summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/fuse/cuse.c4
-rw-r--r--fs/fuse/file.c56
-rw-r--r--fs/fuse/fuse_i.h9
-rw-r--r--fs/nfs/blocklayout/blocklayout.c13
-rw-r--r--fs/nfs/callback.h3
-rw-r--r--fs/nfs/callback_proc.c69
-rw-r--r--fs/nfs/callback_xdr.c12
-rw-r--r--fs/nfs/file.c12
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c2
-rw-r--r--fs/nfs/inode.c2
-rw-r--r--fs/nfs/internal.h6
-rw-r--r--fs/nfs/nfs4file.c33
-rw-r--r--fs/nfs/nfs4proc.c63
-rw-r--r--fs/nfs/nfs4session.c54
-rw-r--r--fs/nfs/nfs4session.h8
-rw-r--r--fs/nfs/pnfs_nfs.c16
-rw-r--r--fs/overlayfs/copy_up.c35
-rw-r--r--fs/overlayfs/dir.c61
-rw-r--r--fs/overlayfs/overlayfs.h1
-rw-r--r--fs/overlayfs/readdir.c53
-rw-r--r--fs/overlayfs/super.c18
21 files changed, 369 insertions, 161 deletions
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 8e3ee1936c7e..c5b6b7165489 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -90,7 +90,7 @@ static struct list_head *cuse_conntbl_head(dev_t devt)
static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to)
{
- struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp };
+ struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp);
loff_t pos = 0;
return fuse_direct_io(&io, to, &pos, FUSE_DIO_CUSE);
@@ -98,7 +98,7 @@ static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to)
static ssize_t cuse_write_iter(struct kiocb *kiocb, struct iov_iter *from)
{
- struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp };
+ struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp);
loff_t pos = 0;
/*
* No locking or generic_write_checks(), the server is
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b03d253ece15..9dde38f12c07 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -528,6 +528,11 @@ static void fuse_release_user_pages(struct fuse_req *req, int write)
}
}
+static void fuse_io_release(struct kref *kref)
+{
+ kfree(container_of(kref, struct fuse_io_priv, refcnt));
+}
+
static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io)
{
if (io->err)
@@ -585,8 +590,9 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
}
io->iocb->ki_complete(io->iocb, res, 0);
- kfree(io);
}
+
+ kref_put(&io->refcnt, fuse_io_release);
}
static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req)
@@ -613,6 +619,7 @@ static size_t fuse_async_req_send(struct fuse_conn *fc, struct fuse_req *req,
size_t num_bytes, struct fuse_io_priv *io)
{
spin_lock(&io->lock);
+ kref_get(&io->refcnt);
io->size += num_bytes;
io->reqs++;
spin_unlock(&io->lock);
@@ -691,7 +698,7 @@ static void fuse_short_read(struct fuse_req *req, struct inode *inode,
static int fuse_do_readpage(struct file *file, struct page *page)
{
- struct fuse_io_priv io = { .async = 0, .file = file };
+ struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
struct inode *inode = page->mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
@@ -984,7 +991,7 @@ static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
size_t res;
unsigned offset;
unsigned i;
- struct fuse_io_priv io = { .async = 0, .file = file };
+ struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
for (i = 0; i < req->num_pages; i++)
fuse_wait_on_page_writeback(inode, req->pages[i]->index);
@@ -1240,6 +1247,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
size_t *nbytesp, int write)
{
size_t nbytes = 0; /* # bytes already packed in req */
+ ssize_t ret = 0;
/* Special case for kernel I/O: can copy directly into the buffer */
if (ii->type & ITER_KVEC) {
@@ -1259,13 +1267,12 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
while (nbytes < *nbytesp && req->num_pages < req->max_pages) {
unsigned npages;
size_t start;
- ssize_t ret = iov_iter_get_pages(ii,
- &req->pages[req->num_pages],
+ ret = iov_iter_get_pages(ii, &req->pages[req->num_pages],
*nbytesp - nbytes,
req->max_pages - req->num_pages,
&start);
if (ret < 0)
- return ret;
+ break;
iov_iter_advance(ii, ret);
nbytes += ret;
@@ -1288,7 +1295,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
*nbytesp = nbytes;
- return 0;
+ return ret;
}
static inline int fuse_iter_npages(const struct iov_iter *ii_p)
@@ -1312,6 +1319,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
pgoff_t idx_to = (pos + count - 1) >> PAGE_CACHE_SHIFT;
ssize_t res = 0;
struct fuse_req *req;
+ int err = 0;
if (io->async)
req = fuse_get_req_for_background(fc, fuse_iter_npages(iter));
@@ -1332,11 +1340,9 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
size_t nres;
fl_owner_t owner = current->files;
size_t nbytes = min(count, nmax);
- int err = fuse_get_user_pages(req, iter, &nbytes, write);
- if (err) {
- res = err;
+ err = fuse_get_user_pages(req, iter, &nbytes, write);
+ if (err && !nbytes)
break;
- }
if (write)
nres = fuse_send_write(req, io, pos, nbytes, owner);
@@ -1346,11 +1352,11 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
if (!io->async)
fuse_release_user_pages(req, !write);
if (req->out.h.error) {
- if (!res)
- res = req->out.h.error;
+ err = req->out.h.error;
break;
} else if (nres > nbytes) {
- res = -EIO;
+ res = 0;
+ err = -EIO;
break;
}
count -= nres;
@@ -1374,7 +1380,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
if (res > 0)
*ppos = pos;
- return res;
+ return res > 0 ? res : err;
}
EXPORT_SYMBOL_GPL(fuse_direct_io);
@@ -1398,7 +1404,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
- struct fuse_io_priv io = { .async = 0, .file = iocb->ki_filp };
+ struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb->ki_filp);
return __fuse_direct_read(&io, to, &iocb->ki_pos);
}
@@ -1406,7 +1412,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
- struct fuse_io_priv io = { .async = 0, .file = file };
+ struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
ssize_t res;
if (is_bad_inode(inode))
@@ -2843,6 +2849,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
loff_t i_size;
size_t count = iov_iter_count(iter);
struct fuse_io_priv *io;
+ bool is_sync = is_sync_kiocb(iocb);
pos = offset;
inode = file->f_mapping->host;
@@ -2863,6 +2870,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
if (!io)
return -ENOMEM;
spin_lock_init(&io->lock);
+ kref_init(&io->refcnt);
io->reqs = 1;
io->bytes = -1;
io->size = 0;
@@ -2882,12 +2890,18 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
* to wait on real async I/O requests, so we must submit this request
* synchronously.
*/
- if (!is_sync_kiocb(iocb) && (offset + count > i_size) &&
+ if (!is_sync && (offset + count > i_size) &&
iov_iter_rw(iter) == WRITE)
io->async = false;
- if (io->async && is_sync_kiocb(iocb))
+ if (io->async && is_sync) {
+ /*
+ * Additional reference to keep io around after
+ * calling fuse_aio_complete()
+ */
+ kref_get(&io->refcnt);
io->done = &wait;
+ }
if (iov_iter_rw(iter) == WRITE) {
ret = fuse_direct_io(io, iter, &pos, FUSE_DIO_WRITE);
@@ -2900,14 +2914,14 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
/* we have a non-extending, async request, so return */
- if (!is_sync_kiocb(iocb))
+ if (!is_sync)
return -EIOCBQUEUED;
wait_for_completion(&wait);
ret = fuse_get_res_by_io(io);
}
- kfree(io);
+ kref_put(&io->refcnt, fuse_io_release);
if (iov_iter_rw(iter) == WRITE) {
if (ret > 0)
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index ce394b5fe6b4..eddbe02c4028 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -22,6 +22,7 @@
#include <linux/rbtree.h>
#include <linux/poll.h>
#include <linux/workqueue.h>
+#include <linux/kref.h>
/** Max number of pages that can be used in a single read request */
#define FUSE_MAX_PAGES_PER_REQ 32
@@ -243,6 +244,7 @@ struct fuse_args {
/** The request IO state (for asynchronous processing) */
struct fuse_io_priv {
+ struct kref refcnt;
int async;
spinlock_t lock;
unsigned reqs;
@@ -256,6 +258,13 @@ struct fuse_io_priv {
struct completion *done;
};
+#define FUSE_IO_PRIV_SYNC(f) \
+{ \
+ .refcnt = { ATOMIC_INIT(1) }, \
+ .async = 0, \
+ .file = f, \
+}
+
/**
* Request flags
*
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index ddd0138f410c..8bc870e4c467 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -743,7 +743,7 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
static bool
is_aligned_req(struct nfs_pageio_descriptor *pgio,
- struct nfs_page *req, unsigned int alignment)
+ struct nfs_page *req, unsigned int alignment, bool is_write)
{
/*
* Always accept buffered writes, higher layers take care of the
@@ -758,7 +758,8 @@ is_aligned_req(struct nfs_pageio_descriptor *pgio,
if (IS_ALIGNED(req->wb_bytes, alignment))
return true;
- if (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode)) {
+ if (is_write &&
+ (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode))) {
/*
* If the write goes up to the inode size, just write
* the full page. Data past the inode size is
@@ -775,7 +776,7 @@ is_aligned_req(struct nfs_pageio_descriptor *pgio,
static void
bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
- if (!is_aligned_req(pgio, req, SECTOR_SIZE)) {
+ if (!is_aligned_req(pgio, req, SECTOR_SIZE, false)) {
nfs_pageio_reset_read_mds(pgio);
return;
}
@@ -791,7 +792,7 @@ static size_t
bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
struct nfs_page *req)
{
- if (!is_aligned_req(pgio, req, SECTOR_SIZE))
+ if (!is_aligned_req(pgio, req, SECTOR_SIZE, false))
return 0;
return pnfs_generic_pg_test(pgio, prev, req);
}
@@ -824,7 +825,7 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
u64 wb_size;
- if (!is_aligned_req(pgio, req, PAGE_SIZE)) {
+ if (!is_aligned_req(pgio, req, PAGE_SIZE, true)) {
nfs_pageio_reset_write_mds(pgio);
return;
}
@@ -846,7 +847,7 @@ static size_t
bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
struct nfs_page *req)
{
- if (!is_aligned_req(pgio, req, PAGE_SIZE))
+ if (!is_aligned_req(pgio, req, PAGE_SIZE, true))
return 0;
return pnfs_generic_pg_test(pgio, prev, req);
}
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index ff8195bd75ea..5fe1cecbf9f0 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -37,10 +37,11 @@ enum nfs4_callback_opnum {
OP_CB_ILLEGAL = 10044,
};
+struct nfs4_slot;
struct cb_process_state {
__be32 drc_status;
struct nfs_client *clp;
- u32 slotid;
+ struct nfs4_slot *slot;
u32 minorversion;
struct net *net;
};
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index f0939d097406..618ced381a14 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -354,47 +354,38 @@ out:
* a single outstanding callback request at a time.
*/
static __be32
-validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
+validate_seqid(const struct nfs4_slot_table *tbl, const struct nfs4_slot *slot,
+ const struct cb_sequenceargs * args)
{
- struct nfs4_slot *slot;
-
- dprintk("%s enter. slotid %u seqid %u\n",
- __func__, args->csa_slotid, args->csa_sequenceid);
+ dprintk("%s enter. slotid %u seqid %u, slot table seqid: %u\n",
+ __func__, args->csa_slotid, args->csa_sequenceid, slot->seq_nr);
- if (args->csa_slotid >= NFS41_BC_MAX_CALLBACKS)
+ if (args->csa_slotid > tbl->server_highest_slotid)
return htonl(NFS4ERR_BADSLOT);
- slot = tbl->slots + args->csa_slotid;
- dprintk("%s slot table seqid: %u\n", __func__, slot->seq_nr);
-
- /* Normal */
- if (likely(args->csa_sequenceid == slot->seq_nr + 1))
- goto out_ok;
-
/* Replay */
if (args->csa_sequenceid == slot->seq_nr) {
dprintk("%s seqid %u is a replay\n",
__func__, args->csa_sequenceid);
+ if (nfs4_test_locked_slot(tbl, slot->slot_nr))
+ return htonl(NFS4ERR_DELAY);
/* Signal process_op to set this error on next op */
if (args->csa_cachethis == 0)
return htonl(NFS4ERR_RETRY_UNCACHED_REP);
- /* The ca_maxresponsesize_cached is 0 with no DRC */
- else if (args->csa_cachethis == 1)
- return htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE);
+ /* Liar! We never allowed you to set csa_cachethis != 0 */
+ return htonl(NFS4ERR_SEQ_FALSE_RETRY);
}
/* Wraparound */
- if (args->csa_sequenceid == 1 && (slot->seq_nr + 1) == 0) {
- slot->seq_nr = 1;
- goto out_ok;
- }
+ if (unlikely(slot->seq_nr == 0xFFFFFFFFU)) {
+ if (args->csa_sequenceid == 1)
+ return htonl(NFS4_OK);
+ } else if (likely(args->csa_sequenceid == slot->seq_nr + 1))
+ return htonl(NFS4_OK);
/* Misordered request */
return htonl(NFS4ERR_SEQ_MISORDERED);
-out_ok:
- tbl->highest_used_slotid = args->csa_slotid;
- return htonl(NFS4_OK);
}
/*
@@ -473,6 +464,12 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
tbl = &clp->cl_session->bc_slot_table;
slot = tbl->slots + args->csa_slotid;
+ /* Set up res before grabbing the spinlock */
+ memcpy(&res->csr_sessionid, &args->csa_sessionid,
+ sizeof(res->csr_sessionid));
+ res->csr_sequenceid = args->csa_sequenceid;
+ res->csr_slotid = args->csa_slotid;
+
spin_lock(&tbl->slot_tbl_lock);
/* state manager is resetting the session */
if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
@@ -485,18 +482,26 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
goto out_unlock;
}
- memcpy(&res->csr_sessionid, &args->csa_sessionid,
- sizeof(res->csr_sessionid));
- res->csr_sequenceid = args->csa_sequenceid;
- res->csr_slotid = args->csa_slotid;
- res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
- res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
+ status = htonl(NFS4ERR_BADSLOT);
+ slot = nfs4_lookup_slot(tbl, args->csa_slotid);
+ if (IS_ERR(slot))
+ goto out_unlock;
+
+ res->csr_highestslotid = tbl->server_highest_slotid;
+ res->csr_target_highestslotid = tbl->target_highest_slotid;
- status = validate_seqid(tbl, args);
+ status = validate_seqid(tbl, slot, args);
if (status)
goto out_unlock;
+ if (!nfs4_try_to_lock_slot(tbl, slot)) {
+ status = htonl(NFS4ERR_DELAY);
+ goto out_unlock;
+ }
+ cps->slot = slot;
- cps->slotid = args->csa_slotid;
+ /* The ca_maxresponsesize_cached is 0 with no DRC */
+ if (args->csa_cachethis != 0)
+ return htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE);
/*
* Check for pending referring calls. If a match is found, a
@@ -513,7 +518,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
* If CB_SEQUENCE returns an error, then the state of the slot
* (sequence ID, cached reply) MUST NOT change.
*/
- slot->seq_nr++;
+ slot->seq_nr = args->csa_sequenceid;
out_unlock:
spin_unlock(&tbl->slot_tbl_lock);
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 646cdac73488..976c90608e56 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -752,7 +752,8 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
return htonl(NFS_OK);
}
-static void nfs4_callback_free_slot(struct nfs4_session *session)
+static void nfs4_callback_free_slot(struct nfs4_session *session,
+ struct nfs4_slot *slot)
{
struct nfs4_slot_table *tbl = &session->bc_slot_table;
@@ -761,15 +762,17 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
* Let the state manager know callback processing done.
* A single slot, so highest used slotid is either 0 or -1
*/
- tbl->highest_used_slotid = NFS4_NO_SLOT;
+ nfs4_free_slot(tbl, slot);
nfs4_slot_tbl_drain_complete(tbl);
spin_unlock(&tbl->slot_tbl_lock);
}
static void nfs4_cb_free_slot(struct cb_process_state *cps)
{
- if (cps->slotid != NFS4_NO_SLOT)
- nfs4_callback_free_slot(cps->clp->cl_session);
+ if (cps->slot) {
+ nfs4_callback_free_slot(cps->clp->cl_session, cps->slot);
+ cps->slot = NULL;
+ }
}
#else /* CONFIG_NFS_V4_1 */
@@ -893,7 +896,6 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
struct cb_process_state cps = {
.drc_status = 0,
.clp = NULL,
- .slotid = NFS4_NO_SLOT,
.net = SVC_NET(rqstp),
};
unsigned int nops = 0;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 748bb813b8ec..89bf093d342a 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -233,7 +233,7 @@ EXPORT_SYMBOL_GPL(nfs_file_mmap);
* nfs_file_write() that a write error occurred, and hence cause it to
* fall back to doing a synchronous write.
*/
-int
+static int
nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
{
struct nfs_open_context *ctx = nfs_file_open_context(file);
@@ -263,9 +263,8 @@ nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
out:
return ret;
}
-EXPORT_SYMBOL_GPL(nfs_file_fsync_commit);
-static int
+int
nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
int ret;
@@ -273,13 +272,15 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
trace_nfs_fsync_enter(inode);
- nfs_inode_dio_wait(inode);
+ inode_dio_wait(inode);
do {
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (ret != 0)
break;
inode_lock(inode);
ret = nfs_file_fsync_commit(file, start, end, datasync);
+ if (!ret)
+ ret = pnfs_sync_inode(inode, !!datasync);
inode_unlock(inode);
/*
* If nfs_file_fsync_commit detected a server reboot, then
@@ -293,6 +294,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
trace_nfs_fsync_exit(inode, ret);
return ret;
}
+EXPORT_SYMBOL_GPL(nfs_file_fsync);
/*
* Decide whether a read/modify/write cycle may be more efficient
@@ -368,7 +370,7 @@ start:
/*
* Wait for O_DIRECT to complete
*/
- nfs_inode_dio_wait(mapping->host);
+ inode_dio_wait(mapping->host);
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index eb370460ce20..add0e5a70bd6 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -418,6 +418,8 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
pnfs_error_mark_layout_for_return(ino, lseg);
} else
pnfs_error_mark_layout_for_return(ino, lseg);
+ ds = NULL;
+ goto out;
}
out_update_creds:
if (ff_layout_update_mirror_cred(mirror, ds))
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 86faecf8f328..33d18c411905 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -141,7 +141,7 @@ void nfs_evict_inode(struct inode *inode)
int nfs_sync_inode(struct inode *inode)
{
- nfs_inode_dio_wait(inode);
+ inode_dio_wait(inode);
return nfs_wb_all(inode);
}
EXPORT_SYMBOL_GPL(nfs_sync_inode);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9a547aa3ec8e..565f8135ae1f 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -358,7 +358,7 @@ int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
/* file.c */
-int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int);
+int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
loff_t nfs_file_llseek(struct file *, loff_t, int);
ssize_t nfs_file_read(struct kiocb *, struct iov_iter *);
ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *,
@@ -515,10 +515,6 @@ extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry);
/* direct.c */
void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
struct nfs_direct_req *dreq);
-static inline void nfs_inode_dio_wait(struct inode *inode)
-{
- inode_dio_wait(inode);
-}
extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
/* nfs4proc.c */
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 57ca1c8039c1..22c35abbee9d 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -128,37 +128,6 @@ nfs4_file_flush(struct file *file, fl_owner_t id)
return vfs_fsync(file, 0);
}
-static int
-nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
-{
- int ret;
- struct inode *inode = file_inode(file);
-
- trace_nfs_fsync_enter(inode);
-
- nfs_inode_dio_wait(inode);
- do {
- ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- if (ret != 0)
- break;
- inode_lock(inode);
- ret = nfs_file_fsync_commit(file, start, end, datasync);
- if (!ret)
- ret = pnfs_sync_inode(inode, !!datasync);
- inode_unlock(inode);
- /*
- * If nfs_file_fsync_commit detected a server reboot, then
- * resend all dirty pages that might have been covered by
- * the NFS_CONTEXT_RESEND_WRITES flag
- */
- start = 0;
- end = LLONG_MAX;
- } while (ret == -EAGAIN);
-
- trace_nfs_fsync_exit(inode, ret);
- return ret;
-}
-
#ifdef CONFIG_NFS_V4_2
static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
{
@@ -266,7 +235,7 @@ const struct file_operations nfs4_file_operations = {
.open = nfs4_file_open,
.flush = nfs4_file_flush,
.release = nfs_file_release,
- .fsync = nfs4_file_fsync,
+ .fsync = nfs_file_fsync,
.lock = nfs_lock,
.flock = nfs_flock,
.splice_read = nfs_file_splice_read,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 400a70b3be7b..327b8c34d360 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6783,13 +6783,26 @@ nfs41_same_server_scope(struct nfs41_server_scope *a,
return false;
}
+static void
+nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
+{
+}
+
+static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
+ .rpc_call_done = &nfs4_bind_one_conn_to_session_done,
+};
+
/*
- * nfs4_proc_bind_conn_to_session()
+ * nfs4_proc_bind_one_conn_to_session()
*
* The 4.1 client currently uses the same TCP connection for the
* fore and backchannel.
*/
-int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred)
+static
+int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
+ struct rpc_xprt *xprt,
+ struct nfs_client *clp,
+ struct rpc_cred *cred)
{
int status;
struct nfs41_bind_conn_to_session_args args = {
@@ -6804,6 +6817,14 @@ int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred
.rpc_resp = &res,
.rpc_cred = cred,
};
+ struct rpc_task_setup task_setup_data = {
+ .rpc_client = clnt,
+ .rpc_xprt = xprt,
+ .callback_ops = &nfs4_bind_one_conn_to_session_ops,
+ .rpc_message = &msg,
+ .flags = RPC_TASK_TIMEOUT,
+ };
+ struct rpc_task *task;
dprintk("--> %s\n", __func__);
@@ -6811,7 +6832,16 @@ int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred
if (!(clp->cl_session->flags & SESSION4_BACK_CHAN))
args.dir = NFS4_CDFC4_FORE;
- status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+ /* Do not set the backchannel flag unless this is clnt->cl_xprt */
+ if (xprt != rcu_access_pointer(clnt->cl_xprt))
+ args.dir = NFS4_CDFC4_FORE;
+
+ task = rpc_run_task(&task_setup_data);
+ if (!IS_ERR(task)) {
+ status = task->tk_status;
+ rpc_put_task(task);
+ } else
+ status = PTR_ERR(task);
trace_nfs4_bind_conn_to_session(clp, status);
if (status == 0) {
if (memcmp(res.sessionid.data,
@@ -6838,6 +6868,31 @@ out:
return status;
}
+struct rpc_bind_conn_calldata {
+ struct nfs_client *clp;
+ struct rpc_cred *cred;
+};
+
+static int
+nfs4_proc_bind_conn_to_session_callback(struct rpc_clnt *clnt,
+ struct rpc_xprt *xprt,
+ void *calldata)
+{
+ struct rpc_bind_conn_calldata *p = calldata;
+
+ return nfs4_proc_bind_one_conn_to_session(clnt, xprt, p->clp, p->cred);
+}
+
+int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred)
+{
+ struct rpc_bind_conn_calldata data = {
+ .clp = clp,
+ .cred = cred,
+ };
+ return rpc_clnt_iterate_for_each_xprt(clp->cl_rpcclient,
+ nfs4_proc_bind_conn_to_session_callback, &data);
+}
+
/*
* Minimum set of SP4_MACH_CRED operations from RFC 5661 in the enforce map
* and operations we'd like to see to enable certain features in the allow map
@@ -7320,7 +7375,7 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
args->bc_attrs.max_resp_sz = PAGE_SIZE;
args->bc_attrs.max_resp_sz_cached = 0;
args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS;
- args->bc_attrs.max_reqs = 1;
+ args->bc_attrs.max_reqs = NFS41_BC_MAX_CALLBACKS;
dprintk("%s: Back Channel : max_rqst_sz=%u max_resp_sz=%u "
"max_resp_sz_cached=%u max_ops=%u max_reqs=%u\n",
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index e23366effcfb..332d06e64fa9 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -135,6 +135,43 @@ static struct nfs4_slot *nfs4_find_or_create_slot(struct nfs4_slot_table *tbl,
return ERR_PTR(-ENOMEM);
}
+static void nfs4_lock_slot(struct nfs4_slot_table *tbl,
+ struct nfs4_slot *slot)
+{
+ u32 slotid = slot->slot_nr;
+
+ __set_bit(slotid, tbl->used_slots);
+ if (slotid > tbl->highest_used_slotid ||
+ tbl->highest_used_slotid == NFS4_NO_SLOT)
+ tbl->highest_used_slotid = slotid;
+ slot->generation = tbl->generation;
+}
+
+/*
+ * nfs4_try_to_lock_slot - Given a slot try to allocate it
+ *
+ * Note: must be called with the slot_tbl_lock held.
+ */
+bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot)
+{
+ if (nfs4_test_locked_slot(tbl, slot->slot_nr))
+ return false;
+ nfs4_lock_slot(tbl, slot);
+ return true;
+}
+
+/*
+ * nfs4_lookup_slot - Find a slot but don't allocate it
+ *
+ * Note: must be called with the slot_tbl_lock held.
+ */
+struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid)
+{
+ if (slotid <= tbl->max_slotid)
+ return nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
+ return ERR_PTR(-E2BIG);
+}
+
/*
* nfs4_alloc_slot - efficiently look for a free slot
*
@@ -153,18 +190,11 @@ struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl)
__func__, tbl->used_slots[0], tbl->highest_used_slotid,
tbl->max_slotid + 1);
slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slotid + 1);
- if (slotid > tbl->max_slotid)
- goto out;
- ret = nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
- if (IS_ERR(ret))
- goto out;
- __set_bit(slotid, tbl->used_slots);
- if (slotid > tbl->highest_used_slotid ||
- tbl->highest_used_slotid == NFS4_NO_SLOT)
- tbl->highest_used_slotid = slotid;
- ret->generation = tbl->generation;
-
-out:
+ if (slotid <= tbl->max_slotid) {
+ ret = nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
+ if (!IS_ERR(ret))
+ nfs4_lock_slot(tbl, ret);
+ }
dprintk("<-- %s used_slots=%04lx highest_used=%u slotid=%u\n",
__func__, tbl->used_slots[0], tbl->highest_used_slotid,
!IS_ERR(ret) ? ret->slot_nr : NFS4_NO_SLOT);
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index e3ea2c5324d6..5b51298d1d03 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -77,6 +77,8 @@ extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
unsigned int max_reqs, const char *queue);
extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
+extern struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid);
+extern bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,
@@ -88,6 +90,12 @@ static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl)
return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
}
+static inline bool nfs4_test_locked_slot(const struct nfs4_slot_table *tbl,
+ u32 slotid)
+{
+ return !!test_bit(slotid, tbl->used_slots);
+}
+
#if defined(CONFIG_NFS_V4_1)
extern void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
u32 target_highest_slotid);
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 81ac6480f9e7..4aaed890048f 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -606,12 +606,22 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
dprintk("%s: DS %s: trying address %s\n",
__func__, ds->ds_remotestr, da->da_remotestr);
- clp = get_v3_ds_connect(mds_srv->nfs_client,
+ if (!IS_ERR(clp)) {
+ struct xprt_create xprt_args = {
+ .ident = XPRT_TRANSPORT_TCP,
+ .net = clp->cl_net,
+ .dstaddr = (struct sockaddr *)&da->da_addr,
+ .addrlen = da->da_addrlen,
+ .servername = clp->cl_hostname,
+ };
+ /* Add this address as an alias */
+ rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
+ rpc_clnt_test_and_add_xprt, NULL);
+ } else
+ clp = get_v3_ds_connect(mds_srv->nfs_client,
(struct sockaddr *)&da->da_addr,
da->da_addrlen, IPPROTO_TCP,
timeo, retrans, au_flavor);
- if (!IS_ERR(clp))
- break;
}
if (IS_ERR(clp)) {
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index d894e7cd9a86..cc514da6f3e7 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -7,6 +7,7 @@
* the Free Software Foundation.
*/
+#include <linux/module.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/file.h>
@@ -16,10 +17,41 @@
#include <linux/uaccess.h>
#include <linux/sched.h>
#include <linux/namei.h>
+#include <linux/fdtable.h>
+#include <linux/ratelimit.h>
#include "overlayfs.h"
#define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
+static bool __read_mostly ovl_check_copy_up;
+module_param_named(check_copy_up, ovl_check_copy_up, bool,
+ S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(ovl_check_copy_up,
+ "Warn on copy-up when causing process also has a R/O fd open");
+
+static int ovl_check_fd(const void *data, struct file *f, unsigned int fd)
+{
+ const struct dentry *dentry = data;
+
+ if (f->f_inode == d_inode(dentry))
+ pr_warn_ratelimited("overlayfs: Warning: Copying up %pD, but open R/O on fd %u which will cease to be coherent [pid=%d %s]\n",
+ f, fd, current->pid, current->comm);
+ return 0;
+}
+
+/*
+ * Check the fds open by this process and warn if something like the following
+ * scenario is about to occur:
+ *
+ * fd1 = open("foo", O_RDONLY);
+ * fd2 = open("foo", O_RDWR);
+ */
+static void ovl_do_check_copy_up(struct dentry *dentry)
+{
+ if (ovl_check_copy_up)
+ iterate_fd(current->files, 0, ovl_check_fd, dentry);
+}
+
int ovl_copy_xattr(struct dentry *old, struct dentry *new)
{
ssize_t list_size, size, value_size = 0;
@@ -235,6 +267,7 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
if (S_ISREG(stat->mode)) {
struct path upperpath;
+
ovl_path_upper(dentry, &upperpath);
BUG_ON(upperpath.dentry != NULL);
upperpath.dentry = newdentry;
@@ -309,6 +342,8 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
if (WARN_ON(!workdir))
return -EROFS;
+ ovl_do_check_copy_up(lowerpath->dentry);
+
ovl_path_upper(parent, &parentpath);
upperdir = parentpath.dentry;
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 52f6de5d40a9..b3fc0a35bf62 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -596,21 +596,25 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
{
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *dir = upperdir->d_inode;
- struct dentry *upper = ovl_dentry_upper(dentry);
+ struct dentry *upper;
int err;
inode_lock_nested(dir, I_MUTEX_PARENT);
+ upper = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(upper);
+ if (IS_ERR(upper))
+ goto out_unlock;
+
err = -ESTALE;
- if (upper->d_parent == upperdir) {
- /* Don't let d_delete() think it can reset d_inode */
- dget(upper);
+ if (upper == ovl_dentry_upper(dentry)) {
if (is_dir)
err = vfs_rmdir(dir, upper);
else
err = vfs_unlink(dir, upper, NULL);
- dput(upper);
ovl_dentry_version_inc(dentry->d_parent);
}
+ dput(upper);
/*
* Keeping this dentry hashed would mean having to release
@@ -620,6 +624,7 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
*/
if (!err)
d_drop(dentry);
+out_unlock:
inode_unlock(dir);
return err;
@@ -714,7 +719,6 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
struct dentry *trap;
bool old_opaque;
bool new_opaque;
- bool new_create = false;
bool cleanup_whiteout = false;
bool overwrite = !(flags & RENAME_EXCHANGE);
bool is_dir = d_is_dir(old);
@@ -840,29 +844,38 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
trap = lock_rename(new_upperdir, old_upperdir);
- olddentry = ovl_dentry_upper(old);
- newdentry = ovl_dentry_upper(new);
- if (newdentry) {
+
+ olddentry = lookup_one_len(old->d_name.name, old_upperdir,
+ old->d_name.len);
+ err = PTR_ERR(olddentry);
+ if (IS_ERR(olddentry))
+ goto out_unlock;
+
+ err = -ESTALE;
+ if (olddentry != ovl_dentry_upper(old))
+ goto out_dput_old;
+
+ newdentry = lookup_one_len(new->d_name.name, new_upperdir,
+ new->d_name.len);
+ err = PTR_ERR(newdentry);
+ if (IS_ERR(newdentry))
+ goto out_dput_old;
+
+ err = -ESTALE;
+ if (ovl_dentry_upper(new)) {
if (opaquedir) {
- newdentry = opaquedir;
- opaquedir = NULL;
+ if (newdentry != opaquedir)
+ goto out_dput;
} else {
- dget(newdentry);
+ if (newdentry != ovl_dentry_upper(new))
+ goto out_dput;
}
} else {
- new_create = true;
- newdentry = lookup_one_len(new->d_name.name, new_upperdir,
- new->d_name.len);
- err = PTR_ERR(newdentry);
- if (IS_ERR(newdentry))
- goto out_unlock;
+ if (!d_is_negative(newdentry) &&
+ (!new_opaque || !ovl_is_whiteout(newdentry)))
+ goto out_dput;
}
- err = -ESTALE;
- if (olddentry->d_parent != old_upperdir)
- goto out_dput;
- if (newdentry->d_parent != new_upperdir)
- goto out_dput;
if (olddentry == trap)
goto out_dput;
if (newdentry == trap)
@@ -925,6 +938,8 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
out_dput:
dput(newdentry);
+out_dput_old:
+ dput(olddentry);
out_unlock:
unlock_rename(new_upperdir, old_upperdir);
out_revert_creds:
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 99b4168c36ff..6a7090f4a441 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -166,6 +166,7 @@ extern const struct file_operations ovl_dir_operations;
int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list);
void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list);
void ovl_cache_free(struct list_head *list);
+int ovl_check_d_type_supported(struct path *realpath);
/* inode.c */
int ovl_setattr(struct dentry *dentry, struct iattr *attr);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index fdaf28f75e12..6ec1e43a9a54 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -36,13 +36,14 @@ struct ovl_dir_cache {
struct ovl_readdir_data {
struct dir_context ctx;
- bool is_merge;
+ bool is_lowest;
struct rb_root root;
struct list_head *list;
struct list_head middle;
struct ovl_cache_entry *first_maybe_whiteout;
int count;
int err;
+ bool d_type_supported;
};
struct ovl_dir_file {
@@ -139,9 +140,9 @@ static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd,
return 0;
}
-static int ovl_fill_lower(struct ovl_readdir_data *rdd,
- const char *name, int namelen,
- loff_t offset, u64 ino, unsigned int d_type)
+static int ovl_fill_lowest(struct ovl_readdir_data *rdd,
+ const char *name, int namelen,
+ loff_t offset, u64 ino, unsigned int d_type)
{
struct ovl_cache_entry *p;
@@ -193,10 +194,10 @@ static int ovl_fill_merge(struct dir_context *ctx, const char *name,
container_of(ctx, struct ovl_readdir_data, ctx);
rdd->count++;
- if (!rdd->is_merge)
+ if (!rdd->is_lowest)
return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type);
else
- return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type);
+ return ovl_fill_lowest(rdd, name, namelen, offset, ino, d_type);
}
static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
@@ -289,7 +290,7 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
.ctx.actor = ovl_fill_merge,
.list = list,
.root = RB_ROOT,
- .is_merge = false,
+ .is_lowest = false,
};
int idx, next;
@@ -306,7 +307,7 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
* allows offsets to be reasonably constant
*/
list_add(&rdd.middle, rdd.list);
- rdd.is_merge = true;
+ rdd.is_lowest = true;
err = ovl_dir_read(&realpath, &rdd);
list_del(&rdd.middle);
}
@@ -577,3 +578,39 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
}
inode_unlock(upper->d_inode);
}
+
+static int ovl_check_d_type(struct dir_context *ctx, const char *name,
+ int namelen, loff_t offset, u64 ino,
+ unsigned int d_type)
+{
+ struct ovl_readdir_data *rdd =
+ container_of(ctx, struct ovl_readdir_data, ctx);
+
+ /* Even if d_type is not supported, DT_DIR is returned for . and .. */
+ if (!strncmp(name, ".", namelen) || !strncmp(name, "..", namelen))
+ return 0;
+
+ if (d_type != DT_UNKNOWN)
+ rdd->d_type_supported = true;
+
+ return 0;
+}
+
+/*
+ * Returns 1 if d_type is supported, 0 not supported/unknown. Negative values
+ * if error is encountered.
+ */
+int ovl_check_d_type_supported(struct path *realpath)
+{
+ int err;
+ struct ovl_readdir_data rdd = {
+ .ctx.actor = ovl_check_d_type,
+ .d_type_supported = false,
+ };
+
+ err = ovl_dir_read(realpath, &rdd);
+ if (err)
+ return err;
+
+ return rdd.d_type_supported;
+}
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 619ad4b016d2..ef64984c9bbc 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -936,7 +936,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
err = -EINVAL;
if (!ufs->config.lowerdir) {
- pr_err("overlayfs: missing 'lowerdir'\n");
+ if (!silent)
+ pr_err("overlayfs: missing 'lowerdir'\n");
goto out_free_config;
}
@@ -1028,6 +1029,21 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
sb->s_flags |= MS_RDONLY;
ufs->workdir = NULL;
}
+
+ /*
+ * Upper should support d_type, else whiteouts are visible.
+ * Given workdir and upper are on same fs, we can do
+ * iterate_dir() on workdir.
+ */
+ err = ovl_check_d_type_supported(&workpath);
+ if (err < 0)
+ goto out_put_workdir;
+
+ if (!err) {
+ pr_err("overlayfs: upper fs needs to support d_type.\n");
+ err = -EINVAL;
+ goto out_put_workdir;
+ }
}
err = -ENOMEM;
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-25 06:23:16 +0300