[PATCH] powerpc/8xx: fix regression introduced by cache coherency rewrite

Mon Oct 5 18:28:15 EST 2009

Benjamin Herrenschmidt <benh at kernel.crashing.org> wrote on 04/10/2009 22:28:38:
>
>
> > I have managed to update the TLB code to make proper use of dirty and accessed states.
> > Advantages are:
> >  - I/D TLB Miss never needs to write to the linux pte, saving a few cycles
>
> That's good, that leaves us with only 40x to fix now. Also we can remove
> atomic updates of PTEs for all non-hash. It's pointless on those CPUs
> anyway.
>
> >  - Accessed is only set by I/D TLB Error, should be a plus when SWAP is used.
>
> No need for that neither.
>
> ISI/DSI shouldn't touch the PTE. They should just fall back to C code
> which takes care of it all.l
>
> >  - _PAGE_DIRTY is mapped to 0x100, the changed bit, and is set directly
> >     and there will be no extra DTLB Error to actually set the changed bit
> >     when a page has been made dirty.
> > - Proper RO/RW mapping of user space.
> >
> > Cons:
> >  - 4 more insn in TLB Miss handlers, but the since the linux pte isn't
> >    written it should still be a win.
> >
> > However, I did this on my 2.4 tree but I can port it to 2.6 if you guys
> > can test it for me.

So it was easy to update the patch for 2.6, this is on top
of "powerpc, 8xx: DTLB Error must check for more errors."
You probably need the extra tlbil_va(), but let us know if you
can get away without it.

Scott and Rex, please give this a spin. Comments welcome too :)

     Jocke

>From 7880d402cc05dd6e27d8804218ee4c80a879403e Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <Joakim.Tjernlund at transmode.se>
Date: Mon, 5 Oct 2009 09:08:31 +0200
Subject: [PATCH] 8xx: get rid of _PAGE_HWWRITE dependency in MMU.

Update the TLB asm to make proper use of _PAGE_DIRY and _PAGE_ACCESSED.
Pros:
 - I/D TLB Miss never needs to write to the linux pte.
 - _PAGE_ACCESSED is only set on I/D TLB Error fixing accounting
 - _PAGE_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.
Cons:
 - 4 more instructions in I/D TLB Miss, but the since the linux pte is
   not written anymore, it should still be a win.
---
 arch/powerpc/include/asm/pte-8xx.h |    9 +-
 arch/powerpc/kernel/head_8xx.S     |  163 ++++++++++++++++++++++++++----------
 2 files changed, 122 insertions(+), 50 deletions(-)

diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/pte-8xx.h
index 8c6e312..af541a2 100644
--- a/arch/powerpc/include/asm/pte-8xx.h
+++ b/arch/powerpc/include/asm/pte-8xx.h
@@ -32,22 +32,21 @@
 #define _PAGE_FILE	0x0002	/* when !present: nonlinear file mapping */
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
 #define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
+#define _PAGE_DIRTY	0x0100	/* C: page changed */

 /* These five software bits must be masked out when the entry is loaded
  * into the TLB.
  */
 #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_USER	0x0020	/* software: User space access */

 /* 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.
  */
-#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_RW	0x0400	/* lsb PP bits */
+#define _PAGE_ACCESSED	0x0800	/* msb PP bits */

 #define _PMD_PRESENT	0x0001
 #define _PMD_BAD	0x0ff0
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 118bb05..e111d2f 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -333,21 +333,15 @@ InstructionTLBMiss:
 	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
 	lwz	r10, 0(r11)	/* Get the pte */

-#ifdef CONFIG_SWAP
-	/* do not set the _PAGE_ACCESSED bit of a non-present page */
-	andi.	r11, r10, _PAGE_PRESENT
-	beq	4f
-	ori	r10, r10, _PAGE_ACCESSED
-	mfspr	r11, SPRN_MD_TWC	/* get the pte address again */
-	stw	r10, 0(r11)
-4:
-#else
-	ori	r10, r10, _PAGE_ACCESSED
-	stw	r10, 0(r11)
-#endif
-
+	andi.	r11, r10, _PAGE_USER | _PAGE_ACCESSED
+	cmpwi	cr0, r11, _PAGE_USER | _PAGE_ACCESSED
+	beq-	cr0, 5f	/* branch if access allowed */
+	rlwinm	r10, r10, 0, 22, 19 /* r20 &= ~(_PAGE_ACCESSED | _PAGE_RW) */
+	b	6f
+5:	xori	r10, r10, _PAGE_RW /* invert RW bit */
+6:
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bit 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.
@@ -409,21 +403,15 @@ DataStoreTLBMiss:
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	SPRN_MD_TWC, r11

-#ifdef CONFIG_SWAP
-	/* do not set the _PAGE_ACCESSED bit of a non-present page */
-	andi.	r11, r10, _PAGE_PRESENT
-	beq	4f
-	ori	r10, r10, _PAGE_ACCESSED
-4:
-	/* and update pte in table */
-#else
-	ori	r10, r10, _PAGE_ACCESSED
-#endif
-	mfspr	r11, SPRN_MD_TWC	/* get the pte address again */
-	stw	r10, 0(r11)
-
+	andi.	r11, r10, _PAGE_USER | _PAGE_ACCESSED
+	cmpwi	cr0, r11, _PAGE_USER | _PAGE_ACCESSED
+	beq-	cr0, 5f	/* branch if access allowed */
+	rlwinm	r10, r10, 0, 22, 19 /* r20 &= ~(_PAGE_ACCESSED | _PAGE_RW) */
+	b	6f
+5:	xori	r10, r10, _PAGE_RW /* invert RW bit */
+6:
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bit 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.
@@ -448,6 +436,91 @@ DataStoreTLBMiss:
  */
 	. = 0x1300
 InstructionTLBError:
+#ifdef CONFIG_8xx_CPU6
+	stw	r3, 8(r0)
+#endif
+	DO_8xx_CPU6(0x3f80, r3)
+	mtspr	SPRN_M_TW, r10	/* Save a couple of working registers */
+	mfcr	r10
+	stw	r10, 0(r0)
+	stw	r11, 4(r0)
+
+	mfspr	r11, SRR1
+	andis.	r11, r11, 0x5000	/* no translation, guarded */
+	bne	2f
+
+	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
+#ifdef CONFIG_8xx_CPU15
+	addi	r11, r10, 0x1000
+	tlbie	r11
+	addi	r11, r10, -0x1000
+	tlbie	r11
+#endif
+	DO_8xx_CPU6(0x3780, r3)
+	mtspr	SPRN_MD_EPN, r10	/* Have to use MD_EPN for walk, MI_EPN can't */
+	mfspr	r10, SPRN_M_TWB	/* Get level 1 table entry address */
+
+	/* If we are faulting a kernel address, we have to use the
+	 * kernel page tables.
+	 */
+	andi.	r11, r10, 0x0800	/* Address >= 0x80000000 */
+	beq	3f
+	lis	r11, swapper_pg_dir at h
+	ori	r11, r11, swapper_pg_dir at l
+	rlwimi	r10, r11, 0, 2, 19
+3:
+	lwz	r11, 0(r10)	/* Get the level 1 entry */
+	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
+	beq	2f		/* If zero, don't try to find a pte */
+
+	/* We have a pte table, so load the MI_TWC with the attributes
+	 * for this "segment."
+	 */
+	ori	r11,r11,1		/* Set valid bit */
+	DO_8xx_CPU6(0x2b80, r3)
+	mtspr	SPRN_MI_TWC, r11	/* Set segment attributes */
+	DO_8xx_CPU6(0x3b80, r3)
+	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
+
+	mfspr	r11, SRR1
+	andi.	r11, r11, 0x4000 /* MSR[PR] */
+	mfspr	r11, MD_TWC	/* ....and get the pte address */
+	lwz	r10, 0(r11)	/* Get the pte */
+	beq	5f /* Kernel access always OK */
+	andi.	r11,r10, _PAGE_USER
+	beq	2f
+5:	ori	r10, r10, _PAGE_ACCESSED
+	mfspr	r21, MD_TWC	/* ....and get the pte address */
+	stw	r10, 0(r11)
+	xori	r10, r10, _PAGE_RW /* invert RW bit */
+
+	/* The Linux PTE won't go exactly into the MMU TLB.
+	 * Software indicator bit 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	r11, 0x00f0
+	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
+	DO_8xx_CPU6(0x2d80, r3)
+	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
+
+	mfspr	r10, SPRN_M_TW	/* Restore registers */
+	lwz	r11, 0(r0)
+	mtcr	r11
+	lwz	r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
+	lwz	r3, 8(r0)
+#endif
+	rfi
+
+2:	mfspr	r10, SPRN_M_TW	/* Restore registers */
+	lwz	r11, 0(r0)
+	mtcr	r11
+	lwz	r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
+	lwz	r3, 8(r0)
+#endif
 	b	InstructionAccess

 /* This is the data TLB error on the MPC8xx.  This could be due to
@@ -472,8 +545,8 @@ DataTLBError:
 	/* First, make sure this was a store operation.
 	*/
 	mfspr	r10, SPRN_DSISR
-	andis.	r11, r10, 0x4800 /* no translation, no permission. */
-	bne	2f	/* branch if either is set */
+	andis.	r11, r10, 0x4000 /* no translation */
+	bne	2f	/* branch if set */

 	/* 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
@@ -522,26 +595,26 @@ DataTLBError:
 	mfspr	r11, SPRN_MD_TWC		/* ....and get the pte address */
 	lwz	r10, 0(r11)		/* Get the pte */

-	andi.	r11, r10, _PAGE_RW	/* Is it writeable? */
-	beq	2f			/* Bail out if not */
+	mfspr	r11, SRR1
+	andi.	r11, r11, 0x4000 /* MSR[PR] */
+	beq	5f /* Kernel access always OK */
+	andi.	r11,r10, _PAGE_USER
+	beq	2f
+5:	mfspr	r11, DSISR
+	andis.	r11, r11, 0x0200	/* store */
+	beq	6f
+	andi.	r11, r10, _PAGE_RW	/* writeable? */
+	beq	2f /* branch if not */
+	ori	r10, r10, _PAGE_DIRTY | _PAGE_HWWRITE
+6:	ori	r10, r10, _PAGE_ACCESSED

-	/* Update 'changed', among others.
-	*/
-#ifdef CONFIG_SWAP
-	ori	r10, r10, _PAGE_DIRTY|_PAGE_HWWRITE
-	/* do not set the _PAGE_ACCESSED bit of a non-present page */
-	andi.	r11, r10, _PAGE_PRESENT
-	beq	4f
-	ori	r10, r10, _PAGE_ACCESSED
-4:
-#else
-	ori	r10, r10, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
-#endif
 	mfspr	r11, SPRN_MD_TWC		/* Get pte address again */
 	stw	r10, 0(r11)		/* and update pte in table */

+	xori	r10, r10, _PAGE_RW	/* Invert RW bit */
+
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bit 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.
--
1.6.4.4

