VMCI: Add support for ARM64

Add support for ARM64 architecture so that the driver can now be built
and VMCI device can be used.

Update Kconfig file to allow the driver to be built on ARM64 as well.
Fail vmci_guest_probe_device() on ARM64 if the device does not support
MMIO register access.  Lastly, add virtualization specific barriers
which map to actual memory barrier instructions on ARM64, because it
is required in case of ARM64 for queuepair (de)queuing.

Reviewed-by: Bryan Tan <bryantan@vmware.com>
Reviewed-by: Cyprien Laplace <claplace@vmware.com>
Signed-off-by: Vishnu Dasa <vdasa@vmware.com>
Link: https://lore.kernel.org/r/20220414193316.14356-1-vdasa@vmware.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/misc/vmw_vmci/Kconfig

@@ -5,7 +5,7 @@
 
 config VMWARE_VMCI
 	tristate "VMware VMCI Driver"
-	depends on X86 && PCI
+	depends on (X86 || ARM64) && !CPU_BIG_ENDIAN && PCI
 	help
 	  This is VMware's Virtual Machine Communication Interface.  It enables
 	  high-speed communication between host and guest in a virtual

drivers/misc/vmw_vmci/vmci_guest.c

@@ -614,6 +614,10 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
 	}
 
 	if (!mmio_base) {
+		if (IS_ENABLED(CONFIG_ARM64)) {
+			dev_err(&pdev->dev, "MMIO base is invalid\n");
+			return -ENXIO;
+		}
 		error = pcim_iomap_regions(pdev, BIT(0), KBUILD_MODNAME);
 		if (error) {
 			dev_err(&pdev->dev, "Failed to reserve/map IO regions\n");

drivers/misc/vmw_vmci/vmci_queue_pair.c

@@ -2577,6 +2577,12 @@ static ssize_t qp_enqueue_locked(struct vmci_queue *produce_q,
 	if (result < VMCI_SUCCESS)
 		return result;
 
+	/*
+	 * This virt_wmb() ensures that data written to the queue
+	 * is observable before the new producer_tail is.
+	 */
+	virt_wmb();
+
 	vmci_q_header_add_producer_tail(produce_q->q_header, written,
 					produce_q_size);
 	return written;
@@ -2620,6 +2626,12 @@ static ssize_t qp_dequeue_locked(struct vmci_queue *produce_q,
 	if (buf_ready < VMCI_SUCCESS)
 		return (ssize_t) buf_ready;
 
+	/*
+	 * This virt_rmb() ensures that data from the queue will be read
+	 * after we have determined how much is ready to be consumed.
+	 */
+	virt_rmb();
+
 	read = (size_t) (buf_ready > buf_size ? buf_size : buf_ready);
 	head = vmci_q_header_consumer_head(produce_q->q_header);
 	if (likely(head + read < consume_q_size)) {