[PATCH 24/25] drm/amdkfd: Kmap event page for dGPUs

[Felix Kuehling]

The events page must be accessible in user mode by the GPU and CPU
as well as in kernel mode by the CPU. On dGPUs user mode virtual
addresses are managed by the Thunk's GPU memory allocation code.
Therefore we can't allocate the memory in kernel mode like we do
on APUs. But KFD still needs to map the memory for kernel access.
To facilitate this, the Thunk provides the buffer handle of the
events page to KFD when creating the first event.

Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 56 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_events.c  | 31 ++++++++++++++++--
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h    |  2 ++
 3 files changed, 87 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 2f480c5..ec48010 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -922,6 +922,58 @@ static int kfd_ioctl_create_event(struct file *filp, struct kfd_process *p,
 	struct kfd_ioctl_create_event_args *args = data;
 	int err;
 
+	/* For dGPUs the event page is allocated in user mode. The
+	 * handle is passed to KFD with the first call to this IOCTL
+	 * through the event_page_offset field.
+	 */
+	if (args->event_page_offset) {
+		struct kfd_dev *kfd;
+		struct kfd_process_device *pdd;
+		void *mem, *kern_addr;
+		uint64_t size;
+
+		if (p->signal_page) {
+			pr_err("Event page is already set\n");
+			return -EINVAL;
+		}
+
+		kfd = kfd_device_by_id(GET_GPU_ID(args->event_page_offset));
+		if (!kfd) {
+			pr_err("Getting device by id failed in %s\n", __func__);
+			return -EINVAL;
+		}
+
+		mutex_lock(&p->mutex);
+		pdd = kfd_bind_process_to_device(kfd, p);
+		if (IS_ERR(pdd)) {
+			err = PTR_ERR(pdd);
+			goto out_unlock;
+		}
+
+		mem = kfd_process_device_translate_handle(pdd,
+				GET_IDR_HANDLE(args->event_page_offset));
+		if (!mem) {
+			pr_err("Can't find BO, offset is 0x%llx\n",
+			       args->event_page_offset);
+			err = -EINVAL;
+			goto out_unlock;
+		}
+		mutex_unlock(&p->mutex);
+
+		err = kfd->kfd2kgd->map_gtt_bo_to_kernel(kfd->kgd,
+						mem, &kern_addr, &size);
+		if (err) {
+			pr_err("Failed to map event page to kernel\n");
+			return err;
+		}
+
+		err = kfd_event_page_set(p, kern_addr, size);
+		if (err) {
+			pr_err("Failed to set event page\n");
+			return err;
+		}
+	}
+
 	err = kfd_event_create(filp, p, args->event_type,
 				args->auto_reset != 0, args->node_id,
 				&args->event_id, &args->event_trigger_data,
@@ -929,6 +981,10 @@ static int kfd_ioctl_create_event(struct file *filp, struct kfd_process *p,
 				&args->event_slot_index);
 
 	return err;
+
+out_unlock:
+	mutex_unlock(&p->mutex);
+	return err;
 }
 
 static int kfd_ioctl_destroy_event(struct file *filp, struct kfd_process *p,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 6fb9c0d..4890a90 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -52,6 +52,7 @@ struct kfd_event_waiter {
 struct kfd_signal_page {
 	uint64_t *kernel_address;
 	uint64_t __user *user_address;
+	bool need_to_free_pages;
 };
 
 
@@ -79,6 +80,7 @@ static struct kfd_signal_page *allocate_signal_page(struct kfd_process *p)
 	       KFD_SIGNAL_EVENT_LIMIT * 8);
 
 	page->kernel_address = backing_store;
+	page->need_to_free_pages = true;
 	pr_debug("Allocated new event signal page at %p, for process %p\n",
 			page, p);
 
@@ -269,8 +271,9 @@ static void shutdown_signal_page(struct kfd_process *p)
 	struct kfd_signal_page *page = p->signal_page;
 
 	if (page) {
-		free_pages((unsigned long)page->kernel_address,
-				get_order(KFD_SIGNAL_EVENT_LIMIT * 8));
+		if (page->need_to_free_pages)
+			free_pages((unsigned long)page->kernel_address,
+				   get_order(KFD_SIGNAL_EVENT_LIMIT * 8));
 		kfree(page);
 	}
 }
@@ -292,6 +295,30 @@ static bool event_can_be_cpu_signaled(const struct kfd_event *ev)
 	return ev->type == KFD_EVENT_TYPE_SIGNAL;
 }
 
+int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
+		       uint64_t size)
+{
+	struct kfd_signal_page *page;
+
+	if (p->signal_page)
+		return -EBUSY;
+
+	page = kzalloc(sizeof(*page), GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	/* Initialize all events to unsignaled */
+	memset(kernel_address, (uint8_t) UNSIGNALED_EVENT_SLOT,
+	       KFD_SIGNAL_EVENT_LIMIT * 8);
+
+	page->kernel_address = kernel_address;
+
+	p->signal_page = page;
+	p->signal_mapped_size = size;
+
+	return 0;
+}
+
 int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint32_t event_type, bool auto_reset, uint32_t node_id,
 		     uint32_t *event_id, uint32_t *event_trigger_data,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 449822b..afe381f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -863,6 +863,8 @@ void kfd_signal_iommu_event(struct kfd_dev *dev,
 void kfd_signal_hw_exception_event(unsigned int pasid);
 int kfd_set_event(struct kfd_process *p, uint32_t event_id);
 int kfd_reset_event(struct kfd_process *p, uint32_t event_id);
+int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
+		       uint64_t size);
 int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint32_t event_type, bool auto_reset, uint32_t node_id,
 		     uint32_t *event_id, uint32_t *event_trigger_data,
-- 
2.7.4