+/*
+ * It's worth taking a moment to describe how mmap is implemented
+ * for zfs because it differs considerably from other Linux filesystems.
+ * However, this issue is handled the same way under OpenSolaris.
+ *
+ * The issue is that by design zfs bypasses the Linux page cache and
+ * leaves all caching up to the ARC. This has been shown to work
+ * well for the common read(2)/write(2) case. However, mmap(2)
+ * is problem because it relies on being tightly integrated with the
+ * page cache. To handle this we cache mmap'ed files twice, once in
+ * the ARC and a second time in the page cache. The code is careful
+ * to keep both copies synchronized.
+ *
+ * When a file with an mmap'ed region is written to using write(2)
+ * both the data in the ARC and existing pages in the page cache
+ * are updated. For a read(2) data will be read first from the page
+ * cache then the ARC if needed. Neither a write(2) or read(2) will
+ * will ever result in new pages being added to the page cache.
+ *
+ * New pages are added to the page cache only via .readpage() which
+ * is called when the vfs needs to read a page off disk to back the
+ * virtual memory region. These pages may be modified without
+ * notifying the ARC and will be written out periodically via
+ * .writepage(). This will occur due to either a sync or the usual
+ * page aging behavior. Note because a read(2) of a mmap'ed file
+ * will always check the page cache first even when the ARC is out
+ * of date correct data will still be returned.
+ *
+ * While this implementation ensures correct behavior it does have
+ * have some drawbacks. The most obvious of which is that it
+ * increases the required memory footprint when access mmap'ed
+ * files. It also adds additional complexity to the code keeping
+ * both caches synchronized.
+ *
+ * Longer term it may be possible to cleanly resolve this wart by
+ * mapping page cache pages directly on to the ARC buffers. The
+ * Linux address space operations are flexible enough to allow
+ * selection of which pages back a particular index. The trick
+ * would be working out the details of which subsystem is in
+ * charge, the ARC, the page cache, or both. It may also prove
+ * helpful to move the ARC buffers to a scatter-gather lists
+ * rather than a vmalloc'ed region.
+ */
+static int
+zpl_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ struct inode *ip = filp->f_mapping->host;
+ znode_t *zp = ITOZ(ip);
+ int error;
+
+ error = -zfs_map(ip, vma->vm_pgoff, (caddr_t *)vma->vm_start,
+ (size_t)(vma->vm_end - vma->vm_start), vma->vm_flags);
+ if (error)
+ return (error);
+
+ error = generic_file_mmap(filp, vma);
+ if (error)
+ return (error);
+
+ mutex_enter(&zp->z_lock);
+ zp->z_is_mapped = 1;
+ mutex_exit(&zp->z_lock);
+
+ return (error);
+}
+
+/*
+ * Populate a page with data for the Linux page cache. This function is
+ * only used to support mmap(2). There will be an identical copy of the
+ * data in the ARC which is kept up to date via .write() and .writepage().
+ *
+ * Current this function relies on zpl_read_common() and the O_DIRECT
+ * flag to read in a page. This works but the more correct way is to
+ * update zfs_fillpage() to be Linux friendly and use that interface.
+ */
+static int
+zpl_readpage(struct file *filp, struct page *pp)
+{
+ struct inode *ip;
+ struct page *pl[1];
+ int error = 0;
+
+ ASSERT(PageLocked(pp));
+ ip = pp->mapping->host;
+ pl[0] = pp;
+
+ error = -zfs_getpage(ip, pl, 1);
+
+ if (error) {
+ SetPageError(pp);
+ ClearPageUptodate(pp);
+ } else {
+ ClearPageError(pp);
+ SetPageUptodate(pp);
+ flush_dcache_page(pp);
+ }
+
+ unlock_page(pp);
+ return error;
+}
+
+/*
+ * Populate a set of pages with data for the Linux page cache. This
+ * function will only be called for read ahead and never for demand
+ * paging. For simplicity, the code relies on read_cache_pages() to
+ * correctly lock each page for IO and call zpl_readpage().
+ */
+static int
+zpl_readpages(struct file *filp, struct address_space *mapping,
+ struct list_head *pages, unsigned nr_pages)
+{
+ return (read_cache_pages(mapping, pages,
+ (filler_t *)zpl_readpage, filp));
+}
+
+int
+zpl_putpage(struct page *pp, struct writeback_control *wbc, void *data)
+{
+ struct address_space *mapping = data;
+
+ ASSERT(PageLocked(pp));
+ ASSERT(!PageWriteback(pp));
+
+ /*
+ * Disable the normal reclaim path for zpl_putpage(). This
+ * ensures that all memory allocations under this call path
+ * will never enter direct reclaim. If this were to happen
+ * the VM might try to write out additional pages by calling
+ * zpl_putpage() again resulting in a deadlock.
+ */
+ current->flags |= PF_MEMALLOC;
+ (void) zfs_putpage(mapping->host, pp, wbc);
+ current->flags &= ~PF_MEMALLOC;
+
+ return (0);
+}
+
+static int
+zpl_writepages(struct address_space *mapping, struct writeback_control *wbc)
+{
+ return write_cache_pages(mapping, wbc, zpl_putpage, mapping);
+}
+
+/*
+ * Write out dirty pages to the ARC, this function is only required to
+ * support mmap(2). Mapped pages may be dirtied by memory operations
+ * which never call .write(). These dirty pages are kept in sync with
+ * the ARC buffers via this hook.
+ */
+static int
+zpl_writepage(struct page *pp, struct writeback_control *wbc)
+{
+ return zpl_putpage(pp, wbc, pp->mapping);
+}
+