diff mbox series

[13/13] HV/Storvsc: Add Isolation VM support for storvsc driver

Message ID 20210728145232.285861-14-ltykernel@gmail.com (mailing list archive)
State Superseded
Headers show
Series x86/Hyper-V: Add Hyper-V Isolation VM support | expand

Checks

Context Check Description
netdev/tree_selection success Guessing tree name failed - patch did not apply

Commit Message

Tianyu Lan July 28, 2021, 2:52 p.m. UTC 
From: Tianyu Lan <Tianyu.Lan@microsoft.com>

In Isolation VM, all shared memory with host needs to mark visible
to host via hvcall. vmbus_establish_gpadl() has already done it for
storvsc rx/tx ring buffer. The page buffer used by vmbus_sendpacket_
mpb_desc() still need to handle. Use DMA API to map/umap these
memory during sending/receiving packet and Hyper-V DMA ops callback
will use swiotlb function to allocate bounce buffer and copy data
from/to bounce buffer.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 drivers/scsi/storvsc_drv.c | 68 +++++++++++++++++++++++++++++++++++---
 1 file changed, 63 insertions(+), 5 deletions(-)

Comments

Joerg Roedel Aug. 2, 2021, 1:20 p.m. UTC | #1 
On Wed, Jul 28, 2021 at 10:52:28AM -0400, Tianyu Lan wrote:
> In Isolation VM, all shared memory with host needs to mark visible
> to host via hvcall. vmbus_establish_gpadl() has already done it for
> storvsc rx/tx ring buffer. The page buffer used by vmbus_sendpacket_
> mpb_desc() still need to handle. Use DMA API to map/umap these
> memory during sending/receiving packet and Hyper-V DMA ops callback
> will use swiotlb function to allocate bounce buffer and copy data
> from/to bounce buffer.

I am wondering why you dont't use DMA-API unconditionally? It provides
enough abstraction to do the right thing for isolated and legacy VMs.

Regards,

	Joerg
Tianyu Lan Aug. 2, 2021, 2:08 p.m. UTC | #2 
On 8/2/2021 9:20 PM, Joerg Roedel wrote:
> On Wed, Jul 28, 2021 at 10:52:28AM -0400, Tianyu Lan wrote:
>> In Isolation VM, all shared memory with host needs to mark visible
>> to host via hvcall. vmbus_establish_gpadl() has already done it for
>> storvsc rx/tx ring buffer. The page buffer used by vmbus_sendpacket_
>> mpb_desc() still need to handle. Use DMA API to map/umap these
>> memory during sending/receiving packet and Hyper-V DMA ops callback
>> will use swiotlb function to allocate bounce buffer and copy data
>> from/to bounce buffer.
> 
> I am wondering why you dont't use DMA-API unconditionally? It provides
> enough abstraction to do the right thing for isolated and legacy VMs.
> 

In VMbus, there is already a similar bounce buffer design and so there 
is no need to call DMA-API for such buffer. Calling DMA-API is to use
swiotlb bounce buffer for those buffer which hasn't been covered. This
is why need to conditionally call DMA API.
diff mbox series

Patch

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 328bb961c281..78320719bdd8 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/io.h>
+#include <linux/dma-mapping.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_host.h>
@@ -427,6 +429,8 @@  struct storvsc_cmd_request {
 	u32 payload_sz;
 
 	struct vstor_packet vstor_packet;
+	u32 hvpg_count;
+	struct hv_dma_range *dma_range;
 };
 
 
@@ -509,6 +513,14 @@  struct storvsc_scan_work {
 	u8 tgt_id;
 };
 
+#define storvsc_dma_map(dev, page, offset, size, dir) \
+	dma_map_page(dev, page, offset, size, dir)
+
+#define storvsc_dma_unmap(dev, dma_range, dir)		\
+		dma_unmap_page(dev, dma_range.dma,	\
+			       dma_range.mapping_size,	\
+			       dir ? DMA_FROM_DEVICE : DMA_TO_DEVICE)
+
 static void storvsc_device_scan(struct work_struct *work)
 {
 	struct storvsc_scan_work *wrk;
@@ -1260,6 +1272,7 @@  static void storvsc_on_channel_callback(void *context)
 	struct hv_device *device;
 	struct storvsc_device *stor_device;
 	struct Scsi_Host *shost;
+	int i;
 
 	if (channel->primary_channel != NULL)
 		device = channel->primary_channel->device_obj;
@@ -1314,6 +1327,15 @@  static void storvsc_on_channel_callback(void *context)
 				request = (struct storvsc_cmd_request *)scsi_cmd_priv(scmnd);
 			}
 
+			if (request->dma_range) {
+				for (i = 0; i < request->hvpg_count; i++)
+					storvsc_dma_unmap(&device->device,
+						request->dma_range[i],
+						request->vstor_packet.vm_srb.data_in == READ_TYPE);
+
+				kfree(request->dma_range);
+			}
+
 			storvsc_on_receive(stor_device, packet, request);
 			continue;
 		}
@@ -1810,7 +1832,9 @@  static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *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);
+		dma_addr_t dma;
 		u64 hvpfn;
+		u32 size;
 
 		if (hvpg_count > MAX_PAGE_BUFFER_COUNT) {
 
@@ -1824,6 +1848,13 @@  static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 		payload->range.len = length;
 		payload->range.offset = offset_in_hvpg;
 
+		cmd_request->dma_range = kcalloc(hvpg_count,
+				 sizeof(*cmd_request->dma_range),
+				 GFP_ATOMIC);
+		if (!cmd_request->dma_range) {
+			ret = -ENOMEM;
+			goto free_payload;
+		}
 
 		for (i = 0; sgl != NULL; sgl = sg_next(sgl)) {
 			/*
@@ -1847,9 +1878,29 @@  static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 			 * last sgl should be reached at the same time that
 			 * the PFN array is filled.
 			 */
-			while (hvpfns_to_add--)
-				payload->range.pfn_array[i++] =	hvpfn++;
+			while (hvpfns_to_add--) {
+				size = min(HV_HYP_PAGE_SIZE - offset_in_hvpg,
+					   (unsigned long)length);
+				dma = storvsc_dma_map(&dev->device, pfn_to_page(hvpfn++),
+						      offset_in_hvpg, size,
+						      scmnd->sc_data_direction);
+				if (dma_mapping_error(&dev->device, dma)) {
+					ret = -ENOMEM;
+					goto free_dma_range;
+				}
+
+				if (offset_in_hvpg) {
+					payload->range.offset = dma & ~HV_HYP_PAGE_MASK;
+					offset_in_hvpg = 0;
+				}
+
+				cmd_request->dma_range[i].dma = dma;
+				cmd_request->dma_range[i].mapping_size = size;
+				payload->range.pfn_array[i++] = dma >> HV_HYP_PAGE_SHIFT;
+				length -= size;
+			}
 		}
+		cmd_request->hvpg_count = hvpg_count;
 	}
 
 	cmd_request->payload = payload;
@@ -1860,13 +1911,20 @@  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 free_dma_range;
 	}
 
 	return 0;
+
+free_dma_range:
+	kfree(cmd_request->dma_range);
+
+free_payload:
+	if (payload_sz > sizeof(cmd_request->mpb))
+		kfree(payload);
+	return ret;
 }
 
 static struct scsi_host_template scsi_driver = {