dax: Remove i_mmap_lock protection

[sfrench/cifs-2.6.git] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index 098f00d0546170d6a969d4994b27cfab7a4955dc..06f552504e7977cb28ebfe9a5f3189fa0fc63e84 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -63,6 +63,7 @@
 #include <linux/dma-debug.h>
 #include <linux/debugfs.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/dax.h>
 
 #include <asm/io.h>
 #include <asm/mmu_context.h>
@@ -2054,7 +2055,7 @@ static inline int wp_page_reuse(struct mm_struct *mm,
                VM_BUG_ON_PAGE(PageAnon(page), page);
                mapping = page->mapping;
                unlock_page(page);
-               page_cache_release(page);
+               put_page(page);
 
                if ((dirtied || page_mkwrite) && mapping) {
                        /*
@@ -2188,7 +2189,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
        }
 
        if (new_page)
-               page_cache_release(new_page);
+               put_page(new_page);
 
        pte_unmap_unlock(page_table, ptl);
        mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
@@ -2203,14 +2204,14 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
                                munlock_vma_page(old_page);
                        unlock_page(old_page);
                }
-               page_cache_release(old_page);
+               put_page(old_page);
        }
        return page_copied ? VM_FAULT_WRITE : 0;
 oom_free_new:
-       page_cache_release(new_page);
+       put_page(new_page);
 oom:
        if (old_page)
-               page_cache_release(old_page);
+               put_page(old_page);
        return VM_FAULT_OOM;
 }
 
@@ -2258,7 +2259,7 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma,
 {
        int page_mkwrite = 0;
 
-       page_cache_get(old_page);
+       get_page(old_page);
 
        if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
                int tmp;
@@ -2267,7 +2268,7 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma,
                tmp = do_page_mkwrite(vma, old_page, address);
                if (unlikely(!tmp || (tmp &
                                      (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
-                       page_cache_release(old_page);
+                       put_page(old_page);
                        return tmp;
                }
                /*
@@ -2281,7 +2282,7 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma,
                if (!pte_same(*page_table, orig_pte)) {
                        unlock_page(old_page);
                        pte_unmap_unlock(page_table, ptl);
-                       page_cache_release(old_page);
+                       put_page(old_page);
                        return 0;
                }
                page_mkwrite = 1;
@@ -2341,7 +2342,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
         */
        if (PageAnon(old_page) && !PageKsm(old_page)) {
                if (!trylock_page(old_page)) {
-                       page_cache_get(old_page);
+                       get_page(old_page);
                        pte_unmap_unlock(page_table, ptl);
                        lock_page(old_page);
                        page_table = pte_offset_map_lock(mm, pmd, address,
@@ -2349,10 +2350,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                        if (!pte_same(*page_table, orig_pte)) {
                                unlock_page(old_page);
                                pte_unmap_unlock(page_table, ptl);
-                               page_cache_release(old_page);
+                               put_page(old_page);
                                return 0;
                        }
-                       page_cache_release(old_page);
+                       put_page(old_page);
                }
                if (reuse_swap_page(old_page)) {
                        /*
@@ -2375,7 +2376,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
        /*
         * Ok, we need to copy. Oh, well..
         */
-       page_cache_get(old_page);
+       get_page(old_page);
 
        pte_unmap_unlock(page_table, ptl);
        return wp_page_copy(mm, vma, address, page_table, pmd,
@@ -2400,7 +2401,6 @@ static inline void unmap_mapping_range_tree(struct rb_root *root,
 
                vba = vma->vm_pgoff;
                vea = vba + vma_pages(vma) - 1;
-               /* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
                zba = details->first_index;
                if (zba < vba)
                        zba = vba;
@@ -2453,8 +2453,6 @@ void unmap_mapping_range(struct address_space *mapping,
        if (details.last_index < details.first_index)
                details.last_index = ULONG_MAX;
 
-
-       /* DAX uses i_mmap_lock to serialise file truncate vs page fault */
        i_mmap_lock_write(mapping);
        if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
                unmap_mapping_range_tree(&mapping->i_mmap, &details);
@@ -2619,7 +2617,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 * parallel locked swapcache.
                 */
                unlock_page(swapcache);
-               page_cache_release(swapcache);
+               put_page(swapcache);
        }
 
        if (flags & FAULT_FLAG_WRITE) {
@@ -2641,10 +2639,10 @@ out_nomap:
 out_page:
        unlock_page(page);
 out_release:
-       page_cache_release(page);
+       put_page(page);
        if (page != swapcache) {
                unlock_page(swapcache);
-               page_cache_release(swapcache);
+               put_page(swapcache);
        }
        return ret;
 }
@@ -2752,7 +2750,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
        if (userfaultfd_missing(vma)) {
                pte_unmap_unlock(page_table, ptl);
                mem_cgroup_cancel_charge(page, memcg, false);
-               page_cache_release(page);
+               put_page(page);
                return handle_userfault(vma, address, flags,
                                        VM_UFFD_MISSING);
        }
@@ -2771,10 +2769,10 @@ unlock:
        return 0;
 release:
        mem_cgroup_cancel_charge(page, memcg, false);
-       page_cache_release(page);
+       put_page(page);
        goto unlock;
 oom_free_page:
-       page_cache_release(page);
+       put_page(page);
 oom:
        return VM_FAULT_OOM;
 }
@@ -2786,7 +2784,8 @@ oom:
  */
 static int __do_fault(struct vm_area_struct *vma, unsigned long address,
                        pgoff_t pgoff, unsigned int flags,
-                       struct page *cow_page, struct page **page)
+                       struct page *cow_page, struct page **page,
+                       void **entry)
 {
        struct vm_fault vmf;
        int ret;
@@ -2801,13 +2800,15 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
        ret = vma->vm_ops->fault(vma, &vmf);
        if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
                return ret;
-       if (!vmf.page)
-               goto out;
+       if (ret & VM_FAULT_DAX_LOCKED) {
+               *entry = vmf.entry;
+               return ret;
+       }
 
        if (unlikely(PageHWPoison(vmf.page))) {
                if (ret & VM_FAULT_LOCKED)
                        unlock_page(vmf.page);
-               page_cache_release(vmf.page);
+               put_page(vmf.page);
                return VM_FAULT_HWPOISON;
        }
 
@@ -2816,7 +2817,6 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
        else
                VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page);
 
- out:
        *page = vmf.page;
        return ret;
 }
@@ -2988,7 +2988,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                pte_unmap_unlock(pte, ptl);
        }
 
-       ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
+       ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page, NULL);
        if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
                return ret;
 
@@ -2996,7 +2996,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
        if (unlikely(!pte_same(*pte, orig_pte))) {
                pte_unmap_unlock(pte, ptl);
                unlock_page(fault_page);
-               page_cache_release(fault_page);
+               put_page(fault_page);
                return ret;
        }
        do_set_pte(vma, address, fault_page, pte, false, false);
@@ -3011,6 +3011,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
 {
        struct page *fault_page, *new_page;
+       void *fault_entry;
        struct mem_cgroup *memcg;
        spinlock_t *ptl;
        pte_t *pte;
@@ -3024,30 +3025,28 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                return VM_FAULT_OOM;
 
        if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) {
-               page_cache_release(new_page);
+               put_page(new_page);
                return VM_FAULT_OOM;
        }
 
-       ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page);
+       ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page,
+                        &fault_entry);
        if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
                goto uncharge_out;
 
-       if (fault_page)
+       if (!(ret & VM_FAULT_DAX_LOCKED))
                copy_user_highpage(new_page, fault_page, address, vma);
        __SetPageUptodate(new_page);
 
        pte = pte_offset_map_lock(mm, pmd, address, &ptl);
        if (unlikely(!pte_same(*pte, orig_pte))) {
                pte_unmap_unlock(pte, ptl);
-               if (fault_page) {
+               if (!(ret & VM_FAULT_DAX_LOCKED)) {
                        unlock_page(fault_page);
-                       page_cache_release(fault_page);
+                       put_page(fault_page);
                } else {
-                       /*
-                        * The fault handler has no page to lock, so it holds
-                        * i_mmap_lock for read to protect against truncate.
-                        */
-                       i_mmap_unlock_read(vma->vm_file->f_mapping);
+                       dax_unlock_mapping_entry(vma->vm_file->f_mapping,
+                                                pgoff);
                }
                goto uncharge_out;
        }
@@ -3055,20 +3054,16 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
        mem_cgroup_commit_charge(new_page, memcg, false, false);
        lru_cache_add_active_or_unevictable(new_page, vma);
        pte_unmap_unlock(pte, ptl);
-       if (fault_page) {
+       if (!(ret & VM_FAULT_DAX_LOCKED)) {
                unlock_page(fault_page);
-               page_cache_release(fault_page);
+               put_page(fault_page);
        } else {
-               /*
-                * The fault handler has no page to lock, so it holds
-                * i_mmap_lock for read to protect against truncate.
-                */
-               i_mmap_unlock_read(vma->vm_file->f_mapping);
+               dax_unlock_mapping_entry(vma->vm_file->f_mapping, pgoff);
        }
        return ret;
 uncharge_out:
        mem_cgroup_cancel_charge(new_page, memcg, false);
-       page_cache_release(new_page);
+       put_page(new_page);
        return ret;
 }
 
@@ -3083,7 +3078,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
        int dirtied = 0;
        int ret, tmp;
 
-       ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
+       ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page, NULL);
        if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
                return ret;
 
@@ -3096,7 +3091,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                tmp = do_page_mkwrite(vma, fault_page, address);
                if (unlikely(!tmp ||
                                (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
-                       page_cache_release(fault_page);
+                       put_page(fault_page);
                        return tmp;
                }
        }
@@ -3105,7 +3100,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
        if (unlikely(!pte_same(*pte, orig_pte))) {
                pte_unmap_unlock(pte, ptl);
                unlock_page(fault_page);
-               page_cache_release(fault_page);
+               put_page(fault_page);
                return ret;
        }
        do_set_pte(vma, address, fault_page, pte, true, false);
@@ -3736,7 +3731,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
                                                    buf, maddr + offset, bytes);
                        }
                        kunmap(page);
-                       page_cache_release(page);
+                       put_page(page);
                }
                len -= bytes;
                buf += bytes;