Skip to contentSkip to conversation

MPC5121 TLB errata workaround

RFC PATCH Superseded David Jander 1 participant 2 messages Mar 16, 2009 PowerPC

v4 of 5 Superseded Latest is v5 →

lore
Share & tools
lore
#0 lore raw

RFC PATCH v4 1/1 MPC5121 TLB errata workaround

Complete workaround for DTLB errata in MPC5121e processors of die M36P and older (all currently existing versions).

Due to the bug, the hardware-implemented LRU algorythm always goes to way 1 of the TLB. This fix implements the proposed software workaround in form of a LRW table encoded in 32 bits of SPRG6 for chosing the TLB-way.

---

arch/powerpc/kernel/head_32.S +3 -0
index 0f4fac5..6cc0cd3 100644
@@ -540,9 +540,13 @@ DataLoadTLBMiss:
  * r2:	ptr to linux-style pte
  * r3:	scratch
  */
+	mfspr	r3,SPRN_DMISS
+#ifdef CONFIG_PPC_MPC512x
+	b      e300_read_tlb_fix    /* Code for TLB-errata workaround doesn't fit 

here */
+e300_read_tlb_fix_ret:
+#endif
mfctr r0
/* Get PTE (linux-style) and check access */
- mfspr r3,SPRN_DMISS
lis r1,PAGE_OFFSET@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2,SPRN_SPRG3
@@ -612,9 +616,32 @@ DataStoreTLBMiss:
* r2: ptr to linux-style pte
* r3: scratch
*/
+ mfspr r3,SPRN_DMISS
+#ifdef CONFIG_PPC_MPC512x
+/* MPC512x: workaround for errata in die M36P and earlier:
+ * Implement LRW for TLB way.
+ */
+ rlwinm r0,r3,17,27,31 /* Get Address bits 19:15 */

+	li      r1,1
+	slw     r0,r1,r0       /* Make bitmask */
+	mfspr   r2,SPRN_SPRG6  /* Get lrw table */
+	and.    r1,r2,r0       /* Check entry in lrw */
+	beq-    0,113f         /* 0? Then goto 113: */

+
+ mfspr r1,SPRN_SRR1
+ rlwinm r1,r1,0,15,13 /* Mask out SRR1[WAY] */
+ mtspr SPRN_SRR1,r1
+

+	andc    r2,r2,r0
+	mtspr   SPRN_SPRG6,r2
+	b       114f

+113:
+ or r2,r2,r0
+ mtspr SPRN_SPRG6,r2
+114:
+#endif
mfctr r0
/* Get PTE (linux-style) and check access */
- mfspr r3,SPRN_DMISS
lis r1,PAGE_OFFSET@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2,SPRN_SPRG3
@@ -688,6 +715,29 @@ DataStoreTLBMiss:
.globl mol_trampoline
.set mol_trampoline, i0x2f00

+#ifdef CONFIG_PPC_MPC512x
+e300_read_tlb_fix:
+ rlwinm r0,r3,17,27,31 /* Get Address bits 19:15 */

+	li      r1,1
+	slw     r0,r1,r0       /* Make bitmask */
+	mfspr   r2,SPRN_SPRG6  /* Get lrw table */
+	and.    r1,r2,r0       /* Check entry in lrw */
+	beq-    0,113f         /* 0? Then goto 113: */

+
+ mfspr r1,SPRN_SRR1
+ rlwinm r1,r1,0,15,13 /* Mask out SRR1[WAY] */
+ mtspr SPRN_SRR1,r1
+

+	andc    r2,r2,r0
+	mtspr   SPRN_SPRG6,r2
+	b       114f

+113:
+ or r2,r2,r0
+ mtspr SPRN_SPRG6,r2
+114:
+ b e300_read_tlb_fix_ret
+#endif
+
. = 0x3000

AltiVecUnavailable:

#1 lore raw

Ooops, ok I think I just missed your proposal, Kumar.

Anyway, I'll post my benchmark results to this here:

1.- mplayer -nosound -benchmark testfile.mpeg (a DVD-mpeg2 file):

No fix at all:
VC: 30.5s VO: 53.4s Sys:1.95s Total: 85.8s

First fix (force writes to way 0):
VC: 24.3s VO: 40.6s Sys:1.95s Total: 66.9s

Second fix (implementing lrw):
VC: 23.1s VO: 31.5s Sys:1.03s Total: 55.6s

Third fix (patch v4, lrw in SPRG6):
VC: 21.055s VO: 28.289s Sys:0.972s Total: 50.316s

2.- prboom -timedemo doombench1 (where doombench1.lmp is prerecorded demo):

No fix at all: 14.1 fps
First fix (force writes to way 0): 16.7 fps Second fix (implementing lrw): 18.1 fps Third fix (patch v4, lrw in SPRG6): 19.9 fps

3.- Synthetic and pathologic memcpy() benchmark:
No fix at all: 26 Mbyte/s
First fix (force writes to way 0): 160 MByte/s Second fix (implementing lrw): 163 MByte/s Third fix (patch v4, lrw in SPRG6): 180 MByte/s

Best regards,

Signature · 2 lines
David Jander
Protonic Holland.