On Fri, 13 Sep 2019 11:32:09 +0200
>
> err = ttm_mem_io_lock(man, true);
> - if (unlikely(err != 0)) {
> - ret = VM_FAULT_NOPAGE;
> - goto out_unlock;
> - }
> + if (unlikely(err != 0))
> + return VM_FAULT_NOPAGE;
> err = ttm_mem_io_reser
On 9/13/19 3:40 PM, Hillf Danton wrote:
On Fri, 13 Sep 2019 11:32:09 +0200
err = ttm_mem_io_lock(man, true);
- if (unlikely(err != 0)) {
- ret = VM_FAULT_NOPAGE;
- goto out_unlock;
- }
+ if (unlikely(err != 0))
+ return VM_FAULT
On 9/13/19 5:18 PM, Matthew Wilcox wrote:
On Fri, Sep 13, 2019 at 11:32:09AM +0200, Thomas Hellström (VMware) wrote:
+vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
+ pgprot_t prot,
+ pgoff_t num_prefault)
+{
+
On Fri, Sep 13, 2019 at 11:32:09AM +0200, Thomas Hellström (VMware) wrote:
> +vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
> + pgprot_t prot,
> + pgoff_t num_prefault)
> +{
> + struct vm_area_struct *vma = vmf->vma;
>
On 9/13/19 3:40 PM, Hillf Danton wrote:
On Fri, 13 Sep 2019 11:32:09 +0200
err = ttm_mem_io_lock(man, true);
- if (unlikely(err != 0)) {
- ret = VM_FAULT_NOPAGE;
- goto out_unlock;
- }
+ if (unlikely(err != 0))
+ return VM_FAULT
From: Thomas Hellstrom
With the vmwgfx dirty tracking, the default TTM fault handler is not
completely sufficient (vmwgfx need to modify the vma->vm_flags member,
and also needs to restrict the number of prefaults).
We also want to replicate the new ttm_bo_vm_reserve() functionality
So start tu
