Current code is based on the idea that the max number of SGL entries
also determines the max size of an I/O request. While this idea was
true in older versions of the storvsc driver when SGL entry length
was limited to 4 Kbytes, commit 3d9c3dcc58e9 ("scsi: storvsc: Enable
scatterlist entry lengths > 4Kbytes") removed that limitation. It's
now theoretically possible for the block layer to send requests that
exceed the maximum size supported by Hyper-V. This problem doesn't
currently happen in practice because the block layer defaults to a
512 Kbyte maximum, while Hyper-V in Azure supports 2 Mbyte I/O sizes.
But some future configuration of Hyper-V could have a smaller max I/O
size, and the block layer could exceed that max.
Fix this by correctly setting max_sectors as well as sg_tablesize to
reflect the maximum I/O size that Hyper-V reports. While allowing
I/O sizes larger than the block layer default of 512 Kbytes doesn’t
provide any noticeable performance benefit in the tests we ran, it's
still appropriate to report the correct underlying Hyper-V capabilities
to the Linux block layer.
Also tweak the virt_boundary_mask to reflect that the required
alignment derives from Hyper-V communication using a 4 Kbyte page size,
and not on the guest page size, which might be bigger (eg. ARM64).
Fixes: 3d9c3dcc58e9 ("scsi: storvsc: Enable scatter list entry lengths > 4Kbytes")
Signed-off-by: Saurabh Sengar <[email protected]>
---
V3
- Remove single quotes around the 'Fixes' tag
- max_tx_bytes -> max_xfer_bytes
- Added empty line at start of comment
drivers/scsi/storvsc_drv.c | 27 ++++++++++++++++++++++-----
1 file changed, 22 insertions(+), 5 deletions(-)
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index ca35309..fe000da 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1844,7 +1844,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
.cmd_per_lun = 2048,
.this_id = -1,
/* Ensure there are no gaps in presented sgls */
- .virt_boundary_mask = PAGE_SIZE-1,
+ .virt_boundary_mask = HV_HYP_PAGE_SIZE - 1,
.no_write_same = 1,
.track_queue_depth = 1,
.change_queue_depth = storvsc_change_queue_depth,
@@ -1895,6 +1895,7 @@ static int storvsc_probe(struct hv_device *device,
int target = 0;
struct storvsc_device *stor_device;
int max_sub_channels = 0;
+ u32 max_xfer_bytes;
/*
* We support sub-channels for storage on SCSI and FC controllers.
@@ -1968,12 +1969,28 @@ static int storvsc_probe(struct hv_device *device,
}
/* max cmd length */
host->max_cmd_len = STORVSC_MAX_CMD_LEN;
-
/*
- * set the table size based on the info we got
- * from the host.
+ * Any reasonable Hyper-V configuration should provide
+ * max_transfer_bytes value aligning to HV_HYP_PAGE_SIZE,
+ * protecting it from any weird value.
+ */
+ max_xfer_bytes = round_down(stor_device->max_transfer_bytes, HV_HYP_PAGE_SIZE);
+ /* max_hw_sectors_kb */
+ host->max_sectors = max_xfer_bytes >> 9;
+ /*
+ * There are 2 requirements for Hyper-V storvsc sgl segments,
+ * based on which the below calculation for max segments is
+ * done:
+ *
+ * 1. Except for the first and last sgl segment, all sgl segments
+ * should be align to HV_HYP_PAGE_SIZE, that also means the
+ * maximum number of segments in a sgl can be calculated by
+ * dividing the total max transfer length by HV_HYP_PAGE_SIZE.
+ *
+ * 2. Except for the first and last, each entry in the SGL must
+ * have an offset that is a multiple of HV_HYP_PAGE_SIZE.
*/
- host->sg_tablesize = (stor_device->max_transfer_bytes >> PAGE_SHIFT);
+ host->sg_tablesize = (max_xfer_bytes >> HV_HYP_PAGE_SHIFT) + 1;
/*
* For non-IDE disks, the host supports multiple channels.
* Set the number of HW queues we are supporting.
--
1.8.3.1
From: Saurabh Sengar <[email protected]> Sent: Tuesday, June 14, 2022 12:06 AM
>
> Current code is based on the idea that the max number of SGL entries
> also determines the max size of an I/O request. While this idea was
> true in older versions of the storvsc driver when SGL entry length
> was limited to 4 Kbytes, commit 3d9c3dcc58e9 ("scsi: storvsc: Enable
> scatterlist entry lengths > 4Kbytes") removed that limitation. It's
> now theoretically possible for the block layer to send requests that
> exceed the maximum size supported by Hyper-V. This problem doesn't
> currently happen in practice because the block layer defaults to a
> 512 Kbyte maximum, while Hyper-V in Azure supports 2 Mbyte I/O sizes.
> But some future configuration of Hyper-V could have a smaller max I/O
> size, and the block layer could exceed that max.
>
> Fix this by correctly setting max_sectors as well as sg_tablesize to
> reflect the maximum I/O size that Hyper-V reports. While allowing
> I/O sizes larger than the block layer default of 512 Kbytes doesn’t
> provide any noticeable performance benefit in the tests we ran, it's
> still appropriate to report the correct underlying Hyper-V capabilities
> to the Linux block layer.
>
> Also tweak the virt_boundary_mask to reflect that the required
> alignment derives from Hyper-V communication using a 4 Kbyte page size,
> and not on the guest page size, which might be bigger (eg. ARM64).
>
> Fixes: 3d9c3dcc58e9 ("scsi: storvsc: Enable scatter list entry lengths > 4Kbytes")
> Signed-off-by: Saurabh Sengar <[email protected]>
> ---
> V3
> - Remove single quotes around the 'Fixes' tag
> - max_tx_bytes -> max_xfer_bytes
> - Added empty line at start of comment
>
> drivers/scsi/storvsc_drv.c | 27 ++++++++++++++++++++++-----
> 1 file changed, 22 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
> index ca35309..fe000da 100644
> --- a/drivers/scsi/storvsc_drv.c
> +++ b/drivers/scsi/storvsc_drv.c
> @@ -1844,7 +1844,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host,
> struct scsi_cmnd *scmnd)
> .cmd_per_lun = 2048,
> .this_id = -1,
> /* Ensure there are no gaps in presented sgls */
> - .virt_boundary_mask = PAGE_SIZE-1,
> + .virt_boundary_mask = HV_HYP_PAGE_SIZE - 1,
> .no_write_same = 1,
> .track_queue_depth = 1,
> .change_queue_depth = storvsc_change_queue_depth,
> @@ -1895,6 +1895,7 @@ static int storvsc_probe(struct hv_device *device,
> int target = 0;
> struct storvsc_device *stor_device;
> int max_sub_channels = 0;
> + u32 max_xfer_bytes;
>
> /*
> * We support sub-channels for storage on SCSI and FC controllers.
> @@ -1968,12 +1969,28 @@ static int storvsc_probe(struct hv_device *device,
> }
> /* max cmd length */
> host->max_cmd_len = STORVSC_MAX_CMD_LEN;
> -
> /*
> - * set the table size based on the info we got
> - * from the host.
> + * Any reasonable Hyper-V configuration should provide
> + * max_transfer_bytes value aligning to HV_HYP_PAGE_SIZE,
> + * protecting it from any weird value.
> + */
> + max_xfer_bytes = round_down(stor_device->max_transfer_bytes, HV_HYP_PAGE_SIZE);
> + /* max_hw_sectors_kb */
> + host->max_sectors = max_xfer_bytes >> 9;
> + /*
> + * There are 2 requirements for Hyper-V storvsc sgl segments,
> + * based on which the below calculation for max segments is
> + * done:
> + *
> + * 1. Except for the first and last sgl segment, all sgl segments
> + * should be align to HV_HYP_PAGE_SIZE, that also means the
> + * maximum number of segments in a sgl can be calculated by
> + * dividing the total max transfer length by HV_HYP_PAGE_SIZE.
> + *
> + * 2. Except for the first and last, each entry in the SGL must
> + * have an offset that is a multiple of HV_HYP_PAGE_SIZE.
> */
> - host->sg_tablesize = (stor_device->max_transfer_bytes >> PAGE_SHIFT);
> + host->sg_tablesize = (max_xfer_bytes >> HV_HYP_PAGE_SHIFT) + 1;
> /*
> * For non-IDE disks, the host supports multiple channels.
> * Set the number of HW queues we are supporting.
> --
> 1.8.3.1
Reviewed-by: Michael Kelley <[email protected]>
On Tue, 14 Jun 2022 00:05:55 -0700, Saurabh Sengar wrote:
> Current code is based on the idea that the max number of SGL entries
> also determines the max size of an I/O request. While this idea was
> true in older versions of the storvsc driver when SGL entry length
> was limited to 4 Kbytes, commit 3d9c3dcc58e9 ("scsi: storvsc: Enable
> scatterlist entry lengths > 4Kbytes") removed that limitation. It's
> now theoretically possible for the block layer to send requests that
> exceed the maximum size supported by Hyper-V. This problem doesn't
> currently happen in practice because the block layer defaults to a
> 512 Kbyte maximum, while Hyper-V in Azure supports 2 Mbyte I/O sizes.
> But some future configuration of Hyper-V could have a smaller max I/O
> size, and the block layer could exceed that max.
>
> [...]
Applied to 5.19/scsi-fixes, thanks!
[1/1] scsi: storvsc: Correct reporting of Hyper-V I/O size limits
https://git.kernel.org/mkp/scsi/c/1d3e0980782f
--
Martin K. Petersen Oracle Linux Engineering