Merge tag 'hyperv-next-signed-20220114' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - More patches for Hyper-V isolation VM support (Tianyu Lan)

 - Bug fixes and clean-up patches from various people

* tag 'hyperv-next-signed-20220114' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  scsi: storvsc: Fix storvsc_queuecommand() memory leak
  x86/hyperv: Properly deal with empty cpumasks in hyperv_flush_tlb_multi()
  Drivers: hv: vmbus: Initialize request offers message for Isolation VM
  scsi: storvsc: Fix unsigned comparison to zero
  swiotlb: Add CONFIG_HAS_IOMEM check around swiotlb_mem_remap()
  x86/hyperv: Fix definition of hv_ghcb_pg variable
  Drivers: hv: Fix definition of hypercall input & output arg variables
  net: netvsc: Add Isolation VM support for netvsc driver
  scsi: storvsc: Add Isolation VM support for storvsc driver
  hyper-v: Enable swiotlb bounce buffer for Isolation VM
  x86/hyper-v: Add hyperv Isolation VM check in the cc_platform_has()
  swiotlb: Add swiotlb bounce buffer remap function for HV IVM

8 files changed, 191 insertions, 28 deletions

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 2829575fd9b7..60375879612f 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -1554,7 +1554,7 @@ int vmbus_request_offers(void)
 	struct vmbus_channel_msginfo *msginfo;
 	int ret;
 
-	msginfo = kmalloc(sizeof(*msginfo) +
+	msginfo = kzalloc(sizeof(*msginfo) +
 			  sizeof(struct vmbus_channel_message_header),
 			  GFP_KERNEL);
 	if (!msginfo)
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index 7be173a99f27..181d16bbf49d 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -44,10 +44,10 @@ EXPORT_SYMBOL_GPL(hv_vp_index);
 u32 hv_max_vp_index;
 EXPORT_SYMBOL_GPL(hv_max_vp_index);
 
-void  __percpu **hyperv_pcpu_input_arg;
+void * __percpu *hyperv_pcpu_input_arg;
 EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
 
-void  __percpu **hyperv_pcpu_output_arg;
+void * __percpu *hyperv_pcpu_output_arg;
 EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg);
 
 /*
@@ -295,3 +295,14 @@ u64 __weak hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_s
 	return HV_STATUS_INVALID_PARAMETER;
 }
 EXPORT_SYMBOL_GPL(hv_ghcb_hypercall);
+
+void __weak *hv_map_memory(void *addr, unsigned long size)
+{
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(hv_map_memory);
+
+void __weak hv_unmap_memory(void *addr)
+{
+}
+EXPORT_SYMBOL_GPL(hv_unmap_memory);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 7ae04ccb1043..17bf55fe3169 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -33,6 +33,7 @@
 #include <linux/random.h>
 #include <linux/kernel.h>
 #include <linux/syscore_ops.h>
+#include <linux/dma-map-ops.h>
 #include <clocksource/hyperv_timer.h>
 #include "hyperv_vmbus.h"
 
@@ -2078,6 +2079,7 @@ struct hv_device *vmbus_device_create(const guid_t *type,
 	return child_device_obj;
 }
 
+static u64 vmbus_dma_mask = DMA_BIT_MASK(64);
 /*
  * vmbus_device_register - Register the child device
  */
@@ -2118,6 +2120,8 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 	}
 	hv_debug_add_dev_dir(child_device_obj);
 
+	child_device_obj->device.dma_mask = &vmbus_dma_mask;
+	child_device_obj->device.dma_parms = &child_device_obj->dma_parms;
 	return 0;
 
 err_kset_unregister:
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 315278a7cf88..cf69da0e296c 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -164,6 +164,7 @@ struct hv_netvsc_packet {
 	u32 total_bytes;
 	u32 send_buf_index;
 	u32 total_data_buflen;
+	struct hv_dma_range *dma_range;
 };
 
 #define NETVSC_HASH_KEYLEN 40
@@ -1074,6 +1075,7 @@ struct netvsc_device {
 
 	/* Receive buffer allocated by us but manages by NetVSP */
 	void *recv_buf;
+	void *recv_original_buf;
 	u32 recv_buf_size; /* allocated bytes */
 	struct vmbus_gpadl recv_buf_gpadl_handle;
 	u32 recv_section_cnt;
@@ -1082,6 +1084,7 @@ struct netvsc_device {
 
 	/* Send buffer allocated by us */
 	void *send_buf;
+	void *send_original_buf;
 	u32 send_buf_size;
 	struct vmbus_gpadl send_buf_gpadl_handle;
 	u32 send_section_cnt;
@@ -1731,4 +1734,6 @@ struct rndis_message {
 #define RETRY_US_HI	10000
 #define RETRY_MAX	2000	/* >10 sec */
 
+void netvsc_dma_unmap(struct hv_device *hv_dev,
+		      struct hv_netvsc_packet *packet);
 #endif /* _HYPERV_NET_H */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 5086cd07d1ed..afa81a9480cc 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -153,8 +153,21 @@ static void free_netvsc_device(struct rcu_head *head)
 	int i;
 
 	kfree(nvdev->extension);
-	vfree(nvdev->recv_buf);
-	vfree(nvdev->send_buf);
+
+	if (nvdev->recv_original_buf) {
+		hv_unmap_memory(nvdev->recv_buf);
+		vfree(nvdev->recv_original_buf);
+	} else {
+		vfree(nvdev->recv_buf);
+	}
+
+	if (nvdev->send_original_buf) {
+		hv_unmap_memory(nvdev->send_buf);
+		vfree(nvdev->send_original_buf);
+	} else {
+		vfree(nvdev->send_buf);
+	}
+
 	bitmap_free(nvdev->send_section_map);
 
 	for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
@@ -337,6 +350,7 @@ static int netvsc_init_buf(struct hv_device *device,
 	struct nvsp_message *init_packet;
 	unsigned int buf_size;
 	int i, ret = 0;
+	void *vaddr;
 
 	/* Get receive buffer area. */
 	buf_size = device_info->recv_sections * device_info->recv_section_size;
@@ -372,6 +386,17 @@ static int netvsc_init_buf(struct hv_device *device,
 		goto cleanup;
 	}
 
+	if (hv_isolation_type_snp()) {
+		vaddr = hv_map_memory(net_device->recv_buf, buf_size);
+		if (!vaddr) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+
+		net_device->recv_original_buf = net_device->recv_buf;
+		net_device->recv_buf = vaddr;
+	}
+
 	/* Notify the NetVsp of the gpadl handle */
 	init_packet = &net_device->channel_init_pkt;
 	memset(init_packet, 0, sizeof(struct nvsp_message));
@@ -475,6 +500,17 @@ static int netvsc_init_buf(struct hv_device *device,
 		goto cleanup;
 	}
 
+	if (hv_isolation_type_snp()) {
+		vaddr = hv_map_memory(net_device->send_buf, buf_size);
+		if (!vaddr) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+
+		net_device->send_original_buf = net_device->send_buf;
+		net_device->send_buf = vaddr;
+	}
+
 	/* Notify the NetVsp of the gpadl handle */
 	init_packet = &net_device->channel_init_pkt;
 	memset(init_packet, 0, sizeof(struct nvsp_message));
@@ -764,7 +800,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 
 	/* Notify the layer above us */
 	if (likely(skb)) {
-		const struct hv_netvsc_packet *packet
+		struct hv_netvsc_packet *packet
 			= (struct hv_netvsc_packet *)skb->cb;
 		u32 send_index = packet->send_buf_index;
 		struct netvsc_stats *tx_stats;
@@ -780,6 +816,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 		tx_stats->bytes += packet->total_bytes;
 		u64_stats_update_end(&tx_stats->syncp);
 
+		netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
 		napi_consume_skb(skb, budget);
 	}
 
@@ -944,6 +981,88 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		memset(dest, 0, padding);
 }
 
+void netvsc_dma_unmap(struct hv_device *hv_dev,
+		      struct hv_netvsc_packet *packet)
+{
+	u32 page_count = packet->cp_partial ?
+		packet->page_buf_cnt - packet->rmsg_pgcnt :
+		packet->page_buf_cnt;
+	int i;
+
+	if (!hv_is_isolation_supported())
+		return;
+
+	if (!packet->dma_range)
+		return;
+
+	for (i = 0; i < page_count; i++)
+		dma_unmap_single(&hv_dev->device, packet->dma_range[i].dma,
+				 packet->dma_range[i].mapping_size,
+				 DMA_TO_DEVICE);
+
+	kfree(packet->dma_range);
+}
+
+/* netvsc_dma_map - Map swiotlb bounce buffer with data page of
+ * packet sent by vmbus_sendpacket_pagebuffer() in the Isolation
+ * VM.
+ *
+ * In isolation VM, netvsc send buffer has been marked visible to
+ * host and so the data copied to send buffer doesn't need to use
+ * bounce buffer. The data pages handled by vmbus_sendpacket_pagebuffer()
+ * may not be copied to send buffer and so these pages need to be
+ * mapped with swiotlb bounce buffer. netvsc_dma_map() is to do
+ * that. The pfns in the struct hv_page_buffer need to be converted
+ * to bounce buffer's pfn. The loop here is necessary because the
+ * entries in the page buffer array are not necessarily full
+ * pages of data.  Each entry in the array has a separate offset and
+ * len that may be non-zero, even for entries in the middle of the
+ * array.  And the entries are not physically contiguous.  So each
+ * entry must be individually mapped rather than as a contiguous unit.
+ * So not use dma_map_sg() here.
+ */
+static int netvsc_dma_map(struct hv_device *hv_dev,
+			  struct hv_netvsc_packet *packet,
+			  struct hv_page_buffer *pb)
+{
+	u32 page_count =  packet->cp_partial ?
+		packet->page_buf_cnt - packet->rmsg_pgcnt :
+		packet->page_buf_cnt;
+	dma_addr_t dma;
+	int i;
+
+	if (!hv_is_isolation_supported())
+		return 0;
+
+	packet->dma_range = kcalloc(page_count,
+				    sizeof(*packet->dma_range),
+				    GFP_KERNEL);
+	if (!packet->dma_range)
+		return -ENOMEM;
+
+	for (i = 0; i < page_count; i++) {
+		char *src = phys_to_virt((pb[i].pfn << HV_HYP_PAGE_SHIFT)
+					 + pb[i].offset);
+		u32 len = pb[i].len;
+
+		dma = dma_map_single(&hv_dev->device, src, len,
+				     DMA_TO_DEVICE);
+		if (dma_mapping_error(&hv_dev->device, dma)) {
+			kfree(packet->dma_range);
+			return -ENOMEM;
+		}
+
+		/* pb[].offset and pb[].len are not changed during dma mapping
+		 * and so not reassign.
+		 */
+		packet->dma_range[i].dma = dma;
+		packet->dma_range[i].mapping_size = len;
+		pb[i].pfn = dma >> HV_HYP_PAGE_SHIFT;
+	}
+
+	return 0;
+}
+
 static inline int netvsc_send_pkt(
 	struct hv_device *device,
 	struct hv_netvsc_packet *packet,
@@ -984,14 +1103,24 @@ static inline int netvsc_send_pkt(
 
 	trace_nvsp_send_pkt(ndev, out_channel, rpkt);
 
+	packet->dma_range = NULL;
 	if (packet->page_buf_cnt) {
 		if (packet->cp_partial)
 			pb += packet->rmsg_pgcnt;
 
+		ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb);
+		if (ret) {
+			ret = -EAGAIN;
+			goto exit;
+		}
+
 		ret = vmbus_sendpacket_pagebuffer(out_channel,
 						  pb, packet->page_buf_cnt,
 						  &nvmsg, sizeof(nvmsg),
 						  req_id);
+
+		if (ret)
+			netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
 	} else {
 		ret = vmbus_sendpacket(out_channel,
 				       &nvmsg, sizeof(nvmsg),
@@ -999,6 +1128,7 @@ static inline int netvsc_send_pkt(
 				       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	}
 
+exit:
 	if (ret == 0) {
 		atomic_inc_return(&nvchan->queue_sends);
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index efa963b7af54..3646469433b1 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2516,6 +2516,7 @@ static int netvsc_probe(struct hv_device *dev,
 	net->netdev_ops = &device_ops;
 	net->ethtool_ops = &ethtool_ops;
 	SET_NETDEV_DEV(net, &dev->device);
+	dma_set_min_align_mask(&dev->device, HV_HYP_PAGE_SIZE - 1);
 
 	/* We always need headroom for rndis header */
 	net->needed_headroom = RNDIS_AND_PPI_SIZE;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index f6c9c2a670f9..448fcc325ed7 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -361,6 +361,8 @@ static void rndis_filter_receive_response(struct net_device *ndev,
 			}
 		}
 
+		netvsc_dma_unmap(((struct net_device_context *)
+			netdev_priv(ndev))->device_ctx, &request->pkt);
 		complete(&request->wait_event);
 	} else {
 		netdev_err(ndev,
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 20595c0ba0ae..9a0bba5a51a7 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -21,6 +21,8 @@
 #include <linux/device.h>
 #include <linux/hyperv.h>
 #include <linux/blkdev.h>
+#include <linux/dma-mapping.h>
+
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_host.h>
@@ -1336,6 +1338,7 @@ static void storvsc_on_channel_callback(void *context)
 					continue;
 				}
 				request = (struct storvsc_cmd_request *)scsi_cmd_priv(scmnd);
+				scsi_dma_unmap(scmnd);
 			}
 
 			storvsc_on_receive(stor_device, packet, request);
@@ -1749,9 +1752,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	struct hv_host_device *host_dev = shost_priv(host);
 	struct hv_device *dev = host_dev->dev;
 	struct storvsc_cmd_request *cmd_request = scsi_cmd_priv(scmnd);
-	int i;
 	struct scatterlist *sgl;
-	unsigned int sg_count;
 	struct vmscsi_request *vm_srb;
 	struct vmbus_packet_mpb_array  *payload;
 	u32 payload_sz;
@@ -1824,17 +1825,17 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	memcpy(vm_srb->cdb, scmnd->cmnd, vm_srb->cdb_length);
 
 	sgl = (struct scatterlist *)scsi_sglist(scmnd);
-	sg_count = scsi_sg_count(scmnd);
 
 	length = scsi_bufflen(scmnd);
 	payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb;
 	payload_sz = sizeof(cmd_request->mpb);
 
-	if (sg_count) {
-		unsigned int hvpgoff, hvpfns_to_add;
+	if (scsi_sg_count(scmnd)) {
 		unsigned long offset_in_hvpg = offset_in_hvpage(sgl->offset);
 		unsigned int hvpg_count = HVPFN_UP(offset_in_hvpg + length);
-		u64 hvpfn;
+		struct scatterlist *sg;
+		unsigned long hvpfn, hvpfns_to_add;
+		int j, i = 0, sg_count;
 
 		if (hvpg_count > MAX_PAGE_BUFFER_COUNT) {
 
@@ -1848,21 +1849,24 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 		payload->range.len = length;
 		payload->range.offset = offset_in_hvpg;
 
+		sg_count = scsi_dma_map(scmnd);
+		if (sg_count < 0) {
+			ret = SCSI_MLQUEUE_DEVICE_BUSY;
+			goto err_free_payload;
+		}
 
-		for (i = 0; sgl != NULL; sgl = sg_next(sgl)) {
+		for_each_sg(sgl, sg, sg_count, j) {
 			/*
-			 * Init values for the current sgl entry. hvpgoff
-			 * and hvpfns_to_add are in units of Hyper-V size
-			 * pages. Handling the PAGE_SIZE != HV_HYP_PAGE_SIZE
-			 * case also handles values of sgl->offset that are
-			 * larger than PAGE_SIZE. Such offsets are handled
-			 * even on other than the first sgl entry, provided
-			 * they are a multiple of PAGE_SIZE.
+			 * Init values for the current sgl entry. hvpfns_to_add
+			 * is in units of Hyper-V size pages. Handling the
+			 * PAGE_SIZE != HV_HYP_PAGE_SIZE case also handles
+			 * values of sgl->offset that are larger than PAGE_SIZE.
+			 * Such offsets are handled even on other than the first
+			 * sgl entry, provided they are a multiple of PAGE_SIZE.
 			 */
-			hvpgoff = HVPFN_DOWN(sgl->offset);
-			hvpfn = page_to_hvpfn(sg_page(sgl)) + hvpgoff;
-			hvpfns_to_add =	HVPFN_UP(sgl->offset + sgl->length) -
-						hvpgoff;
+			hvpfn = HVPFN_DOWN(sg_dma_address(sg));
+			hvpfns_to_add = HVPFN_UP(sg_dma_address(sg) +
+						 sg_dma_len(sg)) - hvpfn;
 
 			/*
 			 * Fill the next portion of the PFN array with
@@ -1872,7 +1876,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 			 * the PFN array is filled.
 			 */
 			while (hvpfns_to_add--)
-				payload->range.pfn_array[i++] =	hvpfn++;
+				payload->range.pfn_array[i++] = hvpfn++;
 		}
 	}
 
@@ -1884,13 +1888,18 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	put_cpu();
 
 	if (ret == -EAGAIN) {
-		if (payload_sz > sizeof(cmd_request->mpb))
-			kfree(payload);
 		/* no more space */
-		return SCSI_MLQUEUE_DEVICE_BUSY;
+		ret = SCSI_MLQUEUE_DEVICE_BUSY;
+		goto err_free_payload;
 	}
 
 	return 0;
+
+err_free_payload:
+	if (payload_sz > sizeof(cmd_request->mpb))
+		kfree(payload);
+
+	return ret;
 }
 
 static struct scsi_host_template scsi_driver = {
@@ -2016,6 +2025,7 @@ static int storvsc_probe(struct hv_device *device,
 	stor_device->vmscsi_size_delta = sizeof(struct vmscsi_win8_extension);
 	spin_lock_init(&stor_device->lock);
 	hv_set_drvdata(device, stor_device);
+	dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1);
 
 	stor_device->port_number = host->host_no;
 	ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc);