Merge tag 'ceph-for-4.20-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The highlights are:

   - a series that fixes some old memory allocation issues in libceph
     (myself). We no longer allocate memory in places where allocation
     failures cannot be handled and BUG when the allocation fails.

   - support for copy_file_range() syscall (Luis Henriques). If size and
     alignment conditions are met, it leverages RADOS copy-from
     operation. Otherwise, a local copy is performed.

   - a patch that reduces memory requirement of ceph_sync_read() from
     the size of the entire read to the size of one object (Zheng Yan).

   - fallocate() syscall is now restricted to FALLOC_FL_PUNCH_HOLE (Luis
     Henriques)"

* tag 'ceph-for-4.20-rc1' of git://github.com/ceph/ceph-client: (25 commits)
  ceph: new mount option to disable usage of copy-from op
  ceph: support copy_file_range file operation
  libceph: support the RADOS copy-from operation
  ceph: add non-blocking parameter to ceph_try_get_caps()
  libceph: check reply num_data_items in setup_request_data()
  libceph: preallocate message data items
  libceph, rbd, ceph: move ceph_osdc_alloc_messages() calls
  libceph: introduce alloc_watch_request()
  libceph: assign cookies in linger_submit()
  libceph: enable fallback to ceph_msg_new() in ceph_msgpool_get()
  ceph: num_ops is off by one in ceph_aio_retry_work()
  libceph: no need to call osd_req_opcode_valid() in osd_req_encode_op()
  ceph: set timeout conditionally in __cap_delay_requeue
  libceph: don't consume a ref on pagelist in ceph_msg_data_add_pagelist()
  libceph: introduce ceph_pagelist_alloc()
  libceph: osd_req_op_cls_init() doesn't need to take opcode
  libceph: bump CEPH_MSG_MAX_DATA_LEN
  ceph: only allow punch hole mode in fallocate
  ceph: refactor ceph_sync_read()
  ceph: check if LOOKUPNAME request was aborted when filling trace
  ...

include/linux/ceph/libceph.h

@@ -81,7 +81,13 @@ struct ceph_options {
 
 #define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
 #define CEPH_MSG_MAX_MIDDLE_LEN	(16*1024*1024)
-#define CEPH_MSG_MAX_DATA_LEN	(16*1024*1024)
+
+/*
+ * Handle the largest possible rbd object in one message.
+ * There is no limit on the size of cephfs objects, but it has to obey
+ * rsize and wsize mount options anyway.
+ */
+#define CEPH_MSG_MAX_DATA_LEN	(32*1024*1024)
 
 #define CEPH_AUTH_NAME_DEFAULT   "guest"
 

include/linux/ceph/messenger.h

@@ -82,22 +82,6 @@ enum ceph_msg_data_type {
 	CEPH_MSG_DATA_BVECS,	/* data source/destination is a bio_vec array */
 };
 
-static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type)
-{
-	switch (type) {
-	case CEPH_MSG_DATA_NONE:
-	case CEPH_MSG_DATA_PAGES:
-	case CEPH_MSG_DATA_PAGELIST:
-#ifdef CONFIG_BLOCK
-	case CEPH_MSG_DATA_BIO:
-#endif /* CONFIG_BLOCK */
-	case CEPH_MSG_DATA_BVECS:
-		return true;
-	default:
-		return false;
-	}
-}
-
 #ifdef CONFIG_BLOCK
 
 struct ceph_bio_iter {
@@ -181,7 +165,6 @@ struct ceph_bvec_iter {
 } while (0)
 
 struct ceph_msg_data {
-	struct list_head		links;	/* ceph_msg->data */
 	enum ceph_msg_data_type		type;
 	union {
 #ifdef CONFIG_BLOCK
@@ -202,7 +185,6 @@ struct ceph_msg_data {
 
 struct ceph_msg_data_cursor {
 	size_t			total_resid;	/* across all data items */
-	struct list_head	*data_head;	/* = &ceph_msg->data */
 
 	struct ceph_msg_data	*data;		/* current data item */
 	size_t			resid;		/* bytes not yet consumed */
@@ -240,7 +222,9 @@ struct ceph_msg {
 	struct ceph_buffer *middle;
 
 	size_t				data_length;
-	struct list_head		data;
+	struct ceph_msg_data		*data;
+	int				num_data_items;
+	int				max_data_items;
 	struct ceph_msg_data_cursor	cursor;
 
 	struct ceph_connection *con;
@@ -381,6 +365,8 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos,
 void ceph_msg_data_add_bvecs(struct ceph_msg *msg,
 			     struct ceph_bvec_iter *bvec_pos);
 
+struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items,
+			       gfp_t flags, bool can_fail);
 extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 				     bool can_fail);
 

include/linux/ceph/msgpool.h

@@ -13,14 +13,15 @@ struct ceph_msgpool {
 	mempool_t *pool;
 	int type;               /* preallocated message type */
 	int front_len;          /* preallocated payload size */
+	int max_data_items;
 };
 
-extern int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
-			     int front_len, int size, bool blocking,
-			     const char *name);
+int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
+		      int front_len, int max_data_items, int size,
+		      const char *name);
 extern void ceph_msgpool_destroy(struct ceph_msgpool *pool);
-extern struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *,
-					 int front_len);
+struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len,
+				  int max_data_items);
 extern void ceph_msgpool_put(struct ceph_msgpool *, struct ceph_msg *);
 
 #endif

include/linux/ceph/osd_client.h

@@ -136,6 +136,13 @@ struct ceph_osd_req_op {
 			u64 expected_object_size;
 			u64 expected_write_size;
 		} alloc_hint;
+		struct {
+			u64 snapid;
+			u64 src_version;
+			u8 flags;
+			u32 src_fadvise_flags;
+			struct ceph_osd_data osd_data;
+		} copy_from;
 	};
 };
 
@@ -444,9 +451,8 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *,
 					struct page **pages, u64 length,
 					u32 alignment, bool pages_from_pool,
 					bool own_pages);
-extern int osd_req_op_cls_init(struct ceph_osd_request *osd_req,
-					unsigned int which, u16 opcode,
-					const char *class, const char *method);
+int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
+			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);
@@ -511,6 +517,16 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc,
 				struct timespec64 *mtime,
 				struct page **pages, int nr_pages);
 
+int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
+			u64 src_snapid, u64 src_version,
+			struct ceph_object_id *src_oid,
+			struct ceph_object_locator *src_oloc,
+			u32 src_fadvise_flags,
+			struct ceph_object_id *dst_oid,
+			struct ceph_object_locator *dst_oloc,
+			u32 dst_fadvise_flags,
+			u8 copy_from_flags);
+
 /* watch/notify */
 struct ceph_osd_linger_request *
 ceph_osdc_watch(struct ceph_osd_client *osdc,

include/linux/ceph/pagelist.h

@@ -23,16 +23,7 @@ struct ceph_pagelist_cursor {
 	size_t room;		    /* room remaining to reset to */
 };
 
-static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
-{
-	INIT_LIST_HEAD(&pl->head);
-	pl->mapped_tail = NULL;
-	pl->length = 0;
-	pl->room = 0;
-	INIT_LIST_HEAD(&pl->free_list);
-	pl->num_pages_free = 0;
-	refcount_set(&pl->refcnt, 1);
-}
+struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags);
 
 extern void ceph_pagelist_release(struct ceph_pagelist *pl);
 

include/linux/ceph/rados.h

@@ -410,6 +410,14 @@ enum {
 enum {
 	CEPH_OSD_OP_FLAG_EXCL = 1,      /* EXCL object create */
 	CEPH_OSD_OP_FLAG_FAILOK = 2,    /* continue despite failure */
+	CEPH_OSD_OP_FLAG_FADVISE_RANDOM	    = 0x4, /* the op is random */
+	CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL = 0x8, /* the op is sequential */
+	CEPH_OSD_OP_FLAG_FADVISE_WILLNEED   = 0x10,/* data will be accessed in
+						      the near future */
+	CEPH_OSD_OP_FLAG_FADVISE_DONTNEED   = 0x20,/* data will not be accessed
+						      in the near future */
+	CEPH_OSD_OP_FLAG_FADVISE_NOCACHE    = 0x40,/* data will be accessed only
+						      once by this client */
 };
 
 #define EOLDSNAPC    ERESTART  /* ORDERSNAP flag set; writer has old snapc*/
@@ -431,6 +439,15 @@ enum {
 	CEPH_OSD_CMPXATTR_MODE_U64    = 2
 };
 
+enum {
+	CEPH_OSD_COPY_FROM_FLAG_FLUSH = 1,       /* part of a flush operation */
+	CEPH_OSD_COPY_FROM_FLAG_IGNORE_OVERLAY = 2, /* ignore pool overlay */
+	CEPH_OSD_COPY_FROM_FLAG_IGNORE_CACHE = 4,   /* ignore osd cache logic */
+	CEPH_OSD_COPY_FROM_FLAG_MAP_SNAP_CLONE = 8, /* map snap direct to
+						     * cloneid */
+	CEPH_OSD_COPY_FROM_FLAG_RWORDERED = 16,     /* order with write */
+};
+
 enum {
 	CEPH_OSD_WATCH_OP_UNWATCH = 0,
 	CEPH_OSD_WATCH_OP_LEGACY_WATCH = 1,
@@ -497,6 +514,17 @@ struct ceph_osd_op {
 			__le64 expected_object_size;
 			__le64 expected_write_size;
 		} __attribute__ ((packed)) alloc_hint;
+		struct {
+			__le64 snapid;
+			__le64 src_version;
+			__u8 flags; /* CEPH_OSD_COPY_FROM_FLAG_* */
+			/*
+			 * CEPH_OSD_OP_FLAG_FADVISE_*: fadvise flags
+			 * for src object, flags for dest object are in
+			 * ceph_osd_op::flags.
+			 */
+			__le32 src_fadvise_flags;
+		} __attribute__ ((packed)) copy_from;
 	};
 	__le32 payload_len;
 } __attribute__ ((packed));