hyperv-next for 5.17

-----BEGIN PGP SIGNATURE-----
 
 iQFHBAABCAAxFiEEIbPD0id6easf0xsudhRwX5BBoF4FAmHhw7oTHHdlaS5saXVA
 a2VybmVsLm9yZwAKCRB2FHBfkEGgXrjSB/979LV4Dn1PMcFYsSdlFEMeHcjzJdw/
 kFnLPXMaPJyfg6QPuf83jxzw9uxw8fcePMdVq/FFBtmVV9fJMAv62B8jaGS1p58c
 WnAg+7zsTN+xEoJn+tskSSon8BNMWVrl41zP3K4Ged+5j8UEBk62GB8Orz1qkpwL
 fTh3/+xAvczJeD4zZb1dAm4WnmcQJ4vhg45p07jX6owvnwQAikMFl45aSW54I5o8
 vAxGzFgdsZ2NtExnRNKh3b3DozA8JUE89KckBSZnDtq4rH8Fyy6Wij56Hc6v6Cml
 SUohiNbHX7hsNwit/lxL8wuF97IiA0pQSABobEg3rxfTghTUep51LlaN
 =/m4A
 -----END PGP SIGNATURE-----

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

arch/x86/hyperv/hv_init.c

@@ -28,6 +28,7 @@
 #include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
 #include <linux/highmem.h>
+#include <linux/swiotlb.h>
 
 int hyperv_init_cpuhp;
 u64 hv_current_partition_id = ~0ull;
@@ -36,7 +37,7 @@ EXPORT_SYMBOL_GPL(hv_current_partition_id);
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
-union hv_ghcb __percpu **hv_ghcb_pg;
+union hv_ghcb * __percpu *hv_ghcb_pg;
 
 /* Storage to save the hypercall page temporarily for hibernation */
 static void *hv_hypercall_pg_saved;
@@ -498,6 +499,17 @@ void __init hyperv_init(void)
 
 	/* Query the VMs extended capability once, so that it can be cached. */
 	hv_query_ext_cap(0);
+
+#ifdef CONFIG_SWIOTLB
+	/*
+	 * Swiotlb bounce buffer needs to be mapped in extra address
+	 * space. Map function doesn't work in the early place and so
+	 * call swiotlb_update_mem_attributes() here.
+	 */
+	if (hv_is_isolation_supported())
+		swiotlb_update_mem_attributes();
+#endif
+
 	return;
 
 clean_guest_os_id:

arch/x86/hyperv/ivm.c

@@ -287,3 +287,31 @@ int hv_set_mem_host_visibility(unsigned long kbuffer, int pagecount, bool visibl
 	kfree(pfn_array);
 	return ret;
 }
+
+/*
+ * hv_map_memory - map memory to extra space in the AMD SEV-SNP Isolation VM.
+ */
+void *hv_map_memory(void *addr, unsigned long size)
+{
+	unsigned long *pfns = kcalloc(size / PAGE_SIZE,
+				      sizeof(unsigned long), GFP_KERNEL);
+	void *vaddr;
+	int i;
+
+	if (!pfns)
+		return NULL;
+
+	for (i = 0; i < size / PAGE_SIZE; i++)
+		pfns[i] = vmalloc_to_pfn(addr + i * PAGE_SIZE) +
+			(ms_hyperv.shared_gpa_boundary >> PAGE_SHIFT);
+
+	vaddr = vmap_pfn(pfns, size / PAGE_SIZE, PAGE_KERNEL_IO);
+	kfree(pfns);
+
+	return vaddr;
+}
+
+void hv_unmap_memory(void *addr)
+{
+	vunmap(addr);
+}

arch/x86/hyperv/mmu.c

@@ -68,15 +68,6 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus,
 
 	local_irq_save(flags);
 
-	/*
-	 * Only check the mask _after_ interrupt has been disabled to avoid the
-	 * mask changing under our feet.
-	 */
-	if (cpumask_empty(cpus)) {
-		local_irq_restore(flags);
-		return;
-	}
-
 	flush_pcpu = (struct hv_tlb_flush **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
 
@@ -115,7 +106,9 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus,
 		 * must. We will also check all VP numbers when walking the
 		 * supplied CPU set to remain correct in all cases.
 		 */
-		if (hv_cpu_number_to_vp_number(cpumask_last(cpus)) >= 64)
+		cpu = cpumask_last(cpus);
+
+		if (cpu < nr_cpumask_bits && hv_cpu_number_to_vp_number(cpu) >= 64)
 			goto do_ex_hypercall;
 
 		for_each_cpu(cpu, cpus) {
@@ -131,6 +124,12 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus,
 			__set_bit(vcpu, (unsigned long *)
 				  &flush->processor_mask);
 		}
+
+		/* nothing to flush if 'processor_mask' ends up being empty */
+		if (!flush->processor_mask) {
+			local_irq_restore(flags);
+			return;
+		}
 	}
 
 	/*

arch/x86/include/asm/mshyperv.h

@@ -30,7 +30,7 @@ extern void *hv_hypercall_pg;
 
 extern u64 hv_current_partition_id;
 
-extern union hv_ghcb  __percpu **hv_ghcb_pg;
+extern union hv_ghcb * __percpu *hv_ghcb_pg;
 
 int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages);
 int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id);

arch/x86/kernel/cc_platform.c

@@ -11,6 +11,7 @@
 #include <linux/cc_platform.h>
 #include <linux/mem_encrypt.h>
 
+#include <asm/mshyperv.h>
 #include <asm/processor.h>
 
 static bool __maybe_unused intel_cc_platform_has(enum cc_attr attr)
@@ -66,12 +67,19 @@ static bool amd_cc_platform_has(enum cc_attr attr)
 #endif
 }
 
+static bool hyperv_cc_platform_has(enum cc_attr attr)
+{
+	return attr == CC_ATTR_GUEST_MEM_ENCRYPT;
+}
 
 bool cc_platform_has(enum cc_attr attr)
 {
 	if (sme_me_mask)
 		return amd_cc_platform_has(attr);
 
+	if (hv_is_isolation_supported())
+		return hyperv_cc_platform_has(attr);
+
 	return false;
 }
 EXPORT_SYMBOL_GPL(cc_platform_has);

arch/x86/kernel/cpu/mshyperv.c

@@ -18,6 +18,7 @@
 #include <linux/kexec.h>
 #include <linux/i8253.h>
 #include <linux/random.h>
+#include <linux/swiotlb.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv-tlfs.h>
@@ -329,8 +330,20 @@ static void __init ms_hyperv_init_platform(void)
 		pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n",
 			ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b);
 
-		if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP)
+		if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) {
 			static_branch_enable(&isolation_type_snp);
+#ifdef CONFIG_SWIOTLB
+			swiotlb_unencrypted_base = ms_hyperv.shared_gpa_boundary;
+#endif
+		}
+
+#ifdef CONFIG_SWIOTLB
+		/*
+		 * Enable swiotlb force mode in Isolation VM to
+		 * use swiotlb bounce buffer for dma transaction.
+		 */
+		swiotlb_force = SWIOTLB_FORCE;
+#endif
 	}
 
 	if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) {

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)

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);

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:

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 */

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);
 

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;

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,

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) {
+	if (scsi_sg_count(scmnd)) {
-		unsigned int hvpgoff, hvpfns_to_add;
 		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
+			 * Init values for the current sgl entry. hvpfns_to_add
-			 * and hvpfns_to_add are in units of Hyper-V size
+			 * is in units of Hyper-V size pages. Handling the
-			 * pages. Handling the PAGE_SIZE != HV_HYP_PAGE_SIZE
+			 * PAGE_SIZE != HV_HYP_PAGE_SIZE case also handles
-			 * case also handles values of sgl->offset that are
+			 * values of sgl->offset that are larger than PAGE_SIZE.
-			 * larger than PAGE_SIZE. Such offsets are handled
+			 * Such offsets are handled even on other than the first
-			 * even on other than the first sgl entry, provided
+			 * sgl entry, provided they are a multiple of PAGE_SIZE.
-			 * they are a multiple of PAGE_SIZE.
 			 */
-			hvpgoff = HVPFN_DOWN(sgl->offset);
+			hvpfn = HVPFN_DOWN(sg_dma_address(sg));
-			hvpfn = page_to_hvpfn(sg_page(sgl)) + hvpgoff;
+			hvpfns_to_add = HVPFN_UP(sg_dma_address(sg) +
-			hvpfns_to_add =	HVPFN_UP(sgl->offset + sgl->length) -
+						 sg_dma_len(sg)) - hvpfn;
-						hvpgoff;
 
 			/*
 			 * 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);

include/asm-generic/mshyperv.h

@@ -49,8 +49,8 @@ struct ms_hyperv_info {
 };
 extern struct ms_hyperv_info ms_hyperv;
 
-extern void  __percpu  **hyperv_pcpu_input_arg;
+extern void * __percpu *hyperv_pcpu_input_arg;
-extern void  __percpu  **hyperv_pcpu_output_arg;
+extern void * __percpu *hyperv_pcpu_output_arg;
 
 extern u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
 extern u64 hv_do_fast_hypercall8(u16 control, u64 input8);
@@ -269,6 +269,8 @@ bool hv_isolation_type_snp(void);
 u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size);
 void hyperv_cleanup(void);
 bool hv_query_ext_cap(u64 cap_query);
+void *hv_map_memory(void *addr, unsigned long size);
+void hv_unmap_memory(void *addr);
 #else /* CONFIG_HYPERV */
 static inline bool hv_is_hyperv_initialized(void) { return false; }
 static inline bool hv_is_hibernation_supported(void) { return false; }

include/linux/hyperv.h

@@ -1261,6 +1261,7 @@ struct hv_device {
 
 	struct vmbus_channel *channel;
 	struct kset	     *channels_kset;
+	struct device_dma_parameters dma_parms;
 
 	/* place holder to keep track of the dir for hv device in debugfs */
 	struct dentry *debug_dir;
@@ -1583,6 +1584,11 @@ struct hyperv_service_callback {
 	void (*callback)(void *context);
 };
 
+struct hv_dma_range {
+	dma_addr_t dma;
+	u32 mapping_size;
+};
+
 #define MAX_SRV_VER	0x7ffffff
 extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, u32 buflen,
 				const int *fw_version, int fw_vercnt,

include/linux/swiotlb.h

@@ -73,6 +73,9 @@ extern enum swiotlb_force swiotlb_force;
  * @end:	The end address of the swiotlb memory pool. Used to do a quick
  *		range check to see if the memory was in fact allocated by this
  *		API.
+ * @vaddr:	The vaddr of the swiotlb memory pool. The swiotlb memory pool
+ *		may be remapped in the memory encrypted case and store virtual
+ *		address for bounce buffer operation.
  * @nslabs:	The number of IO TLB blocks (in groups of 64) between @start and
  *		@end. For default swiotlb, this is command line adjustable via
  *		setup_io_tlb_npages.
@@ -92,6 +95,7 @@ extern enum swiotlb_force swiotlb_force;
 struct io_tlb_mem {
 	phys_addr_t start;
 	phys_addr_t end;
+	void *vaddr;
 	unsigned long nslabs;
 	unsigned long used;
 	unsigned int index;
@@ -186,4 +190,6 @@ static inline bool is_swiotlb_for_alloc(struct device *dev)
 }
 #endif /* CONFIG_DMA_RESTRICTED_POOL */
 
+extern phys_addr_t swiotlb_unencrypted_base;
+
 #endif /* __LINUX_SWIOTLB_H */

kernel/dma/swiotlb.c

@@ -50,6 +50,7 @@
 #include <asm/io.h>
 #include <asm/dma.h>
 
+#include <linux/io.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
 #include <linux/iommu-helper.h>
@@ -72,6 +73,8 @@ enum swiotlb_force swiotlb_force;
 
 struct io_tlb_mem io_tlb_default_mem;
 
+phys_addr_t swiotlb_unencrypted_base;
+
 /*
  * Max segment that we can provide which (if pages are contingous) will
  * not be bounced (unless SWIOTLB_FORCE is set).
@@ -155,6 +158,34 @@ static inline unsigned long nr_slots(u64 val)
 	return DIV_ROUND_UP(val, IO_TLB_SIZE);
 }
 
+/*
+ * Remap swioltb memory in the unencrypted physical address space
+ * when swiotlb_unencrypted_base is set. (e.g. for Hyper-V AMD SEV-SNP
+ * Isolation VMs).
+ */
+#ifdef CONFIG_HAS_IOMEM
+static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes)
+{
+	void *vaddr = NULL;
+
+	if (swiotlb_unencrypted_base) {
+		phys_addr_t paddr = mem->start + swiotlb_unencrypted_base;
+
+		vaddr = memremap(paddr, bytes, MEMREMAP_WB);
+		if (!vaddr)
+			pr_err("Failed to map the unencrypted memory %pa size %lx.\n",
+			       &paddr, bytes);
+	}
+
+	return vaddr;
+}
+#else
+static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes)
+{
+	return NULL;
+}
+#endif
+
 /*
  * Early SWIOTLB allocation may be too early to allow an architecture to
  * perform the desired operations.  This function allows the architecture to
@@ -172,7 +203,12 @@ void __init swiotlb_update_mem_attributes(void)
 	vaddr = phys_to_virt(mem->start);
 	bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
 	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
-	memset(vaddr, 0, bytes);
+
+	mem->vaddr = swiotlb_mem_remap(mem, bytes);
+	if (!mem->vaddr)
+		mem->vaddr = vaddr;
+
+	memset(mem->vaddr, 0, bytes);
 }
 
 static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
@@ -196,7 +232,17 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
 		mem->slots[i].alloc_size = 0;
 	}
+
+	/*
+	 * If swiotlb_unencrypted_base is set, the bounce buffer memory will
+	 * be remapped and cleared in swiotlb_update_mem_attributes.
+	 */
+	if (swiotlb_unencrypted_base)
+		return;
+
 	memset(vaddr, 0, bytes);
+	mem->vaddr = vaddr;
+	return;
 }
 
 int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
@@ -371,7 +417,7 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	phys_addr_t orig_addr = mem->slots[index].orig_addr;
 	size_t alloc_size = mem->slots[index].alloc_size;
 	unsigned long pfn = PFN_DOWN(orig_addr);
-	unsigned char *vaddr = phys_to_virt(tlb_addr);
+	unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
 	unsigned int tlb_offset, orig_addr_offset;
 
 	if (orig_addr == INVALID_PHYS_ADDR)