summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/disk-io.c4
-rw-r--r--fs/btrfs/inode.c70
-rw-r--r--fs/btrfs/raid56.c34
-rw-r--r--fs/btrfs/volumes.c10
-rw-r--r--fs/btrfs/volumes.h6
-rw-r--r--fs/ceph/addr.c24
-rw-r--r--fs/ceph/cache.c12
-rw-r--r--fs/cifs/dir.c18
-rw-r--r--fs/cifs/smb2pdu.c4
-rw-r--r--fs/cifs/smb2pdu.h4
-rw-r--r--fs/dax.c29
-rw-r--r--fs/devpts/inode.c69
-rw-r--r--fs/eventpoll.c42
-rw-r--r--fs/ext4/mballoc.c7
-rw-r--r--fs/ext4/xattr.c6
-rw-r--r--fs/jfs/super.c12
-rw-r--r--fs/nfsd/nfs4xdr.c6
-rw-r--r--fs/select.c6
18 files changed, 210 insertions, 153 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 080e2ebb8aa0..f45b61fe9a9a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3516,7 +3516,7 @@ static blk_status_t wait_dev_flush(struct btrfs_device *device)
struct bio *bio = device->flush_bio;
if (!device->flush_bio_sent)
- return 0;
+ return BLK_STS_OK;
device->flush_bio_sent = 0;
wait_for_completion_io(&device->flush_wait);
@@ -3563,7 +3563,7 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
continue;
write_dev_flush(dev);
- dev->last_flush_error = 0;
+ dev->last_flush_error = BLK_STS_OK;
}
/* wait for all the barriers */
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 95c212037095..24bcd5cd9cf2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7924,11 +7924,12 @@ err:
return ret;
}
-static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio,
- int mirror_num)
+static inline blk_status_t submit_dio_repair_bio(struct inode *inode,
+ struct bio *bio,
+ int mirror_num)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- int ret;
+ blk_status_t ret;
BUG_ON(bio_op(bio) == REQ_OP_WRITE);
@@ -7980,10 +7981,10 @@ static int btrfs_check_dio_repairable(struct inode *inode,
return 1;
}
-static int dio_read_error(struct inode *inode, struct bio *failed_bio,
- struct page *page, unsigned int pgoff,
- u64 start, u64 end, int failed_mirror,
- bio_end_io_t *repair_endio, void *repair_arg)
+static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio,
+ struct page *page, unsigned int pgoff,
+ u64 start, u64 end, int failed_mirror,
+ bio_end_io_t *repair_endio, void *repair_arg)
{
struct io_failure_record *failrec;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
@@ -7993,18 +7994,19 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
int read_mode = 0;
int segs;
int ret;
+ blk_status_t status;
BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
ret = btrfs_get_io_failure_record(inode, start, end, &failrec);
if (ret)
- return ret;
+ return errno_to_blk_status(ret);
ret = btrfs_check_dio_repairable(inode, failed_bio, failrec,
failed_mirror);
if (!ret) {
free_io_failure(failure_tree, io_tree, failrec);
- return -EIO;
+ return BLK_STS_IOERR;
}
segs = bio_segments(failed_bio);
@@ -8022,13 +8024,13 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
"Repair DIO Read Error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d\n",
read_mode, failrec->this_mirror, failrec->in_validation);
- ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror);
- if (ret) {
+ status = submit_dio_repair_bio(inode, bio, failrec->this_mirror);
+ if (status) {
free_io_failure(failure_tree, io_tree, failrec);
bio_put(bio);
}
- return ret;
+ return status;
}
struct btrfs_retry_complete {
@@ -8065,8 +8067,8 @@ end:
bio_put(bio);
}
-static int __btrfs_correct_data_nocsum(struct inode *inode,
- struct btrfs_io_bio *io_bio)
+static blk_status_t __btrfs_correct_data_nocsum(struct inode *inode,
+ struct btrfs_io_bio *io_bio)
{
struct btrfs_fs_info *fs_info;
struct bio_vec bvec;
@@ -8076,8 +8078,8 @@ static int __btrfs_correct_data_nocsum(struct inode *inode,
unsigned int pgoff;
u32 sectorsize;
int nr_sectors;
- int ret;
- int err = 0;
+ blk_status_t ret;
+ blk_status_t err = BLK_STS_OK;
fs_info = BTRFS_I(inode)->root->fs_info;
sectorsize = fs_info->sectorsize;
@@ -8183,11 +8185,12 @@ static blk_status_t __btrfs_subio_endio_read(struct inode *inode,
int csum_pos;
bool uptodate = (err == 0);
int ret;
+ blk_status_t status;
fs_info = BTRFS_I(inode)->root->fs_info;
sectorsize = fs_info->sectorsize;
- err = 0;
+ err = BLK_STS_OK;
start = io_bio->logical;
done.inode = inode;
io_bio->bio.bi_iter = io_bio->iter;
@@ -8209,12 +8212,12 @@ try_again:
done.start = start;
init_completion(&done.done);
- ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
- pgoff, start, start + sectorsize - 1,
- io_bio->mirror_num,
- btrfs_retry_endio, &done);
- if (ret) {
- err = errno_to_blk_status(ret);
+ status = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
+ pgoff, start, start + sectorsize - 1,
+ io_bio->mirror_num, btrfs_retry_endio,
+ &done);
+ if (status) {
+ err = status;
goto next;
}
@@ -8250,7 +8253,7 @@ static blk_status_t btrfs_subio_endio_read(struct inode *inode,
if (unlikely(err))
return __btrfs_correct_data_nocsum(inode, io_bio);
else
- return 0;
+ return BLK_STS_OK;
} else {
return __btrfs_subio_endio_read(inode, io_bio, err);
}
@@ -8423,9 +8426,9 @@ static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode,
return 0;
}
-static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
- u64 file_offset, int skip_sum,
- int async_submit)
+static inline blk_status_t
+__btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, u64 file_offset,
+ int skip_sum, int async_submit)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_dio_private *dip = bio->bi_private;
@@ -8488,6 +8491,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
int clone_offset = 0;
int clone_len;
int ret;
+ blk_status_t status;
map_length = orig_bio->bi_iter.bi_size;
submit_len = map_length;
@@ -8537,9 +8541,9 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
*/
atomic_inc(&dip->pending_bios);
- ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
- async_submit);
- if (ret) {
+ status = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
+ async_submit);
+ if (status) {
bio_put(bio);
atomic_dec(&dip->pending_bios);
goto out_err;
@@ -8557,9 +8561,9 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
} while (submit_len > 0);
submit:
- ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
- async_submit);
- if (!ret)
+ status = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
+ async_submit);
+ if (!status)
return 0;
bio_put(bio);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 208638384cd2..2cf6ba40f7c4 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -905,7 +905,7 @@ static void raid_write_end_io(struct bio *bio)
if (!atomic_dec_and_test(&rbio->stripes_pending))
return;
- err = 0;
+ err = BLK_STS_OK;
/* OK, we have read all the stripes we need to. */
max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ?
@@ -1324,7 +1324,7 @@ write_data:
return;
cleanup:
- rbio_orig_end_io(rbio, -EIO);
+ rbio_orig_end_io(rbio, BLK_STS_IOERR);
}
/*
@@ -1475,7 +1475,7 @@ static void raid_rmw_end_io(struct bio *bio)
cleanup:
- rbio_orig_end_io(rbio, -EIO);
+ rbio_orig_end_io(rbio, BLK_STS_IOERR);
}
static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
@@ -1579,7 +1579,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
return 0;
cleanup:
- rbio_orig_end_io(rbio, -EIO);
+ rbio_orig_end_io(rbio, BLK_STS_IOERR);
return -EIO;
finish:
@@ -1795,12 +1795,12 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
void **pointers;
int faila = -1, failb = -1;
struct page *page;
- int err;
+ blk_status_t err;
int i;
pointers = kcalloc(rbio->real_stripes, sizeof(void *), GFP_NOFS);
if (!pointers) {
- err = -ENOMEM;
+ err = BLK_STS_RESOURCE;
goto cleanup_io;
}
@@ -1856,7 +1856,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
* a bad data or Q stripe.
* TODO, we should redo the xor here.
*/
- err = -EIO;
+ err = BLK_STS_IOERR;
goto cleanup;
}
/*
@@ -1882,7 +1882,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
if (rbio->bbio->raid_map[failb] == RAID6_Q_STRIPE) {
if (rbio->bbio->raid_map[faila] ==
RAID5_P_STRIPE) {
- err = -EIO;
+ err = BLK_STS_IOERR;
goto cleanup;
}
/*
@@ -1954,13 +1954,13 @@ pstripe:
}
}
- err = 0;
+ err = BLK_STS_OK;
cleanup:
kfree(pointers);
cleanup_io:
if (rbio->operation == BTRFS_RBIO_READ_REBUILD) {
- if (err == 0)
+ if (err == BLK_STS_OK)
cache_rbio_pages(rbio);
else
clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
@@ -1968,7 +1968,7 @@ cleanup_io:
rbio_orig_end_io(rbio, err);
} else if (rbio->operation == BTRFS_RBIO_REBUILD_MISSING) {
rbio_orig_end_io(rbio, err);
- } else if (err == 0) {
+ } else if (err == BLK_STS_OK) {
rbio->faila = -1;
rbio->failb = -1;
@@ -2005,7 +2005,7 @@ static void raid_recover_end_io(struct bio *bio)
return;
if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
- rbio_orig_end_io(rbio, -EIO);
+ rbio_orig_end_io(rbio, BLK_STS_IOERR);
else
__raid_recover_end_io(rbio);
}
@@ -2104,7 +2104,7 @@ out:
cleanup:
if (rbio->operation == BTRFS_RBIO_READ_REBUILD ||
rbio->operation == BTRFS_RBIO_REBUILD_MISSING)
- rbio_orig_end_io(rbio, -EIO);
+ rbio_orig_end_io(rbio, BLK_STS_IOERR);
return -EIO;
}
@@ -2431,7 +2431,7 @@ submit_write:
nr_data = bio_list_size(&bio_list);
if (!nr_data) {
/* Every parity is right */
- rbio_orig_end_io(rbio, 0);
+ rbio_orig_end_io(rbio, BLK_STS_OK);
return;
}
@@ -2451,7 +2451,7 @@ submit_write:
return;
cleanup:
- rbio_orig_end_io(rbio, -EIO);
+ rbio_orig_end_io(rbio, BLK_STS_IOERR);
}
static inline int is_data_stripe(struct btrfs_raid_bio *rbio, int stripe)
@@ -2519,7 +2519,7 @@ static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio)
return;
cleanup:
- rbio_orig_end_io(rbio, -EIO);
+ rbio_orig_end_io(rbio, BLK_STS_IOERR);
}
/*
@@ -2633,7 +2633,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
return;
cleanup:
- rbio_orig_end_io(rbio, -EIO);
+ rbio_orig_end_io(rbio, BLK_STS_IOERR);
return;
finish:
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index e8b9a269fdde..bd679bc7a1a9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6212,8 +6212,8 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
}
}
-int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
- int mirror_num, int async_submit)
+blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
+ int mirror_num, int async_submit)
{
struct btrfs_device *dev;
struct bio *first_bio = bio;
@@ -6233,7 +6233,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
&map_length, &bbio, mirror_num, 1);
if (ret) {
btrfs_bio_counter_dec(fs_info);
- return ret;
+ return errno_to_blk_status(ret);
}
total_devs = bbio->num_stripes;
@@ -6256,7 +6256,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
}
btrfs_bio_counter_dec(fs_info);
- return ret;
+ return errno_to_blk_status(ret);
}
if (map_length < length) {
@@ -6283,7 +6283,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
dev_nr, async_submit);
}
btrfs_bio_counter_dec(fs_info);
- return 0;
+ return BLK_STS_OK;
}
struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 6f45fd60d15a..93277fc60930 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -74,7 +74,7 @@ struct btrfs_device {
int missing;
int can_discard;
int is_tgtdev_for_dev_replace;
- int last_flush_error;
+ blk_status_t last_flush_error;
int flush_bio_sent;
#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
@@ -416,8 +416,8 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 type);
void btrfs_mapping_init(struct btrfs_mapping_tree *tree);
void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree);
-int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
- int mirror_num, int async_submit);
+blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
+ int mirror_num, int async_submit);
int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
fmode_t flags, void *holder);
int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 50836280a6f8..1bc709fe330a 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -189,7 +189,7 @@ static int ceph_releasepage(struct page *page, gfp_t g)
/*
* read a single page, without unlocking it.
*/
-static int readpage_nounlock(struct file *filp, struct page *page)
+static int ceph_do_readpage(struct file *filp, struct page *page)
{
struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
@@ -219,7 +219,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
err = ceph_readpage_from_fscache(inode, page);
if (err == 0)
- goto out;
+ return -EINPROGRESS;
dout("readpage inode %p file %p page %p index %lu\n",
inode, filp, page, page->index);
@@ -249,8 +249,11 @@ out:
static int ceph_readpage(struct file *filp, struct page *page)
{
- int r = readpage_nounlock(filp, page);
- unlock_page(page);
+ int r = ceph_do_readpage(filp, page);
+ if (r != -EINPROGRESS)
+ unlock_page(page);
+ else
+ r = 0;
return r;
}
@@ -1237,7 +1240,7 @@ retry_locked:
goto retry_locked;
r = writepage_nounlock(page, NULL);
if (r < 0)
- goto fail_nosnap;
+ goto fail_unlock;
goto retry_locked;
}
@@ -1265,11 +1268,14 @@ retry_locked:
}
/* we need to read it. */
- r = readpage_nounlock(file, page);
- if (r < 0)
- goto fail_nosnap;
+ r = ceph_do_readpage(file, page);
+ if (r < 0) {
+ if (r == -EINPROGRESS)
+ return -EAGAIN;
+ goto fail_unlock;
+ }
goto retry_locked;
-fail_nosnap:
+fail_unlock:
unlock_page(page);
return r;
}
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index fd1172823f86..337f88673ed9 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -297,13 +297,7 @@ void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp)
}
}
-static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
-{
- if (!error)
- SetPageUptodate(page);
-}
-
-static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error)
+static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error)
{
if (!error)
SetPageUptodate(page);
@@ -331,7 +325,7 @@ int ceph_readpage_from_fscache(struct inode *inode, struct page *page)
return -ENOBUFS;
ret = fscache_read_or_alloc_page(ci->fscache, page,
- ceph_vfs_readpage_complete, NULL,
+ ceph_readpage_from_fscache_complete, NULL,
GFP_KERNEL);
switch (ret) {
@@ -360,7 +354,7 @@ int ceph_readpages_from_fscache(struct inode *inode,
return -ENOBUFS;
ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
- ceph_vfs_readpage_complete_unlock,
+ ceph_readpage_from_fscache_complete,
NULL, mapping_gfp_mask(mapping));
switch (ret) {
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 56366e984076..e702d48bd023 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -194,15 +194,20 @@ cifs_bp_rename_retry:
}
/*
+ * Don't allow path components longer than the server max.
* Don't allow the separator character in a path component.
* The VFS will not allow "/", but "\" is allowed by posix.
*/
static int
-check_name(struct dentry *direntry)
+check_name(struct dentry *direntry, struct cifs_tcon *tcon)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
int i;
+ if (unlikely(direntry->d_name.len >
+ le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength)))
+ return -ENAMETOOLONG;
+
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
for (i = 0; i < direntry->d_name.len; i++) {
if (direntry->d_name.name[i] == '\\') {
@@ -500,10 +505,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
return finish_no_open(file, res);
}
- rc = check_name(direntry);
- if (rc)
- return rc;
-
xid = get_xid();
cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
@@ -516,6 +517,11 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
}
tcon = tlink_tcon(tlink);
+
+ rc = check_name(direntry, tcon);
+ if (rc)
+ goto out_free_xid;
+
server = tcon->ses->server;
if (server->ops->new_lease_key)
@@ -776,7 +782,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
}
pTcon = tlink_tcon(tlink);
- rc = check_name(direntry);
+ rc = check_name(direntry, pTcon);
if (rc)
goto lookup_out;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 5fb2fc2d0080..97edb4d376cd 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3219,8 +3219,8 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) *
le32_to_cpu(pfs_inf->SectorsPerAllocationUnit);
kst->f_blocks = le64_to_cpu(pfs_inf->TotalAllocationUnits);
- kst->f_bfree = le64_to_cpu(pfs_inf->ActualAvailableAllocationUnits);
- kst->f_bavail = le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits);
+ kst->f_bfree = kst->f_bavail =
+ le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits);
return;
}
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 18700fd25a0b..2826882c81d1 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -84,8 +84,8 @@
#define NUMBER_OF_SMB2_COMMANDS 0x0013
-/* BB FIXME - analyze following length BB */
-#define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
+/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */
+#define MAX_SMB2_HDR_SIZE 0x00b0
#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd)
diff --git a/fs/dax.c b/fs/dax.c
index 306c2b603fb8..ab925dc6647a 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -646,11 +646,10 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
pte_t pte, *ptep = NULL;
pmd_t *pmdp = NULL;
spinlock_t *ptl;
- bool changed;
i_mmap_lock_read(mapping);
vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
- unsigned long address;
+ unsigned long address, start, end;
cond_resched();
@@ -658,8 +657,13 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
continue;
address = pgoff_address(index, vma);
- changed = false;
- if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl))
+
+ /*
+ * Note because we provide start/end to follow_pte_pmd it will
+ * call mmu_notifier_invalidate_range_start() on our behalf
+ * before taking any lock.
+ */
+ if (follow_pte_pmd(vma->vm_mm, address, &start, &end, &ptep, &pmdp, &ptl))
continue;
if (pmdp) {
@@ -676,7 +680,7 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
pmd = pmd_wrprotect(pmd);
pmd = pmd_mkclean(pmd);
set_pmd_at(vma->vm_mm, address, pmdp, pmd);
- changed = true;
+ mmu_notifier_invalidate_range(vma->vm_mm, start, end);
unlock_pmd:
spin_unlock(ptl);
#endif
@@ -691,13 +695,12 @@ unlock_pmd:
pte = pte_wrprotect(pte);
pte = pte_mkclean(pte);
set_pte_at(vma->vm_mm, address, ptep, pte);
- changed = true;
+ mmu_notifier_invalidate_range(vma->vm_mm, start, end);
unlock_pte:
pte_unmap_unlock(ptep, ptl);
}
- if (changed)
- mmu_notifier_invalidate_page(vma->vm_mm, address);
+ mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
}
i_mmap_unlock_read(mapping);
}
@@ -1383,6 +1386,16 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
+ /*
+ * Make sure that the faulting address's PMD offset (color) matches
+ * the PMD offset from the start of the file. This is necessary so
+ * that a PMD range in the page table overlaps exactly with a PMD
+ * range in the radix tree.
+ */
+ if ((vmf->pgoff & PG_PMD_COLOUR) !=
+ ((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR))
+ goto fallback;
+
/* Fall back to PTEs if we're going to COW */
if (write && !(vma->vm_flags & VM_SHARED))
goto fallback;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 44dfbca9306f..7eae33ffa3fc 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -133,7 +133,51 @@ static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb)
return sb->s_fs_info;
}
-struct pts_fs_info *devpts_acquire(struct file *filp, struct vfsmount **ptsmnt)
+static int devpts_ptmx_path(struct path *path)
+{
+ struct super_block *sb;
+ int err;
+
+ /* Has the devpts filesystem already been found? */
+ if (path->mnt->mnt_sb->s_magic == DEVPTS_SUPER_MAGIC)
+ return 0;
+
+ /* Is a devpts filesystem at "pts" in the same directory? */
+ err = path_pts(path);
+ if (err)
+ return err;
+
+ /* Is the path the root of a devpts filesystem? */
+ sb = path->mnt->mnt_sb;
+ if ((sb->s_magic != DEVPTS_SUPER_MAGIC) ||
+ (path->mnt->mnt_root != sb->s_root))
+ return -ENODEV;
+
+ return 0;
+}
+
+struct vfsmount *devpts_mntget(struct file *filp, struct pts_fs_info *fsi)
+{
+ struct path path;
+ int err;
+
+ path = filp->f_path;
+ path_get(&path);
+
+ err = devpts_ptmx_path(&path);
+ dput(path.dentry);
+ if (err) {
+ mntput(path.mnt);
+ path.mnt = ERR_PTR(err);
+ }
+ if (DEVPTS_SB(path.mnt->mnt_sb) != fsi) {
+ mntput(path.mnt);
+ path.mnt = ERR_PTR(-ENODEV);
+ }
+ return path.mnt;
+}
+
+struct pts_fs_info *devpts_acquire(struct file *filp)
{
struct pts_fs_info *result;
struct path path;
@@ -142,31 +186,18 @@ struct pts_fs_info *devpts_acquire(struct file *filp, struct vfsmount **ptsmnt)
path = filp->f_path;
path_get(&path);
- *ptsmnt = NULL;
- /* Has the devpts filesystem already been found? */
- sb = path.mnt->mnt_sb;
- if (sb->s_magic != DEVPTS_SUPER_MAGIC) {
- /* Is a devpts filesystem at "pts" in the same directory? */
- err = path_pts(&path);
- if (err) {
- result = ERR_PTR(err);
- goto out;
- }
-
- /* Is the path the root of a devpts filesystem? */
- result = ERR_PTR(-ENODEV);
- sb = path.mnt->mnt_sb;
- if ((sb->s_magic != DEVPTS_SUPER_MAGIC) ||
- (path.mnt->mnt_root != sb->s_root))
- goto out;
+ err = devpts_ptmx_path(&path);
+ if (err) {
+ result = ERR_PTR(err);
+ goto out;
}
/*
* pty code needs to hold extra references in case of last /dev/tty close
*/
+ sb = path.mnt->mnt_sb;
atomic_inc(&sb->s_active);
- *ptsmnt = mntget(path.mnt);
result = DEVPTS_SB(sb);
out:
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index e767e4389cb1..adbe328b957c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -600,8 +600,13 @@ static void ep_remove_wait_queue(struct eppoll_entry *pwq)
wait_queue_head_t *whead;
rcu_read_lock();
- /* If it is cleared by POLLFREE, it should be rcu-safe */
- whead = rcu_dereference(pwq->whead);
+ /*
+ * If it is cleared by POLLFREE, it should be rcu-safe.
+ * If we read NULL we need a barrier paired with
+ * smp_store_release() in ep_poll_callback(), otherwise
+ * we rely on whead->lock.
+ */
+ whead = smp_load_acquire(&pwq->whead);
if (whead)
remove_wait_queue(whead, &pwq->wait);
rcu_read_unlock();
@@ -1134,17 +1139,6 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
struct eventpoll *ep = epi->ep;
int ewake = 0;
- if ((unsigned long)key & POLLFREE) {
- ep_pwq_from_wait(wait)->whead = NULL;
- /*
- * whead = NULL above can race with ep_remove_wait_queue()
- * which can do another remove_wait_queue() after us, so we
- * can't use __remove_wait_queue(). whead->lock is held by
- * the caller.
- */
- list_del_init(&wait->entry);
- }
-
spin_lock_irqsave(&ep->lock, flags);
ep_set_busy_poll_napi_id(epi);
@@ -1228,10 +1222,26 @@ out_unlock:
if (pwake)
ep_poll_safewake(&ep->poll_wait);
- if (epi->event.events & EPOLLEXCLUSIVE)
- return ewake;
+ if (!(epi->event.events & EPOLLEXCLUSIVE))
+ ewake = 1;
+
+ if ((unsigned long)key & POLLFREE) {
+ /*
+ * If we race with ep_remove_wait_queue() it can miss
+ * ->whead = NULL and do another remove_wait_queue() after
+ * us, so we can't use __remove_wait_queue().
+ */
+ list_del_init(&wait->entry);
+ /*
+ * ->whead != NULL protects us from the race with ep_free()
+ * or ep_remove(), ep_remove_wait_queue() takes whead->lock
+ * held by the caller. Once we nullify it, nothing protects
+ * ep/epi or even wait.
+ */
+ smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL);
+ }
- return 1;
+ return ewake;
}
/*
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5a1052627a81..701085620cd8 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2300,7 +2300,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
EXT4_MAX_BLOCK_LOG_SIZE);
struct sg {
struct ext4_group_info info;
- ext4_grpblk_t counters[blocksize_bits + 2];
+ ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2];
} sg;
group--;
@@ -2309,6 +2309,9 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
" 2^0 2^1 2^2 2^3 2^4 2^5 2^6 "
" 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n");
+ i = (blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
+ sizeof(struct ext4_group_info);
+
grinfo = ext4_get_group_info(sb, group);
/* Load the group info in memory only if not already loaded. */
if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) {
@@ -2320,7 +2323,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
buddy_loaded = 1;
}
- memcpy(&sg, ext4_get_group_info(sb, group), sizeof(sg));
+ memcpy(&sg, ext4_get_group_info(sb, group), i);
if (buddy_loaded)
ext4_mb_unload_buddy(&e4b);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 82a5af9f6668..3dd970168448 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1543,7 +1543,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
/* Clear padding bytes. */
memset(val + i->value_len, 0, new_size - i->value_len);
}
- return 0;
+ goto update_hash;
}
/* Compute min_offs and last. */
@@ -1707,6 +1707,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
here->e_value_size = cpu_to_le32(i->value_len);
}
+update_hash:
if (i->value) {
__le32 hash = 0;
@@ -1725,7 +1726,8 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
here->e_name_len,
&crc32c_hash, 1);
} else if (is_block) {
- __le32 *value = s->base + min_offs - new_size;
+ __le32 *value = s->base + le16_to_cpu(
+ here->e_value_offs);
hash = ext4_xattr_hash_entry(here->e_name,
here->e_name_len, value,
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 78b41e1d5c67..60726ae7cf26 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -619,16 +619,10 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
if (!sb->s_root)
goto out_no_root;
- /* logical blocks are represented by 40 bits in pxd_t, etc. */
- sb->s_maxbytes = ((u64) sb->s_blocksize) << 40;
-#if BITS_PER_LONG == 32
- /*
- * Page cache is indexed by long.
- * I would use MAX_LFS_FILESIZE, but it's only half as big
+ /* logical blocks are represented by 40 bits in pxd_t, etc.
+ * and page cache is indexed by long
*/
- sb->s_maxbytes = min(((u64) PAGE_SIZE << 32) - 1,
- (u64)sb->s_maxbytes);
-#endif
+ sb->s_maxbytes = min(((loff_t)sb->s_blocksize) << 40, MAX_LFS_FILESIZE);
sb->s_time_gran = 1;
return 0;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 20fbcab97753..5f940d2a136b 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -144,7 +144,7 @@ static void next_decode_page(struct nfsd4_compoundargs *argp)
argp->p = page_address(argp->pagelist[0]);
argp->pagelist++;
if (argp->pagelen < PAGE_SIZE) {
- argp->end = argp->p + (argp->pagelen>>2);
+ argp->end = argp->p + XDR_QUADLEN(argp->pagelen);
argp->pagelen = 0;
} else {
argp->end = argp->p + (PAGE_SIZE>>2);
@@ -1279,9 +1279,7 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
argp->pagelen -= pages * PAGE_SIZE;
len -= pages * PAGE_SIZE;
- argp->p = (__be32 *)page_address(argp->pagelist[0]);
- argp->pagelist++;
- argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE);
+ next_decode_page(argp);
}
argp->p += XDR_QUADLEN(len);
diff --git a/fs/select.c b/fs/select.c
index 9d5f15ed87fe..c6362e38ae92 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -1164,11 +1164,7 @@ int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
if (ufdset) {
return compat_get_bitmap(fdset, ufdset, nr);
} else {
- /* Tricky, must clear full unsigned long in the
- * kernel fdset at the end, ALIGN makes sure that
- * actually happens.
- */
- memset(fdset, 0, ALIGN(nr, BITS_PER_LONG));
+ zero_fd_set(nr, fdset);
return 0;
}
}