool deactivated; /* Extract the source vCPU id from the LR */ cpuid = val & GICH_LR_PHYSID_CPUID; @@ -75,7 +76,8 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) raw_spin_lock(&irq->irq_lock); - /* Always preserve the active bit */ + /* Always preserve the active bit, note deactivation */ + deactivated = irq->active && !(val & GICH_LR_ACTIVE_BIT); irq->active = !!(val & GICH_LR_ACTIVE_BIT); if (irq->active && vgic_irq_is_sgi(intid)) @@ -96,36 +98,8 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) if (irq->config == VGIC_CONFIG_LEVEL && !(val & GICH_LR_STATE)) irq->pending_latch = false; - /* - * Level-triggered mapped IRQs are special because we only - * observe rising edges as input to the VGIC. - * - * If the guest never acked the interrupt we have to sample - * the physical line and set the line level, because the - * device state could have changed or we simply need to - * process the still pending interrupt later. - * - * If this causes us to lower the level, we have to also clear - * the physical active state, since we will otherwise never be - * told when the interrupt becomes asserted again. - * - * Another case is when the interrupt requires a helping hand - * on deactivation (no HW deactivation, for example). - */ - if (vgic_irq_is_mapped_level(irq)) { - bool resample = false; - - if (val & GICH_LR_PENDING_BIT) { - irq->line_level = vgic_get_phys_line_level(irq); - resample = !irq->line_level; - } else if (vgic_irq_needs_resampling(irq) && - !(irq->active || irq->pending_latch)) { - resample = true; - } - - if (resample) - vgic_irq_set_phys_active(irq, false); - } + /* Handle resampling for mapped interrupts if required */ + vgic_irq_handle_resampling(irq, deactivated, val & GICH_LR_PENDING_BIT); raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 66004f61cd83..21a6207fb2ee 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -46,6 +46,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) u32 intid, cpuid; struct vgic_irq *irq; bool is_v2_sgi = false; + bool deactivated; cpuid = val & GICH_LR_PHYSID_CPUID; cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT; @@ -68,7 +69,8 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) raw_spin_lock(&irq->irq_lock); - /* Always preserve the active bit */ + /* Always preserve the active bit, note deactivation */ + deactivated = irq->active && !(val & ICH_LR_ACTIVE_BIT); irq->active = !!(val & ICH_LR_ACTIVE_BIT); if (irq->active && is_v2_sgi) @@ -89,36 +91,8 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE)) irq->pending_latch = false; - /* - * Level-triggered mapped IRQs are special because we only - * observe rising edges as input to the VGIC. - * - * If the guest never acked the interrupt we have to sample - * the physical line and set the line level, because the - * device state could have changed or we simply need to - * process the still pending interrupt later. - * - * If this causes us to lower the level, we have to also clear - * the physical active state, since we will otherwise never be - * told when the interrupt becomes asserted again. - * - * Another case is when the interrupt requires a helping hand - * on deactivation (no HW deactivation, for example). - */ - if (vgic_irq_is_mapped_level(irq)) { - bool resample = false; - - if (val & ICH_LR_PENDING_BIT) { - irq->line_level = vgic_get_phys_line_level(irq); - resample = !irq->line_level; - } else if (vgic_irq_needs_resampling(irq) && - !(irq->active || irq->pending_latch)) { - resample = true; - } - - if (resample) - vgic_irq_set_phys_active(irq, false); - } + /* Handle resampling for mapped interrupts if required */ + vgic_irq_handle_resampling(irq, deactivated, val & ICH_LR_PENDING_BIT); raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 111bff47e471..5dad4996cfb2 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -106,7 +106,6 @@ struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, if (intid >= VGIC_MIN_LPI) return vgic_get_lpi(kvm, intid); - WARN(1, "Looking up struct vgic_irq for reserved INTID"); return NULL; } @@ -1022,3 +1021,41 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid) return map_is_active; } + +/* + * Level-triggered mapped IRQs are special because we only observe rising + * edges as input to the VGIC. + * + * If the guest never acked the interrupt we have to sample the physical + * line and set the line level, because the device state could have changed + * or we simply need to process the still pending interrupt later. + * + * We could also have entered the guest with the interrupt active+pending. + * On the next exit, we need to re-evaluate the pending state, as it could + * otherwise result in a spurious interrupt by injecting a now potentially + * stale pending state. + * + * If this causes us to lower the level, we have to also clear the physical + * active state, since we will otherwise never be told when the interrupt + * becomes asserted again. + * + * Another case is when the interrupt requires a helping hand on + * deactivation (no HW deactivation, for example). + */ +void vgic_irq_handle_resampling(struct vgic_irq *irq, + bool lr_deactivated, bool lr_pending) +{ + if (vgic_irq_is_mapped_level(irq)) { + bool resample = false; + + if (unlikely(vgic_irq_needs_resampling(irq))) { + resample = !(irq->active || irq->pending_latch); + } else if (lr_pending || (lr_deactivated && irq->line_level)) { + irq->line_level = vgic_get_phys_line_level(irq); + resample = !irq->line_level; + } + + if (resample) + vgic_irq_set_phys_active(irq, false); + } +} diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index dc1f3d1657ee..14a9218641f5 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -169,6 +169,8 @@ void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active); bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, unsigned long flags); void vgic_kick_vcpus(struct kvm *kvm); +void vgic_irq_handle_resampling(struct vgic_irq *irq, + bool lr_deactivated, bool lr_pending); int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr, phys_addr_t addr, phys_addr_t alignment); diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 136b8d97d8c0..0d7865a0731c 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -2,7 +2,11 @@ #ifndef __LINUX_ENTRYKVM_H #define __LINUX_ENTRYKVM_H -#include <linux/entry-common.h> +#include <linux/static_call_types.h> +#include <linux/tracehook.h> +#include <linux/syscalls.h> +#include <linux/seccomp.h> +#include <linux/sched.h> #include <linux/tick.h> /* Transfer to guest mode work */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ae7735b490b4..9818d271c2a1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -824,7 +824,6 @@ void kvm_release_pfn_clean(kvm_pfn_t pfn); void kvm_release_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_accessed(kvm_pfn_t pfn); -void kvm_get_pfn(kvm_pfn_t pfn); void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5922031ffab6..1ace27c4a8e0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -633,43 +633,6 @@ static inline int PageTransCompound(struct page *page) } /* - * PageTransCompoundMap is the same as PageTransCompound, but it also - * guarantees the primary MMU has the entire compound page mapped - * through pmd_trans_huge, which in turn guarantees the secondary MMUs - * can also map the entire compound page. This allows the secondary - * MMUs to call get_user_pages() only once for each compound page and - * to immediately map the entire compound page with a single secondary - * MMU fault. If there will be a pmd split later, the secondary MMUs - * will get an update through the MMU notifier invalidation through - * split_huge_pmd(). - * - * Unlike PageTransCompound, this is safe to be called only while - * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount check false - * positives. - * - * We have to treat page cache THP differently since every subpage of it - * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE - * mapped in the current process so comparing subpage's _mapcount to - * compound_mapcount to filter out PTE mapped case. - */ -static inline int PageTransCompoundMap(struct page *page) -{ - struct page *head; - - if (!PageTransCompound(page)) - return 0; - - if (PageAnon(page)) - return atomic_read(&page->_mapcount) < 0; - - head = compound_head(page); - /* File THP is PMD mapped and not PTE mapped */ - return atomic_read(&page->_mapcount) == - atomic_read(compound_mapcount_ptr(head)); -} - -/* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 0709af0144c8..98053d3afbda 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only /aarch64/debug-exceptions /aarch64/get-reg-list +/aarch64/psci_cpu_on_test /aarch64/vgic_init /s390x/memop /s390x/resets diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 5832f510a16c..5d05801ab816 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -86,6 +86,7 @@ TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list +TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test TEST_GEN_PROGS_aarch64 += aarch64/vgic_init TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test diff --git a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c new file mode 100644 index 000000000000..018c269990e1 --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * psci_cpu_on_test - Test that the observable state of a vCPU targeted by the + * CPU_ON PSCI call matches what the caller requested. + * + * Copyright (c) 2021 Google LLC. + * + * This is a regression test for a race between KVM servicing the PSCI call and + * userspace reading the vCPUs registers. + */ + +#define _GNU_SOURCE + +#include <linux/psci.h> + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +#define VCPU_ID_SOURCE 0 +#define VCPU_ID_TARGET 1 + +#define CPU_ON_ENTRY_ADDR 0xfeedf00dul +#define CPU_ON_CONTEXT_ID 0xdeadc0deul + +static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr, + uint64_t context_id) +{ + register uint64_t x0 asm("x0") = PSCI_0_2_FN64_CPU_ON; + register uint64_t x1 asm("x1") = target_cpu; + register uint64_t x2 asm("x2") = entry_addr; + register uint64_t x3 asm("x3") = context_id; + + asm("hvc #0" + : "=r"(x0) + : "r"(x0), "r"(x1), "r"(x2), "r"(x3) + : "memory"); + + return x0; +} + +static uint64_t psci_affinity_info(uint64_t target_affinity, + uint64_t lowest_affinity_level) +{ + register uint64_t x0 asm("x0") = PSCI_0_2_FN64_AFFINITY_INFO; + register uint64_t x1 asm("x1") = target_affinity; + register uint64_t x2 asm("x2") = lowest_affinity_level; + + asm("hvc #0" + : "=r"(x0) + : "r"(x0), "r"(x1), "r"(x2) + : "memory"); + + return x0; +} + +static void guest_main(uint64_t target_cpu) +{ + GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID)); + uint64_t target_state; + + do { + target_state = psci_affinity_info(target_cpu, 0); + + GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) || + (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF)); + } while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON); + + GUEST_DONE(); +} + +int main(void) +{ + uint64_t target_mpidr, obs_pc, obs_x0; + struct kvm_vcpu_init init; + struct kvm_vm *vm; + struct ucall uc; + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name); + ucall_init(vm, NULL); + + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); + + aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_main); + + /* + * make sure the target is already off when executing the test. + */ + init.features[0] |= (1 << KVM_ARM_VCPU_POWER_OFF); + aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_main); + + get_reg(vm, VCPU_ID_TARGET, ARM64_SYS_REG(MPIDR_EL1), &target_mpidr); + vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK); + vcpu_run(vm, VCPU_ID_SOURCE); + + switch (get_ucall(vm, VCPU_ID_SOURCE, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__, + uc.args[1]); + break; + default: + TEST_FAIL("Unhandled ucall: %lu", uc.cmd); + } + + get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.pc), &obs_pc); + get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.regs[0]), &obs_x0); + + TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR, + "unexpected target cpu pc: %lx (expected: %lx)", + obs_pc, CPU_ON_ENTRY_ADDR); + TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID, + "unexpected target context id: %lx (expected: %lx)", + obs_x0, CPU_ON_CONTEXT_ID); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 27dc5c2e56b9..c0273aefa63d 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -17,6 +17,7 @@ #define CPACR_EL1 3, 0, 1, 0, 2 #define TCR_EL1 3, 0, 2, 0, 2 #define MAIR_EL1 3, 0, 10, 2, 0 +#define MPIDR_EL1 3, 0, 0, 0, 5 #define TTBR0_EL1 3, 0, 2, 0, 0 #define SCTLR_EL1 3, 0, 1, 0, 0 #define VBAR_EL1 3, 0, 12, 0, 0 @@ -40,6 +41,8 @@ (0xfful << (4 * 8)) | \ (0xbbul << (5 * 8))) +#define MPIDR_HWID_BITMASK (0xff00fffffful) + static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr) { struct kvm_one_reg reg; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d20fba0fc290..1d3a03c0fed3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -189,16 +189,6 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn) return true; } -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn) -{ - struct page *page = pfn_to_page(pfn); - - if (!PageTransCompoundMap(page)) - return false; - - return is_transparent_hugepage(compound_head(page)); -} - /* * Switches to specified vcpu, until a matching vcpu_put() */ @@ -2225,7 +2215,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, * Get a reference here because callers of *hva_to_pfn* and * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the * returned pfn. This is only needed if the VMA has VM_MIXEDMAP - * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will + * set, but the kvm_try_get_pfn/kvm_release_pfn_clean pair will * simply do nothing for reserved pfns. * * Whoever called remap_pfn_range is also going to call e.g. @@ -2622,13 +2612,6 @@ void kvm_set_pfn_accessed(kvm_pfn_t pfn) } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); -void kvm_get_pfn(kvm_pfn_t pfn) -{ - if (!kvm_is_reserved_pfn(pfn)) - get_page(pfn_to_page(pfn)); -} -EXPORT_SYMBOL_GPL(kvm_get_pfn); - static int next_segment(unsigned long len, int offset) { if (len > PAGE_SIZE - offset) |