* 'hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jdelvare/staging:
hwmon: (adm1026) Allow 1 as a valid divider value
hwmon: (adm1026) Fix setting fan_div
hwmon: (it87) Fix manual fan speed control on IT8721F
sector_t (*bmap)(struct address_space *, sector_t);
int (*invalidatepage) (struct page *, unsigned long);
int (*releasepage) (struct page *, int);
+ void (*freepage)(struct page *);
int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
loff_t offset, unsigned long nr_segs);
int (*launder_page) (struct page *);
locking rules:
- All except set_page_dirty may block
+ All except set_page_dirty and freepage may block
BKL PageLocked(page) i_mutex
writepage: no yes, unlocks (see below)
bmap: no
invalidatepage: no yes
releasepage: no yes
+freepage: no yes
direct_IO: no
launder_page: no yes
indicate that the buffers are (or may be) freeable. If ->releasepage is zero,
the kernel assumes that the fs has no private interest in the buffers.
+ ->freepage() is called when the kernel is done dropping the page
+from the page cache.
+
->launder_page() may be called prior to releasing a page if
it is still found to be dirty. It returns zero if the page was successfully
cleaned, or an error value if not. Note that in order to prevent the page
sector_t (*bmap)(struct address_space *, sector_t);
int (*invalidatepage) (struct page *, unsigned long);
int (*releasepage) (struct page *, int);
+ void (*freepage)(struct page *);
ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
loff_t offset, unsigned long nr_segs);
struct page* (*get_xip_page)(struct address_space *, sector_t,
need to ensure this. Possibly it can clear the PageUptodate
bit if it cannot free private data yet.
+ freepage: freepage is called once the page is no longer visible in
+ the page cache in order to allow the cleanup of any private
+ data. Since it may be called by the memory reclaimer, it
+ should not assume that the original address_space mapping still
+ exists, and it should not block.
+
direct_IO: called by the generic read/write routines to perform
direct_IO - that is IO requests which bypass the page cache
and transfer data directly between the storage and the
__btree_submit_bio_done);
}
+#ifdef CONFIG_MIGRATION
static int btree_migratepage(struct address_space *mapping,
struct page *newpage, struct page *page)
{
if (page_has_private(page) &&
!try_to_release_page(page, GFP_KERNEL))
return -EAGAIN;
-#ifdef CONFIG_MIGRATION
return migrate_page(mapping, newpage, page);
-#else
- return -ENOSYS;
-#endif
}
+#endif
static int btree_writepage(struct page *page, struct writeback_control *wbc)
{
blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
blocksize, generation);
- BUG_ON(!root->node);
+ if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) {
+ free_extent_buffer(root->node);
+ return -EIO;
+ }
root->commit_root = btrfs_root_node(root);
return 0;
}
static int cache_block_group(struct btrfs_block_group_cache *cache,
struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
int load_cache_only)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
/*
* We can't do the read from on-disk cache during a commit since we need
- * to have the normal tree locking.
+ * to have the normal tree locking. Also if we are currently trying to
+ * allocate blocks for the tree root we can't do the fast caching since
+ * we likely hold important locks.
*/
- if (!trans->transaction->in_commit) {
+ if (!trans->transaction->in_commit &&
+ (root && root != root->fs_info->tree_root)) {
spin_lock(&cache->lock);
if (cache->cached != BTRFS_CACHE_NO) {
spin_unlock(&cache->lock);
struct btrfs_root *root = block_group->fs_info->tree_root;
struct inode *inode = NULL;
u64 alloc_hint = 0;
+ int dcs = BTRFS_DC_ERROR;
int num_pages = 0;
int retries = 0;
int ret = 0;
spin_lock(&block_group->lock);
if (block_group->cached != BTRFS_CACHE_FINISHED) {
+ /* We're not cached, don't bother trying to write stuff out */
+ dcs = BTRFS_DC_WRITTEN;
spin_unlock(&block_group->lock);
goto out_put;
}
ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, num_pages,
num_pages, num_pages,
&alloc_hint);
+ if (!ret)
+ dcs = BTRFS_DC_SETUP;
btrfs_free_reserved_data_space(inode, num_pages);
out_put:
iput(inode);
btrfs_release_path(root, path);
out:
spin_lock(&block_group->lock);
- if (ret)
- block_group->disk_cache_state = BTRFS_DC_ERROR;
- else
- block_group->disk_cache_state = BTRFS_DC_SETUP;
+ block_group->disk_cache_state = dcs;
spin_unlock(&block_group->lock);
return ret;
u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
{
- u64 num_devices = root->fs_info->fs_devices->rw_devices;
+ /*
+ * we add in the count of missing devices because we want
+ * to make sure that any RAID levels on a degraded FS
+ * continue to be honored.
+ */
+ u64 num_devices = root->fs_info->fs_devices->rw_devices +
+ root->fs_info->fs_devices->missing_devices;
if (num_devices == 1)
flags &= ~(BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID0);
* space back to the block group, otherwise we will leak space.
*/
if (!alloc && cache->cached == BTRFS_CACHE_NO)
- cache_block_group(cache, trans, 1);
+ cache_block_group(cache, trans, NULL, 1);
byte_in_group = bytenr - cache->key.objectid;
WARN_ON(byte_in_group > cache->key.offset);
btrfs_get_block_group(block_group);
search_start = block_group->key.objectid;
+ /*
+ * this can happen if we end up cycling through all the
+ * raid types, but we want to make sure we only allocate
+ * for the proper type.
+ */
+ if (!block_group_bits(block_group, data)) {
+ u64 extra = BTRFS_BLOCK_GROUP_DUP |
+ BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID10;
+
+ /*
+ * if they asked for extra copies and this block group
+ * doesn't provide them, bail. This does allow us to
+ * fill raid0 from raid1.
+ */
+ if ((data & extra) && !(block_group->flags & extra))
+ goto loop;
+ }
+
have_block_group:
if (unlikely(block_group->cached == BTRFS_CACHE_NO)) {
u64 free_percent;
- ret = cache_block_group(block_group, trans, 1);
+ ret = cache_block_group(block_group, trans,
+ orig_root, 1);
if (block_group->cached == BTRFS_CACHE_FINISHED)
goto have_block_group;
if (loop > LOOP_CACHING_NOWAIT ||
(loop > LOOP_FIND_IDEAL &&
atomic_read(&space_info->caching_threads) < 2)) {
- ret = cache_block_group(block_group, trans, 0);
+ ret = cache_block_group(block_group, trans,
+ orig_root, 0);
BUG_ON(ret);
}
found_uncached_bg = true;
u64 num_bytes = ins->offset;
block_group = btrfs_lookup_block_group(root->fs_info, ins->objectid);
- cache_block_group(block_group, trans, 0);
+ cache_block_group(block_group, trans, NULL, 0);
caching_ctl = get_caching_control(block_group);
if (!caching_ctl) {
NULL, NULL);
BUG_ON(ret < 0);
if (ret > 0) {
- ret = btrfs_del_orphan_item(trans, tree_root,
- root->root_key.objectid);
- BUG_ON(ret);
+ /* if we fail to delete the orphan item this time
+ * around, it'll get picked up the next time.
+ *
+ * The most common failure here is just -ENOENT.
+ */
+ btrfs_del_orphan_item(trans, tree_root,
+ root->root_key.objectid);
}
}
u64 stripped = BTRFS_BLOCK_GROUP_RAID0 |
BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
- num_devices = root->fs_info->fs_devices->rw_devices;
+ /*
+ * we add in the count of missing devices because we want
+ * to make sure that any RAID levels on a degraded FS
+ * continue to be honored.
+ */
+ num_devices = root->fs_info->fs_devices->rw_devices +
+ root->fs_info->fs_devices->missing_devices;
+
if (num_devices == 1) {
stripped |= BTRFS_BLOCK_GROUP_DUP;
stripped = flags & ~stripped;
break;
if (ret != 0)
goto error;
-
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
cache = kzalloc(sizeof(*cache), GFP_NOFS);
struct page **prepared_pages,
struct iov_iter *i)
{
- size_t copied;
+ size_t copied = 0;
int pg = 0;
int offset = pos & (PAGE_CACHE_SIZE - 1);
+ int total_copied = 0;
while (write_bytes > 0) {
size_t count = min_t(size_t,
PAGE_CACHE_SIZE - offset, write_bytes);
struct page *page = prepared_pages[pg];
-again:
- if (unlikely(iov_iter_fault_in_readable(i, count)))
- return -EFAULT;
-
- /* Copy data from userspace to the current page */
- copied = iov_iter_copy_from_user(page, i, offset, count);
+ /*
+ * Copy data from userspace to the current page
+ *
+ * Disable pagefault to avoid recursive lock since
+ * the pages are already locked
+ */
+ pagefault_disable();
+ copied = iov_iter_copy_from_user_atomic(page, i, offset, count);
+ pagefault_enable();
/* Flush processor's dcache for this page */
flush_dcache_page(page);
iov_iter_advance(i, copied);
write_bytes -= copied;
+ total_copied += copied;
+ /* Return to btrfs_file_aio_write to fault page */
if (unlikely(copied == 0)) {
- count = min_t(size_t, PAGE_CACHE_SIZE - offset,
- iov_iter_single_seg_count(i));
- goto again;
+ break;
}
if (unlikely(copied < PAGE_CACHE_SIZE - offset)) {
offset = 0;
}
}
- return 0;
+ return total_copied;
}
/*
unsigned long last_index;
int will_write;
int buffered = 0;
+ int copied = 0;
+ int dirty_pages = 0;
will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
(file->f_flags & O_DIRECT));
WARN_ON(num_pages > nrptrs);
memset(pages, 0, sizeof(struct page *) * nrptrs);
- ret = btrfs_delalloc_reserve_space(inode, write_bytes);
+ /*
+ * Fault pages before locking them in prepare_pages
+ * to avoid recursive lock
+ */
+ if (unlikely(iov_iter_fault_in_readable(&i, write_bytes))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ ret = btrfs_delalloc_reserve_space(inode,
+ num_pages << PAGE_CACHE_SHIFT);
if (ret)
goto out;
pos, first_index, last_index,
write_bytes);
if (ret) {
- btrfs_delalloc_release_space(inode, write_bytes);
+ btrfs_delalloc_release_space(inode,
+ num_pages << PAGE_CACHE_SHIFT);
goto out;
}
- ret = btrfs_copy_from_user(pos, num_pages,
+ copied = btrfs_copy_from_user(pos, num_pages,
write_bytes, pages, &i);
- if (ret == 0) {
+ dirty_pages = (copied + PAGE_CACHE_SIZE - 1) >>
+ PAGE_CACHE_SHIFT;
+
+ if (num_pages > dirty_pages) {
+ if (copied > 0)
+ atomic_inc(
+ &BTRFS_I(inode)->outstanding_extents);
+ btrfs_delalloc_release_space(inode,
+ (num_pages - dirty_pages) <<
+ PAGE_CACHE_SHIFT);
+ }
+
+ if (copied > 0) {
dirty_and_release_pages(NULL, root, file, pages,
- num_pages, pos, write_bytes);
+ dirty_pages, pos, copied);
}
btrfs_drop_pages(pages, num_pages);
- if (ret) {
- btrfs_delalloc_release_space(inode, write_bytes);
- goto out;
- }
- if (will_write) {
- filemap_fdatawrite_range(inode->i_mapping, pos,
- pos + write_bytes - 1);
- } else {
- balance_dirty_pages_ratelimited_nr(inode->i_mapping,
- num_pages);
- if (num_pages <
- (root->leafsize >> PAGE_CACHE_SHIFT) + 1)
- btrfs_btree_balance_dirty(root, 1);
- btrfs_throttle(root);
+ if (copied > 0) {
+ if (will_write) {
+ filemap_fdatawrite_range(inode->i_mapping, pos,
+ pos + copied - 1);
+ } else {
+ balance_dirty_pages_ratelimited_nr(
+ inode->i_mapping,
+ dirty_pages);
+ if (dirty_pages <
+ (root->leafsize >> PAGE_CACHE_SHIFT) + 1)
+ btrfs_btree_balance_dirty(root, 1);
+ btrfs_throttle(root);
+ }
}
- pos += write_bytes;
- num_written += write_bytes;
+ pos += copied;
+ num_written += copied;
cond_resched();
}
(unsigned long long)BTRFS_I(inode)->generation,
(unsigned long long)generation,
(unsigned long long)block_group->key.objectid);
- goto out;
+ goto free_cache;
}
if (!num_entries)
return 0;
}
+ node = rb_first(&block_group->free_space_offset);
+ if (!node) {
+ iput(inode);
+ return 0;
+ }
+
last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
filemap_write_and_wait(inode->i_mapping);
btrfs_wait_ordered_range(inode, inode->i_size &
*/
first_page_offset = (sizeof(u32) * num_checksums) + sizeof(u64);
- node = rb_first(&block_group->free_space_offset);
- if (!node)
- goto out_free;
-
/*
* Lock all pages first so we can lock the extent safely.
*
add_async_extent(async_cow, start, num_bytes,
total_compressed, pages, nr_pages_ret);
- if (start + num_bytes < end && start + num_bytes < actual_end) {
+ if (start + num_bytes < end) {
start += num_bytes;
pages = NULL;
cond_resched();
if (err) {
printk(KERN_ERR "btrfs direct IO failed ino %lu rw %lu "
- "disk_bytenr %lu len %u err no %d\n",
- dip->inode->i_ino, bio->bi_rw, bio->bi_sector,
- bio->bi_size, err);
+ "sector %#Lx len %u err no %d\n",
+ dip->inode->i_ino, bio->bi_rw,
+ (unsigned long long)bio->bi_sector, bio->bi_size, err);
dip->errors = 1;
/*
*/
if (write) {
struct btrfs_ordered_extent *ordered;
- ordered = btrfs_lookup_ordered_extent(inode,
- dip->logical_offset);
+ ordered = btrfs_lookup_ordered_extent(inode, file_offset);
if (!test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags) &&
!test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags))
btrfs_free_reserved_extent(root, ordered->start,
static noinline int btrfs_ioctl_snap_create(struct file *file,
void __user *arg, int subvol,
- int async)
+ int v2)
{
struct btrfs_ioctl_vol_args *vol_args = NULL;
- struct btrfs_ioctl_async_vol_args *async_vol_args = NULL;
+ struct btrfs_ioctl_vol_args_v2 *vol_args_v2 = NULL;
char *name;
u64 fd;
- u64 transid = 0;
int ret;
- if (async) {
- async_vol_args = memdup_user(arg, sizeof(*async_vol_args));
- if (IS_ERR(async_vol_args))
- return PTR_ERR(async_vol_args);
+ if (v2) {
+ u64 transid = 0;
+ u64 *ptr = NULL;
- name = async_vol_args->name;
- fd = async_vol_args->fd;
- async_vol_args->name[BTRFS_SNAPSHOT_NAME_MAX] = '\0';
+ vol_args_v2 = memdup_user(arg, sizeof(*vol_args_v2));
+ if (IS_ERR(vol_args_v2))
+ return PTR_ERR(vol_args_v2);
+
+ if (vol_args_v2->flags & ~BTRFS_SUBVOL_CREATE_ASYNC) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ name = vol_args_v2->name;
+ fd = vol_args_v2->fd;
+ vol_args_v2->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+
+ if (vol_args_v2->flags & BTRFS_SUBVOL_CREATE_ASYNC)
+ ptr = &transid;
+
+ ret = btrfs_ioctl_snap_create_transid(file, name, fd,
+ subvol, ptr);
+
+ if (ret == 0 && ptr &&
+ copy_to_user(arg +
+ offsetof(struct btrfs_ioctl_vol_args_v2,
+ transid), ptr, sizeof(*ptr)))
+ ret = -EFAULT;
} else {
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args))
name = vol_args->name;
fd = vol_args->fd;
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
- }
-
- ret = btrfs_ioctl_snap_create_transid(file, name, fd,
- subvol, &transid);
- if (!ret && async) {
- if (copy_to_user(arg +
- offsetof(struct btrfs_ioctl_async_vol_args,
- transid), &transid, sizeof(transid)))
- return -EFAULT;
+ ret = btrfs_ioctl_snap_create_transid(file, name, fd,
+ subvol, NULL);
}
-
+out:
kfree(vol_args);
- kfree(async_vol_args);
+ kfree(vol_args_v2);
return ret;
}
return btrfs_ioctl_getversion(file, argp);
case BTRFS_IOC_SNAP_CREATE:
return btrfs_ioctl_snap_create(file, argp, 0, 0);
- case BTRFS_IOC_SNAP_CREATE_ASYNC:
+ case BTRFS_IOC_SNAP_CREATE_V2:
return btrfs_ioctl_snap_create(file, argp, 0, 1);
case BTRFS_IOC_SUBVOL_CREATE:
return btrfs_ioctl_snap_create(file, argp, 1, 0);
char name[BTRFS_PATH_NAME_MAX + 1];
};
-#define BTRFS_SNAPSHOT_NAME_MAX 4079
-struct btrfs_ioctl_async_vol_args {
+#define BTRFS_SUBVOL_CREATE_ASYNC (1ULL << 0)
+
+#define BTRFS_SUBVOL_NAME_MAX 4039
+struct btrfs_ioctl_vol_args_v2 {
__s64 fd;
__u64 transid;
- char name[BTRFS_SNAPSHOT_NAME_MAX + 1];
+ __u64 flags;
+ __u64 unused[4];
+ char name[BTRFS_SUBVOL_NAME_MAX + 1];
};
#define BTRFS_INO_LOOKUP_PATH_MAX 4080
struct btrfs_ioctl_space_args)
#define BTRFS_IOC_START_SYNC _IOR(BTRFS_IOCTL_MAGIC, 24, __u64)
#define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64)
-#define BTRFS_IOC_SNAP_CREATE_ASYNC _IOW(BTRFS_IOCTL_MAGIC, 23, \
- struct btrfs_ioctl_async_vol_args)
+#define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \
+ struct btrfs_ioctl_vol_args_v2)
#endif
return -ENOMEM;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
- if (ret)
+ if (ret < 0)
goto out;
+ if (ret) {
+ ret = -ENOENT;
+ goto out;
+ }
ret = btrfs_del_item(trans, root, path);
mutex_unlock(&root->d_inode->i_mutex);
if (IS_ERR(new_root)) {
+ dput(root);
deactivate_locked_super(s);
error = PTR_ERR(new_root);
- dput(root);
goto error_free_subvol_name;
}
if (!new_root->d_inode) {
device->fs_devices = fs_devices;
fs_devices->num_devices++;
- } else if (strcmp(device->name, path)) {
+ } else if (!device->name || strcmp(device->name, path)) {
name = kstrdup(path, GFP_NOFS);
if (!name)
return -ENOMEM;
kfree(device->name);
device->name = name;
+ if (device->missing) {
+ fs_devices->missing_devices--;
+ device->missing = 0;
+ }
}
if (found_transid > fs_devices->latest_trans) {
device->fs_devices->num_devices--;
+ if (device->missing)
+ root->fs_info->fs_devices->missing_devices--;
+
next_device = list_entry(root->fs_info->fs_devices->devices.next,
struct btrfs_device, dev_list);
if (device->bdev == root->fs_info->sb->s_bdev)
device->devid = devid;
device->work.func = pending_bios_fn;
device->fs_devices = fs_devices;
+ device->missing = 1;
fs_devices->num_devices++;
+ fs_devices->missing_devices++;
spin_lock_init(&device->io_lock);
INIT_LIST_HEAD(&device->dev_alloc_list);
memcpy(device->uuid, dev_uuid, BTRFS_UUID_SIZE);
device = add_missing_dev(root, devid, dev_uuid);
if (!device)
return -ENOMEM;
+ } else if (!device->missing) {
+ /*
+ * this happens when a device that was properly setup
+ * in the device info lists suddenly goes bad.
+ * device->bdev is NULL, and so we have to set
+ * device->missing to one here
+ */
+ root->fs_info->fs_devices->missing_devices++;
+ device->missing = 1;
}
}
int writeable;
int in_fs_metadata;
+ int missing;
spinlock_t io_lock;
u64 num_devices;
u64 open_devices;
u64 rw_devices;
+ u64 missing_devices;
u64 total_rw_bytes;
struct block_device *latest_bdev;
spin_lock(&dcache_lock);
/* start at beginning? */
- if (filp->f_pos == 2 || (last &&
- filp->f_pos < ceph_dentry(last)->offset)) {
+ if (filp->f_pos == 2 || last == NULL ||
+ filp->f_pos < ceph_dentry(last)->offset) {
if (list_empty(&parent->d_subdirs))
goto out_unlock;
p = parent->d_subdirs.prev;
#include <linux/ioctl.h>
#include <linux/types.h>
-#define CEPH_IOCTL_MAGIC 0x98
+#define CEPH_IOCTL_MAGIC 0x97
/* just use u64 to align sanely on all archs */
struct ceph_ioctl_layout {
* Implement fcntl and flock locking functions.
*/
static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
- u64 pid, u64 pid_ns,
- int cmd, u64 start, u64 length, u8 wait)
+ int cmd, u8 wait, struct file_lock *fl)
{
struct inode *inode = file->f_dentry->d_inode;
struct ceph_mds_client *mdsc =
ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
int err;
+ u64 length = 0;
req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = igrab(inode);
+ /* mds requires start and length rather than start and end */
+ if (LLONG_MAX == fl->fl_end)
+ length = 0;
+ else
+ length = fl->fl_end - fl->fl_start + 1;
+
dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
"length: %llu, wait: %d, type`: %d", (int)lock_type,
- (int)operation, pid, start, length, wait, cmd);
+ (int)operation, (u64)fl->fl_pid, fl->fl_start,
+ length, wait, fl->fl_type);
+
req->r_args.filelock_change.rule = lock_type;
req->r_args.filelock_change.type = cmd;
- req->r_args.filelock_change.pid = cpu_to_le64(pid);
+ req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
/* This should be adjusted, but I'm not sure if
namespaces actually get id numbers*/
req->r_args.filelock_change.pid_namespace =
- cpu_to_le64((u64)pid_ns);
- req->r_args.filelock_change.start = cpu_to_le64(start);
+ cpu_to_le64((u64)(unsigned long)fl->fl_nspid);
+ req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
req->r_args.filelock_change.length = cpu_to_le64(length);
req->r_args.filelock_change.wait = wait;
err = ceph_mdsc_do_request(mdsc, inode, req);
+
+ if ( operation == CEPH_MDS_OP_GETFILELOCK){
+ fl->fl_pid = le64_to_cpu(req->r_reply_info.filelock_reply->pid);
+ if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
+ fl->fl_type = F_RDLCK;
+ else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
+ fl->fl_type = F_WRLCK;
+ else
+ fl->fl_type = F_UNLCK;
+
+ fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
+ length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
+ le64_to_cpu(req->r_reply_info.filelock_reply->length);
+ if (length >= 1)
+ fl->fl_end = length -1;
+ else
+ fl->fl_end = 0;
+
+ }
ceph_mdsc_put_request(req);
dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
- "length: %llu, wait: %d, type`: %d err code %d", (int)lock_type,
- (int)operation, pid, start, length, wait, cmd, err);
+ "length: %llu, wait: %d, type`: %d, err code %d", (int)lock_type,
+ (int)operation, (u64)fl->fl_pid, fl->fl_start,
+ length, wait, fl->fl_type, err);
return err;
}
*/
int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
{
- u64 length;
u8 lock_cmd;
int err;
u8 wait = 0;
else
lock_cmd = CEPH_LOCK_UNLOCK;
- if (LLONG_MAX == fl->fl_end)
- length = 0;
- else
- length = fl->fl_end - fl->fl_start + 1;
-
- err = ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
- (u64)fl->fl_pid,
- (u64)(unsigned long)fl->fl_nspid,
- lock_cmd, fl->fl_start,
- length, wait);
+ err = ceph_lock_message(CEPH_LOCK_FCNTL, op, file, lock_cmd, wait, fl);
if (!err) {
- dout("mds locked, locking locally");
- err = posix_lock_file(file, fl, NULL);
- if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
- /* undo! This should only happen if the kernel detects
- * local deadlock. */
- ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
- (u64)fl->fl_pid,
- (u64)(unsigned long)fl->fl_nspid,
- CEPH_LOCK_UNLOCK, fl->fl_start,
- length, 0);
- dout("got %d on posix_lock_file, undid lock", err);
+ if ( op != CEPH_MDS_OP_GETFILELOCK ){
+ dout("mds locked, locking locally");
+ err = posix_lock_file(file, fl, NULL);
+ if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
+ /* undo! This should only happen if the kernel detects
+ * local deadlock. */
+ ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
+ CEPH_LOCK_UNLOCK, 0, fl);
+ dout("got %d on posix_lock_file, undid lock", err);
+ }
}
+
} else {
dout("mds returned error code %d", err);
}
int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
{
- u64 length;
u8 lock_cmd;
int err;
u8 wait = 1;
lock_cmd = CEPH_LOCK_EXCL;
else
lock_cmd = CEPH_LOCK_UNLOCK;
- /* mds requires start and length rather than start and end */
- if (LLONG_MAX == fl->fl_end)
- length = 0;
- else
- length = fl->fl_end - fl->fl_start + 1;
err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK,
- file, (u64)fl->fl_pid,
- (u64)(unsigned long)fl->fl_nspid,
- lock_cmd, fl->fl_start,
- length, wait);
+ file, lock_cmd, wait, fl);
if (!err) {
err = flock_lock_file_wait(file, fl);
if (err) {
ceph_lock_message(CEPH_LOCK_FLOCK,
CEPH_MDS_OP_SETFILELOCK,
- file, (u64)fl->fl_pid,
- (u64)(unsigned long)fl->fl_nspid,
- CEPH_LOCK_UNLOCK, fl->fl_start,
- length, 0);
+ file, CEPH_LOCK_UNLOCK, 0, fl);
dout("got %d on flock_lock_file_wait, undid lock", err);
}
} else {
return err;
}
+/*
+ * parse fcntl F_GETLK results
+ */
+static int parse_reply_info_filelock(void **p, void *end,
+ struct ceph_mds_reply_info_parsed *info)
+{
+ if (*p + sizeof(*info->filelock_reply) > end)
+ goto bad;
+
+ info->filelock_reply = *p;
+ *p += sizeof(*info->filelock_reply);
+
+ if (unlikely(*p != end))
+ goto bad;
+ return 0;
+
+bad:
+ return -EIO;
+}
+
+/*
+ * parse extra results
+ */
+static int parse_reply_info_extra(void **p, void *end,
+ struct ceph_mds_reply_info_parsed *info)
+{
+ if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
+ return parse_reply_info_filelock(p, end, info);
+ else
+ return parse_reply_info_dir(p, end, info);
+}
+
/*
* parse entire mds reply
*/
goto out_bad;
}
- /* dir content */
+ /* extra */
ceph_decode_32_safe(&p, end, len, bad);
if (len > 0) {
- err = parse_reply_info_dir(&p, p+len, info);
+ err = parse_reply_info_extra(&p, p+len, info);
if (err < 0)
goto out_bad;
}
mutex_lock(&session->s_mutex);
if (err < 0) {
- pr_err("mdsc_handle_reply got corrupt reply mds%d\n", mds);
+ pr_err("mdsc_handle_reply got corrupt reply mds%d(tid:%lld)\n", mds, tid);
ceph_msg_dump(msg);
goto out_err;
}
mutex_lock(&req->r_fill_mutex);
err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
if (err == 0) {
- if (result == 0 && rinfo->dir_nr)
+ if (result == 0 && req->r_op != CEPH_MDS_OP_GETFILELOCK &&
+ rinfo->dir_nr)
ceph_readdir_prepopulate(req, req->r_session);
ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
}
};
/*
- * parsed info about an mds reply, including information about the
- * target inode and/or its parent directory and dentry, and directory
- * contents (for readdir results).
+ * parsed info about an mds reply, including information about
+ * either: 1) the target inode and/or its parent directory and dentry,
+ * and directory contents (for readdir results), or
+ * 2) the file range lock info (for fcntl F_GETLK results).
*/
struct ceph_mds_reply_info_parsed {
struct ceph_mds_reply_head *head;
+ /* trace */
struct ceph_mds_reply_info_in diri, targeti;
struct ceph_mds_reply_dirfrag *dirfrag;
char *dname;
u32 dname_len;
struct ceph_mds_reply_lease *dlease;
- struct ceph_mds_reply_dirfrag *dir_dir;
- int dir_nr;
- char **dir_dname;
- u32 *dir_dname_len;
- struct ceph_mds_reply_lease **dir_dlease;
- struct ceph_mds_reply_info_in *dir_in;
- u8 dir_complete, dir_end;
+ /* extra */
+ union {
+ /* for fcntl F_GETLK results */
+ struct ceph_filelock *filelock_reply;
+
+ /* for readdir results */
+ struct {
+ struct ceph_mds_reply_dirfrag *dir_dir;
+ int dir_nr;
+ char **dir_dname;
+ u32 *dir_dname_len;
+ struct ceph_mds_reply_lease **dir_dlease;
+ struct ceph_mds_reply_info_in *dir_in;
+ u8 dir_complete, dir_end;
+ };
+ };
/* encoded blob describing snapshot contexts for certain
operations (e.g., open) */
cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \
link.o misc.o netmisc.o smbdes.o smbencrypt.o transport.o asn1.o \
md4.o md5.o cifs_unicode.o nterr.o xattr.o cifsencrypt.o \
- readdir.o ioctl.o sess.o export.o cifsacl.o
+ readdir.o ioctl.o sess.o export.o
+
+cifs-$(CONFIG_CIFS_ACL) += cifsacl.o
cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
wsize default write size (default 57344)
maximum wsize currently allowed by CIFS is 57344 (fourteen
4096 byte pages)
+ actimeo=n attribute cache timeout in seconds (default 1 second).
+ After this timeout, the cifs client requests fresh attribute
+ information from the server. This option allows to tune the
+ attribute cache timeout to suit the workload needs. Shorter
+ timeouts mean better the cache coherency, but increased number
+ of calls to the server. Longer timeouts mean reduced number
+ of calls to the server at the expense of less stricter cache
+ coherency checks (i.e. incorrect attribute cache for a short
+ period of time).
rw mount the network share read-write (note that the
server may still consider the share read-only)
ro mount network share read-only
struct nls_table *local_nls;
unsigned int rsize;
unsigned int wsize;
+ unsigned long actimeo; /* attribute cache timeout (jiffies) */
atomic_t active;
uid_t mnt_uid;
gid_t mnt_gid;
#include "cifs_debug.h"
-#ifdef CONFIG_CIFS_EXPERIMENTAL
-
static struct cifs_wksid wksidarr[NUM_WK_SIDS] = {
{{1, 0, {0, 0, 0, 0, 0, 0}, {0, 0, 0, 0, 0} }, "null user"},
{{1, 1, {0, 0, 0, 0, 0, 1}, {0, 0, 0, 0, 0} }, "nobody"},
return rc;
}
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
char sidname[SIDNAMELENGTH];
} __attribute__((packed));
-#ifdef CONFIG_CIFS_EXPERIMENTAL
-
extern int match_sid(struct cifs_sid *);
extern int compare_sids(const struct cifs_sid *, const struct cifs_sid *);
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
-
#endif /* _CIFSACL_H */
seq_printf(s, ",rsize=%d", cifs_sb->rsize);
seq_printf(s, ",wsize=%d", cifs_sb->wsize);
+ /* convert actimeo and display it in seconds */
+ seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
return 0;
}
GlobalCurrentXid = 0;
GlobalTotalActiveXid = 0;
GlobalMaxActiveXid = 0;
- memset(Local_System_Name, 0, 15);
spin_lock_init(&cifs_tcp_ses_lock);
spin_lock_init(&cifs_file_list_lock);
spin_lock_init(&GlobalMid_Lock);
#define CIFS_MIN_RCV_POOL 4
+/*
+ * default attribute cache timeout (jiffies)
+ */
+#define CIFS_DEF_ACTIMEO (1 * HZ)
+
+/*
+ * max attribute cache timeout (jiffies) - 2^30
+ */
+#define CIFS_MAX_ACTIMEO (1 << 30)
+
/*
* MAX_REQ is the maximum number of requests that WE will send
* on one socket concurrently. It also matches the most common
GLOBAL_EXTERN unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Sem */
GLOBAL_EXTERN spinlock_t GlobalMid_Lock; /* protects above & list operations */
/* on midQ entries */
-GLOBAL_EXTERN char Local_System_Name[15];
-
/*
* Global counters, updated atomically
*/
__func__, curr_xid, (int)rc); \
} while (0)
extern char *build_path_from_dentry(struct dentry *);
-extern char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb);
+extern char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb,
+ struct cifsTconInfo *tcon);
extern char *build_wildcard_path_from_dentry(struct dentry *direntry);
extern char *cifs_compose_mount_options(const char *sb_mountdata,
const char *fullpath, const struct dfs_info3_param *ref,
struct TCP_Server_Info *);
extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof);
extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, bool);
-#ifdef CONFIG_CIFS_EXPERIMENTAL
extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool);
-#endif
extern unsigned int smbCalcSize(struct smb_hdr *ptr);
extern unsigned int smbCalcSize_LE(struct smb_hdr *ptr);
extern int decode_negTokenInit(unsigned char *security_blob, int length,
}
#ifdef CONFIG_CIFS_EXPERIMENTAL
-/* Initialize NT TRANSACT SMB into small smb request buffer.
- This assumes that all NT TRANSACTS that we init here have
- total parm and data under about 400 bytes (to fit in small cifs
- buffer size), which is the case so far, it easily fits. NB:
- Setup words themselves and ByteCount
- MaxSetupCount (size of returned setup area) and
- MaxParameterCount (returned parms size) must be set by caller */
-static int
-smb_init_nttransact(const __u16 sub_command, const int setup_count,
- const int parm_len, struct cifsTconInfo *tcon,
- void **ret_buf)
-{
- int rc;
- __u32 temp_offset;
- struct smb_com_ntransact_req *pSMB;
-
- rc = small_smb_init(SMB_COM_NT_TRANSACT, 19 + setup_count, tcon,
- (void **)&pSMB);
- if (rc)
- return rc;
- *ret_buf = (void *)pSMB;
- pSMB->Reserved = 0;
- pSMB->TotalParameterCount = cpu_to_le32(parm_len);
- pSMB->TotalDataCount = 0;
- pSMB->MaxDataCount = cpu_to_le32((tcon->ses->server->maxBuf -
- MAX_CIFS_HDR_SIZE) & 0xFFFFFF00);
- pSMB->ParameterCount = pSMB->TotalParameterCount;
- pSMB->DataCount = pSMB->TotalDataCount;
- temp_offset = offsetof(struct smb_com_ntransact_req, Parms) +
- (setup_count * 2) - 4 /* for rfc1001 length itself */;
- pSMB->ParameterOffset = cpu_to_le32(temp_offset);
- pSMB->DataOffset = cpu_to_le32(temp_offset + parm_len);
- pSMB->SetupCount = setup_count; /* no need to le convert byte fields */
- pSMB->SubCommand = cpu_to_le16(sub_command);
- return 0;
-}
-
-static int
-validate_ntransact(char *buf, char **ppparm, char **ppdata,
- __u32 *pparmlen, __u32 *pdatalen)
-{
- char *end_of_smb;
- __u32 data_count, data_offset, parm_count, parm_offset;
- struct smb_com_ntransact_rsp *pSMBr;
-
- *pdatalen = 0;
- *pparmlen = 0;
-
- if (buf == NULL)
- return -EINVAL;
-
- pSMBr = (struct smb_com_ntransact_rsp *)buf;
-
- /* ByteCount was converted from little endian in SendReceive */
- end_of_smb = 2 /* sizeof byte count */ + pSMBr->ByteCount +
- (char *)&pSMBr->ByteCount;
-
- data_offset = le32_to_cpu(pSMBr->DataOffset);
- data_count = le32_to_cpu(pSMBr->DataCount);
- parm_offset = le32_to_cpu(pSMBr->ParameterOffset);
- parm_count = le32_to_cpu(pSMBr->ParameterCount);
-
- *ppparm = (char *)&pSMBr->hdr.Protocol + parm_offset;
- *ppdata = (char *)&pSMBr->hdr.Protocol + data_offset;
-
- /* should we also check that parm and data areas do not overlap? */
- if (*ppparm > end_of_smb) {
- cFYI(1, "parms start after end of smb");
- return -EINVAL;
- } else if (parm_count + *ppparm > end_of_smb) {
- cFYI(1, "parm end after end of smb");
- return -EINVAL;
- } else if (*ppdata > end_of_smb) {
- cFYI(1, "data starts after end of smb");
- return -EINVAL;
- } else if (data_count + *ppdata > end_of_smb) {
- cFYI(1, "data %p + count %d (%p) past smb end %p start %p",
- *ppdata, data_count, (data_count + *ppdata),
- end_of_smb, pSMBr);
- return -EINVAL;
- } else if (parm_count + data_count > pSMBr->ByteCount) {
- cFYI(1, "parm count and data count larger than SMB");
- return -EINVAL;
- }
- *pdatalen = data_count;
- *pparmlen = parm_count;
- return 0;
-}
-
int
CIFSSMBQueryReparseLinkInfo(const int xid, struct cifsTconInfo *tcon,
const unsigned char *searchName,
#endif /* CONFIG_POSIX */
-#ifdef CONFIG_CIFS_EXPERIMENTAL
+#ifdef CONFIG_CIFS_ACL
+/*
+ * Initialize NT TRANSACT SMB into small smb request buffer. This assumes that
+ * all NT TRANSACTS that we init here have total parm and data under about 400
+ * bytes (to fit in small cifs buffer size), which is the case so far, it
+ * easily fits. NB: Setup words themselves and ByteCount MaxSetupCount (size of
+ * returned setup area) and MaxParameterCount (returned parms size) must be set
+ * by caller
+ */
+static int
+smb_init_nttransact(const __u16 sub_command, const int setup_count,
+ const int parm_len, struct cifsTconInfo *tcon,
+ void **ret_buf)
+{
+ int rc;
+ __u32 temp_offset;
+ struct smb_com_ntransact_req *pSMB;
+
+ rc = small_smb_init(SMB_COM_NT_TRANSACT, 19 + setup_count, tcon,
+ (void **)&pSMB);
+ if (rc)
+ return rc;
+ *ret_buf = (void *)pSMB;
+ pSMB->Reserved = 0;
+ pSMB->TotalParameterCount = cpu_to_le32(parm_len);
+ pSMB->TotalDataCount = 0;
+ pSMB->MaxDataCount = cpu_to_le32((tcon->ses->server->maxBuf -
+ MAX_CIFS_HDR_SIZE) & 0xFFFFFF00);
+ pSMB->ParameterCount = pSMB->TotalParameterCount;
+ pSMB->DataCount = pSMB->TotalDataCount;
+ temp_offset = offsetof(struct smb_com_ntransact_req, Parms) +
+ (setup_count * 2) - 4 /* for rfc1001 length itself */;
+ pSMB->ParameterOffset = cpu_to_le32(temp_offset);
+ pSMB->DataOffset = cpu_to_le32(temp_offset + parm_len);
+ pSMB->SetupCount = setup_count; /* no need to le convert byte fields */
+ pSMB->SubCommand = cpu_to_le16(sub_command);
+ return 0;
+}
+
+static int
+validate_ntransact(char *buf, char **ppparm, char **ppdata,
+ __u32 *pparmlen, __u32 *pdatalen)
+{
+ char *end_of_smb;
+ __u32 data_count, data_offset, parm_count, parm_offset;
+ struct smb_com_ntransact_rsp *pSMBr;
+
+ *pdatalen = 0;
+ *pparmlen = 0;
+
+ if (buf == NULL)
+ return -EINVAL;
+
+ pSMBr = (struct smb_com_ntransact_rsp *)buf;
+
+ /* ByteCount was converted from little endian in SendReceive */
+ end_of_smb = 2 /* sizeof byte count */ + pSMBr->ByteCount +
+ (char *)&pSMBr->ByteCount;
+
+ data_offset = le32_to_cpu(pSMBr->DataOffset);
+ data_count = le32_to_cpu(pSMBr->DataCount);
+ parm_offset = le32_to_cpu(pSMBr->ParameterOffset);
+ parm_count = le32_to_cpu(pSMBr->ParameterCount);
+
+ *ppparm = (char *)&pSMBr->hdr.Protocol + parm_offset;
+ *ppdata = (char *)&pSMBr->hdr.Protocol + data_offset;
+
+ /* should we also check that parm and data areas do not overlap? */
+ if (*ppparm > end_of_smb) {
+ cFYI(1, "parms start after end of smb");
+ return -EINVAL;
+ } else if (parm_count + *ppparm > end_of_smb) {
+ cFYI(1, "parm end after end of smb");
+ return -EINVAL;
+ } else if (*ppdata > end_of_smb) {
+ cFYI(1, "data starts after end of smb");
+ return -EINVAL;
+ } else if (data_count + *ppdata > end_of_smb) {
+ cFYI(1, "data %p + count %d (%p) past smb end %p start %p",
+ *ppdata, data_count, (data_count + *ppdata),
+ end_of_smb, pSMBr);
+ return -EINVAL;
+ } else if (parm_count + data_count > pSMBr->ByteCount) {
+ cFYI(1, "parm count and data count larger than SMB");
+ return -EINVAL;
+ }
+ *pdatalen = data_count;
+ *pparmlen = parm_count;
+ return 0;
+}
+
/* Get Security Descriptor (by handle) from remote server for a file or dir */
int
CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid,
return (rc);
}
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
+#endif /* CONFIG_CIFS_ACL */
/* Legacy Query Path Information call for lookup to old servers such
as Win9x/WinME */
unsigned int wsize;
bool sockopt_tcp_nodelay:1;
unsigned short int port;
+ unsigned long actimeo; /* attribute cache timeout (jiffies) */
char *prepath;
struct sockaddr_storage srcaddr; /* allow binding to a local IP */
struct nls_table *local_nls;
short int override_gid = -1;
bool uid_specified = false;
bool gid_specified = false;
+ char *nodename = utsname()->nodename;
separator[0] = ',';
separator[1] = 0;
- if (Local_System_Name[0] != 0)
- memcpy(vol->source_rfc1001_name, Local_System_Name, 15);
- else {
- char *nodename = utsname()->nodename;
- int n = strnlen(nodename, 15);
- memset(vol->source_rfc1001_name, 0x20, 15);
- for (i = 0; i < n; i++) {
- /* does not have to be perfect mapping since field is
- informational, only used for servers that do not support
- port 445 and it can be overridden at mount time */
- vol->source_rfc1001_name[i] = toupper(nodename[i]);
- }
- }
+ /*
+ * does not have to be perfect mapping since field is
+ * informational, only used for servers that do not support
+ * port 445 and it can be overridden at mount time
+ */
+ memset(vol->source_rfc1001_name, 0x20, 15);
+ for (i = 0; i < strnlen(nodename, 15); i++)
+ vol->source_rfc1001_name[i] = toupper(nodename[i]);
+
vol->source_rfc1001_name[15] = 0;
/* null target name indicates to use *SMBSERVR default called name
if we end up sending RFC1001 session initialize */
/* default to using server inode numbers where available */
vol->server_ino = 1;
+ vol->actimeo = CIFS_DEF_ACTIMEO;
+
if (!options)
return 1;
printk(KERN_WARNING "CIFS: server net"
"biosname longer than 15 truncated.\n");
}
+ } else if (strnicmp(data, "actimeo", 7) == 0) {
+ if (value && *value) {
+ vol->actimeo = HZ * simple_strtoul(value,
+ &value, 0);
+ if (vol->actimeo > CIFS_MAX_ACTIMEO) {
+ cERROR(1, "CIFS: attribute cache"
+ "timeout too large");
+ return 1;
+ }
+ }
} else if (strnicmp(data, "credentials", 4) == 0) {
/* ignore */
} else if (strnicmp(data, "version", 3) == 0) {
cFYI(1, "file mode: 0x%x dir mode: 0x%x",
cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode);
+ cifs_sb->actimeo = pvolume_info->actimeo;
+
if (pvolume_info->noperm)
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM;
if (pvolume_info->setuids)
/* check if a whole path (including prepath) is not remote */
if (!rc && cifs_sb->prepathlen && tcon) {
/* build_path_to_root works only when we have a valid tcon */
- full_path = cifs_build_path_to_root(cifs_sb);
+ full_path = cifs_build_path_to_root(cifs_sb, tcon);
if (full_path == NULL) {
rc = -ENOMEM;
goto mount_fail_check;
}
rc = is_path_accessible(xid, tcon, cifs_sb, full_path);
- if (rc != -EREMOTE) {
+ if (rc != 0 && rc != -EREMOTE) {
kfree(full_path);
goto mount_fail_check;
}
return total_written;
}
-#ifdef CONFIG_CIFS_EXPERIMENTAL
struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
bool fsuid_only)
{
spin_unlock(&cifs_file_list_lock);
return NULL;
}
-#endif
struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
bool fsuid_only)
cFYI(1, "cifs_sfu_type failed: %d", tmprc);
}
-#ifdef CONFIG_CIFS_EXPERIMENTAL
+#ifdef CONFIG_CIFS_ACL
/* fill in 0777 bits from ACL */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
rc = cifs_acl_to_fattr(cifs_sb, &fattr, *pinode, full_path,
goto cgii_exit;
}
}
-#endif
+#endif /* CONFIG_CIFS_ACL */
/* fill in remaining high mode bits e.g. SUID, VTX */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
.lookup = cifs_lookup,
};
-char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb)
+char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb,
+ struct cifsTconInfo *tcon)
{
int pplen = cifs_sb->prepathlen;
int dfsplen;
char *full_path = NULL;
- struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
/* if no prefix path, simply set path to the root of share to "" */
if (pplen == 0) {
char *full_path;
struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
- full_path = cifs_build_path_to_root(cifs_sb);
+ full_path = cifs_build_path_to_root(cifs_sb, tcon);
if (full_path == NULL)
return ERR_PTR(-ENOMEM);
cifs_inode_needs_reval(struct inode *inode)
{
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
if (cifs_i->clientCanCacheRead)
return false;
if (cifs_i->time == 0)
return true;
- /* FIXME: the actimeo should be tunable */
- if (time_after_eq(jiffies, cifs_i->time + HZ))
+ if (!time_in_range(jiffies, cifs_i->time,
+ cifs_i->time + cifs_sb->actimeo))
return true;
/* hardlinked files w/ noserverino get "special" treatment */
- if (!(CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
+ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
S_ISREG(inode->i_mode) && inode->i_nlink != 1)
return true;
if (attrs->ia_valid & ATTR_MODE) {
rc = 0;
-#ifdef CONFIG_CIFS_EXPERIMENTAL
+#ifdef CONFIG_CIFS_ACL
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
rc = mode_to_cifs_acl(inode, full_path, mode);
if (rc) {
goto cifs_setattr_exit;
}
} else
-#endif
+#endif /* CONFIG_CIFS_ACL */
if (((mode & S_IWUGO) == 0) &&
(cifsInode->cifsAttrs & ATTR_READONLY) == 0) {
rc = filldir(direntry, qstring.name, qstring.len, file->f_pos,
ino, fattr.cf_dtype);
- /*
- * we can not return filldir errors to the caller since they are
- * "normal" when the stat blocksize is too small - we return remapped
- * error instead
- *
- * FIXME: This looks bogus. filldir returns -EOVERFLOW in the above
- * case already. Why should we be clobbering other errors from it?
- */
- if (rc) {
- cFYI(1, "filldir rc = %d", rc);
- rc = -EOVERFLOW;
- }
dput(tmp_dentry);
return rc;
}
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/module.h>
+#include <linux/compat.h>
static const struct file_operations fuse_direct_io_file_operations;
return 0;
}
+/*
+ * CUSE servers compiled on 32bit broke on 64bit kernels because the
+ * ABI was defined to be 'struct iovec' which is different on 32bit
+ * and 64bit. Fortunately we can determine which structure the server
+ * used from the size of the reply.
+ */
+static int fuse_copy_ioctl_iovec(struct iovec *dst, void *src,
+ size_t transferred, unsigned count,
+ bool is_compat)
+{
+#ifdef CONFIG_COMPAT
+ if (count * sizeof(struct compat_iovec) == transferred) {
+ struct compat_iovec *ciov = src;
+ unsigned i;
+
+ /*
+ * With this interface a 32bit server cannot support
+ * non-compat (i.e. ones coming from 64bit apps) ioctl
+ * requests
+ */
+ if (!is_compat)
+ return -EINVAL;
+
+ for (i = 0; i < count; i++) {
+ dst[i].iov_base = compat_ptr(ciov[i].iov_base);
+ dst[i].iov_len = ciov[i].iov_len;
+ }
+ return 0;
+ }
+#endif
+
+ if (count * sizeof(struct iovec) != transferred)
+ return -EIO;
+
+ memcpy(dst, src, transferred);
+ return 0;
+}
+
+/* Make sure iov_length() won't overflow */
+static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count)
+{
+ size_t n;
+ u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT;
+
+ for (n = 0; n < count; n++) {
+ if (iov->iov_len > (size_t) max)
+ return -ENOMEM;
+ max -= iov->iov_len;
+ }
+ return 0;
+}
+
/*
* For ioctls, there is no generic way to determine how much memory
* needs to be read and/or written. Furthermore, ioctls are allowed
in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV)
goto out;
- err = -EIO;
- if ((in_iovs + out_iovs) * sizeof(struct iovec) != transferred)
- goto out;
-
- /* okay, copy in iovs and retry */
vaddr = kmap_atomic(pages[0], KM_USER0);
- memcpy(page_address(iov_page), vaddr, transferred);
+ err = fuse_copy_ioctl_iovec(page_address(iov_page), vaddr,
+ transferred, in_iovs + out_iovs,
+ (flags & FUSE_IOCTL_COMPAT) != 0);
kunmap_atomic(vaddr, KM_USER0);
+ if (err)
+ goto out;
in_iov = page_address(iov_page);
out_iov = in_iov + in_iovs;
+ err = fuse_verify_ioctl_iov(in_iov, in_iovs);
+ if (err)
+ goto out;
+
+ err = fuse_verify_ioctl_iov(out_iov, out_iovs);
+ if (err)
+ goto out;
+
goto retry;
}
struct inode *, struct dentry *);
static int nfs_fsync_dir(struct file *, int);
static loff_t nfs_llseek_dir(struct file *, loff_t, int);
-static int nfs_readdir_clear_array(struct page*, gfp_t);
+static void nfs_readdir_clear_array(struct page*);
const struct file_operations nfs_dir_operations = {
.llseek = nfs_llseek_dir,
.setattr = nfs_setattr,
};
-const struct address_space_operations nfs_dir_addr_space_ops = {
- .releasepage = nfs_readdir_clear_array,
+const struct address_space_operations nfs_dir_aops = {
+ .freepage = nfs_readdir_clear_array,
};
#ifdef CONFIG_NFS_V3
struct page *page;
unsigned long page_index;
u64 *dir_cookie;
+ u64 last_cookie;
loff_t current_index;
decode_dirent_t decode;
* we are freeing strings created by nfs_add_to_readdir_array()
*/
static
-int nfs_readdir_clear_array(struct page *page, gfp_t mask)
+void nfs_readdir_clear_array(struct page *page)
{
- struct nfs_cache_array *array = nfs_readdir_get_array(page);
+ struct nfs_cache_array *array;
int i;
- if (IS_ERR(array))
- return PTR_ERR(array);
+ array = kmap_atomic(page, KM_USER0);
for (i = 0; i < array->size; i++)
kfree(array->array[i].string.name);
- nfs_readdir_release_array(page);
- return 0;
+ kunmap_atomic(array, KM_USER0);
}
/*
goto out;
array->last_cookie = entry->cookie;
array->size++;
- if (entry->eof == 1)
+ if (entry->eof != 0)
array->eof_index = array->size;
out:
nfs_readdir_release_array(page);
for (i = 0; i < array->size; i++) {
if (array->array[i].cookie == *desc->dir_cookie) {
desc->cache_entry_index = i;
- status = 0;
- goto out;
+ return 0;
}
}
- if (i == array->eof_index) {
- desc->eof = 1;
+ if (array->eof_index >= 0) {
status = -EBADCOOKIE;
+ if (*desc->dir_cookie == array->last_cookie)
+ desc->eof = 1;
}
-out:
return status;
}
int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
{
struct nfs_cache_array *array;
- int status = -EBADCOOKIE;
-
- if (desc->dir_cookie == NULL)
- goto out;
+ int status;
array = nfs_readdir_get_array(desc->page);
if (IS_ERR(array)) {
else
status = nfs_readdir_search_for_cookie(array, desc);
+ if (status == -EAGAIN) {
+ desc->last_cookie = array->last_cookie;
+ desc->page_index++;
+ }
nfs_readdir_release_array(desc->page);
out:
return status;
count++;
- if (desc->plus == 1)
+ if (desc->plus != 0)
nfs_prime_dcache(desc->file->f_path.dentry, entry);
status = nfs_readdir_add_to_array(entry, page);
break;
} while (!entry->eof);
- if (count == 0 || (status == -EBADCOOKIE && entry->eof == 1)) {
+ if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
array = nfs_readdir_get_array(page);
if (!IS_ERR(array)) {
array->eof_index = array->size;
unsigned int array_size = ARRAY_SIZE(pages);
entry.prev_cookie = 0;
- entry.cookie = *desc->dir_cookie;
+ entry.cookie = desc->last_cookie;
entry.eof = 0;
entry.fh = nfs_alloc_fhandle();
entry.fattr = nfs_alloc_fattr();
static
void cache_page_release(nfs_readdir_descriptor_t *desc)
{
+ if (!desc->page->mapping)
+ nfs_readdir_clear_array(desc->page);
page_cache_release(desc->page);
desc->page = NULL;
}
return PTR_ERR(desc->page);
res = nfs_readdir_search_array(desc);
- if (res == 0)
- return 0;
- cache_page_release(desc);
+ if (res != 0)
+ cache_page_release(desc);
return res;
}
{
int res;
- if (desc->page_index == 0)
+ if (desc->page_index == 0) {
desc->current_index = 0;
- while (1) {
- res = find_cache_page(desc);
- if (res != -EAGAIN)
- break;
- desc->page_index++;
+ desc->last_cookie = 0;
}
+ do {
+ res = find_cache_page(desc);
+ } while (res == -EAGAIN);
return res;
}
-static inline unsigned int dt_type(struct inode *inode)
-{
- return (inode->i_mode >> 12) & 15;
-}
-
/*
* Once we've found the start of the dirent within a page: fill 'er up...
*/
break;
}
file->f_pos++;
- desc->cache_entry_index = i;
if (i < (array->size-1))
*desc->dir_cookie = array->array[i+1].cookie;
else
*desc->dir_cookie = array->last_cookie;
}
- if (i == array->eof_index)
+ if (array->eof_index >= 0)
desc->eof = 1;
nfs_readdir_release_array(desc->page);
}
desc->page_index = 0;
+ desc->last_cookie = *desc->dir_cookie;
desc->page = page;
status = nfs_readdir_xdr_to_array(desc, page, inode);
struct inode *inode = dentry->d_inode;
nfs_readdir_descriptor_t my_desc,
*desc = &my_desc;
- int res = -ENOMEM;
+ int res;
dfprintk(FILE, "NFS: readdir(%s/%s) starting at cookie %llu\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
if (res < 0)
goto out;
- while (desc->eof != 1) {
+ do {
res = readdir_search_pagecache(desc);
if (res == -EBADCOOKIE) {
res = nfs_do_filldir(desc, dirent, filldir);
if (res < 0)
break;
- }
+ } while (!desc->eof);
out:
nfs_unblock_sillyrename(dentry);
if (res > 0)
{
struct inode *inode = filp->f_mapping->host;
int status = 0;
+ unsigned int saved_type = fl->fl_type;
/* Try local locking first */
posix_test_lock(filp, fl);
/* found a conflict */
goto out;
}
+ fl->fl_type = saved_type;
if (nfs_have_delegation(inode, FMODE_READ))
goto out_noconflict;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
inode->i_fop = &nfs_dir_operations;
+ inode->i_data.a_ops = &nfs_dir_aops;
if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS))
set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
/* Deal with crossing mountpoints */
static struct rpc_version mnt_version1 = {
.number = 1,
- .nrprocs = 2,
+ .nrprocs = ARRAY_SIZE(mnt_procedures),
.procs = mnt_procedures,
};
static struct rpc_version mnt_version3 = {
.number = 3,
- .nrprocs = 2,
+ .nrprocs = ARRAY_SIZE(mnt3_procedures),
.procs = mnt3_procedures,
};
ret = nfs_revalidate_inode(server, inode);
if (ret < 0)
return ret;
+ if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
+ nfs_zap_acl_cache(inode);
ret = nfs4_read_cached_acl(inode, buf, buflen);
if (ret != -ENOENT)
return ret;
nfs_inode_return_delegation(inode);
buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
ret = nfs4_call_sync(server, &msg, &arg, &res, 1);
+ /*
+ * Acl update can result in inode attribute update.
+ * so mark the attribute cache invalid.
+ */
+ spin_lock(&inode->i_lock);
+ NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR;
+ spin_unlock(&inode->i_lock);
nfs_access_zap_cache(inode);
nfs_zap_acl_cache(inode);
return ret;
{
if (!nfs_lock_request_dontget(req))
return 0;
- if (req->wb_page != NULL)
+ if (test_bit(PG_MAPPED, &req->wb_flags))
radix_tree_tag_set(&NFS_I(req->wb_context->path.dentry->d_inode)->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
return 1;
}
*/
void nfs_clear_page_tag_locked(struct nfs_page *req)
{
- if (req->wb_page != NULL) {
+ if (test_bit(PG_MAPPED, &req->wb_flags)) {
struct inode *inode = req->wb_context->path.dentry->d_inode;
struct nfs_inode *nfsi = NFS_I(inode);
(long long)NFS_FILEID(req->wb_context->path.dentry->d_inode),
req->wb_bytes,
(long long)req_offset(req));
- nfs_clear_request(req);
nfs_release_request(req);
}
mnt->flags |= NFS_MOUNT_VER3;
mnt->version = 3;
break;
-#ifdef CONFIG_NFS_V4
case Opt_v4:
mnt->flags &= ~NFS_MOUNT_VER3;
mnt->version = 4;
break;
-#endif
case Opt_udp:
mnt->flags &= ~NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
mnt->flags |= NFS_MOUNT_VER3;
mnt->version = 3;
break;
-#ifdef CONFIG_NFS_V4
case NFS4_VERSION:
mnt->flags &= ~NFS_MOUNT_VER3;
mnt->version = 4;
break;
-#endif
default:
goto out_invalid_value;
}
if (nfs_have_delegation(inode, FMODE_WRITE))
nfsi->change_attr++;
}
+ set_bit(PG_MAPPED, &req->wb_flags);
SetPagePrivate(req->wb_page);
set_page_private(req->wb_page, (unsigned long)req);
nfsi->npages++;
spin_lock(&inode->i_lock);
set_page_private(req->wb_page, 0);
ClearPagePrivate(req->wb_page);
+ clear_bit(PG_MAPPED, &req->wb_flags);
radix_tree_delete(&nfsi->nfs_page_tree, req->wb_index);
nfsi->npages--;
if (!nfsi->npages) {
iput(inode);
} else
spin_unlock(&inode->i_lock);
- nfs_clear_request(req);
nfs_release_request(req);
}
err = vfs_getattr(fhp->fh_export->ex_path.mnt, fhp->fh_dentry,
&fhp->fh_post_attr);
fhp->fh_post_change = fhp->fh_dentry->d_inode->i_version;
- if (err)
+ if (err) {
fhp->fh_post_saved = 0;
- else
+ /* Grab the ctime anyway - set_change_info might use it */
+ fhp->fh_post_attr.ctime = fhp->fh_dentry->d_inode->i_ctime;
+ } else
fhp->fh_post_saved = 1;
}
static inline void
set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
{
- BUG_ON(!fhp->fh_pre_saved || !fhp->fh_post_saved);
- cinfo->atomic = 1;
+ BUG_ON(!fhp->fh_pre_saved);
+ cinfo->atomic = fhp->fh_post_saved;
cinfo->change_supported = IS_I_VERSION(fhp->fh_dentry->d_inode);
- if (cinfo->change_supported) {
- cinfo->before_change = fhp->fh_pre_change;
- cinfo->after_change = fhp->fh_post_change;
- } else {
- cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec;
- cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec;
- cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec;
- cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec;
- }
+
+ cinfo->before_change = fhp->fh_pre_change;
+ cinfo->after_change = fhp->fh_post_change;
+ cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec;
+ cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec;
+ cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec;
+ cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec;
+
}
int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
* it and some incremental backup programs won't work without it.
*/
xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG);
+ xfs_trans_log_inode(tp, src_ip, XFS_ILOG_CORE);
/*
* Adjust the link count on src_dp. This is necessary when
sector_t (*bmap)(struct address_space *, sector_t);
void (*invalidatepage) (struct page *, unsigned long);
int (*releasepage) (struct page *, gfp_t);
+ void (*freepage)(struct page *);
ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
loff_t offset, unsigned long nr_segs);
int (*get_xip_mem)(struct address_space *, pgoff_t, int,
#endif /* CONFIG_NFS_V3 */
extern const struct file_operations nfs_file_operations;
extern const struct address_space_operations nfs_file_aops;
+extern const struct address_space_operations nfs_dir_aops;
static inline struct nfs_open_context *nfs_file_open_context(struct file *filp)
{
*/
enum {
PG_BUSY = 0,
+ PG_MAPPED,
PG_CLEAN,
PG_NEED_COMMIT,
PG_NEED_RESCHED,
void remove_from_page_cache(struct page *page)
{
struct address_space *mapping = page->mapping;
+ void (*freepage)(struct page *);
BUG_ON(!PageLocked(page));
+ freepage = mapping->a_ops->freepage;
spin_lock_irq(&mapping->tree_lock);
__remove_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
+
+ if (freepage)
+ freepage(page);
}
EXPORT_SYMBOL(remove_from_page_cache);
__remove_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
+
+ if (mapping->a_ops->freepage)
+ mapping->a_ops->freepage(page);
+
page_cache_release(page); /* pagecache ref */
return 1;
failed:
spin_unlock_irq(&mapping->tree_lock);
swapcache_free(swap, page);
} else {
+ void (*freepage)(struct page *);
+
+ freepage = mapping->a_ops->freepage;
+
__remove_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
+
+ if (freepage != NULL)
+ freepage(page);
}
return 1;
spin_lock(&svc_xprt_class_lock);
list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
struct svc_xprt *newxprt;
+ unsigned short newport;
if (strcmp(xprt_name, xcl->xcl_name))
continue;
spin_lock_bh(&serv->sv_lock);
list_add(&newxprt->xpt_list, &serv->sv_permsocks);
spin_unlock_bh(&serv->sv_lock);
+ newport = svc_xprt_local_port(newxprt);
clear_bit(XPT_BUSY, &newxprt->xpt_flags);
- return svc_xprt_local_port(newxprt);
+ return newport;
}
err:
spin_unlock(&svc_xprt_class_lock);
{
BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags));
xprt->xpt_pool = NULL;
+ /* As soon as we clear busy, the xprt could be closed and
+ * 'put', so we need a reference to call svc_xprt_enqueue with:
+ */
+ svc_xprt_get(xprt);
clear_bit(XPT_BUSY, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
+ svc_xprt_put(xprt);
}
EXPORT_SYMBOL_GPL(svc_xprt_received);