X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=mm%2Fmemory.c;h=19e0ae9beecb71062f4a8030f6ab8df14bfa9d51;hb=8aca6cb1179ed9bef9351028c8d8af852903eae2;hp=153a54b2013ca9927edf1dda4e047a82a952c05e;hpb=37969581301e50872a1ae84dc73962b5f7ee6b76;p=linux-2.6-omap-h63xx.git diff --git a/mm/memory.c b/mm/memory.c index 153a54b2013..19e0ae9beec 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -134,11 +134,9 @@ void pmd_clear_bad(pmd_t *pmd) */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd) { - struct page *page = pmd_page(*pmd); + pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); - pte_lock_deinit(page); - pte_free_tlb(tlb, page); - dec_zone_page_state(page, NR_PAGETABLE); + pte_free_tlb(tlb, token); tlb->mm->nr_ptes--; } @@ -309,21 +307,34 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { - struct page *new = pte_alloc_one(mm, address); + pgtable_t new = pte_alloc_one(mm, address); if (!new) return -ENOMEM; - pte_lock_init(new); + /* + * Ensure all pte setup (eg. pte page lock and page clearing) are + * visible before the pte is made visible to other CPUs by being + * put into page tables. + * + * The other side of the story is the pointer chasing in the page + * table walking code (when walking the page table without locking; + * ie. most of the time). Fortunately, these data accesses consist + * of a chain of data-dependent loads, meaning most CPUs (alpha + * being the notable exception) will already guarantee loads are + * seen in-order. See the alpha page table accessors for the + * smp_read_barrier_depends() barriers in page table walking code. + */ + smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ + spin_lock(&mm->page_table_lock); - if (pmd_present(*pmd)) { /* Another has populated it */ - pte_lock_deinit(new); - pte_free(mm, new); - } else { + if (!pmd_present(*pmd)) { /* Has another populated it ? */ mm->nr_ptes++; - inc_zone_page_state(new, NR_PAGETABLE); pmd_populate(mm, pmd, new); + new = NULL; } spin_unlock(&mm->page_table_lock); + if (new) + pte_free(mm, new); return 0; } @@ -333,12 +344,16 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) if (!new) return -ENOMEM; + smp_wmb(); /* See comment in __pte_alloc */ + spin_lock(&init_mm.page_table_lock); - if (pmd_present(*pmd)) /* Another has populated it */ - pte_free_kernel(&init_mm, new); - else + if (!pmd_present(*pmd)) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); + new = NULL; + } spin_unlock(&init_mm.page_table_lock); + if (new) + pte_free_kernel(&init_mm, new); return 0; } @@ -373,57 +388,93 @@ static inline int is_cow_mapping(unsigned int flags) } /* - * This function gets the "struct page" associated with a pte. + * vm_normal_page -- This function gets the "struct page" associated with a pte. + * + * "Special" mappings do not wish to be associated with a "struct page" (either + * it doesn't exist, or it exists but they don't want to touch it). In this + * case, NULL is returned here. "Normal" mappings do have a struct page. * - * NOTE! Some mappings do not have "struct pages". A raw PFN mapping - * will have each page table entry just pointing to a raw page frame - * number, and as far as the VM layer is concerned, those do not have - * pages associated with them - even if the PFN might point to memory - * that otherwise is perfectly fine and has a "struct page". + * There are 2 broad cases. Firstly, an architecture may define a pte_special() + * pte bit, in which case this function is trivial. Secondly, an architecture + * may not have a spare pte bit, which requires a more complicated scheme, + * described below. * - * The way we recognize those mappings is through the rules set up - * by "remap_pfn_range()": the vma will have the VM_PFNMAP bit set, - * and the vm_pgoff will point to the first PFN mapped: thus every - * page that is a raw mapping will always honor the rule + * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a + * special mapping (even if there are underlying and valid "struct pages"). + * COWed pages of a VM_PFNMAP are always normal. + * + * The way we recognize COWed pages within VM_PFNMAP mappings is through the + * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit + * set, and the vm_pgoff will point to the first PFN mapped: thus every special + * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * - * and if that isn't true, the page has been COW'ed (in which case it - * _does_ have a "struct page" associated with it even if it is in a - * VM_PFNMAP range). + * And for normal mappings this is false. + * + * This restricts such mappings to be a linear translation from virtual address + * to pfn. To get around this restriction, we allow arbitrary mappings so long + * as the vma is not a COW mapping; in that case, we know that all ptes are + * special (because none can have been COWed). + * + * + * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. + * + * VM_MIXEDMAP mappings can likewise contain memory with or without "struct + * page" backing, however the difference is that _all_ pages with a struct + * page (that is, those where pfn_valid is true) are refcounted and considered + * normal pages by the VM. The disadvantage is that pages are refcounted + * (which can be slower and simply not an option for some PFNMAP users). The + * advantage is that we don't have to follow the strict linearity rule of + * PFNMAP mappings in order to support COWable mappings. + * */ -struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) +#ifdef __HAVE_ARCH_PTE_SPECIAL +# define HAVE_PTE_SPECIAL 1 +#else +# define HAVE_PTE_SPECIAL 0 +#endif +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte) { - unsigned long pfn = pte_pfn(pte); + unsigned long pfn; - if (unlikely(vma->vm_flags & VM_PFNMAP)) { - unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT; - if (pfn == vma->vm_pgoff + off) - return NULL; - if (!is_cow_mapping(vma->vm_flags)) - return NULL; + if (HAVE_PTE_SPECIAL) { + if (likely(!pte_special(pte))) { + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + return pte_page(pte); + } + VM_BUG_ON(!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))); + return NULL; } -#ifdef CONFIG_DEBUG_VM - /* - * Add some anal sanity checks for now. Eventually, - * we should just do "return pfn_to_page(pfn)", but - * in the meantime we check that we get a valid pfn, - * and that the resulting page looks ok. - */ - if (unlikely(!pfn_valid(pfn))) { - print_bad_pte(vma, pte, addr); - return NULL; + /* !HAVE_PTE_SPECIAL case follows: */ + + pfn = pte_pfn(pte); + + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } } -#endif + + VM_BUG_ON(!pfn_valid(pfn)); /* - * NOTE! We still have PageReserved() pages in the page - * tables. + * NOTE! We still have PageReserved() pages in the page tables. * - * The PAGE_ZERO() pages and various VDSO mappings can - * cause them to exist. + * eg. VDSO mappings can cause them to exist. */ +out: return pfn_to_page(pfn); } @@ -935,7 +986,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, goto no_page_table; pmd = pmd_offset(pud, address); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + if (pmd_none(*pmd)) goto no_page_table; if (pmd_huge(*pmd)) { @@ -944,6 +995,9 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, goto out; } + if (unlikely(pmd_bad(*pmd))) + goto no_page_table; + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) goto out; @@ -991,6 +1045,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, int i; unsigned int vm_flags; + if (len <= 0) + return 0; /* * Require read or write permissions. * If 'force' is set, we only require the "MAY" flags. @@ -1057,8 +1113,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (pages) foll_flags |= FOLL_GET; if (!write && !(vma->vm_flags & VM_LOCKED) && - (!vma->vm_ops || (!vma->vm_ops->nopage && - !vma->vm_ops->fault))) + (!vma->vm_ops || !vma->vm_ops->fault)) foll_flags |= FOLL_ANON; do { @@ -1141,8 +1196,10 @@ pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, * old drivers should use this, and they needed to mark their * pages reserved for the old functions anyway. */ -static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *page, pgprot_t prot) +static int insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page, pgprot_t prot) { + struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte; spinlock_t *ptl; @@ -1202,40 +1259,26 @@ out: * * The page does not need to be reserved. */ -int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) +int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!page_count(page)) return -EINVAL; vma->vm_flags |= VM_INSERTPAGE; - return insert_page(vma->vm_mm, addr, page, vma->vm_page_prot); + return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); -/** - * vm_insert_pfn - insert single pfn into user vma - * @vma: user vma to map to - * @addr: target user address of this page - * @pfn: source kernel pfn - * - * Similar to vm_inert_page, this allows drivers to insert individual pages - * they've allocated into a user vma. Same comments apply. - * - * This function should only be called from a vm_ops->fault handler, and - * in that case the handler should return NULL. - */ -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn) +static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte, entry; spinlock_t *ptl; - BUG_ON(!(vma->vm_flags & VM_PFNMAP)); - BUG_ON(is_cow_mapping(vma->vm_flags)); - retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) @@ -1245,19 +1288,74 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, goto out_unlock; /* Ok, finally just insert the thing.. */ - entry = pfn_pte(pfn, vma->vm_page_prot); + entry = pte_mkspecial(pfn_pte(pfn, prot)); set_pte_at(mm, addr, pte, entry); - update_mmu_cache(vma, addr, entry); + update_mmu_cache(vma, addr, entry); /* XXX: why not for insert_page? */ retval = 0; out_unlock: pte_unmap_unlock(pte, ptl); - out: return retval; } + +/** + * vm_insert_pfn - insert single pfn into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * + * Similar to vm_inert_page, this allows drivers to insert individual pages + * they've allocated into a user vma. Same comments apply. + * + * This function should only be called from a vm_ops->fault handler, and + * in that case the handler should return NULL. + */ +int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + /* + * Technically, architectures with pte_special can avoid all these + * restrictions (same for remap_pfn_range). However we would like + * consistency in testing and feature parity among all, so we should + * try to keep these invariants in place for everybody. + */ + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + return insert_pfn(vma, addr, pfn, vma->vm_page_prot); +} EXPORT_SYMBOL(vm_insert_pfn); +int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + BUG_ON(!(vma->vm_flags & VM_MIXEDMAP)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + + /* + * If we don't have pte special, then we have to use the pfn_valid() + * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* + * refcount the page if pfn_valid is true (hence insert_page rather + * than insert_pfn). + */ + if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) { + struct page *page; + + page = pfn_to_page(pfn); + return insert_page(vma, addr, page, vma->vm_page_prot); + } + return insert_pfn(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_mixed); + /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results @@ -1276,7 +1374,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); - set_pte_at(mm, addr, pte, pfn_pte(pfn, prot)); + set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); @@ -1390,7 +1488,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, { pte_t *pte; int err; - struct page *pmd_page; + pgtable_t token; spinlock_t *uninitialized_var(ptl); pte = (mm == &init_mm) ? @@ -1401,10 +1499,10 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, BUG_ON(pmd_huge(*pmd)); - pmd_page = pmd_page(*pmd); + token = pmd_pgtable(*pmd); do { - err = fn(pte, pmd_page, addr, data); + err = fn(pte, token, addr, data); if (err) break; } while (pte++, addr += PAGE_SIZE, addr != end); @@ -1711,7 +1809,7 @@ unlock: } return ret; oom_free_new: - __free_page(new_page); + page_cache_release(new_page); oom: if (old_page) page_cache_release(old_page); @@ -2093,12 +2191,9 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unlock_page(page); if (write_access) { - /* XXX: We could OR the do_wp_page code with this one? */ - if (do_wp_page(mm, vma, address, - page_table, pmd, ptl, pte) & VM_FAULT_OOM) { - mem_cgroup_uncharge_page(page); - ret = VM_FAULT_OOM; - } + ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte); + if (ret & VM_FAULT_ERROR) + ret &= VM_FAULT_ERROR; goto out; } @@ -2163,7 +2258,7 @@ release: page_cache_release(page); goto unlock; oom_free_page: - __free_page(page); + page_cache_release(page); oom: return VM_FAULT_OOM; } @@ -2200,22 +2295,9 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, vmf.flags = flags; vmf.page = NULL; - BUG_ON(vma->vm_flags & VM_PFNMAP); - - if (likely(vma->vm_ops->fault)) { - ret = vma->vm_ops->fault(vma, &vmf); - if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) - return ret; - } else { - /* Legacy ->nopage path */ - ret = 0; - vmf.page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret); - /* no page was available -- either SIGBUS or OOM */ - if (unlikely(vmf.page == NOPAGE_SIGBUS)) - return VM_FAULT_SIGBUS; - else if (unlikely(vmf.page == NOPAGE_OOM)) - return VM_FAULT_OOM; - } + ret = vma->vm_ops->fault(vma, &vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) + return ret; /* * For consistency in subsequent calls, make the faulted page always @@ -2380,10 +2462,13 @@ static noinline int do_no_pfn(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long pfn; pte_unmap(page_table); - BUG_ON(!(vma->vm_flags & VM_PFNMAP)); - BUG_ON(is_cow_mapping(vma->vm_flags)); + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); pfn = vma->vm_ops->nopfn(vma, address & PAGE_MASK); + + BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); + if (unlikely(pfn == NOPFN_OOM)) return VM_FAULT_OOM; else if (unlikely(pfn == NOPFN_SIGBUS)) @@ -2461,7 +2546,7 @@ static inline int handle_pte_fault(struct mm_struct *mm, if (!pte_present(entry)) { if (pte_none(entry)) { if (vma->vm_ops) { - if (vma->vm_ops->fault || vma->vm_ops->nopage) + if (likely(vma->vm_ops->fault)) return do_linear_fault(mm, vma, address, pte, pmd, write_access, entry); if (unlikely(vma->vm_ops->nopfn)) @@ -2549,6 +2634,8 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) if (!new) return -ENOMEM; + smp_wmb(); /* See comment in __pte_alloc */ + spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) /* Another has populated it */ pud_free(mm, new); @@ -2570,6 +2657,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) if (!new) return -ENOMEM; + smp_wmb(); /* See comment in __pte_alloc */ + spin_lock(&mm->page_table_lock); #ifndef __ARCH_HAS_4LEVEL_HACK if (pud_present(*pud)) /* Another has populated it */ @@ -2711,6 +2800,13 @@ void print_vma_addr(char *prefix, unsigned long ip) struct mm_struct *mm = current->mm; struct vm_area_struct *vma; + /* + * Do not print if we are in atomic + * contexts (in exception stacks, etc.): + */ + if (preempt_count()) + return; + down_read(&mm->mmap_sem); vma = find_vma(mm, ip); if (vma && vma->vm_file) { @@ -2719,7 +2815,7 @@ void print_vma_addr(char *prefix, unsigned long ip) if (buf) { char *p, *s; - p = d_path(f->f_dentry, f->f_vfsmnt, buf, PAGE_SIZE); + p = d_path(&f->f_path, buf, PAGE_SIZE); if (IS_ERR(p)) p = "?"; s = strrchr(p, '/');