diff options
Diffstat (limited to 'arch/x86/mm')
| -rw-r--r-- | arch/x86/mm/Makefile | 2 | ||||
| -rw-r--r-- | arch/x86/mm/init_32.c | 27 | ||||
| -rw-r--r-- | arch/x86/mm/init_64.c | 27 | ||||
| -rw-r--r-- | arch/x86/mm/ioremap.c | 31 | ||||
| -rw-r--r-- | arch/x86/mm/pageattr.c | 4 | ||||
| -rw-r--r-- | arch/x86/mm/pat.c | 175 | ||||
| -rw-r--r-- | arch/x86/mm/pgtable.c | 276 | ||||
| -rw-r--r-- | arch/x86/mm/pgtable_32.c | 204 |
8 files changed, 515 insertions, 231 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 20941d2954e2..b7b3e4c7cfc9 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,5 +1,5 @@ obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o + pat.o pgtable.o obj-$(CONFIG_X86_32) += pgtable_32.o diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 9ec62da85fd7..baf7c4f643c8 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -71,7 +71,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) if (!(pgd_val(*pgd) & _PAGE_PRESENT)) { pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE); - paravirt_alloc_pd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); + paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); pud = pud_offset(pgd, 0); BUG_ON(pmd_table != pmd_offset(pud, 0)); @@ -100,7 +100,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE); } - paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT); + paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE)); BUG_ON(page_table != pte_offset_kernel(pmd, 0)); } @@ -227,6 +227,25 @@ static inline int page_kills_ppro(unsigned long pagenr) return 0; } +/* + * devmem_is_allowed() checks to see if /dev/mem access to a certain address + * is valid. The argument is a physical page number. + * + * + * On x86, access has to be given to the first megabyte of ram because that area + * contains bios code and data regions used by X and dosemu and similar apps. + * Access has to be given to non-kernel-ram areas as well, these contain the PCI + * mmio resources as well as potential bios/acpi data regions. + */ +int devmem_is_allowed(unsigned long pagenr) +{ + if (pagenr <= 256) + return 1; + if (!page_is_ram(pagenr)) + return 1; + return 0; +} + #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; pgprot_t kmap_prot; @@ -365,7 +384,7 @@ void __init native_pagetable_setup_start(pgd_t *base) pte_clear(NULL, va, pte); } - paravirt_alloc_pd(&init_mm, __pa(base) >> PAGE_SHIFT); + paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT); } void __init native_pagetable_setup_done(pgd_t *base) @@ -457,7 +476,7 @@ void zap_low_mappings(void) * Note that "pgd_clear()" doesn't do it for * us, because pgd_clear() is a no-op on i386. */ - for (i = 0; i < USER_PTRS_PER_PGD; i++) { + for (i = 0; i < KERNEL_PGD_BOUNDARY; i++) { #ifdef CONFIG_X86_PAE set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page))); #else diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 1ff7906a9a4d..0cca62663037 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -135,7 +135,7 @@ static __init void *spp_getpage(void) return ptr; } -static __init void +static void set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) { pgd_t *pgd; @@ -173,7 +173,7 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) new_pte = pfn_pte(phys >> PAGE_SHIFT, prot); pte = pte_offset_kernel(pmd, vaddr); - if (!pte_none(*pte) && + if (!pte_none(*pte) && pte_val(new_pte) && pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask)) pte_ERROR(*pte); set_pte(pte, new_pte); @@ -214,8 +214,7 @@ void __init cleanup_highmap(void) } /* NOTE: this is meant to be run only at boot */ -void __init -__set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot) +void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot) { unsigned long address = __fix_to_virt(idx); @@ -664,6 +663,26 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif /* CONFIG_MEMORY_HOTPLUG */ +/* + * devmem_is_allowed() checks to see if /dev/mem access to a certain address + * is valid. The argument is a physical page number. + * + * + * On x86, access has to be given to the first megabyte of ram because that area + * contains bios code and data regions used by X and dosemu and similar apps. + * Access has to be given to non-kernel-ram areas as well, these contain the PCI + * mmio resources as well as potential bios/acpi data regions. + */ +int devmem_is_allowed(unsigned long pagenr) +{ + if (pagenr <= 256) + return 1; + if (!page_is_ram(pagenr)) + return 1; + return 0; +} + + static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules, kcore_vsyscall; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 3a4baf95e24d..d176b23110cc 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -336,6 +336,35 @@ void iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(iounmap); +/* + * Convert a physical pointer to a virtual kernel pointer for /dev/mem + * access + */ +void *xlate_dev_mem_ptr(unsigned long phys) +{ + void *addr; + unsigned long start = phys & PAGE_MASK; + + /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ + if (page_is_ram(start >> PAGE_SHIFT)) + return __va(phys); + + addr = (void *)ioremap(start, PAGE_SIZE); + if (addr) + addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK)); + + return addr; +} + +void unxlate_dev_mem_ptr(unsigned long phys, void *addr) +{ + if (page_is_ram(phys >> PAGE_SHIFT)) + return; + + iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK)); + return; +} + #ifdef CONFIG_X86_32 int __initdata early_ioremap_debug; @@ -407,7 +436,7 @@ void __init early_ioremap_clear(void) pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); pmd_clear(pmd); - paravirt_release_pt(__pa(bm_pte) >> PAGE_SHIFT); + paravirt_release_pte(__pa(bm_pte) >> PAGE_SHIFT); __flush_tlb_all(); } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index c29ebd037254..bd5e05c654dc 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -483,9 +483,7 @@ static int split_large_page(pte_t *kpte, unsigned long address) goto out_unlock; pbase = (pte_t *)page_address(base); -#ifdef CONFIG_X86_32 - paravirt_alloc_pt(&init_mm, page_to_pfn(base)); -#endif + paravirt_alloc_pte(&init_mm, page_to_pfn(base)); ref_prot = pte_pgprot(pte_clrhuge(*kpte)); #ifdef CONFIG_X86_64 diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 72c0f6097402..ef8b64b89c7d 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/fs.h> +#include <linux/bootmem.h> #include <asm/msr.h> #include <asm/tlbflush.h> @@ -21,6 +22,7 @@ #include <asm/cacheflush.h> #include <asm/fcntl.h> #include <asm/mtrr.h> +#include <asm/io.h> int pat_wc_enabled = 1; @@ -190,6 +192,21 @@ static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot, return 0; } +/* + * req_type typically has one of the: + * - _PAGE_CACHE_WB + * - _PAGE_CACHE_WC + * - _PAGE_CACHE_UC_MINUS + * - _PAGE_CACHE_UC + * + * req_type will have a special case value '-1', when requester want to inherit + * the memory type from mtrr (if WB), existing PAT, defaulting to UC_MINUS. + * + * If ret_type is NULL, function will return an error if it cannot reserve the + * region with req_type. If ret_type is non-null, function will return + * available type in ret_type in case of no error. In case of any error + * it will return a negative return value. + */ int reserve_memtype(u64 start, u64 end, unsigned long req_type, unsigned long *ret_type) { @@ -200,9 +217,14 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, /* Only track when pat_wc_enabled */ if (!pat_wc_enabled) { - if (ret_type) - *ret_type = req_type; - + /* This is identical to page table setting without PAT */ + if (ret_type) { + if (req_type == -1) { + *ret_type = _PAGE_CACHE_WB; + } else { + *ret_type = req_type; + } + } return 0; } @@ -214,8 +236,29 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, return 0; } - req_type &= _PAGE_CACHE_MASK; - err = pat_x_mtrr_type(start, end, req_type, &actual_type); + if (req_type == -1) { + /* + * Special case where caller wants to inherit from mtrr or + * existing pat mapping, defaulting to UC_MINUS in case of + * no match. + */ + u8 mtrr_type = mtrr_type_lookup(start, end); + if (mtrr_type == 0xFE) { /* MTRR match error */ + err = -1; + } + + if (mtrr_type == MTRR_TYPE_WRBACK) { + req_type = _PAGE_CACHE_WB; + actual_type = _PAGE_CACHE_WB; + } else { + req_type = _PAGE_CACHE_UC_MINUS; + actual_type = _PAGE_CACHE_UC_MINUS; + } + } else { + req_type &= _PAGE_CACHE_MASK; + err = pat_x_mtrr_type(start, end, req_type, &actual_type); + } + if (err) { if (ret_type) *ret_type = actual_type; @@ -241,7 +284,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, struct memtype *saved_ptr; if (parse->start >= end) { - printk("New Entry\n"); + pr_debug("New Entry\n"); list_add(&new_entry->nd, parse->nd.prev); new_entry = NULL; break; @@ -343,7 +386,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, break; } - printk("Overlap at 0x%Lx-0x%Lx\n", + printk(KERN_INFO "Overlap at 0x%Lx-0x%Lx\n", saved_ptr->start, saved_ptr->end); /* No conflict. Go ahead and add this new entry */ list_add(&new_entry->nd, &saved_ptr->nd); @@ -353,7 +396,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, } if (err) { - printk( + printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, track %s, req %s\n", start, end, cattr_name(new_entry->type), cattr_name(req_type)); @@ -365,16 +408,16 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, if (new_entry) { /* No conflict. Not yet added to the list. Add to the tail */ list_add_tail(&new_entry->nd, &memtype_list); - printk("New Entry\n"); - } + pr_debug("New Entry\n"); + } if (ret_type) { - printk( + pr_debug( "reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n", start, end, cattr_name(actual_type), cattr_name(req_type), cattr_name(*ret_type)); } else { - printk( + pr_debug( "reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s\n", start, end, cattr_name(actual_type), cattr_name(req_type)); @@ -411,11 +454,115 @@ int free_memtype(u64 start, u64 end) spin_unlock(&memtype_lock); if (err) { - printk(KERN_DEBUG "%s:%d freeing invalid memtype %Lx-%Lx\n", + printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n", current->comm, current->pid, start, end); } - printk( "free_memtype request 0x%Lx-0x%Lx\n", start, end); + pr_debug("free_memtype request 0x%Lx-0x%Lx\n", start, end); return err; } + +/* + * /dev/mem mmap interface. The memtype used for mapping varies: + * - Use UC for mappings with O_SYNC flag + * - Without O_SYNC flag, if there is any conflict in reserve_memtype, + * inherit the memtype from existing mapping. + * - Else use UC_MINUS memtype (for backward compatibility with existing + * X drivers. + */ +pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot) +{ + return vma_prot; +} + +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot) +{ + u64 offset = ((u64) pfn) << PAGE_SHIFT; + unsigned long flags = _PAGE_CACHE_UC_MINUS; + unsigned long ret_flags; + int retval; + + if (file->f_flags & O_SYNC) { + flags = _PAGE_CACHE_UC; + } + +#ifdef CONFIG_X86_32 + /* + * On the PPro and successors, the MTRRs are used to set + * memory types for physical addresses outside main memory, + * so blindly setting UC or PWT on those pages is wrong. + * For Pentiums and earlier, the surround logic should disable + * caching for the high addresses through the KEN pin, but + * we maintain the tradition of paranoia in this code. + */ + if (!pat_wc_enabled && + ! ( test_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability) || + test_bit(X86_FEATURE_K6_MTRR, boot_cpu_data.x86_capability) || + test_bit(X86_FEATURE_CYRIX_ARR, boot_cpu_data.x86_capability) || + test_bit(X86_FEATURE_CENTAUR_MCR, boot_cpu_data.x86_capability)) && + (pfn << PAGE_SHIFT) >= __pa(high_memory)) { + flags = _PAGE_CACHE_UC; + } +#endif + + /* + * With O_SYNC, we can only take UC mapping. Fail if we cannot. + * Without O_SYNC, we want to get + * - WB for WB-able memory and no other conflicting mappings + * - UC_MINUS for non-WB-able memory with no other conflicting mappings + * - Inherit from confliting mappings otherwise + */ + if (flags != _PAGE_CACHE_UC_MINUS) { + retval = reserve_memtype(offset, offset + size, flags, NULL); + } else { + retval = reserve_memtype(offset, offset + size, -1, &ret_flags); + } + + if (retval < 0) + return 0; + + flags = ret_flags; + + if (pfn <= max_pfn_mapped && + ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) { + free_memtype(offset, offset + size); + printk(KERN_INFO + "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n", + current->comm, current->pid, + cattr_name(flags), + offset, offset + size); + return 0; + } + + *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | + flags); + return 1; +} + +void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) +{ + u64 addr = (u64)pfn << PAGE_SHIFT; + unsigned long flags; + unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK); + + reserve_memtype(addr, addr + size, want_flags, &flags); + if (flags != want_flags) { + printk(KERN_INFO + "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n", + current->comm, current->pid, + cattr_name(want_flags), + addr, addr + size, + cattr_name(flags)); + } +} + +void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) +{ + u64 addr = (u64)pfn << PAGE_SHIFT; + + free_memtype(addr, addr + size); +} + diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c new file mode 100644 index 000000000000..50159764f694 --- /dev/null +++ b/arch/x86/mm/pgtable.c @@ -0,0 +1,276 @@ +#include <linux/mm.h> +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/tlb.h> + +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; +} + +void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte) +{ + pgtable_page_dtor(pte); + paravirt_release_pte(page_to_pfn(pte)); + tlb_remove_page(tlb, pte); +} + +#if PAGETABLE_LEVELS > 2 +void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) +{ + paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); + tlb_remove_page(tlb, virt_to_page(pmd)); +} + +#if PAGETABLE_LEVELS > 3 +void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) +{ + paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); + tlb_remove_page(tlb, virt_to_page(pud)); +} +#endif /* PAGETABLE_LEVELS > 3 */ +#endif /* PAGETABLE_LEVELS > 2 */ + +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 ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD) + +static void pgd_ctor(void *p) +{ + pgd_t *pgd = p; + unsigned long flags; + + /* Clear usermode parts of PGD */ + memset(pgd, 0, KERNEL_PGD_BOUNDARY*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) || + PAGETABLE_LEVELS == 4) { + clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT, + __pa(swapper_pg_dir) >> PAGE_SHIFT, + KERNEL_PGD_BOUNDARY, + 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); +} + +/* + * 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 + */ + +#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_pmd(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 >= KERNEL_PGD_BOUNDARY) + memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), + sizeof(pmd_t) * PTRS_PER_PMD); + + pud_populate(mm, pud, pmd); + } + + return 1; +} + +void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) +{ + paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); + + /* Note: almost everything apart from _PAGE_PRESENT is + reserved at the pmd (PDPT) level. */ + set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); + + /* + * According to Intel App note "TLBs, Paging-Structure Caches, + * and Their Invalidation", April 2007, document 317080-001, + * section 8.1: in PAE mode we explicitly have to flush the + * TLB via cr3 if the top-level pgd is changed... + */ + if (mm == current->active_mm) + write_cr3(read_cr3()); +} +#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_pmd 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); +} + +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + int changed = !pte_same(*ptep, entry); + + if (changed && dirty) { + *ptep = entry; + pte_update_defer(vma->vm_mm, address, ptep); + flush_tlb_page(vma, address); + } + + return changed; +} + +int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + int ret = 0; + + if (pte_young(*ptep)) + ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, + &ptep->pte); + + if (ret) + pte_update(vma->vm_mm, addr, ptep); + + return ret; +} + +int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + int young; + + young = ptep_test_and_clear_young(vma, address, ptep); + if (young) + flush_tlb_page(vma, address); + + return young; +} diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 6fb9e7c6893f..9ee007be9142 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -173,210 +173,6 @@ void reserve_top_address(unsigned long reserve) __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); - 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)); |
