2016-10-24 05:51:52

by David Airlie

[permalink] [raw]
Subject: [PATCH 1/2] x86/io: add interface to reserve io memtype for a resource range.

A recent change to the mm code in:
87744ab3832b83ba71b931f86f9cfdb000d07da5
mm: fix cache mode tracking in vm_insert_mixed()

started enforcing checking the memory type against the registered list for
amixed pfn insertion mappings. It happens that the drm drivers for a number
of gpus relied on this being broken. Currently the driver only inserted
VRAM mappings into the tracking table when they came from the kernel,
and userspace mappings never landed in the table. This led to a regression
where all the mapping end up as UC instead of WC now.

I've considered a number of solutions but since this needs to be fixed
in fixes and not next, and some of the solutions were going to introduce
overhead that hadn't been there before I didn't consider them viable at
this stage. These mainly concerned hooking into the TTM io reserve APIs,
but these API have a bunch of fast paths I didn't want to unwind to add
this to.

The solution I've decided on is to add a new API like the arch_phys_wc
APIs (these would have worked but wc_del didn't take a range), and
use them from the drivers to add a WC compatible mapping to the table
for all VRAM on those GPUs. This means we can then create userspace
mapping that won't get degraded to UC.

Signed-off-by: Dave Airlie <[email protected]>
---
arch/x86/include/asm/io.h | 6 ++++++
arch/x86/mm/pat.c | 13 +++++++++++++
include/linux/io.h | 13 +++++++++++++
3 files changed, 32 insertions(+)

diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index de25aad..6e18f66 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_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 170cc4f..49d1b75 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -730,6 +730,19 @@ 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/include/linux/io.h b/include/linux/io.h
index e2c8419..963ab71 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -141,4 +141,17 @@ enum {
void *memremap(resource_size_t offset, size_t size, unsigned long flags);
void memunmap(void *addr);

+#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 */
--
2.5.5


2016-10-24 05:52:18

by David Airlie

[permalink] [raw]
Subject: [PATCH 2/2] drm/drivers: add support for using the arch wc mapping API.

This fixes a regression in all these drivers since the cache
mode tracking was fixed for mixed mappings. It uses the new
arch API to add the VRAM range to the PAT mapping tracking
tables.

Fixes: 87744ab3832 (mm: fix cache mode tracking in vm_insert_mixed())
Signed-off-by: Dave Airlie <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 5 +++++
drivers/gpu/drm/ast/ast_ttm.c | 6 ++++++
drivers/gpu/drm/cirrus/cirrus_ttm.c | 7 +++++++
drivers/gpu/drm/mgag200/mgag200_ttm.c | 7 +++++++
drivers/gpu/drm/nouveau/nouveau_ttm.c | 8 ++++++++
drivers/gpu/drm/radeon/radeon_object.c | 5 +++++
6 files changed, 38 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index aa074fa..f3efb1c 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 608df4c..0743e65 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 bb2438d..5e7e63c 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 919b35f..dcf7d11 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 1825dbc..a6dbe82 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 be30861..41b72ce 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.
--
2.5.5