summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-11-15 20:42:10 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-15 20:42:10 -0800
commite60e1ee60630cafef5e430c2ae364877e061d980 (patch)
tree816aeef8fe8d4a2c6a1ebbc7a350839bac8dd4c2 /drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
parent5d352e69c60e54b5f04d6e337a1d2bf0dbf3d94a (diff)
parentf150891fd9878ef0d9197c4e8451ce67c3bdd014 (diff)
Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux
Pull drm updates from Dave Airlie: "This is the main drm pull request for v4.15. Core: - Atomic object lifetime fixes - Atomic iterator improvements - Sparse/smatch fixes - Legacy kms ioctls to be interruptible - EDID override improvements - fb/gem helper cleanups - Simple outreachy patches - Documentation improvements - Fix dma-buf rcu races - DRM mode object leasing for improving VR use cases. - vgaarb improvements for non-x86 platforms. New driver: - tve200: Faraday Technology TVE200 block. This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in the StorLink SL3516 (later Cortina Systems CS3516) as well as the Grain Media GM8180. New bridges: - SiI9234 support New panels: - S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba LT089AC19000, Innolux AT043TN24 i915: - Remove Coffeelake from alpha support - Cannonlake workarounds - Infoframe refactoring for DisplayPort - VBT updates - DisplayPort vswing/emph/buffer translation refactoring - CCS fixes - Restore GPU clock boost on missed vblanks - Scatter list updates for userptr allocations - Gen9+ transition watermarks - Display IPC (Isochronous Priority Control) - Private PAT management - GVT: improved error handling and pci config sanitizing - Execlist refactoring - Transparent Huge Page support - User defined priorities support - HuC/GuC firmware refactoring - DP MST fixes - eDP power sequencing fixes - Use RCU instead of stop_machine - PSR state tracking support - Eviction fixes - BDW DP aux channel timeout fixes - LSPCON fixes - Cannonlake PLL fixes amdgpu: - Per VM BO support - Powerplay cleanups - CI powerplay support - PASID mgr for kfd - SR-IOV fixes - initial GPU reset for vega10 - Prime mmap support - TTM updates - Clock query interface for Raven - Fence to handle ioctl - UVD encode ring support on Polaris - Transparent huge page DMA support - Compute LRU pipe tweaks - BO flag to allow buffers to opt out of implicit sync - CTX priority setting API - VRAM lost infrastructure plumbing qxl: - fix flicker since atomic rework amdkfd: - Further improvements from internal AMD tree - Usermode events - Drop radeon support nouveau: - Pascal temperature sensor support - Improved BAR2 handling - MMU rework to support Pascal MMU exynos: - Improved HDMI/mixer support - HDMI audio interface support tegra: - Prep work for tegra186 - Cleanup/fixes msm: - Preemption support for a5xx - Display fixes for 8x96 (snapdragon 820) - Async cursor plane fixes - FW loading rework - GPU debugging improvements vc4: - Prep for DSI panels - fix T-format tiling scanout - New madvise ioctl Rockchip: - LVDS support omapdrm: - omap4 HDMI CEC support etnaviv: - GPU performance counters groundwork sun4i: - refactor driver load + TCON backend - HDMI improvements - A31 support - Misc fixes udl: - Probe/EDID read fixes. tilcdc: - Misc fixes. pl111: - Support more variants adv7511: - Improve EDID handling. - HDMI CEC support sii8620: - Add remote control support" * tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits) drm/rockchip: analogix_dp: Use mutex rather than spinlock drm/mode_object: fix documentation for object lookups. drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU drm/i915: Move init_clock_gating() back to where it was drm/i915: Prune the reservation shared fence array drm/i915: Idle the GPU before shinking everything drm/i915: Lock llist_del_first() vs llist_del_all() drm/i915: Calculate ironlake intermediate watermarks correctly, v2. drm/i915: Disable lazy PPGTT page table optimization for vGPU drm/i915/execlists: Remove the priority "optimisation" drm/i915: Filter out spurious execlists context-switch interrupts drm/amdgpu: use irq-safe lock for kiq->ring_lock drm/amdgpu: bypass lru touch for KIQ ring submission drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories() drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs() drm/amd/powerplay: initialize a variable before using it drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug drm/rockchip: add CONFIG_OF dependency for lvds ...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_object.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_object.c122
1 files changed, 38 insertions, 84 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 9e495da0bb03..ea25164e7f4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -40,9 +40,7 @@
static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
- struct amdgpu_bo *bo;
-
- bo = container_of(tbo, struct amdgpu_bo, tbo);
+ struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
amdgpu_bo_kunmap(bo);
@@ -64,11 +62,12 @@ bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
return false;
}
-static void amdgpu_ttm_placement_init(struct amdgpu_device *adev,
- struct ttm_placement *placement,
- struct ttm_place *places,
- u32 domain, u64 flags)
+void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
+ struct ttm_placement *placement = &abo->placement;
+ struct ttm_place *places = abo->placements;
+ u64 flags = abo->flags;
u32 c = 0;
if (domain & AMDGPU_GEM_DOMAIN_VRAM) {
@@ -151,27 +150,6 @@ static void amdgpu_ttm_placement_init(struct amdgpu_device *adev,
placement->busy_placement = places;
}
-void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
-{
- struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
-
- amdgpu_ttm_placement_init(adev, &abo->placement, abo->placements,
- domain, abo->flags);
-}
-
-static void amdgpu_fill_placement_to_bo(struct amdgpu_bo *bo,
- struct ttm_placement *placement)
-{
- BUG_ON(placement->num_placement > (AMDGPU_GEM_DOMAIN_MAX + 1));
-
- memcpy(bo->placements, placement->placement,
- placement->num_placement * sizeof(struct ttm_place));
- bo->placement.num_placement = placement->num_placement;
- bo->placement.num_busy_placement = placement->num_busy_placement;
- bo->placement.placement = bo->placements;
- bo->placement.busy_placement = bo->placements;
-}
-
/**
* amdgpu_bo_create_reserved - create reserved BO for kernel use
*
@@ -303,14 +281,13 @@ void amdgpu_bo_free_kernel(struct amdgpu_bo **bo, u64 *gpu_addr,
*cpu_addr = NULL;
}
-int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
- unsigned long size, int byte_align,
- bool kernel, u32 domain, u64 flags,
- struct sg_table *sg,
- struct ttm_placement *placement,
- struct reservation_object *resv,
- uint64_t init_value,
- struct amdgpu_bo **bo_ptr)
+static int amdgpu_bo_do_create(struct amdgpu_device *adev,
+ unsigned long size, int byte_align,
+ bool kernel, u32 domain, u64 flags,
+ struct sg_table *sg,
+ struct reservation_object *resv,
+ uint64_t init_value,
+ struct amdgpu_bo **bo_ptr)
{
struct amdgpu_bo *bo;
enum ttm_bo_type type;
@@ -384,13 +361,17 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
#endif
- amdgpu_fill_placement_to_bo(bo, placement);
- /* Kernel allocation are uninterruptible */
+ bo->tbo.bdev = &adev->mman.bdev;
+ amdgpu_ttm_placement_from_domain(bo, domain);
initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
+ /* Kernel allocation are uninterruptible */
r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
&bo->placement, page_align, !kernel, NULL,
acc_size, sg, resv, &amdgpu_ttm_bo_destroy);
+ if (unlikely(r != 0))
+ return r;
+
bytes_moved = atomic64_read(&adev->num_bytes_moved) -
initial_bytes_moved;
if (adev->mc.visible_vram_size < adev->mc.real_vram_size &&
@@ -400,9 +381,6 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
else
amdgpu_cs_report_moved_bytes(adev, bytes_moved, 0);
- if (unlikely(r != 0))
- return r;
-
if (kernel)
bo->tbo.priority = 1;
@@ -442,27 +420,17 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
unsigned long size, int byte_align,
struct amdgpu_bo *bo)
{
- struct ttm_placement placement = {0};
- struct ttm_place placements[AMDGPU_GEM_DOMAIN_MAX + 1];
int r;
if (bo->shadow)
return 0;
- memset(&placements, 0, sizeof(placements));
- amdgpu_ttm_placement_init(adev, &placement, placements,
- AMDGPU_GEM_DOMAIN_GTT,
- AMDGPU_GEM_CREATE_CPU_GTT_USWC |
- AMDGPU_GEM_CREATE_SHADOW);
-
- r = amdgpu_bo_create_restricted(adev, size, byte_align, true,
- AMDGPU_GEM_DOMAIN_GTT,
- AMDGPU_GEM_CREATE_CPU_GTT_USWC |
- AMDGPU_GEM_CREATE_SHADOW,
- NULL, &placement,
- bo->tbo.resv,
- 0,
- &bo->shadow);
+ r = amdgpu_bo_do_create(adev, size, byte_align, true,
+ AMDGPU_GEM_DOMAIN_GTT,
+ AMDGPU_GEM_CREATE_CPU_GTT_USWC |
+ AMDGPU_GEM_CREATE_SHADOW,
+ NULL, bo->tbo.resv, 0,
+ &bo->shadow);
if (!r) {
bo->shadow->parent = amdgpu_bo_ref(bo);
mutex_lock(&adev->shadow_list_lock);
@@ -484,18 +452,11 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
uint64_t init_value,
struct amdgpu_bo **bo_ptr)
{
- struct ttm_placement placement = {0};
- struct ttm_place placements[AMDGPU_GEM_DOMAIN_MAX + 1];
uint64_t parent_flags = flags & ~AMDGPU_GEM_CREATE_SHADOW;
int r;
- memset(&placements, 0, sizeof(placements));
- amdgpu_ttm_placement_init(adev, &placement, placements,
- domain, parent_flags);
-
- r = amdgpu_bo_create_restricted(adev, size, byte_align, kernel, domain,
- parent_flags, sg, &placement, resv,
- init_value, bo_ptr);
+ r = amdgpu_bo_do_create(adev, size, byte_align, kernel, domain,
+ parent_flags, sg, resv, init_value, bo_ptr);
if (r)
return r;
@@ -672,7 +633,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
{
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
int r, i;
- unsigned fpfn, lpfn;
if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm))
return -EPERM;
@@ -704,22 +664,16 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
}
bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+ /* force to pin into visible video ram */
+ if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
+ bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
amdgpu_ttm_placement_from_domain(bo, domain);
for (i = 0; i < bo->placement.num_placement; i++) {
- /* force to pin into visible video ram */
- if ((bo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
- !(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS) &&
- (!max_offset || max_offset >
- adev->mc.visible_vram_size)) {
- if (WARN_ON_ONCE(min_offset >
- adev->mc.visible_vram_size))
- return -EINVAL;
- fpfn = min_offset >> PAGE_SHIFT;
- lpfn = adev->mc.visible_vram_size >> PAGE_SHIFT;
- } else {
- fpfn = min_offset >> PAGE_SHIFT;
- lpfn = max_offset >> PAGE_SHIFT;
- }
+ unsigned fpfn, lpfn;
+
+ fpfn = min_offset >> PAGE_SHIFT;
+ lpfn = max_offset >> PAGE_SHIFT;
+
if (fpfn > bo->placements[i].fpfn)
bo->placements[i].fpfn = fpfn;
if (!bo->placements[i].lpfn ||
@@ -928,8 +882,8 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
return;
- abo = container_of(bo, struct amdgpu_bo, tbo);
- amdgpu_vm_bo_invalidate(adev, abo);
+ abo = ttm_to_amdgpu_bo(bo);
+ amdgpu_vm_bo_invalidate(adev, abo, evict);
amdgpu_bo_kunmap(abo);
@@ -955,7 +909,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
return 0;
- abo = container_of(bo, struct amdgpu_bo, tbo);
+ abo = ttm_to_amdgpu_bo(bo);
/* Remember that this BO was accessed by the CPU */
abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;