[PATCH v5 09/22] powerpc/8xx: don't use r12/SPRN_SPRG_SCRATCH2 in TLB Miss handlers

From: Christophe Leroy
Date: Tue Sep 25 2018 - 12:52:16 EST


This patch reworks the TLB Miss handler in order to not use r12
register, hence avoiding having to save it into SPRN_SPRG_SCRATCH2.

In the DAR Fixup code we can now use SPRN_M_TW, freeing
SPRN_SPRG_SCRATCH2.

Then SPRN_SPRG_SCRATCH2 may be used for something else in the future.

Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxx>
---
arch/powerpc/kernel/head_8xx.S | 110 ++++++++++++++++++-----------------------
1 file changed, 49 insertions(+), 61 deletions(-)

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 50e97027b507..d69c6e3d5cc1 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -302,91 +302,88 @@ SystemCall:
*/

#ifdef CONFIG_8xx_CPU15
-#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr) \
- addi tmp, addr, PAGE_SIZE; \
- tlbie tmp; \
- addi tmp, addr, -PAGE_SIZE; \
- tlbie tmp
+#define INVALIDATE_ADJACENT_PAGES_CPU15(addr) \
+ addi addr, addr, PAGE_SIZE; \
+ tlbie addr; \
+ addi addr, addr, -(PAGE_SIZE << 1); \
+ tlbie addr; \
+ addi addr, addr, PAGE_SIZE
#else
-#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr)
+#define INVALIDATE_ADJACENT_PAGES_CPU15(addr)
#endif

InstructionTLBMiss:
mtspr SPRN_SPRG_SCRATCH0, r10
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
mtspr SPRN_SPRG_SCRATCH1, r11
-#ifdef ITLB_MISS_KERNEL
- mtspr SPRN_SPRG_SCRATCH2, r12
#endif

/* If we are faulting a kernel address, we have to use the
* kernel page tables.
*/
mfspr r10, SPRN_SRR0 /* Get effective address of fault */
- INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10)
+ INVALIDATE_ADJACENT_PAGES_CPU15(r10)
mtspr SPRN_MD_EPN, r10
/* Only modules will cause ITLB Misses as we always
* pin the first 8MB of kernel memory */
#ifdef ITLB_MISS_KERNEL
- mfcr r12
+ mfcr r11
#if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT)
- andis. r11, r10, 0x8000 /* Address >= 0x80000000 */
+ cmpi cr0, r10, 0 /* Address >= 0x80000000 */
#else
- rlwinm r11, r10, 16, 0xfff8
- cmpli cr0, r11, PAGE_OFFSET@h
+ rlwinm r10, r10, 16, 0xfff8
+ cmpli cr0, r10, PAGE_OFFSET@h
#ifndef CONFIG_PIN_TLB_TEXT
/* It is assumed that kernel code fits into the first 8M page */
-0: cmpli cr7, r11, (PAGE_OFFSET + 0x0800000)@h
+0: cmpli cr7, r10, (PAGE_OFFSET + 0x0800000)@h
patch_site 0b, patch__itlbmiss_linmem_top
#endif
#endif
#endif
- mfspr r11, SPRN_M_TWB /* Get level 1 table */
+ mfspr r10, SPRN_M_TWB /* Get level 1 table */
#ifdef ITLB_MISS_KERNEL
#if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT)
- beq+ 3f
+ bge+ 3f
#else
blt+ 3f
#endif
#ifndef CONFIG_PIN_TLB_TEXT
blt cr7, ITLBMissLinear
#endif
- rlwinm r11, r11, 0, 20, 31
- oris r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha
+ rlwinm r10, r10, 0, 20, 31
+ oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
3:
#endif
- lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */
+ lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
+ mtspr SPRN_MI_TWC, r10 /* Set segment attributes */

- mtspr SPRN_MD_TWC, r11
+ mtspr SPRN_MD_TWC, r10
mfspr r10, SPRN_MD_TWC
lwz r10, 0(r10) /* Get the pte */

#ifdef ITLB_MISS_KERNEL
- mtcr r12
+ mtcr r11
#endif
- /* Load the MI_TWC with the attributes for this "segment." */
- mtspr SPRN_MI_TWC, r11 /* Set segment attributes */
-
#ifdef CONFIG_SWAP
rlwinm r11, r10, 32-5, _PAGE_PRESENT
and r11, r11, r10
rlwimi r10, r11, 0, _PAGE_PRESENT
#endif
- li r11, RPN_PATTERN | 0x200
/* The Linux PTE won't go exactly into the MMU TLB.
* Software indicator bits 20 and 23 must be clear.
* Software indicator bits 22, 24, 25, 26, and 27 must be
* set. All other Linux PTE bits control the behavior
* of the MMU.
*/
- rlwimi r11, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */
- rlwimi r10, r11, 0, 0x0ff0 /* Set 22, 24-27, clear 20,23 */
+ rlwimi r10, r10, 0, 0x0f00 /* Clear bits 20-23 */
+ rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */
+ ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */
mtspr SPRN_MI_RPN, r10 /* Update TLB entry */

/* Restore registers */
0: mfspr r10, SPRN_SPRG_SCRATCH0
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
mfspr r11, SPRN_SPRG_SCRATCH1
-#ifdef ITLB_MISS_KERNEL
- mfspr r12, SPRN_SPRG_SCRATCH2
#endif
rfi
patch_site 0b, patch__itlbmiss_exit_1
@@ -397,9 +394,8 @@ InstructionTLBMiss:
addi r10, r10, 1
stw r10, (itlb_miss_counter - PAGE_OFFSET)@l(0)
mfspr r10, SPRN_SPRG_SCRATCH0
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
mfspr r11, SPRN_SPRG_SCRATCH1
-#ifdef ITLB_MISS_KERNEL
- mfspr r12, SPRN_SPRG_SCRATCH2
#endif
rfi
#endif
@@ -408,40 +404,37 @@ InstructionTLBMiss:
DataStoreTLBMiss:
mtspr SPRN_SPRG_SCRATCH0, r10
mtspr SPRN_SPRG_SCRATCH1, r11
- mtspr SPRN_SPRG_SCRATCH2, r12
- mfcr r12
+ mfcr r11

/* If we are faulting a kernel address, we have to use the
* kernel page tables.
*/
mfspr r10, SPRN_MD_EPN
- rlwinm r11, r10, 16, 0xfff8
- cmpli cr0, r11, PAGE_OFFSET@h
- mfspr r11, SPRN_M_TWB /* Get level 1 table */
- blt+ 3f
- rlwinm r11, r10, 16, 0xfff8
+ rlwinm r10, r10, 16, 0xfff8
+ cmpli cr0, r10, PAGE_OFFSET@h
#ifndef CONFIG_PIN_TLB_IMMR
- cmpli cr0, r11, VIRT_IMMR_BASE@h
+ cmpli cr6, r10, VIRT_IMMR_BASE@h
#endif
-0: cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h
+0: cmpli cr7, r10, (PAGE_OFFSET + 0x1800000)@h
patch_site 0b, patch__dtlbmiss_linmem_top
+
+ mfspr r10, SPRN_M_TWB /* Get level 1 table */
+ blt+ 3f
#ifndef CONFIG_PIN_TLB_IMMR
-0: beq- DTLBMissIMMR
+0: beq- cr6, DTLBMissIMMR
patch_site 0b, patch__dtlbmiss_immr_jmp
#endif
blt cr7, DTLBMissLinear
- mfspr r11, SPRN_M_TWB /* Get level 1 table */
- rlwinm r11, r11, 0, 20, 31
- oris r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha
+ rlwinm r10, r10, 0, 20, 31
+ oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
3:
- lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */
+ mtcr r11
+ lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */

mtspr SPRN_MD_TWC, r11
mfspr r10, SPRN_MD_TWC
lwz r10, 0(r10) /* Get the pte */

- mtcr r12
-
/* Insert the Guarded flag into the TWC from the Linux PTE.
* It is bit 27 of both the Linux PTE and the TWC (at least
* I got that right :-). It will be better when we can put
@@ -479,7 +472,6 @@ DataStoreTLBMiss:

0: mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
- mfspr r12, SPRN_SPRG_SCRATCH2
rfi
patch_site 0b, patch__dtlbmiss_exit_1

@@ -490,7 +482,6 @@ DataStoreTLBMiss:
stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
- mfspr r12, SPRN_SPRG_SCRATCH2
rfi
#endif

@@ -598,7 +589,7 @@ InstructionBreakpoint:
* not enough space in the DataStoreTLBMiss area.
*/
DTLBMissIMMR:
- mtcr r12
+ mtcr r11
/* Set 512k byte guarded page and mark it valid */
li r10, MD_PS512K | MD_GUARDED | MD_SVALID
mtspr SPRN_MD_TWC, r10
@@ -613,16 +604,15 @@ DTLBMissIMMR:

0: mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
- mfspr r12, SPRN_SPRG_SCRATCH2
rfi
patch_site 0b, patch__dtlbmiss_exit_2

DTLBMissLinear:
- mtcr r12
+ mtcr r11
/* Set 8M byte page and mark it valid */
li r11, MD_PS8MEG | MD_SVALID
mtspr SPRN_MD_TWC, r11
- rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */
+ rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */
ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
_PAGE_PRESENT
mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
@@ -632,24 +622,22 @@ DTLBMissLinear:

0: mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
- mfspr r12, SPRN_SPRG_SCRATCH2
rfi
patch_site 0b, patch__dtlbmiss_exit_3

#ifndef CONFIG_PIN_TLB_TEXT
ITLBMissLinear:
- mtcr r12
+ mtcr r11
/* Set 8M byte page and mark it valid */
li r11, MI_PS8MEG | MI_SVALID
mtspr SPRN_MI_TWC, r11
- rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */
+ rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */
ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
_PAGE_PRESENT
mtspr SPRN_MI_RPN, r10 /* Update TLB entry */

0: mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
- mfspr r12, SPRN_SPRG_SCRATCH2
rfi
patch_site 0b, patch__itlbmiss_exit_2
#endif
@@ -661,7 +649,7 @@ ITLBMissLinear:
/* define if you don't want to use self modifying code */
#define NO_SELF_MODIFYING_CODE
FixupDAR:/* Entry point for dcbx workaround. */
- mtspr SPRN_SPRG_SCRATCH2, r10
+ mtspr SPRN_M_TW, r10
/* fetch instruction from memory. */
mfspr r10, SPRN_SRR0
mtspr SPRN_MD_EPN, r10
@@ -706,7 +694,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
beq+ 142f
cmpwi cr0, r10, 1964 /* Is icbi? */
beq+ 142f
-141: mfspr r10,SPRN_SPRG_SCRATCH2
+141: mfspr r10,SPRN_M_TW
b DARFixed /* Nope, go back to normal TLB processing */

200:
@@ -741,7 +729,7 @@ modified_instr:
bne+ 143f
subf r10,r0,r10 /* r10=r10-r0, only if reg RA is r0 */
143: mtdar r10 /* store faulting EA in DAR */
- mfspr r10,SPRN_SPRG_SCRATCH2
+ mfspr r10,SPRN_M_TW
b DARFixed /* Go back to normal TLB handling */
#else
mfctr r10
@@ -795,7 +783,7 @@ modified_instr:
mfdar r11
mtctr r11 /* restore ctr reg from DAR */
mtdar r10 /* save fault EA to DAR */
- mfspr r10,SPRN_SPRG_SCRATCH2
+ mfspr r10,SPRN_M_TW
b DARFixed /* Go back to normal TLB handling */

/* special handling for r10,r11 since these are modified already */
--
2.13.3