Merge tag 'fuse-update-4.20' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse

Pull fuse updates from Miklos Szeredi:
 "As well as the usual bug fixes, this adds the following new features:

   - cached readdir and readlink

   - max I/O size increased from 128k to 1M

   - improved performance and scalability of request queues

   - copy_file_range support

  The only non-fuse bits are trivial cleanups of macros in
  <linux/bitops.h>"

* tag 'fuse-update-4.20' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse: (31 commits)
  fuse: enable caching of symlinks
  fuse: only invalidate atime in direct read
  fuse: don't need GETATTR after every READ
  fuse: allow fine grained attr cache invaldation
  bitops: protect variables in bit_clear_unless() macro
  bitops: protect variables in set_mask_bits() macro
  fuse: realloc page array
  fuse: add max_pages to init_out
  fuse: allocate page array more efficiently
  fuse: reduce size of struct fuse_inode
  fuse: use iversion for readdir cache verification
  fuse: use mtime for readdir cache verification
  fuse: add readdir cache version
  fuse: allow using readdir cache
  fuse: allow caching readdir
  fuse: extract fuse_emit() helper
  fuse: add FOPEN_CACHE_DIR
  fuse: split out readdir.c
  fuse: Use hash table to link processing request
  fuse: kill req->intr_unique
  ...

fs/fuse/Makefile

@@ -5,4 +5,4 @@
 obj-$(CONFIG_FUSE_FS) += fuse.o
 obj-$(CONFIG_CUSE) += cuse.o
 
-fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o
+fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o

fs/fuse/control.c

@@ -107,7 +107,7 @@ static ssize_t fuse_conn_max_background_read(struct file *file,
 	if (!fc)
 		return 0;
 
-	val = fc->max_background;
+	val = READ_ONCE(fc->max_background);
 	fuse_conn_put(fc);
 
 	return fuse_conn_limit_read(file, buf, len, ppos, val);
@@ -125,7 +125,12 @@ static ssize_t fuse_conn_max_background_write(struct file *file,
 	if (ret > 0) {
 		struct fuse_conn *fc = fuse_ctl_file_conn_get(file);
 		if (fc) {
+			spin_lock(&fc->bg_lock);
 			fc->max_background = val;
+			fc->blocked = fc->num_background >= fc->max_background;
+			if (!fc->blocked)
+				wake_up(&fc->blocked_waitq);
+			spin_unlock(&fc->bg_lock);
 			fuse_conn_put(fc);
 		}
 	}
@@ -144,7 +149,7 @@ static ssize_t fuse_conn_congestion_threshold_read(struct file *file,
 	if (!fc)
 		return 0;
 
-	val = fc->congestion_threshold;
+	val = READ_ONCE(fc->congestion_threshold);
 	fuse_conn_put(fc);
 
 	return fuse_conn_limit_read(file, buf, len, ppos, val);
@@ -155,18 +160,31 @@ static ssize_t fuse_conn_congestion_threshold_write(struct file *file,
 						    size_t count, loff_t *ppos)
 {
 	unsigned uninitialized_var(val);
+	struct fuse_conn *fc;
 	ssize_t ret;
 
 	ret = fuse_conn_limit_write(file, buf, count, ppos, &val,
 				    max_user_congthresh);
-	if (ret > 0) {
-		struct fuse_conn *fc = fuse_ctl_file_conn_get(file);
-		if (fc) {
+	if (ret <= 0)
+		goto out;
+	fc = fuse_ctl_file_conn_get(file);
+	if (!fc)
+		goto out;
+
+	spin_lock(&fc->bg_lock);
 	fc->congestion_threshold = val;
-			fuse_conn_put(fc);
+	if (fc->sb) {
+		if (fc->num_background < fc->congestion_threshold) {
+			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
+			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
+		} else {
+			set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
+			set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
 		}
 	}
-
+	spin_unlock(&fc->bg_lock);
+	fuse_conn_put(fc);
+out:
 	return ret;
 }
 

fs/fuse/fuse_i.h

@@ -28,8 +28,11 @@
 #include <linux/refcount.h>
 #include <linux/user_namespace.h>
 
-/** Max number of pages that can be used in a single read request */
-#define FUSE_MAX_PAGES_PER_REQ 32
+/** Default max number of pages that can be used in a single read request */
+#define FUSE_DEFAULT_MAX_PAGES_PER_REQ 32
+
+/** Maximum of max_pages received in init_out */
+#define FUSE_MAX_MAX_PAGES 256
 
 /** Bias for fi->writectr, meaning new writepages must not be sent */
 #define FUSE_NOWRITE INT_MIN
@@ -77,6 +80,9 @@ struct fuse_inode {
 	/** Time in jiffies until the file attributes are valid */
 	u64 i_time;
 
+	/* Which attributes are invalid */
+	u32 inval_mask;
+
 	/** The sticky bit in inode->i_mode may have been removed, so
 	    preserve the original mode */
 	umode_t orig_i_mode;
@@ -87,21 +93,51 @@ struct fuse_inode {
 	/** Version of last attribute change */
 	u64 attr_version;
 
-	/** Files usable in writepage.  Protected by fc->lock */
+	union {
+		/* Write related fields (regular file only) */
+		struct {
+			/* Files usable in writepage.  Protected by fc->lock */
 			struct list_head write_files;
 
-	/** Writepages pending on truncate or fsync */
+			/* Writepages pending on truncate or fsync */
 			struct list_head queued_writes;
 
-	/** Number of sent writes, a negative bias (FUSE_NOWRITE)
-	 * means more writes are blocked */
+			/* Number of sent writes, a negative bias
+			 * (FUSE_NOWRITE) means more writes are blocked */
 			int writectr;
 
-	/** Waitq for writepage completion */
+			/* Waitq for writepage completion */
 			wait_queue_head_t page_waitq;
 
-	/** List of writepage requestst (pending or sent) */
+			/* List of writepage requestst (pending or sent) */
 			struct list_head writepages;
+		};
+
+		/* readdir cache (directory only) */
+		struct {
+			/* true if fully cached */
+			bool cached;
+
+			/* size of cache */
+			loff_t size;
+
+			/* position at end of cache (position of next entry) */
+			loff_t pos;
+
+			/* version of the cache */
+			u64 version;
+
+			/* modification time of directory when cache was
+			 * started */
+			struct timespec64 mtime;
+
+			/* iversion of directory when cache was started */
+			u64 iversion;
+
+			/* protects above fields */
+			spinlock_t lock;
+		} rdc;
+	};
 
 	/** Miscellaneous bits describing inode state */
 	unsigned long state;
@@ -148,6 +184,25 @@ struct fuse_file {
 	/** Entry on inode's write_files list */
 	struct list_head write_entry;
 
+	/* Readdir related */
+	struct {
+		/*
+		 * Protects below fields against (crazy) parallel readdir on
+		 * same open file.  Uncontended in the normal case.
+		 */
+		struct mutex lock;
+
+		/* Dir stream position */
+		loff_t pos;
+
+		/* Offset in cache */
+		loff_t cache_off;
+
+		/* Version of cache we are reading */
+		u64 version;
+
+	} readdir;
+
 	/** RB node to be linked on fuse_conn->polled_files */
 	struct rb_node polled_node;
 
@@ -311,9 +366,6 @@ struct fuse_req {
 	/** refcount */
 	refcount_t count;
 
-	/** Unique ID for the interrupt request */
-	u64 intr_unique;
-
 	/* Request flags, updated with test/set/clear_bit() */
 	unsigned long flags;
 
@@ -411,6 +463,9 @@ struct fuse_iqueue {
 	struct fasync_struct *fasync;
 };
 
+#define FUSE_PQ_HASH_BITS 8
+#define FUSE_PQ_HASH_SIZE (1 << FUSE_PQ_HASH_BITS)
+
 struct fuse_pqueue {
 	/** Connection established */
 	unsigned connected;
@@ -418,8 +473,8 @@ struct fuse_pqueue {
 	/** Lock protecting accessess to  members of this structure */
 	spinlock_t lock;
 
-	/** The list of requests being processed */
-	struct list_head processing;
+	/** Hash table of requests being processed */
+	struct list_head *processing;
 
 	/** The list of requests under I/O */
 	struct list_head io;
@@ -476,6 +531,9 @@ struct fuse_conn {
 	/** Maximum write size */
 	unsigned max_write;
 
+	/** Maxmum number of pages that can be used in a single request */
+	unsigned int max_pages;
+
 	/** Input queue */
 	struct fuse_iqueue iq;
 
@@ -500,6 +558,10 @@ struct fuse_conn {
 	/** The list of background requests set aside for later queuing */
 	struct list_head bg_queue;
 
+	/** Protects: max_background, congestion_threshold, num_background,
+	 * active_background, bg_queue, blocked */
+	spinlock_t bg_lock;
+
 	/** Flag indicating that INIT reply has been received. Allocating
 	 * any fuse request will be suspended until the flag is set */
 	int initialized;
@@ -551,6 +613,9 @@ struct fuse_conn {
 	/** handle fs handles killing suid/sgid/cap on write/chown/trunc */
 	unsigned handle_killpriv:1;
 
+	/** cache READLINK responses in page cache */
+	unsigned cache_symlinks:1;
+
 	/*
 	 * The following bitfields are only for optimization purposes
 	 * and hence races in setting them will not cause malfunction
@@ -637,6 +702,9 @@ struct fuse_conn {
 	/** Allow other than the mounter user to access the filesystem ? */
 	unsigned allow_other:1;
 
+	/** Does the filesystem support copy_file_range? */
+	unsigned no_copy_file_range:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
@@ -697,6 +765,11 @@ static inline u64 get_node_id(struct inode *inode)
 	return get_fuse_inode(inode)->nodeid;
 }
 
+static inline int invalid_nodeid(u64 nodeid)
+{
+	return !nodeid || nodeid == FUSE_ROOT_ID;
+}
+
 /** Device operations */
 extern const struct file_operations fuse_dev_operations;
 
@@ -812,6 +885,10 @@ struct fuse_req *fuse_request_alloc(unsigned npages);
 
 struct fuse_req *fuse_request_alloc_nofs(unsigned npages);
 
+bool fuse_req_realloc_pages(struct fuse_conn *fc, struct fuse_req *req,
+			    gfp_t flags);
+
+
 /**
  * Free a request
  */
@@ -856,9 +933,7 @@ ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args);
  * Send a request in the background
  */
 void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req);
-
-void fuse_request_send_background_locked(struct fuse_conn *fc,
-					 struct fuse_req *req);
+bool fuse_request_queue_background(struct fuse_conn *fc, struct fuse_req *req);
 
 /* Abort all requests */
 void fuse_abort_conn(struct fuse_conn *fc, bool is_abort);
@@ -873,6 +948,9 @@ void fuse_invalidate_entry_cache(struct dentry *entry);
 
 void fuse_invalidate_atime(struct inode *inode);
 
+u64 entry_attr_timeout(struct fuse_entry_out *o);
+void fuse_change_entry_timeout(struct dentry *entry, struct fuse_entry_out *o);
+
 /**
  * Acquire reference to fuse_conn
  */
@@ -992,4 +1070,8 @@ struct posix_acl;
 struct posix_acl *fuse_get_acl(struct inode *inode, int type);
 int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 
+
+/* readdir.c */
+int fuse_readdir(struct file *file, struct dir_context *ctx);
+
 #endif /* _FS_FUSE_I_H */

fs/fuse/inode.c

@@ -90,16 +90,12 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 
 	fi = get_fuse_inode(inode);
 	fi->i_time = 0;
+	fi->inval_mask = 0;
 	fi->nodeid = 0;
 	fi->nlookup = 0;
 	fi->attr_version = 0;
-	fi->writectr = 0;
 	fi->orig_ino = 0;
 	fi->state = 0;
-	INIT_LIST_HEAD(&fi->write_files);
-	INIT_LIST_HEAD(&fi->queued_writes);
-	INIT_LIST_HEAD(&fi->writepages);
-	init_waitqueue_head(&fi->page_waitq);
 	mutex_init(&fi->mutex);
 	fi->forget = fuse_alloc_forget();
 	if (!fi->forget) {
@@ -119,8 +115,10 @@ static void fuse_i_callback(struct rcu_head *head)
 static void fuse_destroy_inode(struct inode *inode)
 {
 	struct fuse_inode *fi = get_fuse_inode(inode);
-	BUG_ON(!list_empty(&fi->write_files));
-	BUG_ON(!list_empty(&fi->queued_writes));
+	if (S_ISREG(inode->i_mode)) {
+		WARN_ON(!list_empty(&fi->write_files));
+		WARN_ON(!list_empty(&fi->queued_writes));
+	}
 	mutex_destroy(&fi->mutex);
 	kfree(fi->forget);
 	call_rcu(&inode->i_rcu, fuse_i_callback);
@@ -167,6 +165,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 
 	fi->attr_version = ++fc->attr_version;
 	fi->i_time = attr_valid;
+	WRITE_ONCE(fi->inval_mask, 0);
 
 	inode->i_ino     = fuse_squash_ino(attr->ino);
 	inode->i_mode    = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
@@ -594,9 +593,11 @@ static void fuse_iqueue_init(struct fuse_iqueue *fiq)
 
 static void fuse_pqueue_init(struct fuse_pqueue *fpq)
 {
-	memset(fpq, 0, sizeof(struct fuse_pqueue));
+	unsigned int i;
+
 	spin_lock_init(&fpq->lock);
-	INIT_LIST_HEAD(&fpq->processing);
+	for (i = 0; i < FUSE_PQ_HASH_SIZE; i++)
+		INIT_LIST_HEAD(&fpq->processing[i]);
 	INIT_LIST_HEAD(&fpq->io);
 	fpq->connected = 1;
 }
@@ -605,6 +606,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns)
 {
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);
+	spin_lock_init(&fc->bg_lock);
 	init_rwsem(&fc->killsb);
 	refcount_set(&fc->count, 1);
 	atomic_set(&fc->dev_count, 1);
@@ -852,6 +854,7 @@ static void process_init_limits(struct fuse_conn *fc, struct fuse_init_out *arg)
 	sanitize_global_limit(&max_user_bgreq);
 	sanitize_global_limit(&max_user_congthresh);
 
+	spin_lock(&fc->bg_lock);
 	if (arg->max_background) {
 		fc->max_background = arg->max_background;
 
@@ -865,6 +868,7 @@ static void process_init_limits(struct fuse_conn *fc, struct fuse_init_out *arg)
 		    fc->congestion_threshold > max_user_congthresh)
 			fc->congestion_threshold = max_user_congthresh;
 	}
+	spin_unlock(&fc->bg_lock);
 }
 
 static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
@@ -924,8 +928,15 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 				fc->posix_acl = 1;
 				fc->sb->s_xattr = fuse_acl_xattr_handlers;
 			}
+			if (arg->flags & FUSE_CACHE_SYMLINKS)
+				fc->cache_symlinks = 1;
 			if (arg->flags & FUSE_ABORT_ERROR)
 				fc->abort_err = 1;
+			if (arg->flags & FUSE_MAX_PAGES) {
+				fc->max_pages =
+					min_t(unsigned int, FUSE_MAX_MAX_PAGES,
+					max_t(unsigned int, arg->max_pages, 1));
+			}
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -957,7 +968,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 		FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
 		FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT |
 		FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL |
-		FUSE_ABORT_ERROR;
+		FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
@@ -1022,16 +1033,25 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 struct fuse_dev *fuse_dev_alloc(struct fuse_conn *fc)
 {
 	struct fuse_dev *fud;
+	struct list_head *pq;
 
 	fud = kzalloc(sizeof(struct fuse_dev), GFP_KERNEL);
-	if (fud) {
+	if (!fud)
+		return NULL;
+
+	pq = kcalloc(FUSE_PQ_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL);
+	if (!pq) {
+		kfree(fud);
+		return NULL;
+	}
+
+	fud->pq.processing = pq;
 	fud->fc = fuse_conn_get(fc);
 	fuse_pqueue_init(&fud->pq);
 
 	spin_lock(&fc->lock);
 	list_add_tail(&fud->entry, &fc->devices);
 	spin_unlock(&fc->lock);
-	}
 
 	return fud;
 }
@@ -1141,6 +1161,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	fc->user_id = d.user_id;
 	fc->group_id = d.group_id;
 	fc->max_read = max_t(unsigned, 4096, d.max_read);
+	fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
 
 	/* Used by get_root_inode() */
 	sb->s_fs_info = fc;

include/linux/bitops.h

@@ -236,33 +236,33 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
 #ifdef __KERNEL__
 
 #ifndef set_mask_bits
-#define set_mask_bits(ptr, _mask, _bits)	\
+#define set_mask_bits(ptr, mask, bits)	\
 ({								\
-	const typeof(*ptr) mask = (_mask), bits = (_bits);	\
-	typeof(*ptr) old, new;					\
+	const typeof(*(ptr)) mask__ = (mask), bits__ = (bits);	\
+	typeof(*(ptr)) old__, new__;				\
 								\
 	do {							\
-		old = READ_ONCE(*ptr);			\
-		new = (old & ~mask) | bits;			\
-	} while (cmpxchg(ptr, old, new) != old);		\
+		old__ = READ_ONCE(*(ptr));			\
+		new__ = (old__ & ~mask__) | bits__;		\
+	} while (cmpxchg(ptr, old__, new__) != old__);		\
 								\
-	new;							\
+	new__;							\
 })
 #endif
 
 #ifndef bit_clear_unless
-#define bit_clear_unless(ptr, _clear, _test)	\
+#define bit_clear_unless(ptr, clear, test)	\
 ({								\
-	const typeof(*ptr) clear = (_clear), test = (_test);	\
-	typeof(*ptr) old, new;					\
+	const typeof(*(ptr)) clear__ = (clear), test__ = (test);\
+	typeof(*(ptr)) old__, new__;				\
 								\
 	do {							\
-		old = READ_ONCE(*ptr);			\
-		new = old & ~clear;				\
-	} while (!(old & test) &&				\
-		 cmpxchg(ptr, old, new) != old);		\
+		old__ = READ_ONCE(*(ptr));			\
+		new__ = old__ & ~clear__;			\
+	} while (!(old__ & test__) &&				\
+		 cmpxchg(ptr, old__, new__) != old__);		\
 								\
-	!(old & test);						\
+	!(old__ & test__);					\
 })
 #endif
 

include/uapi/linux/fuse.h

@@ -116,6 +116,12 @@
  *
  *  7.27
  *  - add FUSE_ABORT_ERROR
+ *
+ *  7.28
+ *  - add FUSE_COPY_FILE_RANGE
+ *  - add FOPEN_CACHE_DIR
+ *  - add FUSE_MAX_PAGES, add max_pages to init_out
+ *  - add FUSE_CACHE_SYMLINKS
  */
 
 #ifndef _LINUX_FUSE_H
@@ -151,7 +157,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 27
+#define FUSE_KERNEL_MINOR_VERSION 28
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -219,10 +225,12 @@ struct fuse_file_lock {
  * FOPEN_DIRECT_IO: bypass page cache for this open file
  * FOPEN_KEEP_CACHE: don't invalidate the data cache on open
  * FOPEN_NONSEEKABLE: the file is not seekable
+ * FOPEN_CACHE_DIR: allow caching this directory
  */
 #define FOPEN_DIRECT_IO		(1 << 0)
 #define FOPEN_KEEP_CACHE	(1 << 1)
 #define FOPEN_NONSEEKABLE	(1 << 2)
+#define FOPEN_CACHE_DIR		(1 << 3)
 
 /**
  * INIT request/reply flags
@@ -249,6 +257,8 @@ struct fuse_file_lock {
  * FUSE_HANDLE_KILLPRIV: fs handles killing suid/sgid/cap on write/chown/trunc
  * FUSE_POSIX_ACL: filesystem supports posix acls
  * FUSE_ABORT_ERROR: reading the device after abort returns ECONNABORTED
+ * FUSE_MAX_PAGES: init_out.max_pages contains the max number of req pages
+ * FUSE_CACHE_SYMLINKS: cache READLINK responses
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -272,6 +282,8 @@ struct fuse_file_lock {
 #define FUSE_HANDLE_KILLPRIV	(1 << 19)
 #define FUSE_POSIX_ACL		(1 << 20)
 #define FUSE_ABORT_ERROR	(1 << 21)
+#define FUSE_MAX_PAGES		(1 << 22)
+#define FUSE_CACHE_SYMLINKS	(1 << 23)
 
 /**
  * CUSE INIT request/reply flags
@@ -381,6 +393,7 @@ enum fuse_opcode {
 	FUSE_READDIRPLUS	= 44,
 	FUSE_RENAME2		= 45,
 	FUSE_LSEEK		= 46,
+	FUSE_COPY_FILE_RANGE	= 47,
 
 	/* CUSE specific operations */
 	CUSE_INIT		= 4096,
@@ -610,7 +623,9 @@ struct fuse_init_out {
 	uint16_t	congestion_threshold;
 	uint32_t	max_write;
 	uint32_t	time_gran;
-	uint32_t	unused[9];
+	uint16_t	max_pages;
+	uint16_t	padding;
+	uint32_t	unused[8];
 };
 
 #define CUSE_INIT_INFO_MAX 4096
@@ -792,4 +807,14 @@ struct fuse_lseek_out {
 	uint64_t	offset;
 };
 
+struct fuse_copy_file_range_in {
+	uint64_t	fh_in;
+	uint64_t	off_in;
+	uint64_t	nodeid_out;
+	uint64_t	fh_out;
+	uint64_t	off_out;
+	uint64_t	len;
+	uint64_t	flags;
+};
+
 #endif /* _LINUX_FUSE_H */