[PATCH v14 19/44] arm64: RMI: Allocate/free RECs to match vCPUs

[Steven Price <steven.price@arm.com>]

The RMM maintains a data structure known as the Realm Execution Context
(or REC). It is similar to struct kvm_vcpu and tracks the state of the
virtual CPUs. KVM must delegate memory and request the structures are
created when vCPUs are created, and suitably tear down on destruction.

RECs may require additional pages (e.g. for storing larger register
state for SVE). The RMM can request extra pages for this purpose using
the Stateful RMI Operations (SRO) functionality to request pages during
REC creation. These pages are then passed back to the host from the RMM
('reclaimed') when the REC is destroyed. The kernel tracking object
(struct rmi_sro_state) is stored in the realm_rec structure to avoid
memory allocation during the destruction path.

Note that only some of register state for the REC can be set by KVM, the
rest is defined by the RMM (zeroed). The register state then cannot be
changed by KVM after the REC is created (except when the guest
explicitly requests this e.g. by performing a PSCI call).

Signed-off-by: Steven Price <steven.price@arm.com>
---
Changes since v13:
 * Support SRO for REC creation/destruction instead of auxiliary
   granules.
Changes since v12:
 * Use the new range-based delegation RMI.
Changes since v11:
 * Remove the KVM_ARM_VCPU_REC feature. User space no longer needs to
   configure each VCPU separately, RECs are created on the first VCPU
   run of the guest.
Changes since v9:
 * Size the aux_pages array according to the PAGE_SIZE of the host.
Changes since v7:
 * Add comment explaining the aux_pages array.
 * Rename "undeleted_failed" variable to "should_free" to avoid a
   confusing double negative.
Changes since v6:
 * Avoid reporting the KVM_ARM_VCPU_REC feature if the guest isn't a
   realm guest.
 * Support host page size being larger than RMM's granule size when
   allocating/freeing aux granules.
Changes since v5:
 * Separate the concept of vcpu_is_rec() and
   kvm_arm_vcpu_rec_finalized() by using the KVM_ARM_VCPU_REC feature as
   the indication that the VCPU is a REC.
Changes since v2:
 * Free rec->run earlier in kvm_destroy_realm() and adapt to previous patches.
---
 arch/arm64/include/asm/kvm_emulate.h |   2 +-
 arch/arm64/include/asm/kvm_host.h    |   3 +
 arch/arm64/include/asm/kvm_rmi.h     |  17 +++++
 arch/arm64/kvm/arm.c                 |   6 ++
 arch/arm64/kvm/reset.c               |   1 +
 arch/arm64/kvm/rmi.c                 | 105 +++++++++++++++++++++++++++
 6 files changed, 133 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 82fd777bd9bb..2e69fe494716 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -714,7 +714,7 @@ static inline bool kvm_realm_is_created(struct kvm *kvm)
 
 static inline bool vcpu_is_rec(const struct kvm_vcpu *vcpu)
 {
-	return false;
+	return kvm_is_realm(vcpu->kvm);
 }
 
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 3512696ed506..39b5de03d0fe 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -969,6 +969,9 @@ struct kvm_vcpu_arch {
 
 	/* Hyp-readable copy of kvm_vcpu::pid */
 	pid_t pid;
+
+	/* Realm meta data */
+	struct realm_rec rec;
 };
 
 /*
diff --git a/arch/arm64/include/asm/kvm_rmi.h b/arch/arm64/include/asm/kvm_rmi.h
index 8bd743093ccf..d99bf4fc3c39 100644
--- a/arch/arm64/include/asm/kvm_rmi.h
+++ b/arch/arm64/include/asm/kvm_rmi.h
@@ -59,6 +59,22 @@ struct realm {
 	unsigned int ia_bits;
 };
 
+/**
+ * struct realm_rec - Additional per VCPU data for a Realm
+ *
+ * @mpidr: MPIDR (Multiprocessor Affinity Register) value to identify this VCPU
+ * @rec_page: Kernel VA of the RMM's private page for this REC
+ * @aux_pages: Additional pages private to the RMM for this REC
+ * @run: Kernel VA of the RmiRecRun structure shared with the RMM
+ * @sro: A preallocated SRO state context
+ */
+struct realm_rec {
+	unsigned long mpidr;
+	void *rec_page;
+	struct rec_run *run;
+	struct rmi_sro_state *sro;
+};
+
 void kvm_init_rmi(void);
 u32 kvm_realm_ipa_limit(void);
 
@@ -66,6 +82,7 @@ int kvm_init_realm(struct kvm *kvm);
 int kvm_activate_realm(struct kvm *kvm);
 void kvm_destroy_realm(struct kvm *kvm);
 void kvm_realm_destroy_rtts(struct kvm *kvm);
+void kvm_destroy_rec(struct kvm_vcpu *vcpu);
 
 static inline bool kvm_realm_is_private_address(struct realm *realm,
 						unsigned long addr)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index eb2b61fe1f0a..93d34762db91 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -586,6 +586,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	/* Force users to call KVM_ARM_VCPU_INIT */
 	vcpu_clear_flag(vcpu, VCPU_INITIALIZED);
 
+	vcpu->arch.rec.mpidr = INVALID_HWID;
+
 	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
 
 	/* Set up the timer */
@@ -1651,6 +1653,10 @@ static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu,
 	if (test_bit(KVM_ARM_VCPU_HAS_EL2, &features))
 		return -EINVAL;
 
+	/* Realms are incompatible with AArch32 */
+	if (vcpu_is_rec(vcpu))
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index b963fd975aac..c18cdca7d125 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -161,6 +161,7 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
 	free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
 	kfree(vcpu->arch.vncr_tlb);
 	kfree(vcpu->arch.ccsidr);
+	kvm_destroy_rec(vcpu);
 }
 
 static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/rmi.c b/arch/arm64/kvm/rmi.c
index 849111817af7..353a5ca45e78 100644
--- a/arch/arm64/kvm/rmi.c
+++ b/arch/arm64/kvm/rmi.c
@@ -173,9 +173,108 @@ static int realm_ensure_created(struct kvm *kvm)
 	return -ENXIO;
 }
 
+static int kvm_create_rec(struct kvm_vcpu *vcpu)
+{
+	struct user_pt_regs *vcpu_regs = vcpu_gp_regs(vcpu);
+	unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
+	struct realm *realm = &vcpu->kvm->arch.realm;
+	struct realm_rec *rec = &vcpu->arch.rec;
+	unsigned long rec_page_phys;
+	struct rec_params *params;
+	int r, i;
+
+	if (rec->run)
+		return -EBUSY;
+
+	/*
+	 * The RMM will report PSCI v1.0 to Realms and the KVM_ARM_VCPU_PSCI_0_2
+	 * flag covers v0.2 and onwards.
+	 */
+	if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2))
+		return -EINVAL;
+
+	BUILD_BUG_ON(sizeof(*params) > PAGE_SIZE);
+	BUILD_BUG_ON(sizeof(*rec->run) > PAGE_SIZE);
+
+	params = (struct rec_params *)get_zeroed_page(GFP_KERNEL);
+	rec->rec_page = (void *)__get_free_page(GFP_KERNEL);
+	rec->run = (void *)get_zeroed_page(GFP_KERNEL);
+	rec->sro = kmalloc_obj(*rec->sro);
+	if (!params || !rec->rec_page || !rec->run || !rec->sro) {
+		r = -ENOMEM;
+		goto out_free_pages;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(params->gprs); i++)
+		params->gprs[i] = vcpu_regs->regs[i];
+
+	params->pc = vcpu_regs->pc;
+
+	if (vcpu->vcpu_id == 0)
+		params->flags |= REC_PARAMS_FLAG_RUNNABLE;
+
+	rec_page_phys = virt_to_phys(rec->rec_page);
+
+	if (rmi_delegate_page(rec_page_phys)) {
+		r = -ENXIO;
+		goto out_free_pages;
+	}
+
+	params->mpidr = mpidr;
+
+	if (rmi_rec_create(virt_to_phys(realm->rd), rec_page_phys,
+			   virt_to_phys(params), rec->sro)) {
+		r = -ENXIO;
+		goto out_undelegate_rmm_rec;
+	}
+
+	rec->mpidr = mpidr;
+
+	free_page((unsigned long)params);
+	return 0;
+
+out_undelegate_rmm_rec:
+	if (WARN_ON(rmi_undelegate_page(rec_page_phys)))
+		rec->rec_page = NULL;
+out_free_pages:
+	free_page((unsigned long)rec->run);
+	free_page((unsigned long)rec->rec_page);
+	free_page((unsigned long)params);
+	kfree(rec->sro);
+	rec->run = NULL;
+	return r;
+}
+
+void kvm_destroy_rec(struct kvm_vcpu *vcpu)
+{
+	struct realm_rec *rec = &vcpu->arch.rec;
+	unsigned long rec_page_phys;
+
+	if (!vcpu_is_rec(vcpu))
+		return;
+
+	if (!rec->run) {
+		/* Nothing to do if the VCPU hasn't been finalized */
+		return;
+	}
+
+	free_page((unsigned long)rec->run);
+
+	rec_page_phys = virt_to_phys(rec->rec_page);
+
+	if (WARN_ON(rmi_rec_destroy(rec_page_phys, rec->sro)))
+		return;
+
+	kfree(rec->sro);
+
+	free_delegated_page(rec_page_phys);
+}
+
 int kvm_activate_realm(struct kvm *kvm)
 {
 	struct realm *realm = &kvm->arch.realm;
+	struct kvm_vcpu *vcpu;
+	unsigned long i;
 	int ret;
 
 	if (kvm_realm_state(kvm) >= REALM_STATE_ACTIVE)
@@ -198,6 +297,12 @@ int kvm_activate_realm(struct kvm *kvm)
 	/* Mark state as dead in case we fail */
 	kvm_set_realm_state(kvm, REALM_STATE_DEAD);
 
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		ret = kvm_create_rec(vcpu);
+		if (ret)
+			return ret;
+	}
+
 	ret = rmi_realm_activate(virt_to_phys(realm->rd));
 	if (ret)
 		return -ENXIO;
-- 
2.43.0