/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _FS_CEPH_SUPER_H
#define _FS_CEPH_SUPER_H
#include <linux/ceph/ceph_debug.h>
#include <asm/unaligned.h>
#include <linux/backing-dev.h>
#include <linux/completion.h>
#include <linux/exportfs.h>
#include <linux/fs.h>
#include <linux/mempool.h>
#include <linux/pagemap.h>
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/slab.h>
#include <linux/posix_acl.h>
#include <linux/refcount.h>
#include <linux/ceph/libceph.h>
#ifdef CONFIG_CEPH_FSCACHE
#include <linux/fscache.h>
#endif
/* f_type in struct statfs */
#define CEPH_SUPER_MAGIC 0x00c36400
/* large granularity for statfs utilization stats to facilitate
* large volume sizes on 32-bit machines. */
#define CEPH_BLOCK_SHIFT 22 /* 4 MB */
#define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT)
#define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */
#define CEPH_MOUNT_OPT_RBYTES (1<<5) /* dir st_bytes = rbytes */
#define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */
#define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */
#define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */
#define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */
#define CEPH_MOUNT_OPT_NOPOOLPERM (1<<11) /* no pool permission check */
#define CEPH_MOUNT_OPT_MOUNTWAIT (1<<12) /* mount waits if no mds is up */
#define CEPH_MOUNT_OPT_NOQUOTADF (1<<13) /* no root dir quota in statfs */
#define CEPH_MOUNT_OPT_DEFAULT CEPH_MOUNT_OPT_DCACHE
#define ceph_set_mount_opt(fsc, opt) \
(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt;
#define ceph_test_mount_opt(fsc, opt) \
(!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))
/* max size of osd read request, limited by libceph */
#define CEPH_MAX_READ_SIZE CEPH_MSG_MAX_DATA_LEN
/* osd has a configurable limitaion of max write size.
* CEPH_MSG_MAX_DATA_LEN should be small enough. */
#define CEPH_MAX_WRITE_SIZE CEPH_MSG_MAX_DATA_LEN
#define CEPH_RASIZE_DEFAULT (8192*1024) /* max readahead */
#define CEPH_MAX_READDIR_DEFAULT 1024
#define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024)
#define CEPH_SNAPDIRNAME_DEFAULT ".snap"
/*
* Delay telling the MDS we no longer want caps, in case we reopen
* the file. Delay a minimum amount of time, even if we send a cap
* message for some other reason. Otherwise, take the oppotunity to
* update the mds to avoid sending another message later.
*/
#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */
#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */
struct ceph_mount_options {
int flags;
int sb_flags;
int wsize; /* max write size */
int rsize; /* max read size */
int rasize; /* max readahead */
int congestion_kb; /* max writeback in flight */
int caps_wanted_delay_min, caps_wanted_delay_max;
int max_readdir; /* max readdir result (entires) */
int max_readdir_bytes; /* max readdir result (bytes) */
/*
* everything above this point can be memcmp'd; everything below
* is handled in compare_mount_options()
*/
char *snapdir_name; /* default ".snap" */
char *mds_namespace; /* default NULL */
char *server_path; /* default "/" */
char *fscache_uniq; /* default NULL */
};
struct ceph_fs_client {
struct super_block *sb;
struct ceph_mount_options *mount_options;
struct ceph_client *client;
unsigned long mount_state;
int min_caps; /* min caps i added */
struct ceph_mds_client *mdsc;
/* writeback */
mempool_t *wb_pagevec_pool;
struct workqueue_struct *wb_wq;
struct workqueue_struct *pg_inv_wq;
struct workqueue_struct *trunc_wq;
atomic_long_t writeback_count;
#ifdef CONFIG_DEBUG_FS
struct dentry *debugfs_dentry_lru, *debugfs_caps;
struct dentry *debugfs_congestion_kb;
struct dentry *debugfs_bdi;
struct dentry *debugfs_mdsc, *debugfs_mdsmap;
struct dentry *debugfs_mds_sessions;
#endif
#ifdef CONFIG_CEPH_FSCACHE
struct fscache_cookie *fscache;
#endif
};
/*
* File i/o capability. This tracks shared state with the metadata
* server that allows us to cache or writeback attributes or to read
* and write data. For any given inode, we should have one or more
* capabilities, one issued by each metadata server, and our
* cumulative access is the OR of all issued capabilities.
*
* Each cap is referenced by the inode's i_caps rbtree and by per-mds
* session capability lists.
*/
struct ceph_cap {
struct ceph_inode_info *ci;
struct rb_node ci_node; /* per-ci cap tree */
struct ceph_mds_session *session;
struct list_head session_caps; /* per-session caplist */
u64 cap_id; /* unique cap id (mds provided) */
union {
/* in-use caps */
struct {
int issued; /* latest, from the mds */
int implemented; /* implemented superset of
issued (for revocation) */
int mds, mds_wanted;
};
/* caps to release */
struct {
u64 cap_ino;
int queue_release;
};
};
u32 seq, issue_seq, mseq;
u32 cap_gen; /* active/stale cycle */
unsigned long last_used;
struct list_head caps_item;
};
#define CHECK_CAPS_NODELAY 1 /* do not delay any further */
#define CHECK_CAPS_AUTHONLY 2 /* only check auth cap */
#define CHECK_CAPS_FLUSH 4 /* flush any dirty caps */
struct ceph_cap_flush {
u64 tid;
int caps; /* 0 means capsnap */
bool wake; /* wake up flush waiters when finish ? */
struct list_head g_list; // global
struct list_head i_list; // per inode
};
/*
* Snapped cap state that is pending flush to mds. When a snapshot occurs,
* we first complete any in-process sync writes and writeback any dirty
* data before flushing the snapped state (tracked here) back to the MDS.
*/
struct ceph_cap_snap {
refcount_t