[PATCH 14/14] drm/amdgpu: introduce doorbell bo in kernel

[Shashank Sharma <shashank.sharma@amd.com>]

From: Alex Deucher <alexander.deucher@amd.com>

This patch does the following:
- Removes doorbell ptr from adev.
- Moves doorbell.num_doorbells into mman.num_doorbells.
- Introduces a kernel bo for doorbell management in form of mman.doorbell_kernel_bo.
  This bo holds the doorbell space now.
- Introduces mman.doorbell_bo_size: to save total doorbell memory size.
- Also introduces mman.doorbell_va to save CPU address of doorbell BO
  mapping. This ptr will be used now for doorbell read/write from doorbell BAR.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Shashank Sharma <shashank.sharma@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h          |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c   |  5 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c   | 16 ++++++-------
 drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h |  4 ----
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c      | 24 ++++++++++++++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h      |  6 +++++
 6 files changed, 35 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index e1c1a360614e..dd3875ae1ad3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -834,7 +834,6 @@ struct amdgpu_device {
 	spinlock_t audio_endpt_idx_lock;
 	amdgpu_block_rreg_t		audio_endpt_rreg;
 	amdgpu_block_wreg_t		audio_endpt_wreg;
-	struct amdgpu_doorbell		doorbell;
 
 	/* clock/pll info */
 	struct amdgpu_clock            clock;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 28076da2258f..aea943e337df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -109,11 +109,10 @@ static void amdgpu_doorbell_get_kfd_info(struct amdgpu_device *adev,
 		*aperture_base = adev->gmc.doorbell_aper_base;
 		*aperture_size = 0;
 		*start_offset = 0;
-	} else if (adev->gmc.doorbell_aper_size > adev->doorbell.num_doorbells *
-						sizeof(u32)) {
+	} else if (adev->gmc.doorbell_aper_size > adev->mman.doorbell_kernel_bo_size) {
 		*aperture_base = adev->gmc.doorbell_aper_base;
 		*aperture_size = adev->gmc.doorbell_aper_size;
-		*start_offset = adev->doorbell.num_doorbells * sizeof(u32);
+		*start_offset = adev->mman.doorbell_kernel_bo_size;
 	} else {
 		*aperture_base = 0;
 		*aperture_size = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7c21ffe63ebc..9c3ce1ae66ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -593,8 +593,8 @@ u32 amdgpu_mm_rdoorbell(struct amdgpu_device *adev, u32 index)
 	if (amdgpu_device_skip_hw_access(adev))
 		return 0;
 
-	if (index < adev->doorbell.num_doorbells) {
-		return readl(adev->mman.doorbell_aper_base_kaddr + index);
+	if (index < adev->mman.num_doorbells) {
+		return readl(adev->mman.doorbell_va + index);
 	} else {
 		DRM_ERROR("reading beyond doorbell aperture: 0x%08x!\n", index);
 		return 0;
@@ -616,8 +616,8 @@ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v)
 	if (amdgpu_device_skip_hw_access(adev))
 		return;
 
-	if (index < adev->doorbell.num_doorbells) {
-		writel(v, adev->mman.doorbell_aper_base_kaddr + index);
+	if (index < adev->mman.num_doorbells) {
+		writel(v, adev->mman.doorbell_va + index);
 	} else {
 		DRM_ERROR("writing beyond doorbell aperture: 0x%08x!\n", index);
 	}
@@ -637,8 +637,8 @@ u64 amdgpu_mm_rdoorbell64(struct amdgpu_device *adev, u32 index)
 	if (amdgpu_device_skip_hw_access(adev))
 		return 0;
 
-	if (index < adev->doorbell.num_doorbells) {
-		return atomic64_read((atomic64_t *)(adev->mman.doorbell_aper_base_kaddr + index));
+	if (index < adev->mman.num_doorbells) {
+		return atomic64_read((atomic64_t *)(adev->mman.doorbell_va + index));
 	} else {
 		DRM_ERROR("reading beyond doorbell aperture: 0x%08x!\n", index);
 		return 0;
@@ -660,8 +660,8 @@ void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v)
 	if (amdgpu_device_skip_hw_access(adev))
 		return;
 
-	if (index < adev->doorbell.num_doorbells) {
-		atomic64_set((atomic64_t *)(adev->mman.doorbell_aper_base_kaddr + index), v);
+	if (index < adev->mman.num_doorbells) {
+		atomic64_set((atomic64_t *)(adev->mman.doorbell_va + index), v);
 	} else {
 		DRM_ERROR("writing beyond doorbell aperture: 0x%08x!\n", index);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h
index 464be28da4fb..97298a98561f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h
@@ -24,10 +24,6 @@
 /*
  * GPU doorbell structures, functions & helpers
  */
-struct amdgpu_doorbell {
-	u32			num_doorbells;	/* Number of doorbells actually reserved for amdgpu. */
-};
-
 /* Reserved doorbells for amdgpu (including multimedia).
  * KFD can use all the rest in the 2M doorbell bar.
  * For asic before vega10, doorbell is 32-bit, so the
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index e38720b91958..8f0537f16cc8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1742,7 +1742,7 @@ static int amdgpu_ttm_doorbell_init(struct amdgpu_device *adev)
 	if (adev->asic_type < CHIP_BONAIRE) {
 		adev->gmc.doorbell_aper_base = 0;
 		adev->gmc.doorbell_aper_size = 0;
-		adev->doorbell.num_doorbells = 0;
+		adev->mman.num_doorbells = 0;
 		adev->mman.doorbell_aper_base_kaddr = NULL;
 		return 0;
 	}
@@ -1759,13 +1759,13 @@ static int amdgpu_ttm_doorbell_init(struct amdgpu_device *adev)
                                                     adev->gmc.doorbell_aper_size);
 
 	if (adev->enable_mes) {
-		adev->doorbell.num_doorbells =
+		adev->mman.num_doorbells =
 			adev->gmc.doorbell_aper_size / sizeof(u32);
 	} else {
-		adev->doorbell.num_doorbells =
+		adev->mman.num_doorbells =
 			min_t(u32, adev->gmc.doorbell_aper_size / sizeof(u32),
 			      adev->doorbell_index.max_assignment+1);
-		if (adev->doorbell.num_doorbells == 0)
+		if (adev->mman.num_doorbells == 0)
 			return -EINVAL;
 
 		/* For Vega, reserve and map two pages on doorbell BAR since SDMA
@@ -1775,7 +1775,7 @@ static int amdgpu_ttm_doorbell_init(struct amdgpu_device *adev)
 		 * the max num_doorbells should + 1 page (0x400 in dword)
 		 */
 		if (adev->asic_type >= CHIP_VEGA10)
-			adev->doorbell.num_doorbells += 0x400;
+			adev->mman.num_doorbells += 0x400;
 	}
 
 	return 0;
@@ -1901,6 +1901,18 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
+	adev->mman.doorbell_kernel_bo_size = adev->mman.num_doorbells * sizeof(u32);
+	r = amdgpu_bo_create_kernel_at(adev,
+					  0,
+					  adev->mman.doorbell_kernel_bo_size,
+					  AMDGPU_GEM_DOMAIN_DOORBELL,
+					  &adev->mman.doorbell_kernel_bo,
+					  &adev->mman.doorbell_va);
+	if (r) {
+		DRM_ERROR("Failed to create doorbell BO\n");
+		return r;
+	}
+
 	DRM_INFO("amdgpu: %uM of VRAM memory ready\n",
 		 (unsigned) (adev->gmc.real_vram_size / (1024 * 1024)));
 
@@ -1992,6 +2004,8 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
 				      NULL, NULL);
 	amdgpu_bo_free_kernel(&adev->mman.sdma_access_bo, NULL,
 					&adev->mman.sdma_access_ptr);
+	amdgpu_bo_free_kernel(&adev->mman.doorbell_kernel_bo,
+			      NULL, &adev->mman.doorbell_va);
 	amdgpu_ttm_fw_reserve_vram_fini(adev);
 	amdgpu_ttm_drv_reserve_vram_fini(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index a492de079c2e..405294ca9834 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -98,6 +98,12 @@ struct amdgpu_mman {
 	/* PAGE_SIZE'd BO for process memory r/w over SDMA. */
 	struct amdgpu_bo	*sdma_access_bo;
 	void			*sdma_access_ptr;
+
+	/* doorbells reserved for the kernel driver */
+	u32			num_doorbells;	/* Number of doorbells actually reserved for amdgpu. */
+	uint64_t		doorbell_kernel_bo_size;
+	struct amdgpu_bo	*doorbell_kernel_bo;
+	void			*doorbell_va;
 };
 
 struct amdgpu_copy_mem {
-- 
2.34.1