[PATCH 00/13] powerpc: Backport 8xx TLB to 2.4

[PATCH 00/13] powerpc: Backport 8xx TLB to 2.4

[Joakim Tjernlund]

This is a backport from 2.6 which I did to overcome 8xx CPU
bugs. 8xx does not update the DAR register when taking a TLB
error caused by dcbX and icbi insns which makes it very
tricky to use these insns. Also the dcbst wrongly sets the
the store bit when faulting into DTLB error.
A few more bugs very found during development.

I know 2.4 is in strict maintenance mode and 8xx is obsolete
but as it is still in use I wanted 8xx to age with grace.

Joakim Tjernlund (13):
  8xx: Use a macro to simpliy CPU6 errata code.
  8xx: Tag DAR with 0x00f0 to catch buggy instructions.
  8xx: invalidate non present TLBs
  8xx: Fix CONFIG_PIN_TLB
  8xx: Update TLB asm so it behaves as linux mm expects.
  8xx: Always pin kernel instruction TLB
  8xx: Fixup DAR from buggy dcbX instructions.
  8xx: CPU6 errata make DTLB error too big to fit.
  8xx: Add missing Guarded setting in DTLB Error.
  8xx: Restore _PAGE_WRITETHRU
  8xx: start using dcbX instructions in various copy routines
  8xx: Optimize ITLBMiss handler.
  8xx: Optimize TLB Miss handlers

 arch/ppc/kernel/head_8xx.S |  364 ++++++++++++++++++++++++++++++--------------
 arch/ppc/kernel/misc.S     |   18 ---
 arch/ppc/lib/string.S      |   17 --
 arch/ppc/mm/fault.c        |    8 +-
 include/asm-ppc/pgtable.h  |   16 +-
 5 files changed, 266 insertions(+), 157 deletions(-)

-- 
1.7.3.4

[PATCH 01/13] 8xx: Use a macro to simpliy CPU6 errata code.

[Joakim Tjernlund]

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |   84 +++++++++++--------------------------------
 1 files changed, 22 insertions(+), 62 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index f9a30f3..ba05a57 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -31,6 +31,15 @@
 #include <asm/ppc_asm.h>
 #include "ppc_defs.h"
 
+/* Macro to make the code more readable. */
+#ifdef CONFIG_8xx_CPU6
+  #define DO_8xx_CPU6(val, reg) \
+	li	reg, val; \
+	stw	reg, 12(r0); \
+	lwz	reg, 12(r0);
+#else
+  #define DO_8xx_CPU6(val, reg)
+#endif
 	.text
 	.globl	_stext
 _stext:
@@ -310,20 +319,14 @@ SystemCall:
 InstructionTLBMiss:
 #ifdef CONFIG_8xx_CPU6
 	stw	r3, 8(r0)
-	li	r3, 0x3f80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
 #endif
+	DO_8xx_CPU6(0x3f80, r3)
 	mtspr	M_TW, r20	/* Save a couple of working registers */
 	mfcr	r20
 	stw	r20, 0(r0)
 	stw	r21, 4(r0)
 	mfspr	r20, SRR0	/* Get effective address of fault */
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x3780
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x3780, r3)
 	mtspr	MD_EPN, r20	/* Have to use MD_EPN for walk, MI_EPN can't */
 	mfspr	r20, M_TWB	/* Get level 1 table entry address */
 
@@ -345,17 +348,9 @@ InstructionTLBMiss:
 	tophys(r21,r21)
 	ori	r21,r21,1		/* Set valid bit */
 	beq-	2f			/* If zero, don't try to find a pte */
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x2b80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x2b80, r3)
 	mtspr	MI_TWC, r21	/* Set segment attributes */
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x3b80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	MD_TWC, r21	/* Load pte table base address */
 	mfspr	r21, MD_TWC	/* ....and get the pte address */
 	lwz	r20, 0(r21)	/* Get the pte */
@@ -371,12 +366,7 @@ InstructionTLBMiss:
 	 */
 2:	li	r21, 0x00f0
 	rlwimi	r20, r21, 0, 24, 28	/* Set 24-27, clear 28 */
-
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x2d80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x2d80, r3)
 	mtspr	MI_RPN, r20	/* Update TLB entry */
 
 	mfspr	r20, M_TW	/* Restore registers */
@@ -392,10 +382,8 @@ InstructionTLBMiss:
 DataStoreTLBMiss:
 #ifdef CONFIG_8xx_CPU6
 	stw	r3, 8(r0)
-	li	r3, 0x3f80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
 #endif
+	DO_8xx_CPU6(0x3f80, r3)
 	mtspr	M_TW, r20	/* Save a couple of working registers */
 	mfcr	r20
 	stw	r20, 0(r0)
@@ -419,11 +407,7 @@ DataStoreTLBMiss:
 	tophys(r21, r21)
 	ori	r21, r21, 1	/* Set valid bit in physical L2 page */
 	beq-	2f		/* If zero, don't try to find a pte */
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x3b80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	MD_TWC, r21	/* Load pte table base address */
 	mfspr	r20, MD_TWC	/* ....and get the pte address */
 	lwz	r20, 0(r20)	/* Get the pte */
@@ -435,11 +419,7 @@ DataStoreTLBMiss:
 	 * above.
 	 */
 	rlwimi	r21, r20, 0, 27, 27
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x3b80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	MD_TWC, r21
 
 	mfspr	r21, MD_TWC	/* get the pte address again */
@@ -454,12 +434,7 @@ DataStoreTLBMiss:
 	 */
 2:	li	r21, 0x00f0
 	rlwimi	r20, r21, 0, 24, 28	/* Set 24-27, clear 28 */
-
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x3d80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x3d80, r3)
 	mtspr	MD_RPN, r20	/* Update TLB entry */
 
 	mfspr	r20, M_TW	/* Restore registers */
@@ -491,10 +466,8 @@ InstructionTLBError:
 DataTLBError:
 #ifdef CONFIG_8xx_CPU6
 	stw	r3, 8(r0)
-	li	r3, 0x3f80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
 #endif
+	DO_8xx_CPU6(0x3f80, r3)
 	mtspr	M_TW, r20	/* Save a couple of working registers */
 	mfcr	r20
 	stw	r20, 0(r0)
@@ -527,11 +500,7 @@ DataTLBError:
 	ori	r21, r21, MD_EVALID
 	mfspr	r20, M_CASID
 	rlwimi	r21, r20, 0, 28, 31
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x3780
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x3780, r3)
 	mtspr	MD_EPN, r21
 
 	mfspr	r20, M_TWB	/* Get level 1 table entry address */
@@ -553,11 +522,7 @@ DataTLBError:
 	 */
 	tophys(r21, r21)
 	ori	r21, r21, 1		/* Set valid bit in physical L2 page */
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x3b80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	MD_TWC, r21		/* Load pte table base address */
 	mfspr	r21, MD_TWC		/* ....and get the pte address */
 	lwz	r20, 0(r21)		/* Get the pte */
@@ -579,12 +544,7 @@ DataTLBError:
 	 */
 	li	r21, 0x00f0
 	rlwimi	r20, r21, 0, 24, 28	/* Set 24-27, clear 28 */
-
-#ifdef CONFIG_8xx_CPU6
-	li	r3, 0x3d80
-	stw	r3, 12(r0)
-	lwz	r3, 12(r0)
-#endif
+	DO_8xx_CPU6(0x3d80, r3)
 	mtspr	MD_RPN, r20	/* Update TLB entry */
 
 	mfspr	r20, M_TW	/* Restore registers */
-- 
1.7.3.4

[PATCH 02/13] 8xx: Tag DAR with 0x00f0 to catch buggy instructions.

[Joakim Tjernlund]

dcbz, dcbf, dcbi, dcbst and icbi do not set DAR when they
cause a DTLB Error. Dectect this by tagging DAR with 0x00f0
at every exception exit that modifies DAR.
This also fixes MachineCheck to pass DAR and DSISR as well.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |   18 +++++++++++++++++-
 1 files changed, 17 insertions(+), 1 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index ba05a57..57858ce 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -197,7 +197,17 @@ label:						\
 	STD_EXCEPTION(0x100, Reset, UnknownException)
 
 /* Machine check */
-	STD_EXCEPTION(0x200, MachineCheck, MachineCheckException)
+	. = 0x200
+MachineCheck:
+	EXCEPTION_PROLOG
+	mfspr	r20,DSISR
+	stw	r20,_DSISR(r21)
+	mfspr	r20,DAR
+	stw	r20,_DAR(r21)
+	li	r20,0x00f0
+	mtspr	DAR,r20	/* Tag DAR */
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	FINISH_EXCEPTION(MachineCheckException)
 
 /* Data access exception.
  * This is "never generated" by the MPC8xx.  We jump to it for other
@@ -211,6 +221,8 @@ DataAccess:
 	mr	r5,r20
 	mfspr	r4,DAR
 	stw	r4,_DAR(r21)
+	li	r20,0x00f0
+	mtspr	DAR,r20	/* Tag DAR */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	li	r20,MSR_KERNEL
 	rlwimi	r20,r23,0,16,16		/* copy EE bit from saved MSR */
@@ -249,6 +261,8 @@ Alignment:
 	EXCEPTION_PROLOG
 	mfspr	r4,DAR
 	stw	r4,_DAR(r21)
+	li	r20,0x00f0
+	mtspr	DAR,r20	/* Tag DAR */
 	mfspr	r5,DSISR
 	stw	r5,_DSISR(r21)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
@@ -433,6 +447,7 @@ DataStoreTLBMiss:
 	 * of the MMU.
 	 */
 2:	li	r21, 0x00f0
+	mtspr	DAR, r21	/* Tag DAR */
 	rlwimi	r20, r21, 0, 24, 28	/* Set 24-27, clear 28 */
 	DO_8xx_CPU6(0x3d80, r3)
 	mtspr	MD_RPN, r20	/* Update TLB entry */
@@ -543,6 +558,7 @@ DataTLBError:
 	 * of the MMU.
 	 */
 	li	r21, 0x00f0
+	mtspr	DAR, r21	/* Tag DAR */
 	rlwimi	r20, r21, 0, 24, 28	/* Set 24-27, clear 28 */
 	DO_8xx_CPU6(0x3d80, r3)
 	mtspr	MD_RPN, r20	/* Update TLB entry */
-- 
1.7.3.4

[PATCH 03/13] 8xx: invalidate non present TLBs

[Joakim Tjernlund]

8xx sometimes need to load a invalid/non-present TLBs in
it DTLB asm handler.
These must be invalidated separaly as linux mm don't.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/mm/fault.c |    8 +++++++-
 1 files changed, 7 insertions(+), 1 deletions(-)

diff --git a/arch/ppc/mm/fault.c b/arch/ppc/mm/fault.c
index 9d3ce2d..874005a 100644
--- a/arch/ppc/mm/fault.c
+++ b/arch/ppc/mm/fault.c
@@ -116,7 +116,13 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	else
 		is_write = error_code & 0x02000000;
 #endif /* CONFIG_4xx || CONFIG_BOOKE */
-
+#if defined(CONFIG_8xx)
+	/* 8xx does no invalidate TLBs that are ~PRESENT,
+	 * do it here.
+	 */
+	if (error_code & 0x40000000)
+		_tlbie(address);
+#endif
 #if defined(CONFIG_XMON) || defined(CONFIG_KGDB)
 	if (debugger_fault_handler && regs->trap == 0x300) {
 		debugger_fault_handler(regs);
-- 
1.7.3.4

[PATCH 04/13] 8xx: Fix CONFIG_PIN_TLB

[Joakim Tjernlund]

The wrong register was loaded into MD_RPN.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index 57858ce..5269e5b 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -840,13 +840,13 @@ initial_mmu:
 	mtspr	MD_TWC, r9
 	li	r11, MI_BOOTINIT	/* Create RPN for address 0 */
 	addis	r11, r11, 0x0080	/* Add 8M */
-	mtspr	MD_RPN, r8
+	mtspr	MD_RPN, r11
 
 	addis	r8, r8, 0x0080		/* Add 8M */
 	mtspr	MD_EPN, r8
 	mtspr	MD_TWC, r9
 	addis	r11, r11, 0x0080	/* Add 8M */
-	mtspr	MD_RPN, r8
+	mtspr	MD_RPN, r11
 #endif
 
 	/* Since the cache is enabled according to the information we
-- 
1.7.3.4

[PATCH 05/13] 8xx: Update TLB asm so it behaves as linux mm expects.

[Joakim Tjernlund]

Update the TLB asm to make proper use of _PAGE_DIRTY and _PAGE_ACCESSED.
Get rid of _PAGE_HWWRITE too.
Pros:
  - PRESENT is copied to ACCESSED, fixing accounting
  - DIRTY is mapped to 0x100, the changed bit, and is set directly
    when a page has been made dirty.
  - Proper RO/RW mapping of user space.
  - Free up 2 SW TLB bits in the linux pte(add back _PAGE_WRITETHRU ?)
  - kernel RO/user NA support. Not sure this is really needed, would save
    a few insn if not required.
Cons:
  - A few more instructions in the DTLB Miss routine.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |   53 ++++++++++++++++++++++++++-----------------
 include/asm-ppc/pgtable.h  |   15 +++++------
 2 files changed, 39 insertions(+), 29 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index 5269e5b..9eb383b 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -361,25 +361,27 @@ InstructionTLBMiss:
 	 */
 	tophys(r21,r21)
 	ori	r21,r21,1		/* Set valid bit */
-	beq-	2f			/* If zero, don't try to find a pte */
 	DO_8xx_CPU6(0x2b80, r3)
 	mtspr	MI_TWC, r21	/* Set segment attributes */
+	beq-	2f		/* If zero, don't try to find a pte */
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	MD_TWC, r21	/* Load pte table base address */
 	mfspr	r21, MD_TWC	/* ....and get the pte address */
 	lwz	r20, 0(r21)	/* Get the pte */
 
-	ori	r20, r20, _PAGE_ACCESSED
-	stw	r20, 0(r21)
-
+#if 1
+	/* if !swap, you can delete this */
+	rlwimi	r20, r20, 5, _PAGE_PRESENT<<5	/* Copy PRESENT to ACCESSED */
+	stw	r20, 0(r21)	/* Update pte */
+#endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bits 21 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
 2:	li	r21, 0x00f0
-	rlwimi	r20, r21, 0, 24, 28	/* Set 24-27, clear 28 */
+	rlwimi	r20, r21, 0, 0x07f8	/* Set 24-27, clear 21-23,28 */
 	DO_8xx_CPU6(0x2d80, r3)
 	mtspr	MI_RPN, r20	/* Update TLB entry */
 
@@ -436,12 +438,25 @@ DataStoreTLBMiss:
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	MD_TWC, r21
 
-	mfspr	r21, MD_TWC	/* get the pte address again */
-	ori	r20, r20, _PAGE_ACCESSED
-	stw	r20, 0(r21)
+#if 1
+	/* if !swap, you can delete this */
+	mfspr	r21, MD_TWC	/* get the pte address */
+	rlwimi	r20, r20, 5, _PAGE_PRESENT<<5	/* Copy PRESENT to ACCESSED */
+	stw	r20, 0(r21)	/* Update pte */
+#endif
+
+	/* Honour kernel RO, User NA */
+	/* 0x200 == Extended encoding, bit 22 */
+	/* r20 |=  (r20 & _PAGE_USER) >> 2 */
+	rlwimi	r20, r20, 32-2, 0x200
+	/* r21 =  (r20 & _PAGE_RW) >> 1 */
+	rlwinm	r21, r20, 32-1, 0x200
+	or	r20, r21, r20
+	/* invert RW and 0x200 bits */
+	xori	r20, r20, _PAGE_RW | 0x200
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
@@ -488,11 +503,12 @@ DataTLBError:
 	stw	r20, 0(r0)
 	stw	r21, 4(r0)
 
-	/* First, make sure this was a store operation.
-	*/
 	mfspr	r20, DSISR
-	andis.	r21, r20, 0x0200	/* If set, indicates store op */
-	beq	2f
+	andis.	r21, r20, 0x4800	/* !translation or protection */
+	bne-	2f
+	/* Only Change bit left now, do it here as it is faster
+	 * than trapping to the C fault handler.
+ 	 */
 
 	/* The EA of a data TLB miss is automatically stored in the MD_EPN
 	 * register.  The EA of a data TLB error is automatically stored in
@@ -542,17 +558,12 @@ DataTLBError:
 	mfspr	r21, MD_TWC		/* ....and get the pte address */
 	lwz	r20, 0(r21)		/* Get the pte */
 
-	andi.	r21, r20, _PAGE_RW	/* Is it writeable? */
-	beq	2f			/* Bail out if not */
-
-	/* Update 'changed', among others.
-	*/
 	ori	r20, r20, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
-	mfspr	r21, MD_TWC		/* Get pte address again */
 	stw	r20, 0(r21)		/* and update pte in table */
+	xori	r20, r20, _PAGE_RW	/* RW bit is inverted */
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
diff --git a/include/asm-ppc/pgtable.h b/include/asm-ppc/pgtable.h
index 71b2165..2ba37d3 100644
--- a/include/asm-ppc/pgtable.h
+++ b/include/asm-ppc/pgtable.h
@@ -298,21 +298,20 @@ extern unsigned long vmalloc_start;
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
 #define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
 
-/* These five software bits must be masked out when the entry is loaded
- * into the TLB.
+/* These three software bits must be masked out when the entry is loaded
+ * into the TLB, 2 SW bits free.
  */
 #define _PAGE_EXEC	0x0008	/* software: i-cache coherency required */
 #define _PAGE_GUARDED	0x0010	/* software: guarded access */
-#define _PAGE_DIRTY	0x0020	/* software: page changed */
-#define _PAGE_RW	0x0040	/* software: user write access allowed */
-#define _PAGE_ACCESSED	0x0080	/* software: page referenced */
+#define _PAGE_ACCESSED	0x0020	/* software: page referenced */
 
 /* Setting any bits in the nibble with the follow two controls will
  * require a TLB exception handler change.  It is assumed unused bits
- * are always zero.
+ * are always zero, encoding(bit 22).
  */
-#define _PAGE_HWWRITE	0x0100	/* h/w write enable: never set in Linux PTE */
-#define _PAGE_USER	0x0800	/* One of the PP bits, the other is USER&~RW */
+#define _PAGE_DIRTY	0x0100	/* Changed: page changed */
+#define _PAGE_RW	0x0400	/* PP lsb(bit 21), user write access allowed */
+#define _PAGE_USER	0x0800	/* PP msb(bit 20), user access allowed */
 
 #define _PMD_PRESENT	PAGE_MASK
 #define _PMD_PAGE_MASK	0x000c
-- 
1.7.3.4

[PATCH 06/13] 8xx: Always pin kernel instruction TLB

[Joakim Tjernlund]

Various kernel asm modifies SRR0/SRR1 just before executing
a rfi. If such code crosses a page boundary you risk a TLB miss
which will clobber SRR0/SRR1. Avoid this by always pinning
kernel instruction TLB space.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |    9 +++++----
 1 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index 9eb383b..d992c24 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -777,12 +777,13 @@ start_here:
  */
 initial_mmu:
 	tlbia			/* Invalidate all TLB entries */
-#ifdef CONFIG_PIN_TLB
+
+/* Always pin the first 8 MB ITLB to prevent ITLB
+   misses while mucking around with SRR0/SRR1 in asm
+*/
 	lis	r8, MI_RSV4I@h
 	ori	r8, r8, 0x1c00
-#else
-	li	r8, 0
-#endif
+
 	mtspr	MI_CTR, r8	/* Set instruction MMU control */
 
 #ifdef CONFIG_PIN_TLB
-- 
1.7.3.4

[PATCH 07/13] 8xx: Fixup DAR from buggy dcbX instructions.

[Joakim Tjernlund]

This is an assembler version to fixup DAR not being set
by dcbX, icbi instructions. There are two versions, one
uses selfmodifing code, the other uses a
jump table but is much bigger(default).

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |  149 +++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 146 insertions(+), 3 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index d992c24..52ff914 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -503,8 +503,17 @@ DataTLBError:
 	stw	r20, 0(r0)
 	stw	r21, 4(r0)
 
-	mfspr	r20, DSISR
-	andis.	r21, r20, 0x4800	/* !translation or protection */
+	mfspr	r20, DAR
+	cmpwi	cr0, r20, 0x00f0
+	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
+DARFixed:
+	/* As the DAR fixup may clear store we may have all 3 states zero.
+	 * Make sure only 0x0200(store) falls down into DIRTY handling
+	 */
+	mfspr	r21, DSISR
+	andis.	r21, r21, 0x4a00	/* !translation, protection or store */
+	srwi	r21, r21, 16
+	cmpwi	cr0, r21, 0x0200	/* just store ? */
 	bne-	2f
 	/* Only Change bit left now, do it here as it is faster
 	 * than trapping to the C fault handler.
@@ -526,7 +535,7 @@ DataTLBError:
 	 * are initialized in mapin_ram().  This will avoid the problem,
 	 * assuming we only use the dcbi instruction on kernel addresses.
 	 */
-	mfspr	r20, DAR
+	/* DAR is in r20 already */
 	rlwinm	r21, r20, 0, 0, 19
 	ori	r21, r21, MD_EVALID
 	mfspr	r20, M_CASID
@@ -610,6 +619,140 @@ DataTLBError:
 	STD_EXCEPTION(0x1f00, Trap_1f, UnknownException)
 
 	. = 0x2000
+/* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
+ * by decoding the registers used by the dcbx instruction and adding them.
+ * DAR is set to the calculated address and r10 also holds the EA on exit.
+ */
+ /* define if you don't want to use self modifying code */
+#define NO_SELF_MODIFYING_CODE
+FixupDAR:/* Entry point for dcbx workaround. */
+	/* fetch instruction from memory. */
+	mfspr	r20, SRR0
+	andis.	r21, r20, 0x8000	/* Address >= 0x80000000 */
+	DO_8xx_CPU6(0x3780, r3)
+	mtspr	MD_EPN, r20
+	mfspr	r21, M_TWB	/* Get level 1 table entry address */
+	beq-	3f		/* Branch if user space */
+	lis	r21, (swapper_pg_dir-PAGE_OFFSET)@h
+	ori	r21, r21, (swapper_pg_dir-PAGE_OFFSET)@l
+	rlwimi	r21, r20, 32-20, 0xffc /* r21 = r21&~0xffc|(r20>>20)&0xffc */
+3:	lwz	r21, 0(r21)	/* Get the level 1 entry */
+	tophys  (r21, r21)
+	DO_8xx_CPU6(0x3b80, r3)
+	mtspr	MD_TWC, r21	/* Load pte table base address */
+	mfspr	r21, MD_TWC	/* ....and get the pte address */
+	lwz	r21, 0(r21)	/* Get the pte */
+	/* concat physical page address(r21) and page offset(r20) */
+	rlwimi	r21, r20, 0, 20, 31
+	lwz	r21,0(r21)
+/* Check if it really is a dcbx instruction. */
+/* dcbt and dcbtst does not generate DTLB Misses/Errors,
+ * no need to include them here */
+	srwi	r20, r21, 26	/* check if major OP code is 31 */
+	cmpwi	cr0, r20, 31
+	bne-	141f
+	rlwinm	r20, r21, 0, 21, 30
+	cmpwi	cr0, r20, 2028	/* Is dcbz? */
+	beq+	142f
+	cmpwi	cr0, r20, 940	/* Is dcbi? */
+	beq+	142f
+	cmpwi	cr0, r20, 108	/* Is dcbst? */
+	beq+	144f		/* Fix up store bit! */
+	cmpwi	cr0, r20, 172	/* Is dcbf? */
+	beq+	142f
+	cmpwi	cr0, r20, 1964	/* Is icbi? */
+	beq+	142f
+141:	mfspr	r20, DAR	/* r20 must hold DAR at exit */
+	b	DARFixed	/* Nope, go back to normal TLB processing */
+
+144:	mfspr	r20, DSISR
+	rlwinm	r20, r20,0,7,5	/* Clear store bit for buggy dcbst insn */
+	mtspr	DSISR, r20
+142:	/* continue, it was a dcbx, dcbi instruction. */
+#ifdef CONFIG_8xx_CPU6
+	lwz	r3, 8(r0)	/* restore r3 from memory */
+#endif
+#ifndef NO_SELF_MODIFYING_CODE
+	andis.	r20,r21,0x1f	/* test if reg RA is r0 */
+	li	r20,modified_instr@l
+	dcbtst	r0,r20		/* touch for store */
+	rlwinm	r21,r21,0,0,20	/* Zero lower 10 bits */
+	oris	r21,r21,640	/* Transform instr. to a "add r20,RA,RB" */
+	ori	r21,r21,532
+	stw	r21,0(r20)	/* store add/and instruction */
+	dcbf	0,r20		/* flush new instr. to memory. */
+	icbi	0,r20		/* invalidate instr. cache line */
+	lwz	r21, 4(r0)	/* restore r21 from memory */
+	mfspr	r20, M_TW	/* restore r20 from M_TW */
+	isync			/* Wait until new instr is loaded from memory */
+modified_instr:
+	.space	4		/* this is where the add instr. is stored */
+	bne+	143f
+	subf	r20,r0,r20	/* r20=r20-r0, only if reg RA is r0 */
+143:	mtdar	r20		/* store faulting EA in DAR */
+	b	DARFixed	/* Go back to normal TLB handling */
+#else
+	mfctr	r20
+	mtdar	r20			/* save ctr reg in DAR */
+	rlwinm	r20, r21, 24, 24, 28	/* offset into jump table for reg RB */
+	addi	r20, r20, 150f@l	/* add start of table */
+	mtctr	r20			/* load ctr with jump address */
+	xor	r20, r20, r20		/* sum starts at zero */
+	bctr				/* jump into table */
+150:
+	add	r20, r20, r0	;b	151f
+	add	r20, r20, r1	;b	151f
+	add	r20, r20, r2	;b	151f
+	add	r20, r20, r3	;b	151f
+	add	r20, r20, r4	;b	151f
+	add	r20, r20, r5	;b	151f
+	add	r20, r20, r6	;b	151f
+	add	r20, r20, r7	;b	151f
+	add	r20, r20, r8	;b	151f
+	add	r20, r20, r9	;b	151f
+	add	r20, r20, r10	;b	151f
+	add	r20, r20, r11	;b	151f
+	add	r20, r20, r12	;b	151f
+	add	r20, r20, r13	;b	151f
+	add	r20, r20, r14	;b	151f
+	add	r20, r20, r15	;b	151f
+	add	r20, r20, r16	;b	151f
+	add	r20, r20, r17	;b	151f
+	add	r20, r20, r18	;b	151f
+	add	r20, r20, r19	;b	151f
+	mtctr	r21	;b	154f	/* r20 needs special handling */
+	mtctr	r21	;b	153f	/* r21 needs special handling */
+	add	r20, r20, r22	;b	151f
+	add	r20, r20, r23	;b	151f
+	add	r20, r20, r24	;b	151f
+	add	r20, r20, r25	;b	151f
+	add	r20, r20, r26	;b	151f
+	add	r20, r20, r27	;b	151f
+	add	r20, r20, r28	;b	151f
+	add	r20, r20, r29	;b	151f
+	add	r20, r20, r30	;b	151f
+	add	r20, r20, r31
+151:
+	rlwinm. r21,r21,19,24,28	/* offset into jump table for reg RA */
+	beq	152f			/* if reg RA is zero, don't add it */ 
+	addi	r21, r21, 150b@l	/* add start of table */
+	mtctr	r21			/* load ctr with jump address */
+	rlwinm	r21,r21,0,16,10		/* make sure we don't execute this more than once */
+	bctr				/* jump into table */
+152:
+	mfdar	r21
+	mtctr	r21			/* restore ctr reg from DAR */
+	mtdar	r20			/* save fault EA to DAR */
+	b	DARFixed		/* Go back to normal TLB handling */
+
+	/* special handling for r20,r21 since these are modified already */
+153:	lwz	r21, 4(r0)	/* load r21 from memory */
+	b	155f
+154:	mfspr	r21, M_TW	/* load r20 from M_TW */
+155:	add	r20, r20, r21	/* add it */
+	mfctr	r21		/* restore r21 */
+	b	151b
+#endif
 
 /*
  * This code finishes saving the registers to the exception frame
-- 
1.7.3.4

[PATCH 08/13] 8xx: CPU6 errata make DTLB error too big to fit.

[Joakim Tjernlund]

branch to common code in DTLB Miss instead.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |   23 ++---------------------
 1 files changed, 2 insertions(+), 21 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index 52ff914..0aab8ca 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -461,6 +461,7 @@ DataStoreTLBMiss:
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
+finish_DTLB:
 2:	li	r21, 0x00f0
 	mtspr	DAR, r21	/* Tag DAR */
 	rlwimi	r20, r21, 0, 24, 28	/* Set 24-27, clear 28 */
@@ -570,27 +571,7 @@ DARFixed:
 	ori	r20, r20, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
 	stw	r20, 0(r21)		/* and update pte in table */
 	xori	r20, r20, _PAGE_RW	/* RW bit is inverted */
-
-	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 22 and 28 must be clear.
-	 * Software indicator bits 24, 25, 26, and 27 must be
-	 * set.  All other Linux PTE bits control the behavior
-	 * of the MMU.
-	 */
-	li	r21, 0x00f0
-	mtspr	DAR, r21	/* Tag DAR */
-	rlwimi	r20, r21, 0, 24, 28	/* Set 24-27, clear 28 */
-	DO_8xx_CPU6(0x3d80, r3)
-	mtspr	MD_RPN, r20	/* Update TLB entry */
-
-	mfspr	r20, M_TW	/* Restore registers */
-	lwz	r21, 0(r0)
-	mtcr	r21
-	lwz	r21, 4(r0)
-#ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
-#endif
-	rfi
+	b	finish_DTLB
 2:
 	mfspr	r20, M_TW	/* Restore registers */
 	lwz	r21, 0(r0)
-- 
1.7.3.4

[PATCH 09/13] 8xx: Add missing Guarded setting in DTLB Error.

[Joakim Tjernlund]

only DTLB Miss did set this bit, DTLB Error needs too otherwise
the setting is lost when the page becomes dirty.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |   12 +++++++++---
 1 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index 0aab8ca..2659a1e 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -565,9 +565,15 @@ DARFixed:
 	ori	r21, r21, 1		/* Set valid bit in physical L2 page */
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	MD_TWC, r21		/* Load pte table base address */
-	mfspr	r21, MD_TWC		/* ....and get the pte address */
-	lwz	r20, 0(r21)		/* Get the pte */
-
+	mfspr	r20, MD_TWC		/* ....and get the pte address */
+	lwz	r20, 0(r20)		/* Get the pte */
+	/* Insert the Guarded flag into the TWC from the Linux PTE.
+	 * It is bit 27 of both the Linux PTE and the TWC
+	 */
+	rlwimi	r21, r20, 0, 27, 27
+	DO_8xx_CPU6(0x3b80, r3)
+	mtspr	MD_TWC, r21
+	mfspr	r21, MD_TWC		/* get the pte address again */
 	ori	r20, r20, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
 	stw	r20, 0(r21)		/* and update pte in table */
 	xori	r20, r20, _PAGE_RW	/* RW bit is inverted */
-- 
1.7.3.4

[PATCH 10/13] 8xx: Restore _PAGE_WRITETHRU

[Joakim Tjernlund]

8xx has not had WRITETHRU due to lack of bits in the pte.
After the recent rewrite of the 8xx TLB code, there are
two bits left. Use one of them to WRITETHRU.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |    8 ++++++++
 include/asm-ppc/pgtable.h  |    5 +++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index 2659a1e..43bccb1 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -435,6 +435,10 @@ DataStoreTLBMiss:
 	 * above.
 	 */
 	rlwimi	r21, r20, 0, 27, 27
+	/* Insert the WriteThru flag into the TWC from the Linux PTE.
+	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
+	 */
+	rlwimi	r21, r20, 32-5, 30, 30
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	MD_TWC, r21
 
@@ -571,6 +575,10 @@ DARFixed:
 	 * It is bit 27 of both the Linux PTE and the TWC
 	 */
 	rlwimi	r21, r20, 0, 27, 27
+	/* Insert the WriteThru flag into the TWC from the Linux PTE.
+	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
+	 */
+	rlwimi	r21, r20, 32-5, 30, 30
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	MD_TWC, r21
 	mfspr	r21, MD_TWC		/* get the pte address again */
diff --git a/include/asm-ppc/pgtable.h b/include/asm-ppc/pgtable.h
index 2ba37d3..6cfc5fc 100644
--- a/include/asm-ppc/pgtable.h
+++ b/include/asm-ppc/pgtable.h
@@ -298,12 +298,13 @@ extern unsigned long vmalloc_start;
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
 #define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
 
-/* These three software bits must be masked out when the entry is loaded
- * into the TLB, 2 SW bits free.
+/* These four software bits must be masked out when the entry is loaded
+ * into the TLB, 1 SW bits left(0x0080).
  */
 #define _PAGE_EXEC	0x0008	/* software: i-cache coherency required */
 #define _PAGE_GUARDED	0x0010	/* software: guarded access */
 #define _PAGE_ACCESSED	0x0020	/* software: page referenced */
+#define _PAGE_WRITETHRU	0x0040	/* software: caching is write through */
 
 /* Setting any bits in the nibble with the follow two controls will
  * require a TLB exception handler change.  It is assumed unused bits
-- 
1.7.3.4

[PATCH 11/13] 8xx: start using dcbX instructions in various copy routines

[Joakim Tjernlund]

Now that 8xx can fixup dcbX instructions, start using them
where possible like every other PowerPc arch do.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/misc.S |   18 ------------------
 arch/ppc/lib/string.S  |   17 -----------------
 2 files changed, 0 insertions(+), 35 deletions(-)

diff --git a/arch/ppc/kernel/misc.S b/arch/ppc/kernel/misc.S
index c1c3178..6f57957 100644
--- a/arch/ppc/kernel/misc.S
+++ b/arch/ppc/kernel/misc.S
@@ -662,15 +662,7 @@ _GLOBAL(__flush_dcache_icache)
 _GLOBAL(clear_page)
 	li	r0,4096/L1_CACHE_LINE_SIZE
 	mtctr	r0
-#ifdef CONFIG_8xx
-	li	r4, 0
-1:	stw	r4, 0(r3)
-	stw	r4, 4(r3)
-	stw	r4, 8(r3)
-	stw	r4, 12(r3)
-#else
 1:	dcbz	0,r3
-#endif
 	addi	r3,r3,L1_CACHE_LINE_SIZE
 	bdnz	1b
 	blr
@@ -695,15 +687,6 @@ _GLOBAL(copy_page)
 	addi	r3,r3,-4
 	addi	r4,r4,-4
 
-#ifdef CONFIG_8xx
-	/* don't use prefetch on 8xx */
-    	li	r0,4096/L1_CACHE_LINE_SIZE
-	mtctr	r0
-1:	COPY_16_BYTES
-	bdnz	1b
-	blr
-
-#else	/* not 8xx, we can prefetch */
 	li	r5,4
 
 #if MAX_COPY_PREFETCH > 1
@@ -744,7 +727,6 @@ _GLOBAL(copy_page)
 	li	r0,MAX_COPY_PREFETCH
 	li	r11,4
 	b	2b
-#endif	/* CONFIG_8xx */
 
 /*
  * Atomic [test&set] exchange
diff --git a/arch/ppc/lib/string.S b/arch/ppc/lib/string.S
index 6ca54b4..b6ea44b 100644
--- a/arch/ppc/lib/string.S
+++ b/arch/ppc/lib/string.S
@@ -159,14 +159,7 @@ _GLOBAL(cacheable_memzero)
 	bdnz	4b
 3:	mtctr	r9
 	li	r7,4
-#if !defined(CONFIG_8xx)
 10:	dcbz	r7,r6
-#else
-10:	stw	r4, 4(r6)
-	stw	r4, 8(r6)
-	stw	r4, 12(r6)
-	stw	r4, 16(r6)
-#endif
 	addi	r6,r6,CACHELINE_BYTES
 	bdnz	10b
 	clrlwi	r5,r8,32-LG_CACHELINE_BYTES
@@ -261,9 +254,7 @@ _GLOBAL(cacheable_memcpy)
 	mtctr	r0
 	beq	63f
 53:
-#if !defined(CONFIG_8xx)
 	dcbz	r11,r6
-#endif
 	COPY_16_BYTES
 #if L1_CACHE_LINE_SIZE >= 32
 	COPY_16_BYTES
@@ -443,13 +434,6 @@ _GLOBAL(__copy_tofrom_user)
 	li	r11,4
 	beq	63f
 
-#ifdef CONFIG_8xx
-	/* Don't use prefetch on 8xx */
-	mtctr	r0
-53:	COPY_16_BYTES_WITHEX(0)
-	bdnz	53b
-
-#else /* not CONFIG_8xx */
 	/* Here we decide how far ahead to prefetch the source */
 	li	r3,4
 	cmpwi	r0,1
@@ -502,7 +486,6 @@ _GLOBAL(__copy_tofrom_user)
 	li	r3,4
 	li	r7,0
 	bne	114b
-#endif /* CONFIG_8xx */	
 
 63:	srwi.	r0,r5,2
 	mtctr	r0
-- 
1.7.3.4

[PATCH 12/13] 8xx: Optimize ITLBMiss handler.

[Joakim Tjernlund]

Don't check for kernel space if no modules.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |    5 +++++
 1 files changed, 5 insertions(+), 0 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index 43bccb1..5dbbdb4 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -347,12 +347,17 @@ InstructionTLBMiss:
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
+#ifdef CONFIG_MODULES
+	/* Since we PIN the first 8MB text, we only get ITLB misses
+	 * for modules
+	 */
 	andi.	r21, r20, 0x0800	/* Address >= 0x80000000 */
 	beq	3f
 	lis	r21, swapper_pg_dir@h
 	ori	r21, r21, swapper_pg_dir@l
 	rlwimi	r20, r21, 0, 2, 19
 3:
+#endif
 	lwz	r21, 0(r20)	/* Get the level 1 entry */
 	rlwinm.	r20, r21,0,0,19	/* Extract page descriptor page address */
 
-- 
1.7.3.4

[PATCH 13/13] 8xx: Optimize TLB Miss handlers

[Joakim Tjernlund]

Only update pte w.r.t ACCESSED if it isn't already set

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |    7 +++++++
 1 files changed, 7 insertions(+), 0 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index 5dbbdb4..75acaa0 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -376,8 +376,12 @@ InstructionTLBMiss:
 
 #if 1
 	/* if !swap, you can delete this */
+	andi.	r21, r20, _PAGE_ACCESSED	/* test ACCESSED bit */
+	bne+	4f		/* Branch if set */
+	mfspr	r21, MD_TWC	/* get the pte address */
 	rlwimi	r20, r20, 5, _PAGE_PRESENT<<5	/* Copy PRESENT to ACCESSED */
 	stw	r20, 0(r21)	/* Update pte */
+4:
 #endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 21 and 28 must be clear.
@@ -449,9 +453,12 @@ DataStoreTLBMiss:
 
 #if 1
 	/* if !swap, you can delete this */
+	andi.	r21, r20, _PAGE_ACCESSED	/* test ACCESSED bit */
+	bne+	4f		/* Branch if set */
 	mfspr	r21, MD_TWC	/* get the pte address */
 	rlwimi	r20, r20, 5, _PAGE_PRESENT<<5	/* Copy PRESENT to ACCESSED */
 	stw	r20, 0(r21)	/* Update pte */
+4:
 #endif
 
 	/* Honour kernel RO, User NA */
-- 
1.7.3.4

Re: [PATCH 00/13] powerpc: Backport 8xx TLB to 2.4

[Willy Tarreau]

Hi Joakim,

On Mon, Jan 10, 2011 at 10:37:46PM +0100, Joakim Tjernlund wrote:
> This is a backport from 2.6 which I did to overcome 8xx CPU
> bugs. 8xx does not update the DAR register when taking a TLB
> error caused by dcbX and icbi insns which makes it very
> tricky to use these insns. Also the dcbst wrongly sets the
> the store bit when faulting into DTLB error.
> A few more bugs very found during development.
> 
> I know 2.4 is in strict maintenance mode and 8xx is obsolete
> but as it is still in use I wanted 8xx to age with grace.

Thank you very much for taking care of this, that's very much appreciated.
I'll look at this ASAP. Just a quick question in order to be certain, did
you have the opportunity to test all of these changes on real hardware ?

Thanks,
Willy

Re: [PATCH 00/13] powerpc: Backport 8xx TLB to 2.4

[Joakim Tjernlund]

Willy Tarreau <w@1wt.eu> wrote on 2011/01/11 07:09:26:
>
> Hi Joakim,
>
> On Mon, Jan 10, 2011 at 10:37:46PM +0100, Joakim Tjernlund wrote:
> > This is a backport from 2.6 which I did to overcome 8xx CPU
> > bugs. 8xx does not update the DAR register when taking a TLB
> > error caused by dcbX and icbi insns which makes it very
> > tricky to use these insns. Also the dcbst wrongly sets the
> > the store bit when faulting into DTLB error.
> > A few more bugs very found during development.
> >
> > I know 2.4 is in strict maintenance mode and 8xx is obsolete
> > but as it is still in use I wanted 8xx to age with grace.
>
> Thank you very much for taking care of this, that's very much appreciated.
> I'll look at this ASAP. Just a quick question in order to be certain, did
> you have the opportunity to test all of these changes on real hardware ?

I tested these on real 8xx HW but I used an older 2.4 linux as we haven't
moved forward on 2.4 for quite some time.
The affected files were almost identical though. Would be great if
Scott could give them a spin on 8xx with current 2.4.

      Jocke

Re: [PATCH 00/13] powerpc: Backport 8xx TLB to 2.4

[Willy Tarreau]

On Tue, Jan 11, 2011 at 09:12:44AM +0100, Joakim Tjernlund wrote:
> Willy Tarreau <w@1wt.eu> wrote on 2011/01/11 07:09:26:
> >
> > Hi Joakim,
> >
> > On Mon, Jan 10, 2011 at 10:37:46PM +0100, Joakim Tjernlund wrote:
> > > This is a backport from 2.6 which I did to overcome 8xx CPU
> > > bugs. 8xx does not update the DAR register when taking a TLB
> > > error caused by dcbX and icbi insns which makes it very
> > > tricky to use these insns. Also the dcbst wrongly sets the
> > > the store bit when faulting into DTLB error.
> > > A few more bugs very found during development.
> > >
> > > I know 2.4 is in strict maintenance mode and 8xx is obsolete
> > > but as it is still in use I wanted 8xx to age with grace.
> >
> > Thank you very much for taking care of this, that's very much appreciated.
> > I'll look at this ASAP. Just a quick question in order to be certain, did
> > you have the opportunity to test all of these changes on real hardware ?
> 
> I tested these on real 8xx HW but I used an older 2.4 linux as we haven't
> moved forward on 2.4 for quite some time.
> The affected files were almost identical though.

OK thank you for this precision. If you remember what version it was, we can
also diff it against mainline and see if we spot any relevant changes that
we need to take care of.

> Would be great if Scott could give them a spin on 8xx with current 2.4.

Indeed, that would be great. My goal really is that 2.4 users can upgrade
without wondering about any risk of regression. I appreciate a lot your
fixes, they mean some people might see that some issues have suddenly
disappeared. But it's important to stay on the non-reg side as much as
possible.

Thanks,
Willy

Re: [PATCH 00/13] powerpc: Backport 8xx TLB to 2.4

[Joakim Tjernlund]

Willy Tarreau <w@1wt.eu> wrote on 2011/01/11 21:08:53:
>
> On Tue, Jan 11, 2011 at 09:12:44AM +0100, Joakim Tjernlund wrote:
> > Willy Tarreau <w@1wt.eu> wrote on 2011/01/11 07:09:26:
> > >
> > > Hi Joakim,
> > >
> > > On Mon, Jan 10, 2011 at 10:37:46PM +0100, Joakim Tjernlund wrote:
> > > > This is a backport from 2.6 which I did to overcome 8xx CPU
> > > > bugs. 8xx does not update the DAR register when taking a TLB
> > > > error caused by dcbX and icbi insns which makes it very
> > > > tricky to use these insns. Also the dcbst wrongly sets the
> > > > the store bit when faulting into DTLB error.
> > > > A few more bugs very found during development.
> > > >
> > > > I know 2.4 is in strict maintenance mode and 8xx is obsolete
> > > > but as it is still in use I wanted 8xx to age with grace.
> > >
> > > Thank you very much for taking care of this, that's very much appreciated.
> > > I'll look at this ASAP. Just a quick question in order to be certain, did
> > > you have the opportunity to test all of these changes on real hardware ?
> >
> > I tested these on real 8xx HW but I used an older 2.4 linux as we haven't
> > moved forward on 2.4 for quite some time.
> > The affected files were almost identical though.
>
> OK thank you for this precision. If you remember what version it was, we can
> also diff it against mainline and see if we spot any relevant changes that
> we need to take care of.

2.4.21-rc6 is the base version. The we have added bits and pieces.


>
> > Would be great if Scott could give them a spin on 8xx with current 2.4.
>
> Indeed, that would be great. My goal really is that 2.4 users can upgrade
> without wondering about any risk of regression. I appreciate a lot your
> fixes, they mean some people might see that some issues have suddenly
> disappeared. But it's important to stay on the non-reg side as much as
> possible.

Should be faster too :)

Re: [PATCH 00/13] powerpc: Backport 8xx TLB to 2.4

[Joakim Tjernlund]

Joakim Tjernlund/Transmode wrote on 2011/01/11 09:12:44:
>
> Willy Tarreau <w@1wt.eu> wrote on 2011/01/11 07:09:26:
> >
> > Hi Joakim,
> >
> > On Mon, Jan 10, 2011 at 10:37:46PM +0100, Joakim Tjernlund wrote:
> > > This is a backport from 2.6 which I did to overcome 8xx CPU
> > > bugs. 8xx does not update the DAR register when taking a TLB
> > > error caused by dcbX and icbi insns which makes it very
> > > tricky to use these insns. Also the dcbst wrongly sets the
> > > the store bit when faulting into DTLB error.
> > > A few more bugs very found during development.
> > >
> > > I know 2.4 is in strict maintenance mode and 8xx is obsolete
> > > but as it is still in use I wanted 8xx to age with grace.
> >
> > Thank you very much for taking care of this, that's very much appreciated.
> > I'll look at this ASAP. Just a quick question in order to be certain, did
> > you have the opportunity to test all of these changes on real hardware ?

> I tested these on real 8xx HW but I used an older 2.4 linux as we haven't
> moved forward on 2.4 for quite some time.
> The affected files were almost identical though. Would be great if
> Scott could give them a spin on 8xx with current 2.4.

BTW, it occurred to me that the following 8xx quirk is best
done in 8xx code:

>From c1985a3b8b16d96ddce5ef90d5a15e70fb8a2aec Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Date: Tue, 11 Jan 2011 11:24:22 +0100
Subject: [PATCH] 8xx: Move invalidation of non present TLBs

8xx does not invalidate ~PRESENT TLBs, move the workaround
in mm/fault.c here to keep 8xx quirks localized.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
 arch/ppc/kernel/head_8xx.S |   12 ++++++++++--
 arch/ppc/mm/fault.c        |    7 -------
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
index 75acaa0..24b206c 100644
--- a/arch/ppc/kernel/head_8xx.S
+++ b/arch/ppc/kernel/head_8xx.S
@@ -221,7 +221,11 @@ DataAccess:
 	mr	r5,r20
 	mfspr	r4,DAR
 	stw	r4,_DAR(r21)
-	li	r20,0x00f0
+	/* invalidate ~PRESENT TLBs, 8xx MMU don't do this */
+	andis.	r20,r5,0x4000
+	beq+	1f
+	tlbie	r4
+1:	li	r20,0x00f0
 	mtspr	DAR,r20	/* Tag DAR */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	li	r20,MSR_KERNEL
@@ -238,7 +242,11 @@ InstructionAccess:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	mr	r4,r22
 	mr	r5,r23
-	li	r20,MSR_KERNEL
+	/* invalidate ~PRESENT TLBs, 8xx MMU don't do this */
+	andis.	r20,r5,0x4000
+	beq+	1f
+	tlbie	r4
+1:	li	r20,MSR_KERNEL
 	rlwimi	r20,r23,0,16,16		/* copy EE bit from saved MSR */
 	FINISH_EXCEPTION(do_page_fault)

diff --git a/arch/ppc/mm/fault.c b/arch/ppc/mm/fault.c
index 874005a..8819fb1 100644
--- a/arch/ppc/mm/fault.c
+++ b/arch/ppc/mm/fault.c
@@ -116,13 +116,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	else
 		is_write = error_code & 0x02000000;
 #endif /* CONFIG_4xx || CONFIG_BOOKE */
-#if defined(CONFIG_8xx)
-	/* 8xx does no invalidate TLBs that are ~PRESENT,
-	 * do it here.
-	 */
-	if (error_code & 0x40000000)
-		_tlbie(address);
-#endif
 #if defined(CONFIG_XMON) || defined(CONFIG_KGDB)
 	if (debugger_fault_handler && regs->trap == 0x300) {
 		debugger_fault_handler(regs);
--
1.7.3.4

Scott, what do you think of this? Is it safe to call tlbie in this context?

    Jocke

Re: [PATCH 00/13] powerpc: Backport 8xx TLB to 2.4

[Scott Wood]

On Tue, 11 Jan 2011 11:56:32 +0100
Joakim Tjernlund <joakim.tjernlund@transmode.se> wrote:

> Joakim Tjernlund/Transmode wrote on 2011/01/11 09:12:44:
> >
> > Willy Tarreau <w@1wt.eu> wrote on 2011/01/11 07:09:26:
> > >
> > > Hi Joakim,
> > >
> > > On Mon, Jan 10, 2011 at 10:37:46PM +0100, Joakim Tjernlund wrote:
> > > > This is a backport from 2.6 which I did to overcome 8xx CPU
> > > > bugs. 8xx does not update the DAR register when taking a TLB
> > > > error caused by dcbX and icbi insns which makes it very
> > > > tricky to use these insns. Also the dcbst wrongly sets the
> > > > the store bit when faulting into DTLB error.
> > > > A few more bugs very found during development.
> > > >
> > > > I know 2.4 is in strict maintenance mode and 8xx is obsolete
> > > > but as it is still in use I wanted 8xx to age with grace.
> > >
> > > Thank you very much for taking care of this, that's very much appreciated.
> > > I'll look at this ASAP. Just a quick question in order to be certain, did
> > > you have the opportunity to test all of these changes on real hardware ?
> 
> > I tested these on real 8xx HW but I used an older 2.4 linux as we haven't
> > moved forward on 2.4 for quite some time.
> > The affected files were almost identical though. Would be great if
> > Scott could give them a spin on 8xx with current 2.4.

Is ep88xc (the board I have easily available to test) supported in
mainline 2.4?  I don't see a platform file, defconfig, or bootwrapper
code that obviously covers it.

Is there anyone out there actually using 8xx on top-of-tree mainline
2.4 who can test it?

> BTW, it occurred to me that the following 8xx quirk is best
> done in 8xx code:
> 
> From c1985a3b8b16d96ddce5ef90d5a15e70fb8a2aec Mon Sep 17 00:00:00 2001
> From: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
> Date: Tue, 11 Jan 2011 11:24:22 +0100
> Subject: [PATCH] 8xx: Move invalidation of non present TLBs
> 
> 8xx does not invalidate ~PRESENT TLBs, move the workaround
> in mm/fault.c here to keep 8xx quirks localized.
> 
> Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
> ---
>  arch/ppc/kernel/head_8xx.S |   12 ++++++++++--
>  arch/ppc/mm/fault.c        |    7 -------
>  2 files changed, 10 insertions(+), 9 deletions(-)
> 
> diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
> index 75acaa0..24b206c 100644
> --- a/arch/ppc/kernel/head_8xx.S
> +++ b/arch/ppc/kernel/head_8xx.S
> @@ -221,7 +221,11 @@ DataAccess:
>  	mr	r5,r20
>  	mfspr	r4,DAR
>  	stw	r4,_DAR(r21)
> -	li	r20,0x00f0
> +	/* invalidate ~PRESENT TLBs, 8xx MMU don't do this */
> +	andis.	r20,r5,0x4000
> +	beq+	1f
> +	tlbie	r4
> +1:	li	r20,0x00f
>  	mtspr	DAR,r20	/* Tag DAR */
>  	addi	r3,r1,STACK_FRAME_OVERHEAD
>  	li	r20,MSR_KERNEL
> @@ -238,7 +242,11 @@ InstructionAccess:
>  	addi	r3,r1,STACK_FRAME_OVERHEAD
>  	mr	r4,r22
>  	mr	r5,r23
> -	li	r20,MSR_KERNEL
> +	/* invalidate ~PRESENT TLBs, 8xx MMU don't do this */
> +	andis.	r20,r5,0x4000
> +	beq+	1f
> +	tlbie	r4
> +1:	li	r20,MSR_KERNEL
>  	rlwimi	r20,r23,0,16,16		/* copy EE bit from saved MSR */
>  	FINISH_EXCEPTION(do_page_fault)
> 
> diff --git a/arch/ppc/mm/fault.c b/arch/ppc/mm/fault.c
> index 874005a..8819fb1 100644
> --- a/arch/ppc/mm/fault.c
> +++ b/arch/ppc/mm/fault.c
> @@ -116,13 +116,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
>  	else
>  		is_write = error_code & 0x02000000;
>  #endif /* CONFIG_4xx || CONFIG_BOOKE */
> -#if defined(CONFIG_8xx)
> -	/* 8xx does no invalidate TLBs that are ~PRESENT,
> -	 * do it here.
> -	 */
> -	if (error_code & 0x40000000)
> -		_tlbie(address);
> -#endif
>  #if defined(CONFIG_XMON) || defined(CONFIG_KGDB)
>  	if (debugger_fault_handler && regs->trap == 0x300) {
>  		debugger_fault_handler(regs);
> --
> 1.7.3.4
> 
> Scott, what do you think of this? Is it safe to call tlbie in this context?

I'd guess so (I assume the concern is MMU translation being off?), but I
don't have any particular knowledge about this.  I'd be checking the
same manual that you have. :-)

-Scott

Re: [PATCH 00/13] powerpc: Backport 8xx TLB to 2.4

[Joakim Tjernlund]

Scott Wood <scottwood@freescale.com> wrote on 2011/01/13 21:44:00:
> > BTW, it occurred to me that the following 8xx quirk is best
> > done in 8xx code:
> >
> > From c1985a3b8b16d96ddce5ef90d5a15e70fb8a2aec Mon Sep 17 00:00:00 2001
> > From: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
> > Date: Tue, 11 Jan 2011 11:24:22 +0100
> > Subject: [PATCH] 8xx: Move invalidation of non present TLBs
> >
> > 8xx does not invalidate ~PRESENT TLBs, move the workaround
> > in mm/fault.c here to keep 8xx quirks localized.
> >
> > Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
> > ---
> >  arch/ppc/kernel/head_8xx.S |   12 ++++++++++--
> >  arch/ppc/mm/fault.c        |    7 -------
> >  2 files changed, 10 insertions(+), 9 deletions(-)
> >
> > diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
> > index 75acaa0..24b206c 100644
> > --- a/arch/ppc/kernel/head_8xx.S
> > +++ b/arch/ppc/kernel/head_8xx.S
> > @@ -221,7 +221,11 @@ DataAccess:
> >     mr   r5,r20
> >     mfspr   r4,DAR
> >     stw   r4,_DAR(r21)
> > -   li   r20,0x00f0
> > +   /* invalidate ~PRESENT TLBs, 8xx MMU don't do this */
> > +   andis.   r20,r5,0x4000
> > +   beq+   1f
> > +   tlbie   r4
> > +1:   li   r20,0x00f
> >     mtspr   DAR,r20   /* Tag DAR */
> >     addi   r3,r1,STACK_FRAME_OVERHEAD
> >     li   r20,MSR_KERNEL
> > @@ -238,7 +242,11 @@ InstructionAccess:
> >     addi   r3,r1,STACK_FRAME_OVERHEAD
> >     mr   r4,r22
> >     mr   r5,r23
> > -   li   r20,MSR_KERNEL
> > +   /* invalidate ~PRESENT TLBs, 8xx MMU don't do this */
> > +   andis.   r20,r5,0x4000
> > +   beq+   1f
> > +   tlbie   r4
> > +1:   li   r20,MSR_KERNEL
> >     rlwimi   r20,r23,0,16,16      /* copy EE bit from saved MSR */
> >     FINISH_EXCEPTION(do_page_fault)
> >
> > diff --git a/arch/ppc/mm/fault.c b/arch/ppc/mm/fault.c
> > index 874005a..8819fb1 100644
> > --- a/arch/ppc/mm/fault.c
> > +++ b/arch/ppc/mm/fault.c
> > @@ -116,13 +116,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
> >     else
> >        is_write = error_code & 0x02000000;
> >  #endif /* CONFIG_4xx || CONFIG_BOOKE */
> > -#if defined(CONFIG_8xx)
> > -   /* 8xx does no invalidate TLBs that are ~PRESENT,
> > -    * do it here.
> > -    */
> > -   if (error_code & 0x40000000)
> > -      _tlbie(address);
> > -#endif
> >  #if defined(CONFIG_XMON) || defined(CONFIG_KGDB)
> >     if (debugger_fault_handler && regs->trap == 0x300) {
> >        debugger_fault_handler(regs);
> > --
> > 1.7.3.4
> >
> > Scott, what do you think of this? Is it safe to call tlbie in this context?
>
> I'd guess so (I assume the concern is MMU translation being off?), but I
> don't have any particular knowledge about this.  I'd be checking the
> same manual that you have. :-)

I noticed 2.6 uses tlbie in CPU15 errata workaround so it is fine
and it is better to invalidate as soon as possible to free up a TLB slot.
Runs on my old 2.4 too.

 Jocke