aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/hash_low_64.S
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/mm/hash_low_64.S')
-rw-r--r--arch/powerpc/mm/hash_low_64.S261
1 files changed, 161 insertions, 100 deletions
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 602aeb06d29..057cbbb4c57 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -63,7 +63,7 @@ _GLOBAL(__hash_page_4K)
/* Save non-volatile registers.
* r31 will hold "old PTE"
* r30 is "new PTE"
- * r29 is "va"
+ * r29 is vpn
* r28 is a hash value
* r27 is hashtab mask (maybe dynamic patched instead ?)
*/
@@ -111,25 +111,33 @@ BEGIN_FTR_SECTION
cmpdi r9,0 /* check segment size */
bne 3f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
- /* Calc va and put it in r29 */
- rldicr r29,r5,28,63-28
- rldicl r3,r3,0,36
- or r29,r3,r29
-
- /* Calculate hash value for primary slot and store it in r28 */
- rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */
- rldicl r0,r3,64-12,48 /* (ea >> 12) & 0xffff */
- xor r28,r5,r0
+ /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT - VPN_SHIFT
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
+ or r29,r28,r29
+ /*
+ * Calculate hash value for primary slot and store it in r28
+ * r3 = va, r5 = vsid
+ * r0 = (va >> 12) & ((1ul << (28 - 12)) -1)
+ */
+ rldicl r0,r3,64-12,48
+ xor r28,r5,r0 /* hash */
b 4f
-3: /* Calc VA and hash in r29 and r28 for 1T segment */
- sldi r29,r5,40 /* vsid << 40 */
- clrldi r3,r3,24 /* ea & 0xffffffffff */
- rldic r28,r5,25,25 /* (vsid << 25) & 0x7fffffffff */
- clrldi r5,r5,40 /* vsid & 0xffffff */
- rldicl r0,r3,64-12,36 /* (ea >> 12) & 0xfffffff */
- xor r28,r28,r5
- or r29,r3,r29 /* VA */
+3: /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
+ or r29,r28,r29
+
+ /*
+ * calculate hash value for primary slot and
+ * store it in r28 for 1T segment
+ * r3 = va, r5 = vsid
+ */
+ sldi r28,r5,25 /* vsid << 25 */
+ /* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */
+ rldicl r0,r3,64-12,36
+ xor r28,r28,r5 /* vsid ^ ( vsid << 25) */
xor r28,r28,r0 /* hash */
/* Convert linux PTE bits into HW equivalents */
@@ -140,7 +148,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/
andc r0,r30,r0 /* r0 = pte & ~r0 */
rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */
- ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */
+ /*
+ * Always add "C" bit for perf. Memory coherence is always enabled
+ */
+ ori r3,r3,HPTE_R_C | HPTE_R_M
/* We eventually do the icache sync here (maybe inline that
* code rather than call a C function...)
@@ -148,7 +159,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
BEGIN_FTR_SECTION
mr r4,r30
mr r5,r7
- bl .hash_page_do_lazy_icache
+ bl hash_page_do_lazy_icache
END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
/* At this point, r3 contains new PP bits, save them in
@@ -185,11 +196,13 @@ htab_insert_pte:
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,0 /* !bolted, !secondary */
li r8,MMU_PAGE_4K /* page size */
- ld r9,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+ li r9,MMU_PAGE_4K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
bl . /* Patched by htab_finish_init() */
cmpdi 0,r3,0
bge htab_pte_insert_ok /* Insertion successful */
@@ -208,11 +221,13 @@ _GLOBAL(htab_call_hpte_insert1)
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,HPTE_V_SECONDARY /* !bolted, secondary */
li r8,MMU_PAGE_4K /* page size */
- ld r9,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+ li r9,MMU_PAGE_4K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
bl . /* Patched by htab_finish_init() */
cmpdi 0,r3,0
bge+ htab_pte_insert_ok /* Insertion successful */
@@ -229,7 +244,8 @@ _GLOBAL(htab_call_hpte_insert2)
2: and r0,r5,r27
rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */
/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
bl . /* Patched by htab_finish_init() */
/* Try all again */
@@ -278,11 +294,13 @@ htab_modify_pte:
add r3,r0,r3 /* add slot idx */
/* Call ppc_md.hpte_updatepp */
- mr r5,r29 /* va */
- li r6,MMU_PAGE_4K /* page size */
- ld r7,STK_PARAM(R9)(r1) /* segment size */
- ld r8,STK_PARAM(R8)(r1) /* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+ mr r5,r29 /* vpn */
+ li r6,MMU_PAGE_4K /* base page size */
+ li r7,MMU_PAGE_4K /* actual page size */
+ ld r8,STK_PARAM(R9)(r1) /* segment size */
+ ld r9,STK_PARAM(R8)(r1) /* get "local" param */
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
bl . /* Patched by htab_finish_init() */
/* if we failed because typically the HPTE wasn't really here
@@ -339,7 +357,7 @@ _GLOBAL(__hash_page_4K)
/* Save non-volatile registers.
* r31 will hold "old PTE"
* r30 is "new PTE"
- * r29 is "va"
+ * r29 is vpn
* r28 is a hash value
* r27 is hashtab mask (maybe dynamic patched instead ?)
* r26 is the hidx mask
@@ -394,25 +412,41 @@ BEGIN_FTR_SECTION
cmpdi r9,0 /* check segment size */
bne 3f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
- /* Calc va and put it in r29 */
- rldicr r29,r5,28,63-28 /* r29 = (vsid << 28) */
- rldicl r3,r3,0,36 /* r3 = (ea & 0x0fffffff) */
- or r29,r3,r29 /* r29 = va */
-
- /* Calculate hash value for primary slot and store it in r28 */
- rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */
- rldicl r0,r3,64-12,48 /* (ea >> 12) & 0xffff */
- xor r28,r5,r0
+ /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT - VPN_SHIFT
+ /*
+ * clrldi r3,r3,64 - SID_SHIFT --> ea & 0xfffffff
+ * srdi r28,r3,VPN_SHIFT
+ */
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
+ or r29,r28,r29
+ /*
+ * Calculate hash value for primary slot and store it in r28
+ * r3 = va, r5 = vsid
+ * r0 = (va >> 12) & ((1ul << (28 - 12)) -1)
+ */
+ rldicl r0,r3,64-12,48
+ xor r28,r5,r0 /* hash */
b 4f
-3: /* Calc VA and hash in r29 and r28 for 1T segment */
- sldi r29,r5,40 /* vsid << 40 */
- clrldi r3,r3,24 /* ea & 0xffffffffff */
- rldic r28,r5,25,25 /* (vsid << 25) & 0x7fffffffff */
- clrldi r5,r5,40 /* vsid & 0xffffff */
- rldicl r0,r3,64-12,36 /* (ea >> 12) & 0xfffffff */
- xor r28,r28,r5
- or r29,r3,r29 /* VA */
+3: /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT
+ /*
+ * clrldi r3,r3,64 - SID_SHIFT_1T --> ea & 0xffffffffff
+ * srdi r28,r3,VPN_SHIFT
+ */
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
+ or r29,r28,r29
+
+ /*
+ * Calculate hash value for primary slot and
+ * store it in r28 for 1T segment
+ * r3 = va, r5 = vsid
+ */
+ sldi r28,r5,25 /* vsid << 25 */
+ /* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */
+ rldicl r0,r3,64-12,36
+ xor r28,r28,r5 /* vsid ^ ( vsid << 25) */
xor r28,r28,r0 /* hash */
/* Convert linux PTE bits into HW equivalents */
@@ -430,7 +464,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/
andc r0,r3,r0 /* r0 = pte & ~r0 */
rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */
- ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */
+ /*
+ * Always add "C" bit for perf. Memory coherence is always enabled
+ */
+ ori r3,r3,HPTE_R_C | HPTE_R_M
/* We eventually do the icache sync here (maybe inline that
* code rather than call a C function...)
@@ -438,7 +475,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
BEGIN_FTR_SECTION
mr r4,r30
mr r5,r7
- bl .hash_page_do_lazy_icache
+ bl hash_page_do_lazy_icache
END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
/* At this point, r3 contains new PP bits, save them in
@@ -466,7 +503,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
beq htab_inval_old_hpte
ld r6,STK_PARAM(R6)(r1)
- ori r26,r6,0x8000 /* Load the hidx mask */
+ ori r26,r6,PTE_PAGE_HIDX_OFFSET /* Load the hidx mask. */
ld r26,0(r26)
addi r5,r25,36 /* Check actual HPTE_SUB bit, this */
rldcr. r0,r31,r5,0 /* must match pgtable.h definition */
@@ -488,11 +525,13 @@ htab_special_pfn:
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,0 /* !bolted, !secondary */
li r8,MMU_PAGE_4K /* page size */
- ld r9,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+ li r9,MMU_PAGE_4K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
bge htab_pte_insert_ok /* Insertion successful */
@@ -515,11 +554,13 @@ _GLOBAL(htab_call_hpte_insert1)
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,HPTE_V_SECONDARY /* !bolted, secondary */
li r8,MMU_PAGE_4K /* page size */
- ld r9,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+ li r9,MMU_PAGE_4K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
bge+ htab_pte_insert_ok /* Insertion successful */
@@ -536,7 +577,8 @@ _GLOBAL(htab_call_hpte_insert2)
2: and r0,r5,r27
rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */
/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
bl . /* patched by htab_finish_init() */
/* Try all again */
@@ -547,13 +589,13 @@ _GLOBAL(htab_call_hpte_remove)
* useless now that the segment has been switched to 4k pages.
*/
htab_inval_old_hpte:
- mr r3,r29 /* virtual addr */
+ mr r3,r29 /* vpn */
mr r4,r31 /* PTE.pte */
li r5,0 /* PTE.hidx */
li r6,MMU_PAGE_64K /* psize */
ld r7,STK_PARAM(R9)(r1) /* ssize */
ld r8,STK_PARAM(R8)(r1) /* local */
- bl .flush_hash_page
+ bl flush_hash_page
/* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */
lis r0,_PAGE_HPTE_SUB@h
ori r0,r0,_PAGE_HPTE_SUB@l
@@ -583,7 +625,7 @@ htab_pte_insert_ok:
sld r4,r4,r5
andc r26,r26,r4
or r26,r26,r3
- ori r5,r6,0x8000
+ ori r5,r6,PTE_PAGE_HIDX_OFFSET
std r26,0(r5)
lwsync
std r30,0(r6)
@@ -620,11 +662,13 @@ htab_modify_pte:
add r3,r0,r3 /* add slot idx */
/* Call ppc_md.hpte_updatepp */
- mr r5,r29 /* va */
- li r6,MMU_PAGE_4K /* page size */
- ld r7,STK_PARAM(R9)(r1) /* segment size */
- ld r8,STK_PARAM(R8)(r1) /* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+ mr r5,r29 /* vpn */
+ li r6,MMU_PAGE_4K /* base page size */
+ li r7,MMU_PAGE_4K /* actual page size */
+ ld r8,STK_PARAM(R9)(r1) /* segment size */
+ ld r9,STK_PARAM(R8)(r1) /* get "local" param */
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
bl . /* patched by htab_finish_init() */
/* if we failed because typically the HPTE wasn't really here
@@ -676,7 +720,7 @@ _GLOBAL(__hash_page_64K)
/* Save non-volatile registers.
* r31 will hold "old PTE"
* r30 is "new PTE"
- * r29 is "va"
+ * r29 is vpn
* r28 is a hash value
* r27 is hashtab mask (maybe dynamic patched instead ?)
*/
@@ -729,25 +773,32 @@ BEGIN_FTR_SECTION
cmpdi r9,0 /* check segment size */
bne 3f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
- /* Calc va and put it in r29 */
- rldicr r29,r5,28,63-28
- rldicl r3,r3,0,36
- or r29,r3,r29
-
- /* Calculate hash value for primary slot and store it in r28 */
- rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */
- rldicl r0,r3,64-16,52 /* (ea >> 16) & 0xfff */
- xor r28,r5,r0
+ /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT - VPN_SHIFT
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
+ or r29,r28,r29
+
+ /* Calculate hash value for primary slot and store it in r28
+ * r3 = va, r5 = vsid
+ * r0 = (va >> 16) & ((1ul << (28 - 16)) -1)
+ */
+ rldicl r0,r3,64-16,52
+ xor r28,r5,r0 /* hash */
b 4f
-3: /* Calc VA and hash in r29 and r28 for 1T segment */
- sldi r29,r5,40 /* vsid << 40 */
- clrldi r3,r3,24 /* ea & 0xffffffffff */
- rldic r28,r5,25,25 /* (vsid << 25) & 0x7fffffffff */
- clrldi r5,r5,40 /* vsid & 0xffffff */
- rldicl r0,r3,64-16,40 /* (ea >> 16) & 0xffffff */
- xor r28,r28,r5
- or r29,r3,r29 /* VA */
+3: /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
+ or r29,r28,r29
+ /*
+ * calculate hash value for primary slot and
+ * store it in r28 for 1T segment
+ * r3 = va, r5 = vsid
+ */
+ sldi r28,r5,25 /* vsid << 25 */
+ /* r0 = (va >> 16) & ((1ul << (40 - 16)) -1) */
+ rldicl r0,r3,64-16,40
+ xor r28,r28,r5 /* vsid ^ ( vsid << 25) */
xor r28,r28,r0 /* hash */
/* Convert linux PTE bits into HW equivalents */
@@ -758,7 +809,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/
andc r0,r30,r0 /* r0 = pte & ~r0 */
rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */
- ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */
+ /*
+ * Always add "C" bit for perf. Memory coherence is always enabled
+ */
+ ori r3,r3,HPTE_R_C | HPTE_R_M
/* We eventually do the icache sync here (maybe inline that
* code rather than call a C function...)
@@ -766,7 +820,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
BEGIN_FTR_SECTION
mr r4,r30
mr r5,r7
- bl .hash_page_do_lazy_icache
+ bl hash_page_do_lazy_icache
END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
/* At this point, r3 contains new PP bits, save them in
@@ -806,11 +860,13 @@ ht64_insert_pte:
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,0 /* !bolted, !secondary */
li r8,MMU_PAGE_64K
- ld r9,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(ht64_call_hpte_insert1)
+ li r9,MMU_PAGE_64K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
+.globl ht64_call_hpte_insert1
+ht64_call_hpte_insert1:
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
bge ht64_pte_insert_ok /* Insertion successful */
@@ -829,11 +885,13 @@ _GLOBAL(ht64_call_hpte_insert1)
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,HPTE_V_SECONDARY /* !bolted, secondary */
li r8,MMU_PAGE_64K
- ld r9,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(ht64_call_hpte_insert2)
+ li r9,MMU_PAGE_64K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
+.globl ht64_call_hpte_insert2
+ht64_call_hpte_insert2:
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
bge+ ht64_pte_insert_ok /* Insertion successful */
@@ -850,7 +908,8 @@ _GLOBAL(ht64_call_hpte_insert2)
2: and r0,r5,r27
rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */
/* Call ppc_md.hpte_remove */
-_GLOBAL(ht64_call_hpte_remove)
+.globl ht64_call_hpte_remove
+ht64_call_hpte_remove:
bl . /* patched by htab_finish_init() */
/* Try all again */
@@ -899,11 +958,13 @@ ht64_modify_pte:
add r3,r0,r3 /* add slot idx */
/* Call ppc_md.hpte_updatepp */
- mr r5,r29 /* va */
- li r6,MMU_PAGE_64K
- ld r7,STK_PARAM(R9)(r1) /* segment size */
- ld r8,STK_PARAM(R8)(r1) /* get "local" param */
-_GLOBAL(ht64_call_hpte_updatepp)
+ mr r5,r29 /* vpn */
+ li r6,MMU_PAGE_64K /* base page size */
+ li r7,MMU_PAGE_64K /* actual page size */
+ ld r8,STK_PARAM(R9)(r1) /* segment size */
+ ld r9,STK_PARAM(R8)(r1) /* get "local" param */
+.globl ht64_call_hpte_updatepp
+ht64_call_hpte_updatepp:
bl . /* patched by htab_finish_init() */
/* if we failed because typically the HPTE wasn't really here