patches to fix a regression in 4.9-rc1 on x86 PAT

-----BEGIN PGP SIGNATURE-----
 
 iQIcBAABAgAGBQJYEFHpAAoJEAx081l5xIa+tyYP/0xq+ZqHwS90k1mge/2uWYB3
 sVQvFFIV55r6siOjIdDek+dsHq7IGFOChbsxegGyGvfwYVjzSmdoBwO1aMTV+Ii9
 OoqLS/53kts9jHOVm1UNsbxW1lzJVWoFWpMY57KDodWsWxVbd0NuP9mfTRIH2Sfj
 MmymKigXgwHSndn07+2xp9jI9Y5krtOLl+4YDsly7JF2IR7UBRRoW8n/WHR75lny
 MNn2Vtn9NBwxDieFQc/KQGUQ1nC8wB0c3wtGDDQIux0gp6IVW+pQoCLo6CMtgHXB
 IXGDojVA9KpcyEUz5RkBsVHYmvZR1PoS+nrnEE6b/C8p7UDuyCrk1Zfy0ZTGV/hq
 LKmfRKB3NWbgKnBbqOdFYhsh/iyVjqoNdGYqfR4qJx5JGIltVWbjYwlwUpImlrIY
 gKqtAdVFaFuoJs8MpFharxFlBf/o9DPDTPTWPQxGI16y7poH+86v7QmAJT9dJHRE
 pf3oyYI3eHTeIQb42f7PHSp4hsVJMX5Awkm9a8b9PhNlu/3cHUOYkCT060ripMBc
 ZksIUqKFzuk+TDRTnQrCQjaC4vJ6s8XUwntFhfHCZUmnnH8YhYpryDwdyzavcUvX
 or8rkKsO/+Jxa1kRr8d2c1JYi2FIMHBP0srAu43WeYyAsSPFIL/9l5flIeHi2Ow3
 tSHbCo4W5YRbQaVcBzxG
 =prah
 -----END PGP SIGNATURE-----

Merge tag 'drm-x86-pat-regression-fix' of git://people.freedesktop.org/~airlied/linux

Pull drm x86/pat regression fixes from Dave Airlie:
 "This is a standalone pull request for the fix for a regression
  introduced in -rc1 by a change to vm_insert_mixed to start using the
  PAT range tracking to validate page protections. With this fix in
  place, all the VRAM mappings for GPU drivers ended up at UC instead of
  WC.

  There are probably better ways to fix this long term, but nothing I'd
  considered for -fixes that wouldn't need more settling in time. So
  I've just created a new arch API that the drivers can reserve all
  their VRAM aperture ranges as WC"

* tag 'drm-x86-pat-regression-fix' of git://people.freedesktop.org/~airlied/linux:
  drm/drivers: add support for using the arch wc mapping API.
  x86/io: add interface to reserve io memtype for a resource range. (v1.1)

arch/x86/include/asm/io.h

@@ -351,4 +351,10 @@ extern void arch_phys_wc_del(int handle);
 #define arch_phys_wc_add arch_phys_wc_add
 #endif
 
+#ifdef CONFIG_X86_PAT
+extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size);
+extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size);
+#define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc
+#endif
+
 #endif /* _ASM_X86_IO_H */

arch/x86/mm/pat.c

@@ -730,6 +730,20 @@ void io_free_memtype(resource_size_t start, resource_size_t end)
 	free_memtype(start, end);
 }
 
+int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size)
+{
+	enum page_cache_mode type = _PAGE_CACHE_MODE_WC;
+
+	return io_reserve_memtype(start, start + size, &type);
+}
+EXPORT_SYMBOL(arch_io_reserve_memtype_wc);
+
+void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size)
+{
+	io_free_memtype(start, start + size);
+}
+EXPORT_SYMBOL(arch_io_free_memtype_wc);
+
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t vma_prot)
 {

drivers/gpu/drm/amd/amdgpu/amdgpu_object.c

@@ -754,6 +754,10 @@ static const char *amdgpu_vram_names[] = {
 
 int amdgpu_bo_init(struct amdgpu_device *adev)
 {
+	/* reserve PAT memory space to WC for VRAM */
+	arch_io_reserve_memtype_wc(adev->mc.aper_base,
+				   adev->mc.aper_size);
+
 	/* Add an MTRR for the VRAM */
 	adev->mc.vram_mtrr = arch_phys_wc_add(adev->mc.aper_base,
 					      adev->mc.aper_size);
@@ -769,6 +773,7 @@ void amdgpu_bo_fini(struct amdgpu_device *adev)
 {
 	amdgpu_ttm_fini(adev);
 	arch_phys_wc_del(adev->mc.vram_mtrr);
+	arch_io_free_memtype_wc(adev->mc.aper_base, adev->mc.aper_size);
 }
 
 int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,

drivers/gpu/drm/ast/ast_ttm.c

@@ -267,6 +267,8 @@ int ast_mm_init(struct ast_private *ast)
 		return ret;
 	}
 
+	arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
+				   pci_resource_len(dev->pdev, 0));
 	ast->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
 					pci_resource_len(dev->pdev, 0));
 
@@ -275,11 +277,15 @@ int ast_mm_init(struct ast_private *ast)
 
 void ast_mm_fini(struct ast_private *ast)
 {
+	struct drm_device *dev = ast->dev;
+
 	ttm_bo_device_release(&ast->ttm.bdev);
 
 	ast_ttm_global_release(ast);
 
 	arch_phys_wc_del(ast->fb_mtrr);
+	arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
+				pci_resource_len(dev->pdev, 0));
 }
 
 void ast_ttm_placement(struct ast_bo *bo, int domain)

drivers/gpu/drm/cirrus/cirrus_ttm.c

@@ -267,6 +267,9 @@ int cirrus_mm_init(struct cirrus_device *cirrus)
 		return ret;
 	}
 
+	arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
+				   pci_resource_len(dev->pdev, 0));
+
 	cirrus->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
 					   pci_resource_len(dev->pdev, 0));
 
@@ -276,6 +279,8 @@ int cirrus_mm_init(struct cirrus_device *cirrus)
 
 void cirrus_mm_fini(struct cirrus_device *cirrus)
 {
+	struct drm_device *dev = cirrus->dev;
+
 	if (!cirrus->mm_inited)
 		return;
 
@@ -285,6 +290,8 @@ void cirrus_mm_fini(struct cirrus_device *cirrus)
 
 	arch_phys_wc_del(cirrus->fb_mtrr);
 	cirrus->fb_mtrr = 0;
+	arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
+				pci_resource_len(dev->pdev, 0));
 }
 
 void cirrus_ttm_placement(struct cirrus_bo *bo, int domain)

drivers/gpu/drm/mgag200/mgag200_ttm.c

@@ -266,6 +266,9 @@ int mgag200_mm_init(struct mga_device *mdev)
 		return ret;
 	}
 
+	arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
+				   pci_resource_len(dev->pdev, 0));
+
 	mdev->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
 					 pci_resource_len(dev->pdev, 0));
 
@@ -274,10 +277,14 @@ int mgag200_mm_init(struct mga_device *mdev)
 
 void mgag200_mm_fini(struct mga_device *mdev)
 {
+	struct drm_device *dev = mdev->dev;
+
 	ttm_bo_device_release(&mdev->ttm.bdev);
 
 	mgag200_ttm_global_release(mdev);
 
+	arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
+				pci_resource_len(dev->pdev, 0));
 	arch_phys_wc_del(mdev->fb_mtrr);
 	mdev->fb_mtrr = 0;
 }

drivers/gpu/drm/nouveau/nouveau_ttm.c

@@ -398,6 +398,9 @@ nouveau_ttm_init(struct nouveau_drm *drm)
 	/* VRAM init */
 	drm->gem.vram_available = drm->device.info.ram_user;
 
+	arch_io_reserve_memtype_wc(device->func->resource_addr(device, 1),
+				   device->func->resource_size(device, 1));
+
 	ret = ttm_bo_init_mm(&drm->ttm.bdev, TTM_PL_VRAM,
 			      drm->gem.vram_available >> PAGE_SHIFT);
 	if (ret) {
@@ -430,6 +433,8 @@ nouveau_ttm_init(struct nouveau_drm *drm)
 void
 nouveau_ttm_fini(struct nouveau_drm *drm)
 {
+	struct nvkm_device *device = nvxx_device(&drm->device);
+
 	ttm_bo_clean_mm(&drm->ttm.bdev, TTM_PL_VRAM);
 	ttm_bo_clean_mm(&drm->ttm.bdev, TTM_PL_TT);
 
@@ -439,4 +444,7 @@ nouveau_ttm_fini(struct nouveau_drm *drm)
 
 	arch_phys_wc_del(drm->ttm.mtrr);
 	drm->ttm.mtrr = 0;
+	arch_io_free_memtype_wc(device->func->resource_addr(device, 1),
+				device->func->resource_size(device, 1));
+
 }

drivers/gpu/drm/radeon/radeon_object.c

@@ -446,6 +446,10 @@ void radeon_bo_force_delete(struct radeon_device *rdev)
 
 int radeon_bo_init(struct radeon_device *rdev)
 {
+	/* reserve PAT memory space to WC for VRAM */
+	arch_io_reserve_memtype_wc(rdev->mc.aper_base,
+				   rdev->mc.aper_size);
+
 	/* Add an MTRR for the VRAM */
 	if (!rdev->fastfb_working) {
 		rdev->mc.vram_mtrr = arch_phys_wc_add(rdev->mc.aper_base,
@@ -463,6 +467,7 @@ void radeon_bo_fini(struct radeon_device *rdev)
 {
 	radeon_ttm_fini(rdev);
 	arch_phys_wc_del(rdev->mc.vram_mtrr);
+	arch_io_free_memtype_wc(rdev->mc.aper_base, rdev->mc.aper_size);
 }
 
 /* Returns how many bytes TTM can move per IB.

include/linux/io.h

@@ -141,4 +141,26 @@ enum {
 void *memremap(resource_size_t offset, size_t size, unsigned long flags);
 void memunmap(void *addr);
 
+/*
+ * On x86 PAT systems we have memory tracking that keeps track of
+ * the allowed mappings on memory ranges. This tracking works for
+ * all the in-kernel mapping APIs (ioremap*), but where the user
+ * wishes to map a range from a physical device into user memory
+ * the tracking won't be updated. This API is to be used by
+ * drivers which remap physical device pages into userspace,
+ * and wants to make sure they are mapped WC and not UC.
+ */
+#ifndef arch_io_reserve_memtype_wc
+static inline int arch_io_reserve_memtype_wc(resource_size_t base,
+					     resource_size_t size)
+{
+	return 0;
+}
+
+static inline void arch_io_free_memtype_wc(resource_size_t base,
+					   resource_size_t size)
+{
+}
+#endif
+
 #endif /* _LINUX_IO_H */