From 9280be24dc9c7aaee230de3ed33f8357386de9a2 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Tue, 14 Oct 2014 10:33:35 +0800
Subject: ceph: fix file lock interruption

When a lock operation is interrupted, current code sends a unlock request to
MDS to undo the lock operation. This method does not work as expected because
the unlock request can drop locks that have already been acquired.

The fix is use the newly introduced CEPH_LOCK_FCNTL_INTR/CEPH_LOCK_FLOCK_INTR
requests to interrupt blocked file lock request. These requests do not drop
locks that have alread been acquired, they only interrupt blocked file lock
request.

Signed-off-by: Yan, Zheng <zyan@redhat.com>
---
 include/linux/ceph/ceph_fs.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 3c97d5e9b951..31d8b98b7f96 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -522,8 +522,11 @@ struct ceph_mds_reply_dirfrag {
 	__le32 dist[];
 } __attribute__ ((packed));
 
-#define CEPH_LOCK_FCNTL    1
-#define CEPH_LOCK_FLOCK    2
+#define CEPH_LOCK_FCNTL		1
+#define CEPH_LOCK_FLOCK		2
+#define CEPH_LOCK_FCNTL_INTR    3
+#define CEPH_LOCK_FLOCK_INTR    4
+
 
 #define CEPH_LOCK_SHARED   1
 #define CEPH_LOCK_EXCL     2
-- 
cgit v1.2.3


From 4965fc38c460b274b2a1789e1165a25fb0409d7e Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@redhat.com>
Date: Thu, 23 Oct 2014 16:32:57 +0400
Subject: libceph: nuke ceph_kvfree()

Use kvfree() from linux/mm.h instead, which is identical.  Also fix the
ceph_buffer comment: we will allocate with kmalloc() up to 32k - the
value of PAGE_ALLOC_COSTLY_ORDER, but that really is just an
implementation detail so don't mention it at all.

Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/buffer.h  | 3 +--
 include/linux/ceph/libceph.h | 1 -
 net/ceph/buffer.c            | 4 ++--
 net/ceph/ceph_common.c       | 8 --------
 net/ceph/messenger.c         | 2 +-
 5 files changed, 4 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/buffer.h b/include/linux/ceph/buffer.h
index 07ad423cc37f..07ca15e76100 100644
--- a/include/linux/ceph/buffer.h
+++ b/include/linux/ceph/buffer.h
@@ -10,8 +10,7 @@
 /*
  * a simple reference counted buffer.
  *
- * use kmalloc for small sizes (<= one page), vmalloc for larger
- * sizes.
+ * use kmalloc for smaller sizes, vmalloc for larger sizes.
  */
 struct ceph_buffer {
 	struct kref kref;
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 07bc359b88ac..d293f7e38814 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -184,7 +184,6 @@ extern bool libceph_compatible(void *data);
 extern const char *ceph_msg_type_name(int type);
 extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
 extern void *ceph_kvmalloc(size_t size, gfp_t flags);
-extern void ceph_kvfree(const void *ptr);
 
 extern struct ceph_options *ceph_parse_options(char *options,
 			      const char *dev_name, const char *dev_name_end,
diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c
index 621b5f65407f..add5f921a0ff 100644
--- a/net/ceph/buffer.c
+++ b/net/ceph/buffer.c
@@ -6,7 +6,7 @@
 
 #include <linux/ceph/buffer.h>
 #include <linux/ceph/decode.h>
-#include <linux/ceph/libceph.h> /* for ceph_kv{malloc,free} */
+#include <linux/ceph/libceph.h> /* for ceph_kvmalloc */
 
 struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
 {
@@ -35,7 +35,7 @@ void ceph_buffer_release(struct kref *kref)
 	struct ceph_buffer *b = container_of(kref, struct ceph_buffer, kref);
 
 	dout("buffer_release %p\n", b);
-	ceph_kvfree(b->vec.iov_base);
+	kvfree(b->vec.iov_base);
 	kfree(b);
 }
 EXPORT_SYMBOL(ceph_buffer_release);
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 58fbfe134f93..d361a274aee7 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -184,14 +184,6 @@ void *ceph_kvmalloc(size_t size, gfp_t flags)
 	return __vmalloc(size, flags | __GFP_HIGHMEM, PAGE_KERNEL);
 }
 
-void ceph_kvfree(const void *ptr)
-{
-	if (is_vmalloc_addr(ptr))
-		vfree(ptr);
-	else
-		kfree(ptr);
-}
-
 
 static int parse_fsid(const char *str, struct ceph_fsid *fsid)
 {
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 8d1653caffdb..863d07ab2129 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -3288,7 +3288,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 static void ceph_msg_free(struct ceph_msg *m)
 {
 	dout("%s %p\n", __func__, m);
-	ceph_kvfree(m->front.iov_base);
+	kvfree(m->front.iov_base);
 	kmem_cache_free(ceph_msg_cache, m);
 }
 
-- 
cgit v1.2.3


From 33d07337962c7bbd2fd5cf7f1106735c9507fbe2 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Tue, 4 Nov 2014 16:33:37 +0800
Subject: libceph: message signature support

Signed-off-by: Yan, Zheng <zyan@redhat.com>
---
 fs/ceph/mds_client.c               | 16 +++++++++++
 include/linux/ceph/auth.h          | 26 +++++++++++++++++
 include/linux/ceph/ceph_features.h |  1 +
 include/linux/ceph/messenger.h     |  9 +++++-
 include/linux/ceph/msgr.h          |  8 ++++++
 net/ceph/auth_x.c                  | 58 ++++++++++++++++++++++++++++++++++++++
 net/ceph/messenger.c               | 32 +++++++++++++++++++--
 net/ceph/osd_client.c              | 16 +++++++++++
 8 files changed, 162 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index fc74617069a3..9f00853f6d42 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3744,6 +3744,20 @@ static struct ceph_msg *mds_alloc_msg(struct ceph_connection *con,
 	return msg;
 }
 
+static int sign_message(struct ceph_connection *con, struct ceph_msg *msg)
+{
+       struct ceph_mds_session *s = con->private;
+       struct ceph_auth_handshake *auth = &s->s_auth;
+       return ceph_auth_sign_message(auth, msg);
+}
+
+static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg)
+{
+       struct ceph_mds_session *s = con->private;
+       struct ceph_auth_handshake *auth = &s->s_auth;
+       return ceph_auth_check_message_signature(auth, msg);
+}
+
 static const struct ceph_connection_operations mds_con_ops = {
 	.get = con_get,
 	.put = con_put,
@@ -3753,6 +3767,8 @@ static const struct ceph_connection_operations mds_con_ops = {
 	.invalidate_authorizer = invalidate_authorizer,
 	.peer_reset = peer_reset,
 	.alloc_msg = mds_alloc_msg,
+	.sign_message = sign_message,
+	.check_message_signature = check_message_signature,
 };
 
 /* eof */
diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h
index 5f3386844134..260d78b587c4 100644
--- a/include/linux/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -13,6 +13,7 @@
 
 struct ceph_auth_client;
 struct ceph_authorizer;
+struct ceph_msg;
 
 struct ceph_auth_handshake {
 	struct ceph_authorizer *authorizer;
@@ -20,6 +21,10 @@ struct ceph_auth_handshake {
 	size_t authorizer_buf_len;
 	void *authorizer_reply_buf;
 	size_t authorizer_reply_buf_len;
+	int (*sign_message)(struct ceph_auth_handshake *auth,
+			    struct ceph_msg *msg);
+	int (*check_message_signature)(struct ceph_auth_handshake *auth,
+				       struct ceph_msg *msg);
 };
 
 struct ceph_auth_client_ops {
@@ -66,6 +71,11 @@ struct ceph_auth_client_ops {
 	void (*reset)(struct ceph_auth_client *ac);
 
 	void (*destroy)(struct ceph_auth_client *ac);
+
+	int (*sign_message)(struct ceph_auth_handshake *auth,
+			    struct ceph_msg *msg);
+	int (*check_message_signature)(struct ceph_auth_handshake *auth,
+				       struct ceph_msg *msg);
 };
 
 struct ceph_auth_client {
@@ -113,4 +123,20 @@ extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac,
 extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac,
 					    int peer_type);
 
+static inline int ceph_auth_sign_message(struct ceph_auth_handshake *auth,
+					 struct ceph_msg *msg)
+{
+	if (auth->sign_message)
+		return auth->sign_message(auth, msg);
+	return 0;
+}
+
+static inline
+int ceph_auth_check_message_signature(struct ceph_auth_handshake *auth,
+				      struct ceph_msg *msg)
+{
+	if (auth->check_message_signature)
+		return auth->check_message_signature(auth, msg);
+	return 0;
+}
 #endif
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index d12659ce550d..71e05bbf8ceb 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -84,6 +84,7 @@ static inline u64 ceph_sanitize_features(u64 features)
 	 CEPH_FEATURE_PGPOOL3 |			\
 	 CEPH_FEATURE_OSDENC |			\
 	 CEPH_FEATURE_CRUSH_TUNABLES |		\
+	 CEPH_FEATURE_MSG_AUTH |		\
 	 CEPH_FEATURE_CRUSH_TUNABLES2 |		\
 	 CEPH_FEATURE_REPLY_CREATE_INODE |	\
 	 CEPH_FEATURE_OSDHASHPSPOOL |		\
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 40ae58e3e9db..d9d396c16503 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -42,6 +42,10 @@ struct ceph_connection_operations {
 	struct ceph_msg * (*alloc_msg) (struct ceph_connection *con,
 					struct ceph_msg_header *hdr,
 					int *skip);
+	int (*sign_message) (struct ceph_connection *con, struct ceph_msg *msg);
+
+	int (*check_message_signature) (struct ceph_connection *con,
+					struct ceph_msg *msg);
 };
 
 /* use format string %s%d */
@@ -142,7 +146,10 @@ struct ceph_msg_data_cursor {
  */
 struct ceph_msg {
 	struct ceph_msg_header hdr;	/* header */
-	struct ceph_msg_footer footer;	/* footer */
+	union {
+		struct ceph_msg_footer footer;		/* footer */
+		struct ceph_msg_footer_old old_footer;	/* old format footer */
+	};
 	struct kvec front;              /* unaligned blobs of message */
 	struct ceph_buffer *middle;
 
diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
index 3d94a73b5f30..cac4b28ac1c0 100644
--- a/include/linux/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
@@ -164,13 +164,21 @@ struct ceph_msg_header {
 /*
  * follows data payload
  */
+struct ceph_msg_footer_old {
+	__le32 front_crc, middle_crc, data_crc;
+	__u8 flags;
+} __attribute__ ((packed));
+
 struct ceph_msg_footer {
 	__le32 front_crc, middle_crc, data_crc;
+	// sig holds the 64 bits of the digital signature for the message PLR
+	__le64  sig;
 	__u8 flags;
 } __attribute__ ((packed));
 
 #define CEPH_MSG_FOOTER_COMPLETE  (1<<0)   /* msg wasn't aborted */
 #define CEPH_MSG_FOOTER_NOCRC     (1<<1)   /* no data crc */
+#define CEPH_MSG_FOOTER_SIGNED	  (1<<2)   /* msg was signed */
 
 
 #endif
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 77f3885c16bc..15845814a0f2 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -8,6 +8,7 @@
 
 #include <linux/ceph/decode.h>
 #include <linux/ceph/auth.h>
+#include <linux/ceph/messenger.h>
 
 #include "crypto.h"
 #include "auth_x.h"
@@ -567,6 +568,8 @@ static int ceph_x_create_authorizer(
 	auth->authorizer_buf_len = au->buf->vec.iov_len;
 	auth->authorizer_reply_buf = au->reply_buf;
 	auth->authorizer_reply_buf_len = sizeof (au->reply_buf);
+	auth->sign_message = ac->ops->sign_message;
+	auth->check_message_signature = ac->ops->check_message_signature;
 
 	return 0;
 }
@@ -667,6 +670,59 @@ static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac,
 		memset(&th->validity, 0, sizeof(th->validity));
 }
 
+static int calcu_signature(struct ceph_x_authorizer *au,
+			   struct ceph_msg *msg, __le64 *sig)
+{
+	int ret;
+	char tmp_enc[40];
+	__le32 tmp[5] = {
+		16u, msg->hdr.crc, msg->footer.front_crc,
+		msg->footer.middle_crc, msg->footer.data_crc,
+	};
+	ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp),
+			     tmp_enc, sizeof(tmp_enc));
+	if (ret < 0)
+		return ret;
+	*sig = *(__le64*)(tmp_enc + 4);
+	return 0;
+}
+
+static int ceph_x_sign_message(struct ceph_auth_handshake *auth,
+			       struct ceph_msg *msg)
+{
+	int ret;
+	if (!auth->authorizer)
+		return 0;
+	ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
+			      msg, &msg->footer.sig);
+	if (ret < 0)
+		return ret;
+	msg->footer.flags |= CEPH_MSG_FOOTER_SIGNED;
+	return 0;
+}
+
+static int ceph_x_check_message_signature(struct ceph_auth_handshake *auth,
+					  struct ceph_msg *msg)
+{
+	__le64 sig_check;
+	int ret;
+
+	if (!auth->authorizer)
+		return 0;
+	ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
+			      msg, &sig_check);
+	if (ret < 0)
+		return ret;
+	if (sig_check == msg->footer.sig)
+		return 0;
+	if (msg->footer.flags & CEPH_MSG_FOOTER_SIGNED)
+		dout("ceph_x_check_message_signature %p has signature %llx "
+		     "expect %llx\n", msg, msg->footer.sig, sig_check);
+	else
+		dout("ceph_x_check_message_signature %p sender did not set "
+		     "CEPH_MSG_FOOTER_SIGNED\n", msg);
+	return -EBADMSG;
+}
 
 static const struct ceph_auth_client_ops ceph_x_ops = {
 	.name = "x",
@@ -681,6 +737,8 @@ static const struct ceph_auth_client_ops ceph_x_ops = {
 	.invalidate_authorizer = ceph_x_invalidate_authorizer,
 	.reset =  ceph_x_reset,
 	.destroy = ceph_x_destroy,
+	.sign_message = ceph_x_sign_message,
+	.check_message_signature = ceph_x_check_message_signature,
 };
 
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 863d07ab2129..33a2f201e460 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1196,8 +1196,18 @@ static void prepare_write_message_footer(struct ceph_connection *con)
 	dout("prepare_write_message_footer %p\n", con);
 	con->out_kvec_is_msg = true;
 	con->out_kvec[v].iov_base = &m->footer;
-	con->out_kvec[v].iov_len = sizeof(m->footer);
-	con->out_kvec_bytes += sizeof(m->footer);
+	if (con->peer_features & CEPH_FEATURE_MSG_AUTH) {
+		if (con->ops->sign_message)
+			con->ops->sign_message(con, m);
+		else
+			m->footer.sig = 0;
+		con->out_kvec[v].iov_len = sizeof(m->footer);
+		con->out_kvec_bytes += sizeof(m->footer);
+	} else {
+		m->old_footer.flags = m->footer.flags;
+		con->out_kvec[v].iov_len = sizeof(m->old_footer);
+		con->out_kvec_bytes += sizeof(m->old_footer);
+	}
 	con->out_kvec_left++;
 	con->out_more = m->more_to_follow;
 	con->out_msg_done = true;
@@ -2249,6 +2259,7 @@ static int read_partial_message(struct ceph_connection *con)
 	int ret;
 	unsigned int front_len, middle_len, data_len;
 	bool do_datacrc = !con->msgr->nocrc;
+	bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH);
 	u64 seq;
 	u32 crc;
 
@@ -2361,12 +2372,21 @@ static int read_partial_message(struct ceph_connection *con)
 	}
 
 	/* footer */
-	size = sizeof (m->footer);
+	if (need_sign)
+		size = sizeof(m->footer);
+	else
+		size = sizeof(m->old_footer);
+
 	end += size;
 	ret = read_partial(con, end, size, &m->footer);
 	if (ret <= 0)
 		return ret;
 
+	if (!need_sign) {
+		m->footer.flags = m->old_footer.flags;
+		m->footer.sig = 0;
+	}
+
 	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
 	     m, front_len, m->footer.front_crc, middle_len,
 	     m->footer.middle_crc, data_len, m->footer.data_crc);
@@ -2390,6 +2410,12 @@ static int read_partial_message(struct ceph_connection *con)
 		return -EBADMSG;
 	}
 
+	if (need_sign && con->ops->check_message_signature &&
+	    con->ops->check_message_signature(con, m)) {
+		pr_err("read_partial_message %p signature check failed\n", m);
+		return -EBADMSG;
+	}
+
 	return 1; /* done! */
 }
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6f164289bde8..1f6c4055adaf 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -2920,6 +2920,20 @@ static int invalidate_authorizer(struct ceph_connection *con)
 	return ceph_monc_validate_auth(&osdc->client->monc);
 }
 
+static int sign_message(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	return ceph_auth_sign_message(auth, msg);
+}
+
+static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	return ceph_auth_check_message_signature(auth, msg);
+}
+
 static const struct ceph_connection_operations osd_con_ops = {
 	.get = get_osd_con,
 	.put = put_osd_con,
@@ -2928,5 +2942,7 @@ static const struct ceph_connection_operations osd_con_ops = {
 	.verify_authorizer_reply = verify_authorizer_reply,
 	.invalidate_authorizer = invalidate_authorizer,
 	.alloc_msg = alloc_msg,
+	.sign_message = sign_message,
+	.check_message_signature = check_message_signature,
 	.fault = osd_reset,
 };
-- 
cgit v1.2.3


From d4e1a4e0db439209672f9803f9f23b0123fb09aa Mon Sep 17 00:00:00 2001
From: John Spray <john.spray@redhat.com>
Date: Thu, 16 Oct 2014 12:05:34 +0100
Subject: libceph: update ceph_msg_header structure

2 bytes of what was reserved space is now used by userspace for the
compat_version field.

Signed-off-by: John Spray <john.spray@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
---
 include/linux/ceph/msgr.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
index cac4b28ac1c0..1c1887206ffa 100644
--- a/include/linux/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
@@ -152,7 +152,8 @@ struct ceph_msg_header {
 			     receiver: mask against ~PAGE_MASK */
 
 	struct ceph_entity_name src;
-	__le32 reserved;
+	__le16 compat_version;
+	__le16 reserved;
 	__le32 crc;       /* header crc32c */
 } __attribute__ ((packed));
 
-- 
cgit v1.2.3


From a3fc98005c9c6e4649d26bee0935a7048a95c9e6 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Tue, 11 Nov 2014 16:30:55 +0800
Subject: libceph: require cephx message signature by default

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/libceph.h |  1 +
 net/ceph/ceph_common.c       | 13 +++++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index d293f7e38814..8b11a79ca1cb 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -29,6 +29,7 @@
 #define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
 #define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
 #define CEPH_OPT_NOCRC            (1<<3) /* no data crc on writes */
+#define CEPH_OPT_NOMSGAUTH	  (1<<4) /* not require cephx message signature */
 
 #define CEPH_OPT_DEFAULT   (0)
 
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index d361a274aee7..5d5ab67f516d 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -237,6 +237,8 @@ enum {
 	Opt_noshare,
 	Opt_crc,
 	Opt_nocrc,
+	Opt_cephx_require_signatures,
+	Opt_nocephx_require_signatures,
 };
 
 static match_table_t opt_tokens = {
@@ -255,6 +257,8 @@ static match_table_t opt_tokens = {
 	{Opt_noshare, "noshare"},
 	{Opt_crc, "crc"},
 	{Opt_nocrc, "nocrc"},
+	{Opt_cephx_require_signatures, "cephx_require_signatures"},
+	{Opt_nocephx_require_signatures, "nocephx_require_signatures"},
 	{-1, NULL}
 };
 
@@ -453,6 +457,12 @@ ceph_parse_options(char *options, const char *dev_name,
 		case Opt_nocrc:
 			opt->flags |= CEPH_OPT_NOCRC;
 			break;
+		case Opt_cephx_require_signatures:
+			opt->flags &= ~CEPH_OPT_NOMSGAUTH;
+			break;
+		case Opt_nocephx_require_signatures:
+			opt->flags |= CEPH_OPT_NOMSGAUTH;
+			break;
 
 		default:
 			BUG_ON(token);
@@ -496,6 +506,9 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 	init_waitqueue_head(&client->auth_wq);
 	client->auth_err = 0;
 
+	if (!ceph_test_opt(client, NOMSGAUTH))
+		required_features |= CEPH_FEATURE_MSG_AUTH;
+
 	client->extra_mon_dispatch = NULL;
 	client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT |
 		supported_features;
-- 
cgit v1.2.3


From d74b50bed037794135cb5a4e7418ad71d9848ce1 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Wed, 12 Nov 2014 14:00:43 +0800
Subject: libceph: add SETXATTR/CMPXATTR osd operations support

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/osd_client.h | 10 +++++++++
 net/ceph/osd_client.c           | 47 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)

(limited to 'include')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 03aeb27fcc69..bcf9c2180ea5 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -86,6 +86,13 @@ struct ceph_osd_req_op {
 			u32 truncate_seq;
 			struct ceph_osd_data osd_data;
 		} extent;
+		struct {
+			__le32 name_len;
+			__le32 value_len;
+			__u8 cmp_op;       /* CEPH_OSD_CMPXATTR_OP_* */
+			__u8 cmp_mode;     /* CEPH_OSD_CMPXATTR_MODE_* */
+			struct ceph_osd_data osd_data;
+		} xattr;
 		struct {
 			const char *class_name;
 			const char *method_name;
@@ -295,6 +302,9 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *,
 extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req,
 					unsigned int which, u16 opcode,
 					const char *class, const char *method);
+extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
+				 u16 opcode, const char *name, const void *value,
+				 size_t size, u8 cmp_op, u8 cmp_mode);
 extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
 					unsigned int which, u16 opcode,
 					u64 cookie, u64 version, int flag);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 1f6c4055adaf..2b0555b36e4d 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -292,6 +292,10 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
 		ceph_osd_data_release(&op->cls.request_data);
 		ceph_osd_data_release(&op->cls.response_data);
 		break;
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+		ceph_osd_data_release(&op->xattr.osd_data);
+		break;
 	default:
 		break;
 	}
@@ -545,6 +549,39 @@ void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
 }
 EXPORT_SYMBOL(osd_req_op_cls_init);
 
+int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
+			  u16 opcode, const char *name, const void *value,
+			  size_t size, u8 cmp_op, u8 cmp_mode)
+{
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode);
+	struct ceph_pagelist *pagelist;
+	size_t payload_len;
+
+	BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR);
+
+	pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
+	if (!pagelist)
+		return -ENOMEM;
+
+	ceph_pagelist_init(pagelist);
+
+	payload_len = strlen(name);
+	op->xattr.name_len = payload_len;
+	ceph_pagelist_append(pagelist, name, payload_len);
+
+	op->xattr.value_len = size;
+	ceph_pagelist_append(pagelist, value, size);
+	payload_len += size;
+
+	op->xattr.cmp_op = cmp_op;
+	op->xattr.cmp_mode = cmp_mode;
+
+	ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist);
+	op->payload_len = payload_len;
+	return 0;
+}
+EXPORT_SYMBOL(osd_req_op_xattr_init);
+
 void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
 				unsigned int which, u16 opcode,
 				u64 cookie, u64 version, int flag)
@@ -676,6 +713,16 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 		dst->alloc_hint.expected_write_size =
 		    cpu_to_le64(src->alloc_hint.expected_write_size);
 		break;
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+		dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
+		dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
+		dst->xattr.cmp_op = src->xattr.cmp_op;
+		dst->xattr.cmp_mode = src->xattr.cmp_mode;
+		osd_data = &src->xattr.osd_data;
+		ceph_osdc_msg_data_add(req->r_request, osd_data);
+		request_data_len = osd_data->pagelist->length;
+		break;
 	default:
 		pr_err("unsupported osd opcode %s\n",
 			ceph_osd_op_name(src->op));
-- 
cgit v1.2.3


From 715e4cd405cfd67bd058e410b3e599bab2072645 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Thu, 13 Nov 2014 14:40:37 +0800
Subject: libceph: specify position of extent operation

allow specifying position of extent operation in multi-operations
osd request. This is required for cephfs to convert inline data to
normal data (compare xattr, then write object).

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
---
 fs/ceph/addr.c                  |  9 ++++++---
 fs/ceph/file.c                  |  8 +++++---
 include/linux/ceph/osd_client.h |  3 ++-
 net/ceph/osd_client.c           | 19 ++++++-------------
 4 files changed, 19 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 18c06bbaf136..f2c7aa878aa4 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -319,7 +319,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 	     off, len);
 	vino = ceph_vino(inode);
 	req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len,
-				    1, CEPH_OSD_OP_READ,
+				    0, 1, CEPH_OSD_OP_READ,
 				    CEPH_OSD_FLAG_READ, NULL,
 				    ci->i_truncate_seq, ci->i_truncate_size,
 				    false);
@@ -750,7 +750,6 @@ retry:
 	last_snapc = snapc;
 
 	while (!done && index <= end) {
-		int num_ops = do_sync ? 2 : 1;
 		unsigned i;
 		int first;
 		pgoff_t next;
@@ -850,7 +849,8 @@ get_more_pages:
 				len = wsize;
 				req = ceph_osdc_new_request(&fsc->client->osdc,
 							&ci->i_layout, vino,
-							offset, &len, num_ops,
+							offset, &len, 0,
+							do_sync ? 2 : 1,
 							CEPH_OSD_OP_WRITE,
 							CEPH_OSD_FLAG_WRITE |
 							CEPH_OSD_FLAG_ONDISK,
@@ -862,6 +862,9 @@ get_more_pages:
 					break;
 				}
 
+				if (do_sync)
+					osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
+
 				req->r_callback = writepages_finish;
 				req->r_inode = inode;
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d7e0da8366e6..c03ac4c4bcd1 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -598,7 +598,7 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
 		snapc = ci->i_snap_realm->cached_context;
 		vino = ceph_vino(inode);
 		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
-					    vino, pos, &len,
+					    vino, pos, &len, 0,
 					    2,/*include a 'startsync' command*/
 					    CEPH_OSD_OP_WRITE, flags, snapc,
 					    ci->i_truncate_seq,
@@ -609,6 +609,8 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
 			break;
 		}
 
+		osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
+
 		n = iov_iter_get_pages_alloc(from, &pages, len, &start);
 		if (unlikely(n < 0)) {
 			ret = n;
@@ -713,7 +715,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
 		snapc = ci->i_snap_realm->cached_context;
 		vino = ceph_vino(inode);
 		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
-					    vino, pos, &len, 1,
+					    vino, pos, &len, 0, 1,
 					    CEPH_OSD_OP_WRITE, flags, snapc,
 					    ci->i_truncate_seq,
 					    ci->i_truncate_size,
@@ -1111,7 +1113,7 @@ static int ceph_zero_partial_object(struct inode *inode,
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 					ceph_vino(inode),
 					offset, length,
-					1, op,
+					0, 1, op,
 					CEPH_OSD_FLAG_WRITE |
 					CEPH_OSD_FLAG_ONDISK,
 					NULL, 0, 0, false);
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index bcf9c2180ea5..5d86416d35f2 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -328,7 +328,8 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
 				      struct ceph_file_layout *layout,
 				      struct ceph_vino vino,
 				      u64 offset, u64 *len,
-				      int num_ops, int opcode, int flags,
+				      unsigned int which, int num_ops,
+				      int opcode, int flags,
 				      struct ceph_snap_context *snapc,
 				      u32 truncate_seq, u64 truncate_size,
 				      bool use_mempool);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index af1b3ee195e9..53299c7b0ca4 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -753,7 +753,8 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 					       struct ceph_file_layout *layout,
 					       struct ceph_vino vino,
-					       u64 off, u64 *plen, int num_ops,
+					       u64 off, u64 *plen,
+					       unsigned int which, int num_ops,
 					       int opcode, int flags,
 					       struct ceph_snap_context *snapc,
 					       u32 truncate_seq,
@@ -785,7 +786,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	}
 
 	if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
-		osd_req_op_init(req, 0, opcode);
+		osd_req_op_init(req, which, opcode);
 	} else {
 		u32 object_size = le32_to_cpu(layout->fl_object_size);
 		u32 object_base = off - objoff;
@@ -798,17 +799,9 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 					truncate_size = object_size;
 			}
 		}
-
-		osd_req_op_extent_init(req, 0, opcode, objoff, objlen,
+		osd_req_op_extent_init(req, which, opcode, objoff, objlen,
 				       truncate_size, truncate_seq);
 	}
-	/*
-	 * A second op in the ops array means the caller wants to
-	 * also issue a include a 'startsync' command so that the
-	 * osd will flush data quickly.
-	 */
-	if (num_ops > 1)
-		osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
 
 	req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
 
@@ -2675,7 +2668,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 
 	dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino,
 	     vino.snap, off, *plen);
-	req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 1,
+	req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1,
 				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
 				    NULL, truncate_seq, truncate_size,
 				    false);
@@ -2718,7 +2711,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 	int page_align = off & ~PAGE_MASK;
 
 	BUG_ON(vino.snap != CEPH_NOSNAP);	/* snapshots aren't writeable */
-	req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 1,
+	req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1,
 				    CEPH_OSD_OP_WRITE,
 				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
 				    snapc, truncate_seq, truncate_size,
-- 
cgit v1.2.3


From 31c542a199d79f0f402c2f3e04229464510d47ec Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Fri, 14 Nov 2014 21:41:55 +0800
Subject: ceph: add inline data to pagecache

Request reply and cap message can contain inline data. add inline data
to the page cache if there is Fc cap.

Signed-off-by: Yan, Zheng <zyan@redhat.com>
---
 fs/ceph/addr.c               | 43 +++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/caps.c               | 11 +++++++++++
 fs/ceph/inode.c              | 16 ++++++++++++++++
 fs/ceph/super.h              |  5 ++++-
 fs/ceph/super.h.rej          | 10 ++++++++++
 include/linux/ceph/ceph_fs.h |  1 +
 6 files changed, 85 insertions(+), 1 deletion(-)
 create mode 100644 fs/ceph/super.h.rej

(limited to 'include')

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index f2c7aa878aa4..4a3f55f27ab4 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1318,6 +1318,49 @@ out:
 	return ret;
 }
 
+void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
+			   char	*data, size_t len)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page;
+
+	if (locked_page) {
+		page = locked_page;
+	} else {
+		if (i_size_read(inode) == 0)
+			return;
+		page = find_or_create_page(mapping, 0,
+					   mapping_gfp_mask(mapping) & ~__GFP_FS);
+		if (!page)
+			return;
+		if (PageUptodate(page)) {
+			unlock_page(page);
+			page_cache_release(page);
+			return;
+		}
+	}
+
+	dout("fill_inline_data %p %llx.%llx len %lu locked_page %p\n",
+	     inode, ceph_vinop(inode), len, locked_page);
+
+	if (len > 0) {
+		void *kaddr = kmap_atomic(page);
+		memcpy(kaddr, data, len);
+		kunmap_atomic(kaddr);
+	}
+
+	if (page != locked_page) {
+		if (len < PAGE_CACHE_SIZE)
+			zero_user_segment(page, len, PAGE_CACHE_SIZE);
+		else
+			flush_dcache_page(page);
+
+		SetPageUptodate(page);
+		unlock_page(page);
+		page_cache_release(page);
+	}
+}
+
 static struct vm_operations_struct ceph_vmops = {
 	.fault		= ceph_filemap_fault,
 	.page_mkwrite	= ceph_page_mkwrite,
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b88ae601f309..6372eb9ce491 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2405,6 +2405,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	bool queue_invalidate = false;
 	bool queue_revalidate = false;
 	bool deleted_inode = false;
+	bool fill_inline = false;
 
 	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
 	     inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2578,6 +2579,13 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	}
 	BUG_ON(cap->issued & ~cap->implemented);
 
+	if (inline_version > 0 && inline_version >= ci->i_inline_version) {
+		ci->i_inline_version = inline_version;
+		if (ci->i_inline_version != CEPH_INLINE_NONE &&
+		    (newcaps & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)))
+			fill_inline = true;
+	}
+
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
@@ -2591,6 +2599,9 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			wake = true;
 	}
 
+	if (fill_inline)
+		ceph_fill_inline_data(inode, NULL, inline_data, inline_len);
+
 	if (queue_trunc) {
 		ceph_queue_vmtruncate(inode);
 		ceph_queue_revalidate(inode);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 72607c17e6fd..feea6a8f88ae 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -387,6 +387,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	spin_lock_init(&ci->i_ceph_lock);
 
 	ci->i_version = 0;
+	ci->i_inline_version = 0;
 	ci->i_time_warp_seq = 0;
 	ci->i_ceph_flags = 0;
 	ci->i_ordered_count = 0;
@@ -676,6 +677,7 @@ static int fill_inode(struct inode *inode,
 	bool wake = false;
 	bool queue_trunc = false;
 	bool new_version = false;
+	bool fill_inline = false;
 
 	dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
 	     inode, ceph_vinop(inode), le64_to_cpu(info->version),
@@ -875,8 +877,22 @@ static int fill_inode(struct inode *inode,
 			   ceph_vinop(inode));
 		__ceph_get_fmode(ci, cap_fmode);
 	}
+
+	if (iinfo->inline_version > 0 &&
+	    iinfo->inline_version >= ci->i_inline_version) {
+		int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
+		ci->i_inline_version = iinfo->inline_version;
+		if (ci->i_inline_version != CEPH_INLINE_NONE &&
+		    (le32_to_cpu(info->cap.caps) & cache_caps))
+			fill_inline = true;
+	}
+
 	spin_unlock(&ci->i_ceph_lock);
 
+	if (fill_inline)
+		ceph_fill_inline_data(inode, NULL,
+				      iinfo->inline_data, iinfo->inline_len);
+
 	if (wake)
 		wake_up_all(&ci->i_cap_wq);
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fc1c8255dead..b0de9162758b 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -253,6 +253,7 @@ struct ceph_inode_info {
 	spinlock_t i_ceph_lock;
 
 	u64 i_version;
+	u64 i_inline_version;
 	u32 i_time_warp_seq;
 
 	unsigned i_ceph_flags;
@@ -858,7 +859,7 @@ extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
 				      int mds, int drop, int unless);
 
 extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
-			 int *got, loff_t endoff);
+			 loff_t endoff, int *got, struct page **pinned_page);
 
 /* for counting open files by mode */
 static inline void __ceph_get_fmode(struct ceph_inode_info *ci, int mode)
@@ -880,6 +881,8 @@ extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags, umode_t mode,
 			    int *opened);
 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);
 
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;
diff --git a/fs/ceph/super.h.rej b/fs/ceph/super.h.rej
new file mode 100644
index 000000000000..88fe3dfadb29
--- /dev/null
+++ b/fs/ceph/super.h.rej
@@ -0,0 +1,10 @@
+--- fs/ceph/super.h
++++ fs/ceph/super.h
+@@ -254,6 +255,7 @@
+	spinlock_t i_ceph_lock;
+
+	u64 i_version;
++	u64 i_inline_version;
+	u32 i_time_warp_seq;
+
+	unsigned i_ceph_flags;
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 31d8b98b7f96..2d4acfa2c7b7 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -552,6 +552,7 @@ struct ceph_filelock {
 
 int ceph_flags_to_mode(int flags);
 
+#define CEPH_INLINE_NONE	((__u64)-1)
 
 /* capability bits */
 #define CEPH_CAP_PIN         1  /* no specific capabilities beyond the pin */
-- 
cgit v1.2.3


From 01deead041e03c9a6b4e1b2dd165dee4cced6112 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Fri, 14 Nov 2014 21:56:29 +0800
Subject: ceph: use getattr request to fetch inline data

Add a new parameter 'locked_page' to ceph_do_getattr(). If inline data
in getattr reply will be copied to the page.

Signed-off-by: Yan, Zheng <zyan@redhat.com>
---
 fs/ceph/inode.c              | 34 +++++++++++++++++++++++++---------
 fs/ceph/mds_client.h         |  1 +
 fs/ceph/super.h              |  7 ++++++-
 include/linux/ceph/ceph_fs.h |  2 ++
 4 files changed, 34 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index feea6a8f88ae..0bdabd1bff8a 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -659,7 +659,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
  * Populate an inode based on info from mds.  May be called on new or
  * existing inodes.
  */
-static int fill_inode(struct inode *inode,
+static int fill_inode(struct inode *inode, struct page *locked_page,
 		      struct ceph_mds_reply_info_in *iinfo,
 		      struct ceph_mds_reply_dirfrag *dirinfo,
 		      struct ceph_mds_session *session,
@@ -883,14 +883,15 @@ static int fill_inode(struct inode *inode,
 		int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
 		ci->i_inline_version = iinfo->inline_version;
 		if (ci->i_inline_version != CEPH_INLINE_NONE &&
-		    (le32_to_cpu(info->cap.caps) & cache_caps))
+		    (locked_page ||
+		     (le32_to_cpu(info->cap.caps) & cache_caps)))
 			fill_inline = true;
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (fill_inline)
-		ceph_fill_inline_data(inode, NULL,
+		ceph_fill_inline_data(inode, locked_page,
 				      iinfo->inline_data, iinfo->inline_len);
 
 	if (wake)
@@ -1080,7 +1081,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		struct inode *dir = req->r_locked_dir;
 
 		if (dir) {
-			err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
+			err = fill_inode(dir, NULL,
+					 &rinfo->diri, rinfo->dirfrag,
 					 session, req->r_request_started, -1,
 					 &req->r_caps_reservation);
 			if (err < 0)
@@ -1150,7 +1152,7 @@ retry_lookup:
 		}
 		req->r_target_inode = in;
 
-		err = fill_inode(in, &rinfo->targeti, NULL,
+		err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
 				session, req->r_request_started,
 				(!req->r_aborted && rinfo->head->result == 0) ?
 				req->r_fmode : -1,
@@ -1321,7 +1323,7 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
 			dout("new_inode badness got %d\n", err);
 			continue;
 		}
-		rc = fill_inode(in, &rinfo->dir_in[i], NULL, session,
+		rc = fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
 				req->r_request_started, -1,
 				&req->r_caps_reservation);
 		if (rc < 0) {
@@ -1437,7 +1439,7 @@ retry_lookup:
 			}
 		}
 
-		if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
+		if (fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
 			       req->r_request_started, -1,
 			       &req->r_caps_reservation) < 0) {
 			pr_err("fill_inode badness on %p\n", in);
@@ -1920,7 +1922,8 @@ out_put:
  * Verify that we have a lease on the given mask.  If not,
  * do a getattr against an mds.
  */
-int ceph_do_getattr(struct inode *inode, int mask, bool force)
+int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
+		      int mask, bool force)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1932,7 +1935,8 @@ int ceph_do_getattr(struct inode *inode, int mask, bool force)
 		return 0;
 	}
 
-	dout("do_getattr inode %p mask %s mode 0%o\n", inode, ceph_cap_string(mask), inode->i_mode);
+	dout("do_getattr inode %p mask %s mode 0%o\n",
+	     inode, ceph_cap_string(mask), inode->i_mode);
 	if (!force && ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
 		return 0;
 
@@ -1943,7 +1947,19 @@ int ceph_do_getattr(struct inode *inode, int mask, bool force)
 	ihold(inode);
 	req->r_num_caps = 1;
 	req->r_args.getattr.mask = cpu_to_le32(mask);
+	req->r_locked_page = locked_page;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	if (locked_page && err == 0) {
+		u64 inline_version = req->r_reply_info.targeti.inline_version;
+		if (inline_version == 0) {
+			/* the reply is supposed to contain inline data */
+			err = -EINVAL;
+		} else if (inline_version == CEPH_INLINE_NONE) {
+			err = -ENODATA;
+		} else {
+			err = req->r_reply_info.targeti.inline_len;
+		}
+	}
 	ceph_mdsc_put_request(req);
 	dout("do_getattr result=%d\n", err);
 	return err;
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 01f5e4cfd684..e2817d00f7d9 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -223,6 +223,7 @@ struct ceph_mds_request {
 	int r_request_release_offset;
 	struct ceph_msg  *r_reply;
 	struct ceph_mds_reply_info_parsed r_reply_info;
+	struct page *r_locked_page;
 	int r_err;
 	bool r_aborted;
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b0de9162758b..6d56fae863ca 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -744,7 +744,12 @@ extern void ceph_queue_vmtruncate(struct inode *inode);
 extern void ceph_queue_invalidate(struct inode *inode);
 extern void ceph_queue_writeback(struct inode *inode);
 
-extern int ceph_do_getattr(struct inode *inode, int mask, bool force);
+extern int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
+			     int mask, bool force);
+static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
+{
+	return __ceph_do_getattr(inode, NULL, mask, force);
+}
 extern int ceph_permission(struct inode *inode, int mask);
 extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
 extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 2d4acfa2c7b7..c0dadaac26e3 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -617,6 +617,8 @@ int ceph_flags_to_mode(int flags);
 				 CEPH_CAP_LINK_SHARED |	\
 				 CEPH_CAP_FILE_SHARED |	\
 				 CEPH_CAP_XATTR_SHARED)
+#define CEPH_STAT_CAP_INLINE_DATA (CEPH_CAP_FILE_SHARED | \
+				   CEPH_CAP_FILE_RD)
 
 #define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED |			\
 			      CEPH_CAP_LINK_SHARED |			\
-- 
cgit v1.2.3


From 84a1d2d1ecd9ae2fc1ae51d8529090000e88a210 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@redhat.com>
Date: Mon, 17 Nov 2014 21:45:24 +0300
Subject: libceph: fixup includes in pagelist.h

pagelist.h needs to include linux/types.h and asm/byteorder.h and not
rely on other headers pulling yet another set of headers.

Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/pagelist.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h
index 5f871d84ddce..13d71fe18b0c 100644
--- a/include/linux/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -1,8 +1,10 @@
 #ifndef __FS_CEPH_PAGELIST_H
 #define __FS_CEPH_PAGELIST_H
 
-#include <linux/list.h>
+#include <asm/byteorder.h>
 #include <linux/atomic.h>
+#include <linux/list.h>
+#include <linux/types.h>
 
 struct ceph_pagelist {
 	struct list_head head;
-- 
cgit v1.2.3