From patchwork Mon Sep 28 04:41:14 2009 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Gibson X-Patchwork-Id: 34367 X-Patchwork-Delegate: benh@kernel.crashing.org Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from bilbo.ozlabs.org (localhost [127.0.0.1]) by ozlabs.org (Postfix) with ESMTP id 190FE101908 for ; Mon, 28 Sep 2009 14:42:00 +1000 (EST) Received: by ozlabs.org (Postfix) id E38BFB7BF4; Mon, 28 Sep 2009 14:41:14 +1000 (EST) Delivered-To: linuxppc-dev@ozlabs.org Received: by ozlabs.org (Postfix, from userid 1007) id E1129B7BFA; Mon, 28 Sep 2009 14:41:14 +1000 (EST) To: Benjamin Herrenschmidt , From: David Gibson Subject: [5/5] Split hash MMU specific hugepage code into a new file In-Reply-To: <20090928043902.GA6302@yookeroo.seuss> Message-Id: <20090928044114.E1129B7BFA@ozlabs.org> Date: Mon, 28 Sep 2009 14:41:14 +1000 (EST) X-BeenThere: linuxppc-dev@lists.ozlabs.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: linuxppc-dev-bounces+patchwork-incoming=ozlabs.org@lists.ozlabs.org Errors-To: linuxppc-dev-bounces+patchwork-incoming=ozlabs.org@lists.ozlabs.org This patch separates the parts of hugetlbpage.c which are inherently specific to the hash MMU into a new hugelbpage-hash64.c file. Signed-off-by: David Gibson --- arch/powerpc/include/asm/hugetlb.h | 3 arch/powerpc/mm/Makefile | 5 - arch/powerpc/mm/hugetlbpage-hash64.c | 167 ++++++++++++++++++++++++++++++++++ arch/powerpc/mm/hugetlbpage.c | 168 ----------------------------------- 4 files changed, 176 insertions(+), 167 deletions(-) Index: working-2.6/arch/powerpc/mm/Makefile =================================================================== --- working-2.6.orig/arch/powerpc/mm/Makefile 2009-09-28 13:51:57.000000000 +1000 +++ working-2.6/arch/powerpc/mm/Makefile 2009-09-28 13:53:21.000000000 +1000 @@ -28,7 +28,10 @@ obj-$(CONFIG_44x) += 44x_mmu.o obj-$(CONFIG_FSL_BOOKE) += fsl_booke_mmu.o obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o obj-$(CONFIG_PPC_MM_SLICES) += slice.o -obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o +ifeq ($(CONFIG_HUGETLB_PAGE),y) +obj-y += hugetlbpage.o +obj-$(CONFIG_PPC_STD_MMU_64) += hugetlbpage-hash64.o +endif obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage-prot.o obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o obj-$(CONFIG_HIGHMEM) += highmem.o Index: working-2.6/arch/powerpc/mm/hugetlbpage-hash64.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ working-2.6/arch/powerpc/mm/hugetlbpage-hash64.c 2009-09-28 13:53:21.000000000 +1000 @@ -0,0 +1,167 @@ +/* + * PPC64 Huge TLB Page Support for hash based MMUs (POWER4 and later) + * + * Copyright (C) 2003 David Gibson, IBM Corporation. + * + * Based on the IA-32 version: + * Copyright (C) 2002, Rohit Seth + */ + +#include +#include +#include +#include +#include +#include + +/* + * Called by asm hashtable.S for doing lazy icache flush + */ +static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags, + pte_t pte, int trap, unsigned long sz) +{ + struct page *page; + int i; + + if (!pfn_valid(pte_pfn(pte))) + return rflags; + + page = pte_page(pte); + + /* page is dirty */ + if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) { + if (trap == 0x400) { + for (i = 0; i < (sz / PAGE_SIZE); i++) + __flush_dcache_icache(page_address(page+i)); + set_bit(PG_arch_1, &page->flags); + } else { + rflags |= HPTE_R_N; + } + } + return rflags; +} + +int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, + pte_t *ptep, unsigned long trap, int local, int ssize, + unsigned int shift, unsigned int mmu_psize) +{ + unsigned long old_pte, new_pte; + unsigned long va, rflags, pa, sz; + long slot; + int err = 1; + + BUG_ON(shift != mmu_psize_defs[mmu_psize].shift); + + /* Search the Linux page table for a match with va */ + va = hpt_va(ea, vsid, ssize); + + /* + * Check the user's access rights to the page. If access should be + * prevented then send the problem up to do_page_fault. + */ + if (unlikely(access & ~pte_val(*ptep))) + goto out; + /* + * At this point, we have a pte (old_pte) which can be used to build + * or update an HPTE. There are 2 cases: + * + * 1. There is a valid (present) pte with no associated HPTE (this is + * the most common case) + * 2. There is a valid (present) pte with an associated HPTE. The + * current values of the pp bits in the HPTE prevent access + * because we are doing software DIRTY bit management and the + * page is currently not DIRTY. + */ + + + do { + old_pte = pte_val(*ptep); + if (old_pte & _PAGE_BUSY) + goto out; + new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED; + } while(old_pte != __cmpxchg_u64((unsigned long *)ptep, + old_pte, new_pte)); + + rflags = 0x2 | (!(new_pte & _PAGE_RW)); + /* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */ + rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N); + sz = ((1UL) << shift); + if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) + /* No CPU has hugepages but lacks no execute, so we + * don't need to worry about that case */ + rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte), + trap, sz); + + /* Check if pte already has an hpte (case 2) */ + if (unlikely(old_pte & _PAGE_HASHPTE)) { + /* There MIGHT be an HPTE for this pte */ + unsigned long hash, slot; + + hash = hpt_hash(va, shift, ssize); + if (old_pte & _PAGE_F_SECOND) + hash = ~hash; + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot += (old_pte & _PAGE_F_GIX) >> 12; + + if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize, + ssize, local) == -1) + old_pte &= ~_PAGE_HPTEFLAGS; + } + + if (likely(!(old_pte & _PAGE_HASHPTE))) { + unsigned long hash = hpt_hash(va, shift, ssize); + unsigned long hpte_group; + + pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; + +repeat: + hpte_group = ((hash & htab_hash_mask) * + HPTES_PER_GROUP) & ~0x7UL; + + /* clear HPTE slot informations in new PTE */ +#ifdef CONFIG_PPC_64K_PAGES + new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0; +#else + new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE; +#endif + /* Add in WIMG bits */ + rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | + _PAGE_COHERENT | _PAGE_GUARDED)); + + /* Insert into the hash table, primary slot */ + slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0, + mmu_psize, ssize); + + /* Primary is full, try the secondary */ + if (unlikely(slot == -1)) { + hpte_group = ((~hash & htab_hash_mask) * + HPTES_PER_GROUP) & ~0x7UL; + slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, + HPTE_V_SECONDARY, + mmu_psize, ssize); + if (slot == -1) { + if (mftb() & 0x1) + hpte_group = ((hash & htab_hash_mask) * + HPTES_PER_GROUP)&~0x7UL; + + ppc_md.hpte_remove(hpte_group); + goto repeat; + } + } + + if (unlikely(slot == -2)) + panic("hash_huge_page: pte_insert failed\n"); + + new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX); + } + + /* + * No need to use ldarx/stdcx here + */ + *ptep = __pte(new_pte & ~_PAGE_BUSY); + + err = 0; + + out: + return err; +} Index: working-2.6/arch/powerpc/mm/hugetlbpage.c =================================================================== --- working-2.6.orig/arch/powerpc/mm/hugetlbpage.c 2009-09-28 13:53:16.000000000 +1000 +++ working-2.6/arch/powerpc/mm/hugetlbpage.c 2009-09-28 13:53:21.000000000 +1000 @@ -7,29 +7,17 @@ * Copyright (C) 2002, Rohit Seth */ -#include -#include #include +#include #include -#include -#include -#include -#include -#include +#include #include #include -#include -#include -#include -#include -#include #define PAGE_SHIFT_64K 16 #define PAGE_SHIFT_16M 24 #define PAGE_SHIFT_16G 34 -#define NUM_LOW_AREAS (0x100000000UL >> SID_SHIFT) -#define NUM_HIGH_AREAS (PGTABLE_RANGE >> HTLB_AREA_SHIFT) #define MAX_NUMBER_GPAGES 1024 /* Tracks the 16G pages after the device tree is scanned and before the @@ -507,158 +495,6 @@ unsigned long vma_mmu_pagesize(struct vm return 1UL << mmu_psize_to_shift(psize); } -/* - * Called by asm hashtable.S for doing lazy icache flush - */ -static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags, - pte_t pte, int trap, unsigned long sz) -{ - struct page *page; - int i; - - if (!pfn_valid(pte_pfn(pte))) - return rflags; - - page = pte_page(pte); - - /* page is dirty */ - if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) { - if (trap == 0x400) { - for (i = 0; i < (sz / PAGE_SIZE); i++) - __flush_dcache_icache(page_address(page+i)); - set_bit(PG_arch_1, &page->flags); - } else { - rflags |= HPTE_R_N; - } - } - return rflags; -} - -int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, - pte_t *ptep, unsigned long trap, int local, int ssize, - unsigned int shift, unsigned int mmu_psize) -{ - unsigned long old_pte, new_pte; - unsigned long va, rflags, pa, sz; - long slot; - int err = 1; - - BUG_ON(shift != mmu_psize_defs[mmu_psize].shift); - - /* Search the Linux page table for a match with va */ - va = hpt_va(ea, vsid, ssize); - - /* - * Check the user's access rights to the page. If access should be - * prevented then send the problem up to do_page_fault. - */ - if (unlikely(access & ~pte_val(*ptep))) - goto out; - /* - * At this point, we have a pte (old_pte) which can be used to build - * or update an HPTE. There are 2 cases: - * - * 1. There is a valid (present) pte with no associated HPTE (this is - * the most common case) - * 2. There is a valid (present) pte with an associated HPTE. The - * current values of the pp bits in the HPTE prevent access - * because we are doing software DIRTY bit management and the - * page is currently not DIRTY. - */ - - - do { - old_pte = pte_val(*ptep); - if (old_pte & _PAGE_BUSY) - goto out; - new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED; - } while(old_pte != __cmpxchg_u64((unsigned long *)ptep, - old_pte, new_pte)); - - rflags = 0x2 | (!(new_pte & _PAGE_RW)); - /* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */ - rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N); - sz = ((1UL) << shift); - if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) - /* No CPU has hugepages but lacks no execute, so we - * don't need to worry about that case */ - rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte), - trap, sz); - - /* Check if pte already has an hpte (case 2) */ - if (unlikely(old_pte & _PAGE_HASHPTE)) { - /* There MIGHT be an HPTE for this pte */ - unsigned long hash, slot; - - hash = hpt_hash(va, shift, ssize); - if (old_pte & _PAGE_F_SECOND) - hash = ~hash; - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - slot += (old_pte & _PAGE_F_GIX) >> 12; - - if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize, - ssize, local) == -1) - old_pte &= ~_PAGE_HPTEFLAGS; - } - - if (likely(!(old_pte & _PAGE_HASHPTE))) { - unsigned long hash = hpt_hash(va, shift, ssize); - unsigned long hpte_group; - - pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; - -repeat: - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; - - /* clear HPTE slot informations in new PTE */ -#ifdef CONFIG_PPC_64K_PAGES - new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0; -#else - new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE; -#endif - /* Add in WIMG bits */ - rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | - _PAGE_COHERENT | _PAGE_GUARDED)); - - /* Insert into the hash table, primary slot */ - slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0, - mmu_psize, ssize); - - /* Primary is full, try the secondary */ - if (unlikely(slot == -1)) { - hpte_group = ((~hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; - slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, - HPTE_V_SECONDARY, - mmu_psize, ssize); - if (slot == -1) { - if (mftb() & 0x1) - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP)&~0x7UL; - - ppc_md.hpte_remove(hpte_group); - goto repeat; - } - } - - if (unlikely(slot == -2)) - panic("hash_huge_page: pte_insert failed\n"); - - new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX); - } - - /* - * No need to use ldarx/stdcx here - */ - *ptep = __pte(new_pte & ~_PAGE_BUSY); - - err = 0; - - out: - return err; -} - static int __init add_huge_page_size(unsigned long long size) { int shift = __ffs(size); Index: working-2.6/arch/powerpc/include/asm/hugetlb.h =================================================================== --- working-2.6.orig/arch/powerpc/include/asm/hugetlb.h 2009-09-28 13:53:00.000000000 +1000 +++ working-2.6/arch/powerpc/include/asm/hugetlb.h 2009-09-28 13:53:21.000000000 +1000 @@ -13,6 +13,9 @@ static inline int hugepd_ok(hugepd_t hpd #define is_hugepd(pdep) (hugepd_ok(*((hugepd_t *)(pdep)))) #define HUGEPD_SHIFT_MASK 0x3f +pte_t *huge_pte_offset_and_shift(struct mm_struct *mm, + unsigned long addr, unsigned *shift); + int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len);