openkylin
/
linux
mirror of https://gitee.com/openkylin/linux.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity

openrisc: tlb miss handler optimizations 

By slightly reorganizing the code, the number of registers
used in the tlb miss handlers can be reduced by two,
thus removing the need to save them to memory.

Also, some dead and commented out code is removed.

No functional change.

Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Signed-off-by: Jonas Bonn <jonas@southpole.se>
Signed-off-by: Stafford Horne <shorne@gmail.com>
This commit is contained in:
Stefan Kristiansson 2013-08-01 10:46:10 +03:00 committed by Stafford Horne
parent 3e06a16339
commit 742fb582b4
1 changed files with 46 additions and 95 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

141
arch/openrisc/kernel/head.S
View File

@ -971,8 +971,6 @@ ENTRY(dtlb_miss_handler)
EXCEPTION_STORE_GPR2 EXCEPTION_STORE_GPR2
EXCEPTION_STORE_GPR3 EXCEPTION_STORE_GPR3
EXCEPTION_STORE_GPR4 EXCEPTION_STORE_GPR4
EXCEPTION_STORE_GPR5
EXCEPTION_STORE_GPR6
/* /*
* get EA of the miss * get EA of the miss
*/ */
@ -980,91 +978,70 @@ ENTRY(dtlb_miss_handler)
/* /*
* pmd = (pmd_t *)(current_pgd + pgd_index(daddr)); * pmd = (pmd_t *)(current_pgd + pgd_index(daddr));
*/ */
GET_CURRENT_PGD(r3,r5) // r3 is current_pgd, r5 is temp GET_CURRENT_PGD(r3,r4) // r3 is current_pgd, r4 is temp
l.srli r4,r2,0x18 // >> PAGE_SHIFT + (PAGE_SHIFT - 2) l.srli r4,r2,0x18 // >> PAGE_SHIFT + (PAGE_SHIFT - 2)
l.slli r4,r4,0x2 // to get address << 2 l.slli r4,r4,0x2 // to get address << 2
l.add r5,r4,r3 // r4 is pgd_index(daddr) l.add r3,r4,r3 // r4 is pgd_index(daddr)
/* /*
* if (pmd_none(*pmd)) * if (pmd_none(*pmd))
* goto pmd_none: * goto pmd_none:
*/ */
tophys (r4,r5) tophys (r4,r3)
l.lwz r3,0x0(r4) // get *pmd value l.lwz r3,0x0(r4) // get *pmd value
l.sfne r3,r0 l.sfne r3,r0
l.bnf d_pmd_none l.bnf d_pmd_none
l.andi r3,r3,~PAGE_MASK //0x1fff // ~PAGE_MASK l.addi r3,r0,0xffffe000 // PAGE_MASK
/*
* if (pmd_bad(*pmd))
* pmd_clear(pmd)
* goto pmd_bad:
*/
// l.sfeq r3,r0 // check *pmd value
// l.bf d_pmd_good
l.addi r3,r0,0xffffe000 // PAGE_MASK
// l.j d_pmd_bad
// l.sw 0x0(r4),r0 // clear pmd
d_pmd_good: d_pmd_good:
/* /*
* pte = *pte_offset(pmd, daddr); * pte = *pte_offset(pmd, daddr);
*/ */
l.lwz r4,0x0(r4) // get **pmd value l.lwz r4,0x0(r4) // get **pmd value
l.and r4,r4,r3 // & PAGE_MASK l.and r4,r4,r3 // & PAGE_MASK
l.srli r5,r2,0xd // >> PAGE_SHIFT, r2 == EEAR l.srli r2,r2,0xd // >> PAGE_SHIFT, r2 == EEAR
l.andi r3,r5,0x7ff // (1UL << PAGE_SHIFT - 2) - 1 l.andi r3,r2,0x7ff // (1UL << PAGE_SHIFT - 2) - 1
l.slli r3,r3,0x2 // to get address << 2 l.slli r3,r3,0x2 // to get address << 2
l.add r3,r3,r4 l.add r3,r3,r4
l.lwz r2,0x0(r3) // this is pte at last l.lwz r3,0x0(r3) // this is pte at last
/* /*
* if (!pte_present(pte)) * if (!pte_present(pte))
*/ */
l.andi r4,r2,0x1 l.andi r4,r3,0x1
l.sfne r4,r0 // is pte present l.sfne r4,r0 // is pte present
l.bnf d_pte_not_present l.bnf d_pte_not_present
l.addi r3,r0,0xffffe3fa // PAGE_MASK | DTLB_UP_CONVERT_MASK l.addi r4,r0,0xffffe3fa // PAGE_MASK | DTLB_UP_CONVERT_MASK
/* /*
* fill DTLB TR register * fill DTLB TR register
*/ */
l.and r4,r2,r3 // apply the mask l.and r4,r3,r4 // apply the mask
// Determine number of DMMU sets // Determine number of DMMU sets
l.mfspr r6, r0, SPR_DMMUCFGR l.mfspr r2, r0, SPR_DMMUCFGR
l.andi r6, r6, SPR_DMMUCFGR_NTS l.andi r2, r2, SPR_DMMUCFGR_NTS
l.srli r6, r6, SPR_DMMUCFGR_NTS_OFF l.srli r2, r2, SPR_DMMUCFGR_NTS_OFF
l.ori r3, r0, 0x1 l.ori r3, r0, 0x1
l.sll r3, r3, r6 // r3 = number DMMU sets DMMUCFGR l.sll r3, r3, r2 // r3 = number DMMU sets DMMUCFGR
l.addi r6, r3, -1 // r6 = nsets mask l.addi r2, r3, -1 // r2 = nsets mask
l.and r5, r5, r6 // calc offset: & (NUM_TLB_ENTRIES-1) l.mfspr r3, r0, SPR_EEAR_BASE
l.srli r3, r3, 0xd // >> PAGE_SHIFT
l.and r2, r3, r2 // calc offset: & (NUM_TLB_ENTRIES-1)
//NUM_TLB_ENTRIES //NUM_TLB_ENTRIES
l.mtspr r5,r4,SPR_DTLBTR_BASE(0) l.mtspr r2,r4,SPR_DTLBTR_BASE(0)
/* /*
* fill DTLB MR register * fill DTLB MR register
*/ */
l.mfspr r2,r0,SPR_EEAR_BASE l.slli r3, r3, 0xd /* << PAGE_SHIFT => EA & PAGE_MASK */
l.addi r3,r0,0xffffe000 // PAGE_MASK l.ori r4,r3,0x1 // set hardware valid bit: DTBL_MR entry
l.and r4,r2,r3 // apply PAGE_MASK to EA (__PHX__ do we really need this?) l.mtspr r2,r4,SPR_DTLBMR_BASE(0)
l.ori r4,r4,0x1 // set hardware valid bit: DTBL_MR entry
l.mtspr r5,r4,SPR_DTLBMR_BASE(0)
EXCEPTION_LOAD_GPR2 EXCEPTION_LOAD_GPR2
EXCEPTION_LOAD_GPR3 EXCEPTION_LOAD_GPR3
EXCEPTION_LOAD_GPR4 EXCEPTION_LOAD_GPR4
EXCEPTION_LOAD_GPR5
EXCEPTION_LOAD_GPR6
l.rfe
d_pmd_bad:
l.nop 1
EXCEPTION_LOAD_GPR2
EXCEPTION_LOAD_GPR3
EXCEPTION_LOAD_GPR4
EXCEPTION_LOAD_GPR5
EXCEPTION_LOAD_GPR6
l.rfe l.rfe
d_pmd_none: d_pmd_none:
d_pte_not_present: d_pte_not_present:
EXCEPTION_LOAD_GPR2 EXCEPTION_LOAD_GPR2
EXCEPTION_LOAD_GPR3 EXCEPTION_LOAD_GPR3
EXCEPTION_LOAD_GPR4 EXCEPTION_LOAD_GPR4
EXCEPTION_LOAD_GPR5
EXCEPTION_LOAD_GPR6
EXCEPTION_HANDLE(_dtlb_miss_page_fault_handler) EXCEPTION_HANDLE(_dtlb_miss_page_fault_handler)
/* ==============================================[ ITLB miss handler ]=== */ /* ==============================================[ ITLB miss handler ]=== */
@ -1072,8 +1049,6 @@ ENTRY(itlb_miss_handler)
EXCEPTION_STORE_GPR2 EXCEPTION_STORE_GPR2
EXCEPTION_STORE_GPR3 EXCEPTION_STORE_GPR3
EXCEPTION_STORE_GPR4 EXCEPTION_STORE_GPR4
EXCEPTION_STORE_GPR5
EXCEPTION_STORE_GPR6
/* /*
* get EA of the miss * get EA of the miss
*/ */
@ -1083,30 +1058,19 @@ ENTRY(itlb_miss_handler)
* pmd = (pmd_t *)(current_pgd + pgd_index(daddr)); * pmd = (pmd_t *)(current_pgd + pgd_index(daddr));
* *
*/ */
GET_CURRENT_PGD(r3,r5) // r3 is current_pgd, r5 is temp GET_CURRENT_PGD(r3,r4) // r3 is current_pgd, r5 is temp
l.srli r4,r2,0x18 // >> PAGE_SHIFT + (PAGE_SHIFT - 2) l.srli r4,r2,0x18 // >> PAGE_SHIFT + (PAGE_SHIFT - 2)
l.slli r4,r4,0x2 // to get address << 2 l.slli r4,r4,0x2 // to get address << 2
l.add r5,r4,r3 // r4 is pgd_index(daddr) l.add r3,r4,r3 // r4 is pgd_index(daddr)
/* /*
* if (pmd_none(*pmd)) * if (pmd_none(*pmd))
* goto pmd_none: * goto pmd_none:
*/ */
tophys (r4,r5) tophys (r4,r3)
l.lwz r3,0x0(r4) // get *pmd value l.lwz r3,0x0(r4) // get *pmd value
l.sfne r3,r0 l.sfne r3,r0
l.bnf i_pmd_none l.bnf i_pmd_none
l.andi r3,r3,0x1fff // ~PAGE_MASK l.addi r3,r0,0xffffe000 // PAGE_MASK
/*
* if (pmd_bad(*pmd))
* pmd_clear(pmd)
* goto pmd_bad:
*/
// l.sfeq r3,r0 // check *pmd value
// l.bf i_pmd_good
l.addi r3,r0,0xffffe000 // PAGE_MASK
// l.j i_pmd_bad
// l.sw 0x0(r4),r0 // clear pmd
i_pmd_good: i_pmd_good:
/* /*
@ -1115,35 +1079,36 @@ i_pmd_good:
*/ */
l.lwz r4,0x0(r4) // get **pmd value l.lwz r4,0x0(r4) // get **pmd value
l.and r4,r4,r3 // & PAGE_MASK l.and r4,r4,r3 // & PAGE_MASK
l.srli r5,r2,0xd // >> PAGE_SHIFT, r2 == EEAR l.srli r2,r2,0xd // >> PAGE_SHIFT, r2 == EEAR
l.andi r3,r5,0x7ff // (1UL << PAGE_SHIFT - 2) - 1 l.andi r3,r2,0x7ff // (1UL << PAGE_SHIFT - 2) - 1
l.slli r3,r3,0x2 // to get address << 2 l.slli r3,r3,0x2 // to get address << 2
l.add r3,r3,r4 l.add r3,r3,r4
l.lwz r2,0x0(r3) // this is pte at last l.lwz r3,0x0(r3) // this is pte at last
/* /*
* if (!pte_present(pte)) * if (!pte_present(pte))
* *
*/ */
l.andi r4,r2,0x1 l.andi r4,r3,0x1
l.sfne r4,r0 // is pte present l.sfne r4,r0 // is pte present
l.bnf i_pte_not_present l.bnf i_pte_not_present
l.addi r3,r0,0xffffe03a // PAGE_MASK | ITLB_UP_CONVERT_MASK l.addi r4,r0,0xffffe03a // PAGE_MASK | ITLB_UP_CONVERT_MASK
/* /*
* fill ITLB TR register * fill ITLB TR register
*/ */
l.and r4,r2,r3 // apply the mask l.and r4,r3,r4 // apply the mask
l.andi r3,r2,0x7c0 // _PAGE_EXEC | _PAGE_SRE | _PAGE_SWE | _PAGE_URE | _PAGE_UWE l.andi r3,r3,0x7c0 // _PAGE_EXEC | _PAGE_SRE | _PAGE_SWE | _PAGE_URE | _PAGE_UWE
// l.andi r3,r2,0x400 // _PAGE_EXEC
l.sfeq r3,r0 l.sfeq r3,r0
l.bf itlb_tr_fill //_workaround l.bf itlb_tr_fill //_workaround
// Determine number of IMMU sets // Determine number of IMMU sets
l.mfspr r6, r0, SPR_IMMUCFGR l.mfspr r2, r0, SPR_IMMUCFGR
l.andi r6, r6, SPR_IMMUCFGR_NTS l.andi r2, r2, SPR_IMMUCFGR_NTS
l.srli r6, r6, SPR_IMMUCFGR_NTS_OFF l.srli r2, r2, SPR_IMMUCFGR_NTS_OFF
l.ori r3, r0, 0x1 l.ori r3, r0, 0x1
l.sll r3, r3, r6 // r3 = number IMMU sets IMMUCFGR l.sll r3, r3, r2 // r3 = number IMMU sets IMMUCFGR
l.addi r6, r3, -1 // r6 = nsets mask l.addi r2, r3, -1 // r2 = nsets mask
l.and r5, r5, r6 // calc offset: & (NUM_TLB_ENTRIES-1) l.mfspr r3, r0, SPR_EEAR_BASE
l.srli r3, r3, 0xd // >> PAGE_SHIFT
l.and r2, r3, r2 // calc offset: & (NUM_TLB_ENTRIES-1)
/* /*
* __PHX__ :: fixme * __PHX__ :: fixme
@ -1155,38 +1120,24 @@ i_pmd_good:
itlb_tr_fill_workaround: itlb_tr_fill_workaround:
l.ori r4,r4,0xc0 // | (SPR_ITLBTR_UXE | ITLBTR_SXE) l.ori r4,r4,0xc0 // | (SPR_ITLBTR_UXE | ITLBTR_SXE)
itlb_tr_fill: itlb_tr_fill:
l.mtspr r5,r4,SPR_ITLBTR_BASE(0) l.mtspr r2,r4,SPR_ITLBTR_BASE(0)
/* /*
* fill DTLB MR register * fill DTLB MR register
*/ */
l.mfspr r2,r0,SPR_EEAR_BASE l.slli r3, r3, 0xd /* << PAGE_SHIFT => EA & PAGE_MASK */
l.addi r3,r0,0xffffe000 // PAGE_MASK l.ori r4,r3,0x1 // set hardware valid bit: ITBL_MR entry
l.and r4,r2,r3 // apply PAGE_MASK to EA (__PHX__ do we really need this?) l.mtspr r2,r4,SPR_ITLBMR_BASE(0)
l.ori r4,r4,0x1 // set hardware valid bit: DTBL_MR entry
l.mtspr r5,r4,SPR_ITLBMR_BASE(0)
EXCEPTION_LOAD_GPR2 EXCEPTION_LOAD_GPR2
EXCEPTION_LOAD_GPR3 EXCEPTION_LOAD_GPR3
EXCEPTION_LOAD_GPR4 EXCEPTION_LOAD_GPR4
EXCEPTION_LOAD_GPR5
EXCEPTION_LOAD_GPR6
l.rfe l.rfe
i_pmd_bad:
l.nop 1
EXCEPTION_LOAD_GPR2
EXCEPTION_LOAD_GPR3
EXCEPTION_LOAD_GPR4
EXCEPTION_LOAD_GPR5
EXCEPTION_LOAD_GPR6
l.rfe
i_pmd_none: i_pmd_none:
i_pte_not_present: i_pte_not_present:
EXCEPTION_LOAD_GPR2 EXCEPTION_LOAD_GPR2
EXCEPTION_LOAD_GPR3 EXCEPTION_LOAD_GPR3
EXCEPTION_LOAD_GPR4 EXCEPTION_LOAD_GPR4
EXCEPTION_LOAD_GPR5
EXCEPTION_LOAD_GPR6
EXCEPTION_HANDLE(_itlb_miss_page_fault_handler) EXCEPTION_HANDLE(_itlb_miss_page_fault_handler)
/* ==============================================[ boot tlb handlers ]=== */ /* ==============================================[ boot tlb handlers ]=== */