*/
#define DRBD_SIGKILL SIGHUP
-/* All EEs on the free list should have ID_VACANT (== 0)
- * freshly allocated EEs get !ID_VACANT (== 1)
- * so if it says "cannot dereference null pointer at address 0x00000001",
- * it is most likely one of these :( */
-
#define ID_IN_SYNC (4711ULL)
#define ID_OUT_OF_SYNC (4712ULL)
-
#define ID_SYNCER (-1ULL)
-#define ID_VACANT 0
-#define is_syncer_block_id(id) ((id) == ID_SYNCER)
+
#define UUID_NEW_BM_OFFSET ((u64)0x0001000000000000ULL)
struct drbd_conf;
+struct drbd_tconn;
/* to shorten dev_warn(DEV, "msg"); and relatives statements */
#define D_ASSERT(exp) if (!(exp)) \
dev_err(DEV, "ASSERT( " #exp " ) in %s:%d\n", __FILE__, __LINE__)
-#define ERR_IF(exp) if (({ \
- int _b = (exp) != 0; \
- if (_b) dev_err(DEV, "ASSERT FAILED: %s: (%s) in %s:%d\n", \
- __func__, #exp, __FILE__, __LINE__); \
- _b; \
- }))
+/**
+ * expect - Make an assertion
+ *
+ * Unlike the assert macro, this macro returns a boolean result.
+ */
+#define expect(exp) ({ \
+ bool _bool = (exp); \
+ if (!_bool) \
+ dev_err(DEV, "ASSERTION %s FAILED in %s\n", \
+ #exp, __func__); \
+ _bool; \
+ })
/* Defines to control fault insertion */
enum {
/**********************************************************************/
enum drbd_thread_state {
- None,
- Running,
- Exiting,
- Restarting
+ NONE,
+ RUNNING,
+ EXITING,
+ RESTARTING
};
struct drbd_thread {
drbd_work_cb cb;
};
-struct drbd_tl_epoch;
+#include "drbd_interval.h"
+
struct drbd_request {
struct drbd_work w;
struct drbd_conf *mdev;
* see drbd_endio_pri(). */
struct bio *private_bio;
- struct hlist_node colision;
- sector_t sector;
- unsigned int size;
+ struct drbd_interval i;
unsigned int epoch; /* barrier_nr */
/* barrier_nr: used to check on "completion" whether this req was in
struct drbd_epoch_entry {
struct drbd_work w;
- struct hlist_node colision;
struct drbd_epoch *epoch; /* for writes */
struct drbd_conf *mdev;
struct page *pages;
atomic_t pending_bios;
- unsigned int size;
+ struct drbd_interval i;
/* see comments on ee flag bits below */
unsigned long flags;
- sector_t sector;
union {
u64 block_id;
struct digest_info *digest;
unsigned int size;
};
+struct drbd_tconn { /* is a resource from the config file */
+ char *name; /* Resource name */
+ struct list_head all_tconn; /* List of all drbd_tconn, prot by global_state_lock */
+ struct drbd_conf *volume0; /* TODO: Remove me again */
+
+ struct net_conf *net_conf; /* protected by get_net_conf() and put_net_conf() */
+ atomic_t net_cnt; /* Users of net_conf */
+ wait_queue_head_t net_cnt_wait;
+
+ struct drbd_socket data; /* data/barrier/cstate/parameter packets */
+ struct drbd_socket meta; /* ping/ack (metadata) packets */
+
+ struct drbd_thread receiver;
+ struct drbd_thread worker;
+ struct drbd_thread asender;
+};
+
struct drbd_conf {
+ struct drbd_tconn *tconn;
+ int vnr; /* volume number within the connection */
+
/* things that are stored as / read from meta data on disk */
unsigned long flags;
/* configured by drbdsetup */
- struct net_conf *net_conf; /* protected by get_net_conf() and put_net_conf() */
struct syncer_conf sync_conf;
struct drbd_backing_dev *ldev __protected_by(local);
struct block_device *this_bdev;
struct gendisk *vdisk;
- struct drbd_socket data; /* data/barrier/cstate/parameter packets */
- struct drbd_socket meta; /* ping/ack (metadata) packets */
int agreed_pro_version; /* actually used protocol version */
unsigned long last_received; /* in jiffies, either socket */
unsigned int ko_count;
union drbd_state state;
wait_queue_head_t misc_wait;
wait_queue_head_t state_wait; /* upon each state change. */
- wait_queue_head_t net_cnt_wait;
unsigned int send_cnt;
unsigned int recv_cnt;
unsigned int read_cnt;
atomic_t rs_pending_cnt; /* RS request/data packets on the wire */
atomic_t unacked_cnt; /* Need to send replys for */
atomic_t local_cnt; /* Waiting for local completion */
- atomic_t net_cnt; /* Users of net_conf */
+
spinlock_t req_lock;
struct drbd_tl_epoch *unused_spare_tle; /* for pre-allocation */
struct drbd_tl_epoch *newest_tle;
struct drbd_tl_epoch *oldest_tle;
struct list_head out_of_sequence_requests;
- struct hlist_head *tl_hash;
- unsigned int tl_hash_s;
+
+ /* Interval tree of pending local requests */
+ struct rb_root read_requests;
+ struct rb_root write_requests;
/* blocks to resync in this run [unit BM_BLOCK_SIZE] */
unsigned long rs_total;
struct crypto_hash *csums_tfm;
struct crypto_hash *verify_tfm;
- struct drbd_thread receiver;
- struct drbd_thread worker;
- struct drbd_thread asender;
struct drbd_bitmap *bitmap;
unsigned long bm_resync_fo; /* bit offset for drbd_bm_find_next */
struct list_head done_ee; /* send ack */
struct list_head read_ee; /* IO in progress (any read) */
struct list_head net_ee; /* zero-copy network send in progress */
- struct hlist_head *ee_hash; /* is proteced by req_lock! */
- unsigned int ee_hash_s;
+
+ /* Interval tree of pending remote write requests (struct drbd_epoch_entry) */
+ struct rb_root epoch_entries;
/* this one is protected by ee_lock, single thread */
struct drbd_epoch_entry *last_write_w_barrier;
int next_barrier_nr;
- struct hlist_head *app_reads_hash; /* is proteced by req_lock */
struct list_head resync_reads;
atomic_t pp_in_use; /* allocated from page pool */
atomic_t pp_in_use_by_net; /* sendpage()d, still referenced by tcp */
int rs_in_flight; /* resync sectors in flight (to proxy, in proxy and from proxy) */
int rs_planed; /* resync sectors already planned */
atomic_t ap_in_flight; /* App sectors in flight (waiting for ack) */
+ int peer_max_bio_size;
+ int local_max_bio_size;
};
static inline struct drbd_conf *minor_to_mdev(unsigned int minor)
*/
static inline int drbd_get_data_sock(struct drbd_conf *mdev)
{
- mutex_lock(&mdev->data.mutex);
+ mutex_lock(&mdev->tconn->data.mutex);
/* drbd_disconnect() could have called drbd_free_sock()
* while we were waiting in down()... */
- if (unlikely(mdev->data.socket == NULL)) {
- mutex_unlock(&mdev->data.mutex);
+ if (unlikely(mdev->tconn->data.socket == NULL)) {
+ mutex_unlock(&mdev->tconn->data.mutex);
return 0;
}
return 1;
static inline void drbd_put_data_sock(struct drbd_conf *mdev)
{
- mutex_unlock(&mdev->data.mutex);
+ mutex_unlock(&mdev->tconn->data.mutex);
}
/*
extern void tl_release(struct drbd_conf *mdev, unsigned int barrier_nr,
unsigned int set_size);
extern void tl_clear(struct drbd_conf *mdev);
-enum drbd_req_event;
-extern void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what);
extern void _tl_add_barrier(struct drbd_conf *, struct drbd_tl_epoch *);
extern void drbd_free_sock(struct drbd_conf *mdev);
extern int drbd_send(struct drbd_conf *mdev, struct socket *sock,
#endif
#endif
-/* Sector shift value for the "hash" functions of tl_hash and ee_hash tables.
- * With a value of 8 all IO in one 128K block make it to the same slot of the
- * hash table. */
#define HT_SHIFT 8
#define DRBD_MAX_BIO_SIZE (1U<<(9+HT_SHIFT))
+#define DRBD_MAX_BIO_SIZE_SAFE (1 << 12) /* Works always = 4k */
#define DRBD_MAX_SIZE_H80_PACKET (1 << 15) /* The old header only allows packets up to 32Kib data */
-/* Number of elements in the app_reads_hash */
-#define APP_R_HSIZE 15
-
extern int drbd_bm_init(struct drbd_conf *mdev);
extern int drbd_bm_resize(struct drbd_conf *mdev, sector_t sectors, int set_new_bits);
extern void drbd_bm_cleanup(struct drbd_conf *mdev);
extern struct drbd_conf *drbd_new_device(unsigned int minor);
extern void drbd_free_mdev(struct drbd_conf *mdev);
+struct drbd_tconn *drbd_new_tconn(char *name);
+extern void drbd_free_tconn(struct drbd_tconn *tconn);
+
extern int proc_details;
/* drbd_req */
extern char *ppsize(char *buf, unsigned long long size);
extern sector_t drbd_new_dev_size(struct drbd_conf *, struct drbd_backing_dev *, int);
enum determine_dev_size { dev_size_error = -1, unchanged = 0, shrunk = 1, grew = 2 };
-extern enum determine_dev_size drbd_determin_dev_size(struct drbd_conf *, enum dds_flags) __must_hold(local);
+extern enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *, enum dds_flags) __must_hold(local);
extern void resync_after_online_grow(struct drbd_conf *);
-extern void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int) __must_hold(local);
+extern void drbd_reconsider_max_bio_size(struct drbd_conf *mdev);
extern enum drbd_state_rv drbd_set_role(struct drbd_conf *mdev,
enum drbd_role new_role,
int force);
extern void drbd_set_recv_tcq(struct drbd_conf *mdev, int tcq_enabled);
extern void _drbd_clear_done_ee(struct drbd_conf *mdev, struct list_head *to_be_freed);
extern void drbd_flush_workqueue(struct drbd_conf *mdev);
-extern void drbd_free_tl_hash(struct drbd_conf *mdev);
/* yes, there is kernel_setsockopt, but only since 2.6.18. we don't need to
* mess with get_fs/set_fs, we know we are KERNEL_DS always. */
if (!forcedetach) {
if (__ratelimit(&drbd_ratelimit_state))
dev_err(DEV, "Local IO failed in %s.\n", where);
+ if (mdev->state.disk > D_INCONSISTENT)
+ _drbd_set_state(_NS(mdev, disk, D_INCONSISTENT), CS_HARD, NULL);
break;
}
/* NOTE fall through to detach case if forcedetach set */
static inline void wake_asender(struct drbd_conf *mdev)
{
if (test_bit(SIGNAL_ASENDER, &mdev->flags))
- force_sig(DRBD_SIG, mdev->asender.task);
+ force_sig(DRBD_SIG, mdev->tconn->asender.task);
}
static inline void request_ping(struct drbd_conf *mdev)
* or implicit barrier packets as necessary.
* increased:
* w_send_barrier
- * _req_mod(req, queue_for_net_write or queue_for_net_read);
+ * _req_mod(req, QUEUE_FOR_NET_WRITE or QUEUE_FOR_NET_READ);
* it is much easier and equally valid to count what we queue for the
* worker, even before it actually was queued or send.
* (drbd_make_request_common; recovery path on read io-error)
* decreased:
* got_BarrierAck (respective tl_clear, tl_clear_barrier)
- * _req_mod(req, data_received)
+ * _req_mod(req, DATA_RECEIVED)
* [from receive_DataReply]
- * _req_mod(req, write_acked_by_peer or recv_acked_by_peer or neg_acked)
+ * _req_mod(req, WRITE_ACKED_BY_PEER or RECV_ACKED_BY_PEER or NEG_ACKED)
* [from got_BlockAck (P_WRITE_ACK, P_RECV_ACK)]
* for some reason it is NOT decreased in got_NegAck,
* but in the resulting cleanup code from report_params.
* we should try to remember the reason for that...
- * _req_mod(req, send_failed or send_canceled)
- * _req_mod(req, connection_lost_while_pending)
+ * _req_mod(req, SEND_FAILED or SEND_CANCELED)
+ * _req_mod(req, CONNECTION_LOST_WHILE_PENDING)
* [from tl_clear_barrier]
*/
static inline void inc_ap_pending(struct drbd_conf *mdev)
ERR_IF_CNT_IS_NEGATIVE(unacked_cnt); } while (0)
-static inline void put_net_conf(struct drbd_conf *mdev)
+static inline void put_net_conf(struct drbd_tconn *tconn)
{
- if (atomic_dec_and_test(&mdev->net_cnt))
- wake_up(&mdev->net_cnt_wait);
+ if (atomic_dec_and_test(&tconn->net_cnt))
+ wake_up(&tconn->net_cnt_wait);
}
/**
- * get_net_conf() - Increase ref count on mdev->net_conf; Returns 0 if nothing there
+ * get_net_conf() - Increase ref count on mdev->tconn->net_conf; Returns 0 if nothing there
* @mdev: DRBD device.
*
- * You have to call put_net_conf() when finished working with mdev->net_conf.
+ * You have to call put_net_conf() when finished working with mdev->tconn->net_conf.
*/
-static inline int get_net_conf(struct drbd_conf *mdev)
+static inline int get_net_conf(struct drbd_tconn *tconn)
{
int have_net_conf;
- atomic_inc(&mdev->net_cnt);
- have_net_conf = mdev->state.conn >= C_UNCONNECTED;
+ atomic_inc(&tconn->net_cnt);
+ have_net_conf = tconn->volume0->state.conn >= C_UNCONNECTED;
if (!have_net_conf)
- put_net_conf(mdev);
+ put_net_conf(tconn);
return have_net_conf;
}
static inline void put_ldev(struct drbd_conf *mdev)
{
int i = atomic_dec_return(&mdev->local_cnt);
+
+ /* This may be called from some endio handler,
+ * so we must not sleep here. */
+
__release(local);
D_ASSERT(i >= 0);
if (i == 0) {
static inline int drbd_get_max_buffers(struct drbd_conf *mdev)
{
int mxb = 1000000; /* arbitrary limit on open requests */
- if (get_net_conf(mdev)) {
- mxb = mdev->net_conf->max_buffers;
- put_net_conf(mdev);
+ if (get_net_conf(mdev->tconn)) {
+ mxb = mdev->tconn->net_conf->max_buffers;
+ put_net_conf(mdev->tconn);
}
return mxb;
}
wake_up(&mdev->misc_wait);
if (ap_bio == 0 && test_bit(BITMAP_IO, &mdev->flags)) {
if (!test_and_set_bit(BITMAP_IO_QUEUED, &mdev->flags))
- drbd_queue_work(&mdev->data.work, &mdev->bm_io_work.w);
+ drbd_queue_work(&mdev->tconn->data.work, &mdev->bm_io_work.w);
}
}
static inline void drbd_update_congested(struct drbd_conf *mdev)
{
- struct sock *sk = mdev->data.socket->sk;
+ struct sock *sk = mdev->tconn->data.socket->sk;
if (sk->sk_wmem_queued > sk->sk_sndbuf * 4 / 5)
set_bit(NET_CONGESTED, &mdev->flags);
}
projects / mirror_ubuntu-bionic-kernel.git / blobdiff