aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
diff options
context:
space:
mode:
authorLinus Torvalds <[email protected]>2017-09-03 17:02:26 -0700
committerLinus Torvalds <[email protected]>2017-09-03 17:02:26 -0700
commit906dde0f355bd97c080c215811ae7db1137c4af8 (patch)
tree1e1b4ba58a59c4027f06d86e7430566ee0dcbb15 /drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
parent69c0067aa3f40d3e52ab78643aecb17d669d3389 (diff)
parent7846b12fe0b5feab5446d892f41b5140c1419109 (diff)
Merge tag 'drm-for-v4.14' of git://people.freedesktop.org/~airlied/linux
Pull drm updates from Dave Airlie: "This is the main drm pull request for 4.14 merge window. I'm sending this early, as my continuing journey into fatherhood is occurring really soon now, I'm going to be mostly useless for the next couple of weeks, though I may be able to read email, I doubt I'll be doing much patch applications or git sending. If anything urgent pops up I've asked Daniel/Jani/Alex/Sean to try and direct stuff towards you. Outside drm changes: Some rcar-du updates that touch the V4L tree, all acks should be in place. It adds one export to the radix tree code for new i915 use case. There are some minor AGP cleanups (don't see that too often). Changes to the vbox driver in staging to avoid breaking compilation. Summary: core: - Atomic helper fixes - Atomic UAPI fixes - Add YCBCR 4:2:0 support - Drop set_busid hook - Refactor fb_helper locking - Remove a bunch of internal APIs - Add a bunch of better default handlers - Format modifier/blob plane property added - More internal header refactoring - Make more internal API names consistent - Enhanced syncobj APIs (wait/signal/reset/create signalled) bridge: - Add Synopsys Designware MIPI DSI host bridge driver tiny: - Add Pervasive Displays RePaper displays - Add support for LEGO MINDSTORMS EV3 LCD i915: - Lots of GEN10/CNL support patches - drm syncobj support - Skylake+ watermark refactoring - GVT vGPU 48-bit ppgtt support - GVT performance improvements - NOA change ioctl - CCS (color compression) scanout support - GPU reset improvements amdgpu: - Initial hugepage support - BO migration logic rework - Vega10 improvements - Powerplay fixes - Stop reprogramming the MC - Fixes for ACP audio on stoney - SR-IOV fixes/improvements - Command submission overhead improvements amdkfd: - Non-dGPU upstreaming patches - Scratch VA ioctl - Image tiling modes - Update PM4 headers for new firmware - Drop all BUG_ONs. nouveau: - GP108 modesetting support. - Disable MSI on big endian. vmwgfx: - Add fence fd support. msm: - Runtime PM improvements exynos: - NV12MT support - Refactor KMS drivers imx-drm: - Lock scanout channel to improve memory bw - Cleanups etnaviv: - GEM object population fixes tegra: - Prep work for Tegra186 support - PRIME mmap support sunxi: - HDMI support improvements - HDMI CEC support omapdrm: - HDMI hotplug IRQ support - Big driver cleanup - OMAP5 DSI support rcar-du: - vblank fixes - VSP1 updates arcgpu: - Minor fixes stm: - Add STM32 DSI controller driver dw_hdmi: - Add support for Rockchip RK3399 - HDMI CEC support atmel-hlcdc: - Add 8-bit color support vc4: - Atomic fixes - New ioctl to attach a label to a buffer object - HDMI CEC support - Allow userspace to dictate rendering order on submit ioctl" * tag 'drm-for-v4.14' of git://people.freedesktop.org/~airlied/linux: (1074 commits) drm/syncobj: Add a signal ioctl (v3) drm/syncobj: Add a reset ioctl (v3) drm/syncobj: Add a syncobj_array_find helper drm/syncobj: Allow wait for submit and signal behavior (v5) drm/syncobj: Add a CREATE_SIGNALED flag drm/syncobj: Add a callback mechanism for replace_fence (v3) drm/syncobj: add sync obj wait interface. (v8) i915: Use drm_syncobj_fence_get drm/syncobj: Add a race-free drm_syncobj_fence_get helper (v2) drm/syncobj: Rename fence_get to find_fence drm: kirin: Add mode_valid logic to avoid mode clocks we can't generate drm/vmwgfx: Bump the version for fence FD support drm/vmwgfx: Add export fence to file descriptor support drm/vmwgfx: Add support for imported Fence File Descriptor drm/vmwgfx: Prepare to support fence fd drm/vmwgfx: Fix incorrect command header offset at restart drm/vmwgfx: Support the NOP_ERROR command drm/vmwgfx: Restart command buffers after errors drm/vmwgfx: Move irq bottom half processing to threads drm/vmwgfx: Don't use drm_irq_[un]install ...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c77
1 files changed, 73 insertions, 4 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index a2c59a08b2bd..26e900627971 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -28,6 +28,8 @@
struct amdgpu_vram_mgr {
struct drm_mm mm;
spinlock_t lock;
+ atomic64_t usage;
+ atomic64_t vis_usage;
};
/**
@@ -79,6 +81,27 @@ static int amdgpu_vram_mgr_fini(struct ttm_mem_type_manager *man)
}
/**
+ * amdgpu_vram_mgr_vis_size - Calculate visible node size
+ *
+ * @adev: amdgpu device structure
+ * @node: MM node structure
+ *
+ * Calculate how many bytes of the MM node are inside visible VRAM
+ */
+static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
+ struct drm_mm_node *node)
+{
+ uint64_t start = node->start << PAGE_SHIFT;
+ uint64_t end = (node->size + node->start) << PAGE_SHIFT;
+
+ if (start >= adev->mc.visible_vram_size)
+ return 0;
+
+ return (end > adev->mc.visible_vram_size ?
+ adev->mc.visible_vram_size : end) - start;
+}
+
+/**
* amdgpu_vram_mgr_new - allocate new ranges
*
* @man: TTM memory type manager
@@ -93,11 +116,13 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
const struct ttm_place *place,
struct ttm_mem_reg *mem)
{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
struct amdgpu_vram_mgr *mgr = man->priv;
struct drm_mm *mm = &mgr->mm;
struct drm_mm_node *nodes;
enum drm_mm_insert_mode mode;
unsigned long lpfn, num_nodes, pages_per_node, pages_left;
+ uint64_t usage = 0, vis_usage = 0;
unsigned i;
int r;
@@ -142,6 +167,9 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
if (unlikely(r))
goto error;
+ usage += nodes[i].size << PAGE_SHIFT;
+ vis_usage += amdgpu_vram_mgr_vis_size(adev, &nodes[i]);
+
/* Calculate a virtual BO start address to easily check if
* everything is CPU accessible.
*/
@@ -155,6 +183,9 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
}
spin_unlock(&mgr->lock);
+ atomic64_add(usage, &mgr->usage);
+ atomic64_add(vis_usage, &mgr->vis_usage);
+
mem->mm_node = nodes;
return 0;
@@ -181,8 +212,10 @@ error:
static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man,
struct ttm_mem_reg *mem)
{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
struct amdgpu_vram_mgr *mgr = man->priv;
struct drm_mm_node *nodes = mem->mm_node;
+ uint64_t usage = 0, vis_usage = 0;
unsigned pages = mem->num_pages;
if (!mem->mm_node)
@@ -192,31 +225,67 @@ static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man,
while (pages) {
pages -= nodes->size;
drm_mm_remove_node(nodes);
+ usage += nodes->size << PAGE_SHIFT;
+ vis_usage += amdgpu_vram_mgr_vis_size(adev, nodes);
++nodes;
}
spin_unlock(&mgr->lock);
+ atomic64_sub(usage, &mgr->usage);
+ atomic64_sub(vis_usage, &mgr->vis_usage);
+
kfree(mem->mm_node);
mem->mm_node = NULL;
}
/**
+ * amdgpu_vram_mgr_usage - how many bytes are used in this domain
+ *
+ * @man: TTM memory type manager
+ *
+ * Returns how many bytes are used in this domain.
+ */
+uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man)
+{
+ struct amdgpu_vram_mgr *mgr = man->priv;
+
+ return atomic64_read(&mgr->usage);
+}
+
+/**
+ * amdgpu_vram_mgr_vis_usage - how many bytes are used in the visible part
+ *
+ * @man: TTM memory type manager
+ *
+ * Returns how many bytes are used in the visible part of VRAM
+ */
+uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man)
+{
+ struct amdgpu_vram_mgr *mgr = man->priv;
+
+ return atomic64_read(&mgr->vis_usage);
+}
+
+/**
* amdgpu_vram_mgr_debug - dump VRAM table
*
* @man: TTM memory type manager
- * @prefix: text prefix
+ * @printer: DRM printer to use
*
* Dump the table content using printk.
*/
static void amdgpu_vram_mgr_debug(struct ttm_mem_type_manager *man,
- const char *prefix)
+ struct drm_printer *printer)
{
struct amdgpu_vram_mgr *mgr = man->priv;
- struct drm_printer p = drm_debug_printer(prefix);
spin_lock(&mgr->lock);
- drm_mm_print(&mgr->mm, &p);
+ drm_mm_print(&mgr->mm, printer);
spin_unlock(&mgr->lock);
+
+ drm_printf(printer, "man size:%llu pages, ram usage:%lluMB, vis usage:%lluMB\n",
+ man->size, amdgpu_vram_mgr_usage(man) >> 20,
+ amdgpu_vram_mgr_vis_usage(man) >> 20);
}
const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func = {