[v18,56/71] ceph: plumb in decryption during sync reads

Commit Message

Xiubo Li April 12, 2023, 11:09 a.m. UTC

From: Jeff Layton <[e-mail]>

Switch to using sparse reads when the inode is encrypted.

Note that the crypto block may be smaller than a page, but the reverse
cannot be true.

Tested-by: Luís Henriques <[e-mail]>
Tested-by: Venky Shankar <[e-mail]>
Reviewed-by: Luís Henriques <[e-mail]>
Reviewed-by: Xiubo Li <[e-mail]>
Signed-off-by: Jeff Layton <[e-mail]>
---
 fs/ceph/file.c | 89 ++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 65 insertions(+), 24 deletions(-)

Patch

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 3ba5f74acbaa..0adaa89d0604 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -967,7 +967,7 @@  ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 	u64 off = *ki_pos;
 	u64 len = iov_iter_count(to);
 	u64 i_size = i_size_read(inode);
-	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
+	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
 	u64 objver = 0;
 
 	dout("sync_read on inode %p %llx~%llx\n", inode, *ki_pos, len);
@@ -998,10 +998,19 @@  ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		int idx;
 		size_t left;
 		struct ceph_osd_req_op *op;
+		u64 read_off = off;
+		u64 read_len = len;
+
+		/* determine new offset/length if encrypted */
+		ceph_fscrypt_adjust_off_and_len(inode, &read_off, &read_len);
+
+		dout("sync_read orig %llu~%llu reading %llu~%llu",
+		     off, len, read_off, read_len);
 
 		req = ceph_osdc_new_request(osdc, &ci->i_layout,
-					ci->i_vino, off, &len, 0, 1,
-					sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
+					ci->i_vino, read_off, &read_len, 0, 1,
+					sparse ? CEPH_OSD_OP_SPARSE_READ :
+						 CEPH_OSD_OP_READ,
 					CEPH_OSD_FLAG_READ,
 					NULL, ci->i_truncate_seq,
 					ci->i_truncate_size, false);
@@ -1010,10 +1019,13 @@  ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			break;
 		}
 
+		/* adjust len downward if the request truncated the len */
+		if (off + len > read_off + read_len)
+			len = read_off + read_len - off;
 		more = len < iov_iter_count(to);
 
-		num_pages = calc_pages_for(off, len);
-		page_off = off & ~PAGE_MASK;
+		num_pages = calc_pages_for(read_off, read_len);
+		page_off = offset_in_page(off);
 		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 		if (IS_ERR(pages)) {
 			ceph_osdc_put_request(req);
@@ -1021,7 +1033,8 @@  ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			break;
 		}
 
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
+		osd_req_op_extent_osd_data_pages(req, 0, pages, read_len,
+						 offset_in_page(read_off),
 						 false, false);
 
 		op = &req->r_ops[0];
@@ -1039,7 +1052,7 @@  ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		ceph_update_read_metrics(&fsc->mdsc->metric,
 					 req->r_start_latency,
 					 req->r_end_latency,
-					 len, ret);
+					 read_len, ret);
 
 		if (ret > 0)
 			objver = req->r_version;
@@ -1054,8 +1067,34 @@  ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		else if (ret == -ENOENT)
 			ret = 0;
 
+		if (ret > 0 && IS_ENCRYPTED(inode)) {
+			int fret;
+
+			fret = ceph_fscrypt_decrypt_extents(inode, pages, read_off,
+					op->extent.sparse_ext, op->extent.sparse_ext_cnt);
+			if (fret < 0) {
+				ret = fret;
+				ceph_osdc_put_request(req);
+				break;
+			}
+
+			/* account for any partial block at the beginning */
+			fret -= (off - read_off);
+
+			/*
+			 * Short read after big offset adjustment?
+			 * Nothing is usable, just call it a zero
+			 * len read.
+			 */
+			fret = max(fret, 0);
+
+			/* account for partial block at the end */
+			ret = min_t(ssize_t, fret, len);
+		}
+
 		ceph_osdc_put_request(req);
 
+		/* Short read but not EOF? Zero out the remainder. */
 		if (ret >= 0 && ret < len && (off + ret < i_size)) {
 			int zlen = min(len - ret, i_size - off - ret);
 			int zoff = page_off + ret;
@@ -1069,15 +1108,16 @@  ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		idx = 0;
 		left = ret > 0 ? ret : 0;
 		while (left > 0) {
-			size_t len, copied;
-			page_off = off & ~PAGE_MASK;
-			len = min_t(size_t, left, PAGE_SIZE - page_off);
+			size_t plen, copied;
+
+			plen = min_t(size_t, left, PAGE_SIZE - page_off);
 			SetPageUptodate(pages[idx]);
 			copied = copy_page_to_iter(pages[idx++],
-						   page_off, len, to);
+						   page_off, plen, to);
 			off += copied;
 			left -= copied;
-			if (copied < len) {
+			page_off = 0;
+			if (copied < plen) {
 				ret = -EFAULT;
 				break;
 			}
@@ -1094,20 +1134,21 @@  ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			break;
 	}
 
-	if (off > *ki_pos) {
-		if (off >= i_size) {
-			*retry_op = CHECK_EOF;
-			ret = i_size - *ki_pos;
-			*ki_pos = i_size;
-		} else {
-			ret = off - *ki_pos;
-			*ki_pos = off;
+	if (ret > 0) {
+		if (off > *ki_pos) {
+			if (off >= i_size) {
+				*retry_op = CHECK_EOF;
+				ret = i_size - *ki_pos;
+				*ki_pos = i_size;
+			} else {
+				ret = off - *ki_pos;
+				*ki_pos = off;
+			}
 		}
-	}
-
-	if (last_objver && ret > 0)
-		*last_objver = objver;
 
+		if (last_objver)
+			*last_objver = objver;
+	}
 	dout("sync_read result %zd retry_op %d\n", ret, *retry_op);
 	return ret;
 }