[PATCH] drm/amdkfd: Allocate doorbells only when needed

[Felix Kuehling]

Only allocate doorbells when the first queue is created on a GPU or the
doorbells need to be mapped into CPU or GPU virtual address space. This
avoids allocating doorbells unnecessarily and can allow more processes
to use KFD on multi-GPU systems.

Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c  | 13 +++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c |  9 +++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_process.c  |  5 -----
 3 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 2b3d8bc8f0aa..907f4711abce 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -327,6 +327,12 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 		goto err_bind_process;
 	}
 
+	if (!pdd->doorbell_index &&
+	    kfd_alloc_process_doorbells(dev, &pdd->doorbell_index) < 0) {
+		err = -ENOMEM;
+		goto err_alloc_doorbells;
+	}
+
 	/* Starting with GFX11, wptr BOs must be mapped to GART for MES to determine work
 	 * on unmapped queues for usermode queue oversubscription (no aggregated doorbell)
 	 */
@@ -404,6 +410,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 	if (wptr_bo)
 		amdgpu_amdkfd_free_gtt_mem(dev->adev, wptr_bo);
 err_wptr_map_gart:
+err_alloc_doorbells:
 err_bind_process:
 err_pdd:
 	mutex_unlock(&p->mutex);
@@ -1092,6 +1099,10 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 			goto err_unlock;
 		}
 		offset = kfd_get_process_doorbells(pdd);
+		if (!offset) {
+			err = -ENOMEM;
+			goto err_unlock;
+		}
 	} else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) {
 		if (args->size != PAGE_SIZE) {
 			err = -EINVAL;
@@ -2173,6 +2184,8 @@ static int criu_restore_memory_of_gpu(struct kfd_process_device *pdd,
 			return -EINVAL;
 
 		offset = kfd_get_process_doorbells(pdd);
+		if (!offset)
+			return -ENOMEM;
 	} else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) {
 		/* MMIO BOs need remapped bus address */
 		if (bo_bucket->size != PAGE_SIZE) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index cb3d2ccc5100..b33798f89ef0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -157,6 +157,8 @@ int kfd_doorbell_mmap(struct kfd_dev *dev, struct kfd_process *process,
 
 	/* Calculate physical address of doorbell */
 	address = kfd_get_process_doorbells(pdd);
+	if (!address)
+		return -ENOMEM;
 	vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE |
 				VM_DONTDUMP | VM_PFNMAP;
 
@@ -275,6 +277,13 @@ uint64_t kfd_get_number_elems(struct kfd_dev *kfd)
 
 phys_addr_t kfd_get_process_doorbells(struct kfd_process_device *pdd)
 {
+	if (!pdd->doorbell_index) {
+		int r = kfd_alloc_process_doorbells(pdd->dev,
+						    &pdd->doorbell_index);
+		if (r)
+			return 0;
+	}
+
 	return pdd->dev->doorbell_base +
 		pdd->doorbell_index * kfd_doorbell_process_slice(pdd->dev);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 6c83a519b3a1..951b63677248 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1499,11 +1499,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 	if (!pdd)
 		return NULL;
 
-	if (kfd_alloc_process_doorbells(dev, &pdd->doorbell_index) < 0) {
-		pr_err("Failed to alloc doorbell for pdd\n");
-		goto err_free_pdd;
-	}
-
 	if (init_doorbell_bitmap(&pdd->qpd, dev)) {
 		pr_err("Failed to init doorbell for process\n");
 		goto err_free_pdd;
-- 
2.32.0