29 files changed, 315 insertions, 188 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 633532a2e7ec..25bc47f3c1cf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include "kfd_priv.h"
 #include "kfd_device_queue_manager.h"
+#include "kfd_pm4_headers.h"
 
 #define MQD_SIZE_ALIGNED 768
 
@@ -169,9 +170,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
         kfd->shared_resources = *gpu_resources;
 
         /* calculate max size of mqds needed for queues */
-        size = max_num_of_processes *
-                max_num_of_queues_per_process *
-                kfd->device_info->mqd_size_aligned;
+        size = max_num_of_queues_per_device *
+                        kfd->device_info->mqd_size_aligned;
 
         /* add another 512KB for all other allocations on gart */
         size += 512 * 1024;
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 30c8fda9622e..0d8694f015c1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -183,6 +183,13 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 
         mutex_lock(&dqm->lock);
 
+        if (dqm->total_queue_count >= max_num_of_queues_per_device) {
+                pr_warn("amdkfd: Can't create new usermode queue because %d queues were already created\n",
+                                dqm->total_queue_count);
+                mutex_unlock(&dqm->lock);
+                return -EPERM;
+        }
+
         if (list_empty(&qpd->queues_list)) {
                 retval = allocate_vmid(dqm, qpd, q);
                 if (retval != 0) {
@@ -207,6 +214,14 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
         list_add(&q->list, &qpd->queues_list);
         dqm->queue_count++;
 
+        /*
+         * Unconditionally increment this counter, regardless of the queue's
+         * type or whether the queue is active.
+         */
+        dqm->total_queue_count++;
+        pr_debug("Total of %d queues are accountable so far\n",
+                        dqm->total_queue_count);
+
         mutex_unlock(&dqm->lock);
         return 0;
 }
@@ -326,6 +341,15 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
         if (list_empty(&qpd->queues_list))
                 deallocate_vmid(dqm, qpd, q);
         dqm->queue_count--;
+
+        /*
+         * Unconditionally decrement this counter, regardless of the queue's
+         * type
+         */
+        dqm->total_queue_count--;
+        pr_debug("Total of %d queues are accountable so far\n",
+                        dqm->total_queue_count);
+
 out:
         mutex_unlock(&dqm->lock);
         return retval;
@@ -541,10 +565,14 @@ static int init_pipelines(struct device_queue_manager *dqm,
 
         for (i = 0; i < pipes_num; i++) {
                 inx = i + first_pipe;
+                /*
+                 * HPD buffer on GTT is allocated by amdkfd, no need to waste
+                 * space in GTT for pipelines we don't initialize
+                 */
                 pipe_hpd_addr = dqm->pipelines_addr + i * CIK_HPD_EOP_BYTES;
                 pr_debug("kfd: pipeline address %llX\n", pipe_hpd_addr);
                 /* = log2(bytes/4)-1 */
-                kfd2kgd->init_pipeline(dqm->dev->kgd, i,
+                kfd2kgd->init_pipeline(dqm->dev->kgd, inx,
                                 CIK_HPD_EOP_BYTES_LOG2 - 3, pipe_hpd_addr);
         }
 
@@ -560,7 +588,7 @@ static int init_scheduler(struct device_queue_manager *dqm)
 
         pr_debug("kfd: In %s\n", __func__);
 
-        retval = init_pipelines(dqm, get_pipes_num(dqm), KFD_DQM_FIRST_PIPE);
+        retval = init_pipelines(dqm, get_pipes_num(dqm), get_first_pipe(dqm));
         if (retval != 0)
                 return retval;
 
@@ -752,6 +780,21 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
         pr_debug("kfd: In func %s\n", __func__);
 
         mutex_lock(&dqm->lock);
+        if (dqm->total_queue_count >= max_num_of_queues_per_device) {
+                pr_warn("amdkfd: Can't create new kernel queue because %d queues were already created\n",
+                                dqm->total_queue_count);
+                mutex_unlock(&dqm->lock);
+                return -EPERM;
+        }
+
+        /*
+         * Unconditionally increment this counter, regardless of the queue's
+         * type or whether the queue is active.
+         */
+        dqm->total_queue_count++;
+        pr_debug("Total of %d queues are accountable so far\n",
+                        dqm->total_queue_count);
+
         list_add(&kq->list, &qpd->priv_queue_list);
         dqm->queue_count++;
         qpd->is_debug = true;
@@ -775,6 +818,13 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,