diff options
44 files changed, 1110 insertions, 332 deletions
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 50d5e4de244c..d5b0386ef765 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -63,6 +63,7 @@ enum __kvm_host_smccc_func { /* Hypercalls available after pKVM finalisation */ __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp, + __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp, __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc, __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run, __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context, diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2a5f7f38006f..9360a2804df1 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -26,7 +26,6 @@ #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> -#include <asm/thread_info.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -321,8 +320,8 @@ struct kvm_vcpu_arch { struct kvm_guest_debug_arch vcpu_debug_state; struct kvm_guest_debug_arch external_debug_state; - struct thread_info *host_thread_info; /* hyp VA */ struct user_fpsimd_state *host_fpsimd_state; /* hyp VA */ + struct task_struct *parent_task; struct { /* {Break,watch}point registers */ @@ -367,9 +366,6 @@ struct kvm_vcpu_arch { int target; DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES); - /* Detect first run of a vcpu */ - bool has_run_once; - /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; @@ -411,20 +407,17 @@ struct kvm_vcpu_arch { #define KVM_ARM64_DEBUG_DIRTY (1 << 0) #define KVM_ARM64_FP_ENABLED (1 << 1) /* guest FP regs loaded */ #define KVM_ARM64_FP_HOST (1 << 2) /* host FP regs loaded */ -#define KVM_ARM64_HOST_SVE_IN_USE (1 << 3) /* backup for host TIF_SVE */ #define KVM_ARM64_HOST_SVE_ENABLED (1 << 4) /* SVE enabled for EL0 */ #define KVM_ARM64_GUEST_HAS_SVE (1 << 5) /* SVE exposed to guest */ #define KVM_ARM64_VCPU_SVE_FINALIZED (1 << 6) /* SVE config completed */ #define KVM_ARM64_GUEST_HAS_PTRAUTH (1 << 7) /* PTRAUTH exposed to guest */ #define KVM_ARM64_PENDING_EXCEPTION (1 << 8) /* Exception pending */ +/* + * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be + * set together with an exception... + */ +#define KVM_ARM64_INCREMENT_PC (1 << 9) /* Increment PC */ #define KVM_ARM64_EXCEPT_MASK (7 << 9) /* Target EL/MODE */ -#define KVM_ARM64_DEBUG_STATE_SAVE_SPE (1 << 12) /* Save SPE context if active */ -#define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ - -#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ - KVM_GUESTDBG_USE_SW_BP | \ - KVM_GUESTDBG_USE_HW | \ - KVM_GUESTDBG_SINGLESTEP) /* * When KVM_ARM64_PENDING_EXCEPTION is set, KVM_ARM64_EXCEPT_MASK can * take the following values: @@ -442,11 +435,14 @@ struct kvm_vcpu_arch { #define KVM_ARM64_EXCEPT_AA64_EL1 (0 << 11) #define KVM_ARM64_EXCEPT_AA64_EL2 (1 << 11) -/* - * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be - * set together with an exception... - */ -#define KVM_ARM64_INCREMENT_PC (1 << 9) /* Increment PC */ +#define KVM_ARM64_DEBUG_STATE_SAVE_SPE (1 << 12) /* Save SPE context if active */ +#define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ +#define KVM_ARM64_FP_FOREIGN_FPSTATE (1 << 14) + +#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ + KVM_GUESTDBG_USE_SW_BP | \ + KVM_GUESTDBG_USE_HW | \ + KVM_GUESTDBG_SINGLESTEP) #define vcpu_has_sve(vcpu) (system_supports_sve() && \ ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE)) @@ -606,6 +602,8 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, void kvm_arm_halt_guest(struct kvm *kvm); void kvm_arm_resume_guest(struct kvm *kvm); +#define vcpu_has_run_once(vcpu) !!rcu_access_pointer((vcpu)->pid) + #ifndef __KVM_NVHE_HYPERVISOR__ #define kvm_call_hyp_nvhe(f, ...) \ ({ \ @@ -737,8 +735,10 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu); +void kvm_vcpu_unshare_task_fp(struct kvm_vcpu *vcpu); static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) { @@ -749,12 +749,7 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu); -#ifdef CONFIG_KVM /* Avoid conflicts with core headers if CONFIG_KVM=n */ -static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) -{ - return kvm_arch_vcpu_run_map_fp(vcpu); -} - +#ifdef CONFIG_KVM void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u32 clr); diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 5afd14ab15b9..462882f356c7 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -90,7 +90,6 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu); void __fpsimd_save_state(struct user_fpsimd_state *fp_regs); void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs); -void __sve_save_state(void *sve_pffr, u32 *fpsr); void __sve_restore_state(void *sve_pffr, u32 *fpsr); #ifndef __KVM_NVHE_HYPERVISOR__ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 02d378887743..81839e9a8a24 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -150,6 +150,8 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) #include <asm/kvm_pgtable.h> #include <asm/stage2_pgtable.h> +int kvm_share_hyp(void *from, void *to); +void kvm_unshare_hyp(void *from, void *to); int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot); int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **kaddr, diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 027783829584..9d076f36401d 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -252,6 +252,27 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot); /** + * kvm_pgtable_hyp_unmap() - Remove a mapping from a hypervisor stage-1 page-table. + * @pgt: Page-table structure initialised by kvm_pgtable_hyp_init(). + * @addr: Virtual address from which to remove the mapping. + * @size: Size of the mapping. + * + * The offset of @addr within a page is ignored, @size is rounded-up to + * the next page boundary and @phys is rounded-down to the previous page + * boundary. + * + * TLB invalidation is performed for each page-table entry cleared during the + * unmapping operation and the reference count for the page-table page + * containing the cleared entry is decremented, with unreferenced pages being + * freed. The unmapping operation will stop early if it encounters either an + * invalid page-table entry or a valid block mapping which maps beyond the range + * being unmapped. + * + * Return: Number of bytes unmapped, which may be 0. + */ +u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size); + +/** * kvm_get_vtcr() - Helper to construct VTCR_EL2 * @mmfr0: Sanitized value of SYS_ID_AA64MMFR0_EL1 register. * @mmfr1: Sanitized value of SYS_ID_AA64MMFR1_EL1 register. diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h new file mode 100644 index 000000000000..9f4ad2a8df59 --- /dev/null +++ b/arch/arm64/include/asm/kvm_pkvm.h @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020 - Google LLC + * Author: Quentin Perret <qperret@google.com> + */ +#ifndef __ARM64_KVM_PKVM_H__ +#define __ARM64_KVM_PKVM_H__ + +#include <linux/memblock.h> +#include <asm/kvm_pgtable.h> + +#define HYP_MEMBLOCK_REGIONS 128 + +extern struct memblock_region kvm_nvhe_sym(hyp_memory)[]; +extern unsigned int kvm_nvhe_sym(hyp_memblock_nr); + +static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages) +{ + unsigned long total = 0, i; + + /* Provision the worst case scenario */ + for (i = 0; i < KVM_PGTABLE_MAX_LEVELS; i++) { + nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE); + total += nr_pages; + } + + return total; +} + +static inline unsigned long __hyp_pgtable_total_pages(void) +{ + unsigned long res = 0, i; + + /* Cover all of memory with page-granularity */ + for (i = 0; i < kvm_nvhe_sym(hyp_memblock_nr); i++) { + struct memblock_region *reg = &kvm_nvhe_sym(hyp_memory)[i]; + res += __hyp_pgtable_max_pages(reg->size >> PAGE_SHIFT); + } + + return res; +} + +static inline unsigned long hyp_s1_pgtable_pages(void) +{ + unsigned long res; + + res = __hyp_pgtable_total_pages(); + + /* Allow 1 GiB for private mappings */ + res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT); + + return res; +} + +static inline unsigned long host_s2_pgtable_pages(void) +{ + unsigned long res; + + /* + * Include an extra 16 pages to safely upper-bound the worst case of + * concatenated pgds. + */ + res = __hyp_pgtable_total_pages() + 16; + + /* Allow 1 GiB for MMIO mappings */ + res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT); + + return res; +} + +#endif /* __ARM64_KVM_PKVM_H__ */ diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index e9c30859f80c..48f8466a4be9 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -15,6 +15,7 @@ #ifndef __ASSEMBLY__ #include <linux/refcount.h> +#include <asm/cpufeature.h> typedef struct { atomic64_t id; diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 16b3f1a1d468..615dd6278f8b 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -937,6 +937,7 @@ #define ID_AA64DFR0_PMUVER_8_1 0x4 #define ID_AA64DFR0_PMUVER_8_4 0x5 #define ID_AA64DFR0_PMUVER_8_5 0x6 +#define ID_AA64DFR0_PMUVER_8_7 0x7 #define ID_AA64DFR0_PMUVER_IMP_DEF 0xf #define ID_AA64DFR0_PMSVER_8_2 0x1 diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index fa244c426f61..6fb361e8bed8 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -78,7 +78,11 @@ * indicate whether or not the userland FPSIMD state of the current task is * present in the registers. The flag is set unless the FPSIMD registers of this * CPU currently contain the most recent userland FPSIMD state of the current - * task. + * task. If the task is behaving as a VMM, then this is will be managed by + * KVM which will clear it to indicate that the vcpu FPSIMD state is currently + * loaded on the CPU, allowing the state to be saved if a FPSIMD-aware + * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and + * flag the register state as invalid. * * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may * save the task's FPSIMD context back to task_struct from softirq context. diff --git a/arch/arm64/kvm/.gitignore b/arch/arm64/kvm/.gitignore new file mode 100644 index 000000000000..6182aefb8302 --- /dev/null +++ b/arch/arm64/kvm/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +hyp_constants.h diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 989bb5dad2c8..8ca8cf6f5619 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -15,7 +15,7 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o \ - vgic-sys-reg-v3.o fpsimd.o pmu.o \ + vgic-sys-reg-v3.o fpsimd.o pmu.o pkvm.o \ arch_timer.o trng.o\ vgic/vgic.o vgic/vgic-init.o \ vgic/vgic-irqfd.o vgic/vgic-v2.o \ @@ -25,3 +25,19 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ vgic/vgic-its.o vgic/vgic-debug.o kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o + +always-y := hyp_constants.h hyp-constants.s + +define rule_gen_hyp_constants + $(call filechk,offsets,__HYP_CONSTANTS_H__) +endef + +CFLAGS_hyp-constants.o = -I $(srctree)/$(src)/hyp/include +$(obj)/hyp-constants.s: $(src)/hyp/hyp-constants.c FORCE + $(call if_changed_dep,cc_s_c) + +$(obj)/hyp_constants.h: $(obj)/hyp-constants.s FORCE + $(call if_changed_rule,gen_hyp_constants) + +obj-kvm := $(addprefix $(obj)/, $(kvm-y)) +$(obj-kvm): $(obj)/hyp_constants.h diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e4727dc771bf..6057f3c5aafe 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -146,7 +146,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) return ret; - ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP); + ret = kvm_share_hyp(kvm, kvm + 1); if (ret) goto out_free_stage2_pgd; @@ -188,6 +188,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm) } } atomic_set(&kvm->online_vcpus, 0); + + kvm_unshare_hyp(kvm, kvm + 1); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -342,7 +344,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (err) return err; - return create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP); + return kvm_share_hyp(vcpu, vcpu + 1); } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) @@ -351,7 +353,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm))) + if (vcpu_has_run_once(vcpu) && unlikely(!irqchip_in_kernel(vcpu->kvm))) static_branch_dec(&userspace_irqchip_in_use); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); @@ -584,18 +586,33 @@ static void update_vmid(struct kvm_vmid *vmid) spin_unlock(&kvm_vmid_lock); } -static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) +static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.target >= 0; +} + +/* + * Handle both the initialisation that is being done when the vcpu is + * run for the first time, as well as the updates that must be + * performed each time we get a new thread dealing with this vcpu. + */ +int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; - int ret = 0; + int ret; - if (likely(vcpu->arch.has_run_once)) - return 0; + if (!kvm_vcpu_initialized(vcpu)) + return -ENOEXEC; if (!kvm_arm_vcpu_is_finalized(vcpu)) return -EPERM; - vcpu->arch.has_run_once = true; + ret = kvm_arch_vcpu_run_map_fp(vcpu); + if (ret) + return ret; + + if (likely(vcpu_has_run_once(vcpu))) + return 0; kvm_arm_vcpu_init_debug(vcpu); @@ -607,12 +624,6 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) ret = kvm_vgic_map_resources(kvm); if (ret) return ret; - } else { - /* - * Tell the rest of the code that there are userspace irqchip - * VMs in the wild. - */ - static_branch_inc(&userspace_irqchip_in_use); } ret = kvm_timer_enable(vcpu); @@ -620,6 +631,16 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) return ret; ret = kvm_arm_pmu_v3_enable(vcpu); + if (ret) + return ret; + + if (!irqchip_in_kernel(kvm)) { + /* + * Tell the rest of the code that there are userspace irqchip + * VMs in the wild. + */ + static_branch_inc(&userspace_irqchip_in_use); + } /* * Initialize traps for protected VMs. @@ -679,11 +700,6 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu) smp_rmb(); } -static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.target >= 0; -} - static void check_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_request_pending(vcpu)) { @@ -779,13 +795,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) struct kvm_run *run = vcpu->run; int ret; - if (unlikely(!kvm_vcpu_initialized(vcpu))) - return -ENOEXEC; - - ret = kvm_vcpu_first_run_init(vcpu); - if (ret) - return ret; - if (run->exit_reason == KVM_EXIT_MMIO) { ret = kvm_handle_mmio_return(vcpu); if (ret) @@ -849,6 +858,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) } kvm_arm_setup_debug(vcpu); + kvm_arch_vcpu_ctxflush_fp(vcpu); /************************************************************** * Enter the guest @@ -1123,7 +1133,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, * need to invalidate the I-cache though, as FWB does *not* * imply CTR_EL0.DIC. */ - if (vcpu->arch.has_run_once) { + if (vcpu_has_run_once(vcpu)) { if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) stage2_unmap_vm(vcpu->kvm); else diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 5621020b28de..2f48fd362a8c 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -7,7 +7,6 @@ */ #include <linux/irqflags.h> #include <linux/sched.h> -#include <linux/thread_info.h> #include <linux/kvm_host.h> #include <asm/fpsimd.h> #include <asm/kvm_asm.h> @@ -15,6 +14,19 @@ #include <asm/kvm_mmu.h> #include <asm/sysreg.h> +void kvm_vcpu_unshare_task_fp(struct kvm_vcpu *vcpu) +{ + struct task_struct *p = vcpu->arch.parent_task; + struct user_fpsimd_state *fpsimd; + + if (!is_protected_kvm_enabled() || !p) + return; + + fpsimd = &p->thread.uw.fpsimd_state; + kvm_unshare_hyp(fpsimd, fpsimd + 1); + put_task_struct(p); +} + /* * Called on entry to KVM_RUN unless this vcpu previously ran at least * once and the most recent prior KVM_RUN for this vcpu was called from @@ -28,36 +40,29 @@ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu) { int ret; - struct thread_info *ti = ¤t->thread_info; struct user_fpsimd_state *fpsimd = ¤t->thread.uw.fpsimd_state; - /* - * Make sure the host task thread flags and fpsimd state are - * visible to hyp: - */ - ret = create_hyp_mappings(ti, ti + 1, PAGE_HYP); - if (ret) - goto error; + kvm_vcpu_unshare_task_fp(vcpu); - ret = create_hyp_mappings(fpsimd, fpsimd + 1, PAGE_HYP); + /* Make sure the host task fpsimd state is visible to hyp: */ + ret = kvm_share_hyp(fpsimd, fpsimd + 1); if (ret) - goto error; - - if (vcpu->arch.sve_state) { - void *sve_end; + return ret; - sve_end = vcpu->arch.sve_state + vcpu_sve_state_size(vcpu); + vcpu->arch.host_fpsimd_state = kern_hyp_va(fpsimd); - ret = create_hyp_mappings(vcpu->arch.sve_state, sve_end, - PAGE_HYP); - if (ret) - goto error; + /* + * We need to keep current's task_struct pinned until its data has been + * unshared with the hypervisor to make sure it is not re-used by the + * kernel and donated to someone else while already shared -- see + * kvm_vcpu_unshare_task_fp() for the matching put_task_struct(). + */ + if (is_protected_kvm_enabled()) { + get_task_struct(current); + vcpu->arch.parent_task = current; } - vcpu->arch.host_thread_info = kern_hyp_va(ti); - vcpu->arch.host_fpsimd_state = kern_hyp_va(fpsimd); -error: - return ret; + return 0; } /* @@ -66,26 +71,27 @@ error: * * Here, we just set the correct metadata to indicate that the FPSIMD * state in the cpu regs (if any) belongs to current on the host. - * - * TIF_SVE is backed up here, since it may get clobbered with guest state. - * This flag is restored by kvm_arch_vcpu_put_fp(vcpu). */ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) { BUG_ON(!current->mm); + BUG_ON(test_thread_flag(TIF_SVE)); - vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | - KVM_ARM64_HOST_SVE_IN_USE | - KVM_ARM64_HOST_SVE_ENABLED); + vcpu->arch.flags &= ~KVM_ARM64_FP_ENABLED; vcpu->arch.flags |= KVM_ARM64_FP_HOST; - if (test_thread_flag(TIF_SVE)) - vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE; - if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; } +void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu) +{ + if (test_thread_flag(TIF_FOREIGN_FPSTATE)) + vcpu->arch.flags |= KVM_ARM64_FP_FOREIGN_FPSTATE; + else + vcpu->arch.flags &= ~KVM_ARM64_FP_FOREIGN_FPSTATE; +} + /* * If the guest FPSIMD state was loaded, update the host's context * tracking data mark the CPU FPSIMD regs as dirty and belonging to vcpu @@ -115,13 +121,11 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) { unsigned long flags; - bool host_has_sve = system_supports_sve(); - bool guest_has_sve = vcpu_has_sve(vcpu); local_irq_save(flags); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { - if (guest_has_sve) { + if (vcpu_has_sve(vcpu)) { __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR); /* Restore the VL that was saved when bound to the CPU */ @@ -131,7 +135,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) } fpsimd_save_and_flush_cpu_state(); - } else if (has_vhe() && host_has_sve) { + } else if (has_vhe() && system_supports_sve()) { /* * The FPSIMD/SVE state in the CPU has not been touched, and we * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been @@ -145,8 +149,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } - update_thread_flag(TIF_SVE, - vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE); + update_thread_flag(TIF_SVE, 0); local_irq_restore(flags); } diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index b726332eec49..687598e41b21 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -10,4 +10,4 @@ subdir-ccflags-y := -I$(incdir) \ -DDISABLE_BRANCH_PROFILING \ $(DISABLE_STACKLEAK_PLUGIN) -obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o reserved_mem.o +obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S index e950875e31ce..61e6f3ba7b7d 100644 --- a/arch/arm64/kvm/hyp/fpsimd.S +++ b/arch/arm64/kvm/hyp/fpsimd.S @@ -25,9 +25,3 @@ SYM_FUNC_START(__sve_restore_state) sve_load 0, x1, x2, 3 ret SYM_FUNC_END(__sve_restore_state) - -SYM_FUNC_START(__sve_save_state) - mov x2, #1 - sve_save 0, x1, x2, 3 - ret -SYM_FUNC_END(__sve_save_state) diff --git a/arch/arm64/kvm/hyp/hyp-constants.c b/arch/arm64/kvm/hyp/hyp-constants.c new file mode 100644 index 000000000000..b3742a6691e8 --- /dev/null +++ b/arch/arm64/kvm/hyp/hyp-constants.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/kbuild.h> +#include <nvhe/memory.h> + +int main(void) +{ + DEFINE(STRUCT_HYP_PAGE_SIZE, sizeof(struct hyp_page)); + return 0; +} diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 7a0af1d39303..11e8580f2fdc 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -29,7 +29,6 @@ #include <asm/fpsimd.h> #include <asm/debug-monitors.h> #include <asm/processor.h> -#include <asm/thread_info.h> struct kvm_exception_table_entry { int insn, fixup; @@ -49,7 +48,7 @@ static inline bool update_fp_enabled(struct kvm_vcpu *vcpu) * trap the accesses. */ if (!system_supports_fpsimd() || - vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE) + vcpu->arch.flags & KVM_ARM64_FP_FOREIGN_FPSTATE) vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_FP_HOST); @@ -143,16 +142,6 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault); } -static inline void __hyp_sve_save_host(struct kvm_vcpu *vcpu) -{ - struct thread_struct *thread; - - thread = container_of(vcpu->arch.host_fpsimd_state, struct thread_struct, - uw.fpsimd_state); - - __sve_save_state(sve_pffr(thread), &vcpu->arch.host_fpsimd_state->fpsr); -} - static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu) { sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2); @@ -169,21 +158,14 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu) */ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) { - bool sve_guest, sve_host; + bool sve_guest; u8 esr_ec; u64 reg; if (!system_supports_fpsimd()) return false; - if (system_supports_sve()) { - sve_guest = vcpu_has_sve(vcpu); - sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE; - } else { - sve_guest = false; - sve_host = false; - } - + sve_guest = vcpu_has_sve(vcpu); esr_ec = kvm_vcpu_trap_get_class(vcpu); /* Don't handle SVE traps for non-SVE vcpus here: */ @@ -207,11 +189,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) isb(); if (vcpu->arch.flags & KVM_ARM64_FP_HOST) { - if (sve_host) - __hyp_sve_save_host(vcpu); - else - __fpsimd_save_state(vcpu->arch.host_fpsimd_state); - + __fpsimd_save_state(vcpu->arch.host_fpsimd_state); vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; } diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h index b58c910babaf..80e99836eac7 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h @@ -24,6 +24,11 @@ enum pkvm_page_state { PKVM_PAGE_OWNED = 0ULL, PKVM_PAGE_SHARED_OWNED = KVM_PGTABLE_PROT_SW0, PKVM_PAGE_SHARED_BORROWED = KVM_PGTABLE_PROT_SW1, + __PKVM_PAGE_RESERVED = KVM_PGTABLE_PROT_SW0 | + KVM_PGTABLE_PROT_SW1, + + /* Meta-states which aren't encoded directly in the PTE's SW bits */ + PKVM_NOPAGE, }; #define PKVM_PAGE_STATE_PROT_MASK (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1) @@ -50,6 +55,7 @@ extern const u8 pkvm_hyp_id; int __pkvm_prot_finalize(void); int __pkvm_host_share_hyp(u64 pfn); +int __pkvm_host_unshare_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); diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h index c9a8f535212e..2d08510c6cc1 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mm.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h @@ -10,13 +10,8 @@ #include <nvhe/memory.h> #include <nvhe/spinlock.h> -#define HYP_MEMBLOCK_REGIONS 128 -extern struct memblock_region kvm_nvhe_sym(hyp_memory)[]; -extern unsigned int kvm_nvhe_sym(hyp_memblock_nr); extern struct kvm_pgtable pkvm_pgtable; extern hyp_spinlock_t pkvm_pgd_lock; -extern struct hyp_pool hpool; -extern u64 __io_map_base; int hyp_create_idmap(u32 hyp_va_bits); int hyp_map_vectors(void); @@ -39,58 +34,4 @@ static inline void hyp_vmemmap_range(phys_addr_t phys, unsigned long size, *end = ALIGN(*end, PAGE_SIZE); } -static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages) -{ - unsigned long total = 0, i; - - /* Provision the worst case scenario */ - for (i = 0; i < KVM_PGTABLE_MAX_LEVELS; i++) { - nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE); - total += nr_pages; - } - - return total; -} - -static inline unsigned long __hyp_pgtable_total_pages(void) -{ - unsigned long res = 0, i; - - /* Cover all of memory with page-granularity */ - for (i = 0; i < kvm_nvhe_sym(hyp_memblock_nr); i++) { - struct memblock_region *reg = &kvm_nvhe_sym(hyp_memory)[i]; - res += __hyp_pgtable_max_pages(reg->size >> PAGE_SHIFT); - } - - return res; -} - -static inline unsigned long hyp_s1_pgtable_pages(void) -{ - unsigned long res; - - res = __hyp_pgtable_total_pages(); - - /* Allow 1 GiB for private mappings */ - res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT); - - return res; -} - -static inline unsigned long host_s2_pgtable_pages(void) -{ - unsigned long res; - - /* - * Include an extra 16 pages to safely upper-bound the worst case of - * concatenated pgds. - */ - res = __hyp_pgtable_total_pages() + 16; - - /* Allow 1 GiB for MMIO mappings */ - res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT); - - return res; -} - #endif /* __KVM_HYP_MM_H */ diff --git a/arch/arm64/kvm/hyp/nvhe/early_alloc.c b/arch/arm64/kvm/hyp/nvhe/early_alloc.c index 1306c430ab87..00de04153cc6 100644 --- a/arch/arm64/kvm/hyp/nvhe/early_alloc.c +++ b/arch/arm64/kvm/hyp/nvhe/early_alloc.c @@ -43,6 +43,9 @@ void *hyp_early_alloc_page(void *arg) return hyp_early_alloc_contig(1); } +static void hyp_early_alloc_get_page(void *addr) { } +static void hyp_early_alloc_put_page(void *addr) { } + void hyp_early_alloc_init(void *virt, unsigned long size) { base = cur = (unsigned long)virt; @@ -51,4 +54,6 @@ void hyp_early_alloc_init(void *virt, unsigned long size) hyp_early_alloc_mm_ops.zalloc_page = hyp_early_alloc_page; hyp_early_alloc_mm_ops.phys_to_virt = hyp_phys_to_virt; hyp_early_alloc_mm_ops.virt_to_phys = hyp_virt_to_phys; + hyp_early_alloc_mm_ops.get_page = hyp_early_alloc_get_page; + hyp_early_alloc_mm_ops.put_page = hyp_early_alloc_put_page; } diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index b096bf009144..5e2197db0d32 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -147,6 +147,13 @@ static void handle___pkvm_host_share_hyp(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 1) = __pkvm_host_share_hyp(pfn); } +static void handle___pkvm_host_unshare_hyp(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, pfn, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __pkvm_host_unshare_hyp(pfn); +} + static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(phys_addr_t, phys, host_ctxt, 1); @@ -184,6 +191,7 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__pkvm_prot_finalize), HANDLE_FUNC(__pkvm_host_share_hyp), + HANDLE_FUNC(__pkvm_host_unshare_hyp), HANDLE_FUNC(__kvm_adjust_pc), HANDLE_FUNC(__kvm_vcpu_run), HANDLE_FUNC(__kvm_flush_vm_context), diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index c1a90dd022b8..16776d1d6151 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -9,6 +9,7 @@ #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/kvm_pgtable.h> +#include <asm/kvm_pkvm.h> #include <asm/stage2_pgtable.h> #include <hyp/fault.h> @@ -27,6 +28,26 @@ static struct hyp_pool host_s2_pool; const u8 pkvm_hyp_id = 1; +static void host_lock_component(void) +{ + hyp_spin_lock(&host_kvm.lock); +} + +static void host_unlock_component(void) +{ + hyp_spin_unlock(&host_kvm.lock); +} + +static void hyp_lock_component(void) +{ + hyp_spin_lock(&pkvm_pgd_lock); +} + +static void hyp_unlock_component(void) +{ + hyp_spin_unlock(&pkvm_pgd_lock); +} + static void *host_s2_zalloc_pages_exact(size_t size) { void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size)); @@ -338,116 +359,446 @@ static int host_stage2_idmap(u64 addr) prot = is_memory ? PKVM_HOST_MEM_PROT : PKVM_HOST_MMIO_PROT; - hyp_spin_lock(&host_kvm.lock); + host_lock_component(); ret = host_stage2_adjust_range(addr, &range); if (ret) goto unlock; ret = host_stage2_idmap_locked(range.start, range.end - range.start, prot); unlock: - hyp_spin_unlock(&host_kvm.lock); + host_unlock_component(); return ret; } -static inline bool check_prot(enum kvm_pgtable_prot prot, - enum kvm_pgtable_prot required, - enum kvm_pgtable_prot denied) +void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt) { - return (prot & (required | denied)) == required; + struct kvm_vcpu_fault_info fault; + u64 esr, addr; + int ret = 0; + + esr = read_sysreg_el2(SYS_ESR); + BUG_ON(!__get_fault_info(esr, &fault)); + + addr = (fault.hpfar_el2 & HPFAR_MASK) << 8; + ret = host_stage2_idmap(addr); + BUG_ON(ret && ret != -EAGAIN); } -int __pkvm_host_share_hyp(u64 pfn) +/* This corresponds to locking order */ +enum pkvm_component_id { + PKVM_ID_HOST, + PKVM_ID_HYP, +}; + +struct pkvm_mem_transition { + u64 nr_pages; + + struct { + enum pkvm_component_id id; + /* Address in the initiator's address space */ + u64 addr; + + union { + struct { + /* Address in the completer's address space */ + u64 completer_addr; + } host; + }; + } initiator; + + struct { + enum pkvm_component_id id; + } completer; +}; + +struct pkvm_mem_share { + const struct pkvm_mem_transition tx; + const enum kvm_pgtable_prot completer_prot; +}; + +struct check_walk_data { + enum pkvm_page_state desired; + enum pkvm_page_state (*get_page_state)(kvm_pte_t pte); +}; + +static int __check_page_state_visitor(u64 addr, u64 end, u32 level, + kvm_pte_t *ptep, + enum kvm_pgtable_walk_flags flag, + void * const arg) { - 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; + struct check_walk_data *d = arg; + kvm_pte_t pte = *ptep; - if (!addr_is_memory(addr)) + if (kvm_pte_valid(pte) && !addr_is_memory(kvm_pte_to_phys(pte))) return -EINVAL; - hyp_spin_lock(&host_kvm.lock); - hyp_spin_lock(&pkvm_pgd_lock); + return d->get_page_state(pte) == d->desired ? 0 : -EPERM; +} + +static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size, + struct check_walk_data *data) +{ + struct kvm_pgtable_walker walker = { + .cb = __check_page_state_visitor, + .arg = data, + .flags = KVM_PGTABLE_WALK_LEAF, + }; + + return kvm_pgtable_walk(pgt, addr, size, &walker); +} + +static enum pkvm_page_state host_get_page_state(kvm_pte_t pte) +{ + if (!kvm_pte_valid(pte) && pte) + return PKVM_NOPAGE; + + return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); +} + +static int __host_check_page_state_range(u64 addr, u64 size, + enum pkvm_page_state state) +{ + struct check_walk_data d = { + .desired = state, + .get_page_state = host_get_page_state, + }; + + hyp_assert_lock_held(&host_kvm.lock); + return check_page_state_range(&host_kvm.pgt, addr, size, &d); +} + +static int __host_set_page_state_range(u64 addr, u64 size, + enum pkvm_page_state state) +{ + enum kvm_pgtable_prot prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, state); + + return host_stage2_idmap_locked(addr, size, prot); +} + +static int host_request_owned_transition(u64 *completer_addr, + const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + u64 addr = tx->initiator.addr; + + *completer_addr = tx->initiator.host.completer_addr; + return __host_check_page_state_range(addr, size, PKVM_PAGE_OWNED); +} + +static int host_request_unshare(u64 *completer_addr, + const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + u64 addr = tx->initiator.addr; + + *completer_addr = tx->initiator.host.completer_addr; + return __host_check_page_state_range(addr, size, PKVM_PAGE_SHARED_OWNED); +} + +static int host_initiate_share(u64 *completer_addr, + const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + u64 addr = tx->initiator.addr; + + *completer_addr = tx->initiator.host.completer_addr; + return __host_set_page_state_range(addr, size, PKVM_PAGE_SHARED_OWNED); +} + +static int host_initiate_unshare(u64 *completer_addr, + const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + u64 addr = tx->initiator.addr; + + *completer_addr = tx->initiator.host.completer_addr; + return __host_set_page_state_range(addr, size, PKVM_PAGE_OWNED); +} + +static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte) +{ + if (!kvm_pte_valid(pte)) + return PKVM_NOPAGE; + + return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); +} + +static int __hyp_check_page_state_range(u64 addr, u64 size, + enum pkvm_page_state state) +{ + struct check_walk_data d = { + .desired = state, + .get_page_state = hyp_get_page_state, + }; + + hyp_assert_lock_held(&pkvm_pgd_lock); + return check_page_state_range(&pkvm_pgtable, addr, size, &d); +} + +static bool __hyp_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx) +{ + return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) || + tx->initiator.id != PKVM_ID_HOST); +} + +static int hyp_ack_share(u64 addr, const struct pkvm_mem_transition *tx, + enum kvm_pgtable_prot perms) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + + if (perms != PAGE_HYP) + return -EPERM; + + if (__hyp_ack_skip_pgtable_check(tx)) + return 0; + + return __hyp_check_page_state_range(addr, size, PKVM_NOPAGE); +} + +static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + + if (__hyp_ack_skip_pgtable_check(tx)) + return 0; + + return __hyp_check_page_state_range(addr, size, + PKVM_PAGE_SHARED_BORROWED); +} + +static int hyp_complete_share(u64 addr, const struct pkvm_mem_transition *tx, + enum kvm_pgtable_prot perms) +{ + void *start = (void *)addr, *end = start + (tx->nr_pages * PAGE_SIZE); + enum kvm_pgtable_prot prot; + + prot = pkvm_mkstate(perms, PKVM_PAGE_SHARED_BORROWED); + return pkvm_create_mappings_locked(start, end, prot); +} + +static int hyp_complete_unshare(u64 addr, const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + int ret = kvm_pgtable_hyp_unmap(&pkvm_pgtable, addr, size); + + return (ret != size) ? -EFAULT : 0; +} + +static int check_share(struct pkvm_mem_share *share) +{ + const struct pkvm_mem_transition *tx = &share->tx; + u64 completer_addr; + int ret; + + switch (tx->initiator.id) { + case PKVM_ID_HOST: + ret = host_request_owned_transition(&completer_addr, tx); + break; + default: + ret = -EINVAL; + } - ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, NULL); if (ret) - goto unlock; - if (!pte) - goto map_shared; + return ret; - /* - * 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 - */ - 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; + switch (tx->completer.id) { + case PKVM_ID_HYP: + ret = hyp_ack_share(completer_addr, tx, share->completer_prot); + break; + default: + ret = -EINVAL; } - state = pkvm_getstate(cur); - if (state == PKVM_PAGE_OWNED) - goto map_shared; + return ret; +} - /* - * 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; +static int __do_share(struct pkvm_mem_share *share) +{ + const struct pkvm_mem_transition *tx = &share->tx; + u64 completer_addr; + int ret; + + switch (tx->initiator.id) { + case PKVM_ID_HOST: + ret = host_initiate_share(&completer_addr, tx); + break; + default: + ret = -EINVAL; } - ret = kvm_pgtable_get_leaf(&pkvm_pgtable, (u64)virt, &pte, NULL); if (ret) - goto unlock; + return 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; + switch (tx->completer.id) { + case PKVM_ID_HYP: + ret = hyp_complete_share(completer_addr, tx, share->completer_prot); + break; + default: + ret = -EINVAL; + } -map_shared: - /* - * If the page is not yet shared, adjust mappings in both page-tables - * while both locks are held. - */ - prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED); - ret = pkvm_create_mappings_locked(virt, virt + PAGE_SIZE, prot); - BUG_ON(ret); + return ret; +} - prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_OWNED); - ret = host_stage2_idmap_locked(addr, PAGE_SIZE, prot); - BUG_ON(ret); +/* + * do_share(): + * + * The page owner grants access to another component with a given set + * of permissions. + * + * Initiator: OWNED => SHARED_OWNED + * Completer: NOPAGE => SHARED_BORROWED + */ +static int do_share(struct pkvm_mem_share *share) +{ + int ret; -unlock: - hyp_spin_unlock(&pkvm_pgd_lock); - hyp_spin_unlock(&host_kvm.lock); + ret = check_share(share); + if (ret) + return ret; + + return WARN_ON(__do_share(share)); +} + +static int check_unshare(struct pkvm_mem_share *share) +{ + const struct pkvm_mem_transition *tx = &share->tx; + u64 completer_addr; + int ret; + + switch (tx->initiator.id) { + case PKVM_ID_HOST: + ret = host_request_unshare(&completer_addr, tx); + break; + default: + ret = -EINVAL; + } + + if (ret) + return ret; + + switch (tx->completer.id) { + case PKVM_ID_HYP: + ret = hyp_ack_unshare(completer_addr, tx); + break; + default: + ret = -EINVAL; + } return ret; } -void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt) +static int __do_unshare(struct pkvm_mem_share *share) { - struct kvm_vcpu_fault_info fault; - u64 esr, addr; - int ret = 0; + const struct pkvm_mem_transition *tx = &share->tx; + u64 completer_addr; + int ret; - esr = read_sysreg_el2(SYS_ESR); - BUG_ON(!__get_fault_info(esr, &fault)); + switch (tx->initiator.id) { + case PKVM_ID_HOST: + ret = host_initiate_unshare(&completer_addr, tx); + break; + default: + ret = -EINVAL; + } - addr = (fault.hpfar_el2 & HPFAR_MASK) << 8; - ret = host_stage2_idmap(addr); - BUG_ON(ret && ret != -EAGAIN); + if (ret) + return ret; + + switch (tx->completer.id) { + case PKVM_ID_HYP: + ret = hyp_complete_unshare(completer_addr, tx); + break; + default: + ret = -EINVAL; + } + + return ret; +} + +/* + * do_unshare(): + * + * The page owner revokes access from another component for a range of + * pages which were previously shared using do_share(). + * + * Initiator: SHARED_OWNED => OWNED + * Completer: SHARED_BORROWED => NOPAGE + */ +static int do_unshare(struct pkvm_mem_share *share) +{ + int ret; + + ret = check_unshare(share); + if (ret) + return ret; + + return WARN_ON(__do_unshare(share)); +} + +int __pkvm_host_share_hyp(u64 pfn) +{ + int ret; + u64 host_addr = hyp_pfn_to_phys(pfn); + u64 hyp_addr = (u64)__hyp_va(host_addr); + struct pkvm_mem_share share = { + .tx = { + .nr_pages = 1, + .initiator = { + .id = PKVM_ID_HOST, + .addr = host_addr, + .host = { + .completer_addr = hyp_addr, + }, + }, + .completer = { + .id = PKVM_ID_HYP, + }, + }, + .completer_prot = PAGE_HYP, + }; + + host_lock_component(); + hyp_lock_component(); + + ret = do_share(&share); + + hyp_unlock_component(); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_unshare_hyp(u64 pfn) +{ + int ret; + u64 host_addr = hyp_pfn_to_phys(pfn); + u64 hyp_addr = (u64)__hyp_va(host_addr); + struct pkvm_mem_share share = { + .tx = { + .nr_pages = 1, + .initiator = { + .id = PKVM_ID_HOST, + .addr = host_addr, + .host = { + .completer_addr = hyp_addr, + }, + }, + .completer = { + .id = PKVM_ID_HYP, + }, + }, + .completer_prot = PAGE_HYP, + }; + + host_lock_component(); + hyp_lock_component(); + + ret = do_unshare(&share); + + hyp_unlock_component(); + host_unlock_component(); + + return ret; } diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index 2fabeceb889a..526a7d6fa86f 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -8,6 +8,7 @@ #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/kvm_pgtable.h> +#include <asm/kvm_pkvm.h> #include <asm/spectre.h> #include <nvhe/early_alloc.h> @@ -18,11 +19,12 @@ struct kvm_pgtable pkvm_pgtable; hyp_spinlock_t pkvm_pgd_lock; -u64 __io_map_base; struct memblock_region hyp_memory[HYP_MEMBLOCK_REGIONS]; unsigned int hyp_memblock_nr; +static u64 __io_map_base; + static int __pkvm_create_mappings(unsigned long start, unsigned long size, unsigned long phys, enum kvm_pgtable_prot prot) { diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c index 0bd7701ad1df..543cad6c376a 100644 --- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c +++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c @@ -241,7 +241,7 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages, int i; hyp_spin_lock_init(&pool->lock); - pool->max_order = min(MAX_ORDER, get_order(nr_pages << PAGE_SHIFT)); + pool->max_order = min(MAX_ORDER, get_order((nr_pages + 1) << PAGE_SHIFT)); for (i = 0; i < pool->max_order; i++) INIT_LIST_HEAD(&pool->free_area[i]); pool->range_start = phys; diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 578f71798c2e..27af337f9fea 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -8,6 +8,7 @@ #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/kvm_pgtable.h> +#include <asm/kvm_pkvm.h> #include <nvhe/early_alloc.h> #include <nvhe/fixed_config.h> @@ -17,7 +18,6 @@ #include <nvhe/mm.h> #include <nvhe/trap_handler.h> -struct hyp_pool hpool; unsigned long hyp_nr_cpus; #define hyp_percpu_size ((unsigned long)__per_cpu_end - \ @@ -27,6 +27,7 @@ static void *vmemmap_base; static void *hyp_pgt_base; static void *host_s2_pgt_base; static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; +static struct hyp_pool hpool; static int divide_memory_pool(void *virt, unsigned long size) { @@ -165,6 +166,7 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, enum kvm_pgtable_walk_flags flag, void * const arg) { + struct kvm_pgtable_mm_ops *mm_ops = arg; enum kvm_pgtable_prot prot; enum pkvm_page_state state; kvm_pte_t pte = *ptep; @@ -173,6 +175,15 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, if (!kvm_pte_valid(pte)) return 0; + /* + * Fix-up the refcount for the page-table pages as the early allocator + * was unable to access the hyp_vmemmap and so the buddy allocator has + * initialised the refcount to '1'. + */ + mm_ops->get_page(ptep); + if (flag != KVM_PGTABLE_WALK_LEAF) + return 0; + if (level != (KVM_PGTABLE_MAX_LEVELS - 1)) return -EINVAL; @@ -205,7 +216,8 @@ static int finalize_host_mappings(void) { struct kvm_pgtable_walker walker = { .cb = finalize_host_mappings_walker, - .flags = KVM_PGTABLE_WALK_LEAF, + .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, + .arg = pkvm_pgtable.mm_ops, }; int i, ret; @@ -240,19 +252,20 @@ 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, .virt_to_phys = hyp_virt_to_phys, .get_page = hpool_get_page, .put_page = hpool_put_page, + .page_count = hyp_page_count, }; pkvm_pgtable.mm_ops = &pkvm_pgtable_mm_ops; + ret = finalize_host_mappings(); + if (ret) + goto out; + out: /* * We tail-called to here from handle___pkvm_init() and will not return, diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index c0e3fed26d93..329c706af39f 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -25,7 +25,6 @@ #include <asm/fpsimd.h> #include <asm/debug-monitors.h> #include <asm/processor.h> -#include <asm/thread_info.h> #include <nvhe/fixed_config.h> #include <nvhe/mem_protect.h> diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index f8ceebe4982e..adc73f8cd24f 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -383,21 +383,6 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) 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) { @@ -407,11 +392,16 @@ static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level, if (!kvm_block_mapping_supported(addr, end, phys, level)) return false; + data->phys += granule; new = kvm_init_valid_leaf_pte(phys, data->attr, level); - if (hyp_pte_needs_update(old, new)) - smp_store_release(ptep, new); + if (old == new) + return true; + if (!kvm_pte_valid(old)) + data->mm_ops->get_page(ptep); + else if (WARN_ON((old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) + return false; - data->phys += granule; + smp_store_release(ptep, new); return true; } @@ -433,6 +423,7 @@ static int hyp_map_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, return -ENOMEM; kvm_set_table_pte(ptep, childp, mm_ops); + mm_ops->get_page(ptep); return 0; } @@ -460,6 +451,69 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, return ret; } +struct hyp_unmap_data { + u64 unmapped; + struct kvm_pgtable_mm_ops *mm_ops; +}; + +static int hyp_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, + enum kvm_pgtable_walk_flags flag, void * const arg) +{ + kvm_pte_t pte = *ptep, *childp = NULL; + u64 granule = kvm_granule_size(level); + struct hyp_unmap_data *data = arg; + struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; + + if (!kvm_pte_valid(pte)) + return -EINVAL; + + if (kvm_pte_table(pte, level)) { + childp = kvm_pte_follow(pte, mm_ops); + + if (mm_ops->page_count(childp) != 1) + return 0; + + kvm_clear_pte(ptep); + dsb(ishst); + __tlbi_level(vae2is, __TLBI_VADDR(addr, 0), level); + } else { + if (end - addr < granule) + return -EINVAL; + + kvm_clear_pte(ptep); + dsb(ishst); + __tlbi_level(vale2is, __TLBI_VADDR(addr, 0), level); + data->unmapped += granule; + } + + dsb(ish); + isb(); + mm_ops->put_page(ptep); + + if (childp) + mm_ops->put_page(childp); + + return 0; +} + +u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) +{ + struct hyp_unmap_data unmap_data = { + .mm_ops = pgt->mm_ops, + }; + struct kvm_pgtable_walker walker = { + .cb = hyp_unmap_walker, + .arg = &unmap_data, + .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, + }; + + if (!pgt->mm_ops->page_count) + return 0; + + kvm_pgtable_walk(pgt, addr, size, &walker); + return unmap_data.unmapped; +} + int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, struct kvm_pgtable_mm_ops *mm_ops) { @@ -482,8 +536,16 @@ static int hyp_free_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, enum kvm_pgtable_walk_flags flag, void * const arg) { struct kvm_pgtable_mm_ops *mm_ops = arg; + kvm_pte_t pte = *ptep; + + if (!kvm_pte_valid(pte)) + return 0; + + mm_ops->put_page(ptep); + + if (kvm_pte_table(pte, level)) + mm_ops->put_page(kvm_pte_follow(pte, mm_ops)); - mm_ops->put_page((void *)kvm_pte_follow(*ptep, mm_ops)); return 0; } @@ -491,7 +553,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) { struct kvm_pgtable_walker walker = { .cb = hyp_free_walker, - .flags = KVM_PGTABLE_WALK_TABLE_POST, + .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, .arg = pgt->mm_ops, }; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 5a2cb5d9bc4b..1d162b9c78bf 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -24,7 +24,6 @@ #include <asm/fpsimd.h> #include <asm/debug-monitors.h> #include <asm/processor.h> -#include <asm/thread_info.h> /* VHE specific context */ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 326cdfec74a1..b53e5bc3f4c3 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -239,6 +239,9 @@ void free_hyp_pgds(void) static bool kvm_host_owns_hyp_mappings(void) { + if (is_kernel_in_hyp_mode()) + return false; + if (static_branch_likely(&kvm_protected_mode_initialized)) return false; @@ -281,14 +284,117 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr) } } -static int pkvm_share_hyp(phys_addr_t start, phys_addr_t end) +struct hyp_shared_pfn { + u64 pfn; + int count; + struct rb_node node; +}; + +static DEFINE_MUTEX(hyp_shared_pfns_lock); +static struct rb_root hyp_shared_pfns = RB_ROOT; + +static struct hyp_shared_pfn *find_shared_pfn(u64 pfn, struct rb_node ***node, + struct rb_node **parent) { - phys_addr_t addr; + struct hyp_shared_pfn *this; + + *node = &hyp_shared_pfns.rb_node; + *parent = NULL; + while (**node) { + this = container_of(**node, struct hyp_shared_pfn, node); + *parent = **node; + if (this->pfn < pfn) + *node = &((**node)->rb_left); + else if (this->pfn > pfn) + *node = &((**node)->rb_right); + else + return this; + } + + return NULL; +} + +static int share_pfn_hyp(u64 pfn) +{ + struct rb_node **node, *parent; + struct hyp_shared_pfn *this; + int ret = 0; + + mutex_lock(&hyp_shared_pfns_lock); + this = find_shared_pfn(pfn, &node, &parent); + if (this) { + this->count++; + goto unlock; + } + + this = kzalloc(sizeof(*this), GFP_KERNEL); + if (!this) { + ret = -ENOMEM; + goto unlock; + } + + this->pfn = pfn; + this->count = 1; + rb_link_node(&this->node, parent, node); + rb_insert_color(&this->node, &hyp_shared_pfns); + ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn, 1); +unlock: + mutex_unlock(&hyp_shared_pfns_lock); + + return ret; +} + +static int unshare_pfn_hyp(u64 pfn) +{ + struct rb_node **node, *parent; + struct hyp_shared_pfn *this; + int ret = 0; + + mutex_lock(&hyp_shared_pfns_lock); + this = find_shared_pfn(pfn, &node, &parent); + if (WARN_ON(!this)) { + ret = -ENOENT; + goto unlock; + } + + this->count--; + if (this->count) + goto unlock; + + rb_erase(&this->node, &hyp_shared_pfns); + kfree(this); + ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn, 1); +unlock: + mutex_unlock(&hyp_shared_pfns_lock); + + return ret; +} + +int kvm_share_hyp(void *from, void *to) +{ + phys_addr_t start, end, cur; + u64 pfn; 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 (is_kernel_in_hyp_mode()) + return 0; + + /* + * The share hcall maps things in the 'fixed-offset' region of the hyp + * VA space, so we can only share physically contiguous data-structures + * for now. + */ + if (is_vmalloc_or_module_addr(from) || is_vmalloc_or_module_addr(to)) + return -EINVAL; + + if (kvm_host_owns_hyp_mappings()) + return create_hyp_mappings(from, to, PAGE_HYP); + + start = ALIGN_DOWN(__pa(from), PAGE_SIZE); + end = PAGE_ALIGN(__pa(to)); + for (cur = start; cur < end; cur += PAGE_SIZE) { + pfn = __phys_to_pfn(cur); + ret = share_pfn_hyp(pfn); if (ret) return ret; } @@ -296,6 +402,22 @@ static int pkvm_share_hyp(phys_addr_t start, phys_addr_t end) return 0; } +void kvm_unshare_hyp(void *from, void *to) +{ + phys_addr_t start, end, cur; + u64 pfn; + + if (is_kernel_in_hyp_mode() || kvm_host_owns_hyp_mappings() || !from) + return; + + start = ALIGN_DOWN(__pa(from), PAGE_SIZE); + end = PAGE_ALIGN(__pa(to)); + for (cur = start; cur < end; cur += PAGE_SIZE) { + pfn = __phys_to_pfn(cur); + WARN_ON(unshare_pfn_hyp(pfn)); + } +} + /** * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode * @from: The virtual kernel start address of the range @@ -316,12 +438,8 @@ 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)); - } + if (!kvm_host_owns_hyp_mappings()) + return -EPERM; start = start & PAGE_MASK; end = PAGE_ALIGN(end); @@ -407,6 +525,9 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, unsigned long addr; int ret; + if (is_protected_kvm_enabled()) + return -EPERM; + *kaddr = ioremap(phys_addr, size); if (!*kaddr) return -ENOMEM; @@ -650,6 +771,9 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, KVM_PGTABLE_PROT_R | (writable ? KVM_PGTABLE_PROT_W : 0); + if (is_protected_kvm_enabled()) + return -EPERM; + size += offset_in_page(guest_ipa); guest_ipa &= PAGE_MASK; diff --git a/arch/arm64/kvm/hyp/reserved_mem.c b/arch/arm64/kvm/pkvm.c index 578670e3f608..ebecb7c045f4 100644 --- a/arch/arm64/kvm/hyp/reserved_mem.c +++ b/arch/arm64/kvm/pkvm.c @@ -8,10 +8,9 @@ #include <linux/memblock.h> #include <linux/sort.h> -#include <asm/kvm_host.h> +#include <asm/kvm_pkvm.h> -#include <nvhe/memory.h> -#include <nvhe/mm.h> +#include "hyp_constants.h" static struct memblock_region *hyp_memory = kvm_nvhe_sym(hyp_memory); static unsigned int *hyp_memblock_nr_ptr = &kvm_nvhe_sym(hyp_memblock_nr); @@ -82,7 +81,8 @@ void __init kvm_hyp_reserve(void) do { prev = nr_pages; nr_pages = hyp_mem_pages + prev; - nr_pages = DIV_ROUND_UP(nr_pages * sizeof(struct hyp_page), PAGE_SIZE); + nr_pages = DIV_ROUND_UP(nr_pages * STRUCT_HYP_PAGE_SIZE, + PAGE_SIZE); nr_pages += __hyp_pgtable_max_pages(nr_pages); } while (nr_pages != prev); hyp_mem_pages += nr_pages; diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index a5e4bbf5e68f..ca92cc5c71c6 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -28,6 +28,7 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm) case ID_AA64DFR0_PMUVER_8_1: case ID_AA64DFR0_PMUVER_8_4: case ID_AA64DFR0_PMUVER_8_5: + case ID_AA64DFR0_PMUVER_8_7: return GENMASK(15, 0); default: /* Shouldn't be here, just for sanity */ WARN_ONCE(1, "Unknown PMU version %d\n", kvm->arch.pmuver); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 426bd7fbc3fd..798a84eddbde 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -94,6 +94,8 @@ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu) { void *buf; unsigned int vl; + size_t reg_sz; + int ret; vl = vcpu->arch.sve_max_vl; @@ -106,10 +108,17 @@ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu) vl > SVE_VL_ARCH_MAX)) return -EIO; - buf = kzalloc(SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)), GFP_KERNEL_ACCOUNT); + reg_sz = vcpu_sve_state_size(vcpu); + buf = kzalloc(reg_sz, GFP_KERNEL_ACCOUNT); if (!buf) return -ENOMEM; + ret = kvm_share_hyp(buf, buf + reg_sz); + if (ret) { + kfree(buf); + return ret; + } + vcpu->arch.sve_state = buf; vcpu->arch.flags |= KVM_ARM64_VCPU_SVE_FINALIZED; return 0; @@ -141,7 +150,13 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu) void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) { - kfree(vcpu->arch.sve_state); + void *sve_state = vcpu->arch.sve_state; + + kvm_vcpu_unshare_task_fp(vcpu); + kvm_unshare_hyp(vcpu, vcpu + 1); + if (sve_state) + kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); + kfree(sve_state); } static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 0a06d0648970..ce2b42c38e62 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -91,7 +91,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) return ret; kvm_for_each_vcpu(i, vcpu, kvm) { - if (vcpu->arch.has_run_once) + if (vcpu_has_run_once(vcpu)) goto out_unlock; } ret = 0; diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index bf7ec4a78497..9943a3fe1b0a 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -763,10 +763,12 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm) } if (ret) { - /* The current c failed, so we start with the previous one. */ + /* The current c failed, so iterate over the previous ones. */ + int i; + mutex_lock(&kvm->slots_lock); - for (c--; c >= 0; c--) { - vcpu = kvm_get_vcpu(kvm, c); + for (i = 0; i < c; i++) { + vcpu = kvm_get_vcpu(kvm, i); vgic_unregister_redist_iodev(vcpu); } mutex_unlock(&kvm->slots_lock); diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index 48c6067fc5ec..7068da080799 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -1050,7 +1050,7 @@ static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, return 0; } -struct kvm_io_device_ops kvm_io_gic_ops = { +const struct kvm_io_device_ops kvm_io_gic_ops = { .read = dispatch_mmio_read, .write = dispatch_mmio_write, }; diff --git a/arch/arm64/kvm/vgic/vgic-mmio.h b/arch/arm64/kvm/vgic/vgic-mmio.h index fefcca2b14dc..3fa696f198a3 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.h +++ b/arch/arm64/kvm/vgic/vgic-mmio.h @@ -34,7 +34,7 @@ struct vgic_register_region { }; }; -extern struct kvm_io_device_ops kvm_io_gic_ops; +extern const struct kvm_io_device_ops kvm_io_gic_ops; #define VGIC_ACCESS_8bit 1 #define VGIC_ACCESS_32bit 2 diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c index 95a18cec14a3..645648349c99 100644 --- a/arch/arm64/kvm/vgic/vgic-v2.c +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -293,12 +293,12 @@ int vgic_v2_map_resources(struct kvm *kvm) if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) { - kvm_err("Need to set vgic cpu and dist addresses first\n"); + kvm_debug("Need to set vgic cpu and dist addresses first\n"); return -ENXIO; } if (!vgic_v2_check_base(dist->vgic_dist_base, dist->vgic_cpu_base)) { - kvm_err("VGIC CPU and dist frames overlap\n"); + kvm_debug("VGIC CPU and dist frames overlap\n"); return -EINVAL; } @@ -345,6 +345,11 @@ int vgic_v2_probe(const struct gic_kvm_info *info) int ret; u32 vtr; + if (is_protected_kvm_enabled()) { + kvm_err("GICv2 not supported in protected mode\n"); + return -ENXIO; + } + if (!info->vctrl.start) { kvm_err("GICH not present in the firmware table\n"); return -ENXIO; diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 04f62c4b07fb..78cf674c1230 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -554,12 +554,12 @@ int vgic_v3_map_resources(struct kvm *kvm) } if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { - kvm_err("Need to set vgic distributor addresses first\n"); + kvm_debug("Need to set vgic distributor addresses first\n"); return -ENXIO; } if (!vgic_v3_check_base(kvm)) { - kvm_err("VGIC redist and dist frames overlap\n"); + kvm_debug("VGIC redist and dist frames overlap\n"); return -EINVAL; } @@ -651,7 +651,7 @@ int vgic_v3_probe(const struct gic_kvm_info *info) } else if (!PAGE_ALIGNED(info->vcpu.start)) { pr_warn("GICV physical address 0x%llx not page aligned\n", (unsigned long long)info->vcpu.start); - } else { + } else if (kvm_get_mode() != KVM_MODE_PROTECTED) { kvm_vgic_global_state.vcpu_base = info->vcpu.start; kvm_vgic_global_state.can_emulate_gicv2 = true; ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c310648cc8f1..6d138adc78af 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1174,7 +1174,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 27d8e1bb5b36..8f9f46979a00 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -113,6 +113,9 @@ enum { #define ESR_EC_WP_CURRENT 0x35 #define ESR_EC_BRK_INS 0x3c +void aarch64_get_supported_page_sizes(uint32_t ipa, + bool *ps4k, bool *ps16k, bool *ps64k); + void vm_init_descriptor_tables(struct kvm_vm *vm); void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index db36e6c49983..83e93a65db29 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -42,18 +42,26 @@ enum vm_guest_mode { VM_MODE_P52V48_4K, VM_MODE_P52V48_64K, VM_MODE_P48V48_4K, + VM_MODE_P48V48_16K, VM_MODE_P48V48_64K, VM_MODE_P40V48_4K, + VM_MODE_P40V48_16K, VM_MODE_P40V48_64K, VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ VM_MODE_P47V64_4K, VM_MODE_P44V64_4K, + VM_MODE_P36V48_4K, + VM_MODE_P36V48_16K, + VM_MODE_P36V48_64K, + VM_MODE_P36V47_16K, NUM_VM_MODES, }; #if defined(__aarch64__) -#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +extern enum vm_guest_mode vm_mode_default; + +#define VM_MODE_DEFAULT vm_mode_default #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 8) diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index b4eeeafd2a70..9343d82519b4 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -8,6 +8,7 @@ #include <linux/compiler.h> #include <assert.h> +#include "guest_modes.h" #include "kvm_util.h" #include "../kvm_util_internal.h" #include "processor.h" @@ -237,6 +238,7 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1); get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1); + /* Configure base granule size */ switch (vm->mode) { case VM_MODE_P52V48_4K: TEST_FAIL("AArch64 does not support 4K sized pages " @@ -245,25 +247,47 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init TEST_FAIL("AArch64 does not support 4K sized pages " "with ANY-bit physical address ranges"); case VM_MODE_P52V48_64K: + case VM_MODE_P48V48_64K: + case VM_MODE_P40V48_64K: + case VM_MODE_P36V48_64K: tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ - tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + break; + case VM_MODE_P48V48_16K: + case VM_MODE_P40V48_16K: + case VM_MODE_P36V48_16K: + case VM_MODE_P36V47_16K: + tcr_el1 |= 2ul << 14; /* TG0 = 16KB */ break; case VM_MODE_P48V48_4K: + case VM_MODE_P40V48_4K: + case VM_MODE_P36V48_4K: tcr_el1 |= 0ul << 14; /* TG0 = 4KB */ - tcr_el1 |= 5ul << 32; /* IPS = 48 bits */ break; + default: + TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); + } + + /* Configure output size */ + switch (vm->mode) { + case VM_MODE_P52V48_64K: + tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + break; + case VM_MODE_P48V48_4K: + case VM_MODE_P48V48_16K: case VM_MODE_P48V48_64K: - tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ tcr_el1 |= 5ul << 32; /* IPS = 48 bits */ break; case VM_MODE_P40V48_4K: - tcr_el1 |= 0ul << 14; /* TG0 = 4KB */ - tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ - break; + case VM_MODE_P40V48_16K: case VM_MODE_P40V48_64K: - tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ break; + case VM_MODE_P36V48_4K: + case VM_MODE_P36V48_16K: + case VM_MODE_P36V48_64K: + case VM_MODE_P36V47_16K: + tcr_el1 |= 1ul << 32; /* IPS = 36 bits */ + break; default: TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); } @@ -432,3 +456,47 @@ uint32_t guest_get_vcpuid(void) { return read_sysreg(tpidr_el1); } + +void aarch64_get_supported_page_sizes(uint32_t ipa, + bool *ps4k, bool *ps16k, bool *ps64k) +{ + struct kvm_vcpu_init preferred_init; + int kvm_fd, vm_fd, vcpu_fd, err; + uint64_t val; + struct kvm_one_reg reg = { + .id = KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1), + .addr = (uint64_t)&val, + }; + + kvm_fd = open_kvm_dev_path_or_exit(); + vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, ipa); + TEST_ASSERT(vm_fd >= 0, "Can't create VM"); + + vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0); + TEST_ASSERT(vcpu_fd >= 0, "Can't create vcpu"); + + err = ioctl(vm_fd, KVM_ARM_PREFERRED_TARGET, &preferred_init); + TEST_ASSERT(err == 0, "Can't get target"); + err = ioctl(vcpu_fd, KVM_ARM_VCPU_INIT, &preferred_init); + TEST_ASSERT(err == 0, "Can't get init vcpu"); + + err = ioctl(vcpu_fd, KVM_GET_ONE_REG, ®); + TEST_ASSERT(err == 0, "Can't get MMFR0"); + + *ps4k = ((val >> 28) & 0xf) != 0xf; + *ps64k = ((val >> 24) & 0xf) == 0; + *ps16k = ((val >> 20) & 0xf) != 0; + + close(vcpu_fd); + close(vm_fd); + close(kvm_fd); +} + +/* + * arm64 doesn't have a true default mode, so start by computing the + * available IPA space and page sizes early. + */ +void __attribute__((constructor)) init_guest_modes(void) +{ + guest_modes_append_default(); +} diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index c330f414ef96..da315d3373a3 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -4,22 +4,59 @@ */ #include "guest_modes.h" +#ifdef __aarch64__ +#include "processor.h" +enum vm_guest_mode vm_mode_default; +#endif + struct guest_mode guest_modes[NUM_VM_MODES]; void guest_modes_append_default(void) { +#ifndef __aarch64__ guest_mode_append(VM_MODE_DEFAULT, true, true); - -#ifdef __aarch64__ - guest_mode_append(VM_MODE_P40V48_64K, true, true); +#else { unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + bool ps4k, ps16k, ps64k; + int i; + + aarch64_get_supported_page_sizes(limit, &ps4k, &ps16k, &ps64k); + + vm_mode_default = NUM_VM_MODES; + if (limit >= 52) - guest_mode_append(VM_MODE_P52V48_64K, true, true); + guest_mode_append(VM_MODE_P52V48_64K, ps64k, ps64k); if (limit >= 48) { - guest_mode_append(VM_MODE_P48V48_4K, true, true); - guest_mode_append(VM_MODE_P48V48_64K, true, true); + guest_mode_append(VM_MODE_P48V48_4K, ps4k, ps4k); + guest_mode_append(VM_MODE_P48V48_16K, ps16k, ps16k); + guest_mode_append(VM_MODE_P48V48_64K, ps64k, ps64k); + } + if (limit >= 40) { + guest_mode_append(VM_MODE_P40V48_4K, ps4k, ps4k); + guest_mode_append(VM_MODE_P40V48_16K, ps16k, ps16k); + guest_mode_append(VM_MODE_P40V48_64K, ps64k, ps64k); + if (ps4k) + vm_mode_default = VM_MODE_P40V48_4K; + } + if (limit >= 36) { + guest_mode_append(VM_MODE_P36V48_4K, ps4k, ps4k); + guest_mode_append(VM_MODE_P36V48_16K, ps16k, ps16k); + guest_mode_append(VM_MODE_P36V48_64K, ps64k, ps64k); + guest_mode_append(VM_MODE_P36V47_16K, ps16k, ps16k); } + + /* + * Pick the first supported IPA size if the default + * isn't available. + */ + for (i = 0; vm_mode_default == NUM_VM_MODES && i < NUM_VM_MODES; i++) { + if (guest_modes[i].supported && guest_modes[i].enabled) + vm_mode_default = i; + } + + TEST_ASSERT(vm_mode_default != NUM_VM_MODES, + "No supported mode!"); } #endif #ifdef __s390x__ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 68b56e7e6808..f73516cb91f3 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -166,12 +166,18 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P52V48_4K] = "PA-bits:52, VA-bits:48, 4K pages", [VM_MODE_P52V48_64K] = "PA-bits:52, VA-bits:48, 64K pages", [VM_MODE_P48V48_4K] = "PA-bits:48, VA-bits:48, 4K pages", + [VM_MODE_P48V48_16K] = "PA-bits:48, VA-bits:48, 16K pages", [VM_MODE_P48V48_64K] = "PA-bits:48, VA-bits:48, 64K pages", [VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages", + [VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K pages", [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages", + [VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages", + [VM_MODE_P36V48_16K] = "PA-bits:36, VA-bits:48, 16K pages", + [VM_MODE_P36V48_64K] = "PA-bits:36, VA-bits:48, 64K pages", + [VM_MODE_P36V47_16K] = "PA-bits:36, VA-bits:47, 16K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); @@ -185,12 +191,18 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { [VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 }, [VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 }, [VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 }, + [VM_MODE_P48V48_16K] = { 48, 48, 0x4000, 14 }, [VM_MODE_P48V48_64K] = { 48, 48, 0x10000, 16 }, [VM_MODE_P40V48_4K] = { 40, 48, 0x1000, 12 }, + [VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 }, [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 }, [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 }, [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 }, [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 }, + [VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 }, + [VM_MODE_P36V48_16K] = { 36, 48, 0x4000, 14 }, + [VM_MODE_P36V48_64K] = { 36, 48, 0x10000, 16 }, + [VM_MODE_P36V47_16K] = { 36, 47, 0x4000, 14 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -252,9 +264,19 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) vm->pgtable_levels = 3; break; case VM_MODE_P40V48_4K: + case VM_MODE_P36V48_4K: vm->pgtable_levels = 4; break; case VM_MODE_P40V48_64K: + case VM_MODE_P36V48_64K: + vm->pgtable_levels = 3; + break; + case VM_MODE_P48V48_16K: + case VM_MODE_P40V48_16K: + case VM_MODE_P36V48_16K: + vm->pgtable_levels = 4; + break; + case VM_MODE_P36V47_16K: vm->pgtable_levels = 3; break; case VM_MODE_PXXV48_4K: |