X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=arch%2Fx86%2Fmm%2Fpgtable_32.c;h=b4becbf8c570cfae3d140cbceef0cb74ac7fa2a3;hb=5ed4273af8469ca4723d4bf1bcd3abe2cc792e9f;hp=3165ec0672bd1855cb607c6864b83c810c29d729;hpb=e1c25dc638db01600069b3f9167d1b35f8d574b5;p=linux-2.6-omap-h63xx.git diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 3165ec0672b..b4becbf8c57 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -1,7 +1,3 @@ -/* - * linux/arch/i386/mm/pgtable.c - */ - #include #include #include @@ -75,7 +71,7 @@ void show_mem(void) * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. */ -static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) +void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; pud_t *pud; @@ -98,8 +94,8 @@ static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) return; } pte = pte_offset_kernel(pmd, vaddr); - if (pgprot_val(flags)) - set_pte_present(&init_mm, vaddr, pte, pfn_pte(pfn, flags)); + if (pte_val(pteval)) + set_pte_present(&init_mm, vaddr, pte, pteval); else pte_clear(&init_mm, vaddr, pte); @@ -145,22 +141,9 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) __flush_tlb_one(vaddr); } -static int fixmaps; unsigned long __FIXADDR_TOP = 0xfffff000; EXPORT_SYMBOL(__FIXADDR_TOP); -void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags) -{ - unsigned long address = __fix_to_virt(idx); - - if (idx >= __end_of_fixed_addresses) { - BUG(); - return; - } - set_pte_pfn(address, phys >> PAGE_SHIFT, flags); - fixmaps++; -} - /** * reserve_top_address - reserves a hole in the top of kernel address space * @reserve - size of hole to reserve @@ -168,222 +151,44 @@ void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags) * Can be used to relocate the fixmap area and poke a hole in the top * of kernel address space to make room for a hypervisor. */ -void reserve_top_address(unsigned long reserve) +void __init reserve_top_address(unsigned long reserve) { - BUG_ON(fixmaps > 0); + BUG_ON(fixmaps_set > 0); printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", (int)-reserve); __FIXADDR_TOP = -reserve - PAGE_SIZE; __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 + * vmalloc=size forces the vmalloc area to be exactly 'size' + * bytes. This can be used to increase (or decrease) the + * vmalloc area - the default is 128m. */ -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) +static int __init parse_vmalloc(char *arg) { - struct page *page = virt_to_page(pgd); + if (!arg) + return -EINVAL; - list_del(&page->lru); + __VMALLOC_RESERVE = memparse(arg, &arg); + return 0; } +early_param("vmalloc", parse_vmalloc); -#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. + * reservetop=size reserves a hole at the top of the kernel address space which + * a hypervisor can load into later. Needed for dynamically loaded hypervisors, + * so relocating the fixmap can be done before paging initialization. */ -static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) +static int __init parse_reservetop(char *arg) { - 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); + unsigned long address; - 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); - paravirt_release_pt(page_to_pfn(pte)); - tlb_remove_page(tlb, pte); -} - -#ifdef CONFIG_X86_PAE - -void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) -{ - paravirt_release_pd(__pa(pmd) >> PAGE_SHIFT); - tlb_remove_page(tlb, virt_to_page(pmd)); -} - -#endif - -int pmd_bad(pmd_t pmd) -{ - WARN_ON_ONCE(pmd_bad_v1(pmd) != pmd_bad_v2(pmd)); + if (!arg) + return -EINVAL; - return pmd_bad_v1(pmd); + address = memparse(arg, &arg); + reserve_top_address(address); + return 0; } +early_param("reservetop", parse_reservetop);