To block fast gup we need to make sure TTM ptes are always special.
With MIXEDMAP we, on architectures that don't support pte_special,
insert normal ptes, but OTOH on those architectures, fast is not
supported.
At the same time, the function documentation to vm_normal_page() suggests
that ptes pointing to system memory pages of MIXEDMAP vmas are always
normal, but that doesn't seem consistent with what's implemented in
vmf_insert_mixed(). I'm thus not entirely sure this patch is actually
needed.
But to make sure and to avoid also normal (non-fast) gup, make all
TTM vmas PFNMAP. With PFNMAP we can't allow COW mappings
anymore so make is_cow_mapping() available and use it to reject
COW mappigs at mmap time.
There was previously a comment in the code that WC mappings together
with x86 PAT + PFNMAP was bad for performance. However from looking at
vmf_insert_mixed() it looks like in the current code PFNMAP and MIXEDMAP
are handled the same for architectures that support pte_special. This
means there should not be a performance difference anymore, but this
needs to be verified.
Cc: Christian Koenig <christian.koenig@xxxxxxx>
Cc: David Airlie <airlied@xxxxxxxx>
Cc: Daniel Vetter <daniel@xxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Cc: dri-devel@xxxxxxxxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Signed-off-by: Thomas Hellström (Intel) <thomas_os@xxxxxxxxxxxx>
drivers/gpu/drm/ttm/ttm_bo_vm.c | 22 ++++++++--------------
include/linux/mm.h | 5 +++++
mm/internal.h | 5 -----
3 files changed, 13 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 1c34983480e5..708c6fb9be81 100644
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -372,12 +372,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
* at arbitrary times while the data is mmap'ed.
* See vmf_insert_mixed_prot() for a discussion.
*/
- if (vma->vm_flags & VM_MIXEDMAP)
- ret = vmf_insert_mixed_prot(vma, address,
- __pfn_to_pfn_t(pfn, PFN_DEV),
- prot);
- else
- ret = vmf_insert_pfn_prot(vma, address, pfn, prot);
+ ret = vmf_insert_pfn_prot(vma, address, pfn, prot);
/* Never error on prefaulted PTEs */
if (unlikely((ret & VM_FAULT_ERROR))) {
@@ -555,18 +550,14 @@ static void ttm_bo_mmap_vma_setup(struct ttm_buffer_object *bo, struct vm_area_s
* Note: We're transferring the bo reference to
* vma->vm_private_data here.
*/
-
vma->vm_private_data = bo;
/*
- * We'd like to use VM_PFNMAP on shared mappings, where
- * (vma->vm_flags & VM_SHARED) != 0, for performance reasons,
- * but for some reason VM_PFNMAP + x86 PAT + write-combine is very
- * bad for performance. Until that has been sorted out, use
- * VM_MIXEDMAP on all mappings. See freedesktop.org bug #75719
+ * PFNMAP forces us to block COW mappings in mmap(),
+ * and with MIXEDMAP we would incorrectly allow fast gup
+ * on TTM memory on architectures that don't have pte_special.
*/
- vma->vm_flags |= VM_MIXEDMAP;
- vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
+ vma->vm_flags |= VM_PFNMAP | VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
}
int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
@@ -579,6 +570,9 @@ int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET_START))
return -EINVAL;
+ if (unlikely(is_cow_mapping(vma->vm_flags)))
+ return -EINVAL;
+
bo = ttm_bo_vm_lookup(bdev, vma->vm_pgoff, vma_pages(vma));
if (unlikely(!bo))
return -EINVAL;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 77e64e3eac80..c6ebf7f9ddbb 100644
+++ b/include/linux/mm.h
@@ -686,6 +686,11 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma)
return vma->vm_flags & VM_ACCESS_FLAGS;
}
+static inline bool is_cow_mapping(vm_flags_t flags)
+{
+ return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
+}
