Merge tag 'fuse-update-5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse

Pull fuse update from Miklos Szeredi:
 "Add more caching controls for userspace filesystems to use, as well as
  bug fixes and cleanups"

* tag 'fuse-update-5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
  fuse: clean up fuse_alloc_inode
  fuse: Add ioctl flag for x32 compat ioctl
  fuse: Convert fusectl to use the new mount API
  fuse: fix changelog entry for protocol 7.9
  fuse: fix changelog entry for protocol 7.12
  fuse: document fuse_fsync_in.fsync_flags
  fuse: Add FOPEN_STREAM to use stream_open()
  fuse: require /dev/fuse reads to have enough buffer capacity
  fuse: retrieve: cap requested size to negotiated max_write
  fuse: allow filesystems to have precise control over data cache
  fuse: convert printk -> pr_*
  fuse: honor RLIMIT_FSIZE in fuse_file_fallocate
  fuse: fix writepages on 32bit

7 files changed, 92 insertions, 31 deletions

diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index fe80bea4ad89..14ce1e47f980 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -10,6 +10,7 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/fs_context.h>
 
 #define FUSE_CTL_SUPER_MAGIC 0x65735543
 
@@ -317,7 +318,7 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc)
         drop_nlink(d_inode(fuse_control_sb->s_root));
 }
 
-static int fuse_ctl_fill_super(struct super_block *sb, void *data, int silent)
+static int fuse_ctl_fill_super(struct super_block *sb, struct fs_context *fctx)
 {
         static const struct tree_descr empty_descr = {""};
         struct fuse_conn *fc;
@@ -343,10 +344,19 @@ static int fuse_ctl_fill_super(struct super_block *sb, void *data, int silent)
         return 0;
 }
 
-static struct dentry *fuse_ctl_mount(struct file_system_type *fs_type,
-                        int flags, const char *dev_name, void *raw_data)
+static int fuse_ctl_get_tree(struct fs_context *fc)
 {
-        return mount_single(fs_type, flags, raw_data, fuse_ctl_fill_super);
+        return vfs_get_super(fc, vfs_get_single_super, fuse_ctl_fill_super);
+}
+
+static const struct fs_context_operations fuse_ctl_context_ops = {
+        .get_tree       = fuse_ctl_get_tree,
+};
+
+static int fuse_ctl_init_fs_context(struct fs_context *fc)
+{
+        fc->ops = &fuse_ctl_context_ops;
+        return 0;
 }
 
 static void fuse_ctl_kill_sb(struct super_block *sb)
@@ -365,7 +375,7 @@ static void fuse_ctl_kill_sb(struct super_block *sb)
 static struct file_system_type fuse_ctl_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "fusectl",
-        .mount          = fuse_ctl_mount,
+        .init_fs_context = fuse_ctl_init_fs_context,
         .kill_sb        = fuse_ctl_kill_sb,
 };
 MODULE_ALIAS_FS("fusectl");
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 55a26f351467..4b41df1d4642 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -33,6 +33,8 @@
  * closed.
  */
 
+#define pr_fmt(fmt) "CUSE: " fmt
+
 #include <linux/fuse.h>
 #include <linux/cdev.h>
 #include <linux/device.h>
@@ -225,7 +227,7 @@ static int cuse_parse_one(char **pp, char *end, char **keyp, char **valp)
                 return 0;
 
         if (end[-1] != '\0') {
-                printk(KERN_ERR "CUSE: info not properly terminated\n");
+                pr_err("info not properly terminated\n");
                 return -EINVAL;
         }
 
@@ -242,7 +244,7 @@ static int cuse_parse_one(char **pp, char *end, char **keyp, char **valp)
                 key = strstrip(key);
 
         if (!strlen(key)) {
-                printk(KERN_ERR "CUSE: zero length info key specified\n");
+                pr_err("zero length info key specified\n");
                 return -EINVAL;
         }
 
@@ -282,12 +284,11 @@ static int cuse_parse_devinfo(char *p, size_t len, struct cuse_devinfo *devinfo)
                 if (strcmp(key, "DEVNAME") == 0)
                         devinfo->name = val;
                 else
-                        printk(KERN_WARNING "CUSE: unknown device info \"%s\"\n",
-                               key);
+                        pr_warn("unknown device info \"%s\"\n", key);
         }
 
         if (!devinfo->name || !strlen(devinfo->name)) {
-                printk(KERN_ERR "CUSE: DEVNAME unspecified\n");
+                pr_err("DEVNAME unspecified\n");
                 return -EINVAL;
         }
 
@@ -341,7 +342,7 @@ static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
         else
                 rc = register_chrdev_region(devt, 1, devinfo.name);
         if (rc) {
-                printk(KERN_ERR "CUSE: failed to register chrdev region\n");
+                pr_err("failed to register chrdev region\n");
                 goto err;
         }
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 9971a35cf1ef..24ea19cfe07e 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -906,8 +906,8 @@ static int fuse_check_page(struct page *page)
                1 << PG_lru |
                1 << PG_active |
                1 << PG_reclaim))) {
-                printk(KERN_WARNING "fuse: trying to steal weird page\n");
-                printk(KERN_WARNING "  page=%p index=%li flags=%08lx, count=%i, mapcount=%i, mapping=%p\n", page, page->index, page->flags, page_count(page), page_mapcount(page), page->mapping);
+                pr_warn("trying to steal weird page\n");
+                pr_warn("  page=%p index=%li flags=%08lx, count=%i, mapcount=%i, mapping=%p\n", page, page->index, page->flags, page_count(page), page_mapcount(page), page->mapping);
                 return 1;
         }
         return 0;
@@ -1317,6 +1317,16 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
         unsigned reqsize;
         unsigned int hash;
 
+        /*
+         * Require sane minimum read buffer - that has capacity for fixed part
+         * of any request header + negotated max_write room for data. If the
+         * requirement is not satisfied return EINVAL to the filesystem server
+         * to indicate that it is not following FUSE server/client contract.
+         * Don't dequeue / abort any request.
+         */
+        if (nbytes < max_t(size_t, FUSE_MIN_READ_BUFFER, 4096 + fc->max_write))
+                return -EINVAL;
+
  restart:
         spin_lock(&fiq->waitq.lock);
         err = -EAGAIN;
@@ -1749,7 +1759,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
         offset = outarg->offset & ~PAGE_MASK;
         file_size = i_size_read(inode);
 
-        num = outarg->size;
+        num = min(outarg->size, fc->max_write);
         if (outarg->offset > file_size)
                 num = 0;
         else if (outarg->offset + num > file_size)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 06096b60f1df..3959f08279e6 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -178,7 +178,9 @@ void fuse_finish_open(struct inode *inode, struct file *file)
 
         if (!(ff->open_flags & FOPEN_KEEP_CACHE))
                 invalidate_inode_pages2(inode->i_mapping);
-        if (ff->open_flags & FOPEN_NONSEEKABLE)
+        if (ff->open_flags & FOPEN_STREAM)
+                stream_open(inode, file);
+        else if (ff->open_flags & FOPEN_NONSEEKABLE)
                 nonseekable_open(inode, file);
         if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) {
                 struct fuse_inode *fi = get_fuse_inode(inode);
@@ -462,7 +464,7 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
 
         memset(&inarg, 0, sizeof(inarg));
         inarg.fh = ff->fh;
-        inarg.fsync_flags = datasync ? 1 : 0;
+        inarg.fsync_flags = datasync ? FUSE_FSYNC_FDATASYNC : 0;
         args.in.h.opcode = opcode;
         args.in.h.nodeid = get_node_id(inode);
         args.in.numargs = 1;
@@ -1586,7 +1588,7 @@ __acquires(fi->lock)
 {
         struct fuse_conn *fc = get_fuse_conn(inode);
         struct fuse_inode *fi = get_fuse_inode(inode);
-        size_t crop = i_size_read(inode);
+        loff_t crop = i_size_read(inode);
         struct fuse_req *req;
 
         while (fi->writectr >= 0 && !list_empty(&fi->queued_writes)) {
@@ -2576,8 +2578,13 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 #if BITS_PER_LONG == 32
         inarg.flags |= FUSE_IOCTL_32BIT;
 #else
-        if (flags & FUSE_IOCTL_COMPAT)
+        if (flags & FUSE_IOCTL_COMPAT) {
                 inarg.flags |= FUSE_IOCTL_32BIT;
+#ifdef CONFIG_X86_X32
+                if (in_x32_syscall())
+                        inarg.flags |= FUSE_IOCTL_COMPAT_X32;
+#endif
+        }
 #endif
 
         /* assume all the iovs returned by client always fits in a page */
@@ -3044,6 +3051,13 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
                 }
         }
 
+        if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+            offset + length > i_size_read(inode)) {
+                err = inode_newsize_ok(inode, offset + length);
+                if (err)
+                        return err;
+        }
+
         if (!(mode & FALLOC_FL_KEEP_SIZE))
                 set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
 
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 0920c0c032a0..24dbca777775 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -9,6 +9,10 @@
 #ifndef _FS_FUSE_I_H
 #define _FS_FUSE_I_H
 
+#ifndef pr_fmt
+# define pr_fmt(fmt) "fuse: " fmt
+#endif
+
 #include <linux/fuse.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
@@ -690,6 +694,9 @@ struct fuse_conn {
         /** Use enhanced/automatic page cache invalidation. */
         unsigned auto_inval_data:1;
 
+        /** Filesystem is fully reponsible for page cache invalidation. */
+        unsigned explicit_inval_data:1;
+
         /** Does the filesystem support readdirplus? */
         unsigned do_readdirplus:1;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f485d09d14df..4bb885b0f032 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -81,14 +81,12 @@ struct fuse_forget_link *fuse_alloc_forget(void)
 
 static struct inode *fuse_alloc_inode(struct super_block *sb)
 {
-        struct inode *inode;
         struct fuse_inode *fi;
 
-        inode = kmem_cache_alloc(fuse_inode_cachep, GFP_KERNEL);
-        if (!inode)
+        fi = kmem_cache_alloc(fuse_inode_cachep, GFP_KERNEL);
+        if (!fi)
                 return NULL;
 
-        fi = get_fuse_inode(inode);
         fi->i_time = 0;
         fi->inval_mask = 0;
         fi->nodeid = 0;
@@ -100,11 +98,11 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
         spin_lock_init(&fi->lock);
         fi->forget = fuse_alloc_forget();
         if (!fi->forget) {
-                kmem_cache_free(fuse_inode_cachep, inode);
+                kmem_cache_free(fuse_inode_cachep, fi);
                 return NULL;
         }
 
-        return inode;
+        return &fi->inode;
 }
 
 static void fuse_free_inode(struct inode *inode)
@@ -233,7 +231,8 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 
                 if (oldsize != attr->size) {
                         truncate_pagecache(inode, attr->size);
-                        inval = true;
+                        if (!fc->explicit_inval_data)
+                                inval = true;
                 } else if (fc->auto_inval_data) {
                         struct timespec64 new_mtime = {
                                 .tv_sec = attr->mtime,
@@ -908,6 +907,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
                                 fc->dont_mask = 1;
                         if (arg->flags & FUSE_AUTO_INVAL_DATA)
                                 fc->auto_inval_data = 1;
+                        else if (arg->flags & FUSE_EXPLICIT_INVAL_DATA)
+                                fc->explicit_inval_data = 1;
                         if (arg->flags & FUSE_DO_READDIRPLUS) {
                                 fc->do_readdirplus = 1;
                                 if (arg->flags & FUSE_READDIRPLUS_AUTO)
@@ -969,7 +970,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
                 FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT |
                 FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL |
                 FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS |
-                FUSE_NO_OPENDIR_SUPPORT;
+                FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA;
         req->in.h.opcode = FUSE_INIT;
         req->in.numargs = 1;
         req->in.args[0].size = sizeof(*arg);
@@ -1393,8 +1394,8 @@ static int __init fuse_init(void)
 {
         int res;
 
-        printk(KERN_INFO "fuse init (API version %i.%i)\n",
-               FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION);
+        pr_info("init (API version %i.%i)\n",
+                FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION);
 
         INIT_LIST_HEAD(&fuse_conn_list);
         res = fuse_fs_init();
@@ -1430,7 +1431,7 @@ static int __init fuse_init(void)
 
 static void __exit fuse_exit(void)
 {
-        printk(KERN_DEBUG "fuse exit\n");
+        pr_debug("exit\n");
 
         fuse_ctl_cleanup();
         fuse_sysfs_cleanup();
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 2ac598614a8f..19fb55e3c73e 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -44,6 +44,7 @@
  *  - add lock_owner field to fuse_setattr_in, fuse_read_in and fuse_write_in
  *  - add blksize field to fuse_attr
  *  - add file flags field to fuse_read_in and fuse_write_in
+ *  - Add ATIME_NOW and MTIME_NOW flags to fuse_setattr_in
  *
  * 7.10
  *  - add nonseekable open flag
@@ -54,7 +55,7 @@
  *  - add POLL message and NOTIFY_POLL notification
  *
  * 7.12
- *  - add umask flag to input argument of open, mknod and mkdir
+ *  - add umask flag to input argument of create, mknod and mkdir
  *  - add notification messages for invalidation of inodes and
  *    directory entries
  *
@@ -125,6 +126,10 @@
  *
  *  7.29
  *  - add FUSE_NO_OPENDIR_SUPPORT flag
+ *
+ *  7.30
+ *  - add FUSE_EXPLICIT_INVAL_DATA
+ *  - add FUSE_IOCTL_COMPAT_X32
  */
 
 #ifndef _LINUX_FUSE_H
@@ -160,7 +165,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 29
+#define FUSE_KERNEL_MINOR_VERSION 30
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -229,11 +234,13 @@ struct fuse_file_lock {
  * 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
+ * FOPEN_STREAM: the file is stream-like (no file position at all)
  */
 #define FOPEN_DIRECT_IO         (1 << 0)
 #define FOPEN_KEEP_CACHE        (1 << 1)
 #define FOPEN_NONSEEKABLE       (1 << 2)
 #define FOPEN_CACHE_DIR         (1 << 3)
+#define FOPEN_STREAM            (1 << 4)
 
 /**
  * INIT request/reply flags
@@ -263,6 +270,7 @@ struct fuse_file_lock {
  * FUSE_MAX_PAGES: init_out.max_pages contains the max number of req pages
  * FUSE_CACHE_SYMLINKS: cache READLINK responses
  * FUSE_NO_OPENDIR_SUPPORT: kernel supports zero-message opendir
+ * FUSE_EXPLICIT_INVAL_DATA: only invalidate cached pages on explicit request
  */
 #define FUSE_ASYNC_READ         (1 << 0)
 #define FUSE_POSIX_LOCKS        (1 << 1)
@@ -289,6 +297,7 @@ struct fuse_file_lock {
 #define FUSE_MAX_PAGES          (1 << 22)
 #define FUSE_CACHE_SYMLINKS     (1 << 23)
 #define FUSE_NO_OPENDIR_SUPPORT (1 << 24)
+#define FUSE_EXPLICIT_INVAL_DATA (1 << 25)
 
 /**
  * CUSE INIT request/reply flags
@@ -335,6 +344,7 @@ struct fuse_file_lock {
  * FUSE_IOCTL_RETRY: retry with new iovecs
  * FUSE_IOCTL_32BIT: 32bit ioctl
  * FUSE_IOCTL_DIR: is a directory
+ * FUSE_IOCTL_COMPAT_X32: x32 compat ioctl on 64bit machine (64bit time_t)
  *
  * FUSE_IOCTL_MAX_IOV: maximum of in_iovecs + out_iovecs
  */
@@ -343,6 +353,7 @@ struct fuse_file_lock {
 #define FUSE_IOCTL_RETRY        (1 << 2)
 #define FUSE_IOCTL_32BIT        (1 << 3)
 #define FUSE_IOCTL_DIR          (1 << 4)
+#define FUSE_IOCTL_COMPAT_X32   (1 << 5)
 
 #define FUSE_IOCTL_MAX_IOV      256
 
@@ -353,6 +364,13 @@ struct fuse_file_lock {
  */
 #define FUSE_POLL_SCHEDULE_NOTIFY (1 << 0)
 
+/**
+ * Fsync flags
+ *
+ * FUSE_FSYNC_FDATASYNC: Sync data only, not metadata
+ */
+#define FUSE_FSYNC_FDATASYNC    (1 << 0)
+
 enum fuse_opcode {
         FUSE_LOOKUP             = 1,
         FUSE_FORGET             = 2,  /* no reply */