search for: giova

On Fri, Dec 14, 2018 at 10:43:03AM +0800, Jason Wang wrote: > > On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: > > > Just to make sure I understand this. It looks to me we should: > > > > > > - allow passing GIOVA->GPA through UAPI > > > > > > - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for > > > performance > > > > > > Is this what you suggest? > > > > > > Thanks > > Not really. We already have GPA-&gt...

On Fri, Dec 14, 2018 at 10:43:03AM +0800, Jason Wang wrote: > > On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: > > > Just to make sure I understand this. It looks to me we should: > > > > > > - allow passing GIOVA->GPA through UAPI > > > > > > - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for > > > performance > > > > > > Is this what you suggest? > > > > > > Thanks > > Not really. We already have GPA-&gt...

...kin wrote: > > On Fri, Dec 14, 2018 at 10:43:03AM +0800, Jason Wang wrote: > > > On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: > > > > > Just to make sure I understand this. It looks to me we should: > > > > > > > > > > - allow passing GIOVA->GPA through UAPI > > > > > > > > > > - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for > > > > > performance > > > > > > > > > > Is this what you suggest? > > > > > > &g...

...kin wrote: > > On Fri, Dec 14, 2018 at 10:43:03AM +0800, Jason Wang wrote: > > > On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: > > > > > Just to make sure I understand this. It looks to me we should: > > > > > > > > > > - allow passing GIOVA->GPA through UAPI > > > > > > > > > > - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for > > > > > performance > > > > > > > > > > Is this what you suggest? > > > > > > &g...

On Thu, Dec 13, 2018 at 10:39:41AM +0800, Jason Wang wrote: > > On 2018/12/12 ??10:32, Michael S. Tsirkin wrote: > > On Wed, Dec 12, 2018 at 06:08:19PM +0800, Jason Wang wrote: > > > Vhost dirty page logging API is designed to sync through GPA. But we > > > try to log GIOVA when device IOTLB is enabled. This is wrong and may > > > lead to missing data after migration. > > > > > > To solve this issue, when logging with device IOTLB enabled, we will: > > > > > > 1) reuse the device IOTLB translation result of GIOVA->HVA...

On Thu, Dec 13, 2018 at 10:39:41AM +0800, Jason Wang wrote: > > On 2018/12/12 ??10:32, Michael S. Tsirkin wrote: > > On Wed, Dec 12, 2018 at 06:08:19PM +0800, Jason Wang wrote: > > > Vhost dirty page logging API is designed to sync through GPA. But we > > > try to log GIOVA when device IOTLB is enabled. This is wrong and may > > > lead to missing data after migration. > > > > > > To solve this issue, when logging with device IOTLB enabled, we will: > > > > > > 1) reuse the device IOTLB translation result of GIOVA->HVA...

...8 at 10:43:03AM +0800, Jason Wang wrote: > > > > > On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: > > > > > > > Just to make sure I understand this. It looks to me we should: > > > > > > > > > > > > > > - allow passing GIOVA->GPA through UAPI > > > > > > > > > > > > > > - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for > > > > > > > performance > > > > > > > > > > > > > > Is this w...

...8 at 10:43:03AM +0800, Jason Wang wrote: > > > > > On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: > > > > > > > Just to make sure I understand this. It looks to me we should: > > > > > > > > > > > > > > - allow passing GIOVA->GPA through UAPI > > > > > > > > > > > > > > - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for > > > > > > > performance > > > > > > > > > > > > > > Is this w...

...> > > > > > > On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: > > > > > > > > > Just to make sure I understand this. It looks to me we should: > > > > > > > > > > > > > > > > > > - allow passing GIOVA->GPA through UAPI > > > > > > > > > > > > > > > > > > - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for > > > > > > > > > performance > > > > > > > > > >...

...vring addresses provided by > userspace when using an IOTLB device. The misuse cause failures of > the VHOST_SET_VRING_ADDR ioctl on POWER, which in turn causes QEMU > to crash at migration time. > > While digging some more I realized that log_access_ok() can also be > passed a GIOVA (vq->log_addr) even though log_used() will never log > anything at that address. I could observe addresses beyond the end > of the log bitmap being passed to access_ok(), but it didn't have any > impact because the addresses were still acceptable from an access_ok() > standpoint....

...wrote: >>> On Fri, Dec 14, 2018 at 10:43:03AM +0800, Jason Wang wrote: >>>> On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: >>>>>> Just to make sure I understand this. It looks to me we should: >>>>>> >>>>>> - allow passing GIOVA->GPA through UAPI >>>>>> >>>>>> - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for >>>>>> performance >>>>>> >>>>>> Is this what you suggest? >>>>>> >>&g...

On Wed, Dec 12, 2018 at 06:08:19PM +0800, Jason Wang wrote: > Vhost dirty page logging API is designed to sync through GPA. But we > try to log GIOVA when device IOTLB is enabled. This is wrong and may > lead to missing data after migration. > > To solve this issue, when logging with device IOTLB enabled, we will: > > 1) reuse the device IOTLB translation result of GIOVA->HVA mapping to > get HVA, for writable descripto...

On Wed, Dec 12, 2018 at 06:08:19PM +0800, Jason Wang wrote: > Vhost dirty page logging API is designed to sync through GPA. But we > try to log GIOVA when device IOTLB is enabled. This is wrong and may > lead to missing data after migration. > > To solve this issue, when logging with device IOTLB enabled, we will: > > 1) reuse the device IOTLB translation result of GIOVA->HVA mapping to > get HVA, for writable descripto...

...14, 2018 at 10:43:03AM +0800, Jason Wang wrote: >>>>>> On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: >>>>>>>> Just to make sure I understand this. It looks to me we should: >>>>>>>> >>>>>>>> - allow passing GIOVA->GPA through UAPI >>>>>>>> >>>>>>>> - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for >>>>>>>> performance >>>>>>>> >>>>>>>> Is this what you sugg...

On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: >> Just to make sure I understand this. It looks to me we should: >> >> - allow passing GIOVA->GPA through UAPI >> >> - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for >> performance >> >> Is this what you suggest? >> >> Thanks > Not really. We already have GPA->HVA, so I suggested a flag to pass > GIOVA-&gt...

...n 2018/12/14 ??9:20, Michael S. Tsirkin wrote: > On Fri, Dec 14, 2018 at 10:43:03AM +0800, Jason Wang wrote: >> On 2018/12/13 ??10:31, Michael S. Tsirkin wrote: >>>> Just to make sure I understand this. It looks to me we should: >>>> >>>> - allow passing GIOVA->GPA through UAPI >>>> >>>> - cache GIOVA->GPA somewhere but still use GIOVA->HVA in device IOTLB for >>>> performance >>>> >>>> Is this what you suggest? >>>> >>>> Thanks >>> Not really. We alread...

On 2018/12/12 ??10:32, Michael S. Tsirkin wrote: > On Wed, Dec 12, 2018 at 06:08:19PM +0800, Jason Wang wrote: >> Vhost dirty page logging API is designed to sync through GPA. But we >> try to log GIOVA when device IOTLB is enabled. This is wrong and may >> lead to missing data after migration. >> >> To solve this issue, when logging with device IOTLB enabled, we will: >> >> 1) reuse the device IOTLB translation result of GIOVA->HVA mapping to >> get HVA,...

...write barrier between used idx updating and logging. - Patch 2-3 brings back the protection of device IOTLB through vq mutex, this fixes possible use after free in device IOTLB entries. - Patch 4-7 fixes the diry page logging when device IOTLB is enabled. We should done through GPA instead of GIOVA, this was done through intorudce HVA->GPA reverse mapping and convert HVA to GPA during logging dirty pages. Please consider them for -stable. Thanks Changes from V1: - silent compiler warning for 32bit. - use mutex_trylock() on slowpath instead of mutex_lock() even on fast path. Jason...

...write barrier between used idx updating and logging. - Patch 2-3 brings back the protection of device IOTLB through vq mutex, this fixes possible use after free in device IOTLB entries. - Patch 4-7 fixes the diry page logging when device IOTLB is enabled. We should done through GPA instead of GIOVA, this was done through intorudce HVA->GPA reverse mapping and convert HVA to GPA during logging dirty pages. Please consider them for -stable. Thanks Changes from V1: - silent compiler warning for 32bit. - use mutex_trylock() on slowpath instead of mutex_lock() even on fast path. Jason...

Vhost dirty page logging API is designed to sync through GPA. But we try to log GIOVA when device IOTLB is enabled. This is wrong and may lead to missing data after migration. To solve this issue, when logging with device IOTLB enabled, we will: 1) reuse the device IOTLB translation result of GIOVA->HVA mapping to get HVA, for writable descriptor, get HVA through iovec. For...