NEX-9200 Improve the scalability of attribute locking in zfs_zget
Reviewed by: Joyce McIntosh <joyce.mcintosh@nexenta.com>
Reviewed by: Sanjay Nadkarni <sanjay.nadkarni@nexenta.com>
NEX-9436 Rate limiting controls (was QoS) per ZFS dataset, updates from demo
Reviewed by: Gordon Ross <gordon.ross@nexenta.com>
Reviewed by: Rob Gittins <rob.gittins@nexenta.com>
NEX-8972 Async-delete side-effect that may cause unmount EBUSY
Reviewed by: Alek Pinchuk <alek@nexenta.com>
Reviewed by: Sanjay Nadkarni <sanjay.nadkarni@nexenta.com>
NEX-8852 Quality-of-Service (QoS) controls per NFS share
Reviewed by: Rob Gittins <rob.gittins@nexenta.com>
Reviewed by: Evan Layton <evan.layton@nexenta.com>
Reviewed by: Sanjay Nadkarni <sanjay.nadkarni@nexenta.com>
NEX-3762 Appliance crashes with a NULL pointer dereference during a zpool export when a zfs_vn_rele_taskq thread attempts to check a bogus rwlock from rw_write_held
Reviewed by: Josef 'Jeff' Sipek <josef.sipek@nexenta.com>
OS-80 support for vdev and CoS properties for the new I/O scheduler
OS-95 lint warning introduced by OS-61
Fixup merge results
re #13204 rb4280 zfs receive/rollback deadlock
re #6815 rb1758 need WORM in nza-kernel (4.0)

@@ -18,10 +18,11 @@
  *
  * CDDL HEADER END
  */
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
+ * Copyright 2016 Nexenta Systems, Inc.  All rights reserved.
  */
 
 #ifndef _SYS_FS_ZFS_VFSOPS_H
 #define _SYS_FS_ZFS_VFSOPS_H
 

@@ -39,10 +40,33 @@
 #endif
 
 typedef struct zfsvfs zfsvfs_t;
 struct znode;
 
+/*
+ * ZFS Quality of Service (QoS) I/O throttling state,
+ * per file system.  Limits the I/O rate in this FS.
+ * See "Token Bucket" on Wikipedia
+ */
+typedef struct zfs_rate_state {
+        uint64_t rate_cap;              /* zero means no cap */
+        int64_t rate_token_bucket;      /* bytes I/O allowed without waiting */
+        hrtime_t rate_last_update;
+        kmutex_t rate_lock;
+        kcondvar_t rate_wait_cv;
+        int rate_waiters;
+} zfs_rate_state_t;
+
+/*
+ * Status of the zfs_unlinked_drain thread.
+ */
+typedef enum drain_state {
+        ZFS_DRAIN_SHUTDOWN = 0,
+        ZFS_DRAIN_RUNNING,
+        ZFS_DRAIN_SHUTDOWN_REQ
+} drain_state_t;
+
 struct zfsvfs {
         vfs_t           *z_vfs;         /* generic fs struct */
         zfsvfs_t        *z_parent;      /* parent fs */
         objset_t        *z_os;          /* objset reference */
         uint64_t        z_root;         /* id of root znode */

@@ -66,10 +90,11 @@
         boolean_t       z_unmounted;    /* unmounted */
         rrmlock_t       z_teardown_lock;
         krwlock_t       z_teardown_inactive_lock;
         list_t          z_all_znodes;   /* all vnodes in the fs */
         kmutex_t        z_znodes_lock;  /* lock for z_all_znodes */
+        uint_t          z_znodes_freeing_cnt; /* number of znodes to be freed */
         vnode_t         *z_ctldir;      /* .zfs directory pointer */
         boolean_t       z_show_ctldir;  /* expose .zfs in the root dir */
         boolean_t       z_issnap;       /* true if this is a snapshot */
         boolean_t       z_vscan;        /* virus scan on/off */
         boolean_t       z_use_fuids;    /* version allows fuids */

@@ -80,12 +105,20 @@
         kmutex_t        z_lock;
         uint64_t        z_userquota_obj;
         uint64_t        z_groupquota_obj;
         uint64_t        z_replay_eof;   /* New end of file - replay only */
         sa_attr_type_t  *z_attr_table;  /* SA attr mapping->id */
-#define ZFS_OBJ_MTX_SZ  64
-        kmutex_t        z_hold_mtx[ZFS_OBJ_MTX_SZ];     /* znode hold locks */
+        boolean_t       z_isworm;       /* true if this is a WORM FS */
+        /* true if suspend-resume cycle is in progress */
+        boolean_t       z_busy;
+        int     z_hold_mtx_sz; /* the size of z_hold_mtx array */
+        kmutex_t        *z_hold_mtx;    /* znode hold locks */
+        /* for controlling async zfs_unlinked_drain */
+        kmutex_t        z_drain_lock;
+        kcondvar_t      z_drain_cv;
+        drain_state_t   z_drain_state;
+        zfs_rate_state_t z_rate;
 };
 
 /*
  * Normal filesystems (those not under .zfs/snapshot) have a total
  * file ID size limited to 12 bytes (including the length field) due to