Merge branch 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux into drm-next

First feature request for 4.16.  Highlights:
- RV and Vega header cleanups
- TTM operation context support
- 48 bit GPUVM fixes for Vega/RV
- More smatch fixes
- ECC support for vega10
- Resizeable BAR support
- Multi-display sync support in DC
- SR-IOV fixes
- Various scheduler improvements
- GPU reset fixes and vram lost tracking
- Clean up DC/powerplay interfaces
- DCN display fixes
- Various DC fixes

* 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux: (291 commits)
  drm/radeon: Use drm_fb_helper_lastclose() and _poll_changed()
  drm/amdgpu: Use drm_fb_helper_lastclose() and _poll_changed()
  drm/amd/display: Use drm_fb_helper_poll_changed()
  drm/ttm: swap consecutive allocated pooled pages v4
  drm/amdgpu: fix amdgpu_sync_resv v2
  drm/ttm: swap consecutive allocated cached pages v3
  drm/amd/amdgpu: set gtt size according to system memory size only
  drm/amdgpu: Get rid of dep_sync as a seperate object.
  drm/amdgpu: allow specifying vm_block_size for multi level PDs v2
  drm/amdgpu: move validation of the VM size into the VM code
  drm/amdgpu: allow non pot VM size values
  drm/amdgpu: choose number of VM levels based on VM size
  drm/amdgpu: unify VM size handling of Vega10 with older generation
  drm/amdgpu: fix amdgpu_vm_num_entries
  drm/amdgpu: fix VM PD addr shift
  drm/amdgpu: correct vce4.0 fw config for SRIOV (V2)
  drm/amd/display: Don't call dm_log_to_buffer directly in dc_conn_log
  drm/amd/display: Add dm_logger_append_va API
  drm/ttm: Use a static string instead of an array of char *
  drm/amd/display: remove usage of legacy_cursor_update
  ...

1 files changed, 18 insertions, 9 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index b4906d2f30d3..ad9054e3903c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -22,11 +22,11 @@
  */
 
 #include "amdgpu.h"
-#include "vega10/soc15ip.h"
-#include "vega10/NBIO/nbio_6_1_offset.h"
-#include "vega10/NBIO/nbio_6_1_sh_mask.h"
-#include "vega10/GC/gc_9_0_offset.h"
-#include "vega10/GC/gc_9_0_sh_mask.h"
+#include "soc15ip.h"
+#include "nbio/nbio_6_1_offset.h"
+#include "nbio/nbio_6_1_sh_mask.h"
+#include "gc/gc_9_0_offset.h"
+#include "gc/gc_9_0_sh_mask.h"
 #include "soc15.h"
 #include "vega10_ih.h"
 #include "soc15_common.h"
@@ -254,7 +254,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	}
 
 	/* Trigger recovery due to world switch failure */
-	amdgpu_sriov_gpu_reset(adev, NULL);
+	amdgpu_gpu_recover(adev, NULL);
 }
 
 static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
@@ -282,9 +282,17 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
 		/* see what event we get */
 		r = xgpu_ai_mailbox_rcv_msg(adev, IDH_FLR_NOTIFICATION);
 
-		/* only handle FLR_NOTIFY now */
-		if (!r)
-			schedule_work(&adev->virt.flr_work);
+		/* sometimes the interrupt is delayed to inject to VM, so under such case
+		 * the IDH_FLR_NOTIFICATION is overwritten by VF FLR from GIM side, thus
+		 * above recieve message could be failed, we should schedule the flr_work
+		 * anyway
+		 */
+		if (r) {
+			DRM_ERROR("FLR_NOTIFICATION is missed\n");
+			xgpu_ai_mailbox_send_ack(adev);
+		}
+
+		schedule_work(&adev->virt.flr_work);
 	}
 
 	return 0;
@@ -353,5 +361,6 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = {
 	.req_full_gpu	= xgpu_ai_request_full_gpu_access,
 	.rel_full_gpu	= xgpu_ai_release_full_gpu_access,
 	.reset_gpu = xgpu_ai_request_reset,
+	.wait_reset = NULL,
 	.trans_msg = xgpu_ai_mailbox_trans_msg,
 };