On Fri, Jun 09, 2017 at 10:59:47AM +0200, Christian König wrote:
> From: Christian König <christian.koenig@xxxxxxx>
>
> Try to resize BAR0 to let CPU access all of VRAM.
>
> v2: rebased, style cleanups, disable mem decode before resize,
> handle gmc_v9 as well, round size up to power of two.
> v3: handle gmc_v6 as well, release and reassign all BARs in the driver.
>
> Signed-off-by: Christian König <christian.koenig@xxxxxxx>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 40 ++++++++++++++++++++++++++++++
> drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 8 +++---
> drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 8 +++---
> drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 8 +++---
> drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 10 +++++---
> 6 files changed, 62 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index c6a2ca4..87655e2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1943,6 +1943,7 @@ uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
> struct ttm_mem_reg *mem);
> void amdgpu_vram_location(struct amdgpu_device *adev, struct amdgpu_mc *mc, u64 base);
> void amdgpu_gtt_location(struct amdgpu_device *adev, struct amdgpu_mc *mc);
> +void amdgpu_resize_bar0(struct amdgpu_device *adev);
> void amdgpu_ttm_set_active_vram_size(struct amdgpu_device *adev, u64 size);
> int amdgpu_ttm_init(struct amdgpu_device *adev);
> void amdgpu_ttm_fini(struct amdgpu_device *adev);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 99290af..f74b79f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -709,6 +709,46 @@ void amdgpu_gtt_location(struct amdgpu_device *adev, struct amdgpu_mc *mc)
> mc->gtt_size >> 20, mc->gtt_start, mc->gtt_end);
> }
>
> +/**
> + * amdgpu_resize_bar0 - try to resize BAR0
> + *
> + * @adev: amdgpu_device pointer
> + *
> + * Try to resize BAR0 to make all VRAM CPU accessible.
> + */
> +void amdgpu_resize_bar0(struct amdgpu_device *adev)
> +{
> + u64 space_needed = roundup_pow_of_two(adev->mc.real_vram_size);
> + u32 rbar_size = order_base_2(((space_needed >> 20) | 1)) - 1;
> + u16 cmd;
> + int r;
> +
> + /* Disable memory decoding while we change the BAR addresses and size */
> + pci_read_config_word(adev->pdev, PCI_COMMAND, &cmd);
> + pci_write_config_word(adev->pdev, PCI_COMMAND,
> + cmd & ~PCI_COMMAND_MEMORY);
> +
> + /* Free the VRAM and doorbell BAR, we most likely need to move both. */
> + amdgpu_doorbell_fini(adev);
> + pci_release_resource(adev->pdev, 0);
> + if (adev->asic_type >= CHIP_BONAIRE)
> + pci_release_resource(adev->pdev, 2);
> +
> + r = pci_resize_resource(adev->pdev, 0, rbar_size);
> + if (r == -ENOSPC)
> + DRM_INFO("Not enough PCI address space for a large BAR.");
> + else if (r && r != -ENOTSUPP)
> + DRM_ERROR("Problem resizing BAR0 (%d).", r);
> +
> + pci_assign_unassigned_bus_resources(adev->pdev->bus);
> + pci_write_config_word(adev->pdev, PCI_COMMAND, cmd);
I think it's problematic to unconditionally re-enable decoding here
because the pci_assign_unassigned_bus_resources() above may have
failed. A pci_enable_decoding() interface would be one way to handle
this.
> +
> + /* When the doorbell BAR isn't available we have no chance of
> + * using the device.
> + */
> + BUG_ON(amdgpu_doorbell_init(adev));
> +}
> +
> /*
> * GPU helpers function.
> */
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
> index a33ba60..af3c3c6 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
> @@ -334,12 +334,14 @@ static int gmc_v6_0_mc_init(struct amdgpu_device *adev)
> break;
> }
> adev->mc.vram_width = numchan * chansize;
> - /* Could aper size report 0 ? */
> - adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
> - adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
> /* size in MB on si */
> adev->mc.mc_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
> adev->mc.real_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
> +
> + if (!(adev->flags & AMD_IS_APU))
> + amdgpu_resize_bar0(adev);
> + adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
> + adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
> adev->mc.visible_vram_size = adev->mc.aper_size;
>
> /* unless the user had overridden it, set the gart
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
> index 1326c1f..1d9f7a2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
> @@ -372,13 +372,15 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev)
> }
> adev->mc.vram_width = numchan * chansize;
> }
> - /* Could aper size report 0 ? */
> - adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
> - adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
> /* size in MB on si */
> adev->mc.mc_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
> adev->mc.real_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
>
> + if (!(adev->flags & AMD_IS_APU))
> + amdgpu_resize_bar0(adev);
> + adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
> + adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
> +
> #ifdef CONFIG_X86_64
> if (adev->flags & AMD_IS_APU) {
> adev->mc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22;
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
> index 42e5b55..858153d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
> @@ -534,13 +534,15 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
> }
> adev->mc.vram_width = numchan * chansize;
> }
> - /* Could aper size report 0 ? */
> - adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
> - adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
> /* size in MB on si */
> adev->mc.mc_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
> adev->mc.real_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
>
> + if (!(adev->flags & AMD_IS_APU))
> + amdgpu_resize_bar0(adev);
> + adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
> + adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
> +
> #ifdef CONFIG_X86_64
> if (adev->flags & AMD_IS_APU) {
> adev->mc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22;
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> index 68172aa..f2e311d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> @@ -480,17 +480,19 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
> }
> adev->mc.vram_width = numchan * chansize;
>
> - /* Could aper size report 0 ? */
> - adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
> - adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
> /* size in MB on si */
> adev->mc.mc_vram_size =
> ((adev->flags & AMD_IS_APU) ? nbio_v7_0_get_memsize(adev) :
> nbio_v6_1_get_memsize(adev)) * 1024ULL * 1024ULL;
> adev->mc.real_vram_size = adev->mc.mc_vram_size;
> - adev->mc.visible_vram_size = adev->mc.aper_size;
> +
> + if (!(adev->flags & AMD_IS_APU))
> + amdgpu_resize_bar0(adev);
> + adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
> + adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
>
> /* In case the PCI BAR is larger than the actual amount of vram */
> + adev->mc.visible_vram_size = adev->mc.aper_size;
> if (adev->mc.visible_vram_size > adev->mc.real_vram_size)
> adev->mc.visible_vram_size = adev->mc.real_vram_size;
>
> --
> 2.7.4
>
