Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Three trivial overlapping conflicts.

Signed-off-by: David S. Miller <davem@davemloft.net>

17 files changed, 337 insertions, 155 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 24615c76c1d0..bb28e2ead679 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -264,7 +264,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	bio_for_each_segment_all(bvec, &bio, i, iter_all) {
 		if (should_dirty && !PageCompound(bvec->bv_page))
 			set_page_dirty_lock(bvec->bv_page);
-		put_page(bvec->bv_page);
+		if (!bio_flagged(&bio, BIO_NO_PAGE_REF))
+			put_page(bvec->bv_page);
 	}
 
 	if (unlikely(bio.bi_status))
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 920bf3b4b0ef..cccc75d15970 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -427,9 +428,13 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 	unsigned long this_sum_bytes = 0;
 	int i;
 	u64 offset;
+	unsigned nofs_flag;
+
+	nofs_flag = memalloc_nofs_save();
+	sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
+		       GFP_KERNEL);
+	memalloc_nofs_restore(nofs_flag);
 
-	sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
-		       GFP_NOFS);
 	if (!sums)
 		return BLK_STS_RESOURCE;
 
@@ -472,8 +477,10 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 
 				bytes_left = bio->bi_iter.bi_size - total_bytes;
 
-				sums = kzalloc(btrfs_ordered_sum_size(fs_info, bytes_left),
-					       GFP_NOFS);
+				nofs_flag = memalloc_nofs_save();
+				sums = kvzalloc(btrfs_ordered_sum_size(fs_info,
+						      bytes_left), GFP_KERNEL);
+				memalloc_nofs_restore(nofs_flag);
 				BUG_ON(!sums); /* -ENOMEM */
 				sums->len = bytes_left;
 				ordered = btrfs_lookup_ordered_extent(inode,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 82fdda8ff5ab..2973608824ec 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6783,7 +6783,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 	u64 extent_start = 0;
 	u64 extent_end = 0;
 	u64 objectid = btrfs_ino(inode);
-	u8 extent_type;
+	int extent_type = -1;
 	struct btrfs_path *path = NULL;
 	struct btrfs_root *root = inode->root;
 	struct btrfs_file_extent_item *item;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 6fde2b2741ef..45e3cfd1198b 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
@@ -442,7 +443,7 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 			cur = entry->list.next;
 			sum = list_entry(cur, struct btrfs_ordered_sum, list);
 			list_del(&sum->list);
-			kfree(sum);
+			kvfree(sum);
 		}
 		kmem_cache_free(btrfs_ordered_extent_cache, entry);
 	}
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index a8f429882249..0637149fb9f9 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1766,6 +1766,7 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size,
 unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
 {
 	struct ceph_inode_info *dci = ceph_inode(dir);
+	unsigned hash;
 
 	switch (dci->i_dir_layout.dl_dir_hash) {
 	case 0:	/* for backward compat */
@@ -1773,8 +1774,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
 		return dn->d_name.hash;
 
 	default:
-		return ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
+		spin_lock(&dn->d_lock);
+		hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
 				     dn->d_name.name, dn->d_name.len);
+		spin_unlock(&dn->d_lock);
+		return hash;
 	}
 }
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 2d61ddda9bf5..c2feb310ac1e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1163,6 +1163,19 @@ static int splice_dentry(struct dentry **pdn, struct inode *in)
 	return 0;
 }
 
+static int d_name_cmp(struct dentry *dentry, const char *name, size_t len)
+{
+	int ret;
+
+	/* take d_lock to ensure dentry->d_name stability */
+	spin_lock(&dentry->d_lock);
+	ret = dentry->d_name.len - len;
+	if (!ret)
+		ret = memcmp(dentry->d_name.name, name, len);
+	spin_unlock(&dentry->d_lock);
+	return ret;
+}
+
 /*
  * Incorporate results into the local cache.  This is either just
  * one inode, or a directory, dentry, and possibly linked-to inode (e.g.,
@@ -1412,7 +1425,8 @@ retry_lookup:
 		err = splice_dentry(&req->r_dentry, in);
 		if (err < 0)
 			goto done;
-	} else if (rinfo->head->is_dentry) {
+	} else if (rinfo->head->is_dentry &&
+		   !d_name_cmp(req->r_dentry, rinfo->dname, rinfo->dname_len)) {
 		struct ceph_vino *ptvino = NULL;
 
 		if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) ||
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 21c33ed048ed..9049c2a3e972 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1414,6 +1414,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 			list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove);
 			ci->i_prealloc_cap_flush = NULL;
 		}
+
+               if (drop &&
+                  ci->i_wrbuffer_ref_head == 0 &&
+                  ci->i_wr_ref == 0 &&
+                  ci->i_dirty_caps == 0 &&
+                  ci->i_flushing_caps == 0) {
+                      ceph_put_snap_context(ci->i_head_snapc);
+                      ci->i_head_snapc = NULL;
+               }
 	}
 	spin_unlock(&ci->i_ceph_lock);
 	while (!list_empty(&to_remove)) {
@@ -2161,10 +2170,39 @@ retry:
 	return path;
 }
 
+/* Duplicate the dentry->d_name.name safely */
+static int clone_dentry_name(struct dentry *dentry, const char **ppath,
+			     int *ppathlen)
+{
+	u32 len;
+	char *name;
+
+retry:
+	len = READ_ONCE(dentry->d_name.len);
+	name = kmalloc(len + 1, GFP_NOFS);
+	if (!name)
+		return -ENOMEM;
+
+	spin_lock(&dentry->d_lock);
+	if (dentry->d_name.len != len) {
+		spin_unlock(&dentry->d_lock);
+		kfree(name);
+		goto retry;
+	}
+	memcpy(name, dentry->d_name.name, len);
+	spin_unlock(&dentry->d_lock);
+
+	name[len] = '\0';
+	*ppath = name;
+	*ppathlen = len;
+	return 0;
+}
+
 static int build_dentry_path(struct dentry *dentry, struct inode *dir,
 			     const char **ppath, int *ppathlen, u64 *pino,
-			     int *pfreepath)
+			     bool *pfreepath, bool parent_locked)
 {
+	int ret;
 	char *path;
 
 	rcu_read_lock();
@@ -2173,8 +2211,15 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
 	if (dir && ceph_snap(dir) == CEPH_NOSNAP) {
 		*pino = ceph_ino(dir);
 		rcu_read_unlock();
-		*ppath = dentry->d_name.name;
-		*ppathlen = dentry->d_name.len;
+		if (parent_locked) {
+			*ppath = dentry->d_name.name;
+			*ppathlen = dentry->d_name.len;
+		} else {
+			ret = clone_dentry_name(dentry, ppath, ppathlen);
+			if (ret)
+				return ret;
+			*pfreepath = true;
+		}
 		return 0;
 	}
 	rcu_read_unlock();
@@ -2182,13 +2227,13 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	*ppath = path;
-	*pfreepath = 1;
+	*pfreepath = true;
 	return 0;
 }
 
 static int build_inode_path(struct inode *inode,
 			    const char **ppath, int *ppathlen, u64 *pino,
-			    int *pfreepath)
+			    bool *pfreepath)
 {
 	struct dentry *dentry;
 	char *path;
@@ -2204,7 +2249,7 @@ static int build_inode_path(struct inode *inode,
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	*ppath = path;
-	*pfreepath = 1;
+	*pfreepath = true;
 	return 0;
 }
 
@@ -2215,7 +2260,7 @@ static int build_inode_path(struct inode *inode,
 static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
 				  struct inode *rdiri, const char *rpath,
 				  u64 rino, const char **ppath, int *pathlen,
-				  u64 *ino, int *freepath)
+				  u64 *ino, bool *freepath, bool parent_locked)
 {
 	int r = 0;
 
@@ -2225,7 +2270,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
 		     ceph_snap(rinode));
 	} else if (rdentry) {
 		r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino,
-					freepath);
+					freepath, parent_locked);
 		dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen,
 		     *ppath);
 	} else if (rpath || rino) {
@@ -2251,7 +2296,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 	const char *path2 = NULL;
 	u64 ino1 = 0, ino2 = 0;
 	int pathlen1 = 0, pathlen2 = 0;
-	int freepath1 = 0, freepath2 = 0;
+	bool freepath1 = false, freepath2 = false;
 	int len;
 	u16 releases;
 	void *p, *end;
@@ -2259,16 +2304,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 
 	ret = set_request_path_attr(req->r_inode, req->r_dentry,
 			      req->r_parent, req->r_path1, req->r_ino1.ino,
-			      &path1, &pathlen1, &ino1, &freepath1);
+			      &path1, &pathlen1, &ino1, &freepath1,
+			      test_bit(CEPH_MDS_R_PARENT_LOCKED,
+					&req->r_req_flags));
 	if (ret < 0) {
 		msg = ERR_PTR(ret);
 		goto out;
 	}
 
+	/* If r_old_dentry is set, then assume that its parent is locked */
 	ret = set_request_path_attr(NULL, req->r_old_dentry,
 			      req->r_old_dentry_dir,
 			      req->r_path2, req->r_ino2.ino,
-			      &path2, &pathlen2, &ino2, &freepath2);
+			      &path2, &pathlen2, &ino2, &freepath2, true);
 	if (ret < 0) {
 		msg = ERR_PTR(ret);
 		goto out_free1;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 89aa37fa0f84..b26e12cd8ec3 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -572,7 +572,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 	old_snapc = NULL;
 
 update_snapc:
-	if (ci->i_head_snapc) {
+       if (ci->i_wrbuffer_ref_head == 0 &&
+           ci->i_wr_ref == 0 &&
+           ci->i_dirty_caps == 0 &&
+           ci->i_flushing_caps == 0) {
+               ci->i_head_snapc = NULL;
+       } else {
 		ci->i_head_snapc = ceph_get_snap_context(new_snapc);
 		dout(" new snapc is %p\n", new_snapc);
 	}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 9c0ccc06d172..7037a137fa53 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2877,7 +2877,6 @@ static void collect_uncached_write_data(struct cifs_aio_ctx *ctx)
 	struct cifs_tcon *tcon;
 	struct cifs_sb_info *cifs_sb;
 	struct dentry *dentry = ctx->cfile->dentry;
-	unsigned int i;
 	int rc;
 
 	tcon = tlink_tcon(ctx->cfile->tlink);
@@ -2941,10 +2940,6 @@ restart_loop:
 		kref_put(&wdata->refcount, cifs_uncached_writedata_release);
 	}
 
-	if (!ctx->direct_io)
-		for (i = 0; i < ctx->npages; i++)
-			put_page(ctx->bv[i].bv_page);
-
 	cifs_stats_bytes_written(tcon, ctx->total_len);
 	set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags);
 
@@ -3582,7 +3577,6 @@ collect_uncached_read_data(struct cifs_aio_ctx *ctx)
 	struct iov_iter *to = &ctx->iter;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
-	unsigned int i;
 	int rc;
 
 	tcon = tlink_tcon(ctx->cfile->tlink);
@@ -3666,15 +3660,8 @@ again:
 		kref_put(&rdata->refcount, cifs_uncached_readdata_release);
 	}
 
-	if (!ctx->direct_io) {
-		for (i = 0; i < ctx->npages; i++) {
-			if (ctx->should_dirty)
-				set_page_dirty(ctx->bv[i].bv_page);
-			put_page(ctx->bv[i].bv_page);
-		}
-
+	if (!ctx->direct_io)
 		ctx->total_len = ctx->len - iov_iter_count(to);
-	}
 
 	/* mask nodata case */
 	if (rc == -ENODATA)
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 53fdb5df0d2e..538fd7d807e4 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1735,6 +1735,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
 	if (rc == 0 || rc != -EBUSY)
 		goto do_rename_exit;
 
+	/* Don't fall back to using SMB on SMB 2+ mount */
+	if (server->vals->protocol_id != 0)
+		goto do_rename_exit;
+
 	/* open-file renames don't work across directories */
 	if (to_dentry->d_parent != from_dentry->d_parent)
 		goto do_rename_exit;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 1e1626a2cfc3..0dc6f08020ac 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -789,6 +789,11 @@ cifs_aio_ctx_alloc(void)
 {
 	struct cifs_aio_ctx *ctx;
 
+	/*
+	 * Must use kzalloc to initialize ctx->bv to NULL and ctx->direct_io
+	 * to false so that we know when we have to unreference pages within
+	 * cifs_aio_ctx_release()
+	 */
 	ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL);
 	if (!ctx)
 		return NULL;
@@ -807,7 +812,23 @@ cifs_aio_ctx_release(struct kref *refcount)
 					struct cifs_aio_ctx, refcount);
 
 	cifsFileInfo_put(ctx->cfile);
-	kvfree(ctx->bv);
+
+	/*
+	 * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly
+	 * which means that iov_iter_get_pages() was a success and thus that
+	 * we have taken reference on pages.
+	 */
+	if (ctx->bv) {
+		unsigned i;
+
+		for (i = 0; i < ctx->npages; i++) {
+			if (ctx->should_dirty)
+				set_page_dirty(ctx->bv[i].bv_page);
+			put_page(ctx->bv[i].bv_page);
+		}
+		kvfree(ctx->bv);
+	}
+
 	kfree(ctx);
 }
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index b8f7262ac354..a37774a55f3a 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3466,6 +3466,7 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 				    io_parms->tcon->tid, ses->Suid,
 				    io_parms->offset, 0);
 		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+		cifs_small_buf_release(req);
 		return rc == -ENODATA ? 0 : rc;
 	} else
 		trace_smb3_read_done(xid, req->PersistentFileId,
diff --git a/fs/io_uring.c b/fs/io_uring.c
index f65f85d89217..84efb8956734 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4,15 +4,28 @@
  * supporting fast/efficient IO.
  *
  * A note on the read/write ordering memory barriers that are matched between
- * the application and kernel side. When the application reads the CQ ring
- * tail, it must use an appropriate smp_rmb() to order with the smp_wmb()
- * the kernel uses after writing the tail. Failure to do so could cause a
- * delay in when the application notices that completion events available.
- * This isn't a fatal condition. Likewise, the application must use an
- * appropriate smp_wmb() both before writing the SQ tail, and after writing
- * the SQ tail. The first one orders the sqe writes with the tail write, and
- * the latter is paired with the smp_rmb() the kernel will issue before
- * reading the SQ tail on submission.
+ * the application and kernel side.
+ *
+ * After the application reads the CQ ring tail, it must use an
+ * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
+ * before writing the tail (using smp_load_acquire to read the tail will
+ * do). It also needs a smp_mb() before updating CQ head (ordering the
+ * entry load(s) with the head store), pairing with an implicit barrier
+ * through a control-dependency in io_get_cqring (smp_store_release to
+ * store head will do). Failure to do so could lead to reading invalid
+ * CQ entries.
+ *
+ * Likewise, the application must use an appropriate smp_wmb() before
+ * writing the SQ tail (ordering SQ entry stores with the tail store),
+ * which pairs with smp_load_acquire in io_get_sqring (smp_store_release
+ * to store the tail will do). And it needs a barrier ordering the SQ
+ * head load before writing new SQ entries (smp_load_acquire to read
+ * head will do).
+ *
+ * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application
+ * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after*
+ * updating the SQ tail; a full memory barrier smp_mb() is needed
+ * between.
  *
  * Also see the examples in the liburing library:
  *
@@ -70,20 +83,108 @@ struct io_uring {
 	u32 tail ____cacheline_aligned_in_smp;
 };
 
+/*
+ * This data is shared with the application through the mmap at offset
+ * IORING_OFF_SQ_RING.
+ *
+ * The offsets to the member fields are published through struct
+ * io_sqring_offsets when calling io_uring_setup.
+ */
 struct io_sq_ring {
+	/*
+	 * Head and tail offsets into the ring; the offsets need to be
+	 * masked to get valid indices.
+	 *
+	 * The kernel controls head and the application controls tail.
+	 */
 	struct io_uring		r;
+	/*
+	 * Bitmask to apply to head and tail offsets (constant, equals
+	 * ring_entries - 1)
+	 */
 	u32			ring_mask;
+	/* Ring size (constant, power of 2) */
 	u32			ring_entries;
+	/*
+	 * Number of invalid entries dropped by the kernel due to
+	 * invalid index stored in array
+	 *
+	 * Written by the kernel, shouldn't be modified by the
+	 * application (i.e. get number of "new events" by comparing to
+	 * cached value).
+	 *
+	 * After a new SQ head value was read by the application this
+	 * counter includes all submissions that were dropped reaching
+	 * the new SQ head (and possibly more).
+	 */
 	u32			dropped;
+	/*
+	 * Runtime flags
+	 *
+	 * Written by the kernel, shouldn't be modified by the
+	 * application.
+	 *
+	 * The application needs a full memory barrier before checking
+	 * for IORING_SQ_NEED_WAKEUP after updating the sq tail.
+	 */
 	u32			flags;
+	/*
+	 * Ring buffer of indices into array of io_uring_sqe, which is
+	 * mmapped by the application using the IORING_OFF_SQES offset.
+	 *
+	 * This indirection could e.g. be used to assign fixed
+	 * io_uring_sqe entries to operations and only submit them to
+	 * the queue when needed.
+	 *
+	 * The kernel modifies neither the indices array nor the entries
+	 * array.
+	 */
 	u32			array[];
 };
 
+/*
+ * This data is shared with the application through the mmap at offset
+ * IORING_OFF_CQ_RING.
+ *
+ * The offsets to the member fields are published through struct
+ * io_cqring_offsets when calling io_uring_setup.
+ */
 struct io_cq_ring {
+	/*
+	 * Head and tail offsets into the ring; the offsets need to be
+	 * masked to get valid indices.
+	 *
+	 * The application controls head and the kernel tail.
+	 */
 	struct io_uring		r;
+	/*
+	 * Bitmask to apply to head and tail offsets (constant, equals
+	 * ring_entries - 1)
+	 */
 	u32			ring_mask;
+	/* Ring size (constant, power of 2) */
 	u32			ring_entries;
+	/*
+	 * Number of completion events lost because the queue was full;
+	 * this should be avoided by the application by making sure
+	 * there are not more requests pending thatn there is space in
+	 * the completion queue.
+	 *
+	 * Written by the kernel, shouldn't be modified by the
+	 * application (i.e. get number of "new events" by comparing to
+	 * cached value).
+	 *
+	 * As completion events come in out of order this counter is not
+	 * ordered with any other data.
+	 */
 	u32			overflow;
+	/*
+	 * Ring buffer of completion events.
+	 *
+	 * The kernel writes completion events fresh every time they are
+	 * produced, so the application is allowed to modify pending
+	 * entries.
+	 */
 	struct io_uring_cqe	cqes[];
 };
 
@@ -221,7 +322,7 @@ struct io_kiocb {
 	struct list_head	list;
 	unsigned int		flags;
 	refcount_t		refs;
-#define REQ_F_FORCE_NONBLOCK	1	/* inline submission attempt */
+#define REQ_F_NOWAIT		1	/* must not punt to workers */
 #define REQ_F_IOPOLL_COMPLETED	2	/* polled IO has completed */
 #define REQ_F_FIXED_FILE	4	/* ctx owns file */
 #define REQ_F_SEQ_PREV		8	/* sequential with previous */
@@ -317,12 +418,6 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
 		/* order cqe stores with ring update */
 		smp_store_release(&ring->r.tail, ctx->cached_cq_tail);
 
-		/*
-		 * Write sider barrier of tail update, app has read side. See
-		 * comment at the top of this file.
-		 */
-		smp_wmb();
-
 		if (wq_has_sleeper(&ctx->cq_wait)) {
 			wake_up_interruptible(&ctx->cq_wait);
 			kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
@@ -336,8 +431,11 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 	unsigned tail;
 
 	tail = ctx->cached_cq_tail;
-	/* See comment at the top of the file */
-	smp_rmb();
+	/*
+	 * writes to the cq entry need to come after reading head; the
+	 * control dependency is enough as we're using WRITE_ONCE to
+	 * fill the cq entry
+	 */
 	if (tail - READ_ONCE(ring->r.head) == ring->ring_entries)
 		return NULL;
 
@@ -740,7 +838,7 @@ static bool io_file_supports_async(struct file *file)
 }
 
 static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
-		      bool force_nonblock, struct io_submit_state *state)
+		      bool force_nonblock)
 {
 	const struct io_uring_sqe *sqe = s->sqe;
 	struct io_ring_ctx *ctx = req->ctx;
@@ -774,10 +872,14 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 	ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
 	if (unlikely(ret))
 		return ret;
-	if (force_nonblock) {
+
+	/* don't allow async punt if RWF_NOWAIT was requested */
+	if (kiocb->ki_flags & IOCB_NOWAIT)
+		req->flags |= REQ_F_NOWAIT;
+
+	if (force_nonblock)
 		kiocb->ki_flags |= IOCB_NOWAIT;
-		req->flags |= REQ_F_FORCE_NONBLOCK;
-	}
+
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		if (!(kiocb->ki_flags & IOCB_DIRECT) ||
 		    !kiocb->ki_filp->f_op->iopoll)
@@ -938,7 +1040,7 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
 }
 
 static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
-		   bool force_nonblock, struct io_submit_state *state)
+		   bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw;
@@ -947,7 +1049,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 	size_t iov_count;
 	int ret;
 
-	ret = io_prep_rw(req, s, force_nonblock, state);
+	ret = io_prep_rw(req, s, force_nonblock);
 	if (ret)
 		return ret;
 	file = kiocb->ki_filp;
@@ -985,7 +1087,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 }
 
 static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
-		    bool force_nonblock, struct io_submit_state *state)
+		    bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw;
@@ -994,7 +1096,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 	size_t iov_count;
 	int ret;
 
-	ret = io_prep_rw(req, s, force_nonblock, state);
+	ret = io_prep_rw(req, s, force_nonblock);
 	if (ret)
 		return ret;
 
@@ -1336,8 +1438,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 }
 
 static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			   const struct sqe_submit *s, bool force_nonblock,
-			   struct io_submit_state *state)
+			   const struct sqe_submit *s, bool force_nonblock)
 {
 	int ret, opcode;
 
@@ -1353,18 +1454,18 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_READV:
 		if (unlikely(s->sqe->buf_index))
 			return -EINVAL;
-		ret = io_read(req, s, force_nonblock, state);
+		ret = io_read(req, s, force_nonblock);
 		break;
 	case IORING_OP_WRITEV:
 		if (unlikely(s->sqe->buf_index))
 			return -EINVAL;
-		ret = io_write(req, s, force_nonblock, state);
+		ret = io_write(req, s, force_nonblock);
 		break;
 	case IORING_OP_READ_FIXED:
-		ret = io_read(req, s, force_nonblock, state);
+		ret = io_read(req, s, force_nonblock);
 		break;
 	case IORING_OP_WRITE_FIXED:
-		ret = io_write(req, s, force_nonblock, state);
+		ret = io_write(req, s, force_nonblock);
 		break;
 	case IORING_OP_FSYNC:
 		ret = io_fsync(req, s->sqe, force_nonblock);
@@ -1437,8 +1538,7 @@ restart:
 		struct sqe_submit *s = &req->submit;
 		const struct io_uring_sqe *sqe = s->sqe;
 
-		/* Ensure we clear previously set forced non-block flag */
-		req->flags &= ~REQ_F_FORCE_NONBLOCK;
+		/* Ensure we clear previously set non-block flag */
 		req->rw.ki_flags &= ~IOCB_NOWAIT;
 
 		ret = 0;
@@ -1457,7 +1557,7 @@ restart:
 			s->has_user = cur_mm != NULL;
 			s->needs_lock = true;
 			do {
-				ret = __io_submit_sqe(ctx, req, s, false, NULL);
+				ret = __io_submit_sqe(ctx, req, s, false);
 				/*
 				 * We can get EAGAIN for polled IO even though
 				 * we're forcing a sync submission from here,
@@ -1468,10 +1568,11 @@ restart:
 					break;
 				cond_resched();
 			} while (1);
-
-			/* drop submission reference */
-			io_put_req(req);
 		}
+
+		/* drop submission reference */
+		io_put_req(req);
+
 		if (ret) {
 			io_cqring_add_event(ctx, sqe->user_data, ret, 0);
 			io_put_req(req);
@@ -1623,8 +1724,8 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
 	if (unlikely(ret))
 		goto out;
 
-	ret = __io_submit_sqe(ctx, req, s, true, state);
-	if (ret == -EAGAIN) {
+	ret = __io_submit_sqe(ctx, req, s, true);
+	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
 		struct io_uring_sqe *sqe_copy;
 
 		sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
@@ -1698,24 +1799,10 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
 		 * write new data to them.
 		 */
 		smp_store_release(&ring->r.head, ctx->cached_sq_head);
-
-		/*
-		 * write side barrier of head update, app has read side. See
-		 * comment at the top of this file
-		 */
-		smp_wmb();
 	}
 }
 
 /*
- * Undo last io_get_sqring()
- */
-static void io_drop_sqring(struct io_ring_ctx *ctx)
-{
-	ctx->cached_sq_head--;
-}
-
-/*
  * Fetch an sqe, if one is available. Note that s->sqe will point to memory
  * that is mapped by userspace. This means that care needs to be taken to
  * ensure that reads are stable, as we cannot rely on userspace always
@@ -1737,9 +1824,8 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 	 *    though the application is the one updating it.
 	 */
 	head = ctx->cached_sq_head;
-	/* See comment at the top of this file */
-	smp_rmb();
-	if (head == READ_ONCE(ring->r.tail))
+	/* make sure SQ entry isn't read before tail */
+	if (head == smp_load_acquire(&ring->r.tail))
 		return false;
 
 	head = READ_ONCE(ring->array[head & ctx->sq_mask]);
@@ -1753,8 +1839,6 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 	/* drop invalid entries */
 	ctx->cached_sq_head++;
 	ring->dropped++;
-	/* See comment at the top of this file */
-	smp_wmb();
 	return false;
 }
 
@@ -1864,7 +1948,8 @@ static int io_sq_thread(void *data)
 
 			/* Tell userspace we may need a wakeup call */
 			ctx->sq_ring->flags |= IORING_SQ_NEED_WAKEUP;
-			smp_wmb();
+			/* make sure to read SQ tail after writing flags */
+			smp_mb();
 
 			if (!io_get_sqring(ctx, &sqes[0])) {
 				if (kthread_should_stop()) {
@@ -1877,13 +1962,11 @@ static int io_sq_thread(void *data)
 				finish_wait(&ctx->sqo_wait, &wait);
 
 				ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
-				smp_wmb();
 				continue;
 			}
 			finish_wait(&ctx->sqo_wait, &wait);
 
 			ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
-			smp_wmb();
 		}
 
 		i = 0;
@@ -1928,7 +2011,7 @@ static int io_sq_thread(void *data)
 static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 {
 	struct io_submit_state state, *statep = NULL;
-	int i, ret = 0, submit = 0;
+	int i, submit = 0;
 
 	if (to_submit > IO_PLUG_THRESHOLD) {
 		io_submit_state_start(&state, ctx, to_submit);
@@ -1937,6 +2020,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 
 	for (i = 0; i < to_submit; i++) {
 		struct sqe_submit s;
+		int ret;
 
 		if (!io_get_sqring(ctx, &s))
 			break;
@@ -1944,21 +2028,18 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 		s.has_user = true;
 		s.needs_lock = false;
 		s.needs_fixed_file = false;
+		submit++;
 
 		ret = io_submit_sqe(ctx, &s, statep);
-		if (ret) {
-			io_drop_sqring(ctx);
-			break;
-		}
-
-		submit++;
+		if (ret)
+			io_cqring_add_event(ctx, s.sqe->user_data, ret, 0);
 	}
 	io_commit_sqring(ctx);
 
 	if (statep)
 		io_submit_state_end(statep);
 
-	return submit ? submit : ret;
+	return submit;
 }
 
 static unsigned io_cqring_events(struct io_cq_ring *ring)
@@ -2239,10 +2320,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 	mmgrab(current->mm);
 	ctx->sqo_mm = current->mm;
 
-	ret = -EINVAL;
-	if (!cpu_possible(p->sq_thread_cpu))
-		goto err;
-
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		ret = -EPERM;
 		if (!capable(CAP_SYS_ADMIN))
@@ -2253,11 +2330,11 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 			ctx->sq_thread_idle = HZ;
 
 		if (p->flags & IORING_SETUP_SQ_AFF) {
-			int cpu;
+			int cpu = array_index_nospec(p->sq_thread_cpu,
+							nr_cpu_ids);
 
-			cpu = array_index_nospec(p->sq_thread_cpu, NR_CPUS);
 			ret = -EINVAL;
-			if (!cpu_possible(p->sq_thread_cpu))
+			if (!cpu_possible(cpu))
 				goto err;
 
 			ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread,
@@ -2320,8 +2397,12 @@ static int io_account_mem(struct user_struct *user, unsigned long nr_pages)
 
 static void io_mem_free(void *ptr)
 {
-	struct page *page = virt_to_head_page(ptr);
+	struct page *page;
+
+	if (!ptr)
+		return;
 
+	page = virt_to_head_page(ptr);
 	if (put_page_testzero(page))
 		free_compound_page(page);
 }
@@ -2362,7 +2443,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)
 
 		if (ctx->account_mem)
 			io_unaccount_mem(ctx->user, imu->nr_bvecs);
-		kfree(imu->bvec);
+		kvfree(imu->bvec);
 		imu->nr_bvecs = 0;
 	}
 
@@ -2454,9 +2535,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 		if (!pages || nr_pages > got_pages) {
 			kfree(vmas);
 			kfree(pages);
-			pages = kmalloc_array(nr_pages, sizeof(struct page *),
+			pages = kvmalloc_array(nr_pages, sizeof(struct page *),
 						GFP_KERNEL);
-			vmas = kmalloc_array(nr_pages,
+			vmas = kvmalloc_array(nr_pages,
 					sizeof(struct vm_area_struct *),
 					GFP_KERNEL);
 			if (!pages || !vmas) {
@@ -2468,7 +2549,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 			got_pages = nr_pages;
 		}
 
-		imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec),
+		imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec),
 						GFP_KERNEL);
 		ret = -ENOMEM;
 		if (!imu->bvec) {
@@ -2507,6 +2588,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 			}
 			if (ctx->account_mem)
 				io_unaccount_mem(ctx->user, nr_pages);
+			kvfree(imu->bvec);
 			goto err;
 		}
 
@@ -2529,12 +2611,12 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 
 		ctx->nr_user_bufs++;
 	}
-	kfree(pages);
-	kfree(vmas);
+	kvfree(pages);
+	kvfree(vmas);
 	return 0;
 err:
-	kfree(pages);
-	kfree(vmas);
+	kvfree(pages);
+	kvfree(vmas);
 	io_sqe_buffer_unregister(ctx);
 	return ret;
 }
@@ -2572,9 +2654,13 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	__poll_t mask = 0;
 
 	poll_wait(file, &ctx->cq_wait, wait);
-	/* See comment at the top of this file */
+	/*
+	 * synchronizes with barrier from wq_has_sleeper call in
+	 * io_commit_cqring
+	 */
 	smp_rmb();
-	if (READ_ONCE(ctx->sq_ring->r.tail) + 1 != ctx->cached_sq_head)
+	if (READ_ONCE(ctx->sq_ring->r.tail) - ctx->cached_sq_head !=
+	    ctx->sq_ring->ring_entries)
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail)
 		mask |= EPOLLIN | EPOLLRDNORM;
@@ -2685,24 +2771,12 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		mutex_lock(&ctx->uring_lock);
 		submitted = io_ring_submit(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
-
-		if (submitted < 0)
-			goto out_ctx;
 	}
 	if (flags & IORING_ENTER_GETEVENTS) {
 		unsigned nr_events = 0;
 
 		min_complete = min(min_complete, ctx->cq_entries);
 
-		/*
-		 * The application could have included the 'to_submit' count
-		 * in how many events it wanted to wait for. If we failed to
-		 * submit the desired count, we may need to adjust the number
-		 * of events to poll/wait for.
-		 */
-		if (submitted < to_submit)
-			min_complete = min_t(unsigned, submitted, min_complete);
-
 		if (ctx->flags & IORING_SETUP_IOPOLL) {
 			mutex_lock(&ctx->uring_lock);
 			ret = io_iopoll_check(ctx, &nr_events, min_complete);
@@ -2748,17 +2822,12 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 		return -EOVERFLOW;
 
 	ctx->sq_sqes = io_mem_alloc(size);
-	if (!ctx->sq_sqes) {
-		io_mem_free(ctx->sq_ring);
+	if (!ctx->sq_sqes)
 		return -ENOMEM;
-	}
 
 	cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries));
-	if (!cq_ring) {
-		io_mem_free(ctx->sq_ring);
-		io_mem_free(ctx->sq_sqes);
+	if (!cq_ring)
 		return -ENOMEM;
-	}
 
 	ctx->cq_ring = cq_ring;
 	cq_ring->ring_mask = p->cq_entries - 1;
@@ -2934,6 +3003,14 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 {
 	int ret;
 
+	/*
+	 * We're inside the ring mutex, if the ref is already dying, then
+	 * someone else killed the ctx or is already going through
+	 * io_uring_register().
+	 */
+	if (percpu_ref_is_dying(&ctx->refs))
+		return -ENXIO;
+
 	percpu_ref_kill(&ctx->refs);
 
 	/*
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 6b9c27548997..63c6bb1f8c4d 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -346,10 +346,16 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 	__kernel_fsid_t fsid = {};
 
 	fsnotify_foreach_obj_type(type) {
+		struct fsnotify_mark_connector *conn;
+
 		if (!fsnotify_iter_should_report_type(iter_info, type))
 			continue;
 
-		fsid = iter_info->marks[type]->connector->fsid;
+		conn = READ_ONCE(iter_info->marks[type]->connector);
+		/* Mark is just getting destroyed or created? */
+		if (!conn)
+			continue;
+		fsid = conn->fsid;
 		if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
 			continue;
 		return fsid;
@@ -408,8 +414,12 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 			return 0;
 	}
 
-	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID))
+	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
 		fsid = fanotify_get_fsid(iter_info);
+		/* Racing with mark destruction or creation? */
+		if (!fsid.val[0] && !fsid.val[1])
+			return 0;
+	}
 
 	event = fanotify_alloc_event(group, inode, mask, data, data_type,
 				     &fsid);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d593d4269561..22acb0a79b53 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -239,13 +239,13 @@ static void fsnotify_drop_object(unsigned int type, void *objp)
 
 void fsnotify_put_mark(struct fsnotify_mark *mark)
 {
-	struct fsnotify_mark_connector *conn;
+	struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector);
 	void *objp = NULL;
 	unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED;
 	bool free_conn = false;
 
 	/* Catch marks that were actually never attached to object */
-	if (!mark->connector) {
+	if (!conn) {
 		if (refcount_dec_and_test(&mark->refcnt))
 			fsnotify_final_mark_destroy(mark);
 		return;
@@ -255,10 +255,9 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	 * We have to be careful so that traversals of obj_list under lock can
 	 * safely grab mark reference.
 	 */
-	if (!refcount_dec_and_lock(&mark->refcnt, &mark->connector->lock))
+	if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock))
 		return;
 
-	conn = mark->connector;
 	hlist_del_init_rcu(&mark->obj_list);
 	if (hlist_empty(&conn->list)) {
 		objp = fsnotify_detach_connector_from_object(conn, &type);
@@ -266,7 +265,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	} else {
 		__fsnotify_recalc_mask(conn);
 	}
-	mark->connector = NULL;
+	WRITE_ONCE(mark->connector, NULL);
 	spin_unlock(&conn->lock);
 
 	fsnotify_drop_object(type, objp);
@@ -620,7 +619,7 @@ restart:
 	/* mark should be the last entry.  last is the current last entry */
 	hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
 added:
-	mark->connector = conn;
+	WRITE_ONCE(mark->connector, conn);
 out_err:
 	spin_unlock(&conn->lock);
 	spin_unlock(&mark->lock);
@@ -808,6 +807,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	refcount_set(&mark->refcnt, 1);
 	fsnotify_get_group(group);
 	mark->group = group;
+	WRITE_ONCE(mark->connector, NULL);
 }
 
 /*
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 2d61e5e8c863..c74570736b24 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1643,9 +1643,11 @@ static void drop_sysctl_table(struct ctl_table_header *header)
 	if (--header->nreg)
 		return;
 
-	if (parent)
+	if (parent) {
 		put_links(header);
-	start_unregistering(header);
+		start_unregistering(header);
+	}
+
 	if (!--header->count)
 		kfree_rcu(header, rcu);
 
diff --git a/fs/splice.c b/fs/splice.c
index 98943d9b219c..25212dcca2df 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -330,8 +330,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = {
 	.get = generic_pipe_buf_get,
 };
 
-static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
-				    struct pipe_buffer *buf)
+int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+			     struct pipe_buffer *buf)
 {
 	return 1;
 }