From: Marc Zyngier <maz@kernel.org>
To: kvmarm@lists.linux.dev, kvm@vger.kernel.org,
linux-arm-kernel@lists.infradead.org
Cc: Alexandru Elisei <alexandru.elisei@arm.com>,
Andre Przywara <andre.przywara@arm.com>,
Chase Conklin <chase.conklin@arm.com>,
Christoffer Dall <christoffer.dall@arm.com>,
Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>,
Darren Hart <darren@os.amperecomputing.com>,
Jintack Lim <jintack@cs.columbia.edu>,
Russell King <rmk+kernel@armlinux.org.uk>,
Miguel Luis <miguel.luis@oracle.com>,
James Morse <james.morse@arm.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
Oliver Upton <oliver.upton@linux.dev>,
Zenghui Yu <yuzenghui@huawei.com>
Subject: [PATCH v10 25/59] KVM: arm64: nv: Support multiple nested Stage-2 mmu structures
Date: Mon, 15 May 2023 18:30:29 +0100 [thread overview]
Message-ID: <20230515173103.1017669-26-maz@kernel.org> (raw)
In-Reply-To: <20230515173103.1017669-1-maz@kernel.org>
Add Stage-2 mmu data structures for virtual EL2 and for nested guests.
We don't yet populate shadow Stage-2 page tables, but we now have a
framework for getting to a shadow Stage-2 pgd.
We allocate twice the number of vcpus as Stage-2 mmu structures because
that's sufficient for each vcpu running two translation regimes without
having to flush the Stage-2 page tables.
Co-developed-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
arch/arm64/include/asm/kvm_host.h | 41 ++++++
arch/arm64/include/asm/kvm_mmu.h | 9 ++
arch/arm64/include/asm/kvm_nested.h | 7 +
arch/arm64/kvm/arm.c | 18 ++-
arch/arm64/kvm/mmu.c | 78 ++++++++---
arch/arm64/kvm/nested.c | 210 ++++++++++++++++++++++++++++
arch/arm64/kvm/reset.c | 6 +
7 files changed, 345 insertions(+), 24 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 65810618cb42..2e2969f53b4a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -170,8 +170,40 @@ struct kvm_s2_mmu {
int __percpu *last_vcpu_ran;
struct kvm_arch *arch;
+
+ /*
+ * For a shadow stage-2 MMU, the virtual vttbr used by the
+ * host to parse the guest S2.
+ * This either contains:
+ * - the virtual VTTBR programmed by the guest hypervisor with
+ * CnP cleared
+ * - The value 1 (VMID=0, BADDR=0, CnP=1) if invalid
+ *
+ * We also cache the full VTCR which gets used for TLB invalidation,
+ * taking the ARM ARM's "Any of the bits in VTCR_EL2 are permitted
+ * to be cached in a TLB" to the letter.
+ */
+ u64 tlb_vttbr;
+ u64 tlb_vtcr;
+
+ /*
+ * true when this represents a nested context where virtual
+ * HCR_EL2.VM == 1
+ */
+ bool nested_stage2_enabled;
+
+ /*
+ * 0: Nobody is currently using this, check vttbr for validity
+ * >0: Somebody is actively using this.
+ */
+ atomic_t refcnt;
};
+static inline bool kvm_s2_mmu_valid(struct kvm_s2_mmu *mmu)
+{
+ return !(mmu->tlb_vttbr & 1);
+}
+
struct kvm_arch_memory_slot {
};
@@ -198,6 +230,14 @@ struct kvm_protected_vm {
struct kvm_arch {
struct kvm_s2_mmu mmu;
+ /*
+ * Stage 2 paging state for VMs with nested S2 using a virtual
+ * VMID.
+ */
+ struct kvm_s2_mmu *nested_mmus;
+ size_t nested_mmus_size;
+ int nested_mmus_next;
+
/* Interrupt controller */
struct vgic_dist vgic;
@@ -1082,6 +1122,7 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
int __init kvm_set_ipa_limit(void);
+u32 kvm_get_pa_bits(struct kvm *kvm);
#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 346754b2f3b0..896acdf98e71 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -119,6 +119,7 @@ alternative_cb_end
#include <asm/mmu_context.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_host.h>
+#include <asm/kvm_nested.h>
void kvm_update_va_mask(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst);
@@ -170,6 +171,7 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
void **haddr);
void __init free_hyp_pgds(void);
+void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
void stage2_unmap_vm(struct kvm *kvm);
int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);
void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
@@ -311,5 +313,12 @@ static inline struct kvm *kvm_s2_mmu_to_kvm(struct kvm_s2_mmu *mmu)
{
return container_of(mmu->arch, struct kvm, arch);
}
+
+static inline u64 get_vmid(u64 vttbr)
+{
+ return (vttbr & VTTBR_VMID_MASK(kvm_get_vmid_bits())) >>
+ VTTBR_VMID_SHIFT;
+}
+
#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 948ba0337558..d57e609dd3f4 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -59,6 +59,13 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
return ttbr0 & ~GENMASK_ULL(63, 48);
}
+extern void kvm_init_nested(struct kvm *kvm);
+extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu);
+extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);
+extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu);
+extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
+extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
+
extern bool forward_smc_trap(struct kvm_vcpu *vcpu);
extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 7b0241eb7483..9036206f0be8 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -36,9 +36,10 @@
#include <asm/virt.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
#include <asm/kvm_pkvm.h>
-#include <asm/kvm_emulate.h>
#include <asm/sections.h>
#include <kvm/arm_hypercalls.h>
@@ -138,6 +139,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
mutex_unlock(&kvm->lock);
#endif
+ kvm_init_nested(kvm);
+
ret = kvm_share_hyp(kvm, kvm + 1);
if (ret)
return ret;
@@ -413,6 +416,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
struct kvm_s2_mmu *mmu;
int *last_ran;
+ if (vcpu_has_nv(vcpu))
+ kvm_vcpu_load_hw_mmu(vcpu);
+
mmu = vcpu->arch.hw_mmu;
last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
@@ -463,9 +469,12 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
kvm_timer_vcpu_put(vcpu);
kvm_vgic_put(vcpu);
kvm_vcpu_pmu_restore_host(vcpu);
+ if (vcpu_has_nv(vcpu))
+ kvm_vcpu_put_hw_mmu(vcpu);
kvm_arm_vmid_clear_active();
vcpu_clear_on_unsupported_cpu(vcpu);
+
vcpu->cpu = -1;
}
@@ -1206,8 +1215,13 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
vcpu->arch.target = phys_target;
+ /* Prepare for nested if required */
+ ret = kvm_vcpu_init_nested(vcpu);
+
/* Now we know what it is, we can reset it. */
- ret = kvm_reset_vcpu(vcpu);
+ if (!ret)
+ ret = kvm_reset_vcpu(vcpu);
+
if (ret) {
vcpu->arch.target = -1;
bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c934c911c702..3268936eec40 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -217,7 +217,7 @@ static void invalidate_icache_guest_page(void *va, size_t size)
* does.
*/
/**
- * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
+ * __unmap_stage2_range -- Clear stage2 page table entries to unmap a range
* @mmu: The KVM stage-2 MMU pointer
* @start: The intermediate physical base address of the range to unmap
* @size: The size of the area to unmap
@@ -240,7 +240,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
may_block));
}
-static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
{
__unmap_stage2_range(mmu, start, size, true);
}
@@ -711,21 +711,9 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
.icache_inval_pou = invalidate_icache_guest_page,
};
-/**
- * kvm_init_stage2_mmu - Initialise a S2 MMU structure
- * @kvm: The pointer to the KVM structure
- * @mmu: The pointer to the s2 MMU structure
- * @type: The machine type of the virtual machine
- *
- * Allocates only the stage-2 HW PGD level table(s).
- * Note we don't need locking here as this is only called when the VM is
- * created, which can only be done once.
- */
-int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type)
+static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
{
u32 kvm_ipa_limit = get_kvm_ipa_limit();
- int cpu, err;
- struct kvm_pgtable *pgt;
u64 mmfr0, mmfr1;
u32 phys_shift;
@@ -752,11 +740,58 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);
+ return 0;
+}
+
+/**
+ * kvm_init_stage2_mmu - Initialise a S2 MMU structure
+ * @kvm: The pointer to the KVM structure
+ * @mmu: The pointer to the s2 MMU structure
+ * @type: The machine type of the virtual machine
+ *
+ * Allocates only the stage-2 HW PGD level table(s).
+ * Note we don't need locking here as this is only called in two cases:
+ *
+ * - when the VM is created, which can't race against anything
+ *
+ * - when secondary kvm_s2_mmu structures are initialised for NV
+ * guests, and the caller must hold kvm->lock as this is called on a
+ * per-vcpu basis.
+ */
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type)
+{
+ int cpu, err;
+ struct kvm_pgtable *pgt;
+
+ /*
+ * If we already have our page tables in place, and that the
+ * MMU context is the canonical one, we have a bug somewhere,
+ * as this is only supposed to ever happen once per VM.
+ *
+ * Otherwise, we're building nested page tables, and that's
+ * probably because userspace called KVM_ARM_VCPU_INIT more
+ * than once on the same vcpu. Since that's actually legal,
+ * don't kick a fuss and leave gracefully.
+ */
if (mmu->pgt != NULL) {
+ if (&kvm->arch.mmu != mmu)
+ return 0;
+
kvm_err("kvm_arch already initialized?\n");
return -EINVAL;
}
+ /*
+ * We only initialise the IPA range on the canonical MMU, so
+ * the type is meaningless in all other situations.
+ */
+ if (&kvm->arch.mmu != mmu)
+ type = kvm_get_pa_bits(kvm);
+
+ err = kvm_init_ipa_range(mmu, type);
+ if (err)
+ return err;
+
pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT);
if (!pgt)
return -ENOMEM;
@@ -777,6 +812,10 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
mmu->pgt = pgt;
mmu->pgd_phys = __pa(pgt->pgd);
+
+ if (&kvm->arch.mmu != mmu)
+ kvm_init_nested_s2_mmu(mmu);
+
return 0;
out_destroy_pgtable:
@@ -822,7 +861,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
if (!(vma->vm_flags & VM_PFNMAP)) {
gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
- unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
+ kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
}
hva = vm_end;
} while (hva < reg_end);
@@ -1876,11 +1915,6 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
{
}
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
- kvm_free_stage2_pgd(&kvm->arch.mmu);
-}
-
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot)
{
@@ -1888,7 +1922,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
phys_addr_t size = slot->npages << PAGE_SHIFT;
write_lock(&kvm->mmu_lock);
- unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+ kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, size);
write_unlock(&kvm->mmu_lock);
}
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 7f80f385d9e8..c3da57d16d88 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -7,7 +7,9 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <asm/kvm_arm.h>
#include <asm/kvm_emulate.h>
+#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/sysreg.h>
@@ -16,6 +18,214 @@
/* Protection against the sysreg repainting madness... */
#define NV_FTR(r, f) ID_AA64##r##_EL1_##f
+void kvm_init_nested(struct kvm *kvm)
+{
+ kvm->arch.nested_mmus = NULL;
+ kvm->arch.nested_mmus_size = 0;
+}
+
+int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_s2_mmu *tmp;
+ int num_mmus;
+ int ret = -ENOMEM;
+
+ if (!test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features))
+ return 0;
+
+ if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
+ return -EINVAL;
+
+ mutex_lock(&kvm->arch.config_lock);
+
+ /*
+ * Let's treat memory allocation failures as benign: If we fail to
+ * allocate anything, return an error and keep the allocated array
+ * alive. Userspace may try to recover by intializing the vcpu
+ * again, and there is no reason to affect the whole VM for this.
+ */
+ num_mmus = atomic_read(&kvm->online_vcpus) * 2;
+ tmp = krealloc(kvm->arch.nested_mmus,
+ num_mmus * sizeof(*kvm->arch.nested_mmus),
+ GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ if (tmp) {
+ /*
+ * If we went through a realocation, adjust the MMU
+ * back-pointers in the previously initialised
+ * pg_table structures.
+ */
+ if (kvm->arch.nested_mmus != tmp) {
+ int i;
+
+ for (i = 0; i < num_mmus - 2; i++)
+ tmp[i].pgt->mmu = &tmp[i];
+ }
+
+ if (kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 1], 0) ||
+ kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 2], 0)) {
+ kvm_free_stage2_pgd(&tmp[num_mmus - 1]);
+ kvm_free_stage2_pgd(&tmp[num_mmus - 2]);
+ } else {
+ kvm->arch.nested_mmus_size = num_mmus;
+ ret = 0;
+ }
+
+ kvm->arch.nested_mmus = tmp;
+ }
+
+ mutex_unlock(&kvm->arch.config_lock);
+ return ret;
+}
+
+/* Must be called with kvm->mmu_lock held */
+struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu)
+{
+ bool nested_stage2_enabled;
+ u64 vttbr, vtcr, hcr;
+ struct kvm *kvm;
+ int i;
+
+ kvm = vcpu->kvm;
+
+ vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+ vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+ hcr = vcpu_read_sys_reg(vcpu, HCR_EL2);
+
+ nested_stage2_enabled = hcr & HCR_VM;
+
+ /* Don't consider the CnP bit for the vttbr match */
+ vttbr = vttbr & ~VTTBR_CNP_BIT;
+
+ /*
+ * Two possibilities when looking up a S2 MMU context:
+ *
+ * - either S2 is enabled in the guest, and we need a context that is
+ * S2-enabled and matches the full VTTBR (VMID+BADDR) and VTCR,
+ * which makes it safe from a TLB conflict perspective (a broken
+ * guest won't be able to generate them),
+ *
+ * - or S2 is disabled, and we need a context that is S2-disabled
+ * and matches the VMID only, as all TLBs are tagged by VMID even
+ * if S2 translation is disabled.
+ */
+ for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+ struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+ if (!kvm_s2_mmu_valid(mmu))
+ continue;
+
+ if (nested_stage2_enabled &&
+ mmu->nested_stage2_enabled &&
+ vttbr == mmu->tlb_vttbr &&
+ vtcr == mmu->tlb_vtcr)
+ return mmu;
+
+ if (!nested_stage2_enabled &&
+ !mmu->nested_stage2_enabled &&
+ get_vmid(vttbr) == get_vmid(mmu->tlb_vttbr))
+ return mmu;
+ }
+ return NULL;
+}
+
+/* Must be called with kvm->mmu_lock held */
+static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_s2_mmu *s2_mmu;
+ int i;
+
+ s2_mmu = lookup_s2_mmu(vcpu);
+ if (s2_mmu)
+ goto out;
+
+ /*
+ * Make sure we don't always search from the same point, or we
+ * will always reuse a potentially active context, leaving
+ * free contexts unused.
+ */
+ for (i = kvm->arch.nested_mmus_next;
+ i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next);
+ i++) {
+ s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size];
+
+ if (atomic_read(&s2_mmu->refcnt) == 0)
+ break;
+ }
+ BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */
+
+ /* Set the scene for the next search */
+ kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
+
+ if (kvm_s2_mmu_valid(s2_mmu)) {
+ /* Clear the old state */
+ kvm_unmap_stage2_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
+ if (atomic64_read(&s2_mmu->vmid.id))
+ kvm_call_hyp(__kvm_tlb_flush_vmid, s2_mmu);
+ }
+
+ /*
+ * The virtual VMID (modulo CnP) will be used as a key when matching
+ * an existing kvm_s2_mmu.
+ *
+ * We cache VTCR at allocation time, once and for all. It'd be great
+ * if the guest didn't screw that one up, as this is not very
+ * forgiving...
+ */
+ s2_mmu->tlb_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2) & ~VTTBR_CNP_BIT;
+ s2_mmu->tlb_vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+ s2_mmu->nested_stage2_enabled = vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_VM;
+
+out:
+ atomic_inc(&s2_mmu->refcnt);
+ return s2_mmu;
+}
+
+void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
+{
+ mmu->tlb_vttbr = 1;
+ mmu->nested_stage2_enabled = false;
+ atomic_set(&mmu->refcnt, 0);
+}
+
+void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
+{
+ if (is_hyp_ctxt(vcpu)) {
+ vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
+ } else {
+ write_lock(&vcpu->kvm->mmu_lock);
+ vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu);
+ write_unlock(&vcpu->kvm->mmu_lock);
+ }
+}
+
+void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
+{
+ if (vcpu->arch.hw_mmu != &vcpu->kvm->arch.mmu) {
+ atomic_dec(&vcpu->arch.hw_mmu->refcnt);
+ vcpu->arch.hw_mmu = NULL;
+ }
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+ int i;
+
+ for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+ struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+ WARN_ON(atomic_read(&mmu->refcnt));
+
+ if (!atomic_read(&mmu->refcnt))
+ kvm_free_stage2_pgd(mmu);
+ }
+ kfree(kvm->arch.nested_mmus);
+ kvm->arch.nested_mmus = NULL;
+ kvm->arch.nested_mmus_size = 0;
+ kvm_free_stage2_pgd(&kvm->arch.mmu);
+}
+
/*
* Our emulated CPU doesn't support all the possible features. For the
* sake of simplicity (and probably mental sanity), wipe out a number
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index b5dee8e57e77..ad11cc514b3d 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -365,6 +365,12 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
return ret;
}
+u32 kvm_get_pa_bits(struct kvm *kvm)
+{
+ /* Fixed limit until we can configure ID_AA64MMFR0.PARange */
+ return kvm_ipa_limit;
+}
+
u32 get_kvm_ipa_limit(void)
{
return kvm_ipa_limit;
--
2.34.1
WARNING: multiple messages have this Message-ID (diff)
From: Marc Zyngier <maz@kernel.org>
To: kvmarm@lists.linux.dev, kvm@vger.kernel.org,
linux-arm-kernel@lists.infradead.org
Cc: Alexandru Elisei <alexandru.elisei@arm.com>,
Andre Przywara <andre.przywara@arm.com>,
Chase Conklin <chase.conklin@arm.com>,
Christoffer Dall <christoffer.dall@arm.com>,
Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>,
Darren Hart <darren@os.amperecomputing.com>,
Jintack Lim <jintack@cs.columbia.edu>,
Russell King <rmk+kernel@armlinux.org.uk>,
Miguel Luis <miguel.luis@oracle.com>,
James Morse <james.morse@arm.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
Oliver Upton <oliver.upton@linux.dev>,
Zenghui Yu <yuzenghui@huawei.com>
Subject: [PATCH v10 25/59] KVM: arm64: nv: Support multiple nested Stage-2 mmu structures
Date: Mon, 15 May 2023 18:30:29 +0100 [thread overview]
Message-ID: <20230515173103.1017669-26-maz@kernel.org> (raw)
In-Reply-To: <20230515173103.1017669-1-maz@kernel.org>
Add Stage-2 mmu data structures for virtual EL2 and for nested guests.
We don't yet populate shadow Stage-2 page tables, but we now have a
framework for getting to a shadow Stage-2 pgd.
We allocate twice the number of vcpus as Stage-2 mmu structures because
that's sufficient for each vcpu running two translation regimes without
having to flush the Stage-2 page tables.
Co-developed-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
arch/arm64/include/asm/kvm_host.h | 41 ++++++
arch/arm64/include/asm/kvm_mmu.h | 9 ++
arch/arm64/include/asm/kvm_nested.h | 7 +
arch/arm64/kvm/arm.c | 18 ++-
arch/arm64/kvm/mmu.c | 78 ++++++++---
arch/arm64/kvm/nested.c | 210 ++++++++++++++++++++++++++++
arch/arm64/kvm/reset.c | 6 +
7 files changed, 345 insertions(+), 24 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 65810618cb42..2e2969f53b4a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -170,8 +170,40 @@ struct kvm_s2_mmu {
int __percpu *last_vcpu_ran;
struct kvm_arch *arch;
+
+ /*
+ * For a shadow stage-2 MMU, the virtual vttbr used by the
+ * host to parse the guest S2.
+ * This either contains:
+ * - the virtual VTTBR programmed by the guest hypervisor with
+ * CnP cleared
+ * - The value 1 (VMID=0, BADDR=0, CnP=1) if invalid
+ *
+ * We also cache the full VTCR which gets used for TLB invalidation,
+ * taking the ARM ARM's "Any of the bits in VTCR_EL2 are permitted
+ * to be cached in a TLB" to the letter.
+ */
+ u64 tlb_vttbr;
+ u64 tlb_vtcr;
+
+ /*
+ * true when this represents a nested context where virtual
+ * HCR_EL2.VM == 1
+ */
+ bool nested_stage2_enabled;
+
+ /*
+ * 0: Nobody is currently using this, check vttbr for validity
+ * >0: Somebody is actively using this.
+ */
+ atomic_t refcnt;
};
+static inline bool kvm_s2_mmu_valid(struct kvm_s2_mmu *mmu)
+{
+ return !(mmu->tlb_vttbr & 1);
+}
+
struct kvm_arch_memory_slot {
};
@@ -198,6 +230,14 @@ struct kvm_protected_vm {
struct kvm_arch {
struct kvm_s2_mmu mmu;
+ /*
+ * Stage 2 paging state for VMs with nested S2 using a virtual
+ * VMID.
+ */
+ struct kvm_s2_mmu *nested_mmus;
+ size_t nested_mmus_size;
+ int nested_mmus_next;
+
/* Interrupt controller */
struct vgic_dist vgic;
@@ -1082,6 +1122,7 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
int __init kvm_set_ipa_limit(void);
+u32 kvm_get_pa_bits(struct kvm *kvm);
#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 346754b2f3b0..896acdf98e71 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -119,6 +119,7 @@ alternative_cb_end
#include <asm/mmu_context.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_host.h>
+#include <asm/kvm_nested.h>
void kvm_update_va_mask(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst);
@@ -170,6 +171,7 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
void **haddr);
void __init free_hyp_pgds(void);
+void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
void stage2_unmap_vm(struct kvm *kvm);
int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);
void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
@@ -311,5 +313,12 @@ static inline struct kvm *kvm_s2_mmu_to_kvm(struct kvm_s2_mmu *mmu)
{
return container_of(mmu->arch, struct kvm, arch);
}
+
+static inline u64 get_vmid(u64 vttbr)
+{
+ return (vttbr & VTTBR_VMID_MASK(kvm_get_vmid_bits())) >>
+ VTTBR_VMID_SHIFT;
+}
+
#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 948ba0337558..d57e609dd3f4 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -59,6 +59,13 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
return ttbr0 & ~GENMASK_ULL(63, 48);
}
+extern void kvm_init_nested(struct kvm *kvm);
+extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu);
+extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);
+extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu);
+extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
+extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
+
extern bool forward_smc_trap(struct kvm_vcpu *vcpu);
extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 7b0241eb7483..9036206f0be8 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -36,9 +36,10 @@
#include <asm/virt.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
#include <asm/kvm_pkvm.h>
-#include <asm/kvm_emulate.h>
#include <asm/sections.h>
#include <kvm/arm_hypercalls.h>
@@ -138,6 +139,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
mutex_unlock(&kvm->lock);
#endif
+ kvm_init_nested(kvm);
+
ret = kvm_share_hyp(kvm, kvm + 1);
if (ret)
return ret;
@@ -413,6 +416,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
struct kvm_s2_mmu *mmu;
int *last_ran;
+ if (vcpu_has_nv(vcpu))
+ kvm_vcpu_load_hw_mmu(vcpu);
+
mmu = vcpu->arch.hw_mmu;
last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
@@ -463,9 +469,12 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
kvm_timer_vcpu_put(vcpu);
kvm_vgic_put(vcpu);
kvm_vcpu_pmu_restore_host(vcpu);
+ if (vcpu_has_nv(vcpu))
+ kvm_vcpu_put_hw_mmu(vcpu);
kvm_arm_vmid_clear_active();
vcpu_clear_on_unsupported_cpu(vcpu);
+
vcpu->cpu = -1;
}
@@ -1206,8 +1215,13 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
vcpu->arch.target = phys_target;
+ /* Prepare for nested if required */
+ ret = kvm_vcpu_init_nested(vcpu);
+
/* Now we know what it is, we can reset it. */
- ret = kvm_reset_vcpu(vcpu);
+ if (!ret)
+ ret = kvm_reset_vcpu(vcpu);
+
if (ret) {
vcpu->arch.target = -1;
bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c934c911c702..3268936eec40 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -217,7 +217,7 @@ static void invalidate_icache_guest_page(void *va, size_t size)
* does.
*/
/**
- * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
+ * __unmap_stage2_range -- Clear stage2 page table entries to unmap a range
* @mmu: The KVM stage-2 MMU pointer
* @start: The intermediate physical base address of the range to unmap
* @size: The size of the area to unmap
@@ -240,7 +240,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
may_block));
}
-static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
{
__unmap_stage2_range(mmu, start, size, true);
}
@@ -711,21 +711,9 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
.icache_inval_pou = invalidate_icache_guest_page,
};
-/**
- * kvm_init_stage2_mmu - Initialise a S2 MMU structure
- * @kvm: The pointer to the KVM structure
- * @mmu: The pointer to the s2 MMU structure
- * @type: The machine type of the virtual machine
- *
- * Allocates only the stage-2 HW PGD level table(s).
- * Note we don't need locking here as this is only called when the VM is
- * created, which can only be done once.
- */
-int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type)
+static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
{
u32 kvm_ipa_limit = get_kvm_ipa_limit();
- int cpu, err;
- struct kvm_pgtable *pgt;
u64 mmfr0, mmfr1;
u32 phys_shift;
@@ -752,11 +740,58 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);
+ return 0;
+}
+
+/**
+ * kvm_init_stage2_mmu - Initialise a S2 MMU structure
+ * @kvm: The pointer to the KVM structure
+ * @mmu: The pointer to the s2 MMU structure
+ * @type: The machine type of the virtual machine
+ *
+ * Allocates only the stage-2 HW PGD level table(s).
+ * Note we don't need locking here as this is only called in two cases:
+ *
+ * - when the VM is created, which can't race against anything
+ *
+ * - when secondary kvm_s2_mmu structures are initialised for NV
+ * guests, and the caller must hold kvm->lock as this is called on a
+ * per-vcpu basis.
+ */
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type)
+{
+ int cpu, err;
+ struct kvm_pgtable *pgt;
+
+ /*
+ * If we already have our page tables in place, and that the
+ * MMU context is the canonical one, we have a bug somewhere,
+ * as this is only supposed to ever happen once per VM.
+ *
+ * Otherwise, we're building nested page tables, and that's
+ * probably because userspace called KVM_ARM_VCPU_INIT more
+ * than once on the same vcpu. Since that's actually legal,
+ * don't kick a fuss and leave gracefully.
+ */
if (mmu->pgt != NULL) {
+ if (&kvm->arch.mmu != mmu)
+ return 0;
+
kvm_err("kvm_arch already initialized?\n");
return -EINVAL;
}
+ /*
+ * We only initialise the IPA range on the canonical MMU, so
+ * the type is meaningless in all other situations.
+ */
+ if (&kvm->arch.mmu != mmu)
+ type = kvm_get_pa_bits(kvm);
+
+ err = kvm_init_ipa_range(mmu, type);
+ if (err)
+ return err;
+
pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT);
if (!pgt)
return -ENOMEM;
@@ -777,6 +812,10 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
mmu->pgt = pgt;
mmu->pgd_phys = __pa(pgt->pgd);
+
+ if (&kvm->arch.mmu != mmu)
+ kvm_init_nested_s2_mmu(mmu);
+
return 0;
out_destroy_pgtable:
@@ -822,7 +861,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
if (!(vma->vm_flags & VM_PFNMAP)) {
gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
- unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
+ kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
}
hva = vm_end;
} while (hva < reg_end);
@@ -1876,11 +1915,6 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
{
}
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
- kvm_free_stage2_pgd(&kvm->arch.mmu);
-}
-
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot)
{
@@ -1888,7 +1922,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
phys_addr_t size = slot->npages << PAGE_SHIFT;
write_lock(&kvm->mmu_lock);
- unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+ kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, size);
write_unlock(&kvm->mmu_lock);
}
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 7f80f385d9e8..c3da57d16d88 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -7,7 +7,9 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <asm/kvm_arm.h>
#include <asm/kvm_emulate.h>
+#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/sysreg.h>
@@ -16,6 +18,214 @@
/* Protection against the sysreg repainting madness... */
#define NV_FTR(r, f) ID_AA64##r##_EL1_##f
+void kvm_init_nested(struct kvm *kvm)
+{
+ kvm->arch.nested_mmus = NULL;
+ kvm->arch.nested_mmus_size = 0;
+}
+
+int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_s2_mmu *tmp;
+ int num_mmus;
+ int ret = -ENOMEM;
+
+ if (!test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features))
+ return 0;
+
+ if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
+ return -EINVAL;
+
+ mutex_lock(&kvm->arch.config_lock);
+
+ /*
+ * Let's treat memory allocation failures as benign: If we fail to
+ * allocate anything, return an error and keep the allocated array
+ * alive. Userspace may try to recover by intializing the vcpu
+ * again, and there is no reason to affect the whole VM for this.
+ */
+ num_mmus = atomic_read(&kvm->online_vcpus) * 2;
+ tmp = krealloc(kvm->arch.nested_mmus,
+ num_mmus * sizeof(*kvm->arch.nested_mmus),
+ GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ if (tmp) {
+ /*
+ * If we went through a realocation, adjust the MMU
+ * back-pointers in the previously initialised
+ * pg_table structures.
+ */
+ if (kvm->arch.nested_mmus != tmp) {
+ int i;
+
+ for (i = 0; i < num_mmus - 2; i++)
+ tmp[i].pgt->mmu = &tmp[i];
+ }
+
+ if (kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 1], 0) ||
+ kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 2], 0)) {
+ kvm_free_stage2_pgd(&tmp[num_mmus - 1]);
+ kvm_free_stage2_pgd(&tmp[num_mmus - 2]);
+ } else {
+ kvm->arch.nested_mmus_size = num_mmus;
+ ret = 0;
+ }
+
+ kvm->arch.nested_mmus = tmp;
+ }
+
+ mutex_unlock(&kvm->arch.config_lock);
+ return ret;
+}
+
+/* Must be called with kvm->mmu_lock held */
+struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu)
+{
+ bool nested_stage2_enabled;
+ u64 vttbr, vtcr, hcr;
+ struct kvm *kvm;
+ int i;
+
+ kvm = vcpu->kvm;
+
+ vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+ vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+ hcr = vcpu_read_sys_reg(vcpu, HCR_EL2);
+
+ nested_stage2_enabled = hcr & HCR_VM;
+
+ /* Don't consider the CnP bit for the vttbr match */
+ vttbr = vttbr & ~VTTBR_CNP_BIT;
+
+ /*
+ * Two possibilities when looking up a S2 MMU context:
+ *
+ * - either S2 is enabled in the guest, and we need a context that is
+ * S2-enabled and matches the full VTTBR (VMID+BADDR) and VTCR,
+ * which makes it safe from a TLB conflict perspective (a broken
+ * guest won't be able to generate them),
+ *
+ * - or S2 is disabled, and we need a context that is S2-disabled
+ * and matches the VMID only, as all TLBs are tagged by VMID even
+ * if S2 translation is disabled.
+ */
+ for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+ struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+ if (!kvm_s2_mmu_valid(mmu))
+ continue;
+
+ if (nested_stage2_enabled &&
+ mmu->nested_stage2_enabled &&
+ vttbr == mmu->tlb_vttbr &&
+ vtcr == mmu->tlb_vtcr)
+ return mmu;
+
+ if (!nested_stage2_enabled &&
+ !mmu->nested_stage2_enabled &&
+ get_vmid(vttbr) == get_vmid(mmu->tlb_vttbr))
+ return mmu;
+ }
+ return NULL;
+}
+
+/* Must be called with kvm->mmu_lock held */
+static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_s2_mmu *s2_mmu;
+ int i;
+
+ s2_mmu = lookup_s2_mmu(vcpu);
+ if (s2_mmu)
+ goto out;
+
+ /*
+ * Make sure we don't always search from the same point, or we
+ * will always reuse a potentially active context, leaving
+ * free contexts unused.
+ */
+ for (i = kvm->arch.nested_mmus_next;
+ i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next);
+ i++) {
+ s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size];
+
+ if (atomic_read(&s2_mmu->refcnt) == 0)
+ break;
+ }
+ BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */
+
+ /* Set the scene for the next search */
+ kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
+
+ if (kvm_s2_mmu_valid(s2_mmu)) {
+ /* Clear the old state */
+ kvm_unmap_stage2_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
+ if (atomic64_read(&s2_mmu->vmid.id))
+ kvm_call_hyp(__kvm_tlb_flush_vmid, s2_mmu);
+ }
+
+ /*
+ * The virtual VMID (modulo CnP) will be used as a key when matching
+ * an existing kvm_s2_mmu.
+ *
+ * We cache VTCR at allocation time, once and for all. It'd be great
+ * if the guest didn't screw that one up, as this is not very
+ * forgiving...
+ */
+ s2_mmu->tlb_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2) & ~VTTBR_CNP_BIT;
+ s2_mmu->tlb_vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+ s2_mmu->nested_stage2_enabled = vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_VM;
+
+out:
+ atomic_inc(&s2_mmu->refcnt);
+ return s2_mmu;
+}
+
+void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
+{
+ mmu->tlb_vttbr = 1;
+ mmu->nested_stage2_enabled = false;
+ atomic_set(&mmu->refcnt, 0);
+}
+
+void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
+{
+ if (is_hyp_ctxt(vcpu)) {
+ vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
+ } else {
+ write_lock(&vcpu->kvm->mmu_lock);
+ vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu);
+ write_unlock(&vcpu->kvm->mmu_lock);
+ }
+}
+
+void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
+{
+ if (vcpu->arch.hw_mmu != &vcpu->kvm->arch.mmu) {
+ atomic_dec(&vcpu->arch.hw_mmu->refcnt);
+ vcpu->arch.hw_mmu = NULL;
+ }
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+ int i;
+
+ for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+ struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+ WARN_ON(atomic_read(&mmu->refcnt));
+
+ if (!atomic_read(&mmu->refcnt))
+ kvm_free_stage2_pgd(mmu);
+ }
+ kfree(kvm->arch.nested_mmus);
+ kvm->arch.nested_mmus = NULL;
+ kvm->arch.nested_mmus_size = 0;
+ kvm_free_stage2_pgd(&kvm->arch.mmu);
+}
+
/*
* Our emulated CPU doesn't support all the possible features. For the
* sake of simplicity (and probably mental sanity), wipe out a number
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index b5dee8e57e77..ad11cc514b3d 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -365,6 +365,12 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
return ret;
}
+u32 kvm_get_pa_bits(struct kvm *kvm)
+{
+ /* Fixed limit until we can configure ID_AA64MMFR0.PARange */
+ return kvm_ipa_limit;
+}
+
u32 get_kvm_ipa_limit(void)
{
return kvm_ipa_limit;
--
2.34.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2023-05-15 17:47 UTC|newest]
Thread overview: 189+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-15 17:30 [PATCH v10 00/59] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 01/59] KVM: arm64: Move VTCR_EL2 into struct s2_mmu Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 02/59] arm64: Add missing Set/Way CMO encodings Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 03/59] arm64: Add missing VA " Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-06-05 17:46 ` Eric Auger
2023-06-05 17:46 ` Eric Auger
2023-05-15 17:30 ` [PATCH v10 04/59] arm64: Add missing ERXMISCx_EL1 encodings Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-06-05 17:47 ` Eric Auger
2023-06-05 17:47 ` Eric Auger
2023-05-15 17:30 ` [PATCH v10 05/59] arm64: Add missing DC ZVA/GVA/GZVA encodings Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-06-05 17:47 ` Eric Auger
2023-06-05 17:47 ` Eric Auger
2023-05-15 17:30 ` [PATCH v10 06/59] arm64: Add TLBI operation encodings Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-06-06 9:33 ` Eric Auger
2023-06-06 9:33 ` Eric Auger
2023-05-15 17:30 ` [PATCH v10 07/59] arm64: Add AT " Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-06-14 15:08 ` Eric Auger
2023-06-14 15:08 ` Eric Auger
2023-05-15 17:30 ` [PATCH v10 08/59] KVM: arm64: Add missing HCR_EL2 trap bits Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-06-14 15:08 ` Eric Auger
2023-06-14 15:08 ` Eric Auger
2023-05-15 17:30 ` [PATCH v10 09/59] KVM: arm64: nv: Add trap forwarding infrastructure Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-07-13 14:29 ` Eric Auger
2023-07-13 14:29 ` Eric Auger
2023-07-14 10:53 ` Marc Zyngier
2023-07-14 10:53 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 10/59] KVM: arm64: nv: Add trap forwarding for HCR_EL2 Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 11/59] KVM: arm64: nv: Expose FEAT_EVT to nested guests Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 12/59] KVM: arm64: nv: Add trap forwarding for MDCR_EL2 Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 13/59] KVM: arm64: nv: Add trap forwarding for CNTHCTL_EL2 Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 14/59] KVM: arm64: nv: Add non-VHE-EL2->EL1 translation helpers Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 15/59] KVM: arm64: nv: Handle virtual EL2 registers in vcpu_read/write_sys_reg() Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 16/59] KVM: arm64: nv: Handle SPSR_EL2 specially Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 17/59] KVM: arm64: nv: Handle HCR_EL2.E2H specially Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 18/59] KVM: arm64: nv: Save/Restore vEL2 sysregs Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 19/59] KVM: arm64: nv: Trap EL1 VM register accesses in virtual EL2 Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 20/59] KVM: arm64: nv: Trap CPACR_EL1 access " Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 21/59] KVM: arm64: nv: Respect virtual HCR_EL2.TWX setting Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 22/59] KVM: arm64: nv: Respect virtual CPTR_EL2.{TFP,FPEN} settings Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 23/59] KVM: arm64: nv: Respect virtual HCR_EL2.{NV,TSC) settings Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 24/59] KVM: arm64: nv: Configure HCR_EL2 for nested virtualization Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier [this message]
2023-05-15 17:30 ` [PATCH v10 25/59] KVM: arm64: nv: Support multiple nested Stage-2 mmu structures Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 26/59] KVM: arm64: nv: Implement nested Stage-2 page table walk logic Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 27/59] KVM: arm64: nv: Handle shadow stage 2 page faults Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 28/59] KVM: arm64: nv: Restrict S2 RD/WR permissions to match the guest's Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 29/59] KVM: arm64: nv: Unmap/flush shadow stage 2 page tables Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-09-14 13:10 ` Ganapatrao Kulkarni
2023-09-14 13:10 ` Ganapatrao Kulkarni
2023-09-14 13:37 ` Marc Zyngier
2023-09-14 13:37 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 30/59] KVM: arm64: nv: Set a handler for the system instruction traps Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 31/59] KVM: arm64: nv: Trap and emulate AT instructions from virtual EL2 Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 32/59] KVM: arm64: nv: Trap and emulate TLBI " Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 33/59] KVM: arm64: nv: Fold guest's HCR_EL2 configuration into the host's Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 34/59] KVM: arm64: nv: Hide RAS from nested guests Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 35/59] KVM: arm64: nv: Add handling of EL2-specific timer registers Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 36/59] KVM: arm64: nv: Load timer before the GIC Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 37/59] KVM: arm64: nv: Nested GICv3 Support Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 38/59] KVM: arm64: nv: Don't load the GICv4 context on entering a nested guest Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 39/59] KVM: arm64: nv: vgic: Emulate the HW bit in software Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 40/59] KVM: arm64: nv: vgic: Allow userland to set VGIC maintenance IRQ Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 41/59] KVM: arm64: nv: Implement maintenance interrupt forwarding Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 42/59] KVM: arm64: nv: Deal with broken VGIC on maintenance interrupt delivery Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 43/59] KVM: arm64: nv: Allow userspace to request KVM_ARM_VCPU_NESTED_VIRT Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 44/59] KVM: arm64: nv: Add handling of FEAT_TTL TLB invalidation Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 45/59] KVM: arm64: nv: Invalidate TLBs based on shadow S2 TTL-like information Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 46/59] KVM: arm64: nv: Tag shadow S2 entries with nested level Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 47/59] KVM: arm64: nv: Add include containing the VNCR_EL2 offsets Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 48/59] KVM: arm64: nv: Map VNCR-capable registers to a separate page Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 49/59] KVM: arm64: nv: Move nested vgic state into the sysreg file Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 50/59] KVM: arm64: Add FEAT_NV2 cpu feature Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 51/59] KVM: arm64: nv: Sync nested timer state with FEAT_NV2 Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 52/59] KVM: arm64: nv: Fold GICv3 host trapping requirements into guest setup Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 53/59] KVM: arm64: nv: Publish emulated timer interrupt state in the in-memory state Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 54/59] KVM: arm64: nv: Allocate VNCR page when required Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:30 ` [PATCH v10 55/59] KVM: arm64: nv: Enable ARMv8.4-NV support Marc Zyngier
2023-05-15 17:30 ` Marc Zyngier
2023-05-15 17:31 ` [PATCH v10 56/59] KVM: arm64: nv: Fast-track 'InHost' exception returns Marc Zyngier
2023-05-15 17:31 ` Marc Zyngier
2023-05-15 17:31 ` [PATCH v10 57/59] KVM: arm64: nv: Fast-track EL1 TLBIs for VHE guests Marc Zyngier
2023-05-15 17:31 ` Marc Zyngier
2023-05-15 17:31 ` [PATCH v10 58/59] KVM: arm64: nv: Use FEAT_ECV to trap access to EL0 timers Marc Zyngier
2023-05-15 17:31 ` Marc Zyngier
2023-05-15 17:31 ` [PATCH v10 59/59] KVM: arm64: nv: Accelerate EL0 timer read accesses when FEAT_ECV is on Marc Zyngier
2023-05-15 17:31 ` Marc Zyngier
2023-05-16 16:53 ` [PATCH v10 00/59] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support Eric Auger
2023-05-16 16:53 ` Eric Auger
2023-05-16 18:47 ` Marc Zyngier
2023-05-16 18:47 ` Marc Zyngier
2023-05-16 20:28 ` Marc Zyngier
2023-05-16 20:28 ` Marc Zyngier
2023-05-17 8:59 ` Eric Auger
2023-05-17 8:59 ` Eric Auger
2023-05-17 14:12 ` Marc Zyngier
2023-05-17 14:12 ` Marc Zyngier
2023-06-06 9:33 ` Eric Auger
2023-06-06 9:33 ` Eric Auger
2023-06-06 16:30 ` Marc Zyngier
2023-06-06 16:30 ` Marc Zyngier
2023-06-07 16:39 ` Eric Auger
2023-06-07 16:39 ` Eric Auger
2023-06-06 17:52 ` Miguel Luis
2023-06-06 17:52 ` Miguel Luis
2023-06-07 16:40 ` Eric Auger
2023-06-07 16:40 ` Eric Auger
2023-06-10 8:25 ` Miguel Luis
2023-06-10 8:25 ` Miguel Luis
2023-06-11 16:28 ` Eric Auger
2023-06-05 11:28 ` Eric Auger
2023-06-05 11:28 ` Eric Auger
2023-06-06 7:30 ` Marc Zyngier
2023-06-06 7:30 ` Marc Zyngier
2023-06-06 9:29 ` Eric Auger
2023-06-06 9:29 ` Eric Auger
2023-06-06 16:22 ` Marc Zyngier
2023-06-06 16:22 ` Marc Zyngier
2023-06-07 16:30 ` Eric Auger
2023-06-07 16:30 ` Eric Auger
2023-06-28 6:45 ` Ganapatrao Kulkarni
2023-06-28 6:45 ` Ganapatrao Kulkarni
2023-06-29 7:03 ` Marc Zyngier
2023-06-29 7:03 ` Marc Zyngier
2023-07-04 12:31 ` Ganapatrao Kulkarni
2023-07-04 12:31 ` Ganapatrao Kulkarni
2023-07-07 9:46 ` Ganapatrao Kulkarni
2023-07-07 9:46 ` Ganapatrao Kulkarni
2023-07-11 11:56 ` Ganapatrao Kulkarni
2023-07-11 11:56 ` Ganapatrao Kulkarni
2023-07-11 12:30 ` Marc Zyngier
2023-07-11 12:30 ` Marc Zyngier
2023-07-10 12:56 ` Miguel Luis
2023-07-10 12:56 ` Miguel Luis
2023-07-18 10:29 ` Miguel Luis
2023-07-18 10:29 ` Miguel Luis
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230515173103.1017669-26-maz@kernel.org \
--to=maz@kernel.org \
--cc=alexandru.elisei@arm.com \
--cc=andre.przywara@arm.com \
--cc=chase.conklin@arm.com \
--cc=christoffer.dall@arm.com \
--cc=darren@os.amperecomputing.com \
--cc=gankulkarni@os.amperecomputing.com \
--cc=james.morse@arm.com \
--cc=jintack@cs.columbia.edu \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.linux.dev \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=miguel.luis@oracle.com \
--cc=oliver.upton@linux.dev \
--cc=rmk+kernel@armlinux.org.uk \
--cc=suzuki.poulose@arm.com \
--cc=yuzenghui@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.