aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDavid Miller <davem@davemloft.net>2008-08-12 15:08:51 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2008-08-12 16:07:28 -0700
commit969830b2fedf8336c41d6195f49d250b1e166ff8 (patch)
treeba7eec39395531b9baf62a0e13a875f085524409
parent2b26736c88db85c038e04c2306d0745553e69602 (diff)
radeonfb: fix accel engine hangs
Some chips appear to have the 2D engine hang during screen redraw, typically in a sequence of copyarea operations. This appear to be solved by adding a flush of the engine destination pixel cache and waiting for the engine to be idle before issuing the accel operation. The performance impact seems to be fairly small. Here is a trace on an RV370 (PCI device ID 0x5b64), it records the RBBM_STATUS register, then the source x/y, destination x/y, and width/height used for the copy: ---------------------------------------- radeonfb_prim_copyarea: STATUS[00000140] src[210:70] dst[210:60] wh[a0:10] radeonfb_prim_copyarea: STATUS[00000140] src[2b8:70] dst[2b8:60] wh[88:10] radeonfb_prim_copyarea: STATUS[00000140] src[348:70] dst[348:60] wh[40:10] radeonfb_prim_copyarea: STATUS[80020140] src[390:70] dst[390:60] wh[88:10] radeonfb_prim_copyarea: STATUS[8002613f] src[40:80] dst[40:70] wh[28:10] radeonfb_prim_copyarea: STATUS[80026139] src[a8:80] dst[a8:70] wh[38:10] radeonfb_prim_copyarea: STATUS[80026133] src[e8:80] dst[e8:70] wh[80:10] radeonfb_prim_copyarea: STATUS[8002612d] src[170:80] dst[170:70] wh[30:10] radeonfb_prim_copyarea: STATUS[80026127] src[1a8:80] dst[1a8:70] wh[8:10] radeonfb_prim_copyarea: STATUS[80026121] src[1b8:80] dst[1b8:70] wh[88:10] radeonfb_prim_copyarea: STATUS[8002611b] src[248:80] dst[248:70] wh[68:10] ---------------------------------------- When things are going fine the copies complete before the next ROP is even issued, but all of a sudden the 2D unit becomes active (bit 17 in RBBM_STATUS) and the FIFO retry (bit 13) and FIFO pipeline busy (bit 14) are set as well. The FIFO begins to backup until it becomes full. What happens next is the radeon_fifo_wait() times out, and we access the chip illegally leading to a bus error which usually wedges the box. None of this makes it to the console screen, of course :-) radeon_fifo_wait() should be modified to reset the accelerator when this timeout happens instead of programming the chip anyways. ---------------------------------------- radeonfb: FIFO Timeout ! ERROR(0): Cheetah error trap taken afsr[0010080005000000] afar[000007f900800e40] TL1(0) ERROR(0): TPC[595114] TNPC[595118] O7[459788] TSTATE[11009601] ERROR(0): TPC<radeonfb_copyarea+0xfc/0x248> ERROR(0): M_SYND(0), E_SYND(0), Privileged ERROR(0): Highest priority error (0000080000000000) "Bus error response from system bus" ERROR(0): D-cache idx[0] tag[0000000000000000] utag[0000000000000000] stag[0000000000000000] ERROR(0): D-cache data0[0000000000000000] data1[0000000000000000] data2[0000000000000000] data3[0000000000000000] ERROR(0): I-cache idx[0] tag[0000000000000000] utag[0000000000000000] stag[0000000000000000] u[0000000000000000] l[00\ ERROR(0): I-cache INSN0[0000000000000000] INSN1[0000000000000000] INSN2[0000000000000000] INSN3[0000000000000000] ERROR(0): I-cache INSN4[0000000000000000] INSN5[0000000000000000] INSN6[0000000000000000] INSN7[0000000000000000] ERROR(0): E-cache idx[800e40] tag[000000000e049f4c] ERROR(0): E-cache data0[fffff8127d300180] data1[00000000004b5384] data2[0000000000000000] data3[0000000000000000] Ker:xnel panic - not syncing: Irrecoverable deferred error trap. ---------------------------------------- Another quirk is that these copyarea calls will not happen until the first drivers/char/vt.c:redraw_screen() occurs. This will only happen if you 1) VC switch or 2) run "consolechars" or 3) unblank the screen. This seems to happen because until a redraw_screen() the screen scrolling method used by fbcon is not finalized yet. I've seen this with other fb drivers too. So if all you do is boot straight into X you will never see this bug on the relevant chips. Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: <stable@kernel.org> [2.6.25.x, 2.6.26.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--drivers/video/aty/radeon_accel.c8
-rw-r--r--include/video/radeon.h4
2 files changed, 12 insertions, 0 deletions
diff --git a/drivers/video/aty/radeon_accel.c b/drivers/video/aty/radeon_accel.c
index 4d13f68436e..aa95f835024 100644
--- a/drivers/video/aty/radeon_accel.c
+++ b/drivers/video/aty/radeon_accel.c
@@ -55,6 +55,10 @@ static void radeonfb_prim_fillrect(struct radeonfb_info *rinfo,
OUTREG(DP_WRITE_MSK, 0xffffffff);
OUTREG(DP_CNTL, (DST_X_LEFT_TO_RIGHT | DST_Y_TOP_TO_BOTTOM));
+ radeon_fifo_wait(2);
+ OUTREG(DSTCACHE_CTLSTAT, RB2D_DC_FLUSH_ALL);
+ OUTREG(WAIT_UNTIL, (WAIT_2D_IDLECLEAN | WAIT_DMA_GUI_IDLE));
+
radeon_fifo_wait(2);
OUTREG(DST_Y_X, (region->dy << 16) | region->dx);
OUTREG(DST_WIDTH_HEIGHT, (region->width << 16) | region->height);
@@ -116,6 +120,10 @@ static void radeonfb_prim_copyarea(struct radeonfb_info *rinfo,
OUTREG(DP_CNTL, (xdir>=0 ? DST_X_LEFT_TO_RIGHT : 0)
| (ydir>=0 ? DST_Y_TOP_TO_BOTTOM : 0));
+ radeon_fifo_wait(2);
+ OUTREG(DSTCACHE_CTLSTAT, RB2D_DC_FLUSH_ALL);
+ OUTREG(WAIT_UNTIL, (WAIT_2D_IDLECLEAN | WAIT_DMA_GUI_IDLE));
+
radeon_fifo_wait(3);
OUTREG(SRC_Y_X, (sy << 16) | sx);
OUTREG(DST_Y_X, (dy << 16) | dx);
diff --git a/include/video/radeon.h b/include/video/radeon.h
index 95a1f2038b1..099ffa5e5be 100644
--- a/include/video/radeon.h
+++ b/include/video/radeon.h
@@ -742,6 +742,10 @@
#define SOFT_RESET_RB (1 << 6)
#define SOFT_RESET_HDP (1 << 7)
+/* WAIT_UNTIL bit constants */
+#define WAIT_DMA_GUI_IDLE (1 << 9)
+#define WAIT_2D_IDLECLEAN (1 << 16)
+
/* SURFACE_CNTL bit consants */
#define SURF_TRANSLATION_DIS (1 << 8)
#define NONSURF_AP0_SWP_16BPP (1 << 20)