1 files changed, 116 insertions, 36 deletions

diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 5e479d54918c..5d9cb5bf2d62 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -19,6 +19,8 @@
 #include <linux/vmalloc.h>
 #include <linux/hyperv.h>
 #include <linux/export.h>
+#include <linux/io.h>
+#include <linux/set_memory.h>
 #include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
@@ -32,8 +34,8 @@ struct vmbus_connection vmbus_connection = {
 
 	.ready_for_suspend_event = COMPLETION_INITIALIZER(
 				  vmbus_connection.ready_for_suspend_event),
-	.ready_for_resume_event	= COMPLETION_INITIALIZER(
-				  vmbus_connection.ready_for_resume_event),
+	.all_offers_delivered_event = COMPLETION_INITIALIZER(
+				  vmbus_connection.all_offers_delivered_event),
 };
 EXPORT_SYMBOL_GPL(vmbus_connection);
 
@@ -45,8 +47,11 @@ EXPORT_SYMBOL_GPL(vmbus_proto_version);
 
 /*
  * Table of VMBus versions listed from newest to oldest.
+ * VERSION_WIN7 and VERSION_WS2008 are no longer supported in
+ * Linux guests and are not listed.
  */
 static __u32 vmbus_versions[] = {
+	VERSION_WIN10_V6_0,
 	VERSION_WIN10_V5_3,
 	VERSION_WIN10_V5_2,
 	VERSION_WIN10_V5_1,
@@ -54,16 +59,14 @@ static __u32 vmbus_versions[] = {
 	VERSION_WIN10_V4_1,
 	VERSION_WIN10,
 	VERSION_WIN8_1,
-	VERSION_WIN8,
-	VERSION_WIN7,
-	VERSION_WS2008
+	VERSION_WIN8
 };
 
 /*
  * Maximal VMBus protocol version guests can negotiate.  Useful to cap the
  * VMBus version for testing and debugging purpose.
  */
-static uint max_version = VERSION_WIN10_V5_3;
+static uint max_version = VERSION_WIN10_V6_0;
 
 module_param(max_version, uint, S_IRUGO);
 MODULE_PARM_DESC(max_version,
@@ -96,14 +99,25 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 	 */
 	if (version >= VERSION_WIN10_V5) {
 		msg->msg_sint = VMBUS_MESSAGE_SINT;
+		msg->msg_vtl = ms_hyperv.vtl;
 		vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID_4;
 	} else {
 		msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
 		vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID;
 	}
 
-	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
-	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
+	if (vmbus_is_confidential() && version >= VERSION_WIN10_V6_0)
+		msg->feature_flags = VMBUS_FEATURE_FLAG_CONFIDENTIAL_CHANNELS;
+
+	/*
+	 * shared_gpa_boundary is zero in non-SNP VMs, so it's safe to always
+	 * bitwise OR it
+	 */
+	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]) |
+				ms_hyperv.shared_gpa_boundary;
+	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]) |
+				ms_hyperv.shared_gpa_boundary;
+
 	msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
 
 	/*
@@ -168,6 +182,14 @@ int vmbus_connect(void)
 		goto cleanup;
 	}
 
+	vmbus_connection.rescind_work_queue =
+		create_workqueue("hv_vmbus_rescind");
+	if (!vmbus_connection.rescind_work_queue) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+	vmbus_connection.ignore_any_offer_msg = false;
+
 	vmbus_connection.handle_primary_chan_wq =
 		create_workqueue("hv_pri_chan");
 	if (!vmbus_connection.handle_primary_chan_wq) {
@@ -189,11 +211,19 @@ int vmbus_connect(void)
 	mutex_init(&vmbus_connection.channel_mutex);
 
 	/*
+	 * The following Hyper-V interrupt and monitor pages can be used by
+	 * UIO for mapping to user-space, so they should always be allocated on
+	 * system page boundaries. The system page size must be >= the Hyper-V
+	 * page size.
+	 */
+	BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE);
+
+	/*
 	 * Setup the vmbus event connection for channel interrupt
 	 * abstraction stuff
 	 */
 	vmbus_connection.int_page =
-	(void *)hv_alloc_hyperv_zeroed_page();
+		(void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	if (vmbus_connection.int_page == NULL) {
 		ret = -ENOMEM;
 		goto cleanup;
@@ -208,14 +238,37 @@ int vmbus_connect(void)
 	 * Setup the monitor notification facility. The 1st page for
 	 * parent->child and the 2nd page for child->parent
 	 */
-	vmbus_connection.monitor_pages[0] = (void *)hv_alloc_hyperv_zeroed_page();
-	vmbus_connection.monitor_pages[1] = (void *)hv_alloc_hyperv_zeroed_page();
+	vmbus_connection.monitor_pages[0] = (void *)__get_free_page(GFP_KERNEL);
+	vmbus_connection.monitor_pages[1] = (void *)__get_free_page(GFP_KERNEL);
 	if ((vmbus_connection.monitor_pages[0] == NULL) ||
 	    (vmbus_connection.monitor_pages[1] == NULL)) {
 		ret = -ENOMEM;
 		goto cleanup;
 	}
 
+	ret = set_memory_decrypted((unsigned long)
+				vmbus_connection.monitor_pages[0], 1);
+	ret |= set_memory_decrypted((unsigned long)
+				vmbus_connection.monitor_pages[1], 1);
+	if (ret) {
+		/*
+		 * If set_memory_decrypted() fails, the encryption state
+		 * of the memory is unknown. So leak the memory instead
+		 * of risking returning decrypted memory to the free list.
+		 * For simplicity, always handle both pages the same.
+		 */
+		vmbus_connection.monitor_pages[0] = NULL;
+		vmbus_connection.monitor_pages[1] = NULL;
+		goto cleanup;
+	}
+
+	/*
+	 * Set_memory_decrypted() will change the memory contents if
+	 * decryption occurs, so zero monitor pages here.
+	 */
+	memset(vmbus_connection.monitor_pages[0], 0x00, HV_HYP_PAGE_SIZE);
+	memset(vmbus_connection.monitor_pages[1], 0x00, HV_HYP_PAGE_SIZE);
+
 	msginfo = kzalloc(sizeof(*msginfo) +
 			  sizeof(struct vmbus_channel_initiate_contact),
 			  GFP_KERNEL);
@@ -295,18 +348,32 @@ void vmbus_disconnect(void)
 	if (vmbus_connection.handle_primary_chan_wq)
 		destroy_workqueue(vmbus_connection.handle_primary_chan_wq);
 
+	if (vmbus_connection.rescind_work_queue)
+		destroy_workqueue(vmbus_connection.rescind_work_queue);
+
 	if (vmbus_connection.work_queue)
 		destroy_workqueue(vmbus_connection.work_queue);
 
 	if (vmbus_connection.int_page) {
-		hv_free_hyperv_page((unsigned long)vmbus_connection.int_page);
+		free_page((unsigned long)vmbus_connection.int_page);
 		vmbus_connection.int_page = NULL;
 	}
 
-	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[0]);
-	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[1]);
-	vmbus_connection.monitor_pages[0] = NULL;
-	vmbus_connection.monitor_pages[1] = NULL;
+	if (vmbus_connection.monitor_pages[0]) {
+		if (!set_memory_encrypted(
+			(unsigned long)vmbus_connection.monitor_pages[0], 1))
+			free_page((unsigned long)
+				vmbus_connection.monitor_pages[0]);
+		vmbus_connection.monitor_pages[0] = NULL;
+	}
+
+	if (vmbus_connection.monitor_pages[1]) {
+		if (!set_memory_encrypted(
+			(unsigned long)vmbus_connection.monitor_pages[1], 1))
+			free_page((unsigned long)
+				vmbus_connection.monitor_pages[1]);
+		vmbus_connection.monitor_pages[1] = NULL;
+	}
 }
 
 /*
@@ -315,6 +382,10 @@ void vmbus_disconnect(void)
  */
 struct vmbus_channel *relid2channel(u32 relid)
 {
+	if (vmbus_connection.channels == NULL) {
+		pr_warn_once("relid2channel: relid=%d: No channels mapped!\n", relid);
+		return NULL;
+	}
 	if (WARN_ON(relid >= MAX_CHANNEL_RELIDS))
 		return NULL;
 	return READ_ONCE(vmbus_connection.channels[relid]);
@@ -337,34 +408,29 @@ struct vmbus_channel *relid2channel(u32 relid)
 void vmbus_on_event(unsigned long data)
 {
 	struct vmbus_channel *channel = (void *) data;
-	unsigned long time_limit = jiffies + 2;
+	void (*callback_fn)(void *context);
 
 	trace_vmbus_on_event(channel);
 
 	hv_debug_delay_test(channel, INTERRUPT_DELAY);
-	do {
-		void (*callback_fn)(void *);
-
-		/* A channel once created is persistent even when
-		 * there is no driver handling the device. An
-		 * unloading driver sets the onchannel_callback to NULL.
-		 */
-		callback_fn = READ_ONCE(channel->onchannel_callback);
-		if (unlikely(callback_fn == NULL))
-			return;
 
-		(*callback_fn)(channel->channel_callback_context);
+	/* A channel once created is persistent even when
+	 * there is no driver handling the device. An
+	 * unloading driver sets the onchannel_callback to NULL.
+	 */
+	callback_fn = READ_ONCE(channel->onchannel_callback);
+	if (unlikely(!callback_fn))
+		return;
 
-		if (channel->callback_mode != HV_CALL_BATCHED)
-			return;
+	(*callback_fn)(channel->channel_callback_context);
 
-		if (likely(hv_end_read(&channel->inbound) == 0))
-			return;
+	if (channel->callback_mode != HV_CALL_BATCHED)
+		return;
 
-		hv_begin_read(&channel->inbound);
-	} while (likely(time_before(jiffies, time_limit)));
+	if (likely(hv_end_read(&channel->inbound) == 0))
+		return;
 
-	/* The time limit (2 jiffies) has been reached */
+	hv_begin_read(&channel->inbound);
 	tasklet_schedule(&channel->callback_event);
 }
 
@@ -447,6 +513,20 @@ void vmbus_set_event(struct vmbus_channel *channel)
 
 	++channel->sig_events;
 
-	hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event);
+	if (ms_hyperv.paravisor_present) {
+		if (hv_isolation_type_snp())
+			hv_ghcb_hypercall(HVCALL_SIGNAL_EVENT, &channel->sig_event,
+					  NULL, sizeof(channel->sig_event));
+		else if (hv_isolation_type_tdx())
+			hv_tdx_hypercall(HVCALL_SIGNAL_EVENT | HV_HYPERCALL_FAST_BIT,
+					 channel->sig_event, 0);
+		else
+			WARN_ON_ONCE(1);
+	} else {
+		u64 control = HVCALL_SIGNAL_EVENT;
+
+		control |= hv_nested ? HV_HYPERCALL_NESTED : 0;
+		hv_do_fast_hypercall8(control, channel->sig_event);
+	}
 }
 EXPORT_SYMBOL_GPL(vmbus_set_event);