blob: 32d98e63d25e2c7d243e2653844b37058f0429c5 [file] [log] [blame]
/* SPDX-License-Identifier: GPL-2.0-only */
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
** Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved.
#ifndef __DLM_INTERNAL_DOT_H__
#define __DLM_INTERNAL_DOT_H__
* This is the main header file to be included in each DLM source file.
#include <uapi/linux/dlm_device.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/ctype.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/list.h>
#include <linux/errno.h>
#include <linux/random.h>
#include <linux/delay.h>
#include <linux/socket.h>
#include <linux/kthread.h>
#include <linux/kobject.h>
#include <linux/kref.h>
#include <linux/kernel.h>
#include <linux/jhash.h>
#include <linux/miscdevice.h>
#include <linux/rhashtable.h>
#include <linux/mutex.h>
#include <linux/xarray.h>
#include <linux/ratelimit.h>
#include <linux/uaccess.h>
#include <linux/dlm.h>
#include "config.h"
struct dlm_ls;
struct dlm_lkb;
struct dlm_rsb;
struct dlm_member;
struct dlm_rsbtable;
struct dlm_recover;
struct dlm_header;
struct dlm_message;
struct dlm_rcom;
struct dlm_mhandle;
struct dlm_msg;
#define log_print(fmt, args...) \
printk(KERN_ERR "dlm: "fmt"\n" , ##args)
#define log_print_ratelimited(fmt, args...) \
printk_ratelimited(KERN_ERR "dlm: "fmt"\n", ##args)
#define log_error(ls, fmt, args...) \
printk(KERN_ERR "dlm: %s: " fmt "\n", (ls)->ls_name , ##args)
#define log_rinfo(ls, fmt, args...) \
do { \
if (dlm_config.ci_log_info) \
printk(KERN_INFO "dlm: %s: " fmt "\n", \
(ls)->ls_name, ##args); \
else if (dlm_config.ci_log_debug) \
printk(KERN_DEBUG "dlm: %s: " fmt "\n", \
(ls)->ls_name , ##args); \
} while (0)
#define log_debug(ls, fmt, args...) \
do { \
if (dlm_config.ci_log_debug) \
printk(KERN_DEBUG "dlm: %s: " fmt "\n", \
(ls)->ls_name , ##args); \
} while (0)
#define log_limit(ls, fmt, args...) \
do { \
if (dlm_config.ci_log_debug) \
printk_ratelimited(KERN_DEBUG "dlm: %s: " fmt "\n", \
(ls)->ls_name , ##args); \
} while (0)
#define DLM_ASSERT(x, do) \
{ \
if (!(x)) \
{ \
printk(KERN_ERR "\nDLM: Assertion failed on line %d of file %s\n" \
"DLM: assertion: \"%s\"\n" \
"DLM: time = %lu\n", \
__LINE__, __FILE__, #x, jiffies); \
{do} \
printk("\n"); \
panic("DLM: Record message above and reboot.\n"); \
} \
* Lockspace member (per node in a ls)
struct dlm_member {
struct list_head list;
int nodeid;
int weight;
int slot;
int slot_prev;
int comm_seq;
uint32_t generation;
* Save and manage recovery state for a lockspace.
struct dlm_recover {
struct list_head list;
struct dlm_config_node *nodes;
int nodes_count;
uint64_t seq;
* Pass input args to second stage locking function.
struct dlm_args {
uint32_t flags;
void (*astfn) (void *astparam);
void *astparam;
void (*bastfn) (void *astparam, int mode);
int mode;
struct dlm_lksb *lksb;
* Lock block
* A lock can be one of three types:
* local copy lock is mastered locally
* (lkb_nodeid is zero and DLM_LKF_MSTCPY is not set)
* process copy lock is mastered on a remote node
* (lkb_nodeid is non-zero and DLM_LKF_MSTCPY is not set)
* master copy master node's copy of a lock owned by remote node
* (lkb_nodeid is non-zero and DLM_LKF_MSTCPY is set)
* lkb_exflags: a copy of the most recent flags arg provided to dlm_lock or
* dlm_unlock. The dlm does not modify these or use any private flags in
* this field; it only contains DLM_LKF_ flags from dlm.h. These flags
* are sent as-is to the remote master when the lock is remote.
* lkb_flags: internal dlm flags (DLM_IFL_ prefix) from dlm_internal.h.
* Some internal flags are shared between the master and process nodes;
* these shared flags are kept in the lower two bytes. One of these
* flags set on the master copy will be propagated to the process copy
* and v.v. Other internal flags are private to the master or process
* node (e.g. DLM_IFL_MSTCPY). These are kept in the high two bytes.
* lkb_sbflags: status block flags. These flags are copied directly into
* the caller's lksb.sb_flags prior to the dlm_lock/dlm_unlock completion
* ast. All defined in dlm.h with DLM_SBF_ prefix.
* lkb_status: the lock status indicates which rsb queue the lock is
* on, grant, convert, or wait. DLM_LKSTS_ WAITING/GRANTED/CONVERT
* lkb_wait_type: the dlm message type (DLM_MSG_ prefix) for which a
* reply is needed. Only set when the lkb is on the lockspace waiters
* list awaiting a reply from a remote node.
* lkb_nodeid: when the lkb is a local copy, nodeid is 0; when the lkb
* is a master copy, nodeid specifies the remote lock holder, when the
* lkb is a process copy, the nodeid specifies the lock master.
/* lkb_status */
/* lkb_iflags */
#define DLM_IFL_DEAD_BIT 18
/* lkb_dflags */
#define DLM_DFL_USER_BIT 0
#define DLM_CB_CAST 0x00000001
#define DLM_CB_BAST 0x00000002
/* much of this is just saving user space pointers associated with the
* lock that we pass back to the user lib with an ast
struct dlm_user_args {
struct dlm_user_proc *proc; /* each process that opens the lockspace
* device has private data
* (dlm_user_proc) on the struct file,
* the process's locks point back to it
struct dlm_lksb lksb;
struct dlm_lksb __user *user_lksb;
void __user *castparam;
void __user *castaddr;
void __user *bastparam;
void __user *bastaddr;
uint64_t xid;
struct dlm_callback {
uint32_t flags; /* DLM_CBF_ */
int sb_status; /* copy to lksb status */
uint8_t sb_flags; /* copy to lksb flags */
int8_t mode; /* rq mode of bast, gr mode of cast */
bool copy_lvb;
struct dlm_lksb *lkb_lksb;
unsigned char lvbptr[DLM_USER_LVB_LEN];
union {
void *astparam; /* caller's ast arg */
struct dlm_user_args ua;
struct work_struct work;
void (*bastfn)(void *astparam, int mode);
void (*astfn)(void *astparam);
char res_name[DLM_RESNAME_MAXLEN];
size_t res_length;
uint32_t ls_id;
uint32_t lkb_id;
struct list_head list;
struct dlm_lkb {
struct dlm_rsb *lkb_resource; /* the rsb */
struct kref lkb_ref;
int lkb_nodeid; /* copied from rsb */
int lkb_ownpid; /* pid of lock owner */
uint32_t lkb_id; /* our lock ID */
uint32_t lkb_remid; /* lock ID on remote partner */
uint32_t lkb_exflags; /* external flags from caller */
unsigned long lkb_sbflags; /* lksb flags */
unsigned long lkb_dflags; /* distributed flags */
unsigned long lkb_iflags; /* internal flags */
uint32_t lkb_lvbseq; /* lvb sequence number */
int8_t lkb_status; /* granted, waiting, convert */
int8_t lkb_rqmode; /* requested lock mode */
int8_t lkb_grmode; /* granted lock mode */
int8_t lkb_highbast; /* highest mode bast sent for */
int8_t lkb_wait_type; /* type of reply waiting for */
int8_t lkb_wait_count;
int lkb_wait_nodeid; /* for debugging */
struct list_head lkb_statequeue; /* rsb g/c/w list */
struct list_head lkb_rsb_lookup; /* waiting for rsb lookup */
struct list_head lkb_wait_reply; /* waiting for remote reply */
struct list_head lkb_ownqueue; /* list of locks for a process */
ktime_t lkb_timestamp;
int8_t lkb_last_cast_cb_mode;
int8_t lkb_last_bast_cb_mode;
int8_t lkb_last_cb_mode;
uint8_t lkb_last_cb_flags;
ktime_t lkb_last_cast_time; /* for debugging */
ktime_t lkb_last_bast_time; /* for debugging */
uint64_t lkb_recover_seq; /* from ls_recover_seq */
char *lkb_lvbptr;
struct dlm_lksb *lkb_lksb; /* caller's status block */
void (*lkb_astfn) (void *astparam);
void (*lkb_bastfn) (void *astparam, int mode);
union {
void *lkb_astparam; /* caller's ast arg */
struct dlm_user_args *lkb_ua;
* res_master_nodeid is "normal": 0 is unset/invalid, non-zero is the real
* nodeid, even when nodeid is our_nodeid.
* res_nodeid is "odd": -1 is unset/invalid, zero means our_nodeid,
* greater than zero when another nodeid.
* (TODO: remove res_nodeid and only use res_master_nodeid)
struct dlm_rsb {
struct dlm_ls *res_ls; /* the lockspace */
struct kref res_ref;
spinlock_t res_lock;
unsigned long res_flags;
int res_length; /* length of rsb name */
int res_nodeid;
int res_master_nodeid;
int res_dir_nodeid;
unsigned long res_id; /* for ls_recover_xa */
uint32_t res_lvbseq;
uint32_t res_hash;
unsigned long res_toss_time;
uint32_t res_first_lkid;
struct list_head res_lookup; /* lkbs waiting on first */
struct rhash_head res_node; /* rsbtbl */
struct list_head res_grantqueue;
struct list_head res_convertqueue;
struct list_head res_waitqueue;
struct list_head res_slow_list; /* ls_slow_* */
struct list_head res_scan_list;
struct list_head res_root_list; /* used for recovery */
struct list_head res_masters_list; /* used for recovery */
struct list_head res_recover_list; /* used for recovery */
int res_recover_locks_count;
struct rcu_head rcu;
char *res_lvbptr;
char res_name[DLM_RESNAME_MAXLEN+1];
/* dlm_master_lookup() flags */
/* dlm_master_lookup() results */
#define DLM_LU_MATCH 1
#define DLM_LU_ADD 2
/* find_rsb() flags */
#define R_REQUEST 0x00000001
#define R_RECEIVE_REQUEST 0x00000002
#define R_RECEIVE_RECOVER 0x00000004
/* rsb_flags */
enum rsb_flags {
RSB_HASHED, /* set while rsb is on ls_rsbtbl */
static inline void rsb_set_flag(struct dlm_rsb *r, enum rsb_flags flag)
__set_bit(flag, &r->res_flags);
static inline void rsb_clear_flag(struct dlm_rsb *r, enum rsb_flags flag)
__clear_bit(flag, &r->res_flags);
static inline int rsb_flag(struct dlm_rsb *r, enum rsb_flags flag)
return test_bit(flag, &r->res_flags);
/* dlm_header is first element of all structs sent between nodes */
#define DLM_HEADER_MAJOR 0x00030000
#define DLM_HEADER_MINOR 0x00000002
#define DLM_VERSION_3_1 0x00030001
#define DLM_VERSION_3_2 0x00030002
#define DLM_HEADER_SLOTS 0x00000001
#define DLM_MSG 1
#define DLM_RCOM 2
#define DLM_OPTS 3
#define DLM_ACK 4
#define DLM_FIN 5
struct dlm_header {
__le32 h_version;
union {
/* for DLM_MSG and DLM_RCOM */
__le32 h_lockspace;
/* for DLM_ACK and DLM_OPTS */
__le32 h_seq;
} u;
__le32 h_nodeid; /* nodeid of sender */
__le16 h_length;
uint8_t h_cmd; /* DLM_MSG, DLM_RCOM */
uint8_t h_pad;
#define DLM_MSG_UNLOCK 3
#define DLM_MSG_CANCEL 4
#define DLM_MSG_GRANT 9
#define DLM_MSG_BAST 10
#define DLM_MSG_LOOKUP 11
#define DLM_MSG_REMOVE 12
#define DLM_MSG_PURGE 14
struct dlm_message {
struct dlm_header m_header;
__le32 m_type; /* DLM_MSG_ */
__le32 m_nodeid;
__le32 m_pid;
__le32 m_lkid; /* lkid on sender */
__le32 m_remid; /* lkid on receiver */
__le32 m_parent_lkid;
__le32 m_parent_remid;
__le32 m_exflags;
__le32 m_sbflags;
__le32 m_flags;
__le32 m_lvbseq;
__le32 m_hash;
__le32 m_status;
__le32 m_grmode;
__le32 m_rqmode;
__le32 m_bastmode;
__le32 m_asts;
__le32 m_result; /* 0 or -EXXX */
char m_extra[]; /* name or lvb */
#define DLM_RS_NODES 0x00000001
#define DLM_RS_NODES_ALL 0x00000002
#define DLM_RS_DIR 0x00000004
#define DLM_RS_DIR_ALL 0x00000008
#define DLM_RS_LOCKS 0x00000010
#define DLM_RS_LOCKS_ALL 0x00000020
#define DLM_RS_DONE 0x00000040
#define DLM_RS_DONE_ALL 0x00000080
#define DLM_RCOM_NAMES 2
#define DLM_RCOM_LOCK 4
struct dlm_rcom {
struct dlm_header rc_header;
__le32 rc_type; /* DLM_RCOM_ */
__le32 rc_result; /* multi-purpose */
__le64 rc_id; /* match reply with request */
__le64 rc_seq; /* sender's ls_recover_seq */
__le64 rc_seq_reply; /* remote ls_recover_seq */
char rc_buf[];
struct dlm_opt_header {
__le16 t_type;
__le16 t_length;
__le32 t_pad;
/* need to be 8 byte aligned */
char t_value[];
/* encapsulation header */
struct dlm_opts {
struct dlm_header o_header;
uint8_t o_nextcmd;
uint8_t o_pad;
__le16 o_optlen;
__le32 o_pad2;
char o_opts[];
union dlm_packet {
struct dlm_header header; /* common to other two */
struct dlm_message message;
struct dlm_rcom rcom;
struct dlm_opts opts;
#define DLM_RSF_NEED_SLOTS 0x00000001
/* RCOM_STATUS data */
struct rcom_status {
__le32 rs_flags;
__le32 rs_unused1;
__le64 rs_unused2;
struct rcom_config {
__le32 rf_lvblen;
__le32 rf_lsflags;
/* DLM_HEADER_SLOTS adds: */
__le32 rf_flags;
__le16 rf_our_slot;
__le16 rf_num_slots;
__le32 rf_generation;
__le32 rf_unused1;
__le64 rf_unused2;
struct rcom_slot {
__le32 ro_nodeid;
__le16 ro_slot;
__le16 ro_unused1;
__le64 ro_unused2;
struct rcom_lock {
__le32 rl_ownpid;
__le32 rl_lkid;
__le32 rl_remid;
__le32 rl_parent_lkid;
__le32 rl_parent_remid;
__le32 rl_exflags;
__le32 rl_flags;
__le32 rl_lvbseq;
__le32 rl_result;
int8_t rl_rqmode;
int8_t rl_grmode;
int8_t rl_status;
int8_t rl_asts;
__le16 rl_wait_type;
__le16 rl_namelen;
char rl_name[DLM_RESNAME_MAXLEN];
char rl_lvb[];
struct dlm_ls {
struct list_head ls_list; /* list of lockspaces */
uint32_t ls_global_id; /* global unique lockspace ID */
uint32_t ls_generation;
uint32_t ls_exflags;
int ls_lvblen;
atomic_t ls_count; /* refcount of processes in
the dlm using this ls */
wait_queue_head_t ls_count_wait;
int ls_create_count; /* create/release refcount */
unsigned long ls_flags; /* LSFL_ */
struct kobject ls_kobj;
struct xarray ls_lkbxa;
rwlock_t ls_lkbxa_lock;
/* an rsb is on rsbtl for primary locking functions,
and on a slow list for recovery/dump iteration */
struct rhashtable ls_rsbtbl;
rwlock_t ls_rsbtbl_lock; /* for ls_rsbtbl and ls_slow */
struct list_head ls_slow_inactive; /* to iterate rsbtbl */
struct list_head ls_slow_active; /* to iterate rsbtbl */
struct timer_list ls_scan_timer; /* based on first scan_list rsb toss_time */
struct list_head ls_scan_list; /* rsbs ordered by res_toss_time */
spinlock_t ls_scan_lock;
spinlock_t ls_waiters_lock;
struct list_head ls_waiters; /* lkbs needing a reply */
spinlock_t ls_orphans_lock;
struct list_head ls_orphans;
struct list_head ls_nodes; /* current nodes in ls */
struct list_head ls_nodes_gone; /* dead node list, recovery */
int ls_num_nodes; /* number of nodes in ls */
int ls_low_nodeid;
int ls_total_weight;
int *ls_node_array;
int ls_slot;
int ls_num_slots;
int ls_slots_size;
struct dlm_slot *ls_slots;
struct dlm_rsb ls_local_rsb; /* for returning errors */
struct dlm_lkb ls_local_lkb; /* for returning errors */
struct dlm_message ls_local_ms; /* for faking a reply */
struct dentry *ls_debug_rsb_dentry; /* debugfs */
struct dentry *ls_debug_waiters_dentry; /* debugfs */
struct dentry *ls_debug_locks_dentry; /* debugfs */
struct dentry *ls_debug_all_dentry; /* debugfs */
struct dentry *ls_debug_toss_dentry; /* debugfs */
struct dentry *ls_debug_queued_asts_dentry; /* debugfs */
wait_queue_head_t ls_uevent_wait; /* user part of join/leave */
int ls_uevent_result;
struct completion ls_recovery_done;
int ls_recovery_result;
struct miscdevice ls_device;
struct workqueue_struct *ls_callback_wq;
/* recovery related */
spinlock_t ls_cb_lock;
struct list_head ls_cb_delay; /* save for queue_work later */
struct task_struct *ls_recoverd_task;
struct mutex ls_recoverd_active;
spinlock_t ls_recover_lock;
unsigned long ls_recover_begin; /* jiffies timestamp */
uint32_t ls_recover_status; /* DLM_RS_ */
uint64_t ls_recover_seq;
struct dlm_recover *ls_recover_args;
struct rw_semaphore ls_in_recovery; /* block local requests */
rwlock_t ls_recv_active; /* block dlm_recv */
struct list_head ls_requestqueue;/* queue remote requests */
rwlock_t ls_requestqueue_lock;
struct dlm_rcom *ls_recover_buf;
int ls_recover_nodeid; /* for debugging */
unsigned int ls_recover_locks_in; /* for log info */
uint64_t ls_rcom_seq;
spinlock_t ls_rcom_spin;
struct list_head ls_recover_list;
spinlock_t ls_recover_list_lock;
int ls_recover_list_count;
struct xarray ls_recover_xa;
spinlock_t ls_recover_xa_lock;
wait_queue_head_t ls_wait_general;
wait_queue_head_t ls_recover_lock_wait;
spinlock_t ls_clear_proc_locks;
struct list_head ls_masters_list; /* root resources */
rwlock_t ls_masters_lock; /* protect root_list */
struct list_head ls_dir_dump_list; /* root resources */
rwlock_t ls_dir_dump_lock; /* protect root_list */
const struct dlm_lockspace_ops *ls_ops;
void *ls_ops_arg;
int ls_namelen;
char ls_name[DLM_LOCKSPACE_LEN + 1];
* LSFL_RECOVER_STOP - dlm_ls_stop() sets this to tell dlm recovery routines
* that they should abort what they're doing so new recovery can be started.
* LSFL_RECOVER_DOWN - dlm_ls_stop() sets this to tell dlm_recoverd that it
* should do down_write() on the in_recovery rw_semaphore. (doing down_write
* within dlm_ls_stop causes complaints about the lock acquired/released
* in different contexts.)
* LSFL_RECOVER_LOCK - dlm_recoverd holds the in_recovery rw_semaphore.
* It sets this after it is done with down_write() on the in_recovery
* rw_semaphore and clears it after it has released the rw_semaphore.
* LSFL_RECOVER_WORK - dlm_ls_start() sets this to tell dlm_recoverd that it
* should begin recovery of the lockspace.
* LSFL_RUNNING - set when normal locking activity is enabled.
* dlm_ls_stop() clears this to tell dlm locking routines that they should
* quit what they are doing so recovery can run. dlm_recoverd sets
* this after recovery is finished.
#define LSFL_RUNNING 4
#define LSFL_RCOM_WAIT 6
#define LSFL_CB_DELAY 9
#define LSFL_NODIR 10
#define LSFL_FS 12
#define LSFL_SOFTIRQ 13
/* locks list is kept so we can remove all a process's locks when it
exits (or orphan those that are persistent) */
struct dlm_user_proc {
dlm_lockspace_t *lockspace;
unsigned long flags; /* DLM_PROC_FLAGS */
struct list_head asts;
spinlock_t asts_spin;
struct list_head locks;
spinlock_t locks_spin;
struct list_head unlocking;
wait_queue_head_t wait;
static inline int dlm_locking_stopped(struct dlm_ls *ls)
return !test_bit(LSFL_RUNNING, &ls->ls_flags);
static inline int dlm_recovery_stopped(struct dlm_ls *ls)
return test_bit(LSFL_RECOVER_STOP, &ls->ls_flags);
static inline int dlm_no_directory(struct dlm_ls *ls)
return test_bit(LSFL_NODIR, &ls->ls_flags);
/* takes a snapshot from dlm atomic flags */
static inline uint32_t dlm_flags_val(const unsigned long *addr,
uint32_t min, uint32_t max)
uint32_t bit = min, val = 0;
for_each_set_bit_from(bit, addr, max + 1) {
val |= BIT(bit);
return val;
static inline uint32_t dlm_iflags_val(const struct dlm_lkb *lkb)
return dlm_flags_val(&lkb->lkb_iflags, __DLM_IFL_MIN_BIT,
static inline uint32_t dlm_dflags_val(const struct dlm_lkb *lkb)
return dlm_flags_val(&lkb->lkb_dflags, __DLM_DFL_MIN_BIT,
/* coming from UAPI header
* Move this to UAPI header and let other values point to them and use BIT()
static inline uint32_t dlm_sbflags_val(const struct dlm_lkb *lkb)
/* be sure the next person updates this */
return dlm_flags_val(&lkb->lkb_sbflags, __DLM_SBF_MIN_BIT,
static inline void dlm_set_flags_val(unsigned long *addr, uint32_t val,
uint32_t min, uint32_t max)
uint32_t bit;
for (bit = min; bit < (max + 1); bit++) {
if (val & BIT(bit))
set_bit(bit, addr);
clear_bit(bit, addr);
static inline void dlm_set_dflags_val(struct dlm_lkb *lkb, uint32_t val)
dlm_set_flags_val(&lkb->lkb_dflags, val, __DLM_DFL_MIN_BIT,
static inline void dlm_set_sbflags_val(struct dlm_lkb *lkb, uint32_t val)
dlm_set_flags_val(&lkb->lkb_sbflags, val, __DLM_SBF_MIN_BIT,
int dlm_plock_init(void);
void dlm_plock_exit(void);
void dlm_register_debugfs(void);
void dlm_unregister_debugfs(void);
void dlm_create_debug_file(struct dlm_ls *ls);
void dlm_delete_debug_file(struct dlm_ls *ls);
void *dlm_create_debug_comms_file(int nodeid, void *data);
void dlm_delete_debug_comms_file(void *ctx);
static inline void dlm_register_debugfs(void) { }
static inline void dlm_unregister_debugfs(void) { }
static inline void dlm_create_debug_file(struct dlm_ls *ls) { }
static inline void dlm_delete_debug_file(struct dlm_ls *ls) { }
static inline void *dlm_create_debug_comms_file(int nodeid, void *data) { return NULL; }
static inline void dlm_delete_debug_comms_file(void *ctx) { }
#endif /* __DLM_INTERNAL_DOT_H__ */