Message ID | 1497671564-20030-3-git-send-email-linuxram@us.ibm.com (mailing list archive) |
---|---|
State | Superseded |
Headers | show |
On 06/17/2017 09:22 AM, Ram Pai wrote: > Rearrange 64K PTE bits to free up bits 3, 4, 5 and 6 > in the 64K backed hpte pages. This along with the earlier > patch will entirely free up the four bits from 64K PTE. > > This patch does the following change to 64K PTE that is > backed by 64K hpte. > > H_PAGE_F_SECOND which occupied bit 4 moves to the second part > of the pte. > H_PAGE_F_GIX which occupied bit 5, 6 and 7 also moves to the > second part of the pte. > > since bit 7 is now freed up, we move H_PAGE_BUSY from bit 9 > to bit 7. Trying to minimize gaps so that contiguous bits > can be allocated if needed in the future. > > The second part of the PTE will hold > (H_PAGE_F_SECOND|H_PAGE_F_GIX) at bit 60,61,62,63. I still dont understand how we freed up the 5th bit which is used in the 5th patch. Was that bit never used for any thing on 64K page size (64K and 4K mappings) ? +#define _RPAGE_RSV5 0x00040UL +#define H_PAGE_PKEY_BIT0 _RPAGE_RSV1 +#define H_PAGE_PKEY_BIT1 _RPAGE_RSV2 +#define H_PAGE_PKEY_BIT2 _RPAGE_RSV3 +#define H_PAGE_PKEY_BIT3 _RPAGE_RSV4 +#define H_PAGE_PKEY_BIT4 _RPAGE_RSV5
On Tue, Jun 20, 2017 at 04:21:45PM +0530, Anshuman Khandual wrote: > On 06/17/2017 09:22 AM, Ram Pai wrote: > > Rearrange 64K PTE bits to free up bits 3, 4, 5 and 6 > > in the 64K backed hpte pages. This along with the earlier > > patch will entirely free up the four bits from 64K PTE. > > > > This patch does the following change to 64K PTE that is > > backed by 64K hpte. > > > > H_PAGE_F_SECOND which occupied bit 4 moves to the second part > > of the pte. > > H_PAGE_F_GIX which occupied bit 5, 6 and 7 also moves to the > > second part of the pte. > > > > since bit 7 is now freed up, we move H_PAGE_BUSY from bit 9 > > to bit 7. Trying to minimize gaps so that contiguous bits > > can be allocated if needed in the future. > > > > The second part of the PTE will hold > > (H_PAGE_F_SECOND|H_PAGE_F_GIX) at bit 60,61,62,63. > > I still dont understand how we freed up the 5th bit which is > used in the 5th patch. Was that bit never used for any thing > on 64K page size (64K and 4K mappings) ? yes. it was not used. So I gladly used it :-) RP
Ram Pai <linuxram@us.ibm.com> writes: > Rearrange 64K PTE bits to free up bits 3, 4, 5 and 6 > in the 64K backed hpte pages. This along with the earlier > patch will entirely free up the four bits from 64K PTE. > > This patch does the following change to 64K PTE that is > backed by 64K hpte. > > H_PAGE_F_SECOND which occupied bit 4 moves to the second part > of the pte. > H_PAGE_F_GIX which occupied bit 5, 6 and 7 also moves to the > second part of the pte. > > since bit 7 is now freed up, we move H_PAGE_BUSY from bit 9 > to bit 7. Trying to minimize gaps so that contiguous bits > can be allocated if needed in the future. > > The second part of the PTE will hold > (H_PAGE_F_SECOND|H_PAGE_F_GIX) at bit 60,61,62,63. This patch will be really simple, if you don't use the get_hidx_gslot() helper > > Signed-off-by: Ram Pai <linuxram@us.ibm.com> > --- > arch/powerpc/include/asm/book3s/64/hash-64k.h | 26 ++++++++------------------ > arch/powerpc/mm/hash64_64k.c | 16 +++++++--------- > arch/powerpc/mm/hugetlbpage-hash64.c | 16 ++++++---------- > 3 files changed, 21 insertions(+), 37 deletions(-) > > diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h > index 0eb3c89..2fa5c60 100644 > --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h > +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h > @@ -12,12 +12,8 @@ > */ > #define H_PAGE_COMBO _RPAGE_RPN0 /* this is a combo 4k page */ > #define H_PAGE_4K_PFN _RPAGE_RPN1 /* PFN is for a single 4k page */ > -#define H_PAGE_F_SECOND _RPAGE_RSV2 /* HPTE is in 2ndary HPTEG */ > -#define H_PAGE_F_GIX (_RPAGE_RSV3 | _RPAGE_RSV4 | _RPAGE_RPN44) > -#define H_PAGE_F_GIX_SHIFT 56 > > - > -#define H_PAGE_BUSY _RPAGE_RPN42 /* software: PTE & hash are busy */ > +#define H_PAGE_BUSY _RPAGE_RPN44 /* software: PTE & hash are busy */ > #define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */ > > /* > @@ -56,24 +52,18 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) > unsigned long *hidxp; > > rpte.pte = pte; > - rpte.hidx = 0; > - if (pte_val(pte) & H_PAGE_COMBO) { > - /* > - * Make sure we order the hidx load against the H_PAGE_COMBO > - * check. The store side ordering is done in __hash_page_4K > - */ > - smp_rmb(); > - hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); > - rpte.hidx = *hidxp; > - } > + /* > + * The store side ordering is done in __hash_page_4K > + */ This is not just __hash_page_4k related now and you need to explain the stoer side ordering more. Are we doing this correctly now ? > + smp_rmb(); > + hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); > + rpte.hidx = *hidxp; > return rpte; > } > > static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) > { > - if ((pte_val(rpte.pte) & H_PAGE_COMBO)) > - return (rpte.hidx >> (index<<2)) & 0xf; > - return (pte_val(rpte.pte) >> H_PAGE_F_GIX_SHIFT) & 0xf; > + return ((rpte.hidx >> (index<<2)) & 0xfUL); > } > > static inline unsigned long set_hidx_slot(pte_t *ptep, real_pte_t rpte, > diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c > index 3702a3c..1c25ec2 100644 > --- a/arch/powerpc/mm/hash64_64k.c > +++ b/arch/powerpc/mm/hash64_64k.c > @@ -211,6 +211,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, > unsigned long vsid, pte_t *ptep, unsigned long trap, > unsigned long flags, int ssize) > { > + real_pte_t rpte; > unsigned long hpte_group; > unsigned long rflags, pa; > unsigned long old_pte, new_pte; > @@ -247,6 +248,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, > } while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); > > rflags = htab_convert_pte_flags(new_pte); > + rpte = __real_pte(__pte(old_pte), ptep); > > if (cpu_has_feature(CPU_FTR_NOEXECUTE) && > !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) > @@ -254,16 +256,13 @@ int __hash_page_64K(unsigned long ea, unsigned long access, > > vpn = hpt_vpn(ea, vsid, ssize); > if (unlikely(old_pte & H_PAGE_HASHPTE)) { > + unsigned long gslot; > + > /* > * There MIGHT be an HPTE for this pte > */ > - hash = hpt_hash(vpn, shift, ssize); > - if (old_pte & H_PAGE_F_SECOND) > - hash = ~hash; > - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; > - slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT; > - > - if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K, > + gslot = get_hidx_gslot(vpn, shift, ssize, rpte, 0); > + if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, MMU_PAGE_64K, > MMU_PAGE_64K, ssize, > flags) == -1) > old_pte &= ~_PAGE_HPTEFLAGS; > @@ -313,8 +312,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, > return -1; > } > > - new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & > - (H_PAGE_F_SECOND | H_PAGE_F_GIX); > + set_hidx_slot(ptep, rpte, 0, slot); > new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; > } > *ptep = __pte(new_pte & ~H_PAGE_BUSY); > diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c > index a84bb44..239ca86 100644 > --- a/arch/powerpc/mm/hugetlbpage-hash64.c > +++ b/arch/powerpc/mm/hugetlbpage-hash64.c > @@ -22,6 +22,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > pte_t *ptep, unsigned long trap, unsigned long flags, > int ssize, unsigned int shift, unsigned int mmu_psize) > { > + real_pte_t rpte; > unsigned long vpn; > unsigned long old_pte, new_pte; > unsigned long rflags, pa, sz; > @@ -61,6 +62,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > } while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); > > rflags = htab_convert_pte_flags(new_pte); > + rpte = __real_pte(__pte(old_pte), ptep); > > sz = ((1UL) << shift); > if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) > @@ -71,15 +73,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > /* Check if pte already has an hpte (case 2) */ > if (unlikely(old_pte & H_PAGE_HASHPTE)) { > /* There MIGHT be an HPTE for this pte */ > - unsigned long hash, slot; > + unsigned long gslot; > > - hash = hpt_hash(vpn, shift, ssize); > - if (old_pte & H_PAGE_F_SECOND) > - hash = ~hash; > - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; > - slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT; > - > - if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, mmu_psize, > + gslot = get_hidx_gslot(vpn, shift, ssize, rpte, 0); > + if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, mmu_psize, > mmu_psize, ssize, flags) == -1) > old_pte &= ~_PAGE_HPTEFLAGS; > } > @@ -106,8 +103,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > return -1; > } > > - new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & > - (H_PAGE_F_SECOND | H_PAGE_F_GIX); > + new_pte |= set_hidx_slot(ptep, rpte, 0, slot); > } > > /* > -- > 1.8.3.1
Ram Pai <linuxram@us.ibm.com> writes: .... > diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c > index a84bb44..239ca86 100644 > --- a/arch/powerpc/mm/hugetlbpage-hash64.c > +++ b/arch/powerpc/mm/hugetlbpage-hash64.c > @@ -22,6 +22,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > pte_t *ptep, unsigned long trap, unsigned long flags, > int ssize, unsigned int shift, unsigned int mmu_psize) > { > + real_pte_t rpte; > unsigned long vpn; > unsigned long old_pte, new_pte; > unsigned long rflags, pa, sz; > @@ -61,6 +62,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > } while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); > > rflags = htab_convert_pte_flags(new_pte); > + rpte = __real_pte(__pte(old_pte), ptep); > > sz = ((1UL) << shift); > if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) > @@ -71,15 +73,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > /* Check if pte already has an hpte (case 2) */ > if (unlikely(old_pte & H_PAGE_HASHPTE)) { > /* There MIGHT be an HPTE for this pte */ > - unsigned long hash, slot; > + unsigned long gslot; > > - hash = hpt_hash(vpn, shift, ssize); > - if (old_pte & H_PAGE_F_SECOND) > - hash = ~hash; > - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; > - slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT; > - > - if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, mmu_psize, > + gslot = get_hidx_gslot(vpn, shift, ssize, rpte, 0); > + if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, mmu_psize, > mmu_psize, ssize, flags) == -1) > old_pte &= ~_PAGE_HPTEFLAGS; > } > @@ -106,8 +103,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > return -1; > } > > - new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & > - (H_PAGE_F_SECOND | H_PAGE_F_GIX); > + new_pte |= set_hidx_slot(ptep, rpte, 0, slot); We don't really need rpte here. We are just need to track one entry here. May be it becomes simpler if use different helpers for 4k hpte and others ? -aneesh
On Wed, Jun 21, 2017 at 12:24:34PM +0530, Aneesh Kumar K.V wrote: > Ram Pai <linuxram@us.ibm.com> writes: > > .... > > > diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c > > index a84bb44..239ca86 100644 > > --- a/arch/powerpc/mm/hugetlbpage-hash64.c > > +++ b/arch/powerpc/mm/hugetlbpage-hash64.c > > @@ -22,6 +22,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > > pte_t *ptep, unsigned long trap, unsigned long flags, > > int ssize, unsigned int shift, unsigned int mmu_psize) > > { > > + real_pte_t rpte; > > unsigned long vpn; > > unsigned long old_pte, new_pte; > > unsigned long rflags, pa, sz; > > @@ -61,6 +62,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > > } while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); > > > > rflags = htab_convert_pte_flags(new_pte); > > + rpte = __real_pte(__pte(old_pte), ptep); > > > > sz = ((1UL) << shift); > > if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) > > @@ -71,15 +73,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > > /* Check if pte already has an hpte (case 2) */ > > if (unlikely(old_pte & H_PAGE_HASHPTE)) { > > /* There MIGHT be an HPTE for this pte */ > > - unsigned long hash, slot; > > + unsigned long gslot; > > > > - hash = hpt_hash(vpn, shift, ssize); > > - if (old_pte & H_PAGE_F_SECOND) > > - hash = ~hash; > > - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; > > - slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT; > > - > > - if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, mmu_psize, > > + gslot = get_hidx_gslot(vpn, shift, ssize, rpte, 0); > > + if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, mmu_psize, > > mmu_psize, ssize, flags) == -1) > > old_pte &= ~_PAGE_HPTEFLAGS; > > } > > @@ -106,8 +103,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, > > return -1; > > } > > > > - new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & > > - (H_PAGE_F_SECOND | H_PAGE_F_GIX); > > + new_pte |= set_hidx_slot(ptep, rpte, 0, slot); > > We don't really need rpte here. We are just need to track one entry > here. May be it becomes simpler if use different helpers for 4k hpte and > others ? actually we need rpte here. the hidx for these 64K-hpte backed PTEs are now stored in the second half of the pte. I have abstracted the helpers, so that the caller need not know the location of the hidx. It comes in really handy. RP
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 0eb3c89..2fa5c60 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -12,12 +12,8 @@ */ #define H_PAGE_COMBO _RPAGE_RPN0 /* this is a combo 4k page */ #define H_PAGE_4K_PFN _RPAGE_RPN1 /* PFN is for a single 4k page */ -#define H_PAGE_F_SECOND _RPAGE_RSV2 /* HPTE is in 2ndary HPTEG */ -#define H_PAGE_F_GIX (_RPAGE_RSV3 | _RPAGE_RSV4 | _RPAGE_RPN44) -#define H_PAGE_F_GIX_SHIFT 56 - -#define H_PAGE_BUSY _RPAGE_RPN42 /* software: PTE & hash are busy */ +#define H_PAGE_BUSY _RPAGE_RPN44 /* software: PTE & hash are busy */ #define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */ /* @@ -56,24 +52,18 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) unsigned long *hidxp; rpte.pte = pte; - rpte.hidx = 0; - if (pte_val(pte) & H_PAGE_COMBO) { - /* - * Make sure we order the hidx load against the H_PAGE_COMBO - * check. The store side ordering is done in __hash_page_4K - */ - smp_rmb(); - hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); - rpte.hidx = *hidxp; - } + /* + * The store side ordering is done in __hash_page_4K + */ + smp_rmb(); + hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + rpte.hidx = *hidxp; return rpte; } static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) { - if ((pte_val(rpte.pte) & H_PAGE_COMBO)) - return (rpte.hidx >> (index<<2)) & 0xf; - return (pte_val(rpte.pte) >> H_PAGE_F_GIX_SHIFT) & 0xf; + return ((rpte.hidx >> (index<<2)) & 0xfUL); } static inline unsigned long set_hidx_slot(pte_t *ptep, real_pte_t rpte, diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 3702a3c..1c25ec2 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -211,6 +211,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, unsigned long flags, int ssize) { + real_pte_t rpte; unsigned long hpte_group; unsigned long rflags, pa; unsigned long old_pte, new_pte; @@ -247,6 +248,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, } while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); + rpte = __real_pte(__pte(old_pte), ptep); if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -254,16 +256,13 @@ int __hash_page_64K(unsigned long ea, unsigned long access, vpn = hpt_vpn(ea, vsid, ssize); if (unlikely(old_pte & H_PAGE_HASHPTE)) { + unsigned long gslot; + /* * There MIGHT be an HPTE for this pte */ - hash = hpt_hash(vpn, shift, ssize); - if (old_pte & H_PAGE_F_SECOND) - hash = ~hash; - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT; - - if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K, + gslot = get_hidx_gslot(vpn, shift, ssize, rpte, 0); + if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, MMU_PAGE_64K, MMU_PAGE_64K, ssize, flags) == -1) old_pte &= ~_PAGE_HPTEFLAGS; @@ -313,8 +312,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, return -1; } - new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & - (H_PAGE_F_SECOND | H_PAGE_F_GIX); + set_hidx_slot(ptep, rpte, 0, slot); new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; } *ptep = __pte(new_pte & ~H_PAGE_BUSY); diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index a84bb44..239ca86 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -22,6 +22,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, unsigned long flags, int ssize, unsigned int shift, unsigned int mmu_psize) { + real_pte_t rpte; unsigned long vpn; unsigned long old_pte, new_pte; unsigned long rflags, pa, sz; @@ -61,6 +62,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, } while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); + rpte = __real_pte(__pte(old_pte), ptep); sz = ((1UL) << shift); if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -71,15 +73,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, /* Check if pte already has an hpte (case 2) */ if (unlikely(old_pte & H_PAGE_HASHPTE)) { /* There MIGHT be an HPTE for this pte */ - unsigned long hash, slot; + unsigned long gslot; - hash = hpt_hash(vpn, shift, ssize); - if (old_pte & H_PAGE_F_SECOND) - hash = ~hash; - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT; - - if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, mmu_psize, + gslot = get_hidx_gslot(vpn, shift, ssize, rpte, 0); + if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, mmu_psize, mmu_psize, ssize, flags) == -1) old_pte &= ~_PAGE_HPTEFLAGS; } @@ -106,8 +103,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, return -1; } - new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & - (H_PAGE_F_SECOND | H_PAGE_F_GIX); + new_pte |= set_hidx_slot(ptep, rpte, 0, slot); } /*
Rearrange 64K PTE bits to free up bits 3, 4, 5 and 6 in the 64K backed hpte pages. This along with the earlier patch will entirely free up the four bits from 64K PTE. This patch does the following change to 64K PTE that is backed by 64K hpte. H_PAGE_F_SECOND which occupied bit 4 moves to the second part of the pte. H_PAGE_F_GIX which occupied bit 5, 6 and 7 also moves to the second part of the pte. since bit 7 is now freed up, we move H_PAGE_BUSY from bit 9 to bit 7. Trying to minimize gaps so that contiguous bits can be allocated if needed in the future. The second part of the PTE will hold (H_PAGE_F_SECOND|H_PAGE_F_GIX) at bit 60,61,62,63. Signed-off-by: Ram Pai <linuxram@us.ibm.com> --- arch/powerpc/include/asm/book3s/64/hash-64k.h | 26 ++++++++------------------ arch/powerpc/mm/hash64_64k.c | 16 +++++++--------- arch/powerpc/mm/hugetlbpage-hash64.c | 16 ++++++---------- 3 files changed, 21 insertions(+), 37 deletions(-)