[PATCH v2] drm/amdgpu: Fix KFD oversubscription by tracking queues correctly

[Jay Cornwall]

The number of compute queues available to the KFD was erroneously
calculated as 64. Only the first MEC can execute compute queues and
it has 32 queue slots.

This caused the oversubscription limit to be calculated incorrectly,
leading to a missing chained runlist command at the end of an
oversubscribed runlist.

v2: Remove unused num_mec field to avoid duplicate logic

Change-Id: Ic4a139c04b8a6d025fbb831a0a67e98728bfe461
Signed-off-by: Jay Cornwall <Jay.Cornwall at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c            | 3 +--
 drivers/gpu/drm/amd/amdkfd/kfd_device.c               | 4 ----
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 7 -------
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h       | 3 ---
 drivers/gpu/drm/radeon/radeon_kfd.c                   | 1 -
 5 files changed, 1 insertion(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 7060daf..8c710f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -116,7 +116,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 	if (adev->kfd) {
 		struct kgd2kfd_shared_resources gpu_resources = {
 			.compute_vmid_bitmap = global_compute_vmid_bitmap,
-			.num_mec = adev->gfx.mec.num_mec,
 			.num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec,
 			.num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe,
 			.gpuvm_size = (uint64_t)amdgpu_vm_size << 30
@@ -140,7 +139,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 		/* According to linux/bitmap.h we shouldn't use bitmap_clear if
 		 * nbits is not compile time constant
 		 */
-		last_valid_bit = adev->gfx.mec.num_mec
+		last_valid_bit = 1 /* only first MEC can have compute queues */
 				* adev->gfx.mec.num_pipe_per_mec
 				* adev->gfx.mec.num_queue_per_pipe;
 		for (i = last_valid_bit; i < KGD_MAX_QUEUES; ++i)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 1cf00d4..95f9396 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -494,10 +494,6 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 	} else
 		kfd->max_proc_per_quantum = hws_max_conc_proc;
 
-	/* We only use the first MEC */
-	if (kfd->shared_resources.num_mec > 1)
-		kfd->shared_resources.num_mec = 1;
-
 	/* calculate max size of mqds needed for queues */
 	size = max_num_of_queues_per_device *
 			kfd->device_info->mqd_size_aligned;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 7607989..306144f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -82,13 +82,6 @@ static bool is_pipe_enabled(struct device_queue_manager *dqm, int mec, int pipe)
 	return false;
 }
 
-unsigned int get_mec_num(struct device_queue_manager *dqm)
-{
-	BUG_ON(!dqm || !dqm->dev);
-
-	return dqm->dev->shared_resources.num_mec;
-}
-
 unsigned int get_queues_num(struct device_queue_manager *dqm)
 {
 	BUG_ON(!dqm || !dqm->dev);
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index a4d2fee..10794b3 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -107,9 +107,6 @@ struct kgd2kfd_shared_resources {
 	/* Bit n == 1 means VMID n is available for KFD. */
 	unsigned int compute_vmid_bitmap;
 
-	/* number of mec available from the hardware */
-	uint32_t num_mec;
-
 	/* number of pipes per mec */
 	uint32_t num_pipe_per_mec;
 
diff --git a/drivers/gpu/drm/radeon/radeon_kfd.c b/drivers/gpu/drm/radeon/radeon_kfd.c
index 719ea51..8f8c7c1 100644
--- a/drivers/gpu/drm/radeon/radeon_kfd.c
+++ b/drivers/gpu/drm/radeon/radeon_kfd.c
@@ -251,7 +251,6 @@ void radeon_kfd_device_init(struct radeon_device *rdev)
 	if (rdev->kfd) {
 		struct kgd2kfd_shared_resources gpu_resources = {
 			.compute_vmid_bitmap = 0xFF00,
-			.num_mec = 1,
 			.num_pipe_per_mec = 4,
 			.num_queue_per_pipe = 8,
 			.gpuvm_size = (uint64_t)radeon_vm_size << 30
-- 
2.7.4