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

Pull Hyper-V updates from Wei Liu:

 - a series from Boqun Feng to support page size larger than 4K

 - a few miscellaneous clean-ups

* tag 'hyperv-next-signed' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  hv: clocksource: Add notrace attribute to read_hv_sched_clock_*() functions
  x86/hyperv: Remove aliases with X64 in their name
  PCI: hv: Document missing hv_pci_protocol_negotiation() parameter
  scsi: storvsc: Support PAGE_SIZE larger than 4K
  Driver: hv: util: Use VMBUS_RING_SIZE() for ringbuffer sizes
  HID: hyperv: Use VMBUS_RING_SIZE() for ringbuffer sizes
  Input: hyperv-keyboard: Use VMBUS_RING_SIZE() for ringbuffer sizes
  hv_netvsc: Use HV_HYP_PAGE_SIZE for Hyper-V communication
  hv: hyperv.h: Introduce some hvpfn helper functions
  Drivers: hv: vmbus: Move virt_to_hvpfn() to hyperv header
  Drivers: hv: Use HV_HYP_PAGE in hv_synic_enable_regs()
  Drivers: hv: vmbus: Introduce types of GPADL
  Drivers: hv: vmbus: Move __vmbus_open()
  Drivers: hv: vmbus: Always use HV_HYP_PAGE_SIZE for gpadl
  drivers: hv: remove cast from hyperv_die_event

drivers/clocksource/hyperv_timer.c

@@ -341,7 +341,7 @@ static u64 notrace read_hv_clock_tsc_cs(struct clocksource *arg)
 	return read_hv_clock_tsc();
 }
 
-static u64 read_hv_sched_clock_tsc(void)
+static u64 notrace read_hv_sched_clock_tsc(void)
 {
 	return (read_hv_clock_tsc() - hv_sched_clock_offset) *
 		(NSEC_PER_SEC / HV_CLOCK_HZ);
@@ -404,7 +404,7 @@ static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg)
 	return read_hv_clock_msr();
 }
 
-static u64 read_hv_sched_clock_msr(void)
+static u64 notrace read_hv_sched_clock_msr(void)
 {
 	return (read_hv_clock_msr() - hv_sched_clock_offset) *
 		(NSEC_PER_SEC / HV_CLOCK_HZ);

drivers/hid/hid-hyperv.c

@@ -104,8 +104,8 @@ struct synthhid_input_report {
 
 #pragma pack(pop)
 
-#define INPUTVSC_SEND_RING_BUFFER_SIZE		(40 * 1024)
-#define INPUTVSC_RECV_RING_BUFFER_SIZE		(40 * 1024)
+#define INPUTVSC_SEND_RING_BUFFER_SIZE	VMBUS_RING_SIZE(36 * 1024)
+#define INPUTVSC_RECV_RING_BUFFER_SIZE	VMBUS_RING_SIZE(36 * 1024)
 
 
 enum pipe_prot_msg_type {

drivers/hv/channel.c

@@ -22,20 +22,97 @@
 
 #include "hyperv_vmbus.h"
 
-#define NUM_PAGES_SPANNED(addr, len) \
-((PAGE_ALIGN(addr + len) >> PAGE_SHIFT) - (addr >> PAGE_SHIFT))
+/*
+ * hv_gpadl_size - Return the real size of a gpadl, the size that Hyper-V uses
+ *
+ * For BUFFER gpadl, Hyper-V uses the exact same size as the guest does.
+ *
+ * For RING gpadl, in each ring, the guest uses one PAGE_SIZE as the header
+ * (because of the alignment requirement), however, the hypervisor only
+ * uses the first HV_HYP_PAGE_SIZE as the header, therefore leaving a
+ * (PAGE_SIZE - HV_HYP_PAGE_SIZE) gap. And since there are two rings in a
+ * ringbuffer, the total size for a RING gpadl that Hyper-V uses is the
+ * total size that the guest uses minus twice of the gap size.
+ */
+static inline u32 hv_gpadl_size(enum hv_gpadl_type type, u32 size)
+{
+	switch (type) {
+	case HV_GPADL_BUFFER:
+		return size;
+	case HV_GPADL_RING:
+		/* The size of a ringbuffer must be page-aligned */
+		BUG_ON(size % PAGE_SIZE);
+		/*
+		 * Two things to notice here:
+		 * 1) We're processing two ring buffers as a unit
+		 * 2) We're skipping any space larger than HV_HYP_PAGE_SIZE in
+		 * the first guest-size page of each of the two ring buffers.
+		 * So we effectively subtract out two guest-size pages, and add
+		 * back two Hyper-V size pages.
+		 */
+		return size - 2 * (PAGE_SIZE - HV_HYP_PAGE_SIZE);
+	}
+	BUG();
+	return 0;
+}
 
-static unsigned long virt_to_hvpfn(void *addr)
+/*
+ * hv_ring_gpadl_send_hvpgoffset - Calculate the send offset (in unit of
+ *                                 HV_HYP_PAGE) in a ring gpadl based on the
+ *                                 offset in the guest
+ *
+ * @offset: the offset (in bytes) where the send ringbuffer starts in the
+ *               virtual address space of the guest
+ */
+static inline u32 hv_ring_gpadl_send_hvpgoffset(u32 offset)
 {
-	phys_addr_t paddr;
 
-	if (is_vmalloc_addr(addr))
-		paddr = page_to_phys(vmalloc_to_page(addr)) +
-					 offset_in_page(addr);
-	else
-		paddr = __pa(addr);
+	/*
+	 * For RING gpadl, in each ring, the guest uses one PAGE_SIZE as the
+	 * header (because of the alignment requirement), however, the
+	 * hypervisor only uses the first HV_HYP_PAGE_SIZE as the header,
+	 * therefore leaving a (PAGE_SIZE - HV_HYP_PAGE_SIZE) gap.
+	 *
+	 * And to calculate the effective send offset in gpadl, we need to
+	 * substract this gap.
+	 */
+	return (offset - (PAGE_SIZE - HV_HYP_PAGE_SIZE)) >> HV_HYP_PAGE_SHIFT;
+}
 
-	return  paddr >> PAGE_SHIFT;
+/*
+ * hv_gpadl_hvpfn - Return the Hyper-V page PFN of the @i th Hyper-V page in
+ *                  the gpadl
+ *
+ * @type: the type of the gpadl
+ * @kbuffer: the pointer to the gpadl in the guest
+ * @size: the total size (in bytes) of the gpadl
+ * @send_offset: the offset (in bytes) where the send ringbuffer starts in the
+ *               virtual address space of the guest
+ * @i: the index
+ */
+static inline u64 hv_gpadl_hvpfn(enum hv_gpadl_type type, void *kbuffer,
+				 u32 size, u32 send_offset, int i)
+{
+	int send_idx = hv_ring_gpadl_send_hvpgoffset(send_offset);
+	unsigned long delta = 0UL;
+
+	switch (type) {
+	case HV_GPADL_BUFFER:
+		break;
+	case HV_GPADL_RING:
+		if (i == 0)
+			delta = 0;
+		else if (i <= send_idx)
+			delta = PAGE_SIZE - HV_HYP_PAGE_SIZE;
+		else
+			delta = 2 * (PAGE_SIZE - HV_HYP_PAGE_SIZE);
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	return virt_to_hvpfn(kbuffer + delta + (HV_HYP_PAGE_SIZE * i));
 }
 
 /*
@@ -112,160 +189,6 @@ int vmbus_alloc_ring(struct vmbus_channel *newchannel,
 }
 EXPORT_SYMBOL_GPL(vmbus_alloc_ring);
 
-static int __vmbus_open(struct vmbus_channel *newchannel,
-		       void *userdata, u32 userdatalen,
-		       void (*onchannelcallback)(void *context), void *context)
-{
-	struct vmbus_channel_open_channel *open_msg;
-	struct vmbus_channel_msginfo *open_info = NULL;
-	struct page *page = newchannel->ringbuffer_page;
-	u32 send_pages, recv_pages;
-	unsigned long flags;
-	int err;
-
-	if (userdatalen > MAX_USER_DEFINED_BYTES)
-		return -EINVAL;
-
-	send_pages = newchannel->ringbuffer_send_offset;
-	recv_pages = newchannel->ringbuffer_pagecount - send_pages;
-
-	if (newchannel->state != CHANNEL_OPEN_STATE)
-		return -EINVAL;
-
-	newchannel->state = CHANNEL_OPENING_STATE;
-	newchannel->onchannel_callback = onchannelcallback;
-	newchannel->channel_callback_context = context;
-
-	err = hv_ringbuffer_init(&newchannel->outbound, page, send_pages);
-	if (err)
-		goto error_clean_ring;
-
-	err = hv_ringbuffer_init(&newchannel->inbound,
-				 &page[send_pages], recv_pages);
-	if (err)
-		goto error_clean_ring;
-
-	/* Establish the gpadl for the ring buffer */
-	newchannel->ringbuffer_gpadlhandle = 0;
-
-	err = vmbus_establish_gpadl(newchannel,
-				    page_address(newchannel->ringbuffer_page),
-				    (send_pages + recv_pages) << PAGE_SHIFT,
-				    &newchannel->ringbuffer_gpadlhandle);
-	if (err)
-		goto error_clean_ring;
-
-	/* Create and init the channel open message */
-	open_info = kmalloc(sizeof(*open_info) +
-			   sizeof(struct vmbus_channel_open_channel),
-			   GFP_KERNEL);
-	if (!open_info) {
-		err = -ENOMEM;
-		goto error_free_gpadl;
-	}
-
-	init_completion(&open_info->waitevent);
-	open_info->waiting_channel = newchannel;
-
-	open_msg = (struct vmbus_channel_open_channel *)open_info->msg;
-	open_msg->header.msgtype = CHANNELMSG_OPENCHANNEL;
-	open_msg->openid = newchannel->offermsg.child_relid;
-	open_msg->child_relid = newchannel->offermsg.child_relid;
-	open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle;
-	open_msg->downstream_ringbuffer_pageoffset = newchannel->ringbuffer_send_offset;
-	open_msg->target_vp = hv_cpu_number_to_vp_number(newchannel->target_cpu);
-
-	if (userdatalen)
-		memcpy(open_msg->userdata, userdata, userdatalen);
-
-	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
-	list_add_tail(&open_info->msglistentry,
-		      &vmbus_connection.chn_msg_list);
-	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
-
-	if (newchannel->rescind) {
-		err = -ENODEV;
-		goto error_free_info;
-	}
-
-	err = vmbus_post_msg(open_msg,
-			     sizeof(struct vmbus_channel_open_channel), true);
-
-	trace_vmbus_open(open_msg, err);
-
-	if (err != 0)
-		goto error_clean_msglist;
-
-	wait_for_completion(&open_info->waitevent);
-
-	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
-	list_del(&open_info->msglistentry);
-	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
-
-	if (newchannel->rescind) {
-		err = -ENODEV;
-		goto error_free_info;
-	}
-
-	if (open_info->response.open_result.status) {
-		err = -EAGAIN;
-		goto error_free_info;
-	}
-
-	newchannel->state = CHANNEL_OPENED_STATE;
-	kfree(open_info);
-	return 0;
-
-error_clean_msglist:
-	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
-	list_del(&open_info->msglistentry);
-	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
-error_free_info:
-	kfree(open_info);
-error_free_gpadl:
-	vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle);
-	newchannel->ringbuffer_gpadlhandle = 0;
-error_clean_ring:
-	hv_ringbuffer_cleanup(&newchannel->outbound);
-	hv_ringbuffer_cleanup(&newchannel->inbound);
-	newchannel->state = CHANNEL_OPEN_STATE;
-	return err;
-}
-
-/*
- * vmbus_connect_ring - Open the channel but reuse ring buffer
- */
-int vmbus_connect_ring(struct vmbus_channel *newchannel,
-		       void (*onchannelcallback)(void *context), void *context)
-{
-	return  __vmbus_open(newchannel, NULL, 0, onchannelcallback, context);
-}
-EXPORT_SYMBOL_GPL(vmbus_connect_ring);
-
-/*
- * vmbus_open - Open the specified channel.
- */
-int vmbus_open(struct vmbus_channel *newchannel,
-	       u32 send_ringbuffer_size, u32 recv_ringbuffer_size,
-	       void *userdata, u32 userdatalen,
-	       void (*onchannelcallback)(void *context), void *context)
-{
-	int err;
-
-	err = vmbus_alloc_ring(newchannel, send_ringbuffer_size,
-			       recv_ringbuffer_size);
-	if (err)
-		return err;
-
-	err = __vmbus_open(newchannel, userdata, userdatalen,
-			   onchannelcallback, context);
-	if (err)
-		vmbus_free_ring(newchannel);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(vmbus_open);
-
 /* Used for Hyper-V Socket: a guest client's connect() to the host */
 int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id,
 				  const guid_t *shv_host_servie_id)
@@ -317,7 +240,8 @@ EXPORT_SYMBOL_GPL(vmbus_send_modifychannel);
 /*
  * create_gpadl_header - Creates a gpadl for the specified buffer
  */
-static int create_gpadl_header(void *kbuffer, u32 size,
+static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer,
+			       u32 size, u32 send_offset,
 			       struct vmbus_channel_msginfo **msginfo)
 {
 	int i;
@@ -330,7 +254,7 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 
 	int pfnsum, pfncount, pfnleft, pfncurr, pfnsize;
 
-	pagecount = size >> PAGE_SHIFT;
+	pagecount = hv_gpadl_size(type, size) >> HV_HYP_PAGE_SHIFT;
 
 	/* do we need a gpadl body msg */
 	pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
@@ -357,10 +281,10 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 		gpadl_header->range_buflen = sizeof(struct gpa_range) +
 					 pagecount * sizeof(u64);
 		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = size;
+		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
 		for (i = 0; i < pfncount; i++)
-			gpadl_header->range[0].pfn_array[i] = virt_to_hvpfn(
-				kbuffer + PAGE_SIZE * i);
+			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
+				type, kbuffer, size, send_offset, i);
 		*msginfo = msgheader;
 
 		pfnsum = pfncount;
@@ -411,8 +335,8 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 			 * so the hypervisor guarantees that this is ok.
 			 */
 			for (i = 0; i < pfncurr; i++)
-				gpadl_body->pfn[i] = virt_to_hvpfn(
-					kbuffer + PAGE_SIZE * (pfnsum + i));
+				gpadl_body->pfn[i] = hv_gpadl_hvpfn(type,
+					kbuffer, size, send_offset, pfnsum + i);
 
 			/* add to msg header */
 			list_add_tail(&msgbody->msglistentry,
@@ -438,10 +362,10 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 		gpadl_header->range_buflen = sizeof(struct gpa_range) +
 					 pagecount * sizeof(u64);
 		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = size;
+		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
 		for (i = 0; i < pagecount; i++)
-			gpadl_header->range[0].pfn_array[i] = virt_to_hvpfn(
-				kbuffer + PAGE_SIZE * i);
+			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
+				type, kbuffer, size, send_offset, i);
 
 		*msginfo = msgheader;
 	}
@@ -454,15 +378,20 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 }
 
 /*
- * vmbus_establish_gpadl - Establish a GPADL for the specified buffer
+ * __vmbus_establish_gpadl - Establish a GPADL for a buffer or ringbuffer
  *
  * @channel: a channel
+ * @type: the type of the corresponding GPADL, only meaningful for the guest.
  * @kbuffer: from kmalloc or vmalloc
  * @size: page-size multiple
+ * @send_offset: the offset (in bytes) where the send ring buffer starts,
+ * 		 should be 0 for BUFFER type gpadl
  * @gpadl_handle: some funky thing
  */
-int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
-			       u32 size, u32 *gpadl_handle)
+static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
+				   enum hv_gpadl_type type, void *kbuffer,
+				   u32 size, u32 send_offset,
+				   u32 *gpadl_handle)
 {
 	struct vmbus_channel_gpadl_header *gpadlmsg;
 	struct vmbus_channel_gpadl_body *gpadl_body;
@@ -476,7 +405,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	next_gpadl_handle =
 		(atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1);
 
-	ret = create_gpadl_header(kbuffer, size, &msginfo);
+	ret = create_gpadl_header(type, kbuffer, size, send_offset, &msginfo);
 	if (ret)
 		return ret;
 
@@ -557,8 +486,184 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	kfree(msginfo);
 	return ret;
 }
+
+/*
+ * vmbus_establish_gpadl - Establish a GPADL for the specified buffer
+ *
+ * @channel: a channel
+ * @kbuffer: from kmalloc or vmalloc
+ * @size: page-size multiple
+ * @gpadl_handle: some funky thing
+ */
+int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
+			  u32 size, u32 *gpadl_handle)
+{
+	return __vmbus_establish_gpadl(channel, HV_GPADL_BUFFER, kbuffer, size,
+				       0U, gpadl_handle);
+}
 EXPORT_SYMBOL_GPL(vmbus_establish_gpadl);
 
+static int __vmbus_open(struct vmbus_channel *newchannel,
+		       void *userdata, u32 userdatalen,
+		       void (*onchannelcallback)(void *context), void *context)
+{
+	struct vmbus_channel_open_channel *open_msg;
+	struct vmbus_channel_msginfo *open_info = NULL;
+	struct page *page = newchannel->ringbuffer_page;
+	u32 send_pages, recv_pages;
+	unsigned long flags;
+	int err;
+
+	if (userdatalen > MAX_USER_DEFINED_BYTES)
+		return -EINVAL;
+
+	send_pages = newchannel->ringbuffer_send_offset;
+	recv_pages = newchannel->ringbuffer_pagecount - send_pages;
+
+	if (newchannel->state != CHANNEL_OPEN_STATE)
+		return -EINVAL;
+
+	newchannel->state = CHANNEL_OPENING_STATE;
+	newchannel->onchannel_callback = onchannelcallback;
+	newchannel->channel_callback_context = context;
+
+	err = hv_ringbuffer_init(&newchannel->outbound, page, send_pages);
+	if (err)
+		goto error_clean_ring;
+
+	err = hv_ringbuffer_init(&newchannel->inbound,
+				 &page[send_pages], recv_pages);
+	if (err)
+		goto error_clean_ring;
+
+	/* Establish the gpadl for the ring buffer */
+	newchannel->ringbuffer_gpadlhandle = 0;
+
+	err = __vmbus_establish_gpadl(newchannel, HV_GPADL_RING,
+				      page_address(newchannel->ringbuffer_page),
+				      (send_pages + recv_pages) << PAGE_SHIFT,
+				      newchannel->ringbuffer_send_offset << PAGE_SHIFT,
+				      &newchannel->ringbuffer_gpadlhandle);
+	if (err)
+		goto error_clean_ring;
+
+	/* Create and init the channel open message */
+	open_info = kmalloc(sizeof(*open_info) +
+			   sizeof(struct vmbus_channel_open_channel),
+			   GFP_KERNEL);
+	if (!open_info) {
+		err = -ENOMEM;
+		goto error_free_gpadl;
+	}
+
+	init_completion(&open_info->waitevent);
+	open_info->waiting_channel = newchannel;
+
+	open_msg = (struct vmbus_channel_open_channel *)open_info->msg;
+	open_msg->header.msgtype = CHANNELMSG_OPENCHANNEL;
+	open_msg->openid = newchannel->offermsg.child_relid;
+	open_msg->child_relid = newchannel->offermsg.child_relid;
+	open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle;
+	/*
+	 * The unit of ->downstream_ringbuffer_pageoffset is HV_HYP_PAGE and
+	 * the unit of ->ringbuffer_send_offset (i.e. send_pages) is PAGE, so
+	 * here we calculate it into HV_HYP_PAGE.
+	 */
+	open_msg->downstream_ringbuffer_pageoffset =
+		hv_ring_gpadl_send_hvpgoffset(send_pages << PAGE_SHIFT);
+	open_msg->target_vp = hv_cpu_number_to_vp_number(newchannel->target_cpu);
+
+	if (userdatalen)
+		memcpy(open_msg->userdata, userdata, userdatalen);
+
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+	list_add_tail(&open_info->msglistentry,
+		      &vmbus_connection.chn_msg_list);
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+
+	if (newchannel->rescind) {
+		err = -ENODEV;
+		goto error_free_info;
+	}
+
+	err = vmbus_post_msg(open_msg,
+			     sizeof(struct vmbus_channel_open_channel), true);
+
+	trace_vmbus_open(open_msg, err);
+
+	if (err != 0)
+		goto error_clean_msglist;
+
+	wait_for_completion(&open_info->waitevent);
+
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+	list_del(&open_info->msglistentry);
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+
+	if (newchannel->rescind) {
+		err = -ENODEV;
+		goto error_free_info;
+	}
+
+	if (open_info->response.open_result.status) {
+		err = -EAGAIN;
+		goto error_free_info;
+	}
+
+	newchannel->state = CHANNEL_OPENED_STATE;
+	kfree(open_info);
+	return 0;
+
+error_clean_msglist:
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+	list_del(&open_info->msglistentry);
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+error_free_info:
+	kfree(open_info);
+error_free_gpadl:
+	vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle);
+	newchannel->ringbuffer_gpadlhandle = 0;
+error_clean_ring:
+	hv_ringbuffer_cleanup(&newchannel->outbound);
+	hv_ringbuffer_cleanup(&newchannel->inbound);
+	newchannel->state = CHANNEL_OPEN_STATE;
+	return err;
+}
+
+/*
+ * vmbus_connect_ring - Open the channel but reuse ring buffer
+ */
+int vmbus_connect_ring(struct vmbus_channel *newchannel,
+		       void (*onchannelcallback)(void *context), void *context)
+{
+	return  __vmbus_open(newchannel, NULL, 0, onchannelcallback, context);
+}
+EXPORT_SYMBOL_GPL(vmbus_connect_ring);
+
+/*
+ * vmbus_open - Open the specified channel.
+ */
+int vmbus_open(struct vmbus_channel *newchannel,
+	       u32 send_ringbuffer_size, u32 recv_ringbuffer_size,
+	       void *userdata, u32 userdatalen,
+	       void (*onchannelcallback)(void *context), void *context)
+{
+	int err;
+
+	err = vmbus_alloc_ring(newchannel, send_ringbuffer_size,
+			       recv_ringbuffer_size);
+	if (err)
+		return err;
+
+	err = __vmbus_open(newchannel, userdata, userdatalen,
+			   onchannelcallback, context);
+	if (err)
+		vmbus_free_ring(newchannel);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(vmbus_open);
+
 /*
  * vmbus_teardown_gpadl -Teardown the specified GPADL handle
  */

drivers/hv/hv.c

@@ -165,7 +165,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 	hv_get_simp(simp.as_uint64);
 	simp.simp_enabled = 1;
 	simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
-		>> PAGE_SHIFT;
+		>> HV_HYP_PAGE_SHIFT;
 
 	hv_set_simp(simp.as_uint64);
 
@@ -173,7 +173,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 	hv_get_siefp(siefp.as_uint64);
 	siefp.siefp_enabled = 1;
 	siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
-		>> PAGE_SHIFT;
+		>> HV_HYP_PAGE_SHIFT;
 
 	hv_set_siefp(siefp.as_uint64);
 

drivers/hv/hv_util.c

@@ -500,6 +500,9 @@ static void heartbeat_onchannelcallback(void *context)
 	}
 }
 
+#define HV_UTIL_RING_SEND_SIZE VMBUS_RING_SIZE(3 * HV_HYP_PAGE_SIZE)
+#define HV_UTIL_RING_RECV_SIZE VMBUS_RING_SIZE(3 * HV_HYP_PAGE_SIZE)
+
 static int util_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
 {
@@ -530,8 +533,8 @@ static int util_probe(struct hv_device *dev,
 
 	hv_set_drvdata(dev, srv);
 
-	ret = vmbus_open(dev->channel, 4 * HV_HYP_PAGE_SIZE,
-			 4 * HV_HYP_PAGE_SIZE, NULL, 0, srv->util_cb,
+	ret = vmbus_open(dev->channel, HV_UTIL_RING_SEND_SIZE,
+			 HV_UTIL_RING_RECV_SIZE, NULL, 0, srv->util_cb,
 			 dev->channel);
 	if (ret)
 		goto error;
@@ -590,8 +593,8 @@ static int util_resume(struct hv_device *dev)
 			return ret;
 	}
 
-	ret = vmbus_open(dev->channel, 4 * HV_HYP_PAGE_SIZE,
-			 4 * HV_HYP_PAGE_SIZE, NULL, 0, srv->util_cb,
+	ret = vmbus_open(dev->channel, HV_UTIL_RING_SEND_SIZE,
+			 HV_UTIL_RING_RECV_SIZE, NULL, 0, srv->util_cb,
 			 dev->channel);
 	return ret;
 }

drivers/hv/vmbus_drv.c

@@ -83,7 +83,7 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
 static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
 			    void *args)
 {
-	struct die_args *die = (struct die_args *)args;
+	struct die_args *die = args;
 	struct pt_regs *regs = die->regs;
 
 	/* Don't notify Hyper-V if the die event is other than oops */

drivers/input/serio/hyperv-keyboard.c

@@ -75,8 +75,8 @@ struct synth_kbd_keystroke {
 
 #define HK_MAXIMUM_MESSAGE_SIZE 256
 
-#define KBD_VSC_SEND_RING_BUFFER_SIZE		(40 * 1024)
-#define KBD_VSC_RECV_RING_BUFFER_SIZE		(40 * 1024)
+#define KBD_VSC_SEND_RING_BUFFER_SIZE	VMBUS_RING_SIZE(36 * 1024)
+#define KBD_VSC_RECV_RING_BUFFER_SIZE	VMBUS_RING_SIZE(36 * 1024)
 
 #define XTKBD_EMUL0     0xe0
 #define XTKBD_EMUL1     0xe1

drivers/net/hyperv/netvsc.c

@@ -846,7 +846,7 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 	}
 
 	for (i = 0; i < page_count; i++) {
-		char *src = phys_to_virt(pb[i].pfn << PAGE_SHIFT);
+		char *src = phys_to_virt(pb[i].pfn << HV_HYP_PAGE_SHIFT);
 		u32 offset = pb[i].offset;
 		u32 len = pb[i].len;
 

drivers/net/hyperv/netvsc_drv.c

@@ -373,32 +373,29 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	return txq;
 }
 
-static u32 fill_pg_buf(struct page *page, u32 offset, u32 len,
+static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len,
 		       struct hv_page_buffer *pb)
 {
 	int j = 0;
 
-	/* Deal with compound pages by ignoring unused part
-	 * of the page.
-	 */
-	page += (offset >> PAGE_SHIFT);
-	offset &= ~PAGE_MASK;
+	hvpfn += offset >> HV_HYP_PAGE_SHIFT;
+	offset = offset & ~HV_HYP_PAGE_MASK;
 
 	while (len > 0) {
 		unsigned long bytes;
 
-		bytes = PAGE_SIZE - offset;
+		bytes = HV_HYP_PAGE_SIZE - offset;
 		if (bytes > len)
 			bytes = len;
-		pb[j].pfn = page_to_pfn(page);
+		pb[j].pfn = hvpfn;
 		pb[j].offset = offset;
 		pb[j].len = bytes;
 
 		offset += bytes;
 		len -= bytes;
 
-		if (offset == PAGE_SIZE && len) {
-			page++;
+		if (offset == HV_HYP_PAGE_SIZE && len) {
+			hvpfn++;
 			offset = 0;
 			j++;
 		}
@@ -421,23 +418,26 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 	 * 2. skb linear data
 	 * 3. skb fragment data
 	 */
-	slots_used += fill_pg_buf(virt_to_page(hdr),
-				  offset_in_page(hdr),
-				  len, &pb[slots_used]);
+	slots_used += fill_pg_buf(virt_to_hvpfn(hdr),
+				  offset_in_hvpage(hdr),
+				  len,
+				  &pb[slots_used]);
 
 	packet->rmsg_size = len;
 	packet->rmsg_pgcnt = slots_used;
 
-	slots_used += fill_pg_buf(virt_to_page(data),
-				offset_in_page(data),
-				skb_headlen(skb), &pb[slots_used]);
+	slots_used += fill_pg_buf(virt_to_hvpfn(data),
+				  offset_in_hvpage(data),
+				  skb_headlen(skb),
+				  &pb[slots_used]);
 
 	for (i = 0; i < frags; i++) {
 		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
 
-		slots_used += fill_pg_buf(skb_frag_page(frag),
-					skb_frag_off(frag),
-					skb_frag_size(frag), &pb[slots_used]);
+		slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)),
+					  skb_frag_off(frag),
+					  skb_frag_size(frag),
+					  &pb[slots_used]);
 	}
 	return slots_used;
 }
@@ -453,8 +453,8 @@ static int count_skb_frag_slots(struct sk_buff *skb)
 		unsigned long offset = skb_frag_off(frag);
 
 		/* Skip unused frames from start of page */
-		offset &= ~PAGE_MASK;
-		pages += PFN_UP(offset + size);
+		offset &= ~HV_HYP_PAGE_MASK;
+		pages += HVPFN_UP(offset + size);
 	}
 	return pages;
 }
@@ -462,12 +462,12 @@ static int count_skb_frag_slots(struct sk_buff *skb)
 static int netvsc_get_slots(struct sk_buff *skb)
 {
 	char *data = skb->data;
-	unsigned int offset = offset_in_page(data);
+	unsigned int offset = offset_in_hvpage(data);
 	unsigned int len = skb_headlen(skb);
 	int slots;
 	int frag_slots;
 
-	slots = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+	slots = DIV_ROUND_UP(offset + len, HV_HYP_PAGE_SIZE);
 	frag_slots = count_skb_frag_slots(skb);
 	return slots + frag_slots;
 }

drivers/net/hyperv/rndis_filter.c

@@ -25,7 +25,7 @@
 
 static void rndis_set_multicast(struct work_struct *w);
 
-#define RNDIS_EXT_LEN PAGE_SIZE
+#define RNDIS_EXT_LEN HV_HYP_PAGE_SIZE
 struct rndis_request {
 	struct list_head list_ent;
 	struct completion  wait_event;
@@ -215,18 +215,17 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 	packet->page_buf_cnt = 1;
 
 	pb[0].pfn = virt_to_phys(&req->request_msg) >>
-					PAGE_SHIFT;
+					HV_HYP_PAGE_SHIFT;
 	pb[0].len = req->request_msg.msg_len;
-	pb[0].offset =
-		(unsigned long)&req->request_msg & (PAGE_SIZE - 1);
+	pb[0].offset = offset_in_hvpage(&req->request_msg);
 
 	/* Add one page_buf when request_msg crossing page boundary */
-	if (pb[0].offset + pb[0].len > PAGE_SIZE) {
+	if (pb[0].offset + pb[0].len > HV_HYP_PAGE_SIZE) {
 		packet->page_buf_cnt++;
-		pb[0].len = PAGE_SIZE -
+		pb[0].len = HV_HYP_PAGE_SIZE -
 			pb[0].offset;
 		pb[1].pfn = virt_to_phys((void *)&req->request_msg
-			+ pb[0].len) >> PAGE_SHIFT;
+			+ pb[0].len) >> HV_HYP_PAGE_SHIFT;
 		pb[1].offset = 0;
 		pb[1].len = req->request_msg.msg_len -
 			pb[0].len;

drivers/pci/controller/pci-hyperv.c

@@ -2507,7 +2507,10 @@ static void hv_pci_onchannelcallback(void *context)
 
 /**
  * hv_pci_protocol_negotiation() - Set up protocol
- * @hdev:	VMBus's tracking struct for this root PCI bus
+ * @hdev:		VMBus's tracking struct for this root PCI bus.
+ * @version:		Array of supported channel protocol versions in
+ *			the order of probing - highest go first.
+ * @num_version:	Number of elements in the version array.
  *
  * This driver is intended to support running on Windows 10
  * (server) and later versions. It will not run on earlier

drivers/scsi/storvsc_drv.c

@@ -1739,23 +1739,65 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	payload_sz = sizeof(cmd_request->mpb);
 
 	if (sg_count) {
-		if (sg_count > MAX_PAGE_BUFFER_COUNT) {
+		unsigned int hvpgoff = 0;
+		unsigned long offset_in_hvpg = sgl->offset & ~HV_HYP_PAGE_MASK;
+		unsigned int hvpg_count = HVPFN_UP(offset_in_hvpg + length);
+		u64 hvpfn;
 
-			payload_sz = (sg_count * sizeof(u64) +
+		if (hvpg_count > MAX_PAGE_BUFFER_COUNT) {
+
+			payload_sz = (hvpg_count * sizeof(u64) +
 				      sizeof(struct vmbus_packet_mpb_array));
 			payload = kzalloc(payload_sz, GFP_ATOMIC);
 			if (!payload)
 				return SCSI_MLQUEUE_DEVICE_BUSY;
 		}
 
+		/*
+		 * sgl is a list of PAGEs, and payload->range.pfn_array
+		 * expects the page number in the unit of HV_HYP_PAGE_SIZE (the
+		 * page size that Hyper-V uses, so here we need to divide PAGEs
+		 * into HV_HYP_PAGE in case that PAGE_SIZE > HV_HYP_PAGE_SIZE.
+		 * Besides, payload->range.offset should be the offset in one
+		 * HV_HYP_PAGE.
+		 */
 		payload->range.len = length;
-		payload->range.offset = sgl[0].offset;
+		payload->range.offset = offset_in_hvpg;
+		hvpgoff = sgl->offset >> HV_HYP_PAGE_SHIFT;
 
 		cur_sgl = sgl;
-		for (i = 0; i < sg_count; i++) {
-			payload->range.pfn_array[i] =
-				page_to_pfn(sg_page((cur_sgl)));
-			cur_sgl = sg_next(cur_sgl);
+		for (i = 0; i < hvpg_count; i++) {
+			/*
+			 * 'i' is the index of hv pages in the payload and
+			 * 'hvpgoff' is the offset (in hv pages) of the first
+			 * hv page in the the first page. The relationship
+			 * between the sum of 'i' and 'hvpgoff' and the offset
+			 * (in hv pages) in a payload page ('hvpgoff_in_page')
+			 * is as follow:
+			 *
+			 * |------------------ PAGE -------------------|
+			 * |   NR_HV_HYP_PAGES_IN_PAGE hvpgs in total  |
+			 * |hvpg|hvpg| ...              |hvpg|... |hvpg|
+			 * ^         ^                                 ^                 ^
+			 * +-hvpgoff-+                                 +-hvpgoff_in_page-+
+			 *           ^                                                   |
+			 *           +--------------------- i ---------------------------+
+			 */
+			unsigned int hvpgoff_in_page =
+				(i + hvpgoff) % NR_HV_HYP_PAGES_IN_PAGE;
+
+			/*
+			 * Two cases that we need to fetch a page:
+			 * 1) i == 0, the first step or
+			 * 2) hvpgoff_in_page == 0, when we reach the boundary
+			 *    of a page.
+			 */
+			if (hvpgoff_in_page == 0 || i == 0) {
+				hvpfn = page_to_hvpfn(sg_page(cur_sgl));
+				cur_sgl = sg_next(cur_sgl);
+			}
+
+			payload->range.pfn_array[i] = hvpfn + hvpgoff_in_page;
 		}
 	}
 

include/linux/hyperv.h

@@ -14,6 +14,7 @@
 
 #include <uapi/linux/hyperv.h>
 
+#include <linux/mm.h>
 #include <linux/types.h>
 #include <linux/scatterlist.h>
 #include <linux/list.h>
@@ -23,12 +24,55 @@
 #include <linux/mod_devicetable.h>
 #include <linux/interrupt.h>
 #include <linux/reciprocal_div.h>
+#include <asm/hyperv-tlfs.h>
 
 #define MAX_PAGE_BUFFER_COUNT				32
 #define MAX_MULTIPAGE_BUFFER_COUNT			32 /* 128K */
 
 #pragma pack(push, 1)
 
+/*
+ * Types for GPADL, decides is how GPADL header is created.
+ *
+ * It doesn't make much difference between BUFFER and RING if PAGE_SIZE is the
+ * same as HV_HYP_PAGE_SIZE.
+ *
+ * If PAGE_SIZE is bigger than HV_HYP_PAGE_SIZE, the headers of ring buffers
+ * will be of PAGE_SIZE, however, only the first HV_HYP_PAGE will be put
+ * into gpadl, therefore the number for HV_HYP_PAGE and the indexes of each
+ * HV_HYP_PAGE will be different between different types of GPADL, for example
+ * if PAGE_SIZE is 64K:
+ *
+ * BUFFER:
+ *
+ * gva:    |--       64k      --|--       64k      --| ... |
+ * gpa:    | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k |
+ * index:  0    1    2     15   16   17   18 .. 31   32 ...
+ *         |    |    ...   |    |    |   ...    |   ...
+ *         v    V          V    V    V          V
+ * gpadl:  | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k | ... |
+ * index:  0    1    2 ... 15   16   17   18 .. 31   32 ...
+ *
+ * RING:
+ *
+ *         | header  |           data           | header  |     data      |
+ * gva:    |-- 64k --|--       64k      --| ... |-- 64k --|-- 64k --| ... |
+ * gpa:    | 4k | .. | 4k | 4k | ... | 4k | ... | 4k | .. | 4k | .. | ... |
+ * index:  0    1    16   17   18    31   ...   n   n+1  n+16 ...         2n
+ *         |         /    /          /          |         /               /
+ *         |        /    /          /           |        /               /
+ *         |       /    /   ...    /    ...     |       /      ...      /
+ *         |      /    /          /             |      /               /
+ *         |     /    /          /              |     /               /
+ *         V    V    V          V               V    V               v
+ * gpadl:  | 4k | 4k |   ...    |    ...        | 4k | 4k |  ...     |
+ * index:  0    1    2   ...    16   ...       n-15 n-14 n-13  ...  2n-30
+ */
+enum hv_gpadl_type {
+	HV_GPADL_BUFFER,
+	HV_GPADL_RING
+};
+
 /* Single-page buffer */
 struct hv_page_buffer {
 	u32 len;
@@ -111,7 +155,7 @@ struct hv_ring_buffer {
 	} feature_bits;
 
 	/* Pad it to PAGE_SIZE so that data starts on page boundary */
-	u8	reserved2[4028];
+	u8	reserved2[PAGE_SIZE - 68];
 
 	/*
 	 * Ring data starts here + RingDataStartOffset
@@ -120,6 +164,10 @@ struct hv_ring_buffer {
 	u8 buffer[];
 } __packed;
 
+/* Calculate the proper size of a ringbuffer, it must be page-aligned */
+#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \
+					       (payload_sz))
+
 struct hv_ring_buffer_info {
 	struct hv_ring_buffer *ring_buffer;
 	u32 ring_size;			/* Include the shared header */
@@ -1630,4 +1678,22 @@ struct hyperv_pci_block_ops {
 
 extern struct hyperv_pci_block_ops hvpci_block_ops;
 
+static inline unsigned long virt_to_hvpfn(void *addr)
+{
+	phys_addr_t paddr;
+
+	if (is_vmalloc_addr(addr))
+		paddr = page_to_phys(vmalloc_to_page(addr)) +
+				     offset_in_page(addr);
+	else
+		paddr = __pa(addr);
+
+	return  paddr >> HV_HYP_PAGE_SHIFT;
+}
+
+#define NR_HV_HYP_PAGES_IN_PAGE	(PAGE_SIZE / HV_HYP_PAGE_SIZE)
+#define offset_in_hvpage(ptr)	((unsigned long)(ptr) & ~HV_HYP_PAGE_MASK)
+#define HVPFN_UP(x)	(((x) + HV_HYP_PAGE_SIZE-1) >> HV_HYP_PAGE_SHIFT)
+#define page_to_hvpfn(page)	(page_to_pfn(page) * NR_HV_HYP_PAGES_IN_PAGE)
+
 #endif /* _HYPERV_H */