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)

9 files changed, 80 insertions, 0 deletions

diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index de25aad07853..d34bd370074b 100644
--- a/arch/x86/include/asm/io.h
+++ b/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 */
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 170cc4ff057b..83e701f160a9 100644
--- a/arch/x86/mm/pat.c
+++ b/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)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index aa074fac0c7f..f3efb1c5dae9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/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,
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 608df4c90520..0743e65cb240 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/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)
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index bb2438dd8733..5e7e63ce7bce 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/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)
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 919b35f2ad24..dcf7d11ac380 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/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;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 1825dbc33192..a6dbe8258040 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/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));
+
 }
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index be30861afae9..41b72ce6613f 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/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.
diff --git a/include/linux/io.h b/include/linux/io.h
index e2c8419278c1..82ef36eac8a1 100644
--- a/include/linux/io.h
+++ b/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 */