[RFC PATCH v2 17/33] KVM: SVM: Support MMIO for an SEV-ES guest

[Tom Lendacky]

From: Tom Lendacky <thomas.lendacky@xxxxxxx>

For an SEV-ES guest, MMIO is performed to a shared (un-encrypted) page
so that both the hypervisor and guest can read or write to it and each
see the contents.

The GHCB specification provides software-defined VMGEXIT exit codes to
indicate a request for an MMIO read or an MMIO write. Add support to
recognize the MMIO requests and invoke SEV-ES specific routines that
can complete the MMIO operation. These routines use common KVM support
to complete the MMIO operation.

Signed-off-by: Tom Lendacky <thomas.lendacky@xxxxxxx>
---
 arch/x86/kvm/svm/sev.c | 121 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c |   3 +
 arch/x86/kvm/svm/svm.h |   6 ++
 arch/x86/kvm/x86.c     | 123 +++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.h     |   5 ++
 5 files changed, 258 insertions(+)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 4a4245b34bee..1d287f5cffac 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1350,6 +1350,11 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 		    !ghcb_rcx_is_valid(ghcb))
 			goto vmgexit_err;
 		break;
+	case SVM_VMGEXIT_MMIO_READ:
+	case SVM_VMGEXIT_MMIO_WRITE:
+		if (!ghcb_sw_scratch_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		break;
 	default:
@@ -1378,6 +1383,24 @@ static void pre_sev_es_run(struct vcpu_svm *svm)
 	if (!svm->ghcb)
 		return;
 
+	if (svm->ghcb_sa_free) {
+		/*
+		 * The scratch area lives outside the GHCB, so there is a
+		 * buffer that, depending on the operation performed, may
+		 * need to be synced, then freed.
+		 */
+		if (svm->ghcb_sa_sync) {
+			kvm_write_guest(svm->vcpu.kvm,
+					ghcb_get_sw_scratch(svm->ghcb),
+					svm->ghcb_sa, svm->ghcb_sa_len);
+			svm->ghcb_sa_sync = false;
+		}
+
+		kfree(svm->ghcb_sa);
+		svm->ghcb_sa = NULL;
+		svm->ghcb_sa_free = false;
+	}
+
 	trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb);
 
 	sev_es_sync_to_ghcb(svm);
@@ -1412,6 +1435,86 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu)
 	vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
 }
 
+#define GHCB_SCRATCH_AREA_LIMIT		(16ULL * PAGE_SIZE)
+static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
+{
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	struct ghcb *ghcb = svm->ghcb;
+	u64 ghcb_scratch_beg, ghcb_scratch_end;
+	u64 scratch_gpa_beg, scratch_gpa_end;
+	void *scratch_va;
+
+	scratch_gpa_beg = ghcb_get_sw_scratch(ghcb);
+	if (!scratch_gpa_beg) {
+		pr_err("vmgexit: scratch gpa not provided\n");
+		return false;
+	}
+
+	scratch_gpa_end = scratch_gpa_beg + len;
+	if (scratch_gpa_end < scratch_gpa_beg) {
+		pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n",
+		       len, scratch_gpa_beg);
+		return false;
+	}
+
+	if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) {
+		/* Scratch area begins within GHCB */
+		ghcb_scratch_beg = control->ghcb_gpa +
+				   offsetof(struct ghcb, shared_buffer);
+		ghcb_scratch_end = control->ghcb_gpa +
+				   offsetof(struct ghcb, reserved_1);
+
+		/*
+		 * If the scratch area begins within the GHCB, it must be
+		 * completely contained in the GHCB shared buffer area.
+		 */
+		if (scratch_gpa_beg < ghcb_scratch_beg ||
+		    scratch_gpa_end > ghcb_scratch_end) {
+			pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n",
+			       scratch_gpa_beg, scratch_gpa_end);
+			return false;
+		}
+
+		scratch_va = (void *)svm->ghcb;
+		scratch_va += (scratch_gpa_beg - control->ghcb_gpa);
+	} else {
+		/*
+		 * The guest memory must be read into a kernel buffer, so
+		 * limit the size
+		 */
+		if (len > GHCB_SCRATCH_AREA_LIMIT) {
+			pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n",
+			       len, GHCB_SCRATCH_AREA_LIMIT);
+			return false;
+		}
+		scratch_va = kzalloc(len, GFP_KERNEL);
+		if (!scratch_va)
+			return false;
+
+		if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) {
+			/* Unable to copy scratch area from guest */
+			pr_err("vmgexit: kvm_read_guest for scratch area failed\n");
+
+			kfree(scratch_va);
+			return false;
+		}
+
+		/*
+		 * The scratch area is outside the GHCB. The operation will
+		 * dictate whether the buffer needs to be synced before running
+		 * the vCPU next time (i.e. a read was requested so the data
+		 * must be written back to the guest memory).
+		 */
+		svm->ghcb_sa_sync = sync;
+		svm->ghcb_sa_free = true;
+	}
+
+	svm->ghcb_sa = scratch_va;
+	svm->ghcb_sa_len = len;
+
+	return true;
+}
+
 static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask,
 			      unsigned int pos)
 {
@@ -1549,6 +1652,24 @@ int sev_handle_vmgexit(struct vcpu_svm *svm)
 
 	ret = -EINVAL;
 	switch (exit_code) {
+	case SVM_VMGEXIT_MMIO_READ:
+		if (!setup_vmgexit_scratch(svm, true, control->exit_info_2))
+			break;
+
+		ret = kvm_sev_es_mmio_read(&svm->vcpu,
+					   control->exit_info_1,
+					   control->exit_info_2,
+					   svm->ghcb_sa);
+		break;
+	case SVM_VMGEXIT_MMIO_WRITE:
+		if (!setup_vmgexit_scratch(svm, false, control->exit_info_2))
+			break;
+
+		ret = kvm_sev_es_mmio_write(&svm->vcpu,
+					    control->exit_info_1,
+					    control->exit_info_2,
+					    svm->ghcb_sa);
+		break;
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		vcpu_unimpl(&svm->vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
 			    control->exit_info_1, control->exit_info_2);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index db821f70e561..ac5288a14f18 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1392,6 +1392,9 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 		}
 
 		__free_page(virt_to_page(svm->vmsa));
+
+		if (svm->ghcb_sa_free)
+			kfree(svm->ghcb_sa);
 	}
 
 	__free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT));
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 8a53de9b6d03..386b6b21d93a 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -171,6 +171,12 @@ struct vcpu_svm {
 	struct vmcb_save_area *vmsa;
 	struct ghcb *ghcb;
 	struct kvm_host_map ghcb_map;
+
+	/* SEV-ES scratch area support */
+	void *ghcb_sa;
+	u64 ghcb_sa_len;
+	bool ghcb_sa_sync;
+	bool ghcb_sa_free;
 };
 
 struct svm_cpu_data {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 61fda131d919..762f57ca059f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11152,6 +11152,129 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
 }
 EXPORT_SYMBOL_GPL(kvm_handle_invpcid);
 
+static int complete_sev_es_emulated_mmio(struct kvm_vcpu *vcpu)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_mmio_fragment *frag;
+	unsigned int len;
+
+	BUG_ON(!vcpu->mmio_needed);
+
+	/* Complete previous fragment */
+	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
+	len = min(8u, frag->len);
+	if (!vcpu->mmio_is_write)
+		memcpy(frag->data, run->mmio.data, len);
+
+	if (frag->len <= 8) {
+		/* Switch to the next fragment. */
+		frag++;
+		vcpu->mmio_cur_fragment++;
+	} else {
+		/* Go forward to the next mmio piece. */
+		frag->data += len;
+		frag->gpa += len;
+		frag->len -= len;
+	}
+
+	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
+		vcpu->mmio_needed = 0;
+
+		// VMG change, at this point, we're always done
+		// RIP has already been advanced
+		return 1;
+	}
+
+	// More MMIO is needed
+	run->mmio.phys_addr = frag->gpa;
+	run->mmio.len = min(8u, frag->len);
+	run->mmio.is_write = vcpu->mmio_is_write;
+	if (run->mmio.is_write)
+		memcpy(run->mmio.data, frag->data, min(8u, frag->len));
+	run->exit_reason = KVM_EXIT_MMIO;
+
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;
+
+	return 0;
+}
+
+int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
+			  void *data)
+{
+	int handled;
+	struct kvm_mmio_fragment *frag;
+
+	if (!data)
+		return -EINVAL;
+
+	handled = write_emultor.read_write_mmio(vcpu, gpa, bytes, data);
+	if (handled == bytes)
+		return 1;
+
+	bytes -= handled;
+	gpa += handled;
+	data += handled;
+
+	/*TODO: Check if need to increment number of frags */
+	frag = vcpu->mmio_fragments;
+	vcpu->mmio_nr_fragments = 1;
+	frag->len = bytes;
+	frag->gpa = gpa;
+	frag->data = data;
+
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_cur_fragment = 0;
+
+	vcpu->run->mmio.phys_addr = gpa;
+	vcpu->run->mmio.len = min(8u, frag->len);
+	vcpu->run->mmio.is_write = 1;
+	memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
+	vcpu->run->exit_reason = KVM_EXIT_MMIO;
+
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_write);
+
+int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
+			 void *data)
+{
+	int handled;
+	struct kvm_mmio_fragment *frag;
+
+	if (!data)
+		return -EINVAL;
+
+	handled = read_emultor.read_write_mmio(vcpu, gpa, bytes, data);
+	if (handled == bytes)
+		return 1;
+
+	bytes -= handled;
+	gpa += handled;
+	data += handled;
+
+	/*TODO: Check if need to increment number of frags */
+	frag = vcpu->mmio_fragments;
+	vcpu->mmio_nr_fragments = 1;
+	frag->len = bytes;
+	frag->gpa = gpa;
+	frag->data = data;
+
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_cur_fragment = 0;
+
+	vcpu->run->mmio.phys_addr = gpa;
+	vcpu->run->mmio.len = min(8u, frag->len);
+	vcpu->run->mmio.is_write = 0;
+	vcpu->run->exit_reason = KVM_EXIT_MMIO;
+
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 3900ab0c6004..65396753b6ab 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -401,4 +401,9 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
 	__reserved_bits;                                \
 })
 
+int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t src, unsigned int bytes,
+			  void *dst);
+int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t src, unsigned int bytes,
+			 void *dst);
+
 #endif
-- 
2.28.0