Re: [PATCH RFC 12/12] vdpa_sim_blk: implement ramdisk behaviour

[Stefano Garzarella <sgarzare@redhat.com>]

On Mon, Nov 16, 2020 at 01:25:31PM +0800, Jason Wang wrote:
>
>On 2020/11/13 下午9:47, Stefano Garzarella wrote:
>>The previous implementation wrote only the status of each request.
>>This patch implements a more accurate block device simulator,
>>providing a ramdisk-like behavior.
>>
>>Also handle VIRTIO_BLK_T_GET_ID request, always answering the
>>"vdpa_blk_sim" string.
>
>
>Let's use a separate patch for this.
>

Okay, I'll do.

>
>>
>>Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
>>---
>>  drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 151 +++++++++++++++++++++++----
>>  1 file changed, 133 insertions(+), 18 deletions(-)
>>
>>diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
>>index 8e41b3ab98d5..68e74383322f 100644
>>--- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
>>+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
>>@@ -7,6 +7,7 @@
>>   */
>>  #include <linux/module.h>
>>+#include <linux/blkdev.h>
>>  #include <uapi/linux/virtio_blk.h>
>>  #include "vdpa_sim.h"
>>@@ -24,10 +25,137 @@
>>  static struct vdpasim *vdpasim_blk_dev;
>>+static int vdpasim_blk_handle_req(struct vdpasim *vdpasim,
>>+				  struct vdpasim_virtqueue *vq)
>>+{
>>+	size_t wrote = 0, to_read = 0, to_write = 0;
>>+	struct virtio_blk_outhdr hdr;
>>+	uint8_t status;
>>+	uint32_t type;
>>+	ssize_t bytes;
>>+	loff_t offset;
>>+	int i, ret;
>>+
>>+	vringh_kiov_cleanup(&vq->riov);
>>+	vringh_kiov_cleanup(&vq->wiov);
>
>
>It looks to me we should do those after vringh_get_desc_iotlb()? See 
>comment above vringh_getdesc_kern().

Do you mean after the last vringh_iov_push_iotlb()?

Because vringh_kiov_cleanup() will free the allocated iov[].

>
>
>>+
>>+	ret = vringh_getdesc_iotlb(&vq->vring, &vq->riov, &vq->wiov,
>>+				   &vq->head, GFP_ATOMIC);
>>+	if (ret != 1)
>>+		return ret;
>>+
>>+	for (i = 0; i < vq->wiov.used; i++)
>>+		to_write += vq->wiov.iov[i].iov_len;
>
>
>It's better to introduce a helper for this (or consider to use iov 
>iterator).

Okay, I'll try to find the best solution.

>
>
>>+	to_write -= 1; /* last byte is the status */
>>+
>>+	for (i = 0; i < vq->riov.used; i++)
>>+		to_read += vq->riov.iov[i].iov_len;
>>+
>>+	bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->riov, &hdr, sizeof(hdr));
>>+	if (bytes != sizeof(hdr))
>>+		return 0;
>>+
>>+	to_read -= bytes;
>>+
>>+	type = le32_to_cpu(hdr.type);
>>+	offset = le64_to_cpu(hdr.sector) << SECTOR_SHIFT;
>>+	status = VIRTIO_BLK_S_OK;
>>+
>>+	switch (type) {
>>+	case VIRTIO_BLK_T_IN:
>>+		if (offset + to_write > VDPASIM_BLK_CAPACITY << 
>>SECTOR_SHIFT) {
>>+			dev_err(&vdpasim->vdpa.dev,
>>+				"reading over the capacity - offset: 
>>0x%llx len: 0x%lx\n",
>>+				offset, to_write);
>>+			status = VIRTIO_BLK_S_IOERR;
>>+			break;
>>+		}
>>+
>>+		bytes = vringh_iov_push_iotlb(&vq->vring, &vq->wiov,
>>+					      vdpasim->buffer + offset,
>>+					      to_write);
>>+		if (bytes < 0) {
>>+			dev_err(&vdpasim->vdpa.dev,
>>+				"vringh_iov_push_iotlb() error: %ld offset: 0x%llx len: 0x%lx\n",
>>+				bytes, offset, to_write);
>>+			status = VIRTIO_BLK_S_IOERR;
>>+			break;
>>+		}
>>+
>>+		wrote += bytes;
>>+		break;
>>+
>>+	case VIRTIO_BLK_T_OUT:
>>+		if (offset + to_read > VDPASIM_BLK_CAPACITY << SECTOR_SHIFT) {
>>+			dev_err(&vdpasim->vdpa.dev,
>>+				"writing over the capacity - offset: 0x%llx len: 0x%lx\n",
>>+				offset, to_read);
>>+			status = VIRTIO_BLK_S_IOERR;
>>+			break;
>>+		}
>>+
>>+		bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->riov,
>>+					      vdpasim->buffer + offset,
>>+					      to_read);
>>+		if (bytes < 0) {
>>+			dev_err(&vdpasim->vdpa.dev,
>>+				"vringh_iov_pull_iotlb() error: %ld offset: 0x%llx len: 0x%lx\n",
>>+				bytes, offset, to_read);
>>+			status = VIRTIO_BLK_S_IOERR;
>>+			break;
>>+		}
>>+		break;
>>+
>>+	case VIRTIO_BLK_T_GET_ID: {
>>+		char id[VIRTIO_BLK_ID_BYTES] = "vdpa_blk_sim";
>
>
>Let's use a global static one?

I'll do.

>
>
>>+
>>+		bytes = vringh_iov_push_iotlb(&vq->vring,
>>+					      &vq->wiov, id,
>>+					      VIRTIO_BLK_ID_BYTES);
>>+		if (bytes < 0) {
>>+			dev_err(&vdpasim->vdpa.dev,
>>+				"vringh_iov_push_iotlb() error: %ld\n", bytes);
>>+			status = VIRTIO_BLK_S_IOERR;
>>+			break;
>>+		}
>>+
>>+		wrote += bytes;
>>+		break;
>>+	}
>>+
>>+	default:
>>+		dev_warn(&vdpasim->vdpa.dev,
>>+			 "Unsupported request type %d\n", type);
>>+		status = VIRTIO_BLK_S_IOERR;
>>+		break;
>>+	}
>>+
>>+	/* if VIRTIO_BLK_T_IN or VIRTIO_BLK_T_GET_ID fail, we need to skip
>>+	 * the remaining bytes to put the status in the last byte
>>+	 */
>>+	if (to_write - wrote > 0) {
>>+		vringh_iov_push_iotlb(&vq->vring, &vq->wiov, NULL,
>>+				      to_write - wrote);
>>+	}
>>+
>>+	/* last byte is the status */
>>+	bytes = vringh_iov_push_iotlb(&vq->vring, &vq->wiov, &status, 1);
>>+	if (bytes != 1)
>>+		return 0;
>>+
>>+	wrote += bytes;
>>+
>>+	/* Make sure data is wrote before advancing index */
>>+	smp_wmb();
>>+
>>+	vringh_complete_iotlb(&vq->vring, vq->head, wrote);
>>+
>>+	return ret;
>>+}
>>+
>>  static void vdpasim_blk_work(struct work_struct *work)
>>  {
>>  	struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);
>>-	u8 status = VIRTIO_BLK_S_OK;
>>  	int i;
>>  	spin_lock(&vdpasim->lock);
>>@@ -41,21 +169,7 @@ static void vdpasim_blk_work(struct work_struct *work)
>>  		if (!vq->ready)
>>  			continue;
>>-		while (vringh_getdesc_iotlb(&vq->vring, &vq->riov, &vq->wiov,
>>-					    &vq->head, GFP_ATOMIC) > 0) {
>>-
>>-			int write;
>>-
>>-			vq->wiov.i = vq->wiov.used - 1;
>>-			write = vringh_iov_push_iotlb(&vq->vring, &vq->wiov, &status, 1);
>>-			if (write <= 0)
>>-				break;
>>-
>>-			/* Make sure data is wrote before advancing 
>>index */
>>-			smp_wmb();
>>-
>>-			vringh_complete_iotlb(&vq->vring, vq->head, write);
>>-
>>+		while (vdpasim_blk_handle_req(vdpasim, vq) > 0) {
>>  			/* Make sure used is visible before rasing the interrupt. */
>>  			smp_wmb();
>>@@ -67,6 +181,7 @@ static void vdpasim_blk_work(struct work_struct *work)
>>  				vq->cb(vq->private);
>>  			local_bh_enable();
>>  		}
>>+
>
>
>Unnecessary change.

Removed.

Thanks,
Stefano