Hi Fam,
On 9/25/20 5:44 PM, Fam Zheng wrote:
> On Fri, 2020-09-25 at 17:23 +0200, Auger Eric wrote:
@@ -365,8 +430,12 @@ static int qemu_vfio_init_pci(QEMUVFIOState
*s, const char *device,
if (ret) {
goto fail;
}
+g_free(iommu_info);
On Fri, 2020-09-25 at 17:23 +0200, Auger Eric wrote:
> > > @@ -365,8 +430,12 @@ static int qemu_vfio_init_pci(QEMUVFIOState
> > > *s, const char *device,
> > > if (ret) {
> > > goto fail;
> > > }
> > > +g_free(iommu_info);
> > > return 0;
> > > fail:
> > > +
Hi Fam,
On 9/25/20 4:43 PM, Fam Zheng wrote:
> On 2020-09-25 15:48, Eric Auger wrote:
>> The IOVA allocator currently ignores host reserved regions.
>> As a result some chosen IOVAs may collide with some of them,
>> resulting in VFIO MAP_DMA errors later on. This happens on ARM
>> where the MSI
On 2020-09-25 15:48, Eric Auger wrote:
> The IOVA allocator currently ignores host reserved regions.
> As a result some chosen IOVAs may collide with some of them,
> resulting in VFIO MAP_DMA errors later on. This happens on ARM
> where the MSI reserved window quickly is encountered:
> [0x800,
The IOVA allocator currently ignores host reserved regions.
As a result some chosen IOVAs may collide with some of them,
resulting in VFIO MAP_DMA errors later on. This happens on ARM
where the MSI reserved window quickly is encountered:
[0x800, 0x810]. since 5.4 kernel, VFIO returns the