path: root/fs/fuse/inode.c

/*
  FUSE: Filesystem in Userspace
  Copyright (C) 2001-2008  Miklos Szeredi <miklos@szeredi.hu>

  This program can be distributed under the terms of the GNU GPL.
  See the file COPYING.
*/

#include "fuse_i.h"

#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include <linux/statfs.h>
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/exportfs.h>
#include <linux/posix_acl.h>
#include <linux/pid_namespace.h>

MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Filesystem in Userspace");
MODULE_LICENSE("GPL");

static struct kmem_cache *fuse_inode_cachep;
struct list_head fuse_conn_list;
DEFINE_MUTEX(fuse_mutex);

static int set_global_limit(const char *val, const struct kernel_param *kp);

unsigned max_user_bgreq;
module_param_call(max_user_bgreq, set_global_limit, param_get_uint,
		  &max_user_bgreq, 0644);
__MODULE_PARM_TYPE(max_user_bgreq, "uint");
MODULE_PARM_DESC(max_user_bgreq,
 "Global limit for the maximum number of backgrounded requests an "
 "unprivileged user can set");

unsigned max_user_congthresh;
module_param_call(max_user_congthresh, set_global_limit, param_get_uint,
		  &max_user_congthresh, 0644);
__MODULE_PARM_TYPE(max_user_congthresh, "uint");
MODULE_PARM_DESC(max_user_congthresh,
 "Global limit for the maximum congestion threshold an "
 "unprivileged user can set");

#define FUSE_SUPER_MAGIC 0x65735546

#define FUSE_DEFAULT_BLKSIZE 512

/** Maximum number of outstanding background requests */
#define FUSE_DEFAULT_MAX_BACKGROUND 12

/** Congestion starts at 75% of maximum */
#define FUSE_DEFAULT_CONGESTION_THRESHOLD (FUSE_DEFAULT_MAX_BACKGROUND * 3 / 4)

#ifdef CONFIG_BLOCK
static struct file_system_type fuseblk_fs_type;
#endif

struct fuse_forget_link *fuse_alloc_forget(void)
{
	return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT);
}

static struct inode *fuse_alloc_inode(struct super_block *sb)
{
	struct fuse_inode *fi;

	fi = kmem_cache_alloc(fuse_inode_cachep, GFP_KERNEL);
	if (!fi)
		return NULL;

	fi->i_time = 0;
	fi->inval_mask = 0;
	fi->nodeid = 0;
	fi->nlookup = 0;
	fi->attr_version = 0;
	fi->orig_ino = 0;
	fi->state = 0;
	mutex_init(&fi->mutex);
	spin_lock_init(&fi->lock);
	fi->forget = fuse_alloc_forget();
	if (!fi->forget) {
		kmem_cache_free(fuse_inode_cachep, fi);
		return NULL;
	}

	return &fi->inode;
}

static void fuse_free_inode(struct inode *inode)
{
	struct fuse_inode *fi = get_fuse_inode(inode);

	mutex_destroy(&fi->mutex);
	kfree(fi->forget);
	kmem_cache_free(fuse_inode_cachep, fi);
}

static void fuse_evict_inode(struct inode *inode)
{
	struct fuse_inode *fi = get_fuse_inode(inode);

	truncate_inode_pages_final(&inode->i_data);
	clear_inode(inode);
	if (inode->i_sb->s_flags & SB_ACTIVE) {
		struct fuse_conn *fc = get_fuse_conn(inode);
		fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup);
		fi->forget = NULL;
	}
	if (S_ISREG(inode->i_mode) && !is_bad_inode(inode)) {
		WARN_ON(!list_empty(&fi->write_files));
		WARN_ON(!list_empty(&fi->queued_writes));
	}
}

static int fuse_reconfigure(struct fs_context *fc)
{
	struct super_block *sb = fc->root->d_sb;

	sync_filesystem(sb);
	if (fc->sb_flags & SB_MANDLOCK)
		return -EINVAL;

	return 0;
}

/*
 * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
 * so that it will fit.
 */
static ino_t fuse_squash_ino(u64 ino64)
{
	ino_t ino = (ino_t) ino64;
	if (sizeof(ino_t) < sizeof(u64))
		ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8;
	return ino;
}

void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
				   u64 attr_valid)
{
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_inode *fi = get_fuse_inode(inode);

	lockdep_assert_held(&fi->lock);

	fi->attr_version = atomic64_inc_return(&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);
	set_nlink(inode, attr->nlink);
	inode->i_uid     = make_kuid(fc->user_ns, attr->uid);
	inode->i_gid     = make_kgid(fc->user_ns, attr->gid);
	inode->i_blocks  = attr->blocks;
	inode->i_atime.tv_sec   = attr->atime;
	inode->i_atime.tv_nsec  = attr->atimensec;
	/* mtime from server may be stale due to local buffered write */
	if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) {
		inode->i_mtime.tv_sec   = attr->mtime;
		inode->i_mtime.tv_nsec  = attr->mtimensec;
		inode->i_ctime.tv_sec   = attr->ctime;
		inode->i_ctime.tv_nsec  = attr->ctimensec;
	}

	if (attr->blksize != 0)
		inode->i_blkbits = ilog2(attr->blksize);
	else
		inode->i_blkbits = inode->i_sb->s_blocksize_bits;

	/*
	 * Don't set the sticky bit in i_mode, unless we want the VFS
	 * to check permissions.  This prevents failures due to the
	 * check in may_delete().
	 */
	fi->orig_i_mode = inode->i_mode;
	if (!fc->default_permissions)
		inode->i_mode &= ~S_ISVTX;

	fi->orig_ino = attr->ino;
}

void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
			    u64 attr_valid, u64 attr_version)
{
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_inode *fi = get_fuse_inode(inode);
	bool is_wb = fc->writeback_cache;
	loff_t oldsize;
	struct timespec64 old_mtime;

	spin_lock(&fi->lock);
	if ((attr_version != 0 && fi->attr_version > attr_version) ||
	    test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) {
		spin_unlock(&fi->lock);
		return;
	}

	old_mtime = inode->i_mtime;
	fuse_change_attributes_common(inode, attr, attr_valid);

	oldsize = inode->i_size;
	/*
	 * In case of writeback_cache enabled, the cached writes beyond EOF
	 * extend local i_size without keeping userspace server in sync. So,
	 * attr->size coming from server can be stale. We cannot trust it.
	 */
	if (!is_wb || !S_ISREG(inode->i_mode))
		i_size_write(inode, attr->size);
	spin_unlock(&fi->lock);

	if (!is_wb && S_ISREG(inode->i_mode)) {
		bool inval = false;

		if (oldsize != attr->size) {
			truncate_pagecache(inode, attr->size);
			if (!fc->explicit_inval_data)
				inval = true;
		} else if (fc->auto_inval_data) {
			struct timespec64 new_mtime = {
				.tv_sec = attr->mtime,
				.tv_nsec = attr->mtimensec,
			};

			/*
			 * Auto inval mode also checks and invalidates if mtime
			 * has changed.
			 */
			if (!timespec64_equal(&old_mtime, &new_mtime))
				inval = true;
		}

		if (inval)
			invalidate_inode_pages2(inode->i_mapping);
	}
}

static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
{
	inode->i_mode = attr->mode & S_IFMT;
	inode->i_size = attr->size;
	inode->i_mtime.tv_sec  = attr->mtime;
	inode->i_mtime.tv_nsec = attr->mtimensec;
	inode->i_ctime.tv_sec  = attr->ctime;
	inode->i_ctime.tv_nsec = attr->ctimensec;
	if (S_ISREG(inode->i_mode)) {
		fuse_init_common(inode);
		fuse_init_file_inode(inode);
	} else if (S_ISDIR(inode->i_mode))
		fuse_init_dir(inode);
	else if (S_ISLNK(inode->i_mode))
		fuse_init_symlink(inode);
	else if (S_ISCHR(inode->i_mode) || S_ISBLK(ino