From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
To: Ram Pai <linuxram@us.ibm.com>,
linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Cc: benh@kernel.crashing.org, paulus@samba.org, mpe@ellerman.id.au,
khandual@linux.vnet.ibm.com, bsingharora@gmail.com,
dave.hansen@intel.com, hbabu@us.ibm.com, linuxram@us.ibm.com
Subject: Re: [RFC v2 02/12] powerpc: Free up four 64K PTE bits in 64K backed hpte pages.
Date: Wed, 21 Jun 2017 12:20:18 +0530 [thread overview]
Message-ID: <87zid1al79.fsf@skywalker.in.ibm.com> (raw)
In-Reply-To: <1497671564-20030-3-git-send-email-linuxram@us.ibm.com>
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
next prev parent reply other threads:[~2017-06-21 6:51 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-06-17 3:52 [RFC v2 00/12] powerpc: Memory Protection Keys Ram Pai
2017-06-17 3:52 ` [RFC v2 01/12] powerpc: Free up four 64K PTE bits in 4K backed hpte pages Ram Pai
2017-06-20 10:20 ` Anshuman Khandual
2017-06-20 23:23 ` Ram Pai
2017-06-21 5:35 ` Anshuman Khandual
2017-06-21 6:34 ` Ram Pai
2017-06-21 6:41 ` Aneesh Kumar K.V
2017-06-21 9:30 ` Ram Pai
2017-06-22 9:07 ` Anshuman Khandual
2017-06-22 16:20 ` Ram Pai
2017-06-17 3:52 ` [RFC v2 02/12] powerpc: Free up four 64K PTE bits in 64K " Ram Pai
2017-06-20 10:51 ` Anshuman Khandual
2017-06-20 23:25 ` Ram Pai
2017-06-21 6:50 ` Aneesh Kumar K.V [this message]
2017-06-21 6:54 ` Aneesh Kumar K.V
2017-06-21 20:14 ` Ram Pai
2017-06-17 3:52 ` [RFC v2 03/12] powerpc: Implement sys_pkey_alloc and sys_pkey_free system call Ram Pai
2017-06-19 12:18 ` Michael Ellerman
2017-06-20 22:45 ` Ram Pai
2017-06-17 3:52 ` [RFC v2 04/12] powerpc: store and restore the pkey state across context switches Ram Pai
2017-06-17 3:52 ` [RFC v2 05/12] powerpc: Implementation for sys_mprotect_pkey() system call Ram Pai
2017-06-21 7:16 ` Aneesh Kumar K.V
2017-06-17 3:52 ` [RFC v2 06/12] powerpc: Program HPTE key protection bits Ram Pai
2017-06-20 8:21 ` Anshuman Khandual
2017-06-20 23:26 ` Ram Pai
2017-06-17 3:52 ` [RFC v2 07/12] powerpc: Macro the mask used for checking DSI exception Ram Pai
2017-06-20 8:14 ` Anshuman Khandual
2017-06-20 23:28 ` Ram Pai
2017-06-21 7:25 ` Aneesh Kumar K.V
2017-06-21 9:17 ` Ram Pai
2017-06-17 3:52 ` [RFC v2 08/12] powerpc: Handle exceptions caused by violation of pkey protection Ram Pai
2017-06-20 7:24 ` Anshuman Khandual
2017-06-20 23:43 ` Ram Pai
2017-06-21 3:54 ` Anshuman Khandual
2017-06-21 6:26 ` Ram Pai
2017-06-17 3:52 ` [RFC v2 09/12] powerpc: Deliver SEGV signal on pkey violation Ram Pai
2017-06-20 6:54 ` Anshuman Khandual
2017-06-20 23:56 ` Ram Pai
2017-06-21 3:18 ` Anshuman Khandual
2017-06-21 6:10 ` Ram Pai
2017-06-17 3:52 ` [RFC v2 10/12] powerpc: Read AMR only if pkey-violation caused the exception Ram Pai
2017-06-19 11:06 ` Michael Ellerman
2017-06-19 17:59 ` Ram Pai
2017-06-20 6:46 ` Anshuman Khandual
2017-06-20 23:58 ` Ram Pai
2017-06-20 23:56 ` Ram Pai
2017-06-17 3:52 ` [RFC v2 11/12]Documentation: Documentation updates Ram Pai
2017-06-20 6:18 ` Anshuman Khandual
2017-06-21 0:04 ` Ram Pai
2017-06-17 3:52 ` [RFC v2 12/12]selftest: Updated protection key selftest Ram Pai
2017-06-19 11:04 ` Michael Ellerman
2017-06-20 6:26 ` Anshuman Khandual
2017-06-21 0:10 ` Ram Pai
2017-06-20 5:10 ` [RFC v2 00/12] powerpc: Memory Protection Keys Balbir Singh
2017-06-20 6:05 ` Anshuman Khandual
2017-06-20 9:56 ` Benjamin Herrenschmidt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87zid1al79.fsf@skywalker.in.ibm.com \
--to=aneesh.kumar@linux.vnet.ibm.com \
--cc=benh@kernel.crashing.org \
--cc=bsingharora@gmail.com \
--cc=dave.hansen@intel.com \
--cc=hbabu@us.ibm.com \
--cc=khandual@linux.vnet.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=linuxram@us.ibm.com \
--cc=mpe@ellerman.id.au \
--cc=paulus@samba.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).