Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758632AbYCRFd5 (ORCPT ); Tue, 18 Mar 2008 01:33:57 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753276AbYCRFYc (ORCPT ); Tue, 18 Mar 2008 01:24:32 -0400 Received: from gw.goop.org ([64.81.55.164]:37843 "EHLO mail.goop.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752866AbYCRFYJ (ORCPT ); Tue, 18 Mar 2008 01:24:09 -0400 Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [PATCH 04 of 31] x86: add common mm/pgtable.c X-Mercurial-Node: 3cb76b3ed789674ad73ae7a2f3a17ac3741fb720 Message-Id: <3cb76b3ed789674ad73a.1205797015@localhost> In-Reply-To: Date: Mon, 17 Mar 2008 16:36:55 -0700 From: Jeremy Fitzhardinge To: Ingo Molnar Cc: LKML , Ian Campbell Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 16155 Lines: 607 Add a common arch/x86/mm/pgtable.c file for common pagetable functions. Signed-off-by: Jeremy Fitzhardinge --- arch/x86/mm/Makefile | 2 arch/x86/mm/pgtable.c | 239 ++++++++++++++++++++++++++++++++++++++++++ arch/x86/mm/pgtable_32.c | 187 -------------------------------- include/asm-x86/pgalloc.h | 18 +++ include/asm-x86/pgalloc_32.h | 11 - include/asm-x86/pgalloc_64.h | 67 ----------- 6 files changed, 258 insertions(+), 266 deletions(-) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,4 +1,4 @@ -obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o +obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o pgtable.o mmap.o obj-$(CONFIG_X86_32) += pgtable_32.o diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c new file mode 100644 --- /dev/null +++ b/arch/x86/mm/pgtable.c @@ -0,0 +1,239 @@ +#include +#include +#include + +pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) +{ + return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); +} + +pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) +{ + struct page *pte; + +#ifdef CONFIG_HIGHPTE + pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0); +#else + pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); +#endif + if (pte) + pgtable_page_ctor(pte); + return pte; +} + +#ifdef CONFIG_X86_64 +static inline void pgd_list_add(pgd_t *pgd) +{ + struct page *page = virt_to_page(pgd); + unsigned long flags; + + spin_lock_irqsave(&pgd_lock, flags); + list_add(&page->lru, &pgd_list); + spin_unlock_irqrestore(&pgd_lock, flags); +} + +static inline void pgd_list_del(pgd_t *pgd) +{ + struct page *page = virt_to_page(pgd); + unsigned long flags; + + spin_lock_irqsave(&pgd_lock, flags); + list_del(&page->lru); + spin_unlock_irqrestore(&pgd_lock, flags); +} + +pgd_t *pgd_alloc(struct mm_struct *mm) +{ + unsigned boundary; + pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + if (!pgd) + return NULL; + pgd_list_add(pgd); + /* + * Copy kernel pointers in from init. + * Could keep a freelist or slab cache of those because the kernel + * part never changes. + */ + boundary = pgd_index(__PAGE_OFFSET); + memset(pgd, 0, boundary * sizeof(pgd_t)); + memcpy(pgd + boundary, + init_level4_pgt + boundary, + (PTRS_PER_PGD - boundary) * sizeof(pgd_t)); + return pgd; +} + +void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + BUG_ON((unsigned long)pgd & (PAGE_SIZE-1)); + pgd_list_del(pgd); + free_page((unsigned long)pgd); +} +#else +/* + * List of all pgd's needed for non-PAE so it can invalidate entries + * in both cached and uncached pgd's; not needed for PAE since the + * kernel pmd is shared. If PAE were not to share the pmd a similar + * tactic would be needed. This is essentially codepath-based locking + * against pageattr.c; it is the unique case in which a valid change + * of kernel pagetables can't be lazily synchronized by vmalloc faults. + * vmalloc faults work because attached pagetables are never freed. + * -- wli + */ +static inline void pgd_list_add(pgd_t *pgd) +{ + struct page *page = virt_to_page(pgd); + + list_add(&page->lru, &pgd_list); +} + +static inline void pgd_list_del(pgd_t *pgd) +{ + struct page *page = virt_to_page(pgd); + + list_del(&page->lru); +} + +#define UNSHARED_PTRS_PER_PGD \ + (SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD) + +static void pgd_ctor(void *p) +{ + pgd_t *pgd = p; + unsigned long flags; + + /* Clear usermode parts of PGD */ + memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t)); + + spin_lock_irqsave(&pgd_lock, flags); + + /* If the pgd points to a shared pagetable level (either the + ptes in non-PAE, or shared PMD in PAE), then just copy the + references from swapper_pg_dir. */ + if (PAGETABLE_LEVELS == 2 || + (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD)) { + clone_pgd_range(pgd + USER_PTRS_PER_PGD, + swapper_pg_dir + USER_PTRS_PER_PGD, + KERNEL_PGD_PTRS); + paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT, + __pa(swapper_pg_dir) >> PAGE_SHIFT, + USER_PTRS_PER_PGD, + KERNEL_PGD_PTRS); + } + + /* list required to sync kernel mapping updates */ + if (!SHARED_KERNEL_PMD) + pgd_list_add(pgd); + + spin_unlock_irqrestore(&pgd_lock, flags); +} + +static void pgd_dtor(void *pgd) +{ + unsigned long flags; /* can be called from interrupt context */ + + if (SHARED_KERNEL_PMD) + return; + + spin_lock_irqsave(&pgd_lock, flags); + pgd_list_del(pgd); + spin_unlock_irqrestore(&pgd_lock, flags); +} + +#ifdef CONFIG_X86_PAE +/* + * Mop up any pmd pages which may still be attached to the pgd. + * Normally they will be freed by munmap/exit_mmap, but any pmd we + * preallocate which never got a corresponding vma will need to be + * freed manually. + */ +static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) +{ + int i; + + for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) { + pgd_t pgd = pgdp[i]; + + if (pgd_val(pgd) != 0) { + pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); + + pgdp[i] = native_make_pgd(0); + + paravirt_release_pd(pgd_val(pgd) >> PAGE_SHIFT); + pmd_free(mm, pmd); + } + } +} + +/* + * In PAE mode, we need to do a cr3 reload (=tlb flush) when + * updating the top-level pagetable entries to guarantee the + * processor notices the update. Since this is expensive, and + * all 4 top-level entries are used almost immediately in a + * new process's life, we just pre-populate them here. + * + * Also, if we're in a paravirt environment where the kernel pmd is + * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate + * and initialize the kernel pmds here. + */ +static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd) +{ + pud_t *pud; + unsigned long addr; + int i; + + pud = pud_offset(pgd, 0); + for (addr = i = 0; i < UNSHARED_PTRS_PER_PGD; + i++, pud++, addr += PUD_SIZE) { + pmd_t *pmd = pmd_alloc_one(mm, addr); + + if (!pmd) { + pgd_mop_up_pmds(mm, pgd); + return 0; + } + + if (i >= USER_PTRS_PER_PGD) + memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), + sizeof(pmd_t) * PTRS_PER_PMD); + + pud_populate(mm, pud, pmd); + } + + return 1; +} +#else /* !CONFIG_X86_PAE */ +/* No need to prepopulate any pagetable entries in non-PAE modes. */ +static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd) +{ + return 1; +} + +static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgd) +{ +} +#endif /* CONFIG_X86_PAE */ + +pgd_t *pgd_alloc(struct mm_struct *mm) +{ + pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + + /* so that alloc_pd can use it */ + mm->pgd = pgd; + if (pgd) + pgd_ctor(pgd); + + if (pgd && !pgd_prepopulate_pmd(mm, pgd)) { + pgd_dtor(pgd); + free_page((unsigned long)pgd); + pgd = NULL; + } + + return pgd; +} + +void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + pgd_mop_up_pmds(mm, pgd); + pgd_dtor(pgd); + free_page((unsigned long)pgd); +} +#endif diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -173,193 +173,6 @@ __VMALLOC_RESERVE += reserve; } -pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) -{ - return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); -} - -pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) -{ - struct page *pte; - -#ifdef CONFIG_HIGHPTE - pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0); -#else - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); -#endif - if (pte) - pgtable_page_ctor(pte); - return pte; -} - -/* - * List of all pgd's needed for non-PAE so it can invalidate entries - * in both cached and uncached pgd's; not needed for PAE since the - * kernel pmd is shared. If PAE were not to share the pmd a similar - * tactic would be needed. This is essentially codepath-based locking - * against pageattr.c; it is the unique case in which a valid change - * of kernel pagetables can't be lazily synchronized by vmalloc faults. - * vmalloc faults work because attached pagetables are never freed. - * -- wli - */ -static inline void pgd_list_add(pgd_t *pgd) -{ - struct page *page = virt_to_page(pgd); - - list_add(&page->lru, &pgd_list); -} - -static inline void pgd_list_del(pgd_t *pgd) -{ - struct page *page = virt_to_page(pgd); - - list_del(&page->lru); -} - -#define UNSHARED_PTRS_PER_PGD \ - (SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD) - -static void pgd_ctor(void *p) -{ - pgd_t *pgd = p; - unsigned long flags; - - /* Clear usermode parts of PGD */ - memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t)); - - spin_lock_irqsave(&pgd_lock, flags); - - /* If the pgd points to a shared pagetable level (either the - ptes in non-PAE, or shared PMD in PAE), then just copy the - references from swapper_pg_dir. */ - if (PAGETABLE_LEVELS == 2 || - (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD)) { - clone_pgd_range(pgd + USER_PTRS_PER_PGD, - swapper_pg_dir + USER_PTRS_PER_PGD, - KERNEL_PGD_PTRS); - paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT, - __pa(swapper_pg_dir) >> PAGE_SHIFT, - USER_PTRS_PER_PGD, - KERNEL_PGD_PTRS); - } - - /* list required to sync kernel mapping updates */ - if (!SHARED_KERNEL_PMD) - pgd_list_add(pgd); - - spin_unlock_irqrestore(&pgd_lock, flags); -} - -static void pgd_dtor(void *pgd) -{ - unsigned long flags; /* can be called from interrupt context */ - - if (SHARED_KERNEL_PMD) - return; - - spin_lock_irqsave(&pgd_lock, flags); - pgd_list_del(pgd); - spin_unlock_irqrestore(&pgd_lock, flags); -} - -#ifdef CONFIG_X86_PAE -/* - * Mop up any pmd pages which may still be attached to the pgd. - * Normally they will be freed by munmap/exit_mmap, but any pmd we - * preallocate which never got a corresponding vma will need to be - * freed manually. - */ -static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) -{ - int i; - - for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) { - pgd_t pgd = pgdp[i]; - - if (pgd_val(pgd) != 0) { - pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); - - pgdp[i] = native_make_pgd(0); - - paravirt_release_pd(pgd_val(pgd) >> PAGE_SHIFT); - pmd_free(mm, pmd); - } - } -} - -/* - * In PAE mode, we need to do a cr3 reload (=tlb flush) when - * updating the top-level pagetable entries to guarantee the - * processor notices the update. Since this is expensive, and - * all 4 top-level entries are used almost immediately in a - * new process's life, we just pre-populate them here. - * - * Also, if we're in a paravirt environment where the kernel pmd is - * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate - * and initialize the kernel pmds here. - */ -static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd) -{ - pud_t *pud; - unsigned long addr; - int i; - - pud = pud_offset(pgd, 0); - for (addr = i = 0; i < UNSHARED_PTRS_PER_PGD; - i++, pud++, addr += PUD_SIZE) { - pmd_t *pmd = pmd_alloc_one(mm, addr); - - if (!pmd) { - pgd_mop_up_pmds(mm, pgd); - return 0; - } - - if (i >= USER_PTRS_PER_PGD) - memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), - sizeof(pmd_t) * PTRS_PER_PMD); - - pud_populate(mm, pud, pmd); - } - - return 1; -} -#else /* !CONFIG_X86_PAE */ -/* No need to prepopulate any pagetable entries in non-PAE modes. */ -static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd) -{ - return 1; -} - -static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) -{ -} -#endif /* CONFIG_X86_PAE */ - -pgd_t *pgd_alloc(struct mm_struct *mm) -{ - pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - - /* so that alloc_pd can use it */ - mm->pgd = pgd; - if (pgd) - pgd_ctor(pgd); - - if (pgd && !pgd_prepopulate_pmd(mm, pgd)) { - pgd_dtor(pgd); - free_page((unsigned long)pgd); - pgd = NULL; - } - - return pgd; -} - -void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - pgd_mop_up_pmds(mm, pgd); - pgd_dtor(pgd); - free_page((unsigned long)pgd); -} - void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { pgtable_page_dtor(pte); diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h --- a/include/asm-x86/pgalloc.h +++ b/include/asm-x86/pgalloc.h @@ -1,5 +1,23 @@ +#ifndef _ASM_X86_PGALLOC_H +#define _ASM_X86_PGALLOC_H + +#include +#include /* for struct page */ +#include + +/* + * Allocate and free page tables. + */ +extern pgd_t *pgd_alloc(struct mm_struct *); +extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); + +extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long); +extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long); + #ifdef CONFIG_X86_32 # include "pgalloc_32.h" #else # include "pgalloc_64.h" #endif + +#endif /* _ASM_X86_PGALLOC_H */ diff --git a/include/asm-x86/pgalloc_32.h b/include/asm-x86/pgalloc_32.h --- a/include/asm-x86/pgalloc_32.h +++ b/include/asm-x86/pgalloc_32.h @@ -1,11 +1,5 @@ #ifndef _I386_PGALLOC_H #define _I386_PGALLOC_H - -#include -#include /* for struct page */ -#include -#include -#include #ifdef CONFIG_PARAVIRT #include @@ -36,11 +30,6 @@ /* * Allocate and free page tables. */ -extern pgd_t *pgd_alloc(struct mm_struct *); -extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); - -extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long); -extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long); static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { diff --git a/include/asm-x86/pgalloc_64.h b/include/asm-x86/pgalloc_64.h --- a/include/asm-x86/pgalloc_64.h +++ b/include/asm-x86/pgalloc_64.h @@ -1,8 +1,6 @@ #ifndef _X86_64_PGALLOC_H #define _X86_64_PGALLOC_H -#include -#include #include static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) @@ -49,71 +47,6 @@ free_page((unsigned long)pud); } -static inline void pgd_list_add(pgd_t *pgd) -{ - struct page *page = virt_to_page(pgd); - unsigned long flags; - - spin_lock_irqsave(&pgd_lock, flags); - list_add(&page->lru, &pgd_list); - spin_unlock_irqrestore(&pgd_lock, flags); -} - -static inline void pgd_list_del(pgd_t *pgd) -{ - struct page *page = virt_to_page(pgd); - unsigned long flags; - - spin_lock_irqsave(&pgd_lock, flags); - list_del(&page->lru); - spin_unlock_irqrestore(&pgd_lock, flags); -} - -static inline pgd_t *pgd_alloc(struct mm_struct *mm) -{ - unsigned boundary; - pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); - if (!pgd) - return NULL; - pgd_list_add(pgd); - /* - * Copy kernel pointers in from init. - * Could keep a freelist or slab cache of those because the kernel - * part never changes. - */ - boundary = pgd_index(__PAGE_OFFSET); - memset(pgd, 0, boundary * sizeof(pgd_t)); - memcpy(pgd + boundary, - init_level4_pgt + boundary, - (PTRS_PER_PGD - boundary) * sizeof(pgd_t)); - return pgd; -} - -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - BUG_ON((unsigned long)pgd & (PAGE_SIZE-1)); - pgd_list_del(pgd); - free_page((unsigned long)pgd); -} - -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) -{ - return (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); -} - -static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) -{ - struct page *page; - void *p; - - p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); - if (!p) - return NULL; - page = virt_to_page(p); - pgtable_page_ctor(page); - return page; -} - /* Should really implement gc for free page table pages. This could be done with a reference count in struct page. */ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/