summaryrefslogtreecommitdiff
path: root/include/linux/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/ceph')
-rw-r--r--include/linux/ceph/ceph_debug.h42
-rw-r--r--include/linux/ceph/ceph_fs.h42
-rw-r--r--include/linux/ceph/decode.h2
-rw-r--r--include/linux/ceph/libceph.h21
-rw-r--r--include/linux/ceph/mdsmap.h72
-rw-r--r--include/linux/ceph/messenger.h50
-rw-r--r--include/linux/ceph/mon_client.h2
-rw-r--r--include/linux/ceph/osd_client.h109
-rw-r--r--include/linux/ceph/pagelist.h12
-rw-r--r--include/linux/ceph/rados.h4
10 files changed, 216 insertions, 140 deletions
diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h
index d5a5da838caf..5f904591fa5f 100644
--- a/include/linux/ceph/ceph_debug.h
+++ b/include/linux/ceph/ceph_debug.h
@@ -19,12 +19,21 @@
pr_debug("%.*s %12.12s:%-4d : " fmt, \
8 - (int)sizeof(KBUILD_MODNAME), " ", \
kbasename(__FILE__), __LINE__, ##__VA_ARGS__)
+# define doutc(client, fmt, ...) \
+ pr_debug("%.*s %12.12s:%-4d : [%pU %llu] " fmt, \
+ 8 - (int)sizeof(KBUILD_MODNAME), " ", \
+ kbasename(__FILE__), __LINE__, \
+ &client->fsid, client->monc.auth->global_id, \
+ ##__VA_ARGS__)
# else
/* faux printk call just to see any compiler warnings. */
-# define dout(fmt, ...) do { \
- if (0) \
- printk(KERN_DEBUG fmt, ##__VA_ARGS__); \
- } while (0)
+# define dout(fmt, ...) \
+ no_printk(KERN_DEBUG fmt, ##__VA_ARGS__)
+# define doutc(client, fmt, ...) \
+ no_printk(KERN_DEBUG "[%pU %llu] " fmt, \
+ &client->fsid, \
+ client->monc.auth->global_id, \
+ ##__VA_ARGS__)
# endif
#else
@@ -33,7 +42,32 @@
* or, just wrap pr_debug
*/
# define dout(fmt, ...) pr_debug(" " fmt, ##__VA_ARGS__)
+# define doutc(client, fmt, ...) \
+ pr_debug(" [%pU %llu] %s: " fmt, &client->fsid, \
+ client->monc.auth->global_id, __func__, ##__VA_ARGS__)
#endif
+#define pr_notice_client(client, fmt, ...) \
+ pr_notice("[%pU %llu]: " fmt, &client->fsid, \
+ client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_info_client(client, fmt, ...) \
+ pr_info("[%pU %llu]: " fmt, &client->fsid, \
+ client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_warn_client(client, fmt, ...) \
+ pr_warn("[%pU %llu]: " fmt, &client->fsid, \
+ client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_warn_once_client(client, fmt, ...) \
+ pr_warn_once("[%pU %llu]: " fmt, &client->fsid, \
+ client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_err_client(client, fmt, ...) \
+ pr_err("[%pU %llu]: " fmt, &client->fsid, \
+ client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_warn_ratelimited_client(client, fmt, ...) \
+ pr_warn_ratelimited("[%pU %llu]: " fmt, &client->fsid, \
+ client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_err_ratelimited_client(client, fmt, ...) \
+ pr_err_ratelimited("[%pU %llu]: " fmt, &client->fsid, \
+ client->monc.auth->global_id, ##__VA_ARGS__)
+
#endif
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 49586ff26152..c7f2c63b3bc3 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -357,16 +357,26 @@ enum {
CEPH_MDS_OP_RENAMESNAP = 0x01403,
};
-extern const char *ceph_mds_op_name(int op);
+#define IS_CEPH_MDS_OP_NEWINODE(op) (op == CEPH_MDS_OP_CREATE || \
+ op == CEPH_MDS_OP_MKNOD || \
+ op == CEPH_MDS_OP_MKDIR || \
+ op == CEPH_MDS_OP_SYMLINK)
+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.
@@ -479,7 +489,7 @@ union ceph_mds_request_args_ext {
#define CEPH_MDS_FLAG_WANT_DENTRY 2 /* want dentry in reply */
#define CEPH_MDS_FLAG_ASYNC 4 /* request is asynchronous */
-struct ceph_mds_request_head_old {
+struct ceph_mds_request_head_legacy {
__le64 oldest_client_tid;
__le32 mdsmap_epoch; /* on client */
__le32 flags; /* CEPH_MDS_FLAG_* */
@@ -492,20 +502,26 @@ struct ceph_mds_request_head_old {
union ceph_mds_request_args args;
} __attribute__ ((packed));
-#define CEPH_MDS_REQUEST_HEAD_VERSION 1
+#define CEPH_MDS_REQUEST_HEAD_VERSION 3
struct ceph_mds_request_head {
__le16 version; /* struct version */
__le64 oldest_client_tid;
__le32 mdsmap_epoch; /* on client */
__le32 flags; /* CEPH_MDS_FLAG_* */
- __u8 num_retry, num_fwd; /* count retry, fwd attempts */
+ __u8 num_retry, num_fwd; /* legacy count retry and fwd attempts */
__le16 num_releases; /* # include cap/lease release records */
__le32 op; /* mds op code */
__le32 caller_uid, caller_gid;
__le64 ino; /* use this ino for openc, mkdir, mknod,
etc. (if replaying) */
union ceph_mds_request_args_ext args;
+
+ __le32 ext_num_retry; /* new count retry attempts */
+ __le32 ext_num_fwd; /* new count fwd attempts */
+
+ __le32 struct_len; /* to store size of struct ceph_mds_request_head */
+ __le32 owner_uid, owner_gid; /* used for OPs which create inodes */
} __attribute__ ((packed));
/* cap/lease release record */
@@ -778,7 +794,7 @@ struct ceph_mds_caps {
struct ceph_mds_cap_peer {
__le64 cap_id;
- __le32 seq;
+ __le32 issue_seq;
__le32 mseq;
__le32 mds;
__u8 flags;
@@ -792,7 +808,7 @@ struct ceph_mds_cap_release {
struct ceph_mds_cap_item {
__le64 ino;
__le64 cap_id;
- __le32 migrate_seq, seq;
+ __le32 migrate_seq, issue_seq;
} __attribute__ ((packed));
#define CEPH_MDS_LEASE_REVOKE 1 /* mds -> client */
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index 04f3ace5787b..8fc1aed64113 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -6,7 +6,7 @@
#include <linux/bug.h>
#include <linux/slab.h>
#include <linux/time.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/ceph/types.h>
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 00af2c98da75..63e0e2aa1ce9 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -4,7 +4,7 @@
#include <linux/ceph/ceph_debug.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/backing-dev.h>
#include <linux/completion.h>
#include <linux/exportfs.h>
@@ -99,16 +99,6 @@ struct ceph_options {
#define CEPH_AUTH_NAME_DEFAULT "guest"
-/* mount state */
-enum {
- CEPH_MOUNT_MOUNTING,
- CEPH_MOUNT_MOUNTED,
- CEPH_MOUNT_UNMOUNTING,
- CEPH_MOUNT_UNMOUNTED,
- CEPH_MOUNT_SHUTDOWN,
- CEPH_MOUNT_RECOVER,
-};
-
static inline unsigned long ceph_timeout_jiffies(unsigned long timeout)
{
return timeout ?: MAX_SCHEDULE_TIMEOUT;
@@ -316,8 +306,7 @@ struct ceph_entity_addr *ceph_client_addr(struct ceph_client *client);
u64 ceph_client_gid(struct ceph_client *client);
extern void ceph_destroy_client(struct ceph_client *client);
extern void ceph_reset_client_addr(struct ceph_client *client);
-extern int __ceph_open_session(struct ceph_client *client,
- unsigned long started);
+extern int __ceph_open_session(struct ceph_client *client);
extern int ceph_open_session(struct ceph_client *client);
int ceph_wait_for_latest_osdmap(struct ceph_client *client,
unsigned long timeout);
@@ -327,12 +316,6 @@ extern void ceph_release_page_vector(struct page **pages, int num_pages);
extern void ceph_put_page_vector(struct page **pages, int num_pages,
bool dirty);
extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
-extern int ceph_copy_user_to_page_vector(struct page **pages,
- const void __user *data,
- loff_t off, size_t len);
-extern void ceph_copy_to_page_vector(struct page **pages,
- const void *data,
- loff_t off, size_t len);
extern void ceph_copy_from_page_vector(struct page **pages,
void *data,
loff_t off, size_t len);
diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
deleted file mode 100644
index 4c3e0648dc27..000000000000
--- a/include/linux/ceph/mdsmap.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _FS_CEPH_MDSMAP_H
-#define _FS_CEPH_MDSMAP_H
-
-#include <linux/bug.h>
-#include <linux/ceph/types.h>
-
-/*
- * mds map - describe servers in the mds cluster.
- *
- * we limit fields to those the client actually xcares about
- */
-struct ceph_mds_info {
- u64 global_id;
- struct ceph_entity_addr addr;
- s32 state;
- int num_export_targets;
- bool laggy;
- u32 *export_targets;
-};
-
-struct ceph_mdsmap {
- u32 m_epoch, m_client_epoch, m_last_failure;
- u32 m_root;
- u32 m_session_timeout; /* seconds */
- u32 m_session_autoclose; /* seconds */
- u64 m_max_file_size;
- u64 m_max_xattr_size; /* maximum size for xattrs blob */
- u32 m_max_mds; /* expected up:active mds number */
- u32 m_num_active_mds; /* actual up:active mds number */
- u32 possible_max_rank; /* possible max rank index */
- struct ceph_mds_info *m_info;
-
- /* which object pools file data can be stored in */
- int m_num_data_pg_pools;
- u64 *m_data_pg_pools;
- u64 m_cas_pg_pool;
-
- bool m_enabled;
- bool m_damaged;
- int m_num_laggy;
-};
-
-static inline struct ceph_entity_addr *
-ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
-{
- if (w >= m->possible_max_rank)
- return NULL;
- return &m->m_info[w].addr;
-}
-
-static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w)
-{
- BUG_ON(w < 0);
- if (w >= m->possible_max_rank)
- return CEPH_MDS_STATE_DNE;
- return m->m_info[w].state;
-}
-
-static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w)
-{
- if (w >= 0 && w < m->possible_max_rank)
- return m->m_info[w].laggy;
- return false;
-}
-
-extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m);
-struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2);
-extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m);
-extern bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m);
-
-#endif
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 99c1726be6ee..6aa4c6478c9f 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -2,6 +2,7 @@
#ifndef __FS_CEPH_MESSENGER_H
#define __FS_CEPH_MESSENGER_H
+#include <crypto/sha2.h>
#include <linux/bvec.h>
#include <linux/crypto.h>
#include <linux/kref.h>
@@ -17,6 +18,7 @@
struct ceph_msg;
struct ceph_connection;
+struct ceph_msg_data_cursor;
/*
* Ceph defines these callbacks for handling connection events.
@@ -70,6 +72,30 @@ 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 */
@@ -98,6 +124,7 @@ enum ceph_msg_data_type {
CEPH_MSG_DATA_BIO, /* data source/destination is a bio list */
#endif /* CONFIG_BLOCK */
CEPH_MSG_DATA_BVECS, /* data source/destination is a bio_vec array */
+ CEPH_MSG_DATA_ITER, /* data source/destination is an iov_iter */
};
#ifdef CONFIG_BLOCK
@@ -199,6 +226,7 @@ struct ceph_msg_data {
bool own_pages;
};
struct ceph_pagelist *pagelist;
+ struct iov_iter iter;
};
};
@@ -207,6 +235,7 @@ 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 need_crc; /* crc update needed */
union {
#ifdef CONFIG_BLOCK
@@ -222,6 +251,10 @@ struct ceph_msg_data_cursor {
struct page *page; /* page from list */
size_t offset; /* bytes from list */
};
+ struct {
+ struct iov_iter iov_iter;
+ unsigned int lastlen;
+ };
};
};
@@ -251,6 +284,7 @@ struct ceph_msg {
struct kref kref;
bool more_to_follow;
bool needs_out_seq;
+ u64 sparse_read_total;
int front_alloc_len;
struct ceph_msgpool *pool;
@@ -309,6 +343,10 @@ 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;
@@ -375,7 +413,8 @@ struct ceph_connection_v2_info {
struct ceph_msg_data_cursor in_cursor;
struct ceph_msg_data_cursor out_cursor;
- struct crypto_shash *hmac_tfm; /* post-auth signature */
+ struct hmac_sha256_key hmac_key; /* post-auth signature */
+ bool hmac_key_set;
struct crypto_aead *gcm_tfm; /* on-wire encryption */
struct aead_request *gcm_req;
struct crypto_wait gcm_wait;
@@ -395,6 +434,7 @@ 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];
@@ -510,12 +550,12 @@ void ceph_addr_set_port(struct ceph_entity_addr *addr, int p);
void ceph_con_process_message(struct ceph_connection *con);
int ceph_con_in_msg_alloc(struct ceph_connection *con,
struct ceph_msg_header *hdr, int *skip);
-void ceph_con_get_out_msg(struct ceph_connection *con);
+struct ceph_msg *ceph_con_get_out_msg(struct ceph_connection *con);
/* messenger_v1.c */
int ceph_con_v1_try_read(struct ceph_connection *con);
int ceph_con_v1_try_write(struct ceph_connection *con);
-void ceph_con_v1_revoke(struct ceph_connection *con);
+void ceph_con_v1_revoke(struct ceph_connection *con, struct ceph_msg *msg);
void ceph_con_v1_revoke_incoming(struct ceph_connection *con);
bool ceph_con_v1_opened(struct ceph_connection *con);
void ceph_con_v1_reset_session(struct ceph_connection *con);
@@ -524,7 +564,7 @@ void ceph_con_v1_reset_protocol(struct ceph_connection *con);
/* messenger_v2.c */
int ceph_con_v2_try_read(struct ceph_connection *con);
int ceph_con_v2_try_write(struct ceph_connection *con);
-void ceph_con_v2_revoke(struct ceph_connection *con);
+void ceph_con_v2_revoke(struct ceph_connection *con, struct ceph_msg *msg);
void ceph_con_v2_revoke_incoming(struct ceph_connection *con);
bool ceph_con_v2_opened(struct ceph_connection *con);
void ceph_con_v2_reset_session(struct ceph_connection *con);
@@ -573,6 +613,8 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos,
#endif /* CONFIG_BLOCK */
void ceph_msg_data_add_bvecs(struct ceph_msg *msg,
struct ceph_bvec_iter *bvec_pos);
+void ceph_msg_data_add_iter(struct ceph_msg *msg,
+ struct iov_iter *iter);
struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items,
gfp_t flags, bool can_fail);
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index b658961156a0..7a9a40163c0f 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -19,7 +19,7 @@ struct ceph_monmap {
struct ceph_fsid fsid;
u32 epoch;
u32 num_mon;
- struct ceph_entity_inst mon_inst[];
+ struct ceph_entity_inst mon_inst[] __counted_by(num_mon);
};
struct ceph_mon_client;
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index fb6be72104df..50b14a5661c7 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -29,14 +29,63 @@ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
#define CEPH_HOMELESS_OSD -1
-/* a given osd we're communicating with */
+/*
+ * 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;
+
+/* 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_PRE,
+ 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 */
+ u32 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.
+ *
+ * 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;
+ int o_sparse_op_idx;
struct ceph_osd_client *o_osdc;
int o_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;
@@ -46,6 +95,7 @@ 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
@@ -59,6 +109,7 @@ enum ceph_osd_data_type {
CEPH_OSD_DATA_TYPE_BIO,
#endif /* CONFIG_BLOCK */
CEPH_OSD_DATA_TYPE_BVECS,
+ CEPH_OSD_DATA_TYPE_ITER,
};
struct ceph_osd_data {
@@ -82,6 +133,7 @@ struct ceph_osd_data {
struct ceph_bvec_iter bvec_pos;
u32 num_bvecs;
};
+ struct iov_iter iter;
};
};
@@ -98,6 +150,8 @@ 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 {
@@ -145,6 +199,9 @@ struct ceph_osd_req_op {
u32 src_fadvise_flags;
struct ceph_osd_data osd_data;
} copy_from;
+ struct {
+ u64 ver;
+ } assert_ver;
};
};
@@ -199,6 +256,7 @@ 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;
@@ -211,9 +269,9 @@ 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 */
@@ -221,7 +279,7 @@ struct ceph_osd_request {
int r_attempts;
u32 r_map_dne_bound;
- struct ceph_osd_req_op r_ops[];
+ struct ceph_osd_req_op r_ops[] __counted_by(r_num_ops);
};
struct ceph_request_redirect {
@@ -391,8 +449,6 @@ extern int ceph_osdc_init(struct ceph_osd_client *osdc,
extern void ceph_osdc_stop(struct ceph_osd_client *osdc);
extern void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc);
-extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
- struct ceph_msg *msg);
extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
struct ceph_msg *msg);
void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb);
@@ -434,9 +490,6 @@ extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *,
struct page **pages, u64 length,
u32 alignment, bool pages_from_pool,
bool own_pages);
-extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *,
- unsigned int which,
- struct ceph_pagelist *pagelist);
#ifdef CONFIG_BLOCK
void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
unsigned int which,
@@ -450,10 +503,9 @@ void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
unsigned int which,
struct ceph_bvec_iter *bvec_pos);
+void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req,
+ unsigned int which, struct iov_iter *iter);
-extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *,
- unsigned int which,
- struct ceph_pagelist *pagelist);
extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *,
unsigned int which,
struct page **pages, u64 length,
@@ -504,6 +556,23 @@ 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, int cnt)
+{
+ if (!cnt)
+ cnt = CEPH_SPARSE_EXT_ARRAY_INITIAL;
+
+ return __ceph_alloc_sparse_ext_map(op, cnt);
+}
+
extern void ceph_osdc_get_request(struct ceph_osd_request *req);
extern void ceph_osdc_put_request(struct ceph_osd_request *req);
@@ -551,12 +620,24 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
u32 timeout,
struct page ***preply_pages,
size_t *preply_len);
-int ceph_osdc_watch_check(struct ceph_osd_client *osdc,
- struct ceph_osd_linger_request *lreq);
int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
struct ceph_object_id *oid,
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
diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h
index 5dead8486fd8..879bec0863aa 100644
--- a/include/linux/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -17,12 +17,6 @@ struct ceph_pagelist {
refcount_t refcnt;
};
-struct ceph_pagelist_cursor {
- struct ceph_pagelist *pl; /* pagelist, for error checking */
- struct list_head *page_lru; /* page in list */
- size_t room; /* room remaining to reset to */
-};
-
struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags);
extern void ceph_pagelist_release(struct ceph_pagelist *pl);
@@ -33,12 +27,6 @@ extern int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space);
extern int ceph_pagelist_free_reserve(struct ceph_pagelist *pl);
-extern void ceph_pagelist_set_cursor(struct ceph_pagelist *pl,
- struct ceph_pagelist_cursor *c);
-
-extern int ceph_pagelist_truncate(struct ceph_pagelist *pl,
- struct ceph_pagelist_cursor *c);
-
static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v)
{
__le64 ev = cpu_to_le64(v);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 43a7a1573b51..73c3efbec36c 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -524,6 +524,10 @@ struct ceph_osd_op {
__le64 cookie;
} __attribute__ ((packed)) notify;
struct {
+ __le64 unused;
+ __le64 ver;
+ } __attribute__ ((packed)) assert_ver;
+ struct {
__le64 offset, length;
__le64 src_offset;
} __attribute__ ((packed)) clonerange;
generated by cgit (git 2.34.1) at 2025-12-25 03:42:30 +0000