diff options
Diffstat (limited to 'arch/powerpc/mm/hash_low_64.S')
| -rw-r--r-- | arch/powerpc/mm/hash_low_64.S | 441 |
1 files changed, 283 insertions, 158 deletions
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index 9bc0a9c2b9b..057cbbb4c57 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -34,14 +34,6 @@ * | CR save area (SP + 8) * SP ---> +-- Back chain (SP + 0) */ -#define STACKFRAMESIZE 256 - -/* Save parameters offsets */ -#define STK_PARM(i) (STACKFRAMESIZE + 48 + ((i)-3)*8) - -/* Save non-volatile offsets */ -#define STK_REG(i) (112 + ((i)-14)*8) - #ifndef CONFIG_PPC_64K_PAGES @@ -54,7 +46,7 @@ /* * _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, - * pte_t *ptep, unsigned long trap, int local) + * pte_t *ptep, unsigned long trap, int local, int ssize) * * Adds a 4K page to the hash table in a segment of 4K pages only */ @@ -64,24 +56,22 @@ _GLOBAL(__hash_page_4K) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) /* Save all params that we need after a function call */ - std r6,STK_PARM(r6)(r1) - std r8,STK_PARM(r8)(r1) + std r6,STK_PARAM(R6)(r1) + std r8,STK_PARAM(R8)(r1) + std r9,STK_PARAM(R9)(r1) - /* Add _PAGE_PRESENT to access */ - ori r4,r4,_PAGE_PRESENT - /* 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 ?) */ - std r27,STK_REG(r27)(r1) - std r28,STK_REG(r28)(r1) - std r29,STK_REG(r29)(r1) - std r30,STK_REG(r30)(r1) - std r31,STK_REG(r31)(r1) + std r27,STK_REG(R27)(r1) + std r28,STK_REG(R28)(r1) + std r29,STK_REG(R29)(r1) + std r30,STK_REG(R30)(r1) + std r31,STK_REG(R31)(r1) /* Step 1: * @@ -117,25 +107,51 @@ _GLOBAL(__hash_page_4K) * r4 (access) is re-useable, we use it for the new HPTE flags */ - /* Calc va and put it in r29 */ - rldicr r29,r5,28,63-28 - rldicl r3,r3,0,36 - or r29,r3,r29 +BEGIN_FTR_SECTION + cmpdi r9,0 /* check segment size */ + bne 3f +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) + /* 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 - /* 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 +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 */ - andi. r3,r30,0x1fe /* Get basic set of flags */ +4: andi. r3,r30,0x1fe /* Get basic set of flags */ xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */ 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...) @@ -143,13 +159,13 @@ _GLOBAL(__hash_page_4K) 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 * place of "access" in the param area (sic) */ - std r3,STK_PARM(r4)(r1) + std r3,STK_PARAM(R4)(r1) /* Get htab_hash_mask */ ld r4,htab_hash_mask@got(2) @@ -179,11 +195,14 @@ htab_insert_pte: rldicr r3,r0,3,63-3 /* r3 = (hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retreive new pp bits */ - mr r4,r29 /* Retreive va */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ + mr r4,r29 /* Retrieve vpn */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page 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 */ @@ -201,11 +220,14 @@ _GLOBAL(htab_call_hpte_insert1) rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retreive new pp bits */ - mr r4,r29 /* Retreive va */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ + mr r4,r29 /* Retrieve vpn */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page 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 */ @@ -222,7 +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 */ @@ -240,15 +263,15 @@ htab_pte_insert_ok: * (maybe add eieio may be good still ?) */ htab_write_out_pte: - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r30,0(r6) li r3, 0 htab_bail: - ld r27,STK_REG(r27)(r1) - ld r28,STK_REG(r28)(r1) - ld r29,STK_REG(r29)(r1) - ld r30,STK_REG(r30)(r1) - ld r31,STK_REG(r31)(r1) + ld r27,STK_REG(R27)(r1) + ld r28,STK_REG(R28)(r1) + ld r29,STK_REG(R29)(r1) + ld r30,STK_REG(R30)(r1) + ld r31,STK_REG(R31)(r1) addi r1,r1,STACKFRAMESIZE ld r0,16(r1) mtlr r0 @@ -271,10 +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_PARM(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 @@ -296,7 +322,7 @@ htab_wrong_access: htab_pte_insert_failure: /* Bail out restoring old PTE */ - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r31,0(r6) li r3,-1 b htab_bail @@ -312,7 +338,8 @@ htab_pte_insert_failure: *****************************************************************************/ /* _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, - * pte_t *ptep, unsigned long trap, int local) + * pte_t *ptep, unsigned long trap, int local, int ssize, + * int subpg_prot) */ /* @@ -323,28 +350,26 @@ _GLOBAL(__hash_page_4K) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) /* Save all params that we need after a function call */ - std r6,STK_PARM(r6)(r1) - std r8,STK_PARM(r8)(r1) - - /* Add _PAGE_PRESENT to access */ - ori r4,r4,_PAGE_PRESENT + std r6,STK_PARAM(R6)(r1) + std r8,STK_PARAM(R8)(r1) + std r9,STK_PARAM(R9)(r1) /* 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 * r25 is the index in combo page */ - std r25,STK_REG(r25)(r1) - std r26,STK_REG(r26)(r1) - std r27,STK_REG(r27)(r1) - std r28,STK_REG(r28)(r1) - std r29,STK_REG(r29)(r1) - std r30,STK_REG(r30)(r1) - std r31,STK_REG(r31)(r1) + std r25,STK_REG(R25)(r1) + std r26,STK_REG(R26)(r1) + std r27,STK_REG(R27)(r1) + std r28,STK_REG(R28)(r1) + std r29,STK_REG(R29)(r1) + std r30,STK_REG(R30)(r1) + std r31,STK_REG(R31)(r1) /* Step 1: * @@ -367,7 +392,7 @@ _GLOBAL(__hash_page_4K) */ rlwinm r30,r4,32-9+7,31-7,31-7 /* _PAGE_RW -> _PAGE_DIRTY */ or r30,r30,r31 - ori r30,r30,_PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE + ori r30,r30,_PAGE_BUSY | _PAGE_ACCESSED oris r30,r30,_PAGE_COMBO@h /* Write the linux PTE atomically (setting busy) */ stdcx. r30,0,r6 @@ -383,25 +408,66 @@ _GLOBAL(__hash_page_4K) /* Load the hidx index */ rldicl r25,r3,64-12,60 - /* 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 +BEGIN_FTR_SECTION + cmpdi r9,0 /* check segment size */ + bne 3f +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) + /* 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 - /* 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 +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 */ +4: +#ifdef CONFIG_PPC_SUBPAGE_PROT + andc r10,r30,r10 + andi. r3,r10,0x1fe /* Get basic set of flags */ + rlwinm r0,r10,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ +#else andi. r3,r30,0x1fe /* Get basic set of flags */ - xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ +#endif + xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */ and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ - andc r0,r30,r0 /* r0 = pte & ~r0 */ + 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...) @@ -409,13 +475,13 @@ _GLOBAL(__hash_page_4K) 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 * place of "access" in the param area (sic) */ - std r3,STK_PARM(r4)(r1) + std r3,STK_PARAM(R4)(r1) /* Get htab_hash_mask */ ld r4,htab_hash_mask@got(2) @@ -425,7 +491,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) * go to out-of-line code to try to modify the HPTE. We look for * the bit at (1 >> (index + 32)) */ - andi. r0,r31,_PAGE_HASHPTE + rldicl. r0,r31,64-12,48 li r26,0 /* Default hidx */ beq htab_insert_pte @@ -436,8 +502,8 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) andis. r0,r31,_PAGE_COMBO@h beq htab_inval_old_hpte - ld r6,STK_PARM(r6)(r1) - ori r26,r6,0x8000 /* Load the hidx mask */ + ld r6,STK_PARAM(R6)(r1) + 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 */ @@ -445,9 +511,12 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) htab_insert_pte: /* real page number in r5, PTE RPN value + index */ - rldicl r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT + andis. r0,r31,_PAGE_4K_PFN@h + srdi r5,r31,PTE_RPN_SHIFT + bne- htab_special_pfn sldi r5,r5,PAGE_SHIFT-HW_PAGE_SHIFT add r5,r5,r25 +htab_special_pfn: sldi r5,r5,HW_PAGE_SHIFT /* Calculate primary group hash */ @@ -455,11 +524,14 @@ htab_insert_pte: rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retreive new pp bits */ - mr r4,r29 /* Retreive va */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ + mr r4,r29 /* Retrieve vpn */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page 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 */ @@ -469,21 +541,26 @@ _GLOBAL(htab_call_hpte_insert1) /* Now try secondary slot */ /* real page number in r5, PTE RPN value + index */ - rldicl r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT + andis. r0,r31,_PAGE_4K_PFN@h + srdi r5,r31,PTE_RPN_SHIFT + bne- 3f sldi r5,r5,PAGE_SHIFT-HW_PAGE_SHIFT add r5,r5,r25 - sldi r5,r5,HW_PAGE_SHIFT +3: sldi r5,r5,HW_PAGE_SHIFT /* Calculate secondary group hash */ andc r0,r27,r28 rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retreive new pp bits */ - mr r4,r29 /* Retreive va */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ + mr r4,r29 /* Retrieve vpn */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page 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 */ @@ -500,7 +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 */ @@ -511,12 +589,17 @@ _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_PARM(r8)(r1) /* local */ - bl .flush_hash_page + ld r7,STK_PARAM(R9)(r1) /* ssize */ + ld r8,STK_PARAM(R8)(r1) /* local */ + 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 + andc r30,r30,r0 b htab_insert_pte htab_bail_ok: @@ -527,7 +610,7 @@ htab_pte_insert_ok: /* Insert slot number & secondary bit in PTE second half, * clear _PAGE_BUSY and set approriate HPTE slot bit */ - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) li r0,_PAGE_BUSY andc r30,r30,r0 /* HPTE SUB bit */ @@ -542,19 +625,19 @@ 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) li r3, 0 htab_bail: - ld r25,STK_REG(r25)(r1) - ld r26,STK_REG(r26)(r1) - ld r27,STK_REG(r27)(r1) - ld r28,STK_REG(r28)(r1) - ld r29,STK_REG(r29)(r1) - ld r30,STK_REG(r30)(r1) - ld r31,STK_REG(r31)(r1) + ld r25,STK_REG(R25)(r1) + ld r26,STK_REG(R26)(r1) + ld r27,STK_REG(R27)(r1) + ld r28,STK_REG(R28)(r1) + ld r29,STK_REG(R29)(r1) + ld r30,STK_REG(R30)(r1) + ld r31,STK_REG(R31)(r1) addi r1,r1,STACKFRAMESIZE ld r0,16(r1) mtlr r0 @@ -579,10 +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_PARM(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 @@ -594,7 +680,7 @@ _GLOBAL(htab_call_hpte_updatepp) /* Clear the BUSY bit and Write out the PTE */ li r0,_PAGE_BUSY andc r30,r30,r0 - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r30,0(r6) li r3,0 b htab_bail @@ -607,11 +693,14 @@ htab_wrong_access: htab_pte_insert_failure: /* Bail out restoring old PTE */ - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r31,0(r6) li r3,-1 b htab_bail +#endif /* CONFIG_PPC_64K_PAGES */ + +#ifdef CONFIG_PPC_HAS_HASH_64K /***************************************************************************** * * @@ -624,24 +713,22 @@ _GLOBAL(__hash_page_64K) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) /* Save all params that we need after a function call */ - std r6,STK_PARM(r6)(r1) - std r8,STK_PARM(r8)(r1) - - /* Add _PAGE_PRESENT to access */ - ori r4,r4,_PAGE_PRESENT + std r6,STK_PARAM(R6)(r1) + std r8,STK_PARAM(R8)(r1) + std r9,STK_PARAM(R9)(r1) /* 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 ?) */ - std r27,STK_REG(r27)(r1) - std r28,STK_REG(r28)(r1) - std r29,STK_REG(r29)(r1) - std r30,STK_REG(r30)(r1) - std r31,STK_REG(r31)(r1) + std r27,STK_REG(R27)(r1) + std r28,STK_REG(R28)(r1) + std r29,STK_REG(R29)(r1) + std r30,STK_REG(R30)(r1) + std r31,STK_REG(R31)(r1) /* Step 1: * @@ -664,13 +751,13 @@ BEGIN_FTR_SECTION andi. r0,r31,_PAGE_NO_CACHE /* If so, bail out and refault as a 4k page */ bne- ht64_bail_ok -END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE) +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_CI_LARGE_PAGE) /* Prepare new PTE value (turn access RW into DIRTY, then - * add BUSY,HASHPTE and ACCESSED) + * add BUSY and ACCESSED) */ rlwinm r30,r4,32-9+7,31-7,31-7 /* _PAGE_RW -> _PAGE_DIRTY */ or r30,r30,r31 - ori r30,r30,_PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE + ori r30,r30,_PAGE_BUSY | _PAGE_ACCESSED /* Write the linux PTE atomically (setting busy) */ stdcx. r30,0,r6 bne- 1b @@ -682,25 +769,50 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE) * r4 (access) is re-useable, we use it for the new HPTE flags */ - /* 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 +BEGIN_FTR_SECTION + cmpdi r9,0 /* check segment size */ + bne 3f +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) + /* 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 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 */ - andi. r3,r30,0x1fe /* Get basic set of flags */ +4: andi. r3,r30,0x1fe /* Get basic set of flags */ xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */ 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...) @@ -708,13 +820,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE) 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 * place of "access" in the param area (sic) */ - std r3,STK_PARM(r4)(r1) + std r3,STK_PARAM(R4)(r1) /* Get htab_hash_mask */ ld r4,htab_hash_mask@got(2) @@ -723,18 +835,21 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* Check if we may already be in the hashtable, in this case, we * go to out-of-line code to try to modify the HPTE */ - andi. r0,r31,_PAGE_HASHPTE + rldicl. r0,r31,64-12,48 bne ht64_modify_pte ht64_insert_pte: /* Clear hpte bits in new pte (we also clear BUSY btw) and - * add _PAGE_HASHPTE + * add _PAGE_HPTE_SUB0 */ lis r0,_PAGE_HPTEFLAGS@h ori r0,r0,_PAGE_HPTEFLAGS@l andc r30,r30,r0 +#ifdef CONFIG_PPC_64K_PAGES + oris r30,r30,_PAGE_HPTE_SUB0@h +#else ori r30,r30,_PAGE_HASHPTE - +#endif /* Phyical address in r5 */ rldicl r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT sldi r5,r5,PAGE_SHIFT @@ -744,11 +859,14 @@ ht64_insert_pte: rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retreive new pp bits */ - mr r4,r29 /* Retreive va */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ + mr r4,r29 /* Retrieve vpn */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_64K -_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 */ @@ -766,11 +884,14 @@ _GLOBAL(ht64_call_hpte_insert1) rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retreive new pp bits */ - mr r4,r29 /* Retreive va */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ + mr r4,r29 /* Retrieve vpn */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_64K -_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 */ @@ -787,7 +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 */ @@ -805,15 +927,15 @@ ht64_pte_insert_ok: * (maybe add eieio may be good still ?) */ ht64_write_out_pte: - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r30,0(r6) li r3, 0 ht64_bail: - ld r27,STK_REG(r27)(r1) - ld r28,STK_REG(r28)(r1) - ld r29,STK_REG(r29)(r1) - ld r30,STK_REG(r30)(r1) - ld r31,STK_REG(r31)(r1) + ld r27,STK_REG(R27)(r1) + ld r28,STK_REG(R28)(r1) + ld r29,STK_REG(R29)(r1) + ld r30,STK_REG(R30)(r1) + ld r31,STK_REG(R31)(r1) addi r1,r1,STACKFRAMESIZE ld r0,16(r1) mtlr r0 @@ -836,10 +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_PARM(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 @@ -861,13 +986,13 @@ ht64_wrong_access: ht64_pte_insert_failure: /* Bail out restoring old PTE */ - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r31,0(r6) li r3,-1 b ht64_bail -#endif /* CONFIG_PPC_64K_PAGES */ +#endif /* CONFIG_PPC_HAS_HASH_64K */ /***************************************************************************** |
