nfsd: open file caching

index 95361d2b8a08..899c19687cfa 100644
@@ -246,20 +246,24 @@ static void ____fput(struct callback_head *work)
 
 static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
 
-/*
- * If kernel thread really needs to have the final fput() it has done
- * to complete, call this.  The only user right now is the boot - we
- * *do* need to make sure our writes to binaries on initramfs has
- * not left us with opened struct file waiting for __fput() - execve()
- * won't work without that.  Please, don't add more callers without
- * very good reasons; in particular, never call that with locks
- * held and never call that from a thread that might need to do
- * some work on any kind of umount.
+/**
+ * flush_delayed_fput - ensure that all delayed_fput work is complete
+ *
+ * If kernel thread or task that has used fput_queue really needs to have the
+ * final fput() it has done to complete, call this. One of the main users is
+ * the boot - we *do* need to make sure our writes to binaries on initramfs has
+ * not left us with opened struct file waiting for __fput() - execve() won't
+ * work without that.
+ *
+ * Please, don't add more callers without very good reasons; in particular,
+ * never call that with locks held and never from a thread that might need to
+ * do some work on any kind of umount.
  */
 void flush_delayed_fput(void)
 {
 	flush_delayed_work(&delayed_fput_work);
 }
+EXPORT_SYMBOL(flush_delayed_fput);
 
 /**
  * fput - put a struct file reference

index d16b62cb2854..295d08800126 100644
@@ -81,6 +81,7 @@ void fsnotify_put_group(struct fsnotify_group *group)
 	if (atomic_dec_and_test(&group->refcnt))
 		fsnotify_final_destroy_group(group);
 }
+EXPORT_SYMBOL_GPL(fsnotify_put_group);
 
 /*
  * Create a new fsnotify_group and hold a reference for the group returned.

@@ -109,6 +110,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
 
 	return group;
 }
+EXPORT_SYMBOL_GPL(fsnotify_alloc_group);
 
 int fsnotify_fasync(int fd, struct file *file, int on)
 {

index fc0df4442f7b..1dda1734ac84 100644
@@ -208,6 +208,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 	mutex_unlock(&group->mark_mutex);
 	fsnotify_free_mark(mark);
 }
+EXPORT_SYMBOL_GPL(fsnotify_destroy_mark);
 
 void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock)
 {

@@ -402,6 +403,7 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
 	mutex_unlock(&group->mark_mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(fsnotify_add_mark);
 
 /*
  * Given a list of marks, find the mark associated with given group. If found

@@ -492,6 +494,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	atomic_set(&mark->refcnt, 1);
 	mark->free_mark = free_mark;
 }
+EXPORT_SYMBOL_GPL(fsnotify_init_mark);
 
 static int fsnotify_mark_destroy(void *ignored)
 {

index 82f89070594c..90967466a1e5 100644
@@ -1,5 +1,3 @@
 
-#include "state.h"
-
 #define CREATE_TRACE_POINTS
 #include "trace.h"

index c668520c344b..0befe762762b 100644
@@ -9,6 +9,8 @@
 
 #include <linux/tracepoint.h>
 
+#include "state.h"
+
 DECLARE_EVENT_CLASS(nfsd_stateid_class,
 	TP_PROTO(stateid_t *stp),
 	TP_ARGS(stp),

index 932b58a5774f..9944152df415 100644
@@ -572,7 +572,7 @@ out:
 	return status;
 open_file:
 	/* FIXME: should we abort opening if the link count goes to 0? */
-	status = nfsd_open(rqstp, fhp, S_IFREG, may_flags, &nf->nf_file);
+	status = nfsd_open_verified(rqstp, fhp, S_IFREG, may_flags, &nf->nf_file);
 	clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags);
 	smp_mb__after_atomic();
 	wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING);

81 lines not on this page · raw message

index a877be59d5dd..b3beb896b08d 100644
@@ -72,6 +72,8 @@ __be32		nfsd_commit(struct svc_rqst *, struct svc_fh *,
 int		nfsd_open_break_lease(struct inode *, int);
 __be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
 				int, struct file **);
+__be32		nfsd_open_verified(struct svc_rqst *, struct svc_fh *, umode_t,
+				int, struct file **);
 struct raparms;
 __be32		nfsd_splice_read(struct svc_rqst *,
 				struct file *, loff_t, unsigned long *);

index 7b755b7f785c..4e46ac511479 100644
@@ -192,7 +192,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
 
 	fh_copy(&resp->fh, &argp->fh);
 	resp->committed = argp->stable;
-	nfserr = nfsd_write(rqstp, &resp->fh, NULL,
+	nfserr = nfsd_write(rqstp, &resp->fh,
 				   argp->offset,
 				   rqstp->rq_vec, argp->vlen,
 				   &cnt,

index 4cd78ef4c95c..9893095cbee1 100644
@@ -213,7 +213,7 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
 		SVCFH_fmt(&argp->fh),
 		argp->len, argp->offset);
 
-	nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh), NULL,
+	nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh),
 				   argp->offset,
 				   rqstp->rq_vec, argp->vlen,
 			           &cnt,

index cf4a2018d57a..cb1ab146246b 100644
@@ -42,6 +42,7 @@
 
 #include "nfsd.h"
 #include "vfs.h"
+#include "filecache.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_FILEOP
 

@@ -1030,30 +1031,18 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
  * N.B. After this call fhp needs an fh_put
  */
 __be32
-nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
-		loff_t offset, struct kvec *vec, int vlen, unsigned long *cnt,
-		int *stablep)
+nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
+	   struct kvec *vec, int vlen, unsigned long *cnt, int *stablep)
 {
-	__be32			err = 0;
-
-	if (file) {
-		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
-				NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE);
-		if (err)
-			goto out;
-		err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt,
-				stablep);
-	} else {
-		err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
-		if (err)
-			goto out;
-
-		if (cnt)
-			err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen,
-					     cnt, stablep);
-		fput(file);
+	__be32			err;
+	struct nfsd_file	*nf;
+
+	err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_WRITE, &nf);
+	if (err == nfs_ok) {
+		err = nfsd_vfs_write(rqstp, fhp, nf->nf_file, offset, vec,
+					vlen, cnt, stablep);
+		nfsd_file_put(nf);
 	}
-out:
 	return err;
 }
 

index b3beb896b08d..80692e06302d 100644
@@ -81,7 +81,7 @@ __be32		nfsd_readv(struct file *, loff_t, struct kvec *, int,
 				unsigned long *);
 __be32 		nfsd_read(struct svc_rqst *, struct svc_fh *,
 				loff_t, struct kvec *, int, unsigned long *);
-__be32 		nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *,
+__be32 		nfsd_write(struct svc_rqst *, struct svc_fh *,
 				loff_t, struct kvec *,int, unsigned long *, int *);
 __be32		nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				struct file *file, loff_t offset,

index cb1ab146246b..050db266ef80 100644
@@ -1008,20 +1008,15 @@ out_nfserr:
 __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
 {
-	struct file *file;
-	struct raparms	*ra;
-	__be32 err;
-
-	err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
-	if (err)
-		return err;
-
-	ra = nfsd_init_raparms(file);
-	err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count);
-	if (ra)
-		nfsd_put_raparams(file, ra);
-	fput(file);
+	__be32			err;
+	struct nfsd_file	*nf;
 
+	err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf);
+	if (err == nfs_ok) {
+		err = nfsd_vfs_read(rqstp, nf->nf_file, offset, vec, vlen,
+					count);
+		nfsd_file_put(nf);
+	}
 	return err;
 }
 

index 9ffef06b30d5..1ee1881cf8d0 100644
@@ -144,8 +144,8 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid)
 	list_del_init(&ls->ls_perfile);
 	spin_unlock(&fp->fi_lock);
 
-	vfs_setlease(ls->ls_file, F_UNLCK, NULL, (void **)&ls);
-	fput(ls->ls_file);
+	vfs_setlease(ls->ls_file->nf_file, F_UNLCK, NULL, (void **)&ls);
+	nfsd_file_put(ls->ls_file);
 
 	if (ls->ls_recalled)
 		atomic_dec(&ls->ls_stid.sc_file->fi_lo_recalls);

@@ -169,7 +169,7 @@ nfsd4_layout_setlease(struct nfs4_layout_stateid *ls)
 	fl->fl_end = OFFSET_MAX;
 	fl->fl_owner = ls;
 	fl->fl_pid = current->tgid;
-	fl->fl_file = ls->ls_file;
+	fl->fl_file = ls->ls_file->nf_file;
 
 	status = vfs_setlease(fl->fl_file, fl->fl_type, &fl, NULL);
 	if (status) {

@@ -207,13 +207,13 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 			NFSPROC4_CLNT_CB_LAYOUT);
 
 	if (parent->sc_type == NFS4_DELEG_STID)
-		ls->ls_file = get_file(fp->fi_deleg_file);
+		ls->ls_file = nfsd_file_get(fp->fi_deleg_file);
 	else
 		ls->ls_file = find_any_file(fp);
 	BUG_ON(!ls->ls_file);
 
 	if (nfsd4_layout_setlease(ls)) {
-		fput(ls->ls_file);
+		nfsd_file_put(ls->ls_file);
 		put_nfs4_file(fp);
 		kmem_cache_free(nfs4_layout_stateid_cache, ls);
 		return NULL;

@@ -598,7 +598,7 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 
 	argv[0] = "/sbin/nfsd-recall-failed";
 	argv[1] = addr_str;
-	argv[2] = ls->ls_file->f_path.mnt->mnt_sb->s_id;
+	argv[2] = ls->ls_file->nf_file->f_path.mnt->mnt_sb->s_id;
 	argv[3] = NULL;
 
 	error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);

353 lines not on this page · raw message

index 473faa436e07..ee23de10663c 100644
@@ -501,7 +501,7 @@ struct nfs4_file {
 	 */
 	atomic_t		fi_access[2];
 	u32			fi_share_deny;
-	struct file		*fi_deleg_file;
+	struct nfsd_file	*fi_deleg_file;
 	int			fi_delegees;
 	struct knfsd_fh		fi_fhandle;
 	bool			fi_had_conflict;

@@ -550,7 +550,7 @@ struct nfs4_layout_stateid {
 	spinlock_t			ls_lock;
 	struct list_head		ls_layouts;
 	u32				ls_layout_type;
-	struct file			*ls_file;
+	struct nfsd_file		*ls_file;
 	struct nfsd4_callback		ls_recall;
 	stateid_t			ls_recall_sid;
 	bool				ls_recalled;

@@ -615,7 +615,7 @@ static inline void get_nfs4_file(struct nfs4_file *fi)
 {
 	atomic_inc(&fi->fi_ref);
 }
-struct file *find_any_file(struct nfs4_file *f);
+struct nfsd_file *find_any_file(struct nfs4_file *f);
 
 /* grace period management */
 void nfsd4_end_grace(struct nfsd_net *nn);

index a2d5794d713a..4fccd3035842 100644
@@ -1835,7 +1835,8 @@ setlease_notifier(long arg, struct file_lock *lease)
 int
 vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
 {
-	setlease_notifier(arg, *lease);
+	if (lease)
+		setlease_notifier(arg, *lease);
 	if (filp->f_op->setlease)
 		return filp->f_op->setlease(filp, arg, lease, priv);
 	else

index 2a6b9947aaa3..4534b1b34d2d 100644
@@ -96,6 +96,19 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item);
 bool list_lru_del(struct list_lru *lru, struct list_head *item);
 
 /**
+ * list_lru_rotate: rotate an element to the end of an lru list
+ * @list_lru: the lru pointer
+ * @item: the item to be rotated
+ *
+ * This function moves an entry to the end of an LRU list. Should be used when
+ * an entry that is on the LRU is used, and should be moved to the MRU end of
+ * the list. If the item is not on a list, then this function has no effect.
+ * The comments about an element already pertaining to a list are also valid
+ * for list_lru_rotate.
+ */
+void list_lru_rotate(struct list_lru *lru, struct list_head *item);
+
+/**
  * list_lru_count_one: return the number of objects currently held by @lru
  * @lru: the lru pointer.
  * @nid: the node id to count from.

index e1da19fac1b3..66718c2a9a7b 100644
@@ -130,6 +130,21 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 }
 EXPORT_SYMBOL_GPL(list_lru_del);
 
+void list_lru_rotate(struct list_lru *lru, struct list_head *item)
+{
+	int nid = page_to_nid(virt_to_page(item));
+	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
+
+	spin_lock(&nlru->lock);
+	if (!list_empty(item)) {
+		l = list_lru_from_kmem(nlru, item);
+		list_move_tail(item, &l->list);
+	}
+	spin_unlock(&nlru->lock);
+}
+EXPORT_SYMBOL_GPL(list_lru_rotate);
+
 void list_lru_isolate(struct list_lru_one *list, struct list_head *item)
 {
 	list_del_init(item);

index ad17e05ebf95..52cc6803c07a 100644
@@ -244,6 +244,8 @@ static void ____fput(struct callback_head *work)
 	__fput(container_of(work, struct file, f_u.fu_rcuhead));
 }
 
+static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
+
 /*
  * If kernel thread really needs to have the final fput() it has done
  * to complete, call this.  The only user right now is the boot - we

@@ -256,11 +258,9 @@ static void ____fput(struct callback_head *work)
  */
 void flush_delayed_fput(void)
 {
-	delayed_fput(NULL);
+	flush_delayed_work(&delayed_fput_work);
 }
 
-static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
-
 void fput(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {

index 52cc6803c07a..8cfeaee6323f 100644
@@ -261,6 +261,25 @@ void flush_delayed_fput(void)
 	flush_delayed_work(&delayed_fput_work);
 }
 
+/**
+ * fput - put a struct file reference
+ * @file: file of which to put the reference
+ *
+ * This function decrements the reference count for the struct file reference,
+ * and queues it up for destruction if the count goes to zero. In the case of
+ * most tasks we queue it to the task_work infrastructure, which will be run
+ * just before the task returns back to userspace. kthreads however never
+ * return to userspace, so for those we add them to a global list and schedule
+ * a delayed workqueue job to do the final cleanup work.
+ *
+ * Why not just do it synchronously? __fput can involve taking locks of all
+ * sorts, and doing it synchronously means that the callers must take extra care
+ * not to deadlock. That can be very difficult to ensure, so by deferring it
+ * until just before return to userland or to the workqueue, we sidestep that
+ * nastiness. Also, __fput can be quite stack intensive, so doing a final fput
+ * has the possibility of blowing up if we don't take steps to ensure that we
+ * have enough stack space to make it work.
+ */
 void fput(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {

@@ -281,6 +300,7 @@ void fput(struct file *file)
 			schedule_delayed_work(&delayed_fput_work, 1);
 	}
 }
+EXPORT_SYMBOL(fput);
 
 /*
  * synchronous analog of fput(); for kernel threads that might be needed

@@ -299,7 +319,6 @@ void __fput_sync(struct file *file)
 	}
 }
 
-EXPORT_SYMBOL(fput);
 
 void put_filp(struct file *file)
 {

index 8cfeaee6323f..95361d2b8a08 100644
@@ -302,6 +302,33 @@ void fput(struct file *file)
 }
 EXPORT_SYMBOL(fput);
 
+/**
+ * fput_queue - do an fput without using task_work
+ * @file: file of which to put the reference
+ *
+ * When fput is called in the context of a userland process, it'll queue the
+ * actual work (__fput()) to be done just before returning to userland. In some
+ * cases however, we need to ensure that the __fput runs before that point.
+ * There is no safe way to flush work that has been queued via task_work_add
+ * however, so to do this we borrow the delayed_fput infrastructure that
+ * kthreads use. The userland process can use fput_queue() on one or more
+ * struct files and then call flush_delayed_fput() to ensure that they are
+ * completely closed before proceeding.
+ *
+ * Returns true if the final fput was done, false otherwise. The caller can
+ * use this to determine whether to flush_delayed_fput afterward.
+ */
+bool fput_queue(struct file *file)
+{
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		if (llist_add(&file->f_u.fu_llist, &delayed_fput_list))
+			schedule_delayed_work(&delayed_fput_work, 1);
+		return true;
+	}
+	return false;
+}
+EXPORT_SYMBOL(fput_queue);
+
 /*
  * synchronous analog of fput(); for kernel threads that might be needed
  * in some umount() (and thus can't use flush_delayed_fput() without

index f87d30882a24..f9308c9a0746 100644
@@ -12,6 +12,7 @@
 struct file;
 
 extern void fput(struct file *);
+extern bool fput_queue(struct file *);
 
 struct file_operations;
 struct vfsmount;

index 2a54c800a223..a2d5794d713a 100644
@@ -166,6 +166,7 @@ int lease_break_time = 45;
 DEFINE_STATIC_LGLOCK(file_lock_lglock);
 static DEFINE_PER_CPU(struct hlist_head, file_lock_list);
 
+
 /*
  * The blocked_hash is used to find POSIX lock loops for deadlock detection.
  * It is protected by blocked_lock_lock.

@@ -1780,6 +1781,40 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
 }
 EXPORT_SYMBOL(generic_setlease);
 
+#if IS_ENABLED(CONFIG_SRCU)
+/*
+ * Kernel subsystems can register to be notified on any attempt to set
+ * a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd
+ * to close files that it may have cached when there is an attempt to set a
+ * conflicting lease.
+ */
+struct srcu_notifier_head lease_notifier_chain;
+EXPORT_SYMBOL_GPL(lease_notifier_chain);
+
+static inline void
+lease_notifier_chain_init(void)
+{
+	srcu_init_notifier_head(&lease_notifier_chain);
+}
+
+static inline void
+setlease_notifier(long arg, struct file_lock *lease)
+{
+	if (arg != F_UNLCK)
+		srcu_notifier_call_chain(&lease_notifier_chain, arg, lease);
+}
+#else /* !IS_ENABLED(CONFIG_SRCU) */
+static inline void
+lease_notifier_chain_init(void)
+{
+}
+
+static inline void
+setlease_notifier(long arg, struct file_lock *lease)
+{
+}
+#endif /* IS_ENABLED(CONFIG_SRCU) */
+
 /**
  * vfs_setlease        -       sets a lease on an open file
  * @filp:	file pointer

@@ -1800,6 +1835,7 @@ EXPORT_SYMBOL(generic_setlease);
 int
 vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
 {
+	setlease_notifier(arg, *lease);
 	if (filp->f_op->setlease)
 		return filp->f_op->setlease(filp, arg, lease, priv);
 	else

@@ -2696,6 +2732,7 @@ static int __init filelock_init(void)
 	for_each_possible_cpu(i)
 		INIT_HLIST_HEAD(per_cpu_ptr(&file_lock_list, i));
 
+	lease_notifier_chain_init();
 	return 0;
 }
 

index 72d8a844c692..c0df75909dd4 100644
@@ -1042,6 +1042,7 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
 extern int fcntl_getlease(struct file *filp);
 
 /* fs/locks.c */
+extern struct srcu_notifier_head	lease_notifier_chain;
 void locks_free_lock_context(struct file_lock_context *ctx);
 void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);

index 03d3b4c92d9f..d1c10a978bb2 100644
@@ -98,6 +98,7 @@ struct cache_detail {
 					      int has_died);
 
 	struct cache_head *	(*alloc)(void);
+	void			(*flush)(void);
 	int			(*match)(struct cache_head *orig, struct cache_head *new);
 	void			(*init)(struct cache_head *orig, struct cache_head *new);
 	void			(*update)(struct cache_head *orig, struct cache_head *new);

index 4a2340a54401..60da9aa2bdc5 100644
@@ -1451,6 +1451,9 @@ static ssize_t write_flush(struct file *file, const char __user *buf,
 	cd->nextcheck = seconds_since_boot();
 	cache_flush();
 
+	if (cd->flush)
+		cd->flush();
+
 	*ppos += count;
 	return count;
 }

index b4d84b579f20..4b504edff121 100644
@@ -21,6 +21,7 @@
 #include "nfsfh.h"
 #include "netns.h"
 #include "pnfs.h"
+#include "filecache.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 

@@ -231,6 +232,18 @@ static struct cache_head *expkey_alloc(void)
 		return NULL;
 }
 
+static void
+expkey_flush(void)
+{
+	/*
+	 * Take the nfsd_mutex here to ensure that the file cache is not
+	 * destroyed while we're in the middle of flushing.
+	 */
+	mutex_lock(&nfsd_mutex);
+	nfsd_file_cache_purge();
+	mutex_unlock(&nfsd_mutex);
+}
+
 static struct cache_detail svc_expkey_cache_template = {
 	.owner		= THIS_MODULE,
 	.hash_size	= EXPKEY_HASHMAX,

@@ -243,6 +256,7 @@ static struct cache_detail svc_expkey_cache_template = {
 	.init		= expkey_init,
 	.update       	= expkey_update,
 	.alloc		= expkey_alloc,
+	.flush		= expkey_flush,
 };
 
 static int

573 lines not on this page · raw message

new file mode 100644
index 000000000000..5c871c3114f2
@@ -0,0 +1,37 @@
+#ifndef _FS_NFSD_FILECACHE_H
+#define _FS_NFSD_FILECACHE_H
+
+#include <linux/fsnotify_backend.h>
+
+/*
+ * A representation of a file that has been opened by knfsd. These are hashed
+ * in the hashtable by inode pointer value. Note that this object doesn't
+ * hold a reference to the inode by itself, so the nf_inode pointer should
+ * never be dereferenced, only be used for comparison.
+ */
+struct nfsd_file {
+	struct hlist_node	nf_node;
+	struct list_head	nf_lru;
+	struct rcu_head		nf_rcu;
+	struct file		*nf_file;
+#define NFSD_FILE_HASHED	(0)
+#define NFSD_FILE_PENDING	(1)
+#define NFSD_FILE_BREAK_READ	(2)
+#define NFSD_FILE_BREAK_WRITE	(3)
+	unsigned long		nf_flags;
+	struct inode		*nf_inode;
+	unsigned int		nf_hashval;
+	atomic_t		nf_ref;
+	unsigned char		nf_may;
+	struct fsnotify_mark	nf_mark;
+};
+
+int nfsd_file_cache_init(void);
+void nfsd_file_cache_purge(void);
+void nfsd_file_cache_shutdown(void);
+void nfsd_file_put(struct nfsd_file *nf);
+struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
+void nfsd_file_close_inode_sync(struct inode *inode);
+__be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct nfsd_file **nfp);
+#endif /* _FS_NFSD_FILECACHE_H */

index ad4e2377dd63..d816bb3faa6e 100644
@@ -22,6 +22,7 @@
 #include "cache.h"
 #include "vfs.h"
 #include "netns.h"
+#include "filecache.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_SVC
 

@@ -224,11 +225,17 @@ static int nfsd_startup_generic(int nrservs)
 	if (ret)
 		goto dec_users;
 
-	ret = nfs4_state_start();
+	ret = nfsd_file_cache_init();
 	if (ret)
 		goto out_racache;
+
+	ret = nfs4_state_start();
+	if (ret)
+		goto out_file_cache;
 	return 0;
 
+out_file_cache:
+	nfsd_file_cache_shutdown();
 out_racache:
 	nfsd_racache_shutdown();
 dec_users:

@@ -242,6 +249,7 @@ static void nfsd_shutdown_generic(void)
 		return;
 
 	nfs4_state_shutdown();
+	nfsd_file_cache_shutdown();
 	nfsd_racache_shutdown();
 }
 

139 lines not on this page · raw message

index 4212aaacbb55..a144849cec10 100644
@@ -623,7 +623,8 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor
 }
 #endif /* CONFIG_NFSD_V3 */
 
-static int nfsd_open_break_lease(struct inode *inode, int access)
+int
+nfsd_open_break_lease(struct inode *inode, int access)
 {
 	unsigned int mode;
 

index fcfc48cbe136..a877be59d5dd 100644
@@ -69,6 +69,7 @@ __be32		do_nfsd_create(struct svc_rqst *, struct svc_fh *,
 __be32		nfsd_commit(struct svc_rqst *, struct svc_fh *,
 				loff_t, unsigned long);
 #endif /* CONFIG_NFSD_V3 */
+int		nfsd_open_break_lease(struct inode *, int);
 __be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
 				int, struct file **);
 struct raparms;

index fcbc3bca3bdc..932b58a5774f 100644
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/list_lru.h>
 #include <linux/fsnotify_backend.h>
+#include <linux/seq_file.h>
 
 #include "vfs.h"
 #include "nfsd.h"

@@ -30,6 +31,8 @@
 struct nfsd_fcache_bucket {
 	struct hlist_head	nfb_head;
 	spinlock_t		nfb_lock;
+	unsigned int		nfb_count;
+	unsigned int		nfb_maxcount;
 };
 
 static struct kmem_cache		*nfsd_file_slab;

@@ -111,6 +114,7 @@ nfsd_file_unhash(struct nfsd_file *nf)
 
 	trace_nfsd_file_unhash(nf);
 	if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
+		--nfsd_file_hashtbl[nf->nf_hashval].nfb_count;
 		clear_bit(NFSD_FILE_HASHED, &nf->nf_flags);
 		hlist_del_rcu(&nf->nf_node);
 		list_lru_del(&nfsd_file_lru, &nf->nf_lru);

@@ -491,6 +495,9 @@ retry:
 		list_lru_add(&nfsd_file_lru, &new->nf_lru);
 		hlist_add_head_rcu(&new->nf_node,
 				&nfsd_file_hashtbl[hashval].nfb_head);
+		++nfsd_file_hashtbl[hashval].nfb_count;
+		nfsd_file_hashtbl[hashval].nfb_maxcount = max(nfsd_file_hashtbl[hashval].nfb_maxcount,
+				nfsd_file_hashtbl[hashval].nfb_count);
 		spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock);
 
 		/* This should never fail since we set allow_dups to true */

@@ -571,3 +578,36 @@ open_file:
 	wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING);
 	goto out;
 }
+
+/*
+ * Note that fields may be added, removed or reordered in the future. Programs
+ * scraping this file for info should test the labels to ensure they're
+ * getting the correct field.
+ */
+static int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
+{
+	unsigned int i, count = 0, longest = 0;
+
+	/*
+	 * No need for spinlocks here since we're not terribly interested in
+	 * accuracy. We do take the nfsd_mutex simply to ensure that we
+	 * don't end up racing with server shutdown
+	 */
+	mutex_lock(&nfsd_mutex);
+	if (nfsd_file_hashtbl) {
+		for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) {
+			count += nfsd_file_hashtbl[i].nfb_count;
+			longest = max(longest, nfsd_file_hashtbl[i].nfb_count);
+		}
+	}
+	mutex_unlock(&nfsd_mutex);
+
+	seq_printf(m, "total entries: %u\n", count);
+	seq_printf(m, "longest chain: %u\n", longest);
+	return 0;
+}
+
+int nfsd_file_cache_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nfsd_file_cache_stats_show, NULL);
+}

index 5c871c3114f2..a1467dbf1d29 100644
@@ -34,4 +34,5 @@ struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
 void nfsd_file_close_inode_sync(struct inode *inode);
 __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **nfp);
+int	nfsd_file_cache_stats_open(struct inode *, struct file *);
 #endif /* _FS_NFSD_FILECACHE_H */

index 9690cb4dd588..eff44a277f70 100644
@@ -22,6 +22,7 @@
 #include "state.h"
 #include "netns.h"
 #include "pnfs.h"
+#include "filecache.h"
 
 /*
  *	We have a single directory with several nodes in it.

@@ -36,6 +37,7 @@ enum {
 	NFSD_Threads,
 	NFSD_Pool_Threads,
 	NFSD_Pool_Stats,
+	NFSD_File_Cache_Stats,
 	NFSD_Reply_Cache_Stats,
 	NFSD_Versions,
 	NFSD_Ports,

@@ -220,6 +222,13 @@ static const struct file_operations pool_stats_operations = {
 	.owner		= THIS_MODULE,
 };
 
+static struct file_operations file_cache_stats_operations = {
+	.open		= nfsd_file_cache_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct file_operations reply_cache_stats_operations = {
 	.open		= nfsd_reply_cache_stats_open,
 	.read		= seq_read,

@@ -1138,6 +1147,7 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
 		[NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Pool_Stats] = {"pool_stats", &pool_stats_operations, S_IRUGO},
+		[NFSD_File_Cache_Stats] = {"file_cache_stats", &file_cache_stats_operations, S_IRUGO},
 		[NFSD_Reply_Cache_Stats] = {"reply_cache_stats", &reply_cache_stats_operations, S_IRUGO},
 		[NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO},

index 050db266ef80..571f1000e670 100644
@@ -1055,9 +1055,9 @@ __be32
 nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
                loff_t offset, unsigned long count)
 {
-	struct file	*file;
-	loff_t		end = LLONG_MAX;
-	__be32		err = nfserr_inval;
+	struct nfsd_file	*nf;
+	loff_t			end = LLONG_MAX;
+	__be32			err = nfserr_inval;
 
 	if (offset < 0)
 		goto out;

@@ -1067,12 +1067,12 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			goto out;
 	}
 
-	err = nfsd_open(rqstp, fhp, S_IFREG,
-			NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &file);
+	err = nfsd_file_acquire(rqstp, fhp,
+			NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &nf);
 	if (err)
 		goto out;
 	if (EX_ISSYNC(fhp->fh_export)) {
-		int err2 = vfs_fsync_range(file, offset, end, 0);
+		int err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
 
 		if (err2 != -EINVAL)
 			err = nfserrno(err2);

@@ -1080,7 +1080,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			err = nfserr_notsupp;
 	}
 
-	fput(file);
+	nfsd_file_put(nf);
 out:
 	return err;
 }

index 2b73e2885a82..b72fa6816860 100644
@@ -49,6 +49,7 @@
 
 #include "netns.h"
 #include "pnfs.h"
+#include "filecache.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 

@@ -292,7 +293,7 @@ static struct file *
 __nfs4_get_fd(struct nfs4_file *f, int oflag)
 {
 	if (f->fi_fds[oflag])
-		return get_file(f->fi_fds[oflag]);
+		return get_file(f->fi_fds[oflag]->nf_file);
 	return NULL;
 }
 

@@ -449,17 +450,17 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
 	might_lock(&fp->fi_lock);
 
 	if (atomic_dec_and_lock(&fp->fi_access[oflag], &fp->fi_lock)) {
-		struct file *f1 = NULL;
-		struct file *f2 = NULL;
+		struct nfsd_file *f1 = NULL;
+		struct nfsd_file *f2 = NULL;
 
 		swap(f1, fp->fi_fds[oflag]);
 		if (atomic_read(&fp->fi_access[1 - oflag]) == 0)
 			swap(f2, fp->fi_fds[O_RDWR]);
 		spin_unlock(&fp->fi_lock);
 		if (f1)
-			fput(f1);
+			nfsd_file_put(f1);
 		if (f2)
-			fput(f2);
+			nfsd_file_put(f2);
 	}
 }
 

@@ -3841,7 +3842,7 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
 		struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp,
 		struct nfsd4_open *open)
 {
-	struct file *filp = NULL;
+	struct nfsd_file *nf = NULL;
 	__be32 status;
 	int oflag = nfs4_access_to_omode(open->op_share_access);
 	int access = nfs4_access_to_access(open->op_share_access);

@@ -3877,18 +3878,18 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
 
 	if (!fp->fi_fds[oflag]) {
 		spin_unlock(&fp->fi_lock);
-		status = nfsd_open(rqstp, cur_fh, S_IFREG, access, &filp);
+		status = nfsd_file_acquire(rqstp, cur_fh, access, &nf);
 		if (status)
 			goto out_put_access;
 		spin_lock(&fp->fi_lock);
 		if (!fp->fi_fds[oflag]) {
-			fp->fi_fds[oflag] = filp;
-			filp = NULL;
+			fp->fi_fds[oflag] = nf;
+			nf = NULL;
 		}
 	}
 	spin_unlock(&fp->fi_lock);
-	if (filp)
-		fput(filp);
+	if (nf)
+		nfsd_file_put(nf);
 
 	status = nfsd4_truncate(rqstp, cur_fh, open);
 	if (status)

index 77fdf4de91ba..473faa436e07 100644
@@ -491,7 +491,7 @@ struct nfs4_file {
 	};
 	struct list_head	fi_clnt_odstate;
 	/* One each for O_RDONLY, O_WRONLY, O_RDWR: */
-	struct file *		fi_fds[3];
+	struct nfsd_file	*fi_fds[3];
 	/*
 	 * Each open or lock stateid contributes 0-4 to the counts
 	 * below depending on which bits are set in st_access_bitmap:

index b72fa6816860..4348af408ccb 100644
@@ -5596,11 +5596,11 @@ out:
  */
 static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock)
 {
-	struct file *file;
-	__be32 err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
+	struct nfsd_file *nf;
+	__be32 err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf);
 	if (!err) {
-		err = nfserrno(vfs_test_lock(file, lock));
-		fput(file);
+		err = nfserrno(vfs_test_lock(nf->nf_file, lock));
+		nfsd_file_put(nf);
 	}
 	return err;
 }

index a9f096c7e99f..7e21763a35f2 100644
@@ -758,7 +758,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	__be32 status;
 
-	read->rd_filp = NULL;
+	read->rd_nf = NULL;
 	if (read->rd_offset >= OFFSET_MAX)
 		return nfserr_inval;
 

@@ -775,7 +775,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	/* check stateid */
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &read->rd_stateid,
-			RD_STATE, &read->rd_filp, &read->rd_tmp_file);
+			RD_STATE, &read->rd_nf);
 	if (status) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;

@@ -921,7 +921,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
 		status = nfs4_preprocess_stateid_op(rqstp, cstate,
-			&setattr->sa_stateid, WR_STATE, NULL, NULL);
+			&setattr->sa_stateid, WR_STATE, NULL);
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
 			return status;

@@ -977,7 +977,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	    struct nfsd4_write *write)
 {
 	stateid_t *stateid = &write->wr_stateid;
-	struct file *filp = NULL;
+	struct nfsd_file *nf = NULL;
 	__be32 status = nfs_ok;
 	unsigned long cnt;
 	int nvecs;

@@ -986,7 +986,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return nfserr_inval;
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, stateid, WR_STATE,
-			&filp, NULL);
+			&nf);
 	if (status) {
 		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;

@@ -999,10 +999,10 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	nvecs = fill_in_write_vector(rqstp->rq_vec, write);
 	WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
 
-	status = nfsd_vfs_write(rqstp, &cstate->current_fh, filp,
+	status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf->nf_file,
 				write->wr_offset, rqstp->rq_vec, nvecs, &cnt,
 				&write->wr_how_written);
-	fput(filp);
+	nfsd_file_put(nf);
 
 	write->wr_bytes_written = cnt;
 

@@ -1014,21 +1014,21 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		struct nfsd4_fallocate *fallocate, int flags)
 {
 	__be32 status = nfserr_notsupp;
-	struct file *file;
+	struct nfsd_file *nf;
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate,
 					    &fallocate->falloc_stateid,
-					    WR_STATE, &file, NULL);
+					    WR_STATE, &nf);
 	if (status != nfs_ok) {
 		dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n");
 		return status;
 	}
 
-	status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, file,
+	status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, nf->nf_file,
 				     fallocate->falloc_offset,
 				     fallocate->falloc_length,
 				     flags);
-	fput(file);
+	nfsd_file_put(nf);
 	return status;
 }
 

@@ -1053,11 +1053,11 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	int whence;
 	__be32 status;
-	struct file *file;
+	struct nfsd_file *nf;
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate,
 					    &seek->seek_stateid,
-					    RD_STATE, &file, NULL);
+					    RD_STATE, &nf);
 	if (status) {
 		dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
 		return status;

@@ -1079,14 +1079,14 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * Note:  This call does change file->f_pos, but nothing in NFSD
 	 *        should ever file->f_pos.
 	 */
-	seek->seek_pos = vfs_llseek(file, seek->seek_offset, whence);
+	seek->seek_pos = vfs_llseek(nf->nf_file, seek->seek_offset, whence);
 	if (seek->seek_pos < 0)
 		status = nfserrno(seek->seek_pos);
-	else if (seek->seek_pos >= i_size_read(file_inode(file)))
+	else if (seek->seek_pos >= i_size_read(file_inode(nf->nf_file)))
 		seek->seek_eof = true;
 
 out:
-	fput(file);
+	nfsd_file_put(nf);
 	return status;
 }
 

index 4d58a6db6e41..477fe34567d0 100644
@@ -4658,7 +4658,7 @@ nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags)
 
 static __be32
 nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s,
-		struct file **filpp, bool *tmp_file, int flags)
+		struct nfsd_file **nfp, int flags)
 {
 	int acc = (flags & RD_STATE) ? NFSD_MAY_READ : NFSD_MAY_WRITE;
 	struct nfsd_file *nf;

@@ -4668,20 +4668,18 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s,
 	if (nf) {
 		status = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
 				acc | NFSD_MAY_OWNER_OVERRIDE);
-		if (status)
+		if (status) {
+			nfsd_file_put(nf);
 			goto out;
+		}
 	} else {
 		status = nfsd_file_acquire(rqstp, fhp, acc, &nf);
 		if (status)
 			return status;
-
-		if (tmp_file)
-			*tmp_file = true;
 	}
 
-	*filpp = get_file(nf->nf_file);
+	*nfp = nf;
 out:
-	nfsd_file_put(nf);
 	return status;
 }
 

@@ -4691,7 +4689,7 @@ out:
 __be32
 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, stateid_t *stateid,
-		int flags, struct file **filpp, bool *tmp_file)
+		int flags, struct nfsd_file **nfp)
 {
 	struct svc_fh *fhp = &cstate->current_fh;
 	struct inode *ino = d_inode(fhp->fh_dentry);

@@ -4700,10 +4698,8 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 	struct nfs4_stid *s = NULL;
 	__be32 status;
 
-	if (filpp)
-		*filpp = NULL;
-	if (tmp_file)
-		*tmp_file = false;
+	if (nfp)
+		*nfp = NULL;
 
 	if (grace_disallows_io(net, ino))
 		return nfserr_grace;

@@ -4740,8 +4736,8 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 	status = nfs4_check_fh(fhp, s);
 
 done:
-	if (!status && filpp)
-		status = nfs4_check_file(rqstp, fhp, s, filpp, tmp_file, flags);
+	if (status == nfs_ok && nfp)
+		status = nfs4_check_file(rqstp, fhp, s, nfp, flags);
 out:
 	if (s)
 		nfs4_put_stid(s);

index 325521ce389a..92e5e8f884d0 100644
@@ -49,6 +49,7 @@
 #include "cache.h"
 #include "netns.h"
 #include "pnfs.h"
+#include "filecache.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>

@@ -3460,14 +3461,14 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 {
 	unsigned long maxcount;
 	struct xdr_stream *xdr = &resp->xdr;
-	struct file *file = read->rd_filp;
+	struct file *file;
 	int starting_len = xdr->buf->len;
-	struct raparms *ra = NULL;
 	__be32 *p;
 
 	if (nfserr)
 		goto out;
 
+	file = read->rd_nf->nf_file;
 	p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */
 	if (!p) {
 		WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags));

@@ -3487,24 +3488,17 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 			 (xdr->buf->buflen - xdr->buf->len));
 	maxcount = min_t(unsigned long, maxcount, read->rd_length);
 
-	if (read->rd_tmp_file)
-		ra = nfsd_init_raparms(file);
-
 	if (file->f_op->splice_read &&
 	    test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags))
 		nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount);
 	else
 		nfserr = nfsd4_encode_readv(resp, read, file, maxcount);
 
-	if (ra)
-		nfsd_put_raparams(file, ra);
-
 	if (nfserr)
 		xdr_truncate_encode(xdr, starting_len);
-
 out:
-	if (file)
-		fput(file);
+	if (read->rd_nf)
+		nfsd_file_put(read->rd_nf);
 	return nfserr;
 }
 

index ee23de10663c..732fbb3b5ef1 100644
@@ -579,7 +579,7 @@ struct nfsd_net;
 
 extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, stateid_t *stateid,
-		int flags, struct file **filp, bool *tmp_file);
+		int flags, struct nfsd_file **filp);
 __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn);

index ce7362c88b48..c167d7a5b0e6 100644
@@ -268,15 +268,14 @@ struct nfsd4_open_downgrade {
 
 
 struct nfsd4_read {
-	stateid_t	rd_stateid;         /* request */
-	u64		rd_offset;          /* request */
-	u32		rd_length;          /* request */
-	int		rd_vlen;
-	struct file     *rd_filp;
-	bool		rd_tmp_file;
+	stateid_t		rd_stateid;         /* request */
+	u64			rd_offset;          /* request */
+	u32			rd_length;          /* request */
+	int			rd_vlen;
+	struct nfsd_file	*rd_nf;
 	
-	struct svc_rqst *rd_rqstp;          /* response */
-	struct svc_fh * rd_fhp;             /* response */
+	struct svc_rqst		*rd_rqstp;          /* response */
+	struct svc_fh		*rd_fhp;             /* response */
 };
 
 struct nfsd4_readdir {

index d816bb3faa6e..d1034d119afb 100644
@@ -216,18 +216,9 @@ static int nfsd_startup_generic(int nrservs)
 	if (nfsd_users++)
 		return 0;
 
-	/*
-	 * Readahead param cache - will no-op if it already exists.
-	 * (Note therefore results will be suboptimal if number of
-	 * threads is modified after nfsd start.)
-	 */
-	ret = nfsd_racache_init(2*nrservs);
-	if (ret)
-		goto dec_users;
-
 	ret = nfsd_file_cache_init();
 	if (ret)
-		goto out_racache;
+		goto dec_users;
 
 	ret = nfs4_state_start();
 	if (ret)

@@ -236,8 +227,6 @@ static int nfsd_startup_generic(int nrservs)
 
 out_file_cache:
 	nfsd_file_cache_shutdown();
-out_racache:
-	nfsd_racache_shutdown();
 dec_users:
 	nfsd_users--;
 	return ret;

@@ -250,7 +239,6 @@ static void nfsd_shutdown_generic(void)
 
 	nfs4_state_shutdown();
 	nfsd_file_cache_shutdown();
-	nfsd_racache_shutdown();
 }
 
 static bool nfsd_needs_lockd(void)

162 lines not on this page · raw message

index 80692e06302d..1efccde4bf9a 100644
@@ -39,8 +39,6 @@
 typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
 
 /* nfsd/vfs.c */
-int		nfsd_racache_init(int);
-void		nfsd_racache_shutdown(void);
 int		nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 		                struct svc_export **expp);
 __be32		nfsd_lookup(struct svc_rqst *, struct svc_fh *,

@@ -74,7 +72,6 @@ __be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
 				int, struct file **);
 __be32		nfsd_open_verified(struct svc_rqst *, struct svc_fh *, umode_t,
 				int, struct file **);
-struct raparms;
 __be32		nfsd_splice_read(struct svc_rqst *,
 				struct file *, loff_t, unsigned long *);
 __be32		nfsd_readv(struct file *, loff_t, struct kvec *, int,

@@ -107,9 +104,6 @@ __be32		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
 __be32		nfsd_permission(struct svc_rqst *, struct svc_export *,
 				struct dentry *, int);
 
-struct raparms *nfsd_init_raparms(struct file *file);
-void		nfsd_put_raparams(struct file *file, struct raparms *ra);
-
 static inline int fh_want_write(struct svc_fh *fh)
 {
 	int ret = mnt_want_write(fh->fh_export->ex_path.mnt);