parisc: Add nop instructions after TLB inserts

Commit Message

John David Anglin Oct. 17, 2023, 4:01 p.m. UTC

Helge wrote recently:
In some document I read that newer PA2.0 CPUs had a pipeline of up to 12
instructions (instead of 8?).

Could it be that we need to change our code to cope with that, e.g.
while switching to/from virt/phys mode, or enabling/disabling IRQs ?

Looking up the actual reference, I found this statement:
o The PA8800 violates the seven instruction pipeline rule when performing
  TLB inserts or PxTLBE instructions with the PSW C bit on. The instruction
  will take effect by the 12th instruction after the insert or purge.

While I don't believe we have an issue with the code mentioned by
Helge, I believe we have a problem with handling TLB misses. We don't
fill the pipeline following TLB inserts. As a result, we likely fault
again after returning from the interruption.

The above statement indicates that we need at least seven instructions
after the insert on pre PA8800 processors and we need 12 instructions
on PA8800/PA8900 processors.

Here we add macros and code to provide the required number of nop
instructions.

Tested on c8000.

Signed-off-by: John David Anglin <[e-mail]>
---

Patch

diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 0e5ebfe8d9d2..3412e57dc7b4 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -437,6 +437,64 @@ 
 #endif
 	.endm
 
+/*
+ * We need seven instructions after a TLB insert for it to take effect.
+ * The PA8800/PA8900 processors are an exception and need 12 instructions.
+ * The RFI changes both IAOQ_Back and IAOQ_Front, so it counts as one.
+ * We need these nops to avoid faulting again after the RFI.
+ */
+	.macro		ptl_unlock0_nops
+#ifndef CONFIG_TLB_PTLOCK
+	nop
+	nop
+#endif
+#ifdef CONFIG_64BIT
+	nop
+	nop
+	nop
+	nop
+	nop
+#endif
+	nop
+	nop
+	nop
+	nop
+	.endm
+
+	.macro		ptl_unlock1_nops
+#ifndef CONFIG_TLB_PTLOCK
+	nop
+	nop
+	nop
+#endif
+#ifdef CONFIG_64BIT
+	nop
+	nop
+	nop
+	nop
+	nop
+#endif
+	nop
+	nop
+	nop
+	.endm
+
+	.macro		nops
+#ifdef CONFIG_64BIT
+	nop
+	nop
+	nop
+	nop
+	nop
+#endif
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	.endm
+
 	/* Set the _PAGE_ACCESSED bit of the PTE.  Be clever and
 	 * don't needlessly dirty the cache line if it was already set */
 	.macro		update_accessed	ptp,pte,tmp,tmp1
@@ -1126,6 +1184,7 @@  dtlb_miss_20w:
 	idtlbt          pte,prot
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1134,6 +1193,7 @@  dtlb_check_alias_20w:
 
 	idtlbt          pte,prot
 
+	nops
 	rfir
 	nop
 
@@ -1152,6 +1212,7 @@  nadtlb_miss_20w:
 	idtlbt          pte,prot
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1160,6 +1221,7 @@  nadtlb_check_alias_20w:
 
 	idtlbt          pte,prot
 
+	nops
 	rfir
 	nop
 
@@ -1186,6 +1248,7 @@  dtlb_miss_11:
 	mtsp		t1, %sr1	/* Restore sr1 */
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1195,6 +1258,7 @@  dtlb_check_alias_11:
 	idtlba          pte,(va)
 	idtlbp          prot,(va)
 
+	nops
 	rfir
 	nop
 
@@ -1219,6 +1283,7 @@  nadtlb_miss_11:
 	mtsp		t1, %sr1	/* Restore sr1 */
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1228,6 +1293,7 @@  nadtlb_check_alias_11:
 	idtlba          pte,(va)
 	idtlbp          prot,(va)
 
+	nops
 	rfir
 	nop
 
@@ -1248,6 +1314,7 @@  dtlb_miss_20:
 	idtlbt          pte,prot
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1256,6 +1323,7 @@  dtlb_check_alias_20:
 	
 	idtlbt          pte,prot
 
+	nops
 	rfir
 	nop
 
@@ -1276,6 +1344,7 @@  nadtlb_miss_20:
 	idtlbt		pte,prot
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1284,6 +1353,7 @@  nadtlb_check_alias_20:
 
 	idtlbt          pte,prot
 
+	nops
 	rfir
 	nop
 
@@ -1321,6 +1391,7 @@  itlb_miss_20w:
 	iitlbt          pte,prot
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1345,6 +1416,7 @@  naitlb_miss_20w:
 	iitlbt          pte,prot
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1353,6 +1425,7 @@  naitlb_check_alias_20w:
 
 	iitlbt		pte,prot
 
+	nops
 	rfir
 	nop
 
@@ -1379,6 +1452,7 @@  itlb_miss_11:
 	mtsp		t1, %sr1	/* Restore sr1 */
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1403,6 +1477,7 @@  naitlb_miss_11:
 	mtsp		t1, %sr1	/* Restore sr1 */
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1412,6 +1487,7 @@  naitlb_check_alias_11:
 	iitlba          pte,(%sr0, va)
 	iitlbp          prot,(%sr0, va)
 
+	nops
 	rfir
 	nop
 
@@ -1433,6 +1509,7 @@  itlb_miss_20:
 	iitlbt          pte,prot
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1453,6 +1530,7 @@  naitlb_miss_20:
 	iitlbt          pte,prot
 
 	ptl_unlock1	spc,t0
+	ptl_unlock1_nops
 	rfir
 	nop
 
@@ -1461,6 +1539,7 @@  naitlb_check_alias_20:
 
 	iitlbt          pte,prot
 
+	nops
 	rfir
 	nop
 
@@ -1483,6 +1562,7 @@  dbit_trap_20w:
 	idtlbt          pte,prot
 
 	ptl_unlock0	spc,t0
+	ptl_unlock0_nops
 	rfir
 	nop
 #else
@@ -1509,6 +1589,7 @@  dbit_trap_11:
 	mtsp            t1, %sr1     /* Restore sr1 */
 
 	ptl_unlock0	spc,t0
+	ptl_unlock0_nops
 	rfir
 	nop
 
@@ -1529,6 +1610,7 @@  dbit_trap_20:
 	idtlbt		pte,prot
 
 	ptl_unlock0	spc,t0
+	ptl_unlock0_nops
 	rfir
 	nop
 #endif