Skip to contentSkip to conversation

ceph+fscrypt: full support

PATCH Superseded Jeff Layton 1 participant 60 messages Apr 5, 2022 – Apr 6, 2022

Subsystems (4)

v13 of 14 Superseded Latest is v14 →

lore
Share & tools
lore
#45 lore raw

PATCH v13 45/59 ceph: add __ceph_sync_read helper support

In reply to Jeff Layton

From: Xiubo Li <[email protected]>

Turn the guts of ceph_sync_read into a new helper that takes an inode and an offset instead of a kiocb struct, and make ceph_sync_read call the helper as a wrapper.

---
 fs/ceph/file.c  | 33 +++++++++++++++++++++------------
 fs/ceph/super.h |  2 ++
 2 files changed, 23 insertions(+), 12 deletions(-)
fs/ceph/file.c +21 -12
index b7e2594cc296..c4300381851e 100644
@@ -927,22 +927,19 @@ enum {
  * If we get a short result from the OSD, check against i_size; we need to
  * only return a short read to the caller if we hit EOF.
  */
-static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
-			      int *retry_op)
+ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
+			 struct iov_iter *to, int *retry_op)
 {
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	ssize_t ret;
-	u64 off = iocb->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);
 
-	dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len,
-	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
+	dout("sync_read on inode %p %llx~%llx\n", inode, *ki_pos, len);
 
 	if (!len)
 		return 0;
@@ -1061,14 +1058,14 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 			break;
 	}
 
-	if (off > iocb->ki_pos) {
+	if (off > *ki_pos) {
 		if (off >= i_size) {
 			*retry_op = CHECK_EOF;
-			ret = i_size - iocb->ki_pos;
-			iocb->ki_pos = i_size;
+			ret = i_size - *ki_pos;
+			*ki_pos = i_size;
 		} else {
-			ret = off - iocb->ki_pos;
-			iocb->ki_pos = off;
+			ret = off - *ki_pos;
+			*ki_pos = off;
 		}
 	}
 
@@ -1076,6 +1073,18 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 	return ret;
 }
 
+static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
+			      int *retry_op)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+
+	dout("sync_read on file %p %llx~%zx %s\n", file, iocb->ki_pos,
+	     iov_iter_count(to), (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
+
+	return __ceph_sync_read(inode, &iocb->ki_pos, to, retry_op);
+}
+
 struct ceph_aio_request {
 	struct kiocb *iocb;
 	size_t total_len;
fs/ceph/super.h +2 -0
index 752bc3c820ca..d7ab820aed34 100644
@@ -1258,6 +1258,8 @@ extern int ceph_renew_caps(struct inode *inode, int fmode);
 extern int ceph_open(struct inode *inode, struct file *file);
 extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags, umode_t mode);
+extern ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
+				struct iov_iter *to, int *retry_op);
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);
Signature · 1 line
2.35.1
#2 lore raw

PATCH v13 2/59 libceph: define struct ceph_sparse_extent and add some helpers

In reply to Jeff Layton

When the OSD sends back a sparse read reply, it contains an array of these structures. Define the structure and add a couple of helpers for dealing with them.

Also add a place in struct ceph_osd_req_op to store the extent buffer, and code to free it if it's populated when the req is torn down.

---
 include/linux/ceph/osd_client.h | 43 ++++++++++++++++++++++++++++++++-
 net/ceph/osd_client.c           | 13 ++++++++++
 2 files changed, 55 insertions(+), 1 deletion(-)
include/linux/ceph/osd_client.h +42 -1
index 3122c1a3205f..1dd02240d00d 100644
@@ -29,6 +29,17 @@ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
 
 #define CEPH_HOMELESS_OSD	-1
 
+/*
+ * A single extent in a SPARSE_READ reply.
+ *
+ * Note that these come from the OSD as little-endian values. On BE arches,
+ * we convert them in-place after receipt.
+ */
+struct ceph_sparse_extent {
+	u64	off;
+	u64	len;
+} __packed;
+
 /*
  * A given osd we're communicating with.
  *
@@ -104,6 +115,8 @@ struct ceph_osd_req_op {
 			u64 offset, length;
 			u64 truncate_size;
 			u32 truncate_seq;
+			int sparse_ext_cnt;
+			struct ceph_sparse_extent *sparse_ext;
 			struct ceph_osd_data osd_data;
 		} extent;
 		struct {
@@ -507,6 +520,20 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
 				      u32 truncate_seq, u64 truncate_size,
 				      bool use_mempool);
 
+int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt);
+
+/*
+ * How big an extent array should we preallocate for a sparse read? This is
+ * just a starting value.  If we get more than this back from the OSD, the
+ * receiver will reallocate.
+ */
+#define CEPH_SPARSE_EXT_ARRAY_INITIAL  16
+
+static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op)
+{
+	return __ceph_alloc_sparse_ext_map(op, CEPH_SPARSE_EXT_ARRAY_INITIAL);
+}
+
 extern void ceph_osdc_get_request(struct ceph_osd_request *req);
 extern void ceph_osdc_put_request(struct ceph_osd_request *req);
 
@@ -562,5 +589,19 @@ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
 			    struct ceph_object_locator *oloc,
 			    struct ceph_watch_item **watchers,
 			    u32 *num_watchers);
-#endif
 
+/* Find offset into the buffer of the end of the extent map */
+static inline u64 ceph_sparse_ext_map_end(struct ceph_osd_req_op *op)
+{
+	struct ceph_sparse_extent *ext;
+
+	/* No extents? No data */
+	if (op->extent.sparse_ext_cnt == 0)
+		return 0;
+
+	ext = &op->extent.sparse_ext[op->extent.sparse_ext_cnt - 1];
+
+	return ext->off + ext->len - op->extent.offset;
+}
+
+#endif
net/ceph/osd_client.c +13 -0
index 17c792b32343..c150683f2a2f 100644
@@ -378,6 +378,7 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
 	case CEPH_OSD_OP_READ:
 	case CEPH_OSD_OP_WRITE:
 	case CEPH_OSD_OP_WRITEFULL:
+		kfree(op->extent.sparse_ext);
 		ceph_osd_data_release(&op->extent.osd_data);
 		break;
 	case CEPH_OSD_OP_CALL:
@@ -1141,6 +1142,18 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 }
 EXPORT_SYMBOL(ceph_osdc_new_request);
 
+int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt)
+{
+	op->extent.sparse_ext_cnt = cnt;
+	op->extent.sparse_ext = kmalloc_array(cnt,
+					      sizeof(*op->extent.sparse_ext),
+					      GFP_NOFS);
+	if (!op->extent.sparse_ext)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(__ceph_alloc_sparse_ext_map);
+
 /*
  * We keep osd requests in an rbtree, sorted by ->r_tid.
  */
Signature · 1 line
2.35.1
#4 lore raw

PATCH v13 4/59 libceph: add sparse read support to OSD client

In reply to Jeff Layton

Have get_reply check for the presence of sparse read ops in the request and set the sparse_read boolean in the msg. That will queue the messenger layer to use the sparse read codepath instead of the normal data receive.

Add a new sparse_read operation for the OSD client, driven by its own state machine. The messenger will repeatedly call the sparse_read operation, and it will pass back the necessary info to set up to read the next extent of data, while zero-filling the sparse regions.

The state machine will stop at the end of the last extent, and will attach the extent map buffer to the ceph_osd_req_op so that the caller can use it.

---
 include/linux/ceph/osd_client.h |  32 ++++
 net/ceph/osd_client.c           | 256 +++++++++++++++++++++++++++++++-
 2 files changed, 284 insertions(+), 4 deletions(-)
include/linux/ceph/osd_client.h +32 -0
index 1dd02240d00d..4088601beacc 100644
@@ -40,6 +40,36 @@ struct ceph_sparse_extent {
 	u64	len;
 } __packed;
 
+/* Sparse read state machine state values */
+enum ceph_sparse_read_state {
+	CEPH_SPARSE_READ_HDR	= 0,
+	CEPH_SPARSE_READ_EXTENTS,
+	CEPH_SPARSE_READ_DATA_LEN,
+	CEPH_SPARSE_READ_DATA,
+};
+
+/*
+ * A SPARSE_READ reply is a 32-bit count of extents, followed by an array of
+ * 64-bit offset/length pairs, and then all of the actual file data
+ * concatenated after it (sans holes).
+ *
+ * Unfortunately, we don't know how long the extent array is until we've
+ * started reading the data section of the reply. The caller should send down
+ * a destination buffer for the array, but we'll alloc one if it's too small
+ * or if the caller doesn't.
+ */
+struct ceph_sparse_read {
+	enum ceph_sparse_read_state	sr_state;	/* state machine state */
+	u64				sr_req_off;	/* orig request offset */
+	u64				sr_req_len;	/* orig request length */
+	u64				sr_pos;		/* current pos in buffer */
+	int				sr_index;	/* current extent index */
+	__le32				sr_datalen;	/* length of actual data */
+	u32				sr_count;	/* extent count in reply */
+	int				sr_ext_len;	/* length of extent array */
+	struct ceph_sparse_extent	*sr_extent;	/* extent array */
+};
+
 /*
  * A given osd we're communicating with.
  *
@@ -48,6 +78,7 @@ struct ceph_sparse_extent {
  */
 struct ceph_osd {
 	refcount_t o_ref;
+	int o_sparse_op_idx;
 	struct ceph_osd_client *o_osdc;
 	int o_osd;
 	int o_incarnation;
@@ -63,6 +94,7 @@ struct ceph_osd {
 	unsigned long lru_ttl;
 	struct list_head o_keepalive_item;
 	struct mutex lock;
+	struct ceph_sparse_read	o_sparse_read;
 };
 
 #define CEPH_OSD_SLAB_OPS	2
net/ceph/osd_client.c +252 -4

350 lines not on this page · raw message

Signature · 1 line
2.35.1
#19 lore raw

PATCH v13 19/59 ceph: make the ioctl cmd more readable in debug log

In reply to Jeff Layton

From: Xiubo Li <[email protected]>

    ioctl file 0000000004e6b054 cmd 2148296211 arg 824635143532

The numerical cmd valye in the ioctl debug log message is too hard to understand even when you look at it in the code. Make it more readable.

---
 fs/ceph/ioctl.c | 39 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)
fs/ceph/ioctl.c +38 -1
index 477ecc667aee..b9f0f4e460ab 100644
@@ -313,11 +313,48 @@ static long ceph_set_encryption_policy(struct file *file, unsigned long arg)
 	return ret;
 }
 
+static const char *ceph_ioctl_cmd_name(const unsigned int cmd)
+{
+	switch (cmd) {
+	case CEPH_IOC_GET_LAYOUT:
+		return "get_layout";
+	case CEPH_IOC_SET_LAYOUT:
+		return "set_layout";
+	case CEPH_IOC_SET_LAYOUT_POLICY:
+		return "set_layout_policy";
+	case CEPH_IOC_GET_DATALOC:
+		return "get_dataloc";
+	case CEPH_IOC_LAZYIO:
+		return "lazyio";
+	case CEPH_IOC_SYNCIO:
+		return "syncio";
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+		return "set encryption_policy";
+	case FS_IOC_GET_ENCRYPTION_POLICY:
+		return "get_encryption_policy";
+	case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+		return "get_encryption_policy_ex";
+	case FS_IOC_ADD_ENCRYPTION_KEY:
+		return "add_encryption_key";
+	case FS_IOC_REMOVE_ENCRYPTION_KEY:
+		return "remove_encryption_key";
+	case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS:
+		return "remove_encryption_key_all_users";
+	case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
+		return "get_encryption_key_status";
+	case FS_IOC_GET_ENCRYPTION_NONCE:
+		return "get_encryption_nonce";
+	default:
+		return "unknown";
+	}
+}
+
 long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	int ret;
 
-	dout("ioctl file %p cmd %u arg %lu\n", file, cmd, arg);
+	dout("ioctl file %p cmd %s arg %lu\n", file,
+	     ceph_ioctl_cmd_name(cmd), arg);
 	switch (cmd) {
 	case CEPH_IOC_GET_LAYOUT:
 		return ceph_ioctl_get_layout(file, (void __user *)arg);
Signature · 1 line
2.35.1
#53 lore raw

PATCH v13 53/59 ceph: align data in pages in ceph_sync_write

In reply to Jeff Layton

Encrypted files will need to be dealt with in block-sized chunks and once we do that, the way that ceph_sync_write aligns the data in the bounce buffer won't be acceptable.

Change it to align the data the same way it would be aligned in the pagecache.

---
 fs/ceph/file.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)
fs/ceph/file.c +10 -10
index 41b97d32dfcf..69ac67c93552 100644
@@ -1551,6 +1551,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	bool check_caps = false;
 	struct timespec64 mtime = current_time(inode);
 	size_t count = iov_iter_count(from);
+	size_t off;
 
 	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
@@ -1588,12 +1589,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 			break;
 		}
 
-		/*
-		 * write from beginning of first page,
-		 * regardless of io alignment
-		 */
-		num_pages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-
+		num_pages = calc_pages_for(pos, len);
 		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 		if (IS_ERR(pages)) {
 			ret = PTR_ERR(pages);
@@ -1601,9 +1597,12 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		}
 
 		left = len;
+		off = offset_in_page(pos);
 		for (n = 0; n < num_pages; n++) {
-			size_t plen = min_t(size_t, left, PAGE_SIZE);
-			ret = copy_page_from_iter(pages[n], 0, plen, from);
+			size_t plen = min_t(size_t, left, PAGE_SIZE - off);
+
+			ret = copy_page_from_iter(pages[n], off, plen, from);
+			off = 0;
 			if (ret != plen) {
 				ret = -EFAULT;
 				break;
@@ -1618,8 +1617,9 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 
 		req->r_inode = inode;
 
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
-						false, true);
+		osd_req_op_extent_osd_data_pages(req, 0, pages, len,
+						 offset_in_page(pos),
+						 false, true);
 
 		req->r_mtime = mtime;
 		ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
Signature · 1 line
2.35.1
#49 lore raw

PATCH v13 49/59 libceph: allow ceph_osdc_new_request to accept a multi-op read

In reply to Jeff Layton

Currently we have some special-casing for multi-op writes, but in the case of a read, we can't really handle it. All of the current multi-op callers call it with CEPH_OSD_FLAG_WRITE set.

Have ceph_osdc_new_request check for CEPH_OSD_FLAG_READ and if it's set, allocate multiple reply ops instead of multiple request ops. If neither flag is set, return -EINVAL.

---
 net/ceph/osd_client.c | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)
net/ceph/osd_client.c +21 -6
index febdd728b2fb..39d38b69a953 100644
@@ -1130,15 +1130,30 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	if (flags & CEPH_OSD_FLAG_WRITE)
 		req->r_data_offset = off;
 
-	if (num_ops > 1)
+	if (num_ops > 1) {
+		int num_req_ops, num_rep_ops;
+
 		/*
-		 * This is a special case for ceph_writepages_start(), but it
-		 * also covers ceph_uninline_data().  If more multi-op request
-		 * use cases emerge, we will need a separate helper.
+		 * If this is a multi-op write request, assume that we'll need
+		 * request ops. If it's a multi-op read then assume we'll need
+		 * reply ops. Anything else and call it -EINVAL.
 		 */
-		r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_ops, 0);
-	else
+		if (flags & CEPH_OSD_FLAG_WRITE) {
+			num_req_ops = num_ops;
+			num_rep_ops = 0;
+		} else if (flags & CEPH_OSD_FLAG_READ) {
+			num_req_ops = 0;
+			num_rep_ops = num_ops;
+		} else {
+			r = -EINVAL;
+			goto fail;
+		}
+
+		r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_req_ops,
+					       num_rep_ops);
+	} else {
 		r = ceph_osdc_alloc_messages(req, GFP_NOFS);
+	}
 	if (r)
 		goto fail;
 
Signature · 1 line
2.35.1
#24 lore raw

PATCH v13 24/59 ceph: properly set DCACHE_NOKEY_NAME flag in lookup

In reply to Jeff Layton

This is required so that we know to invalidate these dentries when the directory is unlocked.

---
 fs/ceph/dir.c | 11 +++++++++++
 1 file changed, 11 insertions(+)
fs/ceph/dir.c +11 -0
index 8cc7a49ee508..897f8618151b 100644
@@ -760,6 +760,17 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
 
+	if (IS_ENCRYPTED(dir)) {
+		err = __fscrypt_prepare_readdir(dir);
+		if (err)
+			return ERR_PTR(err);
+		if (!fscrypt_has_encryption_key(dir)) {
+			spin_lock(&dentry->d_lock);
+			dentry->d_flags |= DCACHE_NOKEY_NAME;
+			spin_unlock(&dentry->d_lock);
+		}
+	}
+
 	/* can we conclude ENOENT locally? */
 	if (d_really_is_negative(dentry)) {
 		struct ceph_inode_info *ci = ceph_inode(dir);
Signature · 1 line
2.35.1
#42 lore raw

PATCH v13 42/59 ceph: handle fscrypt fields in cap messages from MDS

In reply to Jeff Layton

Handle the new fscrypt_file and fscrypt_auth fields in cap messages. Use them to populate new fields in cap_extra_info and update the inode with those values.

---
 fs/ceph/caps.c | 78 ++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 76 insertions(+), 2 deletions(-)
fs/ceph/caps.c +76 -2
index cb5cdf2260ad..1f3a2135214c 100644
@@ -3364,6 +3364,9 @@ struct cap_extra_info {
 	/* currently issued */
 	int issued;
 	struct timespec64 btime;
+	u8 *fscrypt_auth;
+	u32 fscrypt_auth_len;
+	u64 fscrypt_file_size;
 };
 
 /*
@@ -3396,6 +3399,14 @@ static void handle_cap_grant(struct inode *inode,
 	bool deleted_inode = false;
 	bool fill_inline = false;
 
+	/*
+	 * If there is at least one crypto block then we'll trust fscrypt_file_size.
+	 * If the real length of the file is 0, then ignore it (it has probably been
+	 * truncated down to 0 by the MDS).
+	 */
+	if (IS_ENCRYPTED(inode) && size)
+		size = extra_info->fscrypt_file_size;
+
 	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
 	     inode, cap, session->s_mds, seq, ceph_cap_string(newcaps));
 	dout(" size %llu max_size %llu, i_size %llu\n", size, max_size,
@@ -3462,6 +3473,10 @@ static void handle_cap_grant(struct inode *inode,
 		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
 		     from_kuid(&init_user_ns, inode->i_uid),
 		     from_kgid(&init_user_ns, inode->i_gid));
+
+		WARN_ON_ONCE(ci->fscrypt_auth_len != extra_info->fscrypt_auth_len ||
+			     memcmp(ci->fscrypt_auth, extra_info->fscrypt_auth,
+				     ci->fscrypt_auth_len));
 	}
 
 	if ((newcaps & CEPH_CAP_LINK_SHARED) &&
@@ -3872,7 +3887,8 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
  */
 static bool handle_cap_trunc(struct inode *inode,
 			     struct ceph_mds_caps *trunc,
-			     struct ceph_mds_session *session)
+			     struct ceph_mds_session *session,
+			     struct cap_extra_info *extra_info)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int mds = session->s_mds;
@@ -3889,6 +3905,14 @@ static bool handle_cap_trunc(struct inode *inode,
 
 	issued |= implemented | dirty;
 
+	/*
+	 * If there is at least one crypto block then we'll trust fscrypt_file_size.
+	 * If the real length of the file is 0, then ignore it (it has probably been
+	 * truncated down to 0 by the MDS).
+	 */
+	if (IS_ENCRYPTED(inode) && size)
+		size = extra_info->fscrypt_file_size;
+
 	dout("handle_cap_trunc inode %p mds%d seq %d to %lld seq %d\n",
 	     inode, mds, seq, truncate_size, truncate_seq);
 	queue_trunc = ceph_fill_file_size(inode, issued,
@@ -4110,6 +4134,49 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
 	*target_cap = cap;
 }
 
+#ifdef CONFIG_FS_ENCRYPTION
+static int parse_fscrypt_fields(void **p, void *end, struct cap_extra_info *extra)
+{
+	u32 len;
+
+	ceph_decode_32_safe(p, end, extra->fscrypt_auth_len, bad);
+	if (extra->fscrypt_auth_len) {
+		ceph_decode_need(p, end, extra->fscrypt_auth_len, bad);
+		extra->fscrypt_auth = kmalloc(extra->fscrypt_auth_len, GFP_KERNEL);
+		if (!extra->fscrypt_auth)
+			return -ENOMEM;
+		ceph_decode_copy_safe(p, end, extra->fscrypt_auth,
+					extra->fscrypt_auth_len, bad);
+	}
+
+	ceph_decode_32_safe(p, end, len, bad);
+	if (len >= sizeof(u64)) {
+		ceph_decode_64_safe(p, end, extra->fscrypt_file_size, bad);
+		len -= sizeof(u64);
+	}
+	ceph_decode_skip_n(p, end, len, bad);
+	return 0;
+bad:
+	return -EIO;
+}
+#else
+static int parse_fscrypt_fields(void **p, void *end, struct cap_extra_info *extra)
+{
+	u32 len;
+
+	/* Don't care about these fields unless we're encryption-capable */
+	ceph_decode_32_safe(p, end, len, bad);
+	if (len)
+		ceph_decode_skip_n(p, end, len, bad);
+	ceph_decode_32_safe(p, end, len, bad);
+	if (len)
+		ceph_decode_skip_n(p, end, len, bad);
+	return 0;
+bad:
+	return -EIO;
+}
+#endif
+
 /*
  * Handle a caps message from the MDS.
  *
@@ -4228,6 +4295,11 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		ceph_decode_64_safe(&p, end, extra_info.nsubdirs, bad);
 	}
 
+	if (msg_version >= 12) {
+		if (parse_fscrypt_fields(&p, end, &extra_info))
+			goto bad;
+	}
+
 	/* lookup ino */
 	inode = ceph_find_inode(mdsc->fsc->sb, vino);
 	dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
@@ -4324,7 +4396,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		break;
 
 	case CEPH_CAP_OP_TRUNC:
-		queue_trunc = handle_cap_trunc(inode, h, session);
+		queue_trunc = handle_cap_trunc(inode, h, session,
+						&extra_info);
 		spin_unlock(&ci->i_ceph_lock);
 		if (queue_trunc)
 			ceph_queue_vmtruncate(inode);
@@ -4342,6 +4415,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	iput(inode);
 out:
 	ceph_put_string(extra_info.pool_ns);
+	kfree(extra_info.fscrypt_auth);
 	return;
 
 flush_cap_releases:
Signature · 1 line
2.35.1
#3 lore raw

PATCH v13 3/59 libceph: add sparse read support to msgr2 crc state machine

In reply to Jeff Layton

Add support for a new sparse_read ceph_connection operation. The idea is that the client driver can define this operation use it to do special handling for incoming reads.

The alloc_msg routine will look at the request and determine whether the reply is expected to be sparse. If it is, then we'll dispatch to a different set of state machine states that will repeatedly call the driver's sparse_read op to get length and placement info for reading the extent map, and the extents themselves.

This necessitates adding some new field to some other structs:

- The msg gets a new bool to track whether it's a sparse_read request.

- A new field is added to the cursor to track the amount remaining in the current extent. This is used to cap the read from the socket into the msg_data

- Handing a revoke with all of this is particularly difficult, so I've added a new data_len_remain field to the v2 connection info, and then use that to skip that much on a revoke. We may want to expand the use of that to the normal read path as well, just for consistency's sake.

---
 include/linux/ceph/messenger.h |  28 ++++++
 net/ceph/messenger.c           |   1 +
 net/ceph/messenger_v2.c        | 168 +++++++++++++++++++++++++++++++--
 3 files changed, 188 insertions(+), 9 deletions(-)
include/linux/ceph/messenger.h +28 -0
index e7f2fb2fc207..7f09a4213834 100644
@@ -17,6 +17,7 @@
 
 struct ceph_msg;
 struct ceph_connection;
+struct ceph_msg_data_cursor;
 
 /*
  * Ceph defines these callbacks for handling connection events.
@@ -70,6 +71,30 @@ struct ceph_connection_operations {
 				      int used_proto, int result,
 				      const int *allowed_protos, int proto_cnt,
 				      const int *allowed_modes, int mode_cnt);
+
+	/**
+	 * sparse_read: read sparse data
+	 * @con: connection we're reading from
+	 * @cursor: data cursor for reading extents
+	 * @buf: optional buffer to read into
+	 *
+	 * This should be called more than once, each time setting up to
+	 * receive an extent into the current cursor position, and zeroing
+	 * the holes between them.
+	 *
+	 * Returns amount of data to be read (in bytes), 0 if reading is
+	 * complete, or -errno if there was an error.
+	 *
+	 * If @buf is set on a >0 return, then the data should be read into
+	 * the provided buffer. Otherwise, it should be read into the cursor.
+	 *
+	 * The sparse read operation is expected to initialize the cursor
+	 * with a length covering up to the end of the last extent.
+	 */
+	int (*sparse_read)(struct ceph_connection *con,
+			   struct ceph_msg_data_cursor *cursor,
+			   char **buf);
+
 };
 
 /* use format string %s%lld */
@@ -207,6 +232,7 @@ struct ceph_msg_data_cursor {
 
 	struct ceph_msg_data	*data;		/* current data item */
 	size_t			resid;		/* bytes not yet consumed */
+	int			sr_resid;	/* residual sparse_read len */
 	bool			last_piece;	/* current is last piece */
 	bool			need_crc;	/* crc update needed */
 	union {
@@ -252,6 +278,7 @@ struct ceph_msg {
 	struct kref kref;
 	bool more_to_follow;
 	bool needs_out_seq;
+	bool sparse_read;
 	int front_alloc_len;
 
 	struct ceph_msgpool *pool;
@@ -396,6 +423,7 @@ struct ceph_connection_v2_info {
 
 	void *conn_bufs[16];
 	int conn_buf_cnt;
+	int data_len_remain;
 
 	struct kvec in_sign_kvecs[8];
 	struct kvec out_sign_kvecs[8];
net/ceph/messenger.c +1 -0
index d3bb656308b4..bf4e7f5751ee 100644
@@ -1034,6 +1034,7 @@ void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor,
 
 	cursor->total_resid = length;
 	cursor->data = msg->data;
+	cursor->sr_resid = 0;
 
 	__ceph_msg_data_cursor_init(cursor);
 }
net/ceph/messenger_v2.c +159 -9

210 lines not on this page · raw message

Signature · 1 line
2.35.1
#8 lore raw

PATCH v13 8/59 fs: change test in inode_insert5 for adding to the sb list

In reply to Jeff Layton

The inode_insert5 currently looks at I_CREATING to decide whether to insert the inode into the sb list. This test is a bit ambiguous though as I_CREATING state is not directly related to that list.

This test is also problematic for some upcoming ceph changes to add fscrypt support. We need to be able to allocate an inode using new_inode and insert it into the hash later if we end up using it, and doing that now means that we double add it and corrupt the list.

What we really want to know in this test is whether the inode is already in its superblock list, and then add it if it isn't. Have it test for list_empty instead and ensure that we always initialize the list by doing it in inode_init_once. It's only ever removed from the list with list_del_init, so that should be sufficient.

---
 fs/inode.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)
fs/inode.c +8 -3
index 9d9b422504d1..743420a55e5f 100644
@@ -422,6 +422,7 @@ void inode_init_once(struct inode *inode)
 	INIT_LIST_HEAD(&inode->i_io_list);
 	INIT_LIST_HEAD(&inode->i_wb_list);
 	INIT_LIST_HEAD(&inode->i_lru);
+	INIT_LIST_HEAD(&inode->i_sb_list);
 	__address_space_init_once(&inode->i_data);
 	i_size_ordered_init(inode);
 }
@@ -1021,7 +1022,6 @@ struct inode *new_inode_pseudo(struct super_block *sb)
 		spin_lock(&inode->i_lock);
 		inode->i_state = 0;
 		spin_unlock(&inode->i_lock);
-		INIT_LIST_HEAD(&inode->i_sb_list);
 	}
 	return inode;
 }
@@ -1165,7 +1165,6 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
 {
 	struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
 	struct inode *old;
-	bool creating = inode->i_state & I_CREATING;
 
 again:
 	spin_lock(&inode_hash_lock);
@@ -1199,7 +1198,13 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
 	inode->i_state |= I_NEW;
 	hlist_add_head_rcu(&inode->i_hash, head);
 	spin_unlock(&inode->i_lock);
-	if (!creating)
+
+	/*
+	 * Add it to the list if it wasn't already in,
+	 * e.g. new_inode. We hold I_NEW at this point, so
+	 * we should be safe to test i_sb_list locklessly.
+	 */
+	if (list_empty(&inode->i_sb_list))
 		inode_sb_list_add(inode);
 unlock:
 	spin_unlock(&inode_hash_lock);
Signature · 1 line
2.35.1
#38 lore raw

PATCH v13 38/59 libceph: add CEPH_OSD_OP_ASSERT_VER support

In reply to Jeff Layton

...and record the user_version in the reply in a new field in ceph_osd_request, so we can populate the assert_ver appropriately. Shuffle the fields a bit too so that the new field fits in an existing hole on x86_64.

---
 include/linux/ceph/osd_client.h | 6 +++++-
 include/linux/ceph/rados.h      | 4 ++++
 net/ceph/osd_client.c           | 5 +++++
 3 files changed, 14 insertions(+), 1 deletion(-)
include/linux/ceph/osd_client.h +5 -1
index 4088601beacc..8c7f34df66d3 100644
@@ -196,6 +196,9 @@ struct ceph_osd_req_op {
 			u32 src_fadvise_flags;
 			struct ceph_osd_data osd_data;
 		} copy_from;
+		struct {
+			u64 ver;
+		} assert_ver;
 	};
 };
 
@@ -250,6 +253,7 @@ struct ceph_osd_request {
 	struct ceph_osd_client *r_osdc;
 	struct kref       r_kref;
 	bool              r_mempool;
+	bool		  r_linger;           /* don't resend on failure */
 	struct completion r_completion;       /* private to osd_client.c */
 	ceph_osdc_callback_t r_callback;
 
@@ -262,9 +266,9 @@ struct ceph_osd_request {
 	struct ceph_snap_context *r_snapc;    /* for writes */
 	struct timespec64 r_mtime;            /* ditto */
 	u64 r_data_offset;                    /* ditto */
-	bool r_linger;                        /* don't resend on failure */
 
 	/* internal */
+	u64 r_version;			      /* data version sent in reply */
 	unsigned long r_stamp;                /* jiffies, send or check time */
 	unsigned long r_start_stamp;          /* jiffies */
 	ktime_t r_start_latency;              /* ktime_t */
include/linux/ceph/rados.h +4 -0
index 43a7a1573b51..73c3efbec36c 100644
@@ -523,6 +523,10 @@ struct ceph_osd_op {
 		struct {
 			__le64 cookie;
 		} __attribute__ ((packed)) notify;
+		struct {
+			__le64 unused;
+			__le64 ver;
+		} __attribute__ ((packed)) assert_ver;
 		struct {
 			__le64 offset, length;
 			__le64 src_offset;
net/ceph/osd_client.c +5 -0
index acf6a19b6677..febdd728b2fb 100644
@@ -1042,6 +1042,10 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst,
 		dst->copy_from.src_fadvise_flags =
 			cpu_to_le32(src->copy_from.src_fadvise_flags);
 		break;
+	case CEPH_OSD_OP_ASSERT_VER:
+		dst->assert_ver.unused = cpu_to_le64(0);
+		dst->assert_ver.ver = cpu_to_le64(src->assert_ver.ver);
+		break;
 	default:
 		pr_err("unsupported osd opcode %s\n",
 			ceph_osd_op_name(src->op));
@@ -3804,6 +3808,7 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
 	 * one (type of) reply back.
 	 */
 	WARN_ON(!(m.flags & CEPH_OSD_FLAG_ONDISK));
+	req->r_version = m.user_version;
 	req->r_result = m.result ?: data_len;
 	finish_request(req);
 	mutex_unlock(&osd->lock);
Signature · 1 line
2.35.1
#54 lore raw

PATCH v13 54/59 ceph: add read/modify/write to ceph_sync_write

In reply to Jeff Layton

When doing a synchronous write on an encrypted inode, we have no guarantee that the caller is writing crypto block-aligned data. When that happens, we must do a read/modify/write cycle.

First, expand the range to cover complete blocks. If we had to change the original pos or length, issue a read to fill the first and/or last pages, and fetch the version of the object from the result.

We then copy data into the pages as usual, encrypt the result and issue a write prefixed by an assertion that the version hasn't changed. If it has changed then we restart the whole thing again.

If there is no object at that position in the file (-ENOENT), we prefix the write on an exclusive create of the object instead.

---
 fs/ceph/file.c | 319 ++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 290 insertions(+), 29 deletions(-)
fs/ceph/file.c +290 -29
index 69ac67c93552..522189ed6642 100644
@@ -1540,18 +1540,16 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_vino vino;
+	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_osd_request *req;
 	struct page **pages;
 	u64 len;
 	int num_pages;
 	int written = 0;
-	int flags;
 	int ret;
 	bool check_caps = false;
 	struct timespec64 mtime = current_time(inode);
 	size_t count = iov_iter_count(from);
-	size_t off;
 
 	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
@@ -1571,29 +1569,236 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	if (ret < 0)
 		dout("invalidate_inode_pages2_range returned %d\n", ret);
 
-	flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE;
-
 	while ((len = iov_iter_count(from)) > 0) {
 		size_t left;
 		int n;
+		u64 write_pos = pos;
+		u64 write_len = len;
+		u64 objnum, objoff;
+		u32 xlen;
+		u64 assert_ver;
+		bool rmw;
+		bool first, last;
+		struct iov_iter saved_iter = *from;
+		size_t off;
+
+		ceph_fscrypt_adjust_off_and_len(inode, &write_pos, &write_len);
+
+		/* clamp the length to the end of first object */
+		ceph_calc_file_object_mapping(&ci->i_layout, write_pos,
+						write_len, &objnum, &objoff,
+						&xlen);
+		write_len = xlen;
+
+		/* adjust len downward if it goes beyond current object */
+		if (pos + len > write_pos + write_len)
+			len = write_pos + write_len - pos;
 
-		vino = ceph_vino(inode);
-		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
-					    vino, pos, &len, 0, 1,
-					    CEPH_OSD_OP_WRITE, flags, snapc,
-					    ci->i_truncate_seq,
-					    ci->i_truncate_size,
-					    false);
-		if (IS_ERR(req)) {
-			ret = PTR_ERR(req);
-			break;
-		}
+		/*
+		 * If we had to adjust the length or position to align with a
+		 * crypto block, then we must do a read/modify/write cycle. We
+		 * use a version assertion to redrive the thing if something
+		 * changes in between.
+		 */
+		first = pos != write_pos;
+		last = (pos + len) != (write_pos + write_len);
+		rmw = first || last;
 
-		num_pages = calc_pages_for(pos, len);
+		dout("sync_write ino %llx %lld~%llu adjusted %lld~%llu -- %srmw\n",
+		     ci->i_vino.ino, pos, len, write_pos, write_len, rmw ? "" : "no ");
+
+		/*
+		 * The data is emplaced into the page as it would be if it were in
+		 * an array of pagecache pages.
+		 */
+		num_pages = calc_pages_for(write_pos, write_len);
 		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 		if (IS_ERR(pages)) {
 			ret = PTR_ERR(pages);
-			goto out;
+			break;
+		}
+
+		/* Do we need to preload the pages? */
+		if (rmw) {
+			u64 first_pos = write_pos;
+			u64 last_pos = (write_pos + write_len) - CEPH_FSCRYPT_BLOCK_SIZE;
+			u64 read_len = CEPH_FSCRYPT_BLOCK_SIZE;
+			struct ceph_osd_req_op *op;
+
+			/* We should only need to do this for encrypted inodes */
+			WARN_ON_ONCE(!IS_ENCRYPTED(inode));
+
+			/* No need to do two reads if first and last blocks are same */
+			if (first && last_pos == first_pos)
+				last = false;
+
+			/*
+			 * Allocate a read request for one or two extents, depending
+			 * on how the request was aligned.
+			 */
+			req = ceph_osdc_new_request(osdc, &ci->i_layout,
+					ci->i_vino, first ? first_pos : last_pos,
+					&read_len, 0, (first && last) ? 2 : 1,
+					CEPH_OSD_OP_SPARSE_READ, CEPH_OSD_FLAG_READ,
+					NULL, ci->i_truncate_seq,
+					ci->i_truncate_size, false);
+			if (IS_ERR(req)) {
+				ceph_release_page_vector(pages, num_pages);
+				ret = PTR_ERR(req);
+				break;
+			}
+
+			/* Something is misaligned! */
+			if (read_len != CEPH_FSCRYPT_BLOCK_SIZE) {
+				ceph_osdc_put_request(req);
+				ceph_release_page_vector(pages, num_pages);
+				ret = -EIO;
+				break;
+			}
+
+			/* Add extent for first block? */
+			op = &req->r_ops[0];
+
+			if (first) {
+				osd_req_op_extent_osd_data_pages(req, 0, pages,
+							 CEPH_FSCRYPT_BLOCK_SIZE,
+							 offset_in_page(first_pos),
+							 false, false);
+				/* We only expect a single extent here */
+				ret = __ceph_alloc_sparse_ext_map(op, 1);
+				if (ret) {
+					ceph_osdc_put_request(req);
+					ceph_release_page_vector(pages, num_pages);
+					break;
+				}
+			}
+
+			/* Add extent for last block */
+			if (last) {
+				/* Init the other extent if first extent has been used */
+				if (first) {
+					op = &req->r_ops[1];
+					osd_req_op_extent_init(req, 1, CEPH_OSD_OP_SPARSE_READ,
+							last_pos, CEPH_FSCRYPT_BLOCK_SIZE,
+							ci->i_truncate_size,
+							ci->i_truncate_seq);
+				}
+
+				ret = __ceph_alloc_sparse_ext_map(op, 1);
+				if (ret) {
+					ceph_osdc_put_request(req);
+					ceph_release_page_vector(pages, num_pages);
+					break;
+				}
+
+				osd_req_op_extent_osd_data_pages(req, first ? 1 : 0,
+							&pages[num_pages - 1],
+							CEPH_FSCRYPT_BLOCK_SIZE,
+							offset_in_page(last_pos),
+							false, false);
+			}
+
+			ret = ceph_osdc_start_request(osdc, req, false);
+			if (!ret)
+				ret = ceph_osdc_wait_request(osdc, req);
+
+			/* FIXME: length field is wrong if there are 2 extents */
+			ceph_update_read_metrics(&fsc->mdsc->metric,
+						 req->r_start_latency,
+						 req->r_end_latency,
+						 read_len, ret);
+
+			/* Ok if object is not already present */
+			if (ret == -ENOENT) {
+				/*
+				 * If there is no object, then we can't assert
+				 * on its version. Set it to 0, and we'll use an
+				 * exclusive create instead.
+				 */
+				ceph_osdc_put_request(req);
+				assert_ver = 0;
+				ret = 0;
+
+				/*
+				 * zero out the soon-to-be uncopied parts of the
+				 * first and last pages.
+				 */
+				if (first)
+					zero_user_segment(pages[0], 0,
+							  offset_in_page(first_pos));
+				if (last)
+					zero_user_segment(pages[num_pages - 1],
+							  offset_in_page(last_pos),
+							  PAGE_SIZE);
+			} else {
+				if (ret < 0) {
+					ceph_osdc_put_request(req);
+					ceph_release_page_vector(pages, num_pages);
+					break;
+				}
+
+				op = &req->r_ops[0];
+				if (op->extent.sparse_ext_cnt == 0) {
+					if (first)
+						zero_user_segment(pages[0], 0,
+								  offset_in_page(first_pos));
+					else
+						zero_user_segment(pages[num_pages - 1],
+								  offset_in_page(last_pos),
+								  PAGE_SIZE);
+				} else if (op->extent.sparse_ext_cnt != 1 ||
+					   ceph_sparse_ext_map_end(op) !=
+						CEPH_FSCRYPT_BLOCK_SIZE) {
+					ret = -EIO;
+					ceph_osdc_put_request(req);
+					ceph_release_page_vector(pages, num_pages);
+					break;
+				}
+
+				if (first && last) {
+					op = &req->r_ops[1];
+					if (op->extent.sparse_ext_cnt == 0) {
+						zero_user_segment(pages[num_pages - 1],
+								  offset_in_page(last_pos),
+								  PAGE_SIZE);
+					} else if (op->extent.sparse_ext_cnt != 1 ||
+						   ceph_sparse_ext_map_end(op) !=
+							CEPH_FSCRYPT_BLOCK_SIZE) {
+						ret = -EIO;
+						ceph_osdc_put_request(req);
+						ceph_release_page_vector(pages, num_pages);
+						break;
+					}
+				}
+
+				/* Grab assert version. It must be non-zero. */
+				assert_ver = req->r_version;
+				WARN_ON_ONCE(ret > 0 && assert_ver == 0);
+
+				ceph_osdc_put_request(req);
+				if (first) {
+					ret = ceph_fscrypt_decrypt_block_inplace(inode,
+							pages[0],
+							CEPH_FSCRYPT_BLOCK_SIZE,
+							offset_in_page(first_pos),
+							first_pos >> CEPH_FSCRYPT_BLOCK_SHIFT);
+					if (ret < 0) {
+						ceph_release_page_vector(pages, num_pages);
+						break;
+					}
+				}
+				if (last) {
+					ret = ceph_fscrypt_decrypt_block_inplace(inode,
+							pages[num_pages - 1],
+							CEPH_FSCRYPT_BLOCK_SIZE,
+							offset_in_page(last_pos),
+							last_pos >> CEPH_FSCRYPT_BLOCK_SHIFT);
+					if (ret < 0) {
+						ceph_release_page_vector(pages, num_pages);
+						break;
+					}
+				}
+			}
 		}
 
 		left = len;
@@ -1601,43 +1806,98 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		for (n = 0; n < num_pages; n++) {
 			size_t plen = min_t(size_t, left, PAGE_SIZE - off);
 
+			/* copy the data */
 			ret = copy_page_from_iter(pages[n], off, plen, from);
-			off = 0;
 			if (ret != plen) {
 				ret = -EFAULT;
 				break;
 			}
+			off = 0;
 			left -= ret;
 		}
-
 		if (ret < 0) {
+			dout("sync_write write failed with %d\n", ret);
 			ceph_release_page_vector(pages, num_pages);
-			goto out;
+			break;
 		}
 
-		req->r_inode = inode;
+		if (IS_ENCRYPTED(inode)) {
+			ret = ceph_fscrypt_encrypt_pages(inode, pages,
+							 write_pos, write_len,
+							 GFP_KERNEL);
+			if (ret < 0) {
+				dout("encryption failed with %d\n", ret);
+				ceph_release_page_vector(pages, num_pages);
+				break;
+			}
+		}
 
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len,
-						 offset_in_page(pos),
-						 false, true);
+		req = ceph_osdc_new_request(osdc, &ci->i_layout,
+					    ci->i_vino, write_pos, &write_len,
+					    rmw ? 1 : 0, rmw ? 2 : 1,
+					    CEPH_OSD_OP_WRITE,
+					    CEPH_OSD_FLAG_WRITE,
+					    snapc, ci->i_truncate_seq,
+					    ci->i_truncate_size, false);
+		if (IS_ERR(req)) {
+			ret = PTR_ERR(req);
+			ceph_release_page_vector(pages, num_pages);
+			break;
+		}
 
+		dout("sync_write write op %lld~%llu\n", write_pos, write_len);
+		osd_req_op_extent_osd_data_pages(req, rmw ? 1 : 0, pages, write_len,
+						 offset_in_page(write_pos), false,
+						 true);
+		req->r_inode = inode;
 		req->r_mtime = mtime;
-		ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
+
+		/* Set up the assertion */
+		if (rmw) {
+			/*
+			 * Set up the assertion. If we don't have a version number,
+			 * then the object doesn't exist yet. Use an exclusive create
+			 * instead of a version assertion in that case.
+			 */
+			if (assert_ver) {
+				osd_req_op_init(req, 0, CEPH_OSD_OP_ASSERT_VER, 0);
+				req->r_ops[0].assert_ver.ver = assert_ver;
+			} else {
+				osd_req_op_init(req, 0, CEPH_OSD_OP_CREATE,
+						CEPH_OSD_OP_FLAG_EXCL);
+			}
+		}
+
+		ret = ceph_osdc_start_request(osdc, req, false);
 		if (!ret)
-			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+			ret = ceph_osdc_wait_request(osdc, req);
 
 		ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 					  req->r_end_latency, len, ret);
-out:
 		ceph_osdc_put_request(req);
 		if (ret != 0) {
+			dout("sync_write osd write returned %d\n", ret);
+			/* Version changed! Must re-do the rmw cycle */
+			if ((assert_ver && (ret == -ERANGE || ret == -EOVERFLOW)) ||
+			     (!assert_ver && ret == -EEXIST)) {
+				/* We should only ever see this on a rmw */
+				WARN_ON_ONCE(!rmw);
+
+				/* The version should never go backward */
+				WARN_ON_ONCE(ret == -EOVERFLOW);
+
+				*from = saved_iter;
+
+				/* FIXME: limit number of times we loop? */
+				continue;
+			}
 			ceph_set_error_write(ci);
 			break;
 		}
-
 		ceph_clear_error_write(ci);
 		pos += len;
 		written += len;
+		dout("sync_write written %d\n", written);
 		if (pos > i_size_read(inode)) {
 			check_caps = ceph_inode_set_size(inode, pos);
 			if (check_caps)
@@ -1652,6 +1912,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		ret = written;
 		iocb->ki_pos = pos;
 	}
+	dout("sync_write returning %d\n", ret);
 	return ret;
 }
 
Signature · 1 line
2.35.1
#22 lore raw

PATCH v13 22/59 ceph: send altname in MClientRequest

In reply to Jeff Layton

In the event that we have a filename longer than CEPH_NOHASH_NAME_MAX, we'll need to hash the tail of the filename. The client however will still need to know the full name of the file if it has a key.

To support this, the MClientRequest field has grown a new alternate_name field that we populate with the full (binary) crypttext of the filename. This is then transmitted to the clients in readdir or traces as part of the dentry lease.

Add support for populating this field when the filenames are very long.

---
 fs/ceph/mds_client.c | 75 +++++++++++++++++++++++++++++++++++++++++---
 fs/ceph/mds_client.h |  3 ++
 2 files changed, 73 insertions(+), 5 deletions(-)
fs/ceph/mds_client.c +70 -5
index 13367a358a85..0be1668b2c32 100644
@@ -972,6 +972,7 @@ void ceph_mdsc_release_request(struct kref *kref)
 	if (req->r_pagelist)
 		ceph_pagelist_release(req->r_pagelist);
 	kfree(req->r_fscrypt_auth);
+	kfree(req->r_altname);
 	put_request_session(req);
 	ceph_unreserve_caps(req->r_mdsc, &req->r_caps_reservation);
 	WARN_ON_ONCE(!list_empty(&req->r_wait));
@@ -2386,6 +2387,63 @@ static inline  u64 __get_oldest_tid(struct ceph_mds_client *mdsc)
 	return mdsc->oldest_tid;
 }
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
+{
+	struct inode *dir = req->r_parent;
+	struct dentry *dentry = req->r_dentry;
+	u8 *cryptbuf = NULL;
+	u32 len = 0;
+	int ret = 0;
+
+	/* only encode if we have parent and dentry */
+	if (!dir || !dentry)
+		goto success;
+
+	/* No-op unless this is encrypted */
+	if (!IS_ENCRYPTED(dir))
+		goto success;
+
+	ret = __fscrypt_prepare_readdir(dir);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* No key? Just ignore it. */
+	if (!fscrypt_has_encryption_key(dir))
+		goto success;
+
+	if (!fscrypt_fname_encrypted_size(dir, dentry->d_name.len, NAME_MAX, &len)) {
+		WARN_ON_ONCE(1);
+		return ERR_PTR(-ENAMETOOLONG);
+	}
+
+	/* No need to append altname if name is short enough */
+	if (len <= CEPH_NOHASH_NAME_MAX) {
+		len = 0;
+		goto success;
+	}
+
+	cryptbuf = kmalloc(len, GFP_KERNEL);
+	if (!cryptbuf)
+		return ERR_PTR(-ENOMEM);
+
+	ret = fscrypt_fname_encrypt(dir, &dentry->d_name, cryptbuf, len);
+	if (ret) {
+		kfree(cryptbuf);
+		return ERR_PTR(ret);
+	}
+success:
+	*plen = len;
+	return cryptbuf;
+}
+#else
+static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
+{
+	*plen = 0;
+	return NULL;
+}
+#endif
+
 /**
  * ceph_mdsc_build_path - build a path string to a given dentry
  * @dentry: dentry to which path should be built
@@ -2606,14 +2664,15 @@ static void encode_mclientrequest_tail(void **p, const struct ceph_mds_request *
 	ceph_encode_timespec64(&ts, &req->r_stamp);
 	ceph_encode_copy(p, &ts, sizeof(ts));
 
-	/* gid_list */
+	/* v4: gid_list */
 	ceph_encode_32(p, req->r_cred->group_info->ngroups);
 	for (i = 0; i < req->r_cred->group_info->ngroups; i++)
 		ceph_encode_64(p, from_kgid(&init_user_ns,
 					    req->r_cred->group_info->gid[i]));
 
-	/* v5: altname (TODO: skip for now) */
-	ceph_encode_32(p, 0);
+	/* v5: altname */
+	ceph_encode_32(p, req->r_altname_len);
+	ceph_encode_copy(p, req->r_altname, req->r_altname_len);
 
 	/* v6: fscrypt_auth and fscrypt_file */
 	if (req->r_fscrypt_auth) {
@@ -2669,7 +2728,13 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		goto out_free1;
 	}
 
-	/* head */
+	req->r_altname = get_fscrypt_altname(req, &req->r_altname_len);
+	if (IS_ERR(req->r_altname)) {
+		msg = ERR_CAST(req->r_altname);
+		req->r_altname = NULL;
+		goto out_free2;
+	}
+
 	len = legacy ? sizeof(*head) : sizeof(struct ceph_mds_request_head);
 
 	/* filepaths */
@@ -2695,7 +2760,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	len += sizeof(u32) + (sizeof(u64) * req->r_cred->group_info->ngroups);
 
 	/* alternate name */
-	len += sizeof(u32);	// TODO
+	len += sizeof(u32) + req->r_altname_len;
 
 	/* fscrypt_auth */
 	len += sizeof(u32); // fscrypt_auth
fs/ceph/mds_client.h +3 -0
index 2cc75f9ae7c7..cd719691a86d 100644
@@ -290,6 +290,9 @@ struct ceph_mds_request {
 
 	struct ceph_fscrypt_auth *r_fscrypt_auth;
 
+	u8 *r_altname;		    /* fscrypt binary crypttext for long filenames */
+	u32 r_altname_len;	    /* length of r_altname */
+
 	int r_fmode;        /* file mode, if expecting cap */
 	int r_request_release_offset;
 	const struct cred *r_cred;
Signature · 1 line
2.35.1
#39 lore raw

PATCH v13 39/59 ceph: size handling for encrypted inodes in cap updates

In reply to Jeff Layton

Transmit the rounded-up size as the normal size, and fill out the fscrypt_file field with the real file size.

---
 fs/ceph/caps.c   | 43 +++++++++++++++++++++++++------------------
 fs/ceph/crypto.h |  4 ++++
 2 files changed, 29 insertions(+), 18 deletions(-)
fs/ceph/caps.c +25 -18
index 22bf3e2696cb..cb5cdf2260ad 100644
@@ -1215,10 +1215,9 @@ struct cap_msg_args {
 	umode_t			mode;
 	bool			inline_data;
 	bool			wake;
+	bool			encrypted;
 	u32			fscrypt_auth_len;
-	u32			fscrypt_file_len;
 	u8			fscrypt_auth[sizeof(struct ceph_fscrypt_auth)]; // for context
-	u8			fscrypt_file[sizeof(u64)]; // for size
 };
 
 /* Marshal up the cap msg to the MDS */
@@ -1253,7 +1252,12 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 	fc->ino = cpu_to_le64(arg->ino);
 	fc->snap_follows = cpu_to_le64(arg->follows);
 
-	fc->size = cpu_to_le64(arg->size);
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	if (arg->encrypted)
+		fc->size = cpu_to_le64(round_up(arg->size, CEPH_FSCRYPT_BLOCK_SIZE));
+	else
+#endif
+		fc->size = cpu_to_le64(arg->size);
 	fc->max_size = cpu_to_le64(arg->max_size);
 	ceph_encode_timespec64(&fc->mtime, &arg->mtime);
 	ceph_encode_timespec64(&fc->atime, &arg->atime);
@@ -1313,11 +1317,17 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 	ceph_encode_64(&p, 0);
 
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-	/* fscrypt_auth and fscrypt_file (version 12) */
+	/*
+	 * fscrypt_auth and fscrypt_file (version 12)
+	 *
+	 * fscrypt_auth holds the crypto context (if any). fscrypt_file
+	 * tracks the real i_size as an __le64 field (and we use a rounded-up
+	 * i_size in * the traditional size field).
+	 */
 	ceph_encode_32(&p, arg->fscrypt_auth_len);
 	ceph_encode_copy(&p, arg->fscrypt_auth, arg->fscrypt_auth_len);
-	ceph_encode_32(&p, arg->fscrypt_file_len);
-	ceph_encode_copy(&p, arg->fscrypt_file, arg->fscrypt_file_len);
+	ceph_encode_32(&p, sizeof(__le64));
+	ceph_encode_64(&p, arg->size);
 #else /* CONFIG_FS_ENCRYPTION */
 	ceph_encode_32(&p, 0);
 	ceph_encode_32(&p, 0);
@@ -1389,7 +1399,6 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 	arg->follows = flushing ? ci->i_head_snapc->seq : 0;
 	arg->flush_tid = flush_tid;
 	arg->oldest_flush_tid = oldest_flush_tid;
-
 	arg->size = i_size_read(inode);
 	ci->i_reported_size = arg->size;
 	arg->max_size = ci->i_wanted_max_size;
@@ -1443,6 +1452,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 		}
 	}
 	arg->flags = flags;
+	arg->encrypted = IS_ENCRYPTED(inode);
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
 	if (ci->fscrypt_auth_len &&
 	    WARN_ON_ONCE(ci->fscrypt_auth_len > sizeof(struct ceph_fscrypt_auth))) {
@@ -1453,21 +1463,21 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 		memcpy(arg->fscrypt_auth, ci->fscrypt_auth,
 			min_t(size_t, ci->fscrypt_auth_len, sizeof(arg->fscrypt_auth)));
 	}
-	/* FIXME: use this to track "real" size */
-	arg->fscrypt_file_len = 0;
 #endif /* CONFIG_FS_ENCRYPTION */
 }
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
 #define CAP_MSG_FIXED_FIELDS (sizeof(struct ceph_mds_caps) + \
-		      4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 4 + 8 + 8 + 4 + 4)
+		      4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 4 + 8 + 8 + 4 + 4 + 8)
 
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
 static inline int cap_msg_size(struct cap_msg_args *arg)
 {
-	return CAP_MSG_FIXED_FIELDS + arg->fscrypt_auth_len +
-			arg->fscrypt_file_len;
+	return CAP_MSG_FIXED_FIELDS + arg->fscrypt_auth_len;
 }
 #else
+#define CAP_MSG_FIXED_FIELDS (sizeof(struct ceph_mds_caps) + \
+		      4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 4 + 8 + 8 + 4 + 4)
+
 static inline int cap_msg_size(struct cap_msg_args *arg)
 {
 	return CAP_MSG_FIXED_FIELDS;
@@ -1546,13 +1556,10 @@ static inline int __send_flush_snap(struct inode *inode,
 	arg.inline_data = capsnap->inline_data;
 	arg.flags = 0;
 	arg.wake = false;
+	arg.encrypted = IS_ENCRYPTED(inode);
 
-	/*
-	 * No fscrypt_auth changes from a capsnap. It will need
-	 * to update fscrypt_file on size changes (TODO).
-	 */
+	/* No fscrypt_auth changes from a capsnap.*/
 	arg.fscrypt_auth_len = 0;
-	arg.fscrypt_file_len = 0;
 
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, cap_msg_size(&arg),
 			   GFP_NOFS, false);
fs/ceph/crypto.h +4 -0
index 080905b0c73c..56a61ba64edc 100644
@@ -9,6 +9,10 @@
 #include <crypto/sha2.h>
 #include <linux/fscrypt.h>
 
+#define CEPH_FSCRYPT_BLOCK_SHIFT   12
+#define CEPH_FSCRYPT_BLOCK_SIZE    (_AC(1, UL) << CEPH_FSCRYPT_BLOCK_SHIFT)
+#define CEPH_FSCRYPT_BLOCK_MASK	   (~(CEPH_FSCRYPT_BLOCK_SIZE-1))
+
 struct ceph_fs_client;
 struct ceph_acl_sec_ctx;
 struct ceph_mds_request;
Signature · 1 line
2.35.1
#13 lore raw

PATCH v13 13/59 ceph: fscrypt_auth handling for ceph

In reply to Jeff Layton

Most fscrypt-enabled filesystems store the crypto context in an xattr, but that's problematic for ceph as xatts are governed by the XATTR cap, but we really want the crypto context as part of the AUTH cap.

Because of this, the MDS has added two new inode metadata fields:
fscrypt_auth and fscrypt_file. The former is used to hold the crypto context, and the latter is used to track the real file size.

Parse new fscrypt_auth and fscrypt_file fields in inode traces. For now, we don't use fscrypt_file, but fscrypt_auth is used to hold the fscrypt context.

Allow the client to use a setattr request for setting the fscrypt_auth field. Since this is not a standard setattr request from the VFS, we add a new field to __ceph_setattr that carries ceph-specific inode attrs.

Have the set_context op do a setattr that sets the fscrypt_auth value, and get_context just return the contents of that field (since it should always be available).

---
 fs/ceph/Makefile             |   1 +
 fs/ceph/acl.c                |   4 +-
 fs/ceph/crypto.c             |  76 ++++++++++++++++++++++++
 fs/ceph/crypto.h             |  36 ++++++++++++
 fs/ceph/inode.c              |  62 ++++++++++++++++++-
 fs/ceph/mds_client.c         | 111 ++++++++++++++++++++++++++++++++---
 fs/ceph/mds_client.h         |   7 +++
 fs/ceph/super.c              |   3 +
 fs/ceph/super.h              |  14 ++++-
 include/linux/ceph/ceph_fs.h |  21 ++++---
 10 files changed, 313 insertions(+), 22 deletions(-)
 create mode 100644 fs/ceph/crypto.c
 create mode 100644 fs/ceph/crypto.h
fs/ceph/Makefile +1 -0
index 50c635dc7f71..1f77ca04c426 100644
@@ -12,3 +12,4 @@ ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
 
 ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
 ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o
+ceph-$(CONFIG_FS_ENCRYPTION) += crypto.o
fs/ceph/acl.c +2 -2
index f4fc8e0b847c..427724c36316 100644
@@ -139,7 +139,7 @@ int ceph_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		newattrs.ia_ctime = current_time(inode);
 		newattrs.ia_mode = new_mode;
 		newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-		ret = __ceph_setattr(inode, &newattrs);
+		ret = __ceph_setattr(inode, &newattrs, NULL);
 		if (ret)
 			goto out_free;
 	}
@@ -150,7 +150,7 @@ int ceph_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 			newattrs.ia_ctime = old_ctime;
 			newattrs.ia_mode = old_mode;
 			newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-			__ceph_setattr(inode, &newattrs);
+			__ceph_setattr(inode, &newattrs, NULL);
 		}
 		goto out_free;
 	}
fs/ceph/crypto.c new file +76 -0

76 lines not on this page · raw message

fs/ceph/crypto.h new file +36 -0
new file mode 100644
index 000000000000..6dca674f79b8
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ceph fscrypt functionality
+ */
+
+#ifndef _CEPH_CRYPTO_H
+#define _CEPH_CRYPTO_H
+
+#include <linux/fscrypt.h>
+
+struct ceph_fscrypt_auth {
+	__le32	cfa_version;
+	__le32	cfa_blob_len;
+	u8	cfa_blob[FSCRYPT_SET_CONTEXT_MAX_SIZE];
+} __packed;
+
+#define CEPH_FSCRYPT_AUTH_VERSION	1
+static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa)
+{
+	u32 ctxsize = le32_to_cpu(fa->cfa_blob_len);
+
+	return offsetof(struct ceph_fscrypt_auth, cfa_blob) + ctxsize;
+}
+
+#ifdef CONFIG_FS_ENCRYPTION
+void ceph_fscrypt_set_ops(struct super_block *sb);
+
+#else /* CONFIG_FS_ENCRYPTION */
+
+static inline void ceph_fscrypt_set_ops(struct super_block *sb)
+{
+}
+
+#endif /* CONFIG_FS_ENCRYPTION */
+
+#endif
fs/ceph/inode.c +60 -2

120 lines not on this page · raw message

fs/ceph/mds_client.c +102 -9

183 lines not on this page · raw message

fs/ceph/mds_client.h +7 -0
index 2e945979a2e0..aab3ab284fce 100644
@@ -88,6 +88,10 @@ struct ceph_mds_reply_info_in {
 	s32 dir_pin;
 	struct ceph_timespec btime;
 	struct ceph_timespec snap_btime;
+	u8 *fscrypt_auth;
+	u8 *fscrypt_file;
+	u32 fscrypt_auth_len;
+	u32 fscrypt_file_len;
 	u64 rsnaps;
 	u64 change_attr;
 };
@@ -280,6 +284,9 @@ struct ceph_mds_request {
 	struct mutex r_fill_mutex;
 
 	union ceph_mds_request_args r_args;
+
+	struct ceph_fscrypt_auth *r_fscrypt_auth;
+
 	int r_fmode;        /* file mode, if expecting cap */
 	int r_request_release_offset;
 	const struct cred *r_cred;
fs/ceph/super.c +3 -0
index 26d924dda721..1f52fc5b89bd 100644
@@ -20,6 +20,7 @@
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
+#include "crypto.h"
 
 #include <linux/ceph/ceph_features.h>
 #include <linux/ceph/decode.h>
@@ -1129,6 +1130,8 @@ static int ceph_set_super(struct super_block *s, struct fs_context *fc)
 	s->s_time_min = 0;
 	s->s_time_max = U32_MAX;
 
+	ceph_fscrypt_set_ops(s);
+
 	ret = set_anon_super_fc(s, fc);
 	if (ret != 0)
 		fsc->sb = NULL;
fs/ceph/super.h +13 -1
index 9eaaab34baae..a4dc7b81a6a4 100644
@@ -434,6 +434,13 @@ struct ceph_inode_info {
 
 	struct work_struct i_work;
 	unsigned long  i_work_mask;
+
+#ifdef CONFIG_FS_ENCRYPTION
+	u32 fscrypt_auth_len;
+	u32 fscrypt_file_len;
+	u8 *fscrypt_auth;
+	u8 *fscrypt_file;
+#endif
 };
 
 static inline struct ceph_inode_info *
@@ -1038,7 +1045,12 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
 }
 extern int ceph_permission(struct user_namespace *mnt_userns,
 			   struct inode *inode, int mask);
-extern int __ceph_setattr(struct inode *inode, struct iattr *attr);
+
+struct ceph_iattr {
+	struct ceph_fscrypt_auth	*fscrypt_auth;
+};
+
+extern int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *cia);
 extern int ceph_setattr(struct user_namespace *mnt_userns,
 			struct dentry *dentry, struct iattr *attr);
 extern int ceph_getattr(struct user_namespace *mnt_userns,
include/linux/ceph/ceph_fs.h +13 -8
index 86bf82dbd8b8..2810b214fa3f 100644
@@ -359,14 +359,19 @@ enum {
 
 extern const char *ceph_mds_op_name(int op);
 
-
-#define CEPH_SETATTR_MODE   1
-#define CEPH_SETATTR_UID    2
-#define CEPH_SETATTR_GID    4
-#define CEPH_SETATTR_MTIME  8
-#define CEPH_SETATTR_ATIME 16
-#define CEPH_SETATTR_SIZE  32
-#define CEPH_SETATTR_CTIME 64
+#define CEPH_SETATTR_MODE              (1 << 0)
+#define CEPH_SETATTR_UID               (1 << 1)
+#define CEPH_SETATTR_GID               (1 << 2)
+#define CEPH_SETATTR_MTIME             (1 << 3)
+#define CEPH_SETATTR_ATIME             (1 << 4)
+#define CEPH_SETATTR_SIZE              (1 << 5)
+#define CEPH_SETATTR_CTIME             (1 << 6)
+#define CEPH_SETATTR_MTIME_NOW         (1 << 7)
+#define CEPH_SETATTR_ATIME_NOW         (1 << 8)
+#define CEPH_SETATTR_BTIME             (1 << 9)
+#define CEPH_SETATTR_KILL_SGUID        (1 << 10)
+#define CEPH_SETATTR_FSCRYPT_AUTH      (1 << 11)
+#define CEPH_SETATTR_FSCRYPT_FILE      (1 << 12)
 
 /*
  * Ceph setxattr request flags.
Signature · 1 line
2.35.1
#35 lore raw

PATCH v13 35/59 ceph: add a new ceph.fscrypt.auth vxattr

In reply to Jeff Layton

Give the client a way to get at the xattr from userland, mostly for future debugging purposes.

---
 fs/ceph/xattr.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)
fs/ceph/xattr.c +26 -0
index 58628cef4207..e080116608b2 100644
@@ -352,6 +352,23 @@ static ssize_t ceph_vxattrcb_auth_mds(struct ceph_inode_info *ci,
 	return ret;
 }
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+static bool ceph_vxattrcb_fscrypt_auth_exists(struct ceph_inode_info *ci)
+{
+	return ci->fscrypt_auth_len;
+}
+
+static ssize_t ceph_vxattrcb_fscrypt_auth(struct ceph_inode_info *ci, char *val, size_t size)
+{
+	if (size) {
+		if (size < ci->fscrypt_auth_len)
+			return -ERANGE;
+		memcpy(val, ci->fscrypt_auth, ci->fscrypt_auth_len);
+	}
+	return ci->fscrypt_auth_len;
+}
+#endif /* CONFIG_FS_ENCRYPTION */
+
 #define CEPH_XATTR_NAME(_type, _name)	XATTR_CEPH_PREFIX #_type "." #_name
 #define CEPH_XATTR_NAME2(_type, _name, _name2)	\
 	XATTR_CEPH_PREFIX #_type "." #_name "." #_name2
@@ -500,6 +517,15 @@ static struct ceph_vxattr ceph_common_vxattrs[] = {
 		.exists_cb = NULL,
 		.flags = VXATTR_FLAG_READONLY,
 	},
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	{
+		.name = "ceph.fscrypt.auth",
+		.name_size = sizeof("ceph.fscrypt.auth"),
+		.getxattr_cb = ceph_vxattrcb_fscrypt_auth,
+		.exists_cb = ceph_vxattrcb_fscrypt_auth_exists,
+		.flags = VXATTR_FLAG_READONLY,
+	},
+#endif /* CONFIG_FS_ENCRYPTION */
 	{ .name = NULL, 0 }	/* Required table terminator */
 };
 
Signature · 1 line
2.35.1
#10 lore raw

PATCH v13 10/59 fscrypt: export fscrypt_fname_encrypt and fscrypt_fname_encrypted_size

In reply to Jeff Layton

For ceph, we want to use our own scheme for handling filenames that are are longer than NAME_MAX after encryption and Base64 encoding. This allows us to have a consistent view of the encrypted filenames for clients that don't support fscrypt and clients that do but that don't have the key.

Currently, fs/crypto only supports encrypting filenames using fscrypt_setup_filename, but that also handles encoding nokey names. Ceph can't use that because it handles nokey names in a different way.

Export fscrypt_fname_encrypt. Rename fscrypt_fname_encrypted_size to __fscrypt_fname_encrypted_size and add a new wrapper called fscrypt_fname_encrypted_size that takes an inode argument rather than a pointer to a fscrypt_policy union.

---
 fs/crypto/fname.c           | 36 ++++++++++++++++++++++++++++++------
 fs/crypto/fscrypt_private.h |  9 +++------
 fs/crypto/hooks.c           |  6 +++---
 include/linux/fscrypt.h     |  4 ++++
 4 files changed, 40 insertions(+), 15 deletions(-)
fs/crypto/fname.c +30 -6
index 1e4233c95005..77d38188a168 100644
@@ -79,7 +79,8 @@ static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
 /**
  * fscrypt_fname_encrypt() - encrypt a filename
  * @inode: inode of the parent directory (for regular filenames)
- *	   or of the symlink (for symlink targets)
+ *	   or of the symlink (for symlink targets). Key must already be
+ *	   set up.
  * @iname: the filename to encrypt
  * @out: (output) the encrypted filename
  * @olen: size of the encrypted filename.  It must be at least @iname->len.
@@ -130,6 +131,7 @@ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(fscrypt_fname_encrypt);
 
 /**
  * fname_decrypt() - decrypt a filename
@@ -257,9 +259,9 @@ int fscrypt_base64url_decode(const char *src, int srclen, u8 *dst)
 }
 EXPORT_SYMBOL_GPL(fscrypt_base64url_decode);
 
-bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
-				  u32 orig_len, u32 max_len,
-				  u32 *encrypted_len_ret)
+bool __fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
+				    u32 orig_len, u32 max_len,
+				    u32 *encrypted_len_ret)
 {
 	int padding = 4 << (fscrypt_policy_flags(policy) &
 			    FSCRYPT_POLICY_FLAGS_PAD_MASK);
@@ -273,6 +275,29 @@ bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
 	return true;
 }
 
+/**
+ * fscrypt_fname_encrypted_size() - calculate length of encrypted filename
+ * @inode:		parent inode of dentry name being encrypted. Key must
+ *			already be set up.
+ * @orig_len:		length of the original filename
+ * @max_len:		maximum length to return
+ * @encrypted_len_ret:	where calculated length should be returned (on success)
+ *
+ * Filenames that are shorter than the maximum length may have their lengths
+ * increased slightly by encryption, due to padding that is applied.
+ *
+ * Return: false if the orig_len is greater than max_len. Otherwise, true and
+ *	   fill out encrypted_len_ret with the length (up to max_len).
+ */
+bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
+				  u32 max_len, u32 *encrypted_len_ret)
+{
+	return __fscrypt_fname_encrypted_size(&inode->i_crypt_info->ci_policy,
+					      orig_len, max_len,
+					      encrypted_len_ret);
+}
+EXPORT_SYMBOL_GPL(fscrypt_fname_encrypted_size);
+
 /**
  * fscrypt_fname_alloc_buffer() - allocate a buffer for presented filenames
  * @max_encrypted_len: maximum length of encrypted filenames the buffer will be
@@ -428,8 +453,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		return ret;
 
 	if (fscrypt_has_encryption_key(dir)) {
-		if (!fscrypt_fname_encrypted_size(&dir->i_crypt_info->ci_policy,
-						  iname->len, NAME_MAX,
+		if (!fscrypt_fname_encrypted_size(dir, iname->len, NAME_MAX,
 						  &fname->crypto_buf.len))
 			return -ENAMETOOLONG;
 		fname->crypto_buf.name = kmalloc(fname->crypto_buf.len,
fs/crypto/fscrypt_private.h +3 -6
index 5b0a9e6478b5..f3e6e566daff 100644
@@ -297,14 +297,11 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
 			 const struct fscrypt_info *ci);
 
 /* fname.c */
-int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
-			  u8 *out, unsigned int olen);
-bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
-				  u32 orig_len, u32 max_len,
-				  u32 *encrypted_len_ret);
+bool __fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
+				    u32 orig_len, u32 max_len,
+				    u32 *encrypted_len_ret);
 
 /* hkdf.c */
-
 struct fscrypt_hkdf {
 	struct crypto_shash *hmac_tfm;
 };
fs/crypto/hooks.c +3 -3
index af74599ae1cf..7c01025879b3 100644
@@ -228,9 +228,9 @@ int fscrypt_prepare_symlink(struct inode *dir, const char *target,
 	 * counting it (even though it is meaningless for ciphertext) is simpler
 	 * for now since filesystems will assume it is there and subtract it.
 	 */
-	if (!fscrypt_fname_encrypted_size(policy, len,
-					  max_len - sizeof(struct fscrypt_symlink_data),
-					  &disk_link->len))
+	if (!__fscrypt_fname_encrypted_size(policy, len,
+					    max_len - sizeof(struct fscrypt_symlink_data),
+					    &disk_link->len))
 		return -ENAMETOOLONG;
 	disk_link->len += sizeof(struct fscrypt_symlink_data);
 
include/linux/fscrypt.h +4 -0
index 629ccd09e095..84b363665162 100644
@@ -308,8 +308,12 @@ void fscrypt_free_inode(struct inode *inode);
 int fscrypt_drop_inode(struct inode *inode);
 
 /* fname.c */
+int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
+			  u8 *out, unsigned int olen);
 int fscrypt_base64url_encode(const u8 *src, int len, char *dst);
 int fscrypt_base64url_decode(const char *src, int len, u8 *dst);
+bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
+				  u32 max_len, u32 *encrypted_len_ret);
 int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname,
 			   int lookup, struct fscrypt_name *fname);
 
Signature · 1 line
2.35.1
#12 lore raw

PATCH v13 12/59 ceph: preallocate inode for ops that may create one

In reply to Jeff Layton

When creating a new inode, we need to determine the crypto context before we can transmit the RPC. The fscrypt API has a routine for getting a crypto context before a create occurs, but it requires an inode.

Change the ceph code to preallocate an inode in advance of a create of any sort (open(), mknod(), symlink(), etc). Move the existing code that generates the ACL and SELinux blobs into this routine since that's mostly common across all the different codepaths.

In most cases, we just want to allow ceph_fill_trace to use that inode after the reply comes in, so add a new field to the MDS request for it (r_new_inode).

The async create codepath is a bit different though. In that case, we want to hash the inode in advance of the RPC so that it can be used before the reply comes in. If the call subsequently fails with -EJUKEBOX, then just put the references and clean up the as_ctx. Note that with this change, we now need to regenerate the as_ctx when this occurs, but it's quite rare for it to happen.

---
 fs/ceph/dir.c        | 70 ++++++++++++++++++++-----------------
 fs/ceph/file.c       | 62 ++++++++++++++++++++-------------
 fs/ceph/inode.c      | 82 ++++++++++++++++++++++++++++++++++++++++----
 fs/ceph/mds_client.c | 13 +++++--
 fs/ceph/mds_client.h |  1 +
 fs/ceph/super.h      |  7 +++-
 6 files changed, 169 insertions(+), 66 deletions(-)
fs/ceph/dir.c +38 -32
index eae417d71136..8cc7a49ee508 100644
@@ -861,13 +861,6 @@ static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir,
 		goto out;
 	}
 
-	err = ceph_pre_init_acls(dir, &mode, &as_ctx);
-	if (err < 0)
-		goto out;
-	err = ceph_security_init_secctx(dentry, mode, &as_ctx);
-	if (err < 0)
-		goto out;
-
 	dout("mknod in dir %p dentry %p mode 0%ho rdev %d\n",
 	     dir, dentry, mode, rdev);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_MKNOD, USE_AUTH_MDS);
@@ -875,6 +868,14 @@ static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir,
 		err = PTR_ERR(req);
 		goto out;
 	}
+
+	req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+	if (IS_ERR(req->r_new_inode)) {
+		err = PTR_ERR(req->r_new_inode);
+		req->r_new_inode = NULL;
+		goto out_req;
+	}
+
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	req->r_parent = dir;
@@ -884,13 +885,13 @@ static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir,
 	req->r_args.mknod.rdev = cpu_to_le32(rdev);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
-	if (as_ctx.pagelist) {
-		req->r_pagelist = as_ctx.pagelist;
-		as_ctx.pagelist = NULL;
-	}
+
+	ceph_as_ctx_to_req(req, &as_ctx);
+
 	err = ceph_mdsc_do_request(mdsc, dir, req);
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
+out_req:
 	ceph_mdsc_put_request(req);
 out:
 	if (!err)
@@ -913,6 +914,7 @@ static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
 	struct ceph_mds_request *req;
 	struct ceph_acl_sec_ctx as_ctx = {};
+	umode_t mode = S_IFLNK | 0777;
 	int err;
 
 	if (ceph_snap(dir) != CEPH_NOSNAP)
@@ -923,21 +925,24 @@ static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 		goto out;
 	}
 
-	err = ceph_security_init_secctx(dentry, S_IFLNK | 0777, &as_ctx);
-	if (err < 0)
-		goto out;
-
 	dout("symlink in dir %p dentry %p to '%s'\n", dir, dentry, dest);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SYMLINK, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out;
 	}
+
+	req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+	if (IS_ERR(req->r_new_inode)) {
+		err = PTR_ERR(req->r_new_inode);
+		req->r_new_inode = NULL;
+		goto out_req;
+	}
+
 	req->r_path2 = kstrdup(dest, GFP_KERNEL);
 	if (!req->r_path2) {
 		err = -ENOMEM;
-		ceph_mdsc_put_request(req);
-		goto out;
+		goto out_req;
 	}
 	req->r_parent = dir;
 	ihold(dir);
@@ -947,13 +952,13 @@ static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	req->r_num_caps = 2;
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
-	if (as_ctx.pagelist) {
-		req->r_pagelist = as_ctx.pagelist;
-		as_ctx.pagelist = NULL;
-	}
+
+	ceph_as_ctx_to_req(req, &as_ctx);
+
 	err = ceph_mdsc_do_request(mdsc, dir, req);
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
+out_req:
 	ceph_mdsc_put_request(req);
 out:
 	if (err)
@@ -989,13 +994,6 @@ static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 		goto out;
 	}
 
-	mode |= S_IFDIR;
-	err = ceph_pre_init_acls(dir, &mode, &as_ctx);
-	if (err < 0)
-		goto out;
-	err = ceph_security_init_secctx(dentry, mode, &as_ctx);
-	if (err < 0)
-		goto out;
 
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
@@ -1003,6 +1001,14 @@ static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 		goto out;
 	}
 
+	mode |= S_IFDIR;
+	req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+	if (IS_ERR(req->r_new_inode)) {
+		err = PTR_ERR(req->r_new_inode);
+		req->r_new_inode = NULL;
+		goto out_req;
+	}
+
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	req->r_parent = dir;
@@ -1011,15 +1017,15 @@ static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 	req->r_args.mkdir.mode = cpu_to_le32(mode);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
-	if (as_ctx.pagelist) {
-		req->r_pagelist = as_ctx.pagelist;
-		as_ctx.pagelist = NULL;
-	}
+
+	ceph_as_ctx_to_req(req, &as_ctx);
+
 	err = ceph_mdsc_do_request(mdsc, dir, req);
 	if (!err &&
 	    !req->r_reply_info.head->is_target &&
 	    !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
+out_req:
 	ceph_mdsc_put_request(req);
 out:
 	if (!err)
fs/ceph/file.c +38 -24

134 lines not on this page · raw message

fs/ceph/inode.c +75 -7

113 lines not on this page · raw message

fs/ceph/mds_client.c +11 -2
index f476c65fb985..7aa253be7edc 100644
@@ -868,6 +868,7 @@ void ceph_mdsc_release_request(struct kref *kref)
 		iput(req->r_parent);
 	}
 	iput(req->r_target_inode);
+	iput(req->r_new_inode);
 	if (req->r_dentry)
 		dput(req->r_dentry);
 	if (req->r_old_dentry)
@@ -3208,13 +3209,21 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 	/* Must find target inode outside of mutexes to avoid deadlocks */
 	if ((err >= 0) && rinfo->head->is_target) {
-		struct inode *in;
+		struct inode *in = xchg(&req->r_new_inode, NULL);
 		struct ceph_vino tvino = {
 			.ino  = le64_to_cpu(rinfo->targeti.in->ino),
 			.snap = le64_to_cpu(rinfo->targeti.in->snapid)
 		};
 
-		in = ceph_get_inode(mdsc->fsc->sb, tvino);
+		/* If we ended up opening an existing inode, discard r_new_inode */
+		if (req->r_op == CEPH_MDS_OP_CREATE && !req->r_reply_info.has_create_ino) {
+			/* This should never happen on an async create */
+			WARN_ON_ONCE(req->r_deleg_ino);
+			iput(in);
+			in = NULL;
+		}
+
+		in = ceph_get_inode(mdsc->fsc->sb, tvino, in);
 		if (IS_ERR(in)) {
 			err = PTR_ERR(in);
 			mutex_lock(&session->s_mutex);
fs/ceph/mds_client.h +1 -0
index 33497846e47e..2e945979a2e0 100644
@@ -265,6 +265,7 @@ struct ceph_mds_request {
 
 	struct inode *r_parent;		    /* parent dir inode */
 	struct inode *r_target_inode;       /* resulting inode */
+	struct inode *r_new_inode;	    /* new inode (for creates) */
 
 #define CEPH_MDS_R_DIRECT_IS_HASH	(1) /* r_direct_hash is valid */
 #define CEPH_MDS_R_ABORTED		(2) /* call was aborted */
fs/ceph/super.h +6 -1
index 80a2399f2878..9eaaab34baae 100644
@@ -967,6 +967,7 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
 /* inode.c */
 struct ceph_mds_reply_info_in;
 struct ceph_mds_reply_dirfrag;
+struct ceph_acl_sec_ctx;
 
 extern const struct inode_operations ceph_file_iops;
 
@@ -974,8 +975,12 @@ extern struct inode *ceph_alloc_inode(struct super_block *sb);
 extern void ceph_evict_inode(struct inode *inode);
 extern void ceph_free_inode(struct inode *inode);
 
+struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
+			     umode_t *mode, struct ceph_acl_sec_ctx *as_ctx);
+void ceph_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_sec_ctx *as_ctx);
+
 extern struct inode *ceph_get_inode(struct super_block *sb,
-				    struct ceph_vino vino);
+				    struct ceph_vino vino, struct inode *newino);
 extern struct inode *ceph_get_snapdir(struct inode *parent);
 extern int ceph_fill_file_size(struct inode *inode, int issued,
 			       u32 truncate_seq, u64 truncate_size, u64 size);
Signature · 1 line
2.35.1
#57 lore raw

PATCH v13 57/59 ceph: set i_blkbits to crypto block size for encrypted inodes

In reply to Jeff Layton

Some of the underlying infrastructure for fscrypt relies on i_blkbits being aligned to the crypto blocksize.

---
 fs/ceph/inode.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)
fs/ceph/inode.c +9 -7
index eb8f066975a8..45ca4e598ef0 100644
@@ -976,13 +976,6 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 	issued |= __ceph_caps_dirty(ci);
 	new_issued = ~issued & info_caps;
 
-	/* directories have fl_stripe_unit set to zero */
-	if (le32_to_cpu(info->layout.fl_stripe_unit))
-		inode->i_blkbits =
-			fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
-	else
-		inode->i_blkbits = CEPH_BLOCK_SHIFT;
-
 	__ceph_update_quota(ci, iinfo->max_bytes, iinfo->max_files);
 
 #ifdef CONFIG_FS_ENCRYPTION
@@ -1008,6 +1001,15 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 		ceph_decode_timespec64(&ci->i_snap_btime, &iinfo->snap_btime);
 	}
 
+	/* directories have fl_stripe_unit set to zero */
+	if (IS_ENCRYPTED(inode))
+		inode->i_blkbits = CEPH_FSCRYPT_BLOCK_SHIFT;
+	else if (le32_to_cpu(info->layout.fl_stripe_unit))
+		inode->i_blkbits =
+			fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+	else
+		inode->i_blkbits = CEPH_BLOCK_SHIFT;
+
 	if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) &&
 	    (issued & CEPH_CAP_LINK_EXCL) == 0)
 		set_nlink(inode, le32_to_cpu(info->nlink));
Signature · 1 line
2.35.1
#48 lore raw

PATCH v13 48/59 ceph: add truncate size handling support for fscrypt

In reply to Jeff Layton

From: Xiubo Li <[email protected]>

This will transfer the encrypted last block contents to the MDS along with the truncate request only when the new size is smaller and not aligned to the fscrypt BLOCK size. When the last block is located in the file hole, the truncate request will only contain the header.

The MDS could fail to do the truncate if there has another client or process has already updated the RADOS object which contains the last block, and will return -EAGAIN, then the kclient needs to retry it. The RMW will take around 50ms, and will let it retry 20 times for now.

---
 fs/ceph/crypto.h |  21 ++++++
 fs/ceph/inode.c  | 192 +++++++++++++++++++++++++++++++++++++++++++++--
 fs/ceph/super.h  |   5 ++
 3 files changed, 211 insertions(+), 7 deletions(-)
fs/ceph/crypto.h +21 -0
index fdd73c50487f..92a7b221a975 100644
@@ -26,6 +26,27 @@ struct ceph_fname {
 	bool		no_copy;
 };
 
+/*
+ * Header for the crypted file when truncating the size, this
+ * will be sent to MDS, and the MDS will update the encrypted
+ * last block and then truncate the size.
+ */
+struct ceph_fscrypt_truncate_size_header {
+	__u8  ver;
+	__u8  compat;
+
+	/*
+	 * It will be sizeof(assert_ver + file_offset + block_size)
+	 * if the last block is empty when it's located in a file
+	 * hole. Or the data_len will plus CEPH_FSCRYPT_BLOCK_SIZE.
+	 */
+	__le32 data_len;
+
+	__le64 change_attr;
+	__le64 file_offset;
+	__le32 block_size;
+} __packed;
+
 struct ceph_fscrypt_auth {
 	__le32	cfa_version;
 	__le32	cfa_blob_len;
fs/ceph/inode.c +185 -7

268 lines not on this page · raw message

fs/ceph/super.h +5 -0
index 9c205c6967b7..a2e1c83ab29a 100644
@@ -410,6 +410,11 @@ struct ceph_inode_info {
 	u32 i_truncate_seq;        /* last truncate to smaller size */
 	u64 i_truncate_size;       /*  and the size we last truncated down to */
 	int i_truncate_pending;    /*  still need to call vmtruncate */
+	/*
+	 * For none fscrypt case it equals to i_truncate_size or it will
+	 * equals to fscrypt_file_size
+	 */
+	u64 i_truncate_pagecache_size;
 
 	u64 i_max_size;            /* max file size authorized by mds */
 	u64 i_reported_size; /* (max_)size reported to or requested of mds */
Signature · 1 line
2.35.1
#9 lore raw

PATCH v13 9/59 fscrypt: export fscrypt_base64url_encode and fscrypt_base64url_decode

In reply to Jeff Layton

Ceph is going to add fscrypt support, but we still want encrypted filenames to be composed of printable characters, so we can maintain compatibility with clients that don't support fscrypt.

We could just adopt fscrypt's current nokey name format, but that is subject to change in the future, and it also contains dirhash fields that we don't need for cephfs. Because of this, we're going to concoct our own scheme for encoding encrypted filenames. It's very similar to fscrypt's current scheme, but doesn't bother with the dirhash fields.

The ceph encoding scheme will use base64 encoding as well, and we also want it to avoid characters that are illegal in filenames. Export the fscrypt base64 encoding/decoding routines so we can use them in ceph's fscrypt implementation.

---
 fs/crypto/fname.c       | 8 ++++----
 include/linux/fscrypt.h | 5 +++++
 2 files changed, 9 insertions(+), 4 deletions(-)
fs/crypto/fname.c +4 -4
index a9be4bc74a94..1e4233c95005 100644
@@ -182,8 +182,6 @@ static int fname_decrypt(const struct inode *inode,
 static const char base64url_table[65] =
 	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_";
 
-#define FSCRYPT_BASE64URL_CHARS(nbytes)	DIV_ROUND_UP((nbytes) * 4, 3)
-
 /**
  * fscrypt_base64url_encode() - base64url-encode some binary data
  * @src: the binary data to encode
@@ -198,7 +196,7 @@ static const char base64url_table[65] =
  * Return: the length of the resulting base64url-encoded string in bytes.
  *	   This will be equal to FSCRYPT_BASE64URL_CHARS(srclen).
  */
-static int fscrypt_base64url_encode(const u8 *src, int srclen, char *dst)
+int fscrypt_base64url_encode(const u8 *src, int srclen, char *dst)
 {
 	u32 ac = 0;
 	int bits = 0;
@@ -217,6 +215,7 @@ static int fscrypt_base64url_encode(const u8 *src, int srclen, char *dst)
 		*cp++ = base64url_table[(ac << (6 - bits)) & 0x3f];
 	return cp - dst;
 }
+EXPORT_SYMBOL_GPL(fscrypt_base64url_encode);
 
 /**
  * fscrypt_base64url_decode() - base64url-decode a string
@@ -233,7 +232,7 @@ static int fscrypt_base64url_encode(const u8 *src, int srclen, char *dst)
  * Return: the length of the resulting decoded binary data in bytes,
  *	   or -1 if the string isn't a valid base64url string.
  */
-static int fscrypt_base64url_decode(const char *src, int srclen, u8 *dst)
+int fscrypt_base64url_decode(const char *src, int srclen, u8 *dst)
 {
 	u32 ac = 0;
 	int bits = 0;
@@ -256,6 +255,7 @@ static int fscrypt_base64url_decode(const char *src, int srclen, u8 *dst)
 		return -1;
 	return bp - dst;
 }
+EXPORT_SYMBOL_GPL(fscrypt_base64url_decode);
 
 bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
 				  u32 orig_len, u32 max_len,
include/linux/fscrypt.h +5 -0
index 50d92d805bd8..629ccd09e095 100644
@@ -46,6 +46,9 @@ struct fscrypt_name {
 /* Maximum value for the third parameter of fscrypt_operations.set_context(). */
 #define FSCRYPT_SET_CONTEXT_MAX_SIZE	40
 
+/* len of resulting string (sans NUL terminator) after base64 encoding nbytes */
+#define FSCRYPT_BASE64URL_CHARS(nbytes)		DIV_ROUND_UP((nbytes) * 4, 3)
+
 #ifdef CONFIG_FS_ENCRYPTION
 
 /*
@@ -305,6 +308,8 @@ void fscrypt_free_inode(struct inode *inode);
 int fscrypt_drop_inode(struct inode *inode);
 
 /* fname.c */
+int fscrypt_base64url_encode(const u8 *src, int len, char *dst);
+int fscrypt_base64url_decode(const char *src, int len, u8 *dst);
 int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname,
 			   int lookup, struct fscrypt_name *fname);
 
Signature · 1 line
2.35.1
#28 lore raw

PATCH v13 28/59 ceph: fix base64 encoded name's length check in ceph_fname_to_usr()

In reply to Jeff Layton

From: Xiubo Li <[email protected]>

The fname->name is based64_encoded names and the max long shouldn't exceed the NAME_MAX.

The FSCRYPT_BASE64URL_CHARS(NAME_MAX) will be 255 * 4 / 3.

---
 fs/ceph/crypto.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/ceph/crypto.c +1 -1
index eefeaa721b9d..d63e4a583413 100644
@@ -204,7 +204,7 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 	}
 
 	/* Sanity check that the resulting name will fit in the buffer */
-	if (fname->name_len > FSCRYPT_BASE64URL_CHARS(NAME_MAX))
+	if (fname->name_len > NAME_MAX || fname->ctext_len > NAME_MAX)
 		return -EIO;
 
 	ret = __fscrypt_prepare_readdir(fname->dir);
Signature · 1 line
2.35.1
#31 lore raw

PATCH v13 31/59 ceph: add ceph_encode_encrypted_dname() helper

In reply to Jeff Layton

From: Xiubo Li <[email protected]>

Add a new helper that basically calls ceph_encode_encrypted_fname, but with a qstr pointer instead of a dentry pointer. This will make it simpler to decrypt names in a readdir reply, before we have a dentry.

---
 fs/ceph/crypto.c | 11 ++++++++---
 fs/ceph/crypto.h |  8 ++++++++
 2 files changed, 16 insertions(+), 3 deletions(-)
fs/ceph/crypto.c +8 -3
index d63e4a583413..84a48c230bd7 100644
@@ -128,7 +128,7 @@ void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_se
 	swap(req->r_fscrypt_auth, as->fscrypt_auth);
 }
 
-int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentry, char *buf)
+int ceph_encode_encrypted_dname(const struct inode *parent, struct qstr *d_name, char *buf)
 {
 	u32 len;
 	int elen;
@@ -143,7 +143,7 @@ int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentr
 	 *
 	 * See: fscrypt_setup_filename
 	 */
-	if (!fscrypt_fname_encrypted_size(parent, dentry->d_name.len, NAME_MAX, &len))
+	if (!fscrypt_fname_encrypted_size(parent, d_name->len, NAME_MAX, &len))
 		return -ENAMETOOLONG;
 
 	/* Allocate a buffer appropriate to hold the result */
@@ -151,7 +151,7 @@ int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentr
 	if (!cryptbuf)
 		return -ENOMEM;
 
-	ret = fscrypt_fname_encrypt(parent, &dentry->d_name, cryptbuf, len);
+	ret = fscrypt_fname_encrypt(parent, d_name, cryptbuf, len);
 	if (ret) {
 		kfree(cryptbuf);
 		return ret;
@@ -175,6 +175,11 @@ int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentr
 	return elen;
 }
 
+int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentry, char *buf)
+{
+	return ceph_encode_encrypted_dname(parent, &dentry->d_name, buf);
+}
+
 /**
  * ceph_fname_to_usr - convert a filename for userland presentation
  * @fname: ceph_fname to be converted
fs/ceph/crypto.h +8 -0
index 7e56aded5124..e54150260eba 100644
@@ -67,6 +67,7 @@ void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc);
 int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
 				 struct ceph_acl_sec_ctx *as);
 void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_sec_ctx *as);
+int ceph_encode_encrypted_dname(const struct inode *parent, struct qstr *d_name, char *buf);
 int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentry, char *buf);
 
 static inline int ceph_fname_alloc_buffer(struct inode *parent, struct fscrypt_str *fname)
@@ -108,6 +109,13 @@ static inline void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 {
 }
 
+static inline int ceph_encode_encrypted_dname(const struct inode *parent,
+					      struct qstr *d_name, char *buf)
+{
+	memcpy(buf, d_name->name, d_name->len);
+	return d_name->len;
+}
+
 static inline int ceph_encode_encrypted_fname(const struct inode *parent,
 						struct dentry *dentry, char *buf)
 {
Signature · 1 line
2.35.1
#21 lore raw

PATCH v13 21/59 ceph: add encrypted fname handling to ceph_mdsc_build_path

In reply to Jeff Layton

Allow ceph_mdsc_build_path to encrypt and base64 encode the filename when the parent is encrypted and we're sending the path to the MDS.

In most cases, we just encrypt the filenames and base64 encode them, but when the name is longer than CEPH_NOHASH_NAME_MAX, we use a similar scheme to fscrypt proper, and hash the remaning bits with sha256.

When doing this, we then send along the full crypttext of the name in the new alternate_name field of the MClientRequest. The MDS can then send that along in readdir responses and traces.

---
 fs/ceph/crypto.c     | 47 ++++++++++++++++++++++++++
 fs/ceph/crypto.h     | 32 ++++++++++++++++++
 fs/ceph/mds_client.c | 80 ++++++++++++++++++++++++++++++++++----------
 3 files changed, 141 insertions(+), 18 deletions(-)
fs/ceph/crypto.c +47 -0
index 1c34b8ed1266..a6ee2e3160ca 100644
@@ -127,3 +127,50 @@ void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_se
 {
 	swap(req->r_fscrypt_auth, as->fscrypt_auth);
 }
+
+int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentry, char *buf)
+{
+	u32 len;
+	int elen;
+	int ret;
+	u8 *cryptbuf;
+
+	WARN_ON_ONCE(!fscrypt_has_encryption_key(parent));
+
+	/*
+	 * Convert cleartext d_name to ciphertext. If result is longer than
+	 * CEPH_NOHASH_NAME_MAX, sha256 the remaining bytes
+	 *
+	 * See: fscrypt_setup_filename
+	 */
+	if (!fscrypt_fname_encrypted_size(parent, dentry->d_name.len, NAME_MAX, &len))
+		return -ENAMETOOLONG;
+
+	/* Allocate a buffer appropriate to hold the result */
+	cryptbuf = kmalloc(len > CEPH_NOHASH_NAME_MAX ? NAME_MAX : len, GFP_KERNEL);
+	if (!cryptbuf)
+		return -ENOMEM;
+
+	ret = fscrypt_fname_encrypt(parent, &dentry->d_name, cryptbuf, len);
+	if (ret) {
+		kfree(cryptbuf);
+		return ret;
+	}
+
+	/* hash the end if the name is long enough */
+	if (len > CEPH_NOHASH_NAME_MAX) {
+		u8 hash[SHA256_DIGEST_SIZE];
+		u8 *extra = cryptbuf + CEPH_NOHASH_NAME_MAX;
+
+		/* hash the extra bytes and overwrite crypttext beyond that point with it */
+		sha256(extra, len - CEPH_NOHASH_NAME_MAX, hash);
+		memcpy(extra, hash, SHA256_DIGEST_SIZE);
+		len = CEPH_NOHASH_NAME_MAX + SHA256_DIGEST_SIZE;
+	}
+
+	/* base64 encode the encrypted name */
+	elen = fscrypt_base64url_encode(cryptbuf, len, buf);
+	kfree(cryptbuf);
+	dout("base64-encoded ciphertext name = %.*s\n", elen, buf);
+	return elen;
+}
fs/ceph/crypto.h +32 -0
index cb00fe42d5b7..9a66a29d5c8b 100644
@@ -6,6 +6,7 @@
 #ifndef _CEPH_CRYPTO_H
 #define _CEPH_CRYPTO_H
 
+#include <crypto/sha2.h>
 #include <linux/fscrypt.h>
 
 struct ceph_fs_client;
@@ -27,6 +28,30 @@ static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa)
 }
 
 #ifdef CONFIG_FS_ENCRYPTION
+/*
+ * We want to encrypt filenames when creating them, but the encrypted
+ * versions of those names may have illegal characters in them. To mitigate
+ * that, we base64 encode them, but that gives us a result that can exceed
+ * NAME_MAX.
+ *
+ * Follow a similar scheme to fscrypt itself, and cap the filename to a
+ * smaller size. If the ciphertext name is longer than the value below, then
+ * sha256 hash the remaining bytes.
+ *
+ * For the fscrypt_nokey_name struct the dirhash[2] member is useless in ceph
+ * so the corresponding struct will be:
+ *
+ * struct fscrypt_ceph_nokey_name {
+ *	u8 bytes[157];
+ *	u8 sha256[SHA256_DIGEST_SIZE];
+ * }; // 189 bytes => 252 bytes base64-encoded, which is <= NAME_MAX (255)
+ *
+ * Note that for long names that end up having their tail portion hashed, we
+ * must also store the full encrypted name (in the dentry's alternate_name
+ * field).
+ */
+#define CEPH_NOHASH_NAME_MAX (189 - SHA256_DIGEST_SIZE)
+
 void ceph_fscrypt_set_ops(struct super_block *sb);
 
 void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc);
@@ -34,6 +59,7 @@ void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc);
 int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
 				 struct ceph_acl_sec_ctx *as);
 void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_sec_ctx *as);
+int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentry, char *buf);
 
 #else /* CONFIG_FS_ENCRYPTION */
 
@@ -57,6 +83,12 @@ static inline void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 						struct ceph_acl_sec_ctx *as_ctx)
 {
 }
+
+static inline int ceph_encode_encrypted_fname(const struct inode *parent,
+						struct dentry *dentry, char *buf)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_FS_ENCRYPTION */
 
 #endif
fs/ceph/mds_client.c +62 -18

131 lines not on this page · raw message

Signature · 1 line
2.35.1
#20 lore raw

PATCH v13 20/59 ceph: make ceph_msdc_build_path use ref-walk

In reply to Jeff Layton

Encryption potentially requires allocation, at which point we'll need to be in a non-atomic context. Convert ceph_msdc_build_path to take dentry spinlocks and references instead of using rcu_read_lock to walk the path.

This is slightly less efficient, and we may want to eventually allow using RCU when the leaf dentry isn't encrypted.

---
 fs/ceph/mds_client.c | 35 +++++++++++++++++++----------------
 1 file changed, 19 insertions(+), 16 deletions(-)
fs/ceph/mds_client.c +19 -16
index 2f2f8221eb25..28315053e116 100644
@@ -2398,7 +2398,8 @@ static inline  u64 __get_oldest_tid(struct ceph_mds_client *mdsc)
 char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *pbase,
 			   int stop_on_nosnap)
 {
-	struct dentry *temp;
+	struct dentry *cur;
+	struct inode *inode;
 	char *path;
 	int pos;
 	unsigned seq;
@@ -2415,34 +2416,35 @@ char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *pbase,
 	path[pos] = '\0';
 
 	seq = read_seqbegin(&rename_lock);
-	rcu_read_lock();
-	temp = dentry;
+	cur = dget(dentry);
 	for (;;) {
-		struct inode *inode;
+		struct dentry *temp;
 
-		spin_lock(&temp->d_lock);
-		inode = d_inode(temp);
+		spin_lock(&cur->d_lock);
+		inode = d_inode(cur);
 		if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
 			dout("build_path path+%d: %p SNAPDIR\n",
-			     pos, temp);
-		} else if (stop_on_nosnap && inode && dentry != temp &&
+			     pos, cur);
+		} else if (stop_on_nosnap && inode && dentry != cur &&
 			   ceph_snap(inode) == CEPH_NOSNAP) {
-			spin_unlock(&temp->d_lock);
+			spin_unlock(&cur->d_lock);
 			pos++; /* get rid of any prepended '/' */
 			break;
 		} else {
-			pos -= temp->d_name.len;
+			pos -= cur->d_name.len;
 			if (pos < 0) {
-				spin_unlock(&temp->d_lock);
+				spin_unlock(&cur->d_lock);
 				break;
 			}
-			memcpy(path + pos, temp->d_name.name, temp->d_name.len);
+			memcpy(path + pos, cur->d_name.name, cur->d_name.len);
 		}
+		temp = cur;
 		spin_unlock(&temp->d_lock);
-		temp = READ_ONCE(temp->d_parent);
+		cur = dget_parent(temp);
+		dput(temp);
 
 		/* Are we at the root? */
-		if (IS_ROOT(temp))
+		if (IS_ROOT(cur))
 			break;
 
 		/* Are we out of buffer? */
@@ -2451,8 +2453,9 @@ char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *pbase,
 
 		path[pos] = '/';
 	}
-	base = ceph_ino(d_inode(temp));
-	rcu_read_unlock();
+	inode = d_inode(cur);
+	base = inode ? ceph_ino(inode) : 0;
+	dput(cur);
 
 	if (read_seqretry(&rename_lock, seq))
 		goto retry;
Signature · 1 line
2.35.1
#56 lore raw

PATCH v13 56/59 ceph: add fscrypt decryption support to ceph_netfs_issue_op

In reply to Jeff Layton

Force the use of sparse reads when the inode is encrypted, and add the appropriate code to decrypt the extent map after receiving.

---
 fs/ceph/addr.c | 32 +++++++++++++++++++++++---------
 1 file changed, 23 insertions(+), 9 deletions(-)
fs/ceph/addr.c +23 -9
index 99021431a391..bcb74b1d46bb 100644
@@ -18,6 +18,7 @@
 #include "mds_client.h"
 #include "cache.h"
 #include "metric.h"
+#include "crypto.h"
 #include <linux/ceph/osd_client.h>
 #include <linux/ceph/striper.h>
 
@@ -216,7 +217,8 @@ static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
 
 static void finish_netfs_read(struct ceph_osd_request *req)
 {
-	struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
+	struct inode *inode = req->r_inode;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
 	struct netfs_io_subrequest *subreq = req->r_priv;
 	struct ceph_osd_req_op *op = &req->r_ops[0];
@@ -231,15 +233,24 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	     subreq->len, i_size_read(req->r_inode));
 
 	/* no object means success but no data */
-	if (sparse && err >= 0)
-		err = ceph_sparse_ext_map_end(op);
-	else if (err == -ENOENT)
+	if (err == -ENOENT)
 		err = 0;
 	else if (err == -EBLOCKLISTED)
 		fsc->blocklisted = true;
 
-	if (err >= 0 && err < subreq->len)
-		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+	if (err >= 0) {
+		if (sparse && err > 0)
+			err = ceph_sparse_ext_map_end(op);
+		if (err < subreq->len)
+			__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+		if (IS_ENCRYPTED(inode) && err > 0) {
+			err = ceph_fscrypt_decrypt_extents(inode, osd_data->pages,
+					subreq->start, op->extent.sparse_ext,
+					op->extent.sparse_ext_cnt);
+			if (err > subreq->len)
+				err = subreq->len;
+		}
+	}
 
 	netfs_subreq_terminated(subreq, err, true);
 
@@ -314,13 +325,16 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	size_t page_off;
 	int err = 0;
 	u64 len = subreq->len;
-	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
+	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
+	u64 off = subreq->start;
 
 	if (ci->i_inline_version != CEPH_INLINE_NONE &&
 	    ceph_netfs_issue_op_inline(subreq))
 		return;
 
-	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
+	ceph_fscrypt_adjust_off_and_len(inode, &off, &len);
+
+	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, off, &len,
 			0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
 			CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
 			NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
@@ -339,7 +353,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	}
 
 	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
-	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
+	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, off, len);
 	err = iov_iter_get_pages_alloc(&iter, &pages, len, &page_off);
 	if (err < 0) {
 		dout("%s: iov_ter_get_pages_alloc returned %d\n", __func__, err);
Signature · 1 line
2.35.1
#32 lore raw

PATCH v13 32/59 ceph: add support to readdir for encrypted filenames

In reply to Jeff Layton

From: Xiubo Li <[email protected]>

Once we've decrypted the names in a readdir reply, we no longer need the crypttext, so overwrite them in ceph_mds_reply_dir_entry with the unencrypted names. Then in both ceph_readdir_prepopulate() and ceph_readdir() we will use the dencrypted name directly.

[ jlayton: convert some BUG_ONs into error returns ]

---
 fs/ceph/crypto.c     | 12 +++++--
 fs/ceph/crypto.h     |  1 +
 fs/ceph/dir.c        | 35 +++++++++++++++----
 fs/ceph/inode.c      | 12 ++++---
 fs/ceph/mds_client.c | 81 ++++++++++++++++++++++++++++++++++++++++----
 fs/ceph/mds_client.h |  4 +--
 6 files changed, 124 insertions(+), 21 deletions(-)
fs/ceph/crypto.c +10 -2
index 84a48c230bd7..19c113afb400 100644
@@ -135,7 +135,10 @@ int ceph_encode_encrypted_dname(const struct inode *parent, struct qstr *d_name,
 	int ret;
 	u8 *cryptbuf;
 
-	WARN_ON_ONCE(!fscrypt_has_encryption_key(parent));
+	if (!fscrypt_has_encryption_key(parent)) {
+		memcpy(buf, d_name->name, d_name->len);
+		return d_name->len;
+	}
 
 	/*
 	 * Convert cleartext d_name to ciphertext. If result is longer than
@@ -177,6 +180,8 @@ int ceph_encode_encrypted_dname(const struct inode *parent, struct qstr *d_name,
 
 int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentry, char *buf)
 {
+	WARN_ON_ONCE(!fscrypt_has_encryption_key(parent));
+
 	return ceph_encode_encrypted_dname(parent, &dentry->d_name, buf);
 }
 
@@ -221,7 +226,10 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 	 * generating a nokey name via fscrypt.
 	 */
 	if (!fscrypt_has_encryption_key(fname->dir)) {
-		memcpy(oname->name, fname->name, fname->name_len);
+		if (fname->no_copy)
+			oname->name = fname->name;
+		else
+			memcpy(oname->name, fname->name, fname->name_len);
 		oname->len = fname->name_len;
 		if (is_nokey)
 			*is_nokey = true;
fs/ceph/crypto.h +1 -0
index e54150260eba..080905b0c73c 100644
@@ -19,6 +19,7 @@ struct ceph_fname {
 	unsigned char	*ctext;		// binary crypttext (if any)
 	u32		name_len;	// length of name buffer
 	u32		ctext_len;	// length of crypttext
+	bool		no_copy;
 };
 
 struct ceph_fscrypt_auth {
fs/ceph/dir.c +29 -6
index caf2547c3fe1..5ce2a6384e55 100644
@@ -9,6 +9,7 @@
 
 #include "super.h"
 #include "mds_client.h"
+#include "crypto.h"
 
 /*
  * Directory operations: readdir, lookup, create, link, unlink,
@@ -241,7 +242,9 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 		di = ceph_dentry(dentry);
 		if (d_unhashed(dentry) ||
 		    d_really_is_negative(dentry) ||
-		    di->lease_shared_gen != shared_gen) {
+		    di->lease_shared_gen != shared_gen ||
+		    ((dentry->d_flags & DCACHE_NOKEY_NAME) &&
+		     fscrypt_has_encryption_key(dir))) {
 			spin_unlock(&dentry->d_lock);
 			dput(dentry);
 			err = -EAGAIN;
@@ -340,6 +343,10 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		ctx->pos = 2;
 	}
 
+	err = fscrypt_prepare_readdir(inode);
+	if (err)
+		return err;
+
 	spin_lock(&ci->i_ceph_lock);
 	/* request Fx cap. if have Fx, we don't need to release Fs cap
 	 * for later create/unlink. */
@@ -389,6 +396,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 		if (IS_ERR(req))
 			return PTR_ERR(req);
+
 		err = ceph_alloc_readdir_reply_buffer(req, inode);
 		if (err) {
 			ceph_mdsc_put_request(req);
@@ -402,11 +410,20 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 			req->r_inode_drop = CEPH_CAP_FILE_EXCL;
 		}
 		if (dfi->last_name) {
-			req->r_path2 = kstrdup(dfi->last_name, GFP_KERNEL);
+			struct qstr d_name = { .name = dfi->last_name,
+					       .len = strlen(dfi->last_name) };
+
+			req->r_path2 = kzalloc(NAME_MAX + 1, GFP_KERNEL);
 			if (!req->r_path2) {
 				ceph_mdsc_put_request(req);
 				return -ENOMEM;
 			}
+
+			err = ceph_encode_encrypted_dname(inode, &d_name, req->r_path2);
+			if (err < 0) {
+				ceph_mdsc_put_request(req);
+				return err;
+			}
 		} else if (is_hash_order(ctx->pos)) {
 			req->r_args.readdir.offset_hash =
 				cpu_to_le32(fpos_hash(ctx->pos));
@@ -511,15 +528,20 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	for (; i < rinfo->dir_nr; i++) {
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
 
-		BUG_ON(rde->offset < ctx->pos);
+		if (rde->offset < ctx->pos) {
+			pr_warn("%s: rde->offset 0x%llx ctx->pos 0x%llx\n",
+				__func__, rde->offset, ctx->pos);
+			return -EIO;
+		}
+
+		if (WARN_ON_ONCE(!rde->inode.in))
+			return -EIO;
 
 		ctx->pos = rde->offset;
 		dout("readdir (%d/%d) -> %llx '%.*s' %p\n",
 		     i, rinfo->dir_nr, ctx->pos,
 		     rde->name_len, rde->name, &rde->inode.in);
 
-		BUG_ON(!rde->inode.in);
-
 		if (!dir_emit(ctx, rde->name, rde->name_len,
 			      ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
 			      le32_to_cpu(rde->inode.in->mode) >> 12)) {
@@ -532,6 +554,8 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 			dout("filldir stopping us...\n");
 			return 0;
 		}
+
+		/* Reset the lengths to their original allocated vals */
 		ctx->pos++;
 	}
 
@@ -586,7 +610,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 					dfi->dir_ordered_count);
 		spin_unlock(&ci->i_ceph_lock);
 	}
-
 	dout("readdir %p file %p done.\n", inode, file);
 	return 0;
 }
fs/ceph/inode.c +8 -4
index 37c2c2977235..d1ade1651214 100644
@@ -1751,7 +1751,8 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 			     struct ceph_mds_session *session)
 {
 	struct dentry *parent = req->r_dentry;
-	struct ceph_inode_info *ci = ceph_inode(d_inode(parent));
+	struct inode *inode = d_inode(parent);
+	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
 	struct qstr dname;
 	struct dentry *dn;
@@ -1825,9 +1826,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 		tvino.snap = le64_to_cpu(rde->inode.in->snapid);
 
 		if (rinfo->hash_order) {
-			u32 hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
-						 rde->name, rde->name_len);
-			hash = ceph_frag_value(hash);
+			u32 hash = ceph_frag_value(rde->raw_hash);
 			if (hash != last_hash)
 				fpos_offset = 2;
 			last_hash = hash;
@@ -1850,6 +1849,11 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 				err = -ENOMEM;
 				goto out;
 			}
+			if (rde->is_nokey) {
+				spin_lock(&dn->d_lock);
+				dn->d_flags |= DCACHE_NOKEY_NAME;
+				spin_unlock(&dn->d_lock);
+			}
 		} else if (d_really_is_positive(dn) &&
 			   (ceph_ino(d_inode(dn)) != tvino.ino ||
 			    ceph_snap(d_inode(dn)) != tvino.snap)) {
fs/ceph/mds_client.c +74 -7

101 lines not on this page · raw message

fs/ceph/mds_client.h +2 -2
index cd719691a86d..046a9368c4a9 100644
@@ -96,10 +96,10 @@ struct ceph_mds_reply_info_in {
 };
 
 struct ceph_mds_reply_dir_entry {
+	bool			      is_nokey;
 	char                          *name;
-	u8			      *altname;
 	u32                           name_len;
-	u32			      altname_len;
+	u32			      raw_hash;
 	struct ceph_mds_reply_lease   *lease;
 	struct ceph_mds_reply_info_in inode;
 	loff_t			      offset;
Signature · 1 line
2.35.1
#40 lore raw

PATCH v13 40/59 ceph: fscrypt_file field handling in MClientRequest messages

In reply to Jeff Layton

For encrypted inodes, transmit a rounded-up size to the MDS as the normal file size and send the real inode size in fscrypt_file field.

Also, fix up creates and truncates to also transmit fscrypt_file.

---
 fs/ceph/dir.c        |  3 +++
 fs/ceph/file.c       |  1 +
 fs/ceph/inode.c      | 18 ++++++++++++++++--
 fs/ceph/mds_client.c |  9 ++++++++-
 fs/ceph/mds_client.h |  2 ++
 5 files changed, 30 insertions(+), 3 deletions(-)
fs/ceph/dir.c +3 -0
index 8a9f916bfc6c..5ccf6453f02f 100644
@@ -910,6 +910,9 @@ static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir,
 		goto out_req;
 	}
 
+	if (S_ISREG(mode) && IS_ENCRYPTED(dir))
+		set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
+
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	req->r_parent = dir;
fs/ceph/file.c +1 -0
index a3afdb9cfddb..b7e2594cc296 100644
@@ -764,6 +764,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	req->r_parent = dir;
 	ihold(dir);
 	if (IS_ENCRYPTED(dir)) {
+		set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
 		if (!fscrypt_has_encryption_key(dir)) {
 			spin_lock(&dentry->d_lock);
 			dentry->d_flags |= DCACHE_NOKEY_NAME;
fs/ceph/inode.c +16 -2
index 183b9f52dc7d..b9454721c976 100644
@@ -2378,11 +2378,25 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c
 			}
 		} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
 			   attr->ia_size != isize) {
-			req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
-			req->r_args.setattr.old_size = cpu_to_le64(isize);
 			mask |= CEPH_SETATTR_SIZE;
 			release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL |
 				   CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
+			if (IS_ENCRYPTED(inode) && attr->ia_size) {
+				set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
+				mask |= CEPH_SETATTR_FSCRYPT_FILE;
+				req->r_args.setattr.size =
+					cpu_to_le64(round_up(attr->ia_size,
+							     CEPH_FSCRYPT_BLOCK_SIZE));
+				req->r_args.setattr.old_size =
+					cpu_to_le64(round_up(isize,
+							     CEPH_FSCRYPT_BLOCK_SIZE));
+				req->r_fscrypt_file = attr->ia_size;
+				/* FIXME: client must zero out any partial blocks! */
+			} else {
+				req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
+				req->r_args.setattr.old_size = cpu_to_le64(isize);
+				req->r_fscrypt_file = 0;
+			}
 		}
 	}
 	if (ia_valid & ATTR_MTIME) {
fs/ceph/mds_client.c +8 -1
index 50fe77768295..0da85c9ce73a 100644
@@ -2752,7 +2752,12 @@ static void encode_mclientrequest_tail(void **p, const struct ceph_mds_request *
 	} else {
 		ceph_encode_32(p, 0);
 	}
-	ceph_encode_32(p, 0); // fscrypt_file for now
+	if (test_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags)) {
+		ceph_encode_32(p, sizeof(__le64));
+		ceph_encode_64(p, req->r_fscrypt_file);
+	} else {
+		ceph_encode_32(p, 0);
+	}
 }
 
 /*
@@ -2838,6 +2843,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 
 	/* fscrypt_file */
 	len += sizeof(u32);
+	if (test_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags))
+		len += sizeof(__le64);
 
 	msg = ceph_msg_new2(CEPH_MSG_CLIENT_REQUEST, len, 1, GFP_NOFS, false);
 	if (!msg) {
fs/ceph/mds_client.h +2 -0
index 046a9368c4a9..e297bf98c39f 100644
@@ -282,6 +282,7 @@ struct ceph_mds_request {
 #define CEPH_MDS_R_DID_PREPOPULATE	(6) /* prepopulated readdir */
 #define CEPH_MDS_R_PARENT_LOCKED	(7) /* is r_parent->i_rwsem wlocked? */
 #define CEPH_MDS_R_ASYNC		(8) /* async request */
+#define CEPH_MDS_R_FSCRYPT_FILE		(9) /* must marshal fscrypt_file field */
 	unsigned long	r_req_flags;
 
 	struct mutex r_fill_mutex;
@@ -289,6 +290,7 @@ struct ceph_mds_request {
 	union ceph_mds_request_args r_args;
 
 	struct ceph_fscrypt_auth *r_fscrypt_auth;
+	u64	r_fscrypt_file;
 
 	u8 *r_altname;		    /* fscrypt binary crypttext for long filenames */
 	u32 r_altname_len;	    /* length of r_altname */
Signature · 1 line
2.35.1
#44 lore raw

PATCH v13 44/59 ceph: add __ceph_get_caps helper support

In reply to Jeff Layton

From: Xiubo Li <[email protected]>

Break out the guts of ceph_get_caps into a helper that takes an inode and ceph_file_info instead of a file pointer.

---
 fs/ceph/caps.c  | 19 +++++++++++++------
 fs/ceph/super.h |  2 ++
 2 files changed, 15 insertions(+), 6 deletions(-)
fs/ceph/caps.c +13 -6
index cb2c18d43946..69af17df59be 100644
@@ -2947,10 +2947,9 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
  * due to a small max_size, make sure we check_max_size (and possibly
  * ask the mds) so we don't get hung up indefinitely.
  */
-int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got)
+int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
+		    int want, loff_t endoff, int *got)
 {
-	struct ceph_file_info *fi = filp->private_data;
-	struct inode *inode = file_inode(filp);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	int ret, _got, flags;
@@ -2959,7 +2958,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 	if (ret < 0)
 		return ret;
 
-	if ((fi->fmode & CEPH_FILE_MODE_WR) &&
+	if (fi && (fi->fmode & CEPH_FILE_MODE_WR) &&
 	    fi->filp_gen != READ_ONCE(fsc->filp_gen))
 		return -EBADF;
 
@@ -2967,7 +2966,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 
 	while (true) {
 		flags &= CEPH_FILE_MODE_MASK;
-		if (atomic_read(&fi->num_locks))
+		if (fi && atomic_read(&fi->num_locks))
 			flags |= CHECK_FILELOCK;
 		_got = 0;
 		ret = try_get_cap_refs(inode, need, want, endoff,
@@ -3012,7 +3011,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 				continue;
 		}
 
-		if ((fi->fmode & CEPH_FILE_MODE_WR) &&
+		if (fi && (fi->fmode & CEPH_FILE_MODE_WR) &&
 		    fi->filp_gen != READ_ONCE(fsc->filp_gen)) {
 			if (ret >= 0 && _got)
 				ceph_put_cap_refs(ci, _got);
@@ -3075,6 +3074,14 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 	return 0;
 }
 
+int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got)
+{
+	struct ceph_file_info *fi = filp->private_data;
+	struct inode *inode = file_inode(filp);
+
+	return __ceph_get_caps(inode, fi, need, want, endoff, got);
+}
+
 /*
  * Take cap refs.  Caller must already know we hold at least one ref
  * on the caps in question or we don't know this is safe.
fs/ceph/super.h +2 -0
index a97a6f6f3089..752bc3c820ca 100644
@@ -1229,6 +1229,8 @@ extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
 				      struct inode *dir,
 				      int mds, int drop, int unless);
 
+extern int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi,
+			   int need, int want, loff_t endoff, int *got);
 extern int ceph_get_caps(struct file *filp, int need, int want,
 			 loff_t endoff, int *got);
 extern int ceph_try_get_caps(struct inode *inode,
Signature · 1 line
2.35.1
#34 lore raw

PATCH v13 34/59 ceph: make ceph_get_name decrypt filenames

In reply to Jeff Layton

When we do a lookupino to the MDS, we get a filename in the trace. ceph_get_name uses that name directly, so we must properly decrypt it before copying it to the name buffer.

---
 fs/ceph/export.c | 44 ++++++++++++++++++++++++++++++++------------
 1 file changed, 32 insertions(+), 12 deletions(-)
fs/ceph/export.c +32 -12
index e0fa66ac8b9f..0ebf2bd93055 100644
@@ -7,6 +7,7 @@
 
 #include "super.h"
 #include "mds_client.h"
+#include "crypto.h"
 
 /*
  * Basic fh
@@ -534,7 +535,9 @@ static int ceph_get_name(struct dentry *parent, char *name,
 {
 	struct ceph_mds_client *mdsc;
 	struct ceph_mds_request *req;
+	struct inode *dir = d_inode(parent);
 	struct inode *inode = d_inode(child);
+	struct ceph_mds_reply_info_parsed *rinfo;
 	int err;
 
 	if (ceph_snap(inode) != CEPH_NOSNAP)
@@ -546,30 +549,47 @@ static int ceph_get_name(struct dentry *parent, char *name,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	inode_lock(d_inode(parent));
-
+	inode_lock(dir);
 	req->r_inode = inode;
 	ihold(inode);
 	req->r_ino2 = ceph_vino(d_inode(parent));
-	req->r_parent = d_inode(parent);
-	ihold(req->r_parent);
+	req->r_parent = dir;
+	ihold(dir);
 	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_num_caps = 2;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	inode_unlock(dir);
 
-	inode_unlock(d_inode(parent));
+	if (err)
+		goto out;
 
-	if (!err) {
-		struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+	rinfo = &req->r_reply_info;
+	if (!IS_ENCRYPTED(dir)) {
 		memcpy(name, rinfo->dname, rinfo->dname_len);
 		name[rinfo->dname_len] = 0;
-		dout("get_name %p ino %llx.%llx name %s\n",
-		     child, ceph_vinop(inode), name);
 	} else {
-		dout("get_name %p ino %llx.%llx err %d\n",
-		     child, ceph_vinop(inode), err);
-	}
+		struct fscrypt_str oname = FSTR_INIT(NULL, 0);
+		struct ceph_fname fname = { .dir	= dir,
+					    .name	= rinfo->dname,
+					    .ctext	= rinfo->altname,
+					    .name_len	= rinfo->dname_len,
+					    .ctext_len	= rinfo->altname_len };
+
+		err = ceph_fname_alloc_buffer(dir, &oname);
+		if (err < 0)
+			goto out;
 
+		err = ceph_fname_to_usr(&fname, NULL, &oname, NULL);
+		if (!err) {
+			memcpy(name, oname.name, oname.len);
+			name[oname.len] = 0;
+		}
+		ceph_fname_free_buffer(dir, &oname);
+	}
+out:
+	dout("get_name %p ino %llx.%llx err %d %s%s\n",
+		     child, ceph_vinop(inode), err,
+		     err ? "" : "name ", err ? "" : name);
 	ceph_mdsc_put_request(req);
 	return err;
 }
Signature · 1 line
2.35.1
#15 lore raw

PATCH v13 15/59 ceph: add support for fscrypt_auth/fscrypt_file to cap messages

In reply to Jeff Layton

Add support for new version 12 cap messages that carry the new fscrypt_auth and fscrypt_file fields from the inode.

---
 fs/ceph/caps.c | 76 +++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 63 insertions(+), 13 deletions(-)
fs/ceph/caps.c +63 -13
index 042d4ca75253..3b31d77eb1ea 100644
@@ -13,6 +13,7 @@
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
+#include "crypto.h"
 #include <linux/ceph/decode.h>
 #include <linux/ceph/messenger.h>
 
@@ -1214,15 +1215,12 @@ struct cap_msg_args {
 	umode_t			mode;
 	bool			inline_data;
 	bool			wake;
+	u32			fscrypt_auth_len;
+	u32			fscrypt_file_len;
+	u8			fscrypt_auth[sizeof(struct ceph_fscrypt_auth)]; // for context
+	u8			fscrypt_file[sizeof(u64)]; // for size
 };
 
-/*
- * cap struct size + flock buffer size + inline version + inline data size +
- * osd_epoch_barrier + oldest_flush_tid
- */
-#define CAP_MSG_SIZE (sizeof(struct ceph_mds_caps) + \
-		      4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 4)
-
 /* Marshal up the cap msg to the MDS */
 static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 {
@@ -1238,7 +1236,7 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 	     arg->size, arg->max_size, arg->xattr_version,
 	     arg->xattr_buf ? (int)arg->xattr_buf->vec.iov_len : 0);
 
-	msg->hdr.version = cpu_to_le16(10);
+	msg->hdr.version = cpu_to_le16(12);
 	msg->hdr.tid = cpu_to_le64(arg->flush_tid);
 
 	fc = msg->front.iov_base;
@@ -1309,6 +1307,21 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 
 	/* Advisory flags (version 10) */
 	ceph_encode_32(&p, arg->flags);
+
+	/* dirstats (version 11) - these are r/o on the client */
+	ceph_encode_64(&p, 0);
+	ceph_encode_64(&p, 0);
+
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	/* fscrypt_auth and fscrypt_file (version 12) */
+	ceph_encode_32(&p, arg->fscrypt_auth_len);
+	ceph_encode_copy(&p, arg->fscrypt_auth, arg->fscrypt_auth_len);
+	ceph_encode_32(&p, arg->fscrypt_file_len);
+	ceph_encode_copy(&p, arg->fscrypt_file, arg->fscrypt_file_len);
+#else /* CONFIG_FS_ENCRYPTION */
+	ceph_encode_32(&p, 0);
+	ceph_encode_32(&p, 0);
+#endif /* CONFIG_FS_ENCRYPTION */
 }
 
 /*
@@ -1430,8 +1443,37 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 		}
 	}
 	arg->flags = flags;
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	if (ci->fscrypt_auth_len &&
+	    WARN_ON_ONCE(ci->fscrypt_auth_len > sizeof(struct ceph_fscrypt_auth))) {
+		/* Don't set this if it's too big */
+		arg->fscrypt_auth_len = 0;
+	} else {
+		arg->fscrypt_auth_len = ci->fscrypt_auth_len;
+		memcpy(arg->fscrypt_auth, ci->fscrypt_auth,
+			min_t(size_t, ci->fscrypt_auth_len, sizeof(arg->fscrypt_auth)));
+	}
+	/* FIXME: use this to track "real" size */
+	arg->fscrypt_file_len = 0;
+#endif /* CONFIG_FS_ENCRYPTION */
 }
 
+#define CAP_MSG_FIXED_FIELDS (sizeof(struct ceph_mds_caps) + \
+		      4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 4 + 8 + 8 + 4 + 4)
+
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+static inline int cap_msg_size(struct cap_msg_args *arg)
+{
+	return CAP_MSG_FIXED_FIELDS + arg->fscrypt_auth_len +
+			arg->fscrypt_file_len;
+}
+#else
+static inline int cap_msg_size(struct cap_msg_args *arg)
+{
+	return CAP_MSG_FIXED_FIELDS;
+}
+#endif /* CONFIG_FS_ENCRYPTION */
+
 /*
  * Send a cap msg on the given inode.
  *
@@ -1442,7 +1484,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci)
 	struct ceph_msg *msg;
 	struct inode *inode = &ci->vfs_inode;
 
-	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, CAP_MSG_SIZE, GFP_NOFS, false);
+	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, cap_msg_size(arg), GFP_NOFS, false);
 	if (!msg) {
 		pr_err("error allocating cap msg: ino (%llx.%llx) flushing %s tid %llu, requeuing cap.\n",
 		       ceph_vinop(inode), ceph_cap_string(arg->dirty),
@@ -1468,10 +1510,6 @@ static inline int __send_flush_snap(struct inode *inode,
 	struct cap_msg_args	arg;
 	struct ceph_msg		*msg;
 
-	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, CAP_MSG_SIZE, GFP_NOFS, false);
-	if (!msg)
-		return -ENOMEM;
-
 	arg.session = session;
 	arg.ino = ceph_vino(inode).ino;
 	arg.cid = 0;
@@ -1509,6 +1547,18 @@ static inline int __send_flush_snap(struct inode *inode,
 	arg.flags = 0;
 	arg.wake = false;
 
+	/*
+	 * No fscrypt_auth changes from a capsnap. It will need
+	 * to update fscrypt_file on size changes (TODO).
+	 */
+	arg.fscrypt_auth_len = 0;
+	arg.fscrypt_file_len = 0;
+
+	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, cap_msg_size(&arg),
+			   GFP_NOFS, false);
+	if (!msg)
+		return -ENOMEM;
+
 	encode_cap_msg(msg, &arg);
 	ceph_con_send(&arg.session->s_con, msg);
 	return 0;
Signature · 1 line
2.35.1
#55 lore raw

PATCH v13 55/59 ceph: plumb in decryption during sync reads

In reply to Jeff Layton

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.

---
 fs/ceph/file.c | 89 ++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 65 insertions(+), 24 deletions(-)
fs/ceph/file.c +65 -24
index 522189ed6642..5d39d8e54273 100644
@@ -938,7 +938,7 @@ 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);
@@ -966,10 +966,19 @@ 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);
@@ -978,10 +987,13 @@ 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);
@@ -989,7 +1001,8 @@ 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];
@@ -1008,7 +1021,7 @@ 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;
@@ -1023,8 +1036,34 @@ 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;
@@ -1038,15 +1077,16 @@ 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;
 			}
@@ -1063,20 +1103,21 @@ 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;
 }
Signature · 1 line
2.35.1
#7 lore raw

PATCH v13 7/59 ceph: add new mount option to enable sparse reads

In reply to Jeff Layton

Add a new mount option that has the client issue sparse reads instead of normal ones. The callers now preallocate an sparse extent buffer that the libceph receive code can populate and hand back after the operation completes.

After a successful sparse read, we can't use the req->r_result value to determine the amount of data "read", so instead we set the received length to be from the end of the last extent in the buffer. Any interstitial holes will have been filled by the receive code.

---
 fs/ceph/addr.c  | 17 +++++++++++++++--
 fs/ceph/file.c  | 51 +++++++++++++++++++++++++++++++++++++++++--------
 fs/ceph/super.c | 16 +++++++++++++++-
 fs/ceph/super.h |  1 +
 4 files changed, 74 insertions(+), 11 deletions(-)
fs/ceph/addr.c +15 -2
index aa25bffd4823..99021431a391 100644
@@ -219,8 +219,10 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
 	struct netfs_io_subrequest *subreq = req->r_priv;
+	struct ceph_osd_req_op *op = &req->r_ops[0];
 	int num_pages;
 	int err = req->r_result;
+	bool sparse = (op->op == CEPH_OSD_OP_SPARSE_READ);
 
 	ceph_update_read_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				 req->r_end_latency, osd_data->length, err);
@@ -229,7 +231,9 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	     subreq->len, i_size_read(req->r_inode));
 
 	/* no object means success but no data */
-	if (err == -ENOENT)
+	if (sparse && err >= 0)
+		err = ceph_sparse_ext_map_end(op);
+	else if (err == -ENOENT)
 		err = 0;
 	else if (err == -EBLOCKLISTED)
 		fsc->blocklisted = true;
@@ -310,13 +314,14 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	size_t page_off;
 	int err = 0;
 	u64 len = subreq->len;
+	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
 
 	if (ci->i_inline_version != CEPH_INLINE_NONE &&
 	    ceph_netfs_issue_op_inline(subreq))
 		return;
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
-			0, 1, CEPH_OSD_OP_READ,
+			0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
 			CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
 			NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
@@ -325,6 +330,14 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 		goto out;
 	}
 
+	if (sparse) {
+		err = ceph_alloc_sparse_ext_map(&req->r_ops[0]);
+		if (err) {
+			ceph_osdc_put_request(req);
+			goto out;
+		}
+	}
+
 	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
 	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
 	err = iov_iter_get_pages_alloc(&iter, &pages, len, &page_off);
fs/ceph/file.c +43 -8

132 lines not on this page · raw message

fs/ceph/super.c +15 -1
index e6987d295079..26d924dda721 100644
@@ -163,6 +163,7 @@ enum {
 	Opt_copyfrom,
 	Opt_wsync,
 	Opt_pagecache,
+	Opt_sparseread,
 };
 
 enum ceph_recover_session_mode {
@@ -205,6 +206,7 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = {
 	fsparam_u32	("wsize",			Opt_wsize),
 	fsparam_flag_no	("wsync",			Opt_wsync),
 	fsparam_flag_no	("pagecache",			Opt_pagecache),
+	fsparam_flag_no	("sparseread",			Opt_sparseread),
 	{}
 };
 
@@ -574,6 +576,12 @@ static int ceph_parse_mount_param(struct fs_context *fc,
 		else
 			fsopt->flags &= ~CEPH_MOUNT_OPT_NOPAGECACHE;
 		break;
+	case Opt_sparseread:
+		if (result.negated)
+			fsopt->flags &= ~CEPH_MOUNT_OPT_SPARSEREAD;
+		else
+			fsopt->flags |= CEPH_MOUNT_OPT_SPARSEREAD;
+		break;
 	default:
 		BUG();
 	}
@@ -708,9 +716,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 
 	if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS))
 		seq_puts(m, ",wsync");
-
 	if (fsopt->flags & CEPH_MOUNT_OPT_NOPAGECACHE)
 		seq_puts(m, ",nopagecache");
+	if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD)
+		seq_puts(m, ",sparseread");
 
 	if (fsopt->wsize != CEPH_MAX_WRITE_SIZE)
 		seq_printf(m, ",wsize=%u", fsopt->wsize);
@@ -1290,6 +1299,11 @@ static int ceph_reconfigure_fc(struct fs_context *fc)
 	else
 		ceph_clear_mount_opt(fsc, ASYNC_DIROPS);
 
+	if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD)
+		ceph_set_mount_opt(fsc, SPARSEREAD);
+	else
+		ceph_clear_mount_opt(fsc, SPARSEREAD);
+
 	if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) {
 		kfree(fsc->mount_options->mon_addr);
 		fsc->mount_options->mon_addr = fsopt->mon_addr;
fs/ceph/super.h +1 -0
index 73db7f6021f3..80a2399f2878 100644
@@ -41,6 +41,7 @@
 #define CEPH_MOUNT_OPT_NOCOPYFROM      (1<<14) /* don't use RADOS 'copy-from' op */
 #define CEPH_MOUNT_OPT_ASYNC_DIROPS    (1<<15) /* allow async directory ops */
 #define CEPH_MOUNT_OPT_NOPAGECACHE     (1<<16) /* bypass pagecache altogether */
+#define CEPH_MOUNT_OPT_SPARSEREAD      (1<<17) /* always do sparse reads */
 
 #define CEPH_MOUNT_OPT_DEFAULT			\
 	(CEPH_MOUNT_OPT_DCACHE |		\
Signature · 1 line
2.35.1
#25 lore raw

PATCH v13 25/59 ceph: set DCACHE_NOKEY_NAME in atomic open

In reply to Jeff Layton

Atomic open can act as a lookup if handed a dentry that is negative on the MDS. Ensure that we set DCACHE_NOKEY_NAME on the dentry in atomic_open, if we don't have the key for the parent. Otherwise, we can end up validating the dentry inappropriately if someone later adds a key.

---
 fs/ceph/file.c | 7 +++++++
 1 file changed, 7 insertions(+)
fs/ceph/file.c +7 -0
index dd183d12a3bd..dfc02caf4229 100644
@@ -758,6 +758,13 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	req->r_args.open.mask = cpu_to_le32(mask);
 	req->r_parent = dir;
 	ihold(dir);
+	if (IS_ENCRYPTED(dir)) {
+		if (!fscrypt_has_encryption_key(dir)) {
+			spin_lock(&dentry->d_lock);
+			dentry->d_flags |= DCACHE_NOKEY_NAME;
+			spin_unlock(&dentry->d_lock);
+		}
+	}
 
 	if (flags & O_CREAT) {
 		struct ceph_file_layout lo;
Signature · 1 line
2.35.1
#26 lore raw

PATCH v13 26/59 ceph: make d_revalidate call fscrypt revalidator for encrypted dentries

In reply to Jeff Layton

If we have a dentry which represents a no-key name, then we need to test whether the parent directory's encryption key has since been added. Do that before we test anything else about the dentry.

---
 fs/ceph/dir.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
fs/ceph/dir.c +6 -2
index 897f8618151b..caf2547c3fe1 100644
@@ -1709,6 +1709,10 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	struct inode *dir, *inode;
 	struct ceph_mds_client *mdsc;
 
+	valid = fscrypt_d_revalidate(dentry, flags);
+	if (valid <= 0)
+		return valid;
+
 	if (flags & LOOKUP_RCU) {
 		parent = READ_ONCE(dentry->d_parent);
 		dir = d_inode_rcu(parent);
@@ -1721,8 +1725,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		inode = d_inode(dentry);
 	}
 
-	dout("d_revalidate %p '%pd' inode %p offset 0x%llx\n", dentry,
-	     dentry, inode, ceph_dentry(dentry)->offset);
+	dout("d_revalidate %p '%pd' inode %p offset 0x%llx nokey %d\n", dentry,
+	     dentry, inode, ceph_dentry(dentry)->offset, !!(dentry->d_flags & DCACHE_NOKEY_NAME));
 
 	mdsc = ceph_sb_to_client(dir->i_sb)->mdsc;
 
Signature · 1 line
2.35.1
#29 lore raw

PATCH v13 29/59 ceph: add fscrypt support to ceph_fill_trace

In reply to Jeff Layton

When we get a dentry in a trace, decrypt the name so we can properly instantiate the dentry.

---
 fs/ceph/inode.c | 30 ++++++++++++++++++++++++++++--
 1 file changed, 28 insertions(+), 2 deletions(-)
fs/ceph/inode.c +28 -2
index 4cbc303730ef..37c2c2977235 100644
@@ -1405,8 +1405,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 		if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME &&
 		    test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
 		    !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
+			bool is_nokey = false;
 			struct qstr dname;
 			struct dentry *dn, *parent;
+			struct fscrypt_str oname = FSTR_INIT(NULL, 0);
+			struct ceph_fname fname = { .dir	= dir,
+						    .name	= rinfo->dname,
+						    .ctext	= rinfo->altname,
+						    .name_len	= rinfo->dname_len,
+						    .ctext_len	= rinfo->altname_len };
 
 			BUG_ON(!rinfo->head->is_target);
 			BUG_ON(req->r_dentry);
@@ -1414,8 +1421,20 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 			parent = d_find_any_alias(dir);
 			BUG_ON(!parent);
 
-			dname.name = rinfo->dname;
-			dname.len = rinfo->dname_len;
+			err = ceph_fname_alloc_buffer(dir, &oname);
+			if (err < 0) {
+				dput(parent);
+				goto done;
+			}
+
+			err = ceph_fname_to_usr(&fname, NULL, &oname, &is_nokey);
+			if (err < 0) {
+				dput(parent);
+				ceph_fname_free_buffer(dir, &oname);
+				goto done;
+			}
+			dname.name = oname.name;
+			dname.len = oname.len;
 			dname.hash = full_name_hash(parent, dname.name, dname.len);
 			tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
 			tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
@@ -1430,9 +1449,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 				     dname.len, dname.name, dn);
 				if (!dn) {
 					dput(parent);
+					ceph_fname_free_buffer(dir, &oname);
 					err = -ENOMEM;
 					goto done;
 				}
+				if (is_nokey) {
+					spin_lock(&dn->d_lock);
+					dn->d_flags |= DCACHE_NOKEY_NAME;
+					spin_unlock(&dn->d_lock);
+				}
 				err = 0;
 			} else if (d_really_is_positive(dn) &&
 				   (ceph_ino(d_inode(dn)) != tvino.ino ||
@@ -1444,6 +1469,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 				dput(dn);
 				goto retry_lookup;
 			}
+			ceph_fname_free_buffer(dir, &oname);
 
 			req->r_dentry = dn;
 			dput(parent);
Signature · 1 line
2.35.1
#18 lore raw

PATCH v13 18/59 ceph: add fscrypt ioctls

In reply to Jeff Layton

We gate most of the ioctls on MDS feature support. The exception is the key removal and status functions that we still want to work if the MDS's were to (inexplicably) lose the feature.

For the set_policy ioctl, we take Fs caps to ensure that nothing can create files in the directory while the ioctl is running. That should be enough to ensure that the "empty_dir" check is reliable.

---
 fs/ceph/ioctl.c | 83 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
fs/ceph/ioctl.c +83 -0
index 6e061bf62ad4..477ecc667aee 100644
@@ -6,6 +6,7 @@
 #include "mds_client.h"
 #include "ioctl.h"
 #include <linux/ceph/striper.h>
+#include <linux/fscrypt.h>
 
 /*
  * ioctls
@@ -268,8 +269,54 @@ static long ceph_ioctl_syncio(struct file *file)
 	return 0;
 }
 
+static int vet_mds_for_fscrypt(struct file *file)
+{
+	int i, ret = -EOPNOTSUPP;
+	struct ceph_mds_client	*mdsc = ceph_sb_to_mdsc(file_inode(file)->i_sb);
+
+	mutex_lock(&mdsc->mutex);
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		struct ceph_mds_session *s = mdsc->sessions[i];
+
+		if (!s)
+			continue;
+		if (test_bit(CEPHFS_FEATURE_ALTERNATE_NAME, &s->s_features))
+			ret = 0;
+		break;
+	}
+	mutex_unlock(&mdsc->mutex);
+	return ret;
+}
+
+static long ceph_set_encryption_policy(struct file *file, unsigned long arg)
+{
+	int ret, got = 0;
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	ret = vet_mds_for_fscrypt(file);
+	if (ret)
+		return ret;
+
+	/*
+	 * Ensure we hold these caps so that we _know_ that the rstats check
+	 * in the empty_dir check is reliable.
+	 */
+	ret = ceph_get_caps(file, CEPH_CAP_FILE_SHARED, 0, -1, &got);
+	if (ret)
+		return ret;
+
+	ret = fscrypt_ioctl_set_policy(file, (const void __user *)arg);
+	if (got)
+		ceph_put_cap_refs(ci, got);
+
+	return ret;
+}
+
 long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
+	int ret;
+
 	dout("ioctl file %p cmd %u arg %lu\n", file, cmd, arg);
 	switch (cmd) {
 	case CEPH_IOC_GET_LAYOUT:
@@ -289,6 +336,42 @@ long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	case CEPH_IOC_SYNCIO:
 		return ceph_ioctl_syncio(file);
+
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+		return ceph_set_encryption_policy(file, arg);
+
+	case FS_IOC_GET_ENCRYPTION_POLICY:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_get_policy(file, (void __user *)arg);
+
+	case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_get_policy_ex(file, (void __user *)arg);
+
+	case FS_IOC_ADD_ENCRYPTION_KEY:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_add_key(file, (void __user *)arg);
+
+	case FS_IOC_REMOVE_ENCRYPTION_KEY:
+		return fscrypt_ioctl_remove_key(file, (void __user *)arg);
+
+	case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS:
+		return fscrypt_ioctl_remove_key_all_users(file, (void __user *)arg);
+
+	case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
+		return fscrypt_ioctl_get_key_status(file, (void __user *)arg);
+
+	case FS_IOC_GET_ENCRYPTION_NONCE:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_get_nonce(file, (void __user *)arg);
 	}
 
 	return -ENOTTY;
Signature · 1 line
2.35.1
#36 lore raw

PATCH v13 36/59 ceph: add some fscrypt guardrails

In reply to Jeff Layton

Add the appropriate calls into fscrypt for various actions, including link, rename, setattr, and the open codepaths.

---
 fs/ceph/dir.c   |  8 ++++++++
 fs/ceph/file.c  | 14 +++++++++++++-
 fs/ceph/inode.c |  4 ++++
 3 files changed, 25 insertions(+), 1 deletion(-)
fs/ceph/dir.c +8 -0
index 82a5f37e9d4a..8a9f916bfc6c 100644
@@ -1121,6 +1121,10 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 	if (ceph_snap(dir) != CEPH_NOSNAP)
 		return -EROFS;
 
+	err = fscrypt_prepare_link(old_dentry, dir, dentry);
+	if (err)
+		return err;
+
 	dout("link in dir %p old_dentry %p dentry %p\n", dir,
 	     old_dentry, dentry);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LINK, USE_AUTH_MDS);
@@ -1318,6 +1322,10 @@ static int ceph_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 	    (!ceph_quota_is_same_realm(old_dir, new_dir)))
 		return -EXDEV;
 
+	err = fscrypt_prepare_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
+	if (err)
+		return err;
+
 	dout("rename dir %p dentry %p to dir %p dentry %p\n",
 	     old_dir, old_dentry, new_dir, new_dentry);
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
fs/ceph/file.c +13 -1
index dfc02caf4229..a3afdb9cfddb 100644
@@ -372,8 +372,13 @@ int ceph_open(struct inode *inode, struct file *file)
 
 	/* filter out O_CREAT|O_EXCL; vfs did that already.  yuck. */
 	flags = file->f_flags & ~(O_CREAT|O_EXCL);
-	if (S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode)) {
 		flags = O_DIRECTORY;  /* mds likes to know */
+	} else if (S_ISREG(inode->i_mode)) {
+		err = fscrypt_file_open(inode, file);
+		if (err)
+			return err;
+	}
 
 	dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
 	     ceph_vinop(inode), file, flags, file->f_flags);
@@ -847,6 +852,13 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		dout("atomic_open finish_no_open on dn %p\n", dn);
 		err = finish_no_open(file, dn);
 	} else {
+		if (IS_ENCRYPTED(dir) &&
+		    !fscrypt_has_permitted_context(dir, d_inode(dentry))) {
+			pr_warn("Inconsistent encryption context (parent %llx:%llx child %llx:%llx)\n",
+				ceph_vinop(dir), ceph_vinop(d_inode(dentry)));
+			goto out_req;
+		}
+
 		dout("atomic_open finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
 			struct inode *newino = d_inode(dentry);
fs/ceph/inode.c +4 -0
index bb1b1a57970c..183b9f52dc7d 100644
@@ -2487,6 +2487,10 @@ int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
+	err = fscrypt_prepare_setattr(dentry, attr);
+	if (err)
+		return err;
+
 	err = setattr_prepare(&init_user_ns, dentry, attr);
 	if (err != 0)
 		return err;
Signature · 1 line
2.35.1
#43 lore raw

PATCH v13 43/59 ceph: update WARN_ON message to pr_warn

In reply to Jeff Layton

Give some more helpful info

---
 fs/ceph/caps.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
fs/ceph/caps.c +7 -4
index 1f3a2135214c..cb2c18d43946 100644
@@ -3473,10 +3473,13 @@ static void handle_cap_grant(struct inode *inode,
 		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
 		     from_kuid(&init_user_ns, inode->i_uid),
 		     from_kgid(&init_user_ns, inode->i_gid));
-
-		WARN_ON_ONCE(ci->fscrypt_auth_len != extra_info->fscrypt_auth_len ||
-			     memcmp(ci->fscrypt_auth, extra_info->fscrypt_auth,
-				     ci->fscrypt_auth_len));
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+		if (ci->fscrypt_auth_len != extra_info->fscrypt_auth_len ||
+		    memcmp(ci->fscrypt_auth, extra_info->fscrypt_auth,
+			   ci->fscrypt_auth_len))
+			pr_warn_ratelimited("%s: cap grant attempt to change fscrypt_auth on non-I_NEW inode (old len %d new len %d)\n",
+				__func__, ci->fscrypt_auth_len, extra_info->fscrypt_auth_len);
+#endif
 	}
 
 	if ((newcaps & CEPH_CAP_LINK_SHARED) &&
Signature · 1 line
2.35.1
#37 lore raw

PATCH v13 37/59 ceph: don't allow changing layout on encrypted files/directories

In reply to Jeff Layton

From: Luis Henriques <[email protected]>

Encryption is currently only supported on files/directories with layouts where stripe_count=1. Forbid changing layouts when encryption is involved.

---
 fs/ceph/ioctl.c | 4 ++++
 1 file changed, 4 insertions(+)
fs/ceph/ioctl.c +4 -0
index b9f0f4e460ab..9675ef3a6c47 100644
@@ -294,6 +294,10 @@ static long ceph_set_encryption_policy(struct file *file, unsigned long arg)
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
+	/* encrypted directories can't have striped layout */
+	if (ci->i_layout.stripe_count > 1)
+		return -EINVAL;
+
 	ret = vet_mds_for_fscrypt(file);
 	if (ret)
 		return ret;
Signature · 1 line
2.35.1
#58 lore raw

PATCH v13 58/59 ceph: add encryption support to writepage

In reply to Jeff Layton

Allow writepage to issue encrypted writes. Extend out the requested size and offset to cover complete blocks, and then encrypt and write them to the OSDs.

---
 fs/ceph/addr.c | 34 +++++++++++++++++++++++++++-------
 1 file changed, 27 insertions(+), 7 deletions(-)
fs/ceph/addr.c +27 -7
index bcb74b1d46bb..ff015f251fcc 100644
@@ -584,10 +584,12 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	loff_t page_off = page_offset(page);
 	int err;
 	loff_t len = thp_size(page);
+	loff_t wlen;
 	struct ceph_writeback_ctl ceph_wbc;
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_osd_request *req;
 	bool caching = ceph_is_cache_enabled(inode);
+	struct page *bounce_page = NULL;
 
 	dout("writepage %p idx %lu\n", page, page->index);
 
@@ -619,6 +621,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 
 	if (ceph_wbc.i_size < page_off + len)
 		len = ceph_wbc.i_size - page_off;
+	if (IS_ENCRYPTED(inode))
+		wlen = round_up(len, CEPH_FSCRYPT_BLOCK_SIZE);
 
 	dout("writepage %p page %p index %lu on %llu~%llu snapc %p seq %lld\n",
 	     inode, page, page->index, page_off, len, snapc, snapc->seq);
@@ -627,22 +631,37 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
 		fsc->write_congested = true;
 
-	req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1,
-				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc,
-				    ceph_wbc.truncate_seq, ceph_wbc.truncate_size,
-				    true);
+	req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode),
+				    page_off, &wlen, 0, 1, CEPH_OSD_OP_WRITE,
+				    CEPH_OSD_FLAG_WRITE, snapc,
+				    ceph_wbc.truncate_seq,
+				    ceph_wbc.truncate_size, true);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	if (wlen < len)
+		len = wlen;
+
 	set_page_writeback(page);
 	if (caching)
 		ceph_set_page_fscache(page);
 	ceph_fscache_write_to_cache(inode, page_off, len, caching);
 
+	if (IS_ENCRYPTED(inode)) {
+		bounce_page = fscrypt_encrypt_pagecache_blocks(page, CEPH_FSCRYPT_BLOCK_SIZE,
+								0, GFP_NOFS);
+		if (IS_ERR(bounce_page)) {
+			err = PTR_ERR(bounce_page);
+			goto out;
+		}
+	}
 	/* it may be a short write due to an object boundary */
 	WARN_ON_ONCE(len > thp_size(page));
-	osd_req_op_extent_osd_data_pages(req, 0, &page, len, 0, false, false);
-	dout("writepage %llu~%llu (%llu bytes)\n", page_off, len, len);
+	osd_req_op_extent_osd_data_pages(req, 0,
+			bounce_page ? &bounce_page : &page, wlen, 0,
+			false, false);
+	dout("writepage %llu~%llu (%llu bytes, %sencrypted)\n",
+	     page_off, len, wlen, IS_ENCRYPTED(inode) ? "" : "not ");
 
 	req->r_mtime = inode->i_mtime;
 	err = ceph_osdc_start_request(osdc, req, true);
@@ -651,7 +670,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 
 	ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				  req->r_end_latency, len, err);
-
+	fscrypt_free_bounce_page(bounce_page);
+out:
 	ceph_osdc_put_request(req);
 	if (err == 0)
 		err = len;
Signature · 1 line
2.35.1
#1 lore raw

PATCH v13 1/59 libceph: add spinlock around osd->o_requests

In reply to Jeff Layton

In a later patch, we're going to need to search for a request in the rbtree, but taking the o_mutex is inconvenient as we already hold the con mutex at the point where we need it.

Add a new spinlock that we take when inserting and erasing entries from the o_requests tree. Search of the rbtree can be done with either the mutex or the spinlock, but insertion and removal requires both.

---
 include/linux/ceph/osd_client.h | 8 +++++++-
 net/ceph/osd_client.c           | 5 +++++
 2 files changed, 12 insertions(+), 1 deletion(-)
include/linux/ceph/osd_client.h +7 -1
index 3431011f364d..3122c1a3205f 100644
@@ -29,7 +29,12 @@ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
 
 #define CEPH_HOMELESS_OSD	-1
 
-/* a given osd we're communicating with */
+/*
+ * A given osd we're communicating with.
+ *
+ * Note that the o_requests tree can be searched while holding the "lock" mutex
+ * or the "o_requests_lock" spinlock. Insertion or removal requires both!
+ */
 struct ceph_osd {
 	refcount_t o_ref;
 	struct ceph_osd_client *o_osdc;
@@ -37,6 +42,7 @@ struct ceph_osd {
 	int o_incarnation;
 	struct rb_node o_node;
 	struct ceph_connection o_con;
+	spinlock_t o_requests_lock;
 	struct rb_root o_requests;
 	struct rb_root o_linger_requests;
 	struct rb_root o_backoff_mappings;
net/ceph/osd_client.c +5 -0
index 83eb97c94e83..17c792b32343 100644
@@ -1198,6 +1198,7 @@ static void osd_init(struct ceph_osd *osd)
 {
 	refcount_set(&osd->o_ref, 1);
 	RB_CLEAR_NODE(&osd->o_node);
+	spin_lock_init(&osd->o_requests_lock);
 	osd->o_requests = RB_ROOT;
 	osd->o_linger_requests = RB_ROOT;
 	osd->o_backoff_mappings = RB_ROOT;
@@ -1427,7 +1428,9 @@ static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req)
 		atomic_inc(&osd->o_osdc->num_homeless);
 
 	get_osd(osd);
+	spin_lock(&osd->o_requests_lock);
 	insert_request(&osd->o_requests, req);
+	spin_unlock(&osd->o_requests_lock);
 	req->r_osd = osd;
 }
 
@@ -1439,7 +1442,9 @@ static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req)
 	     req, req->r_tid);
 
 	req->r_osd = NULL;
+	spin_lock(&osd->o_requests_lock);
 	erase_request(&osd->o_requests, req);
+	spin_unlock(&osd->o_requests_lock);
 	put_osd(osd);
 
 	if (!osd_homeless(osd))
Signature · 1 line
2.35.1
#47 lore raw

PATCH v13 47/59 ceph: add infrastructure for file encryption and decryption

In reply to Jeff Layton

...and allow test_dummy_encryption to bypass content encryption if mounted with test_dummy_encryption=clear.

---
 fs/ceph/crypto.c | 177 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/crypto.h |  71 +++++++++++++++++++
 fs/ceph/super.c  |   8 +++
 fs/ceph/super.h  |   1 +
 4 files changed, 257 insertions(+)
fs/ceph/crypto.c +177 -0
index 19c113afb400..e24e61c51118 100644
@@ -2,6 +2,7 @@
 #include <linux/ceph/ceph_debug.h>
 #include <linux/xattr.h>
 #include <linux/fscrypt.h>
+#include <linux/ceph/striper.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -263,3 +264,179 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 	fscrypt_fname_free_buffer(&_tname);
 	return ret;
 }
+
+int ceph_fscrypt_decrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num)
+{
+	struct ceph_mount_options *opt = ceph_inode_to_client(inode)->mount_options;
+
+	if (opt->flags & CEPH_MOUNT_OPT_DUMMY_ENC_CLEAR)
+		return 0;
+
+	dout("%s: len %u offs %u blk %llu\n", __func__, len, offs, lblk_num);
+	return fscrypt_decrypt_block_inplace(inode, page, len, offs, lblk_num);
+}
+
+int ceph_fscrypt_encrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num, gfp_t gfp_flags)
+{
+	struct ceph_mount_options *opt = ceph_inode_to_client(inode)->mount_options;
+
+	if (opt->flags & CEPH_MOUNT_OPT_DUMMY_ENC_CLEAR)
+		return 0;
+
+	dout("%s: len %u offs %u blk %llu\n", __func__, len, offs, lblk_num);
+	return fscrypt_encrypt_block_inplace(inode, page, len, offs, lblk_num, gfp_flags);
+}
+
+/**
+ * ceph_fscrypt_decrypt_pages - decrypt an array of pages
+ * @inode: pointer to inode associated with these pages
+ * @page: pointer to page array
+ * @off: offset into the file that the read data starts
+ * @len: max length to decrypt
+ *
+ * Decrypt an array of fscrypt'ed pages and return the amount of
+ * data decrypted. Any data in the page prior to the start of the
+ * first complete block in the read is ignored. Any incomplete
+ * crypto blocks at the end of the array are ignored (and should
+ * probably be zeroed by the caller).
+ *
+ * Returns the length of the decrypted data or a negative errno.
+ */
+int ceph_fscrypt_decrypt_pages(struct inode *inode, struct page **page, u64 off, int len)
+{
+	int i, num_blocks;
+	u64 baseblk = off >> CEPH_FSCRYPT_BLOCK_SHIFT;
+	int ret = 0;
+
+	/*
+	 * We can't deal with partial blocks on an encrypted file, so mask off
+	 * the last bit.
+	 */
+	num_blocks = ceph_fscrypt_blocks(off, len & CEPH_FSCRYPT_BLOCK_MASK);
+
+	/* Decrypt each block */
+	for (i = 0; i < num_blocks; ++i) {
+		int blkoff = i << CEPH_FSCRYPT_BLOCK_SHIFT;
+		int pgidx = blkoff >> PAGE_SHIFT;
+		unsigned int pgoffs = offset_in_page(blkoff);
+		int fret;
+
+		fret = ceph_fscrypt_decrypt_block_inplace(inode, page[pgidx],
+				CEPH_FSCRYPT_BLOCK_SIZE, pgoffs,
+				baseblk + i);
+		if (fret < 0) {
+			if (ret == 0)
+				ret = fret;
+			break;
+		}
+		ret += CEPH_FSCRYPT_BLOCK_SIZE;
+	}
+	return ret;
+}
+
+/**
+ * ceph_fscrypt_decrypt_extents: decrypt received extents in given buffer
+ * @inode: inode associated with pages being decrypted
+ * @page: pointer to page array
+ * @off: offset into the file that the data in page[0] starts
+ * @map: pointer to extent array
+ * @ext_cnt: length of extent array
+ *
+ * Given an extent map and a page array, decrypt the received data in-place,
+ * skipping holes. Returns the offset into buffer of end of last decrypted
+ * block.
+ */
+int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page, u64 off,
+				 struct ceph_sparse_extent *map, u32 ext_cnt)
+{
+	int i, ret = 0;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	u64 objno, objoff;
+	u32 xlen;
+
+	/* Nothing to do for empty array */
+	if (ext_cnt == 0) {
+		dout("%s: empty array, ret 0\n", __func__);
+		return 0;
+	}
+
+	ceph_calc_file_object_mapping(&ci->i_layout, off, map[0].len,
+				      &objno, &objoff, &xlen);
+
+	for (i = 0; i < ext_cnt; ++i) {
+		struct ceph_sparse_extent *ext = &map[i];
+		int pgsoff = ext->off - objoff;
+		int pgidx = pgsoff >> PAGE_SHIFT;
+		int fret;
+
+		if ((ext->off | ext->len) & ~CEPH_FSCRYPT_BLOCK_MASK) {
+			pr_warn("%s: bad encrypted sparse extent idx %d off %llx len %llx\n",
+				__func__, i, ext->off, ext->len);
+			return -EIO;
+		}
+		fret = ceph_fscrypt_decrypt_pages(inode, &page[pgidx],
+						 off + pgsoff, ext->len);
+		dout("%s: [%d] 0x%llx~0x%llx fret %d\n", __func__, i,
+				ext->off, ext->len, fret);
+		if (fret < 0) {
+			if (ret == 0)
+				ret = fret;
+			break;
+		}
+		ret = pgsoff + fret;
+	}
+	dout("%s: ret %d\n", __func__, ret);
+	return ret;
+}
+
+/**
+ * ceph_fscrypt_encrypt_pages - encrypt an array of pages
+ * @inode: pointer to inode associated with these pages
+ * @page: pointer to page array
+ * @off: offset into the file that the data starts
+ * @len: max length to encrypt
+ * @gfp: gfp flags to use for allocation
+ *
+ * Decrypt an array of cleartext pages and return the amount of
+ * data encrypted. Any data in the page prior to the start of the
+ * first complete block in the read is ignored. Any incomplete
+ * crypto blocks at the end of the array are ignored.
+ *
+ * Returns the length of the encrypted data or a negative errno.
+ */
+int ceph_fscrypt_encrypt_pages(struct inode *inode, struct page **page, u64 off,
+				int len, gfp_t gfp)
+{
+	int i, num_blocks;
+	u64 baseblk = off >> CEPH_FSCRYPT_BLOCK_SHIFT;
+	int ret = 0;
+
+	/*
+	 * We can't deal with partial blocks on an encrypted file, so mask off
+	 * the last bit.
+	 */
+	num_blocks = ceph_fscrypt_blocks(off, len & CEPH_FSCRYPT_BLOCK_MASK);
+
+	/* Encrypt each block */
+	for (i = 0; i < num_blocks; ++i) {
+		int blkoff = i << CEPH_FSCRYPT_BLOCK_SHIFT;
+		int pgidx = blkoff >> PAGE_SHIFT;
+		unsigned int pgoffs = offset_in_page(blkoff);
+		int fret;
+
+		fret = ceph_fscrypt_encrypt_block_inplace(inode, page[pgidx],
+				CEPH_FSCRYPT_BLOCK_SIZE, pgoffs,
+				baseblk + i, gfp);
+		if (fret < 0) {
+			if (ret == 0)
+				ret = fret;
+			break;
+		}
+		ret += CEPH_FSCRYPT_BLOCK_SIZE;
+	}
+	return ret;
+}
fs/ceph/crypto.h +71 -0

83 lines not on this page · raw message

fs/ceph/super.c +8 -0
index a1f921d5675d..70cd1dcad645 100644
@@ -1093,6 +1093,14 @@ static int ceph_set_test_dummy_encryption(struct super_block *sb, struct fs_cont
 			return -EEXIST;
 		}
 
+		/* HACK: allow for cleartext "encryption" in files for testing */
+		if (fsc->mount_options->test_dummy_encryption &&
+		    !strcmp(fsc->mount_options->test_dummy_encryption, "clear")) {
+			fsopt->flags |= CEPH_MOUNT_OPT_DUMMY_ENC_CLEAR;
+			kfree(fsc->mount_options->test_dummy_encryption);
+			fsc->mount_options->test_dummy_encryption = NULL;
+		}
+
 		err = fscrypt_set_test_dummy_encryption(sb,
 							fsc->mount_options->test_dummy_encryption,
 							&fsc->dummy_enc_policy);
fs/ceph/super.h +1 -0
index 9809bc97b89e..9c205c6967b7 100644
@@ -44,6 +44,7 @@
 #define CEPH_MOUNT_OPT_NOPAGECACHE     (1<<16) /* bypass pagecache altogether */
 #define CEPH_MOUNT_OPT_SPARSEREAD      (1<<17) /* always do sparse reads */
 #define CEPH_MOUNT_OPT_TEST_DUMMY_ENC  (1<<18) /* enable dummy encryption (for testing) */
+#define CEPH_MOUNT_OPT_DUMMY_ENC_CLEAR (1<<19) /* don't actually encrypt content */
 
 #define CEPH_MOUNT_OPT_DEFAULT			\
 	(CEPH_MOUNT_OPT_DCACHE |		\
Signature · 1 line
2.35.1
#51 lore raw

PATCH v13 51/59 ceph: disable copy offload on encrypted inodes

In reply to Jeff Layton

If we have an encrypted inode, then the client will need to re-encrypt the contents of the new object. Disable copy offload to or from encrypted inodes.

---
 fs/ceph/file.c | 4 ++++
 1 file changed, 4 insertions(+)
fs/ceph/file.c +4 -0
index f74563e11058..f9e775d6cdf0 100644
@@ -2526,6 +2526,10 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 		return -EOPNOTSUPP;
 	}
 
+	/* Every encrypted inode gets its own key, so we can't offload them */
+	if (IS_ENCRYPTED(src_inode) || IS_ENCRYPTED(dst_inode))
+		return -EOPNOTSUPP;
+
 	if (len < src_ci->i_layout.object_size)
 		return -EOPNOTSUPP; /* no remote copy will be done */
 
Signature · 1 line
2.35.1
#33 lore raw

PATCH v13 33/59 ceph: create symlinks with encrypted and base64-encoded targets

In reply to Jeff Layton

When creating symlinks in encrypted directories, encrypt and base64-encode the target with the new inode's key before sending to the MDS.

When filling a symlinked inode, base64-decode it into a buffer that we'll keep in ci->i_symlink. When get_link is called, decrypt the buffer into a new one that will hang off i_link.

---
 fs/ceph/dir.c   |  51 ++++++++++++++++++++---
 fs/ceph/inode.c | 107 ++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 141 insertions(+), 17 deletions(-)
fs/ceph/dir.c +46 -5
index 5ce2a6384e55..82a5f37e9d4a 100644
@@ -942,6 +942,40 @@ static int ceph_create(struct user_namespace *mnt_userns, struct inode *dir,
 	return ceph_mknod(mnt_userns, dir, dentry, mode, 0);
 }
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+static int prep_encrypted_symlink_target(struct ceph_mds_request *req, const char *dest)
+{
+	int err;
+	int len = strlen(dest);
+	struct fscrypt_str osd_link = FSTR_INIT(NULL, 0);
+
+	err = fscrypt_prepare_symlink(req->r_parent, dest, len, PATH_MAX, &osd_link);
+	if (err)
+		goto out;
+
+	err = fscrypt_encrypt_symlink(req->r_new_inode, dest, len, &osd_link);
+	if (err)
+		goto out;
+
+	req->r_path2 = kmalloc(FSCRYPT_BASE64URL_CHARS(osd_link.len) + 1, GFP_KERNEL);
+	if (!req->r_path2) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	len = fscrypt_base64url_encode(osd_link.name, osd_link.len, req->r_path2);
+	req->r_path2[len] = '\0';
+out:
+	fscrypt_fname_free_buffer(&osd_link);
+	return err;
+}
+#else
+static int prep_encrypted_symlink_target(struct ceph_mds_request *req, const char *dest)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 			struct dentry *dentry, const char *dest)
 {
@@ -973,14 +1007,21 @@ static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 		goto out_req;
 	}
 
-	req->r_path2 = kstrdup(dest, GFP_KERNEL);
-	if (!req->r_path2) {
-		err = -ENOMEM;
-		goto out_req;
-	}
 	req->r_parent = dir;
 	ihold(dir);
 
+	if (IS_ENCRYPTED(req->r_new_inode)) {
+		err = prep_encrypted_symlink_target(req, dest);
+		if (err)
+			goto out_req;
+	} else {
+		req->r_path2 = kstrdup(dest, GFP_KERNEL);
+		if (!req->r_path2) {
+			err = -ENOMEM;
+			goto out_req;
+		}
+	}
+
 	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
fs/ceph/inode.c +95 -12

158 lines not on this page · raw message

Signature · 1 line
2.35.1
#0 lore raw

v13 cover ceph+fscrypt: full support

Yet another ceph+fscrypt posting! This time, I've included the revised sparse read support patches as they have gotten some small revisions and the main impetus for them is fscrypt anyway.

The main changes since v12:

- rebased onto v5.18-rc1 and fixed up minor merge conflicts :w

- some minor cleanups and simplifications to the sparse_read infrastructure

- dropped a patch from Luis that added a legacy v1 key prefix. He's pursuing a more appropriate userland fix for xfstests instead

- the patch to add has_stable_inodes operation to ceph has been dropped. That operation is only applicable for special storage hardware, so it has no purpose on ceph.

- the patch to export new_inode_pseudo has been replaced with one that changes the I_CREATING test in inode_insert5. This allows us to use new_inode instead.

For now, I've dropped these from the ceph-client/testing branch, but I'll plan to merge them again in a couple of weeks once we rebase ceph-client/master onto a v5.18-rc release (usually around -rc2 or -rc3).

Jeff Layton (49):
libceph: add spinlock around osd->o_requests
libceph: define struct ceph_sparse_extent and add some helpers
libceph: add sparse read support to msgr2 crc state machine
libceph: add sparse read support to OSD client
libceph: support sparse reads on msgr2 secure codepath
libceph: add sparse read support to msgr1
ceph: add new mount option to enable sparse reads
fs: change test in inode_insert5 for adding to the sb list
fscrypt: export fscrypt_base64url_encode and fscrypt_base64url_decode
fscrypt: export fscrypt_fname_encrypt and fscrypt_fname_encrypted_size
fscrypt: add fscrypt_context_for_new_inode
ceph: preallocate inode for ops that may create one
ceph: fscrypt_auth handling for ceph
ceph: ensure that we accept a new context from MDS for new inodes
ceph: add support for fscrypt_auth/fscrypt_file to cap messages
ceph: implement -o test_dummy_encryption mount option
ceph: decode alternate_name in lease info
ceph: add fscrypt ioctls
ceph: make ceph_msdc_build_path use ref-walk
ceph: add encrypted fname handling to ceph_mdsc_build_path
ceph: send altname in MClientRequest
ceph: encode encrypted name in dentry release
ceph: properly set DCACHE_NOKEY_NAME flag in lookup
ceph: set DCACHE_NOKEY_NAME in atomic open
ceph: make d_revalidate call fscrypt revalidator for encrypted
dentries
ceph: add helpers for converting names for userland presentation
ceph: add fscrypt support to ceph_fill_trace
ceph: create symlinks with encrypted and base64-encoded targets
ceph: make ceph_get_name decrypt filenames
ceph: add a new ceph.fscrypt.auth vxattr
ceph: add some fscrypt guardrails
libceph: add CEPH_OSD_OP_ASSERT_VER support
ceph: size handling for encrypted inodes in cap updates
ceph: fscrypt_file field handling in MClientRequest messages
ceph: get file size from fscrypt_file when present in inode traces
ceph: handle fscrypt fields in cap messages from MDS
ceph: update WARN_ON message to pr_warn
ceph: add infrastructure for file encryption and decryption
libceph: allow ceph_osdc_new_request to accept a multi-op read
ceph: disable fallocate for encrypted inodes
ceph: disable copy offload on encrypted inodes
ceph: don't use special DIO path for encrypted inodes
ceph: align data in pages in ceph_sync_write
ceph: add read/modify/write to ceph_sync_write
ceph: plumb in decryption during sync reads
ceph: add fscrypt decryption support to ceph_netfs_issue_op
ceph: set i_blkbits to crypto block size for encrypted inodes
ceph: add encryption support to writepage
ceph: fscrypt support for writepages

Luis Henriques (1):
ceph: don't allow changing layout on encrypted files/directories

Xiubo Li (9):
ceph: make the ioctl cmd more readable in debug log
ceph: fix base64 encoded name's length check in ceph_fname_to_usr()
ceph: pass the request to parse_reply_info_readdir()
ceph: add ceph_encode_encrypted_dname() helper
ceph: add support to readdir for encrypted filenames
ceph: add __ceph_get_caps helper support
ceph: add __ceph_sync_read helper support
ceph: add object version support for sync read
ceph: add truncate size handling support for fscrypt

 fs/ceph/Makefile                |   1 +
 fs/ceph/acl.c                   |   4 +-
 fs/ceph/addr.c                  | 136 ++++++--
 fs/ceph/caps.c                  | 219 ++++++++++--
 fs/ceph/crypto.c                | 442 ++++++++++++++++++++++++
 fs/ceph/crypto.h                | 256 ++++++++++++++
 fs/ceph/dir.c                   | 182 +++++++---
 fs/ceph/export.c                |  44 ++-
 fs/ceph/file.c                  | 579 +++++++++++++++++++++++++++-----
 fs/ceph/inode.c                 | 546 +++++++++++++++++++++++++++---
 fs/ceph/ioctl.c                 | 126 ++++++-
 fs/ceph/mds_client.c            | 465 +++++++++++++++++++++----
 fs/ceph/mds_client.h            |  24 +-
 fs/ceph/super.c                 | 107 +++++-
 fs/ceph/super.h                 |  43 ++-
 fs/ceph/xattr.c                 |  29 ++
 fs/crypto/fname.c               |  44 ++-
 fs/crypto/fscrypt_private.h     |   9 +-
 fs/crypto/hooks.c               |   6 +-
 fs/crypto/policy.c              |  35 +-
 fs/inode.c                      |  11 +-
 include/linux/ceph/ceph_fs.h    |  21 +-
 include/linux/ceph/messenger.h  |  32 ++
 include/linux/ceph/osd_client.h |  89 ++++-
 include/linux/ceph/rados.h      |   4 +
 include/linux/fscrypt.h         |  10 +
 net/ceph/messenger.c            |   1 +
 net/ceph/messenger_v1.c         |  98 +++++-
 net/ceph/messenger_v2.c         | 287 ++++++++++++++--
 net/ceph/osd_client.c           | 306 ++++++++++++++++-
 30 files changed, 3753 insertions(+), 403 deletions(-)
 create mode 100644 fs/ceph/crypto.c
 create mode 100644 fs/ceph/crypto.h
Signature · 1 line
2.35.1
#16 lore raw

PATCH v13 16/59 ceph: implement -o test_dummy_encryption mount option

Add support for the test_dummy_encryption mount option. This allows us to test the encrypted codepaths in ceph without having to manually set keys, etc.

---
 fs/ceph/crypto.c | 53 ++++++++++++++++++++++++++++++++
 fs/ceph/crypto.h | 26 ++++++++++++++++
 fs/ceph/inode.c  | 10 ++++--
 fs/ceph/super.c  | 80 ++++++++++++++++++++++++++++++++++++++++++++++--
 fs/ceph/super.h  | 10 +++++-
 fs/ceph/xattr.c  |  3 ++
 6 files changed, 176 insertions(+), 6 deletions(-)
fs/ceph/crypto.c +53 -0
index a513ff373b13..1c34b8ed1266 100644
@@ -4,6 +4,7 @@
 #include <linux/fscrypt.h>
 
 #include "super.h"
+#include "mds_client.h"
 #include "crypto.h"
 
 static int ceph_crypt_get_context(struct inode *inode, void *ctx, size_t len)
@@ -64,9 +65,15 @@ static bool ceph_crypt_empty_dir(struct inode *inode)
 	return ci->i_rsubdirs + ci->i_rfiles == 1;
 }
 
+static const union fscrypt_policy *ceph_get_dummy_policy(struct super_block *sb)
+{
+	return ceph_sb_to_client(sb)->dummy_enc_policy.policy;
+}
+
 static struct fscrypt_operations ceph_fscrypt_ops = {
 	.get_context		= ceph_crypt_get_context,
 	.set_context		= ceph_crypt_set_context,
+	.get_dummy_policy	= ceph_get_dummy_policy,
 	.empty_dir		= ceph_crypt_empty_dir,
 };
 
@@ -74,3 +81,49 @@ void ceph_fscrypt_set_ops(struct super_block *sb)
 {
 	fscrypt_set_ops(sb, &ceph_fscrypt_ops);
 }
+
+void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc)
+{
+	fscrypt_free_dummy_policy(&fsc->dummy_enc_policy);
+}
+
+int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
+				 struct ceph_acl_sec_ctx *as)
+{
+	int ret, ctxsize;
+	bool encrypted = false;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	ret = fscrypt_prepare_new_inode(dir, inode, &encrypted);
+	if (ret)
+		return ret;
+	if (!encrypted)
+		return 0;
+
+	as->fscrypt_auth = kzalloc(sizeof(*as->fscrypt_auth), GFP_KERNEL);
+	if (!as->fscrypt_auth)
+		return -ENOMEM;
+
+	ctxsize = fscrypt_context_for_new_inode(as->fscrypt_auth->cfa_blob, inode);
+	if (ctxsize < 0)
+		return ctxsize;
+
+	as->fscrypt_auth->cfa_version = cpu_to_le32(CEPH_FSCRYPT_AUTH_VERSION);
+	as->fscrypt_auth->cfa_blob_len = cpu_to_le32(ctxsize);
+
+	WARN_ON_ONCE(ci->fscrypt_auth);
+	kfree(ci->fscrypt_auth);
+	ci->fscrypt_auth_len = ceph_fscrypt_auth_len(as->fscrypt_auth);
+	ci->fscrypt_auth = kmemdup(as->fscrypt_auth, ci->fscrypt_auth_len, GFP_KERNEL);
+	if (!ci->fscrypt_auth)
+		return -ENOMEM;
+
+	inode->i_flags |= S_ENCRYPTED;
+
+	return 0;
+}
+
+void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_sec_ctx *as)
+{
+	swap(req->r_fscrypt_auth, as->fscrypt_auth);
+}
fs/ceph/crypto.h +26 -0
index 6dca674f79b8..cb00fe42d5b7 100644
@@ -8,6 +8,10 @@
 
 #include <linux/fscrypt.h>
 
+struct ceph_fs_client;
+struct ceph_acl_sec_ctx;
+struct ceph_mds_request;
+
 struct ceph_fscrypt_auth {
 	__le32	cfa_version;
 	__le32	cfa_blob_len;
@@ -25,12 +29,34 @@ static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa)
 #ifdef CONFIG_FS_ENCRYPTION
 void ceph_fscrypt_set_ops(struct super_block *sb);
 
+void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc);
+
+int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
+				 struct ceph_acl_sec_ctx *as);
+void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_sec_ctx *as);
+
 #else /* CONFIG_FS_ENCRYPTION */
 
 static inline void ceph_fscrypt_set_ops(struct super_block *sb)
 {
 }
 
+static inline void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc)
+{
+}
+
+static inline int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
+						struct ceph_acl_sec_ctx *as)
+{
+	if (IS_ENCRYPTED(dir))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static inline void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
+						struct ceph_acl_sec_ctx *as_ctx)
+{
+}
 #endif /* CONFIG_FS_ENCRYPTION */
 
 #endif
fs/ceph/inode.c +8 -2
index 9a5641b37978..4cbc303730ef 100644
@@ -83,12 +83,17 @@ struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
 			goto out_err;
 	}
 
+	inode->i_state = 0;
+	inode->i_mode = *mode;
+
 	err = ceph_security_init_secctx(dentry, *mode, as_ctx);
 	if (err < 0)
 		goto out_err;
 
-	inode->i_state = 0;
-	inode->i_mode = *mode;
+	err = ceph_fscrypt_prepare_context(dir, inode, as_ctx);
+	if (err)
+		goto out_err;
+
 	return inode;
 out_err:
 	iput(inode);
@@ -101,6 +106,7 @@ void ceph_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_sec_ctx *a
 		req->r_pagelist = as_ctx->pagelist;
 		as_ctx->pagelist = NULL;
 	}
+	ceph_fscrypt_as_ctx_to_req(req, as_ctx);
 }
 
 /**
fs/ceph/super.c +77 -3

148 lines not on this page · raw message

fs/ceph/super.h +9 -1
index a4dc7b81a6a4..a97a6f6f3089 100644
@@ -21,6 +21,7 @@
 #include <linux/fscache.h>
 
 #include <linux/ceph/libceph.h>
+#include "crypto.h"
 
 /* large granularity for statfs utilization stats to facilitate
  * large volume sizes on 32-bit machines. */
@@ -42,6 +43,7 @@
 #define CEPH_MOUNT_OPT_ASYNC_DIROPS    (1<<15) /* allow async directory ops */
 #define CEPH_MOUNT_OPT_NOPAGECACHE     (1<<16) /* bypass pagecache altogether */
 #define CEPH_MOUNT_OPT_SPARSEREAD      (1<<17) /* always do sparse reads */
+#define CEPH_MOUNT_OPT_TEST_DUMMY_ENC  (1<<18) /* enable dummy encryption (for testing) */
 
 #define CEPH_MOUNT_OPT_DEFAULT			\
 	(CEPH_MOUNT_OPT_DCACHE |		\
@@ -98,6 +100,7 @@ struct ceph_mount_options {
 	char *server_path;    /* default NULL (means "/") */
 	char *fscache_uniq;   /* default NULL */
 	char *mon_addr;
+	char *test_dummy_encryption;	/* default NULL */
 };
 
 struct ceph_fs_client {
@@ -138,9 +141,11 @@ struct ceph_fs_client {
 #ifdef CONFIG_CEPH_FSCACHE
 	struct fscache_volume *fscache;
 #endif
+#ifdef CONFIG_FS_ENCRYPTION
+	struct fscrypt_dummy_policy dummy_enc_policy;
+#endif
 };
 
-
 /*
  * File i/o capability.  This tracks shared state with the metadata
  * server that allows us to cache or writeback attributes or to read
@@ -1084,6 +1089,9 @@ struct ceph_acl_sec_ctx {
 #ifdef CONFIG_CEPH_FS_SECURITY_LABEL
 	void *sec_ctx;
 	u32 sec_ctxlen;
+#endif
+#ifdef CONFIG_FS_ENCRYPTION
+	struct ceph_fscrypt_auth *fscrypt_auth;
 #endif
 	struct ceph_pagelist *pagelist;
 };
fs/ceph/xattr.c +3 -0
index 8c2dc2c762a4..58628cef4207 100644
@@ -1397,6 +1397,9 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx)
 #endif
 #ifdef CONFIG_CEPH_FS_SECURITY_LABEL
 	security_release_secctx(as_ctx->sec_ctx, as_ctx->sec_ctxlen);
+#endif
+#ifdef CONFIG_FS_ENCRYPTION
+	kfree(as_ctx->fscrypt_auth);
 #endif
 	if (as_ctx->pagelist)
 		ceph_pagelist_release(as_ctx->pagelist);
Signature · 1 line
2.35.1
#6 lore raw

PATCH v13 6/59 libceph: add sparse read support to msgr1

In reply to Jeff Layton

Add 2 new fields to ceph_connection_v1_info to track the necessary info in sparse reads. Skip initializing the cursor for a sparse read.

Break out read_partial_message_section into a wrapper around a new read_partial_message_chunk function that doesn't zero out the crc first.

Add new helper functions to drive receiving into the destinations provided by the sparse_read state machine.

---
 include/linux/ceph/messenger.h |  4 ++
 net/ceph/messenger_v1.c        | 98 +++++++++++++++++++++++++++++++---
 2 files changed, 94 insertions(+), 8 deletions(-)
include/linux/ceph/messenger.h +4 -0
index 7f09a4213834..f4adbfee56d5 100644
@@ -337,6 +337,10 @@ struct ceph_connection_v1_info {
 
 	int in_base_pos;     /* bytes read */
 
+	/* sparse reads */
+	struct kvec in_sr_kvec; /* current location to receive into */
+	u64 in_sr_len;		/* amount of data in this extent */
+
 	/* message in temps */
 	u8 in_tag;           /* protocol control byte */
 	struct ceph_msg_header in_hdr;
net/ceph/messenger_v1.c +90 -8

126 lines not on this page · raw message

Signature · 1 line
2.35.1
#23 lore raw

PATCH v13 23/59 ceph: encode encrypted name in dentry release

In reply to Jeff Layton

Encode encrypted dentry names when sending a dentry release request. Also add a more helpful comment over ceph_encode_dentry_release.

---
 fs/ceph/caps.c       | 32 ++++++++++++++++++++++++++++----
 fs/ceph/mds_client.c | 20 ++++++++++++++++----
 2 files changed, 44 insertions(+), 8 deletions(-)
fs/ceph/caps.c +28 -4
index 3b31d77eb1ea..22bf3e2696cb 100644
@@ -4618,6 +4618,18 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
 	return ret;
 }
 
+/**
+ * ceph_encode_dentry_release - encode a dentry release into an outgoing request
+ * @p: outgoing request buffer
+ * @dentry: dentry to release
+ * @dir: dir to release it from
+ * @mds: mds that we're speaking to
+ * @drop: caps being dropped
+ * @unless: unless we have these caps
+ *
+ * Encode a dentry release into an outgoing request buffer. Returns 1 if the
+ * thing was released, or a negative error code otherwise.
+ */
 int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 			       struct inode *dir,
 			       int mds, int drop, int unless)
@@ -4650,13 +4662,25 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 	if (ret && di->lease_session && di->lease_session->s_mds == mds) {
 		dout("encode_dentry_release %p mds%d seq %d\n",
 		     dentry, mds, (int)di->lease_seq);
-		rel->dname_len = cpu_to_le32(dentry->d_name.len);
-		memcpy(*p, dentry->d_name.name, dentry->d_name.len);
-		*p += dentry->d_name.len;
 		rel->dname_seq = cpu_to_le32(di->lease_seq);
 		__ceph_mdsc_drop_dentry_lease(dentry);
+		spin_unlock(&dentry->d_lock);
+		if (IS_ENCRYPTED(dir) && fscrypt_has_encryption_key(dir)) {
+			int ret2 = ceph_encode_encrypted_fname(dir, dentry, *p);
+
+			if (ret2 < 0)
+				return ret2;
+
+			rel->dname_len = cpu_to_le32(ret2);
+			*p += ret2;
+		} else {
+			rel->dname_len = cpu_to_le32(dentry->d_name.len);
+			memcpy(*p, dentry->d_name.name, dentry->d_name.len);
+			*p += dentry->d_name.len;
+		}
+	} else {
+		spin_unlock(&dentry->d_lock);
 	}
-	spin_unlock(&dentry->d_lock);
 	return ret;
 }
 
fs/ceph/mds_client.c +16 -4
index 0be1668b2c32..750a67643850 100644
@@ -2819,15 +2819,23 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		      req->r_inode ? req->r_inode : d_inode(req->r_dentry),
 		      mds, req->r_inode_drop, req->r_inode_unless,
 		      req->r_op == CEPH_MDS_OP_READDIR);
-	if (req->r_dentry_drop)
-		releases += ceph_encode_dentry_release(&p, req->r_dentry,
+	if (req->r_dentry_drop) {
+		ret = ceph_encode_dentry_release(&p, req->r_dentry,
 				req->r_parent, mds, req->r_dentry_drop,
 				req->r_dentry_unless);
-	if (req->r_old_dentry_drop)
-		releases += ceph_encode_dentry_release(&p, req->r_old_dentry,
+		if (ret < 0)
+			goto out_err;
+		releases += ret;
+	}
+	if (req->r_old_dentry_drop) {
+		ret = ceph_encode_dentry_release(&p, req->r_old_dentry,
 				req->r_old_dentry_dir, mds,
 				req->r_old_dentry_drop,
 				req->r_old_dentry_unless);
+		if (ret < 0)
+			goto out_err;
+		releases += ret;
+	}
 	if (req->r_old_inode_drop)
 		releases += ceph_encode_inode_release(&p,
 		      d_inode(req->r_old_dentry),
@@ -2869,6 +2877,10 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		ceph_mdsc_free_path((char *)path1, pathlen1);
 out:
 	return msg;
+out_err:
+	ceph_msg_put(msg);
+	msg = ERR_PTR(ret);
+	goto out_free2;
 }
 
 /*
Signature · 1 line
2.35.1
#27 lore raw

PATCH v13 27/59 ceph: add helpers for converting names for userland presentation

In reply to Jeff Layton

Define a new ceph_fname struct that we can use to carry information about encrypted dentry names. Add helpers for working with these objects, including ceph_fname_to_usr which formats an encrypted filename for userland presentation.

---
 fs/ceph/crypto.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/crypto.h | 41 ++++++++++++++++++++++++++
 2 files changed, 117 insertions(+)
fs/ceph/crypto.c +76 -0
index a6ee2e3160ca..eefeaa721b9d 100644
@@ -174,3 +174,79 @@ int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentr
 	dout("base64-encoded ciphertext name = %.*s\n", elen, buf);
 	return elen;
 }
+
+/**
+ * ceph_fname_to_usr - convert a filename for userland presentation
+ * @fname: ceph_fname to be converted
+ * @tname: temporary name buffer to use for conversion (may be NULL)
+ * @oname: where converted name should be placed
+ * @is_nokey: set to true if key wasn't available during conversion (may be NULL)
+ *
+ * Given a filename (usually from the MDS), format it for presentation to
+ * userland. If @parent is not encrypted, just pass it back as-is.
+ *
+ * Otherwise, base64 decode the string, and then ask fscrypt to format it
+ * for userland presentation.
+ *
+ * Returns 0 on success or negative error code on error.
+ */
+int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
+		      struct fscrypt_str *oname, bool *is_nokey)
+{
+	int ret;
+	struct fscrypt_str _tname = FSTR_INIT(NULL, 0);
+	struct fscrypt_str iname;
+
+	if (!IS_ENCRYPTED(fname->dir)) {
+		oname->name = fname->name;
+		oname->len = fname->name_len;
+		return 0;
+	}
+
+	/* Sanity check that the resulting name will fit in the buffer */
+	if (fname->name_len > FSCRYPT_BASE64URL_CHARS(NAME_MAX))
+		return -EIO;
+
+	ret = __fscrypt_prepare_readdir(fname->dir);
+	if (ret)
+		return ret;
+
+	/*
+	 * Use the raw dentry name as sent by the MDS instead of
+	 * generating a nokey name via fscrypt.
+	 */
+	if (!fscrypt_has_encryption_key(fname->dir)) {
+		memcpy(oname->name, fname->name, fname->name_len);
+		oname->len = fname->name_len;
+		if (is_nokey)
+			*is_nokey = true;
+		return 0;
+	}
+
+	if (fname->ctext_len == 0) {
+		int declen;
+
+		if (!tname) {
+			ret = fscrypt_fname_alloc_buffer(NAME_MAX, &_tname);
+			if (ret)
+				return ret;
+			tname = &_tname;
+		}
+
+		declen = fscrypt_base64url_decode(fname->name, fname->name_len, tname->name);
+		if (declen <= 0) {
+			ret = -EIO;
+			goto out;
+		}
+		iname.name = tname->name;
+		iname.len = declen;
+	} else {
+		iname.name = fname->ctext;
+		iname.len = fname->ctext_len;
+	}
+
+	ret = fscrypt_fname_disk_to_usr(fname->dir, 0, 0, &iname, oname);
+out:
+	fscrypt_fname_free_buffer(&_tname);
+	return ret;
+}
fs/ceph/crypto.h +41 -0

59 lines not on this page · raw message

Signature · 1 line
2.35.1
#11 lore raw

PATCH v13 11/59 fscrypt: add fscrypt_context_for_new_inode

In reply to Jeff Layton

Most filesystems just call fscrypt_set_context on new inodes, which usually causes a setxattr. That's a bit late for ceph, which can send along a full set of attributes with the create request.

Doing so allows it to avoid race windows that where the new inode could be seen by other clients without the crypto context attached. It also avoids the separate round trip to the server.

Refactor the fscrypt code a bit to allow us to create a new crypto context, attach it to the inode, and write it to the buffer, but without calling set_context on it. ceph can later use this to marshal the context into the attributes we send along with the create request.

---
 fs/crypto/policy.c      | 35 +++++++++++++++++++++++++++++------
 include/linux/fscrypt.h |  1 +
 2 files changed, 30 insertions(+), 6 deletions(-)
fs/crypto/policy.c +29 -6
index ed3d623724cd..ec861af96252 100644
@@ -664,6 +664,32 @@ const union fscrypt_policy *fscrypt_policy_to_inherit(struct inode *dir)
 	return fscrypt_get_dummy_policy(dir->i_sb);
 }
 
+/**
+ * fscrypt_context_for_new_inode() - create an encryption context for a new inode
+ * @ctx: where context should be written
+ * @inode: inode from which to fetch policy and nonce
+ *
+ * Given an in-core "prepared" (via fscrypt_prepare_new_inode) inode,
+ * generate a new context and write it to ctx. ctx _must_ be at least
+ * FSCRYPT_SET_CONTEXT_MAX_SIZE bytes.
+ *
+ * Return: size of the resulting context or a negative error code.
+ */
+int fscrypt_context_for_new_inode(void *ctx, struct inode *inode)
+{
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	BUILD_BUG_ON(sizeof(union fscrypt_context) !=
+			FSCRYPT_SET_CONTEXT_MAX_SIZE);
+
+	/* fscrypt_prepare_new_inode() should have set up the key already. */
+	if (WARN_ON_ONCE(!ci))
+		return -ENOKEY;
+
+	return fscrypt_new_context(ctx, &ci->ci_policy, ci->ci_nonce);
+}
+EXPORT_SYMBOL_GPL(fscrypt_context_for_new_inode);
+
 /**
  * fscrypt_set_context() - Set the fscrypt context of a new inode
  * @inode: a new inode
@@ -680,12 +706,9 @@ int fscrypt_set_context(struct inode *inode, void *fs_data)
 	union fscrypt_context ctx;
 	int ctxsize;
 
-	/* fscrypt_prepare_new_inode() should have set up the key already. */
-	if (WARN_ON_ONCE(!ci))
-		return -ENOKEY;
-
-	BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
-	ctxsize = fscrypt_new_context(&ctx, &ci->ci_policy, ci->ci_nonce);
+	ctxsize = fscrypt_context_for_new_inode(&ctx, inode);
+	if (ctxsize < 0)
+		return ctxsize;
 
 	/*
 	 * This may be the first time the inode number is available, so do any
include/linux/fscrypt.h +1 -0
index 84b363665162..ebe908b20d94 100644
@@ -276,6 +276,7 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg);
 int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg);
 int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child);
+int fscrypt_context_for_new_inode(void *ctx, struct inode *inode);
 int fscrypt_set_context(struct inode *inode, void *fs_data);
 
 struct fscrypt_dummy_policy {
Signature · 1 line
2.35.1
#14 lore raw

PATCH v13 14/59 ceph: ensure that we accept a new context from MDS for new inodes

In reply to Jeff Layton
---
 fs/ceph/inode.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)
fs/ceph/inode.c +11 -10
index 2d9bade892cc..9a5641b37978 100644
@@ -944,6 +944,17 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 	__ceph_update_quota(ci, iinfo->max_bytes, iinfo->max_files);
 
+#ifdef CONFIG_FS_ENCRYPTION
+	if (iinfo->fscrypt_auth_len && (inode->i_state & I_NEW)) {
+		kfree(ci->fscrypt_auth);
+		ci->fscrypt_auth_len = iinfo->fscrypt_auth_len;
+		ci->fscrypt_auth = iinfo->fscrypt_auth;
+		iinfo->fscrypt_auth = NULL;
+		iinfo->fscrypt_auth_len = 0;
+		inode_set_flags(inode, S_ENCRYPTED, S_ENCRYPTED);
+	}
+#endif
+
 	if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
 	    (issued & CEPH_CAP_AUTH_EXCL) == 0) {
 		inode->i_mode = mode;
@@ -1033,16 +1044,6 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 		xattr_blob = NULL;
 	}
 
-#ifdef CONFIG_FS_ENCRYPTION
-	if (iinfo->fscrypt_auth_len && !ci->fscrypt_auth) {
-		ci->fscrypt_auth_len = iinfo->fscrypt_auth_len;
-		ci->fscrypt_auth = iinfo->fscrypt_auth;
-		iinfo->fscrypt_auth = NULL;
-		iinfo->fscrypt_auth_len = 0;
-		inode_set_flags(inode, S_ENCRYPTED, S_ENCRYPTED);
-	}
-#endif
-
 	/* finally update i_version */
 	if (le64_to_cpu(info->version) > ci->i_version)
 		ci->i_version = le64_to_cpu(info->version);
Signature · 1 line
2.35.1
#17 lore raw

PATCH v13 17/59 ceph: decode alternate_name in lease info

In reply to Jeff Layton

Ceph is a bit different from local filesystems, in that we don't want to store filenames as raw binary data, since we may also be dealing with clients that don't support fscrypt.

We could just base64-encode the encrypted filenames, but that could leave us with filenames longer than NAME_MAX. It turns out that the MDS doesn't care much about filename length, but the clients do.

To manage this, we've added a new "alternate name" field that can be optionally added to any dentry that we'll use to store the binary crypttext of the filename if its base64-encoded value will be longer than NAME_MAX. When a dentry has one of these names attached, the MDS will send it along in the lease info, which we can then store for later usage.

---
 fs/ceph/mds_client.c | 43 +++++++++++++++++++++++++++++++++----------
 fs/ceph/mds_client.h | 11 +++++++----
 2 files changed, 40 insertions(+), 14 deletions(-)
fs/ceph/mds_client.c +33 -10
index dcb800675dec..2f2f8221eb25 100644
@@ -308,27 +308,47 @@ static int parse_reply_info_dir(void **p, void *end,
 
 static int parse_reply_info_lease(void **p, void *end,
 				  struct ceph_mds_reply_lease **lease,
-				  u64 features)
+				  u64 features, u32 *altname_len, u8 **altname)
 {
+	u8 struct_v;
+	u32 struct_len;
+	void *lend;
+
 	if (features == (u64)-1) {
-		u8 struct_v, struct_compat;
-		u32 struct_len;
+		u8 struct_compat;
+
 		ceph_decode_8_safe(p, end, struct_v, bad);
 		ceph_decode_8_safe(p, end, struct_compat, bad);
+
 		/* struct_v is expected to be >= 1. we only understand
 		 * encoding whose struct_compat == 1. */
 		if (!struct_v || struct_compat != 1)
 			goto bad;
+
 		ceph_decode_32_safe(p, end, struct_len, bad);
-		ceph_decode_need(p, end, struct_len, bad);
-		end = *p + struct_len;
+	} else {
+		struct_len = sizeof(**lease);
+		*altname_len = 0;
+		*altname = NULL;
 	}
 
-	ceph_decode_need(p, end, sizeof(**lease), bad);
+	lend = *p + struct_len;
+	ceph_decode_need(p, end, struct_len, bad);
 	*lease = *p;
 	*p += sizeof(**lease);
-	if (features == (u64)-1)
-		*p = end;
+
+	if (features == (u64)-1) {
+		if (struct_v >= 2) {
+			ceph_decode_32_safe(p, end, *altname_len, bad);
+			ceph_decode_need(p, end, *altname_len, bad);
+			*altname = *p;
+			*p += *altname_len;
+		} else {
+			*altname = NULL;
+			*altname_len = 0;
+		}
+	}
+	*p = lend;
 	return 0;
 bad:
 	return -EIO;
@@ -358,7 +378,8 @@ static int parse_reply_info_trace(void **p, void *end,
 		info->dname = *p;
 		*p += info->dname_len;
 
-		err = parse_reply_info_lease(p, end, &info->dlease, features);
+		err = parse_reply_info_lease(p, end, &info->dlease, features,
+					     &info->altname_len, &info->altname);
 		if (err < 0)
 			goto out_bad;
 	}
@@ -425,9 +446,11 @@ static int parse_reply_info_readdir(void **p, void *end,
 		dout("parsed dir dname '%.*s'\n", rde->name_len, rde->name);
 
 		/* dentry lease */
-		err = parse_reply_info_lease(p, end, &rde->lease, features);
+		err = parse_reply_info_lease(p, end, &rde->lease, features,
+					     &rde->altname_len, &rde->altname);
 		if (err)
 			goto out_bad;
+
 		/* inode */
 		err = parse_reply_info_in(p, end, &rde->inode, features);
 		if (err < 0)
fs/ceph/mds_client.h +7 -4
index aab3ab284fce..2cc75f9ae7c7 100644
@@ -29,8 +29,8 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_MULTI_RECONNECT,
 	CEPHFS_FEATURE_DELEG_INO,
 	CEPHFS_FEATURE_METRIC_COLLECT,
-
-	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT,
+	CEPHFS_FEATURE_ALTERNATE_NAME,
+	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_ALTERNATE_NAME,
 };
 
 /*
@@ -45,8 +45,7 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_MULTI_RECONNECT,		\
 	CEPHFS_FEATURE_DELEG_INO,		\
 	CEPHFS_FEATURE_METRIC_COLLECT,		\
-						\
-	CEPHFS_FEATURE_MAX,			\
+	CEPHFS_FEATURE_ALTERNATE_NAME,		\
 }
 #define CEPHFS_FEATURES_CLIENT_REQUIRED {}
 
@@ -98,7 +97,9 @@ struct ceph_mds_reply_info_in {
 
 struct ceph_mds_reply_dir_entry {
 	char                          *name;
+	u8			      *altname;
 	u32                           name_len;
+	u32			      altname_len;
 	struct ceph_mds_reply_lease   *lease;
 	struct ceph_mds_reply_info_in inode;
 	loff_t			      offset;
@@ -122,7 +123,9 @@ struct ceph_mds_reply_info_parsed {
 	struct ceph_mds_reply_info_in diri, targeti;
 	struct ceph_mds_reply_dirfrag *dirfrag;
 	char                          *dname;
+	u8			      *altname;
 	u32                           dname_len;
+	u32                           altname_len;
 	struct ceph_mds_reply_lease   *dlease;
 	struct ceph_mds_reply_xattr   xattr_info;
 
Signature · 1 line
2.35.1
#59 lore raw

PATCH v13 59/59 ceph: fscrypt support for writepages

In reply to Jeff Layton

Add the appropriate machinery to write back dirty data with encryption.

---
 fs/ceph/addr.c   | 63 +++++++++++++++++++++++++++++++++++++++---------
 fs/ceph/crypto.h | 18 +++++++++++++-
 2 files changed, 68 insertions(+), 13 deletions(-)
fs/ceph/addr.c +51 -12
index ff015f251fcc..939819a1cf41 100644
@@ -545,10 +545,12 @@ static u64 get_writepages_data_length(struct inode *inode,
 				      struct page *page, u64 start)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_snap_context *snapc = page_snap_context(page);
+	struct ceph_snap_context *snapc;
 	struct ceph_cap_snap *capsnap = NULL;
 	u64 end = i_size_read(inode);
+	u64 ret;
 
+	snapc = page_snap_context(ceph_fscrypt_pagecache_page(page));
 	if (snapc != ci->i_head_snapc) {
 		bool found = false;
 		spin_lock(&ci->i_ceph_lock);
@@ -563,9 +565,12 @@ static u64 get_writepages_data_length(struct inode *inode,
 		spin_unlock(&ci->i_ceph_lock);
 		WARN_ON(!found);
 	}
-	if (end > page_offset(page) + thp_size(page))
-		end = page_offset(page) + thp_size(page);
-	return end > start ? end - start : 0;
+	if (end > ceph_fscrypt_page_offset(page) + thp_size(page))
+		end = ceph_fscrypt_page_offset(page) + thp_size(page);
+	ret = end > start ? end - start : 0;
+	if (ret && fscrypt_is_bounce_page(page))
+		ret = round_up(ret, CEPH_FSCRYPT_BLOCK_SIZE);
+	return ret;
 }
 
 /*
@@ -787,6 +792,11 @@ static void writepages_finish(struct ceph_osd_request *req)
 		total_pages += num_pages;
 		for (j = 0; j < num_pages; j++) {
 			page = osd_data->pages[j];
+			if (fscrypt_is_bounce_page(page)) {
+				page = fscrypt_pagecache_page(page);
+				fscrypt_free_bounce_page(osd_data->pages[j]);
+				osd_data->pages[j] = page;
+			}
 			BUG_ON(!page);
 			WARN_ON(!PageUptodate(page));
 
@@ -1048,9 +1058,28 @@ static int ceph_writepages_start(struct address_space *mapping,
 				    fsc->mount_options->congestion_kb))
 				fsc->write_congested = true;
 
-			pages[locked_pages++] = page;
-			pvec.pages[i] = NULL;
+			if (IS_ENCRYPTED(inode)) {
+				pages[locked_pages] =
+					fscrypt_encrypt_pagecache_blocks(page,
+						PAGE_SIZE, 0,
+						locked_pages ? GFP_NOWAIT : GFP_NOFS);
+				if (IS_ERR(pages[locked_pages])) {
+					if (PTR_ERR(pages[locked_pages]) == -EINVAL)
+						pr_err("%s: inode->i_blkbits=%hhu\n",
+							__func__, inode->i_blkbits);
+					/* better not fail on first page! */
+					BUG_ON(locked_pages == 0);
+					pages[locked_pages] = NULL;
+					redirty_page_for_writepage(wbc, page);
+					unlock_page(page);
+					break;
+				}
+				++locked_pages;
+			} else {
+				pages[locked_pages++] = page;
+			}
 
+			pvec.pages[i] = NULL;
 			len += thp_size(page);
 		}
 
@@ -1078,7 +1107,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 		}
 
 new_request:
-		offset = page_offset(pages[0]);
+		offset = ceph_fscrypt_page_offset(pages[0]);
 		len = wsize;
 
 		req = ceph_osdc_new_request(&fsc->client->osdc,
@@ -1099,8 +1128,8 @@ static int ceph_writepages_start(struct address_space *mapping,
 						ceph_wbc.truncate_size, true);
 			BUG_ON(IS_ERR(req));
 		}
-		BUG_ON(len < page_offset(pages[locked_pages - 1]) +
-			     thp_size(page) - offset);
+		BUG_ON(len < ceph_fscrypt_page_offset(pages[locked_pages - 1]) +
+			     thp_size(pages[locked_pages - 1]) - offset);
 
 		req->r_callback = writepages_finish;
 		req->r_inode = inode;
@@ -1110,7 +1139,9 @@ static int ceph_writepages_start(struct address_space *mapping,
 		data_pages = pages;
 		op_idx = 0;
 		for (i = 0; i < locked_pages; i++) {
-			u64 cur_offset = page_offset(pages[i]);
+			struct page *page = ceph_fscrypt_pagecache_page(pages[i]);
+
+			u64 cur_offset = page_offset(page);
 			/*
 			 * Discontinuity in page range? Ceph can handle that by just passing
 			 * multiple extents in the write op.
@@ -1139,9 +1170,9 @@ static int ceph_writepages_start(struct address_space *mapping,
 				op_idx++;
 			}
 
-			set_page_writeback(pages[i]);
+			set_page_writeback(page);
 			if (caching)
-				ceph_set_page_fscache(pages[i]);
+				ceph_set_page_fscache(page);
 			len += thp_size(page);
 		}
 		ceph_fscache_write_to_cache(inode, offset, len, caching);
@@ -1157,8 +1188,16 @@ static int ceph_writepages_start(struct address_space *mapping,
 							 offset);
 			len = max(len, min_len);
 		}
+		if (IS_ENCRYPTED(inode))
+			len = round_up(len, CEPH_FSCRYPT_BLOCK_SIZE);
+
 		dout("writepages got pages at %llu~%llu\n", offset, len);
 
+		if (IS_ENCRYPTED(inode) &&
+		    ((offset | len) & ~CEPH_FSCRYPT_BLOCK_MASK))
+			pr_warn("%s: bad encrypted write offset=%lld len=%llu\n",
+				__func__, offset, len);
+
 		osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len,
 						 0, from_pool, false);
 		osd_req_op_extent_update(req, op_idx, len);
fs/ceph/crypto.h +17 -1
index 92a7b221a975..0cf526f07567 100644
@@ -146,6 +146,12 @@ int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page, u64 of
 				 struct ceph_sparse_extent *map, u32 ext_cnt);
 int ceph_fscrypt_encrypt_pages(struct inode *inode, struct page **page, u64 off,
 				int len, gfp_t gfp);
+
+static inline struct page *ceph_fscrypt_pagecache_page(struct page *page)
+{
+	return fscrypt_is_bounce_page(page) ?  fscrypt_pagecache_page(page) : page;
+}
+
 #else /* CONFIG_FS_ENCRYPTION */
 
 static inline void ceph_fscrypt_set_ops(struct super_block *sb)
@@ -235,6 +241,16 @@ static inline int ceph_fscrypt_encrypt_pages(struct inode *inode, struct page **
 {
 	return 0;
 }
+
+static inline struct page *ceph_fscrypt_pagecache_page(struct page *page)
+{
+	return page;
+}
 #endif /* CONFIG_FS_ENCRYPTION */
 
-#endif
+static inline loff_t ceph_fscrypt_page_offset(struct page *page)
+{
+	return page_offset(ceph_fscrypt_pagecache_page(page));
+}
+
+#endif /* _CEPH_CRYPTO_H */
Signature · 1 line
2.35.1
#5 lore raw

PATCH v13 5/59 libceph: support sparse reads on msgr2 secure codepath

In reply to Jeff Layton

Add a new init_sgs_pages helper that populates the scatterlist from an arbitrary point in an array of pages.

Change setup_message_sgs to take an optional pointer to an array of pages. If that's set, then the scatterlist will be set using that array instead of the cursor.

When given a sparse read on a secure connection, decrypt the data in-place rather than into the final destination, by passing it the in_enc_pages array.

After decrypting, run the sparse_read state machine in a loop, copying data from the decrypted pages until it's complete.

---
 net/ceph/messenger_v2.c | 119 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 109 insertions(+), 10 deletions(-)
net/ceph/messenger_v2.c +109 -10
index d527777af584..3dcaee6f8903 100644
@@ -963,12 +963,48 @@ static void init_sgs_cursor(struct scatterlist **sg,
 	}
 }
 
+/**
+ * init_sgs_pages: set up scatterlist on an array of page pointers
+ * @sg: 	scatterlist to populate
+ * @pages: 	pointer to page array
+ * @dpos:	position in the array to start (bytes)
+ * @dlen:	len to add to sg (bytes)
+ * @pad:	pointer to pad destination (if any)
+ *
+ * Populate the scatterlist from the page array, starting at an arbitrary
+ * byte in the array and running for a specified length.
+ */
+static void init_sgs_pages(struct scatterlist **sg, struct page **pages,
+			     int dpos, int dlen, u8 *pad)
+{
+	int idx = dpos >> PAGE_SHIFT;
+	int off = offset_in_page(dpos);
+	int resid = dlen;
+
+	do {
+		int len = min(resid, (int)PAGE_SIZE - off);
+
+		sg_set_page(*sg, pages[idx], len, off);
+		*sg = sg_next(*sg);
+		off = 0;
+		++idx;
+		resid -= len;
+	} while (resid);
+
+	if (need_padding(dlen)) {
+		sg_set_buf(*sg, pad, padding_len(dlen));
+		*sg = sg_next(*sg);
+	}
+}
+
 static int setup_message_sgs(struct sg_table *sgt, struct ceph_msg *msg,
 			     u8 *front_pad, u8 *middle_pad, u8 *data_pad,
-			     void *epilogue, bool add_tag)
+			     void *epilogue, struct page **pages, int dpos,
+			     bool add_tag)
 {
 	struct ceph_msg_data_cursor cursor;
 	struct scatterlist *cur_sg;
+	int dlen = data_len(msg);
 	int sg_cnt;
 	int ret;
 
@@ -982,9 +1018,15 @@ static int setup_message_sgs(struct sg_table *sgt, struct ceph_msg *msg,
 	if (middle_len(msg))
 		sg_cnt += calc_sg_cnt(msg->middle->vec.iov_base,
 				      middle_len(msg));
-	if (data_len(msg)) {
-		ceph_msg_data_cursor_init(&cursor, msg, data_len(msg));
-		sg_cnt += calc_sg_cnt_cursor(&cursor);
+	if (dlen) {
+		if (pages) {
+			sg_cnt += calc_pages_for(dpos, dlen);
+			if (need_padding(dlen))
+				sg_cnt++;
+		} else {
+			ceph_msg_data_cursor_init(&cursor, msg, dlen);
+			sg_cnt += calc_sg_cnt_cursor(&cursor);
+		}
 	}
 
 	ret = sg_alloc_table(sgt, sg_cnt, GFP_NOIO);
@@ -998,9 +1040,13 @@ static int setup_message_sgs(struct sg_table *sgt, struct ceph_msg *msg,
 	if (middle_len(msg))
 		init_sgs(&cur_sg, msg->middle->vec.iov_base, middle_len(msg),
 			 middle_pad);
-	if (data_len(msg)) {
-		ceph_msg_data_cursor_init(&cursor, msg, data_len(msg));
-		init_sgs_cursor(&cur_sg, &cursor, data_pad);
+	if (dlen) {
+		if (pages) {
+			init_sgs_pages(&cur_sg, pages, dpos, dlen, data_pad);
+		} else {
+			ceph_msg_data_cursor_init(&cursor, msg, dlen);
+			init_sgs_cursor(&cur_sg, &cursor, data_pad);
+		}
 	}
 
 	WARN_ON(!sg_is_last(cur_sg));
@@ -1035,10 +1081,52 @@ static int decrypt_control_remainder(struct ceph_connection *con)
 			 padded_len(rem_len) + CEPH_GCM_TAG_LEN);
 }
 
+/* Process sparse read data that lives in a buffer */
+static int process_v2_sparse_read(struct ceph_connection *con, struct page **pages, int spos)
+{
+	struct ceph_msg_data_cursor *cursor = &con->v2.in_cursor;
+	int ret;
+
+	for (;;) {
+		char *buf = NULL;
+
+		ret = con->ops->sparse_read(con, cursor, &buf);
+		if (ret <= 0)
+			return ret;
+
+		dout("%s: sparse_read return %x buf %p\n", __func__, ret, buf);
+
+		do {
+			int idx = spos >> PAGE_SHIFT;
+			int soff = offset_in_page(spos);
+			struct page *spage = con->v2.in_enc_pages[idx];
+			int len = min_t(int, ret, PAGE_SIZE - soff);
+
+			if (buf) {
+				memcpy_from_page(buf, spage, soff, len);
+				buf += len;
+			} else {
+				struct bio_vec bv;
+
+				get_bvec_at(cursor, &bv);
+				len = min_t(int, len, bv.bv_len);
+				memcpy_page(bv.bv_page, bv.bv_offset,
+					    spage, soff, len);
+				ceph_msg_data_advance(cursor, len);
+			}
+			spos += len;
+			ret -= len;
+		} while (ret);
+	}
+}
+
 static int decrypt_tail(struct ceph_connection *con)
 {
 	struct sg_table enc_sgt = {};
 	struct sg_table sgt = {};
+	struct page **pages = NULL;
+	bool sparse = con->in_msg->sparse_read;
+	int dpos = 0;
 	int tail_len;
 	int ret;
 
@@ -1049,9 +1137,14 @@ static int decrypt_tail(struct ceph_connection *con)
 	if (ret)
 		goto out;
 
+	if (sparse) {
+		dpos = padded_len(front_len(con->in_msg) + padded_len(middle_len(con->in_msg)));
+		pages = con->v2.in_enc_pages;
+	}
+
 	ret = setup_message_sgs(&sgt, con->in_msg, FRONT_PAD(con->v2.in_buf),
-			MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf),
-			con->v2.in_buf, true);
+				MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf),
+				con->v2.in_buf, pages, dpos, true);
 	if (ret)
 		goto out;
 
@@ -1061,6 +1154,12 @@ static int decrypt_tail(struct ceph_connection *con)
 	if (ret)
 		goto out;
 
+	if (sparse && data_len(con->in_msg)) {
+		ret = process_v2_sparse_read(con, con->v2.in_enc_pages, dpos);
+		if (ret)
+			goto out;
+	}
+
 	WARN_ON(!con->v2.in_enc_page_cnt);
 	ceph_release_page_vector(con->v2.in_enc_pages,
 				 con->v2.in_enc_page_cnt);
@@ -1584,7 +1683,7 @@ static int prepare_message_secure(struct ceph_connection *con)
 
 	encode_epilogue_secure(con, false);
 	ret = setup_message_sgs(&sgt, con->out_msg, zerop, zerop, zerop,
-				&con->v2.out_epil, false);
+				&con->v2.out_epil, NULL, 0, false);
 	if (ret)
 		goto out;
 
Signature · 1 line
2.35.1
#30 lore raw

PATCH v13 30/59 ceph: pass the request to parse_reply_info_readdir()

In reply to Jeff Layton

From: Xiubo Li <[email protected]>

Instead of passing just the r_reply_info to the readdir reply parser, pass the request pointer directly instead. This will facilitate implementing readdir on fscrypted directories.

---
 fs/ceph/mds_client.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)
fs/ceph/mds_client.c +12 -10
index 750a67643850..0a7f18d4df73 100644
@@ -406,9 +406,10 @@ static int parse_reply_info_trace(void **p, void *end,
  * parse readdir results
  */
 static int parse_reply_info_readdir(void **p, void *end,
-				struct ceph_mds_reply_info_parsed *info,
-				u64 features)
+				    struct ceph_mds_request *req,
+				    u64 features)
 {
+	struct ceph_mds_reply_info_parsed *info = &req->r_reply_info;
 	u32 num, i = 0;
 	int err;
 
@@ -650,15 +651,16 @@ static int parse_reply_info_getvxattr(void **p, void *end,
  * parse extra results
  */
 static int parse_reply_info_extra(void **p, void *end,
-				  struct ceph_mds_reply_info_parsed *info,
+				  struct ceph_mds_request *req,
 				  u64 features, struct ceph_mds_session *s)
 {
+	struct ceph_mds_reply_info_parsed *info = &req->r_reply_info;
 	u32 op = le32_to_cpu(info->head->op);
 
 	if (op == CEPH_MDS_OP_GETFILELOCK)
 		return parse_reply_info_filelock(p, end, info, features);
 	else if (op == CEPH_MDS_OP_READDIR || op == CEPH_MDS_OP_LSSNAP)
-		return parse_reply_info_readdir(p, end, info, features);
+		return parse_reply_info_readdir(p, end, req, features);
 	else if (op == CEPH_MDS_OP_CREATE)
 		return parse_reply_info_create(p, end, info, features, s);
 	else if (op == CEPH_MDS_OP_GETVXATTR)
@@ -671,9 +673,9 @@ static int parse_reply_info_extra(void **p, void *end,
  * parse entire mds reply
  */
 static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg,
-			    struct ceph_mds_reply_info_parsed *info,
-			    u64 features)
+			    struct ceph_mds_request *req, u64 features)
 {
+	struct ceph_mds_reply_info_parsed *info = &req->r_reply_info;
 	void *p, *end;
 	u32 len;
 	int err;
@@ -695,7 +697,7 @@ static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg,
 	ceph_decode_32_safe(&p, end, len, bad);
 	if (len > 0) {
 		ceph_decode_need(&p, end, len, bad);
-		err = parse_reply_info_extra(&p, p+len, info, features, s);
+		err = parse_reply_info_extra(&p, p+len, req, features, s);
 		if (err < 0)
 			goto out_bad;
 	}
@@ -3440,14 +3442,14 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	}
 
 	dout("handle_reply tid %lld result %d\n", tid, result);
-	rinfo = &req->r_reply_info;
 	if (test_bit(CEPHFS_FEATURE_REPLY_ENCODING, &session->s_features))
-		err = parse_reply_info(session, msg, rinfo, (u64)-1);
+		err = parse_reply_info(session, msg, req, (u64)-1);
 	else
-		err = parse_reply_info(session, msg, rinfo, session->s_con.peer_features);
+		err = parse_reply_info(session, msg, req, session->s_con.peer_features);
 	mutex_unlock(&mdsc->mutex);
 
 	/* Must find target inode outside of mutexes to avoid deadlocks */
+	rinfo = &req->r_reply_info;
 	if ((err >= 0) && rinfo->head->is_target) {
 		struct inode *in = xchg(&req->r_new_inode, NULL);
 		struct ceph_vino tvino = {
Signature · 1 line
2.35.1
#41 lore raw

PATCH v13 41/59 ceph: get file size from fscrypt_file when present in inode traces

In reply to Jeff Layton

When we get an inode trace from the MDS, grab the fscrypt_file field if the inode is encrypted, and use it to populate the i_size field instead of the regular inode size field.

---
 fs/ceph/inode.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)
fs/ceph/inode.c +15 -3
index b9454721c976..f2a59306e4a6 100644
@@ -1024,6 +1024,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 	if (new_version ||
 	    (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+		u64 size = le64_to_cpu(info->size);
 		s64 old_pool = ci->i_layout.pool_id;
 		struct ceph_string *old_ns;
 
@@ -1037,10 +1038,21 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 		pool_ns = old_ns;
 
+		if (IS_ENCRYPTED(inode) && size && (iinfo->fscrypt_file_len == sizeof(__le64))) {
+			u64 fsize = __le64_to_cpu(*(__le64 *)iinfo->fscrypt_file);
+
+			if (size == round_up(fsize, CEPH_FSCRYPT_BLOCK_SIZE)) {
+				size = fsize;
+			} else {
+				pr_warn("fscrypt size mismatch: size=%llu fscrypt_file=%llu, discarding fscrypt_file size.\n",
+					info->size, size);
+			}
+		}
+
 		queue_trunc = ceph_fill_file_size(inode, issued,
-					le32_to_cpu(info->truncate_seq),
-					le64_to_cpu(info->truncate_size),
-					le64_to_cpu(info->size));
+						  le32_to_cpu(info->truncate_seq),
+						  le64_to_cpu(info->truncate_size),
+						  size);
 		/* only update max_size on auth cap */
 		if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
 		    ci->i_max_size != le64_to_cpu(info->max_size)) {
Signature · 1 line
2.35.1
#46 lore raw

PATCH v13 46/59 ceph: add object version support for sync read

In reply to Jeff Layton

From: Xiubo Li <[email protected]>

Always return the last object's version.

---
 fs/ceph/file.c  | 12 ++++++++++--
 fs/ceph/super.h |  3 ++-
 2 files changed, 12 insertions(+), 3 deletions(-)
fs/ceph/file.c +10 -2
index c4300381851e..175a59277726 100644
@@ -928,7 +928,8 @@ enum {
  * only return a short read to the caller if we hit EOF.
  */
 ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
-			 struct iov_iter *to, int *retry_op)
+			 struct iov_iter *to, int *retry_op,
+			 u64 *last_objver)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
@@ -938,6 +939,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 	u64 len = iov_iter_count(to);
 	u64 i_size = i_size_read(inode);
 	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
+	u64 objver = 0;
 
 	dout("sync_read on inode %p %llx~%llx\n", inode, *ki_pos, len);
 
@@ -1008,6 +1010,9 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 					 req->r_end_latency,
 					 len, ret);
 
+		if (ret > 0)
+			objver = req->r_version;
+
 		i_size = i_size_read(inode);
 		dout("sync_read %llu~%llu got %zd i_size %llu%s\n",
 		     off, len, ret, i_size, (more ? " MORE" : ""));
@@ -1069,6 +1074,9 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		}
 	}
 
+	if (last_objver && ret > 0)
+		*last_objver = objver;
+
 	dout("sync_read result %zd retry_op %d\n", ret, *retry_op);
 	return ret;
 }
@@ -1082,7 +1090,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 	dout("sync_read on file %p %llx~%zx %s\n", file, iocb->ki_pos,
 	     iov_iter_count(to), (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
 
-	return __ceph_sync_read(inode, &iocb->ki_pos, to, retry_op);
+	return __ceph_sync_read(inode, &iocb->ki_pos, to, retry_op, NULL);
 }
 
 struct ceph_aio_request {
fs/ceph/super.h +2 -1
index d7ab820aed34..9809bc97b89e 100644
@@ -1259,7 +1259,8 @@ extern int ceph_open(struct inode *inode, struct file *file);
 extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags, umode_t mode);
 extern ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
-				struct iov_iter *to, int *retry_op);
+				struct iov_iter *to, int *retry_op,
+				u64 *last_objver);
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);
Signature · 1 line
2.35.1
#50 lore raw

PATCH v13 50/59 ceph: disable fallocate for encrypted inodes

In reply to Jeff Layton

...hopefully, just for now.

---
 fs/ceph/file.c | 3 +++
 1 file changed, 3 insertions(+)
fs/ceph/file.c +3 -0
index 175a59277726..f74563e11058 100644
@@ -2207,6 +2207,9 @@ static long ceph_fallocate(struct file *file, int mode,
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
+	if (IS_ENCRYPTED(inode))
+		return -EOPNOTSUPP;
+
 	prealloc_cf = ceph_alloc_cap_flush();
 	if (!prealloc_cf)
 		return -ENOMEM;
Signature · 1 line
2.35.1
#52 lore raw

PATCH v13 52/59 ceph: don't use special DIO path for encrypted inodes

In reply to Jeff Layton

Eventually I want to merge the synchronous and direct read codepaths, possibly via new netfs infrastructure. For now, the direct path is not crypto-enabled, so use the sync read/write paths instead.

---
 fs/ceph/file.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
fs/ceph/file.c +4 -2
index f9e775d6cdf0..41b97d32dfcf 100644
@@ -1709,7 +1709,9 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		     ceph_cap_string(got));
 
 		if (ci->i_inline_version == CEPH_INLINE_NONE) {
-			if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) {
+			if (!retry_op &&
+			    (iocb->ki_flags & IOCB_DIRECT) &&
+			    !IS_ENCRYPTED(inode)) {
 				ret = ceph_direct_read_write(iocb, to,
 							     NULL, NULL);
 				if (ret >= 0 && ret < len)
@@ -1935,7 +1937,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 		/* we might need to revert back to that point */
 		data = *from;
-		if (iocb->ki_flags & IOCB_DIRECT)
+		if ((iocb->ki_flags & IOCB_DIRECT) && !IS_ENCRYPTED(inode))
 			written = ceph_direct_read_write(iocb, &data, snapc,
 							 &prealloc_cf);
 		else
Signature · 1 line
2.35.1