1 files changed, 255 insertions, 122 deletions

diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index b14c5f9e0ef2..c100f04b3581 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -18,6 +18,7 @@
 #include <linux/clockchips.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
+#include <linux/export.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/mshyperv.h>
 #include <linux/set_memory.h>
@@ -25,6 +26,7 @@
 
 /* The one and only */
 struct hv_context hv_context;
+EXPORT_SYMBOL_FOR_MODULES(hv_context, "mshv_vtl");
 
 /*
  * hv_init - Main initialization routine.
@@ -74,7 +76,11 @@ int hv_post_message(union hv_connection_id connection_id,
 	aligned_msg->payload_size = payload_size;
 	memcpy((void *)aligned_msg->payload, payload, payload_size);
 
-	if (ms_hyperv.paravisor_present) {
+	if (ms_hyperv.paravisor_present && !vmbus_is_confidential()) {
+		/*
+		 * If the VMBus isn't confidential, use the CoCo-specific
+		 * mechanism to communicate with the hypervisor.
+		 */
 		if (hv_isolation_type_tdx())
 			status = hv_tdx_hypercall(HVCALL_POST_MESSAGE,
 						  virt_to_phys(aligned_msg), 0);
@@ -88,6 +94,11 @@ int hv_post_message(union hv_connection_id connection_id,
 		u64 control = HVCALL_POST_MESSAGE;
 
 		control |= hv_nested ? HV_HYPERCALL_NESTED : 0;
+		/*
+		 * If there is no paravisor, this will go to the hypervisor.
+		 * In the Confidential VMBus case, there is the paravisor
+		 * to which this will trap.
+		 */
 		status = hv_do_hypercall(control, aligned_msg, NULL);
 	}
 
@@ -95,11 +106,72 @@ int hv_post_message(union hv_connection_id connection_id,
 
 	return hv_result(status);
 }
+EXPORT_SYMBOL_FOR_MODULES(hv_post_message, "mshv_vtl");
+
+static int hv_alloc_page(void **page, bool decrypt, const char *note)
+{
+	int ret = 0;
+
+	/*
+	 * After the page changes its encryption status, its contents might
+	 * appear scrambled on some hardware. Thus `get_zeroed_page` would
+	 * zero the page out in vain, so do that explicitly exactly once.
+	 *
+	 * By default, the page is allocated encrypted in a CoCo VM.
+	 */
+	*page = (void *)__get_free_page(GFP_KERNEL);
+	if (!*page)
+		return -ENOMEM;
+
+	if (decrypt)
+		ret = set_memory_decrypted((unsigned long)*page, 1);
+	if (ret)
+		goto failed;
+
+	memset(*page, 0, PAGE_SIZE);
+	return 0;
+
+failed:
+	/*
+	 * Report the failure but don't put the page back on the free list as
+	 * its encryption status is unknown.
+	 */
+	pr_err("allocation failed for %s page, error %d, decrypted %d\n",
+		note, ret, decrypt);
+	*page = NULL;
+	return ret;
+}
+
+static int hv_free_page(void **page, bool encrypt, const char *note)
+{
+	int ret = 0;
+
+	if (!*page)
+		return 0;
+
+	if (encrypt)
+		ret = set_memory_encrypted((unsigned long)*page, 1);
+
+	/*
+	 * In the case of the failure, the page is leaked. Something is wrong,
+	 * prefer to lose the page with the unknown encryption status and stay afloat.
+	 */
+	if (ret)
+		pr_err("deallocation failed for %s page, error %d, encrypt %d\n",
+			note, ret, encrypt);
+	else
+		free_page((unsigned long)*page);
+
+	*page = NULL;
+
+	return ret;
+}
 
 int hv_synic_alloc(void)
 {
 	int cpu, ret = -ENOMEM;
 	struct hv_per_cpu_context *hv_cpu;
+	const bool decrypt = !vmbus_is_confidential();
 
 	/*
 	 * First, zero all per-cpu memory areas so hv_synic_free() can
@@ -125,73 +197,37 @@ int hv_synic_alloc(void)
 			     vmbus_on_msg_dpc, (unsigned long)hv_cpu);
 
 		if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) {
-			hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);
-			if (!hv_cpu->post_msg_page) {
-				pr_err("Unable to allocate post msg page\n");
+			ret = hv_alloc_page(&hv_cpu->post_msg_page,
+				decrypt, "post msg");
+			if (ret)
 				goto err;
-			}
-
-			ret = set_memory_decrypted((unsigned long)hv_cpu->post_msg_page, 1);
-			if (ret) {
-				pr_err("Failed to decrypt post msg page: %d\n", ret);
-				/* Just leak the page, as it's unsafe to free the page. */
-				hv_cpu->post_msg_page = NULL;
-				goto err;
-			}
-
-			memset(hv_cpu->post_msg_page, 0, PAGE_SIZE);
 		}
 
 		/*
-		 * Synic message and event pages are allocated by paravisor.
-		 * Skip these pages allocation here.
+		 * If these SynIC pages are not allocated, SIEF and SIM pages
+		 * are configured using what the root partition or the paravisor
+		 * provides upon reading the SIEFP and SIMP registers.
 		 */
 		if (!ms_hyperv.paravisor_present && !hv_root_partition()) {
-			hv_cpu->synic_message_page =
-				(void *)get_zeroed_page(GFP_ATOMIC);
-			if (!hv_cpu->synic_message_page) {
-				pr_err("Unable to allocate SYNIC message page\n");
+			ret = hv_alloc_page(&hv_cpu->hyp_synic_message_page,
+				decrypt, "hypervisor SynIC msg");
+			if (ret)
 				goto err;
-			}
-
-			hv_cpu->synic_event_page =
-				(void *)get_zeroed_page(GFP_ATOMIC);
-			if (!hv_cpu->synic_event_page) {
-				pr_err("Unable to allocate SYNIC event page\n");
-
-				free_page((unsigned long)hv_cpu->synic_message_page);
-				hv_cpu->synic_message_page = NULL;
+			ret = hv_alloc_page(&hv_cpu->hyp_synic_event_page,
+				decrypt, "hypervisor SynIC event");
+			if (ret)
 				goto err;
-			}
 		}
 
-		if (!ms_hyperv.paravisor_present &&
-		    (hv_isolation_type_snp() || hv_isolation_type_tdx())) {
-			ret = set_memory_decrypted((unsigned long)
-				hv_cpu->synic_message_page, 1);
-			if (ret) {
-				pr_err("Failed to decrypt SYNIC msg page: %d\n", ret);
-				hv_cpu->synic_message_page = NULL;
-
-				/*
-				 * Free the event page here so that hv_synic_free()
-				 * won't later try to re-encrypt it.
-				 */
-				free_page((unsigned long)hv_cpu->synic_event_page);
-				hv_cpu->synic_event_page = NULL;
+		if (vmbus_is_confidential()) {
+			ret = hv_alloc_page(&hv_cpu->para_synic_message_page,
+				false, "paravisor SynIC msg");
+			if (ret)
 				goto err;
-			}
-
-			ret = set_memory_decrypted((unsigned long)
-				hv_cpu->synic_event_page, 1);
-			if (ret) {
-				pr_err("Failed to decrypt SYNIC event page: %d\n", ret);
-				hv_cpu->synic_event_page = NULL;
+			ret = hv_alloc_page(&hv_cpu->para_synic_event_page,
+				false, "paravisor SynIC event");
+			if (ret)
 				goto err;
-			}
-
-			memset(hv_cpu->synic_message_page, 0, PAGE_SIZE);
-			memset(hv_cpu->synic_event_page, 0, PAGE_SIZE);
 		}
 	}
 
@@ -207,70 +243,46 @@ err:
 
 void hv_synic_free(void)
 {
-	int cpu, ret;
+	int cpu;
+	const bool encrypt = !vmbus_is_confidential();
 
 	for_each_present_cpu(cpu) {
 		struct hv_per_cpu_context *hv_cpu =
 			per_cpu_ptr(hv_context.cpu_context, cpu);
 
-		/* It's better to leak the page if the encryption fails. */
-		if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) {
-			if (hv_cpu->post_msg_page) {
-				ret = set_memory_encrypted((unsigned long)
-					hv_cpu->post_msg_page, 1);
-				if (ret) {
-					pr_err("Failed to encrypt post msg page: %d\n", ret);
-					hv_cpu->post_msg_page = NULL;
-				}
-			}
+		if (ms_hyperv.paravisor_present && hv_isolation_type_tdx())
+			hv_free_page(&hv_cpu->post_msg_page,
+				encrypt, "post msg");
+		if (!ms_hyperv.paravisor_present && !hv_root_partition()) {
+			hv_free_page(&hv_cpu->hyp_synic_event_page,
+				encrypt, "hypervisor SynIC event");
+			hv_free_page(&hv_cpu->hyp_synic_message_page,
+				encrypt, "hypervisor SynIC msg");
 		}
-
-		if (!ms_hyperv.paravisor_present &&
-		    (hv_isolation_type_snp() || hv_isolation_type_tdx())) {
-			if (hv_cpu->synic_message_page) {
-				ret = set_memory_encrypted((unsigned long)
-					hv_cpu->synic_message_page, 1);
-				if (ret) {
-					pr_err("Failed to encrypt SYNIC msg page: %d\n", ret);
-					hv_cpu->synic_message_page = NULL;
-				}
-			}
-
-			if (hv_cpu->synic_event_page) {
-				ret = set_memory_encrypted((unsigned long)
-					hv_cpu->synic_event_page, 1);
-				if (ret) {
-					pr_err("Failed to encrypt SYNIC event page: %d\n", ret);
-					hv_cpu->synic_event_page = NULL;
-				}
-			}
+		if (vmbus_is_confidential()) {
+			hv_free_page(&hv_cpu->para_synic_event_page,
+				false, "paravisor SynIC event");
+			hv_free_page(&hv_cpu->para_synic_message_page,
+				false, "paravisor SynIC msg");
 		}
-
-		free_page((unsigned long)hv_cpu->post_msg_page);
-		free_page((unsigned long)hv_cpu->synic_event_page);
-		free_page((unsigned long)hv_cpu->synic_message_page);
 	}
 
 	kfree(hv_context.hv_numa_map);
 }
 
 /*
- * hv_synic_init - Initialize the Synthetic Interrupt Controller.
- *
- * If it is already initialized by another entity (ie x2v shim), we need to
- * retrieve the initialized message and event pages.  Otherwise, we create and
- * initialize the message and event pages.
+ * hv_hyp_synic_enable_regs - Initialize the Synthetic Interrupt Controller
+ * with the hypervisor.
  */
-void hv_synic_enable_regs(unsigned int cpu)
+void hv_hyp_synic_enable_regs(unsigned int cpu)
 {
 	struct hv_per_cpu_context *hv_cpu =
 		per_cpu_ptr(hv_context.cpu_context, cpu);
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_sint shared_sint;
-	union hv_synic_scontrol sctrl;
 
-	/* Setup the Synic's message page */
+	/* Setup the Synic's message page with the hypervisor. */
 	simp.as_uint64 = hv_get_msr(HV_MSR_SIMP);
 	simp.simp_enabled = 1;
 
@@ -278,18 +290,18 @@ void hv_synic_enable_regs(unsigned int cpu)
 		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
 		u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) &
 				~ms_hyperv.shared_gpa_boundary;
-		hv_cpu->synic_message_page =
+		hv_cpu->hyp_synic_message_page =
 			(void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
-		if (!hv_cpu->synic_message_page)
+		if (!hv_cpu->hyp_synic_message_page)
 			pr_err("Fail to map synic message page.\n");
 	} else {
-		simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
+		simp.base_simp_gpa = virt_to_phys(hv_cpu->hyp_synic_message_page)
 			>> HV_HYP_PAGE_SHIFT;
 	}
 
 	hv_set_msr(HV_MSR_SIMP, simp.as_uint64);
 
-	/* Setup the Synic's event page */
+	/* Setup the Synic's event page with the hypervisor. */
 	siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP);
 	siefp.siefp_enabled = 1;
 
@@ -297,16 +309,17 @@ void hv_synic_enable_regs(unsigned int cpu)
 		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
 		u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) &
 				~ms_hyperv.shared_gpa_boundary;
-		hv_cpu->synic_event_page =
+		hv_cpu->hyp_synic_event_page =
 			(void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
-		if (!hv_cpu->synic_event_page)
+		if (!hv_cpu->hyp_synic_event_page)
 			pr_err("Fail to map synic event page.\n");
 	} else {
-		siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
+		siefp.base_siefp_gpa = virt_to_phys(hv_cpu->hyp_synic_event_page)
 			>> HV_HYP_PAGE_SHIFT;
 	}
 
 	hv_set_msr(HV_MSR_SIEFP, siefp.as_uint64);
+	hv_enable_coco_interrupt(cpu, vmbus_interrupt, true);
 
 	/* Setup the shared SINT. */
 	if (vmbus_irq != -1)
@@ -317,6 +330,11 @@ void hv_synic_enable_regs(unsigned int cpu)
 	shared_sint.masked = false;
 	shared_sint.auto_eoi = hv_recommend_using_aeoi();
 	hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+}
+
+static void hv_hyp_synic_enable_interrupts(void)
+{
+	union hv_synic_scontrol sctrl;
 
 	/* Enable the global synic bit */
 	sctrl.as_uint64 = hv_get_msr(HV_MSR_SCONTROL);
@@ -325,23 +343,72 @@ void hv_synic_enable_regs(unsigned int cpu)
 	hv_set_msr(HV_MSR_SCONTROL, sctrl.as_uint64);
 }
 
+static void hv_para_synic_enable_regs(unsigned int cpu)
+{
+	union hv_synic_simp simp;
+	union hv_synic_siefp siefp;
+	struct hv_per_cpu_context *hv_cpu
+		= per_cpu_ptr(hv_context.cpu_context, cpu);
+
+	/* Setup the Synic's message page with the paravisor. */
+	simp.as_uint64 = hv_para_get_synic_register(HV_MSR_SIMP);
+	simp.simp_enabled = 1;
+	simp.base_simp_gpa = virt_to_phys(hv_cpu->para_synic_message_page)
+			>> HV_HYP_PAGE_SHIFT;
+	hv_para_set_synic_register(HV_MSR_SIMP, simp.as_uint64);
+
+	/* Setup the Synic's event page with the paravisor. */
+	siefp.as_uint64 = hv_para_get_synic_register(HV_MSR_SIEFP);
+	siefp.siefp_enabled = 1;
+	siefp.base_siefp_gpa = virt_to_phys(hv_cpu->para_synic_event_page)
+			>> HV_HYP_PAGE_SHIFT;
+	hv_para_set_synic_register(HV_MSR_SIEFP, siefp.as_uint64);
+}
+
+static void hv_para_synic_enable_interrupts(void)
+{
+	union hv_synic_scontrol sctrl;
+
+	/* Enable the global synic bit */
+	sctrl.as_uint64 = hv_para_get_synic_register(HV_MSR_SCONTROL);
+	sctrl.enable = 1;
+	hv_para_set_synic_register(HV_MSR_SCONTROL, sctrl.as_uint64);
+}
+
 int hv_synic_init(unsigned int cpu)
 {
-	hv_synic_enable_regs(cpu);
+	if (vmbus_is_confidential())
+		hv_para_synic_enable_regs(cpu);
+
+	/*
+	 * The SINT is set in hv_hyp_synic_enable_regs() by calling
+	 * hv_set_msr(). hv_set_msr() in turn has special case code for the
+	 * SINT MSRs that write to the hypervisor version of the MSR *and*
+	 * the paravisor version of the MSR (but *without* the proxy bit when
+	 * VMBus is confidential).
+	 *
+	 * Then enable interrupts via the paravisor if VMBus is confidential,
+	 * and otherwise via the hypervisor.
+	 */
+
+	hv_hyp_synic_enable_regs(cpu);
+	if (vmbus_is_confidential())
+		hv_para_synic_enable_interrupts();
+	else
+		hv_hyp_synic_enable_interrupts();
 
 	hv_stimer_legacy_init(cpu, VMBUS_MESSAGE_SINT);
 
 	return 0;
 }
 
-void hv_synic_disable_regs(unsigned int cpu)
+void hv_hyp_synic_disable_regs(unsigned int cpu)
 {
 	struct hv_per_cpu_context *hv_cpu =
 		per_cpu_ptr(hv_context.cpu_context, cpu);
 	union hv_synic_sint shared_sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
-	union hv_synic_scontrol sctrl;
 
 	shared_sint.as_uint64 = hv_get_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT);
 
@@ -350,18 +417,21 @@ void hv_synic_disable_regs(unsigned int cpu)
 	/* Need to correctly cleanup in the case of SMP!!! */
 	/* Disable the interrupt */
 	hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_enable_coco_interrupt(cpu, vmbus_interrupt, false);
 
 	simp.as_uint64 = hv_get_msr(HV_MSR_SIMP);
 	/*
-	 * In Isolation VM, sim and sief pages are allocated by
+	 * In Isolation VM, simp and sief pages are allocated by
 	 * paravisor. These pages also will be used by kdump
 	 * kernel. So just reset enable bit here and keep page
 	 * addresses.
 	 */
 	simp.simp_enabled = 0;
 	if (ms_hyperv.paravisor_present || hv_root_partition()) {
-		iounmap(hv_cpu->synic_message_page);
-		hv_cpu->synic_message_page = NULL;
+		if (hv_cpu->hyp_synic_message_page) {
+			iounmap(hv_cpu->hyp_synic_message_page);
+			hv_cpu->hyp_synic_message_page = NULL;
+		}
 	} else {
 		simp.base_simp_gpa = 0;
 	}
@@ -372,21 +442,51 @@ void hv_synic_disable_regs(unsigned int cpu)
 	siefp.siefp_enabled = 0;
 
 	if (ms_hyperv.paravisor_present || hv_root_partition()) {
-		iounmap(hv_cpu->synic_event_page);
-		hv_cpu->synic_event_page = NULL;
+		if (hv_cpu->hyp_synic_event_page) {
+			iounmap(hv_cpu->hyp_synic_event_page);
+			hv_cpu->hyp_synic_event_page = NULL;
+		}
 	} else {
 		siefp.base_siefp_gpa = 0;
 	}
 
 	hv_set_msr(HV_MSR_SIEFP, siefp.as_uint64);
+}
+
+static void hv_hyp_synic_disable_interrupts(void)
+{
+	union hv_synic_scontrol sctrl;
 
 	/* Disable the global synic bit */
 	sctrl.as_uint64 = hv_get_msr(HV_MSR_SCONTROL);
 	sctrl.enable = 0;
 	hv_set_msr(HV_MSR_SCONTROL, sctrl.as_uint64);
+}
 
-	if (vmbus_irq != -1)
-		disable_percpu_irq(vmbus_irq);
+static void hv_para_synic_disable_regs(unsigned int cpu)
+{
+	union hv_synic_simp simp;
+	union hv_synic_siefp siefp;
+
+	/* Disable SynIC's message page in the paravisor. */
+	simp.as_uint64 = hv_para_get_synic_register(HV_MSR_SIMP);
+	simp.simp_enabled = 0;
+	hv_para_set_synic_register(HV_MSR_SIMP, simp.as_uint64);
+
+	/* Disable SynIC's event page in the paravisor. */
+	siefp.as_uint64 = hv_para_get_synic_register(HV_MSR_SIEFP);
+	siefp.siefp_enabled = 0;
+	hv_para_set_synic_register(HV_MSR_SIEFP, siefp.as_uint64);
+}
+
+static void hv_para_synic_disable_interrupts(void)
+{
+	union hv_synic_scontrol sctrl;
+
+	/* Disable the global synic bit */
+	sctrl.as_uint64 = hv_para_get_synic_register(HV_MSR_SCONTROL);
+	sctrl.enable = 0;
+	hv_para_set_synic_register(HV_MSR_SCONTROL, sctrl.as_uint64);
 }
 
 #define HV_MAX_TRIES 3
@@ -399,16 +499,18 @@ void hv_synic_disable_regs(unsigned int cpu)
  * that the normal interrupt handling mechanism will find and process the channel interrupt
  * "very soon", and in the process clear the bit.
  */
-static bool hv_synic_event_pending(void)
+static bool __hv_synic_event_pending(union hv_synic_event_flags *event, int sint)
 {
-	struct hv_per_cpu_context *hv_cpu = this_cpu_ptr(hv_context.cpu_context);
-	union hv_synic_event_flags *event =
-		(union hv_synic_event_flags *)hv_cpu->synic_event_page + VMBUS_MESSAGE_SINT;
-	unsigned long *recv_int_page = event->flags; /* assumes VMBus version >= VERSION_WIN8 */
+	unsigned long *recv_int_page;
 	bool pending;
 	u32 relid;
 	int tries = 0;
 
+	if (!event)
+		return false;
+
+	event += sint;
+	recv_int_page = event->flags; /* assumes VMBus version >= VERSION_WIN8 */
 retry:
 	pending = false;
 	for_each_set_bit(relid, recv_int_page, HV_EVENT_FLAGS_COUNT) {
@@ -425,6 +527,17 @@ retry:
 	return pending;
 }
 
+static bool hv_synic_event_pending(void)
+{
+	struct hv_per_cpu_context *hv_cpu = this_cpu_ptr(hv_context.cpu_context);
+	union hv_synic_event_flags *hyp_synic_event_page = hv_cpu->hyp_synic_event_page;
+	union hv_synic_event_flags *para_synic_event_page = hv_cpu->para_synic_event_page;
+
+	return
+		__hv_synic_event_pending(hyp_synic_event_page, VMBUS_MESSAGE_SINT) ||
+		__hv_synic_event_pending(para_synic_event_page, VMBUS_MESSAGE_SINT);
+}
+
 static int hv_pick_new_cpu(struct vmbus_channel *channel)
 {
 	int ret = -EBUSY;
@@ -517,7 +630,27 @@ int hv_synic_cleanup(unsigned int cpu)
 always_cleanup:
 	hv_stimer_legacy_cleanup(cpu);
 
-	hv_synic_disable_regs(cpu);
+	/*
+	 * First, disable the event and message pages
+	 * used for communicating with the host, and then
+	 * disable the host interrupts if VMBus is not
+	 * confidential.
+	 */
+	hv_hyp_synic_disable_regs(cpu);
+	if (!vmbus_is_confidential())
+		hv_hyp_synic_disable_interrupts();
+
+	/*
+	 * Perform the same steps for the Confidential VMBus.
+	 * The sequencing provides the guarantee that no data
+	 * may be posted for processing before disabling interrupts.
+	 */
+	if (vmbus_is_confidential()) {
+		hv_para_synic_disable_regs(cpu);
+		hv_para_synic_disable_interrupts();
+	}
+	if (vmbus_irq != -1)
+		disable_percpu_irq(vmbus_irq);
 
 	return ret;
 }