diff options
Diffstat (limited to 'fs/ceph/addr.c')
-rw-r--r-- | fs/ceph/addr.c | 289 |
1 files changed, 157 insertions, 132 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8b67304e4b80..5318a3b704f6 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -143,7 +143,8 @@ static int ceph_set_page_dirty(struct page *page) * dirty page counters appropriately. Only called if there is private * data on the page. */ -static void ceph_invalidatepage(struct page *page, unsigned long offset) +static void ceph_invalidatepage(struct page *page, unsigned int offset, + unsigned int length) { struct inode *inode; struct ceph_inode_info *ci; @@ -163,20 +164,20 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset) if (!PageDirty(page)) pr_err("%p invalidatepage %p page not dirty\n", inode, page); - if (offset == 0) + if (offset == 0 && length == PAGE_CACHE_SIZE) ClearPageChecked(page); ci = ceph_inode(inode); - if (offset == 0) { - dout("%p invalidatepage %p idx %lu full dirty page %lu\n", - inode, page, page->index, offset); + if (offset == 0 && length == PAGE_CACHE_SIZE) { + dout("%p invalidatepage %p idx %lu full dirty page\n", + inode, page, page->index); ceph_put_wrbuffer_cap_refs(ci, 1, snapc); ceph_put_snap_context(snapc); page->private = 0; ClearPagePrivate(page); } else { - dout("%p invalidatepage %p idx %lu partial dirty page\n", - inode, page, page->index); + dout("%p invalidatepage %p idx %lu partial dirty page %u(%u)\n", + inode, page, page->index, offset, length); } } @@ -195,7 +196,7 @@ static int ceph_releasepage(struct page *page, gfp_t g) */ static int readpage_nounlock(struct file *filp, struct page *page) { - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->client->osdc; @@ -205,7 +206,7 @@ static int readpage_nounlock(struct file *filp, struct page *page) dout("readpage inode %p file %p page %p index %lu\n", inode, filp, page, page->index); err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout, - page->index << PAGE_CACHE_SHIFT, &len, + (u64) page_offset(page), &len, ci->i_truncate_seq, ci->i_truncate_size, &page, 1, 0); if (err == -ENOENT) @@ -236,21 +237,21 @@ static int ceph_readpage(struct file *filp, struct page *page) static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg) { struct inode *inode = req->r_inode; - struct ceph_osd_reply_head *replyhead; - int rc, bytes; + struct ceph_osd_data *osd_data; + int rc = req->r_result; + int bytes = le32_to_cpu(msg->hdr.data_len); + int num_pages; int i; - /* parse reply */ - replyhead = msg->front.iov_base; - WARN_ON(le32_to_cpu(replyhead->num_ops) == 0); - rc = le32_to_cpu(replyhead->result); - bytes = le32_to_cpu(msg->hdr.data_len); - dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes); /* unlock all pages, zeroing any data we didn't read */ - for (i = 0; i < req->r_num_pages; i++, bytes -= PAGE_CACHE_SIZE) { - struct page *page = req->r_pages[i]; + osd_data = osd_req_op_extent_osd_data(req, 0); + BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES); + num_pages = calc_pages_for((u64)osd_data->alignment, + (u64)osd_data->length); + for (i = 0; i < num_pages; i++) { + struct page *page = osd_data->pages[i]; if (bytes < (int)PAGE_CACHE_SIZE) { /* zero (remainder of) page */ @@ -263,8 +264,17 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg) SetPageUptodate(page); unlock_page(page); page_cache_release(page); + bytes -= PAGE_CACHE_SIZE; } - kfree(req->r_pages); + kfree(osd_data->pages); +} + +static void ceph_unlock_page_vector(struct page **pages, int num_pages) +{ + int i; + + for (i = 0; i < num_pages; i++) + unlock_page(pages[i]); } /* @@ -277,6 +287,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) &ceph_inode_to_client(inode)->client->osdc; struct ceph_inode_info *ci = ceph_inode(inode); struct page *page = list_entry(page_list->prev, struct page, lru); + struct ceph_vino vino; struct ceph_osd_request *req; u64 off; u64 len; @@ -286,7 +297,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) int nr_pages = 0; int ret; - off = page->index << PAGE_CACHE_SHIFT; + off = (u64) page_offset(page); /* count pages */ next_index = page->index; @@ -301,18 +312,17 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) len = nr_pages << PAGE_CACHE_SHIFT; dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages, off, len); - - req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), - off, &len, - CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, - NULL, 0, + vino = ceph_vino(inode); + req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len, + 1, CEPH_OSD_OP_READ, + CEPH_OSD_FLAG_READ, NULL, ci->i_truncate_seq, ci->i_truncate_size, - NULL, false, 1, 0); - if (!req) - return -ENOMEM; + false); + if (IS_ERR(req)) + return PTR_ERR(req); /* build page vector */ - nr_pages = len >> PAGE_CACHE_SHIFT; + nr_pages = calc_pages_for(0, len); pages = kmalloc(sizeof(*pages) * nr_pages, GFP_NOFS); ret = -ENOMEM; if (!pages) @@ -334,11 +344,12 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) } pages[i] = page; } - req->r_pages = pages; - req->r_num_pages = nr_pages; + osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false); req->r_callback = finish_read; req->r_inode = inode; + ceph_osdc_build_request(req, off, NULL, vino.snap, NULL); + dout("start_read %p starting %p %lld~%lld\n", inode, req, off, len); ret = ceph_osdc_start_request(osdc, req, false); if (ret < 0) @@ -347,6 +358,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) return nr_pages; out_pages: + ceph_unlock_page_vector(pages, nr_pages); ceph_release_page_vector(pages, nr_pages); out: ceph_osdc_put_request(req); @@ -361,7 +373,7 @@ out: static int ceph_readpages(struct file *file, struct address_space *mapping, struct list_head *page_list, unsigned nr_pages) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); int rc = 0; int max = 0; @@ -370,7 +382,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_SHIFT; - dout("readpages %p file %p nr_pages %d max %d\n", inode, file, nr_pages, + dout("readpages %p file %p nr_pages %d max %d\n", inode, + file, nr_pages, max); while (!list_empty(page_list)) { rc = start_read(inode, page_list, max); @@ -426,13 +439,12 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) struct ceph_inode_info *ci; struct ceph_fs_client *fsc; struct ceph_osd_client *osdc; - loff_t page_off = page->index << PAGE_CACHE_SHIFT; - int len = PAGE_CACHE_SIZE; - loff_t i_size; - int err = 0; struct ceph_snap_context *snapc, *oldest; - u64 snap_size = 0; + loff_t page_off = page_offset(page); long writeback_stat; + u64 truncate_size, snap_size = 0; + u32 truncate_seq; + int err = 0, len = PAGE_CACHE_SIZE; dout("writepage %p idx %lu\n", page, page->index); @@ -462,13 +474,20 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) } ceph_put_snap_context(oldest); + spin_lock(&ci->i_ceph_lock); + truncate_seq = ci->i_truncate_seq; + truncate_size = ci->i_truncate_size; + if (!snap_size) + snap_size = i_size_read(inode); + spin_unlock(&ci->i_ceph_lock); + /* is this a partial page at end of file? */ - if (snap_size) - i_size = snap_size; - else - i_size = i_size_read(inode); - if (i_size < page_off + len) - len = i_size - page_off; + if (page_off >= snap_size) { + dout("%p page eof %llu\n", page, snap_size); + goto out; + } + if (snap_size < page_off + len) + len = snap_size - page_off; dout("writepage %p page %p index %lu on %llu~%u snapc %p\n", inode, page, page->index, page_off, len, snapc); @@ -482,9 +501,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) err = ceph_osdc_writepages(osdc, ceph_vino(inode), &ci->i_layout, snapc, page_off, len, - ci->i_truncate_seq, ci->i_truncate_size, - &inode->i_mtime, - &page, 1, 0, 0, true); + truncate_seq, truncate_size, + &inode->i_mtime, &page, 1); if (err < 0) { dout("writepage setting page/mapping error %d %p\n", err, page); SetPageError(page); @@ -545,27 +563,24 @@ static void writepages_finish(struct ceph_osd_request *req, struct ceph_msg *msg) { struct inode *inode = req->r_inode; - struct ceph_osd_reply_head *replyhead; - struct ceph_osd_op *op; struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_osd_data *osd_data; unsigned wrote; struct page *page; + int num_pages; int i; struct ceph_snap_context *snapc = req->r_snapc; struct address_space *mapping = inode->i_mapping; - __s32 rc = -EIO; - u64 bytes = 0; + int rc = req->r_result; + u64 bytes = req->r_ops[0].extent.length; struct ceph_fs_client *fsc = ceph_inode_to_client(inode); long writeback_stat; unsigned issued = ceph_caps_issued(ci); - /* parse reply */ - replyhead = msg->front.iov_base; - WARN_ON(le32_to_cpu(replyhead->num_ops) == 0); - op = (void *)(replyhead + 1); - rc = le32_to_cpu(replyhead->result); - bytes = le64_to_cpu(op->extent.length); - + osd_data = osd_req_op_extent_osd_data(req, 0); + BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES); + num_pages = calc_pages_for((u64)osd_data->alignment, + (u64)osd_data->length); if (rc >= 0) { /* * Assume we wrote the pages we originally sent. The @@ -573,7 +588,7 @@ static void writepages_finish(struct ceph_osd_request *req, * raced with a truncation and was adjusted at the osd, * so don't believe the reply. */ - wrote = req->r_num_pages; + wrote = num_pages; } else { wrote = 0; mapping_set_error(mapping, rc); @@ -582,8 +597,8 @@ static void writepages_finish(struct ceph_osd_request *req, inode, rc, bytes, wrote); /* clean all pages */ - for (i = 0; i < req->r_num_pages; i++) { - page = req->r_pages[i]; + for (i = 0; i < num_pages; i++) { + page = osd_data->pages[i]; BUG_ON(!page); WARN_ON(!PageUptodate(page)); @@ -612,35 +627,18 @@ static void writepages_finish(struct ceph_osd_request *req, unlock_page(page); } dout("%p wrote+cleaned %d pages\n", inode, wrote); - ceph_put_wrbuffer_cap_refs(ci, req->r_num_pages, snapc); + ceph_put_wrbuffer_cap_refs(ci, num_pages, snapc); - ceph_release_pages(req->r_pages, req->r_num_pages); - if (req->r_pages_from_pool) - mempool_free(req->r_pages, + ceph_release_pages(osd_data->pages, num_pages); + if (osd_data->pages_from_pool) + mempool_free(osd_data->pages, ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool); else - kfree(req->r_pages); + kfree(osd_data->pages); ceph_osdc_put_request(req); } /* - * allocate a page vec, either directly, or if necessary, via a the - * mempool. we avoid the mempool if we can because req->r_num_pages - * may be less than the maximum write size. - */ -static void alloc_page_vec(struct ceph_fs_client *fsc, - struct ceph_osd_request *req) -{ - req->r_pages = kmalloc(sizeof(struct page *) * req->r_num_pages, - GFP_NOFS); - if (!req->r_pages) { - req->r_pages = mempool_alloc(fsc->wb_pagevec_pool, GFP_NOFS); - req->r_pages_from_pool = 1; - WARN_ON(!req->r_pages); - } -} - -/* * initiate async writeback */ static int ceph_writepages_start(struct address_space *mapping, @@ -648,7 +646,8 @@ static int ceph_writepages_start(struct address_space *mapping, { struct inode *inode = mapping->host; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_fs_client *fsc; + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_vino vino = ceph_vino(inode); pgoff_t index, start, end; int range_whole = 0; int should_loop = 1; @@ -660,22 +659,22 @@ static int ceph_writepages_start(struct address_space *mapping, unsigned wsize = 1 << inode->i_blkbits; struct ceph_osd_request *req = NULL; int do_sync; - u64 snap_size = 0; + u64 truncate_size, snap_size; + u32 truncate_seq; /* * Include a 'sync' in the OSD request if this is a data * integrity write (e.g., O_SYNC write or fsync()), or if our * cap is being revoked. */ - do_sync = wbc->sync_mode == WB_SYNC_ALL; - if (ceph_caps_revoking(ci, CEPH_CAP_FILE_BUFFER)) + if ((wbc->sync_mode == WB_SYNC_ALL) || + ceph_caps_revoking(ci, CEPH_CAP_FILE_BUFFER)) do_sync = 1; dout("writepages_start %p dosync=%d (mode=%s)\n", inode, do_sync, wbc->sync_mode == WB_SYNC_NONE ? "NONE" : (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD")); - fsc = ceph_inode_to_client(inode); if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) { pr_warning("writepage_start %p on forced umount\n", inode); return -EIO; /* we're in a forced umount, don't write! */ @@ -706,6 +705,7 @@ static int ceph_writepages_start(struct address_space *mapping, retry: /* find oldest snap context with dirty data */ ceph_put_snap_context(snapc); + snap_size = 0; snapc = get_oldest_context(inode, &snap_size); if (!snapc) { /* hmm, why does writepages get called when there @@ -713,8 +713,18 @@ retry: dout(" no snap context with dirty data?\n"); goto out; } + if (snap_size == 0) + snap_size = i_size_read(inode); dout(" oldest snapc is %p seq %lld (%d snaps)\n", snapc, snapc->seq, snapc->num_snaps); + + spin_lock(&ci->i_ceph_lock); + truncate_seq = ci->i_truncate_seq; + truncate_size = ci->i_truncate_size; + if (!snap_size) + snap_size = i_size_read(inode); + spin_unlock(&ci->i_ceph_lock); + if (last_snapc && snapc != last_snapc) { /* if we switched to a newer snapc, restart our scan at the * start of the original file range. */ @@ -725,15 +735,16 @@ retry: last_snapc = snapc; while (!done && index <= end) { + int num_ops = do_sync ? 2 : 1; unsigned i; int first; pgoff_t next; int pvec_pages, locked_pages; + struct page **pages = NULL; + mempool_t *pool = NULL; /* Becomes non-null if mempool used */ struct page *page; int want; u64 offset, len; - struct ceph_osd_request_head *reqhead; - struct ceph_osd_op *op; long writeback_stat; next = 0; @@ -782,11 +793,8 @@ get_more_pages: dout("waiting on writeback %p\n", page); wait_on_page_writeback(page); } - if ((snap_size && page_offset(page) > snap_size) || - (!snap_size && - page_offset(page) > i_size_read(inode))) { - dout("%p page eof %llu\n", page, snap_size ? - snap_size : i_size_read(inode)); + if (page_offset(page) >= snap_size) { + dout("%p page eof %llu\n", page, snap_size); done = 1; unlock_page(page); break; @@ -814,35 +822,42 @@ get_more_pages: break; } - /* ok */ + /* + * We have something to write. If this is + * the first locked page this time through, + * allocate an osd request and a page array + * that it will use. + */ if (locked_pages == 0) { + BUG_ON(pages); /* prepare async write request */ - offset = (unsigned long long)page->index - << PAGE_CACHE_SHIFT; + offset = (u64)page_offset(page); len = wsize; req = ceph_osdc_new_request(&fsc->client->osdc, - &ci->i_layout, - ceph_vino(inode), - offset, &len, - CEPH_OSD_OP_WRITE, - CEPH_OSD_FLAG_WRITE | - CEPH_OSD_FLAG_ONDISK, - snapc, do_sync, - ci->i_truncate_seq, - ci->i_truncate_size, - &inode->i_mtime, true, 1, 0); - - if (!req) { - rc = -ENOMEM; + &ci->i_layout, vino, + offset, &len, num_ops, + CEPH_OSD_OP_WRITE, + CEPH_OSD_FLAG_WRITE | + CEPH_OSD_FLAG_ONDISK, + snapc, truncate_seq, + truncate_size, true); + if (IS_ERR(req)) { + rc = PTR_ERR(req); unlock_page(page); break; } - max_pages = req->r_num_pages; - - alloc_page_vec(fsc, req); req->r_callback = writepages_finish; req->r_inode = inode; + + max_pages = calc_pages_for(0, (u64)len); + pages = kmalloc(max_pages * sizeof (*pages), + GFP_NOFS); + if (!pages) { + pool = fsc->wb_pagevec_pool; + pages = mempool_alloc(pool, GFP_NOFS); + BUG_ON(!pages); + } } /* note position of first page in pvec */ @@ -860,7 +875,7 @@ get_more_pages: } set_page_writeback(page); - req->r_pages[locked_pages] = page; + pages[locked_pages] = page; locked_pages++; next = page->index + 1; } @@ -889,20 +904,27 @@ get_more_pages: pvec.nr -= i-first; } - /* submit the write */ - offset = req->r_pages[0]->index << PAGE_CACHE_SHIFT; - len = min((snap_size ? snap_size : i_size_read(inode)) - offset, + /* Format the osd request message and submit the write */ + + offset = page_offset(pages[0]); + len = min(snap_size - offset, (u64)locked_pages << PAGE_CACHE_SHIFT); dout("writepages got %d pages at %llu~%llu\n", locked_pages, offset, len); - /* revise final length, page count */ - req->r_num_pages = locked_pages; - reqhead = req->r_request->front.iov_base; - op = (void *)(reqhead + 1); - op->extent.length = cpu_to_le64(len); - op->payload_len = cpu_to_le32(len); - req->r_request->hdr.data_len = cpu_to_le32(len); + osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, + !!pool, false); + + pages = NULL; /* request message now owns the pages array */ + pool = NULL; + + /* Update the write op length in case we changed it */ + + osd_req_op_extent_update(req, 0, len); + + vino = ceph_vino(inode); + ceph_osdc_build_request(req, offset, snapc, vino.snap, + &inode->i_mtime); rc = ceph_osdc_start_request(&fsc->client->osdc, req, true); BUG_ON(rc); @@ -969,7 +991,7 @@ static int ceph_update_writeable_page(struct file *file, loff_t pos, unsigned len, struct page *page) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; loff_t page_off = pos & PAGE_CACHE_MASK; @@ -1078,7 +1100,7 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct page *page; pgoff_t index = pos >> PAGE_CACHE_SHIFT; int r; @@ -1108,7 +1130,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_mds_client *mdsc = fsc->mdsc; unsigned from = pos & (PAGE_CACHE_SIZE - 1); @@ -1177,13 +1199,16 @@ const struct address_space_operations ceph_aops = { */ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); struct page *page = vmf->page; struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; - loff_t off = page->index << PAGE_CACHE_SHIFT; + loff_t off = page_offset(page); loff_t size, len; int ret; + /* Update time before taking page lock */ + file_update_time(vma->vm_file); + size = i_size_read(inode); if (off + PAGE_CACHE_SIZE <= size) len = PAGE_CACHE_SIZE; @@ -1222,6 +1247,7 @@ out: static struct vm_operations_struct ceph_vmops = { .fault = filemap_fault, .page_mkwrite = ceph_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int ceph_mmap(struct file *file, struct vm_area_struct *vma) @@ -1232,6 +1258,5 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &ceph_vmops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } |