All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH 1/5] drm/radeon: fix PFP sync in vm_flush
@ 2012-10-22  8:55 Christian König
  2012-10-22  8:55 ` [PATCH 2/5] drm/radeon: fix cayman_vm_set_page Christian König
                   ` (4 more replies)
  0 siblings, 5 replies; 8+ messages in thread
From: Christian König @ 2012-10-22  8:55 UTC (permalink / raw)
  To: dri-devel

Otherwise the next IB might start reading commands
with the page table still invalid.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/ni.c  |    4 ++++
 drivers/gpu/drm/radeon/nid.h |    1 +
 drivers/gpu/drm/radeon/si.c  |    4 ++++
 3 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 8c74c72..19b7fe1 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1586,4 +1586,8 @@ void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	/* bits 0-7 are the VM contexts0-7 */
 	radeon_ring_write(ring, PACKET0(VM_INVALIDATE_REQUEST, 0));
 	radeon_ring_write(ring, 1 << vm->id);
+
+	/* sync PFP to ME, otherwise we might get invalid PFP reads */
+	radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
+	radeon_ring_write(ring, 0x0);
 }
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index 2423d1b..cbef681 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -502,6 +502,7 @@
 #define	PACKET3_MPEG_INDEX				0x3A
 #define	PACKET3_WAIT_REG_MEM				0x3C
 #define	PACKET3_MEM_WRITE				0x3D
+#define	PACKET3_PFP_SYNC_ME				0x42
 #define	PACKET3_SURFACE_SYNC				0x43
 #              define PACKET3_CB0_DEST_BASE_ENA    (1 << 6)
 #              define PACKET3_CB1_DEST_BASE_ENA    (1 << 7)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index df8dd77..da184de 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2868,6 +2868,10 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2);
 	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, 1 << vm->id);
+
+	/* sync PFP to ME, otherwise we might get invalid PFP reads */
+	radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
+	radeon_ring_write(ring, 0x0);
 }
 
 /*
-- 
1.7.9.5

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

^ permalink raw reply related	[flat|nested] 8+ messages in thread

end of thread, other threads:[~2012-10-22 15:24 UTC | newest]

Thread overview: 8+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-10-22  8:55 [PATCH 1/5] drm/radeon: fix PFP sync in vm_flush Christian König
2012-10-22  8:55 ` [PATCH 2/5] drm/radeon: fix cayman_vm_set_page Christian König
2012-10-22 15:12   ` Alex Deucher
2012-10-22 15:24     ` Christian König
2012-10-22  8:55 ` [PATCH 3/5] drm/radeon: fix si_set_page Christian König
2012-10-22  8:55 ` [PATCH 4/5] drm/radeon: remove set_page check from VM code Christian König
2012-10-22  8:55 ` [PATCH 5/5] drm/radeon: fix header size estimation in " Christian König
2012-10-22 13:50 ` [PATCH 1/5] drm/radeon: fix PFP sync in vm_flush Alex Deucher

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.