From: Tianyu Lan <Tianyu.Lan@microsoft.com>

The monitor pages in the CHANNELMSG_INITIATE_CONTACT msg are shared
with host in Isolation VM and so it's necessary to use hvcall to set
them visible to host. In Isolation VM with AMD SEV SNP, the access
address should be in the extra space which is above shared gpa
boundary. So remap these pages into the extra address(pa +
shared_gpa_boundary).

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 drivers/hv/connection.c   | 65 +++++++++++++++++++++++++++++++++++++++
 drivers/hv/hyperv_vmbus.h |  1 +
 2 files changed, 66 insertions(+)

diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 6d315c1465e0..e6a7bae036a8 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -19,6 +19,7 @@
 #include <linux/vmalloc.h>
 #include <linux/hyperv.h>
 #include <linux/export.h>
+#include <linux/io.h>
 #include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
@@ -104,6 +105,12 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 
 	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
 	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
+
+	if (hv_is_isolation_supported()) {
+		msg->monitor_page1 += ms_hyperv.shared_gpa_boundary;
+		msg->monitor_page2 += ms_hyperv.shared_gpa_boundary;
+	}
+
 	msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
 
 	/*
@@ -148,6 +155,31 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 		return -ECONNREFUSED;
 	}
 
+	if (hv_is_isolation_supported()) {
+		vmbus_connection.monitor_pages_va[0]
+			= vmbus_connection.monitor_pages[0];
+		vmbus_connection.monitor_pages[0]
+			= memremap(msg->monitor_page1, HV_HYP_PAGE_SIZE,
+				   MEMREMAP_WB);
+		if (!vmbus_connection.monitor_pages[0])
+			return -ENOMEM;
+
+		vmbus_connection.monitor_pages_va[1]
+			= vmbus_connection.monitor_pages[1];
+		vmbus_connection.monitor_pages[1]
+			= memremap(msg->monitor_page2, HV_HYP_PAGE_SIZE,
+				   MEMREMAP_WB);
+		if (!vmbus_connection.monitor_pages[1]) {
+			memunmap(vmbus_connection.monitor_pages[0]);
+			return -ENOMEM;
+		}
+
+		memset(vmbus_connection.monitor_pages[0], 0x00,
+		       HV_HYP_PAGE_SIZE);
+		memset(vmbus_connection.monitor_pages[1], 0x00,
+		       HV_HYP_PAGE_SIZE);
+	}
+
 	return ret;
 }
 
@@ -159,6 +191,7 @@ int vmbus_connect(void)
 	struct vmbus_channel_msginfo *msginfo = NULL;
 	int i, ret = 0;
 	__u32 version;
+	u64 pfn[2];
 
 	/* Initialize the vmbus connection */
 	vmbus_connection.conn_state = CONNECTING;
@@ -216,6 +249,16 @@ int vmbus_connect(void)
 		goto cleanup;
 	}
 
+	if (hv_is_isolation_supported()) {
+		pfn[0] = virt_to_hvpfn(vmbus_connection.monitor_pages[0]);
+		pfn[1] = virt_to_hvpfn(vmbus_connection.monitor_pages[1]);
+		if (hv_mark_gpa_visibility(2, pfn,
+				VMBUS_PAGE_VISIBLE_READ_WRITE)) {
+			ret = -EFAULT;
+			goto cleanup;
+		}
+	}
+
 	msginfo = kzalloc(sizeof(*msginfo) +
 			  sizeof(struct vmbus_channel_initiate_contact),
 			  GFP_KERNEL);
@@ -284,6 +327,8 @@ int vmbus_connect(void)
 
 void vmbus_disconnect(void)
 {
+	u64 pfn[2];
+
 	/*
 	 * First send the unload request to the host.
 	 */
@@ -303,6 +348,26 @@ void vmbus_disconnect(void)
 		vmbus_connection.int_page = NULL;
 	}
 
+	if (hv_is_isolation_supported()) {
+		if (vmbus_connection.monitor_pages_va[0]) {
+			memunmap(vmbus_connection.monitor_pages[0]);
+			vmbus_connection.monitor_pages[0]
+				= vmbus_connection.monitor_pages_va[0];
+			vmbus_connection.monitor_pages_va[0] = NULL;
+		}
+
+		if (vmbus_connection.monitor_pages_va[1]) {
+			memunmap(vmbus_connection.monitor_pages[1]);
+			vmbus_connection.monitor_pages[1]
+				= vmbus_connection.monitor_pages_va[1];
+			vmbus_connection.monitor_pages_va[1] = NULL;
+		}
+
+		pfn[0] = virt_to_hvpfn(vmbus_connection.monitor_pages[0]);
+		pfn[1] = virt_to_hvpfn(vmbus_connection.monitor_pages[1]);
+		hv_mark_gpa_visibility(2, pfn, VMBUS_PAGE_NOT_VISIBLE);
+	}
+
 	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;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 42f3d9d123a1..40bc0eff6665 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -240,6 +240,7 @@ struct vmbus_connection {
 	 * is child->parent notification
 	 */
 	struct hv_monitor_page *monitor_pages[2];
+	void *monitor_pages_va[2];
 	struct list_head chn_msg_list;
 	spinlock_t channelmsg_lock;
 
-- 
2.25.1

On Wed, Jul 28, 2021 at 10:52:22AM -0400, Tianyu Lan wrote:
> +	if (hv_is_isolation_supported()) {
> +		vmbus_connection.monitor_pages_va[0]
> +			= vmbus_connection.monitor_pages[0];
> +		vmbus_connection.monitor_pages[0]
> +			= memremap(msg->monitor_page1, HV_HYP_PAGE_SIZE,
> +				   MEMREMAP_WB);
> +		if (!vmbus_connection.monitor_pages[0])
> +			return -ENOMEM;
> +
> +		vmbus_connection.monitor_pages_va[1]
> +			= vmbus_connection.monitor_pages[1];
> +		vmbus_connection.monitor_pages[1]
> +			= memremap(msg->monitor_page2, HV_HYP_PAGE_SIZE,
> +				   MEMREMAP_WB);
> +		if (!vmbus_connection.monitor_pages[1]) {
> +			memunmap(vmbus_connection.monitor_pages[0]);
> +			return -ENOMEM;
> +		}
> +
> +		memset(vmbus_connection.monitor_pages[0], 0x00,
> +		       HV_HYP_PAGE_SIZE);
> +		memset(vmbus_connection.monitor_pages[1], 0x00,
> +		       HV_HYP_PAGE_SIZE);
> +	}

Okay, let me see if I got this right. In Hyper-V Isolation VMs, when the
guest wants to make memory shared, it does":

	- Call to the Hypervisor the mark the pages shared. The
	  Hypervisor will do the RMP update and remap the pages at
	  (VTOM + pa)

	- The guest maps the memory again into its page-table, so that
	  the entries point to the correct GPA (which is above VTOM
	  now).

Or in other words, Hyper-V implements a hardware-independent and
configurable c-bit position, as the VTOM value is always power-of-two
aligned. Is that correct?
This would at least explain why there is no separate
allocation/dealloction of memory for the shared range.

Thanks,

	Joerg