Commit 1a6bbc4d authored by Dave Airlie's avatar Dave Airlie
Browse files

Merge tag 'drm-xe-fixes-2024-11-08' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes 



Driver Changes:
- Fix ccs_mode setting for Xe2 and later (Balasubramani)
- Synchronize ccs_mode setting with client creation (Balasubramani)
- Apply scheduling WA for LNL in additional places as needed
  (Nirmoy)
- Fix leak and lock handling in error paths of xe_exec ioctl
  (Matthew Brost)
- Fix GGTT allocation leak leading to eventual crash in SR-IOV
  (Michal Wajdeczko)
- Move run_ticks update out of job handling to avoid synchronization
  with reader (Lucas)

Signed-off-by: default avatarDave Airlie <airlied@redhat.com>

From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/4ffcebtluaaaohquxfyf5babpihmtscxwad3jjmt5nggwh2xpm@ztw67ucywttg
parents 9b984a71 514447a1

drivers/gpu/drm/xe/regs/xe_gt_regs.h

+1 −1
Original line number Diff line number Diff line
@@ -517,7 +517,7 @@ 
 *   [4-6]     RSVD

 *   [7]       Disabled

 */

#define CCS_MODE				XE_REG(0x14804)

#define CCS_MODE				XE_REG(0x14804, XE_REG_OPTION_MASKED)

#define   CCS_MODE_CSLICE_0_3_MASK		REG_GENMASK(11, 0) /* 3 bits per cslice */

#define   CCS_MODE_CSLICE_MASK			0x7 /* CCS0-3 + rsvd */

#define   CCS_MODE_CSLICE_WIDTH			ilog2(CCS_MODE_CSLICE_MASK + 1)

drivers/gpu/drm/xe/xe_device.c

+0 −10
Original line number Diff line number Diff line
@@ -87,10 +87,6 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file) 
	mutex_init(&xef->exec_queue.lock);

	xa_init_flags(&xef->exec_queue.xa, XA_FLAGS_ALLOC1);



	spin_lock(&xe->clients.lock);

	xe->clients.count++;

	spin_unlock(&xe->clients.lock);



	file->driver_priv = xef;

	kref_init(&xef->refcount);
@@ -107,17 +103,12 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file) 
static void xe_file_destroy(struct kref *ref)

{

	struct xe_file *xef = container_of(ref, struct xe_file, refcount);

	struct xe_device *xe = xef->xe;



	xa_destroy(&xef->exec_queue.xa);

	mutex_destroy(&xef->exec_queue.lock);

	xa_destroy(&xef->vm.xa);

	mutex_destroy(&xef->vm.lock);



	spin_lock(&xe->clients.lock);

	xe->clients.count--;

	spin_unlock(&xe->clients.lock);



	xe_drm_client_put(xef->client);

	kfree(xef->process_name);

	kfree(xef);
@@ -333,7 +324,6 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, 
	xe->info.force_execlist = xe_modparam.force_execlist;



	spin_lock_init(&xe->irq.lock);

	spin_lock_init(&xe->clients.lock);



	init_waitqueue_head(&xe->ufence_wq);

drivers/gpu/drm/xe/xe_device.h

+14 −0
Original line number Diff line number Diff line
@@ -178,4 +178,18 @@ void xe_device_declare_wedged(struct xe_device *xe); 
struct xe_file *xe_file_get(struct xe_file *xef);

void xe_file_put(struct xe_file *xef);



/*

 * Occasionally it is seen that the G2H worker starts running after a delay of more than

 * a second even after being queued and activated by the Linux workqueue subsystem. This

 * leads to G2H timeout error. The root cause of issue lies with scheduling latency of

 * Lunarlake Hybrid CPU. Issue disappears if we disable Lunarlake atom cores from BIOS

 * and this is beyond xe kmd.

 *

 * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU.

 */

#define LNL_FLUSH_WORKQUEUE(wq__) \

	flush_workqueue(wq__)

#define LNL_FLUSH_WORK(wrk__) \

	flush_work(wrk__)



#endif

drivers/gpu/drm/xe/xe_device_types.h

+0 −9
Original line number Diff line number Diff line
@@ -353,15 +353,6 @@ struct xe_device { 
		struct workqueue_struct *wq;

	} sriov;



	/** @clients: drm clients info */

	struct {

		/** @clients.lock: Protects drm clients info */

		spinlock_t lock;



		/** @clients.count: number of drm clients */

		u64 count;

	} clients;



	/** @usm: unified memory state */

	struct {

		/** @usm.asid: convert a ASID to VM */

drivers/gpu/drm/xe/xe_exec.c

+9 −4
Original line number Diff line number Diff line
@@ -132,12 +132,16 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) 
	if (XE_IOCTL_DBG(xe, !q))

		return -ENOENT;



	if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_VM))

		return -EINVAL;

	if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_VM)) {

		err = -EINVAL;

		goto err_exec_queue;

	}



	if (XE_IOCTL_DBG(xe, args->num_batch_buffer &&

			 q->width != args->num_batch_buffer))

		return -EINVAL;

			 q->width != args->num_batch_buffer)) {

		err = -EINVAL;

		goto err_exec_queue;

	}



	if (XE_IOCTL_DBG(xe, q->ops->reset_status(q))) {

		err = -ECANCELED;
@@ -220,6 +224,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) 
			fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm);

			if (IS_ERR(fence)) {

				err = PTR_ERR(fence);

				xe_vm_unlock(vm);

				goto err_unlock_list;

			}

			for (i = 0; i < num_syncs; i++)