#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/module.h>
+#include <linux/moduleparam.h>
#include <linux/parser.h>
#include <linux/statfs.h>
#include <linux/random.h>
struct list_head fuse_conn_list;
DEFINE_MUTEX(fuse_mutex);
+static int set_global_limit(const char *val, 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)
+
struct fuse_mount_data {
int fd;
unsigned rootmode;
return 0;
}
-void fuse_truncate(struct address_space *mapping, loff_t offset)
-{
- /* See vmtruncate() */
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- truncate_inode_pages(mapping, offset);
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
-}
-
void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid)
{
spin_unlock(&fc->lock);
if (S_ISREG(inode->i_mode) && oldsize != attr->size) {
- if (attr->size < oldsize)
- fuse_truncate(inode->i_mapping, attr->size);
+ truncate_pagecache(inode, oldsize, attr->size);
invalidate_inode_pages2(inode->i_mapping);
}
}
BUG();
}
-static int fuse_inode_eq(struct inode *inode, void *_nodeidp)
+int fuse_inode_eq(struct inode *inode, void *_nodeidp)
{
u64 nodeid = *(u64 *) _nodeidp;
if (get_node_id(inode) == nodeid)
return inode;
}
+int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
+ loff_t offset, loff_t len)
+{
+ struct inode *inode;
+ pgoff_t pg_start;
+ pgoff_t pg_end;
+
+ inode = ilookup5(sb, nodeid, fuse_inode_eq, &nodeid);
+ if (!inode)
+ return -ENOENT;
+
+ fuse_invalidate_attr(inode);
+ if (offset >= 0) {
+ pg_start = offset >> PAGE_CACHE_SHIFT;
+ if (len <= 0)
+ pg_end = -1;
+ else
+ pg_end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+ invalidate_inode_pages2_range(inode->i_mapping,
+ pg_start, pg_end);
+ }
+ iput(inode);
+ return 0;
+}
+
static void fuse_umount_begin(struct super_block *sb)
{
fuse_abort_conn(get_fuse_conn_super(sb));
}
}
-static void fuse_put_super(struct super_block *sb)
+static void fuse_bdi_destroy(struct fuse_conn *fc)
{
- struct fuse_conn *fc = get_fuse_conn_super(sb);
+ if (fc->bdi_initialized)
+ bdi_destroy(&fc->bdi);
+}
- fuse_send_destroy(fc);
+void fuse_conn_kill(struct fuse_conn *fc)
+{
spin_lock(&fc->lock);
fc->connected = 0;
fc->blocked = 0;
list_del(&fc->entry);
fuse_ctl_remove_conn(fc);
mutex_unlock(&fuse_mutex);
- bdi_destroy(&fc->bdi);
+ fuse_bdi_destroy(fc);
+}
+EXPORT_SYMBOL_GPL(fuse_conn_kill);
+
+static void fuse_put_super(struct super_block *sb)
+{
+ struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+ fuse_send_destroy(fc);
+ fuse_conn_kill(fc);
fuse_conn_put(fc);
}
return 0;
}
-int fuse_conn_init(struct fuse_conn *fc, struct super_block *sb)
+void fuse_conn_init(struct fuse_conn *fc)
{
- int err;
-
memset(fc, 0, sizeof(*fc));
spin_lock_init(&fc->lock);
mutex_init(&fc->inst_mutex);
+ init_rwsem(&fc->killsb);
atomic_set(&fc->count, 1);
init_waitqueue_head(&fc->waitq);
init_waitqueue_head(&fc->blocked_waitq);
INIT_LIST_HEAD(&fc->bg_queue);
INIT_LIST_HEAD(&fc->entry);
atomic_set(&fc->num_waiting, 0);
- fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
- fc->bdi.unplug_io_fn = default_unplug_io_fn;
- /* fuse does it's own writeback accounting */
- fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB;
+ fc->max_background = FUSE_DEFAULT_MAX_BACKGROUND;
+ fc->congestion_threshold = FUSE_DEFAULT_CONGESTION_THRESHOLD;
fc->khctr = 0;
fc->polled_files = RB_ROOT;
- fc->dev = sb->s_dev;
- err = bdi_init(&fc->bdi);
- if (err)
- goto error_mutex_destroy;
- if (sb->s_bdev) {
- err = bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk",
- MAJOR(fc->dev), MINOR(fc->dev));
- } else {
- err = bdi_register_dev(&fc->bdi, fc->dev);
- }
- if (err)
- goto error_bdi_destroy;
- /*
- * For a single fuse filesystem use max 1% of dirty +
- * writeback threshold.
- *
- * This gives about 1M of write buffer for memory maps on a
- * machine with 1G and 10% dirty_ratio, which should be more
- * than enough.
- *
- * Privileged users can raise it by writing to
- *
- * /sys/class/bdi/<bdi>/max_ratio
- */
- bdi_set_max_ratio(&fc->bdi, 1);
fc->reqctr = 0;
fc->blocked = 1;
fc->attr_version = 1;
get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
-
- return 0;
-
- error_bdi_destroy:
- bdi_destroy(&fc->bdi);
- error_mutex_destroy:
- mutex_destroy(&fc->inst_mutex);
- return err;
}
EXPORT_SYMBOL_GPL(fuse_conn_init);
fc->release(fc);
}
}
+EXPORT_SYMBOL_GPL(fuse_conn_put);
struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
{
atomic_inc(&fc->count);
return fc;
}
+EXPORT_SYMBOL_GPL(fuse_conn_get);
static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode)
{
.show_options = fuse_show_options,
};
+static void sanitize_global_limit(unsigned *limit)
+{
+ if (*limit == 0)
+ *limit = ((num_physpages << PAGE_SHIFT) >> 13) /
+ sizeof(struct fuse_req);
+
+ if (*limit >= 1 << 16)
+ *limit = (1 << 16) - 1;
+}
+
+static int set_global_limit(const char *val, struct kernel_param *kp)
+{
+ int rv;
+
+ rv = param_set_uint(val, kp);
+ if (rv)
+ return rv;
+
+ sanitize_global_limit((unsigned *)kp->arg);
+
+ return 0;
+}
+
+static void process_init_limits(struct fuse_conn *fc, struct fuse_init_out *arg)
+{
+ int cap_sys_admin = capable(CAP_SYS_ADMIN);
+
+ if (arg->minor < 13)
+ return;
+
+ sanitize_global_limit(&max_user_bgreq);
+ sanitize_global_limit(&max_user_congthresh);
+
+ if (arg->max_background) {
+ fc->max_background = arg->max_background;
+
+ if (!cap_sys_admin && fc->max_background > max_user_bgreq)
+ fc->max_background = max_user_bgreq;
+ }
+ if (arg->congestion_threshold) {
+ fc->congestion_threshold = arg->congestion_threshold;
+
+ if (!cap_sys_admin &&
+ fc->congestion_threshold > max_user_congthresh)
+ fc->congestion_threshold = max_user_congthresh;
+ }
+}
+
static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
{
struct fuse_init_out *arg = &req->misc.init_out;
else {
unsigned long ra_pages;
+ process_init_limits(fc, arg);
+
if (arg->minor >= 6) {
ra_pages = arg->max_readahead / PAGE_CACHE_SIZE;
if (arg->flags & FUSE_ASYNC_READ)
}
if (arg->flags & FUSE_BIG_WRITES)
fc->big_writes = 1;
+ if (arg->flags & FUSE_DONT_MASK)
+ fc->dont_mask = 1;
} else {
ra_pages = fc->max_read / PAGE_CACHE_SIZE;
fc->no_lock = 1;
arg->minor = FUSE_KERNEL_MINOR_VERSION;
arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
- FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES;
+ FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK;
req->in.h.opcode = FUSE_INIT;
req->in.numargs = 1;
req->in.args[0].size = sizeof(*arg);
kfree(fc);
}
+static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
+{
+ int err;
+
+ fc->bdi.name = "fuse";
+ fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+ fc->bdi.unplug_io_fn = default_unplug_io_fn;
+ /* fuse does it's own writeback accounting */
+ fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB;
+
+ err = bdi_init(&fc->bdi);
+ if (err)
+ return err;
+
+ fc->bdi_initialized = 1;
+
+ if (sb->s_bdev) {
+ err = bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk",
+ MAJOR(fc->dev), MINOR(fc->dev));
+ } else {
+ err = bdi_register_dev(&fc->bdi, fc->dev);
+ }
+
+ if (err)
+ return err;
+
+ /*
+ * For a single fuse filesystem use max 1% of dirty +
+ * writeback threshold.
+ *
+ * This gives about 1M of write buffer for memory maps on a
+ * machine with 1G and 10% dirty_ratio, which should be more
+ * than enough.
+ *
+ * Privileged users can raise it by writing to
+ *
+ * /sys/class/bdi/<bdi>/max_ratio
+ */
+ bdi_set_max_ratio(&fc->bdi, 1);
+
+ return 0;
+}
+
static int fuse_fill_super(struct super_block *sb, void *data, int silent)
{
struct fuse_conn *fc;
if (!fc)
goto err_fput;
- err = fuse_conn_init(fc, sb);
- if (err) {
- kfree(fc);
- goto err_fput;
- }
+ fuse_conn_init(fc);
+
+ fc->dev = sb->s_dev;
+ fc->sb = sb;
+ err = fuse_bdi_init(fc, sb);
+ if (err)
+ goto err_put_conn;
+
+ sb->s_bdi = &fc->bdi;
+
+ /* Handle umasking inside the fuse code */
+ if (sb->s_flags & MS_POSIXACL)
+ fc->dont_mask = 1;
+ sb->s_flags |= MS_POSIXACL;
fc->release = fuse_free_conn;
fc->flags = d.flags;
err_put_root:
dput(root_dentry);
err_put_conn:
- bdi_destroy(&fc->bdi);
+ fuse_bdi_destroy(fc);
fuse_conn_put(fc);
err_fput:
fput(file);
return get_sb_nodev(fs_type, flags, raw_data, fuse_fill_super, mnt);
}
+static void fuse_kill_sb_anon(struct super_block *sb)
+{
+ struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+ if (fc) {
+ down_write(&fc->killsb);
+ fc->sb = NULL;
+ up_write(&fc->killsb);
+ }
+
+ kill_anon_super(sb);
+}
+
static struct file_system_type fuse_fs_type = {
.owner = THIS_MODULE,
.name = "fuse",
.fs_flags = FS_HAS_SUBTYPE,
.get_sb = fuse_get_sb,
- .kill_sb = kill_anon_super,
+ .kill_sb = fuse_kill_sb_anon,
};
#ifdef CONFIG_BLOCK
mnt);
}
+static void fuse_kill_sb_blk(struct super_block *sb)
+{
+ struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+ if (fc) {
+ down_write(&fc->killsb);
+ fc->sb = NULL;
+ up_write(&fc->killsb);
+ }
+
+ kill_block_super(sb);
+}
+
static struct file_system_type fuseblk_fs_type = {
.owner = THIS_MODULE,
.name = "fuseblk",
.get_sb = fuse_get_sb_blk,
- .kill_sb = kill_block_super,
+ .kill_sb = fuse_kill_sb_blk,
.fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE,
};
if (res)
goto err_sysfs_cleanup;
+ sanitize_global_limit(&max_user_bgreq);
+ sanitize_global_limit(&max_user_congthresh);
+
return 0;
err_sysfs_cleanup:
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff