Merge tag 'v4.20-rc6' into for-4.21/block

Pull in v4.20-rc6 to resolve the conflict in NVMe, but also to get the
two corruption fixes. We're going to be overhauling the direct dispatch
path, and we need to do that on top of the changes we made for that
in mainline.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

14 files changed, 74 insertions, 70 deletions

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index efcf89a8ba44..1a4e2b101ef2 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -389,13 +389,11 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info,
 
 	/*
 	 * Here we don't really care about alignment since extent allocator can
-	 * handle it.  We care more about the size, as if one block group is
-	 * larger than maximum size, it's must be some obvious corruption.
+	 * handle it.  We care more about the size.
 	 */
-	if (key->offset > BTRFS_MAX_DATA_CHUNK_SIZE || key->offset == 0) {
+	if (key->offset == 0) {
 		block_group_err(fs_info, leaf, slot,
-			"invalid block group size, have %llu expect (0, %llu]",
-				key->offset, BTRFS_MAX_DATA_CHUNK_SIZE);
+				"invalid block group size 0");
 		return -EUCLEAN;
 	}
 
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index abcd78e332fe..85dadb93c992 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -133,7 +133,7 @@ config CIFS_XATTR
 
 config CIFS_POSIX
         bool "CIFS POSIX Extensions"
-        depends on CIFS_XATTR
+        depends on CIFS && CIFS_ALLOW_INSECURE_LEGACY && CIFS_XATTR
         help
           Enabling this option will cause the cifs client to attempt to
 	  negotiate a newer dialect with servers, such as Samba 3.0.5
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 3713d22b95a7..907e85d65bb4 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -174,7 +174,7 @@ cifs_bp_rename_retry:
 
 		cifs_dbg(FYI, "using cifs_sb prepath <%s>\n", cifs_sb->prepath);
 		memcpy(full_path+dfsplen+1, cifs_sb->prepath, pplen-1);
-		full_path[dfsplen] = '\\';
+		full_path[dfsplen] = dirsep;
 		for (i = 0; i < pplen-1; i++)
 			if (full_path[dfsplen+1+i] == '/')
 				full_path[dfsplen+1+i] = CIFS_DIR_SEP(cifs_sb);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 74c33d5fafc8..c9bc56b1baac 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2541,14 +2541,13 @@ static int
 cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
 	struct cifs_aio_ctx *ctx)
 {
-	int wait_retry = 0;
 	unsigned int wsize, credits;
 	int rc;
 	struct TCP_Server_Info *server =
 		tlink_tcon(wdata->cfile->tlink)->ses->server;
 
 	/*
-	 * Try to resend this wdata, waiting for credits up to 3 seconds.
+	 * Wait for credits to resend this wdata.
 	 * Note: we are attempting to resend the whole wdata not in segments
 	 */
 	do {
@@ -2556,19 +2555,13 @@ cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
 			server, wdata->bytes, &wsize, &credits);
 
 		if (rc)
-			break;
+			goto out;
 
 		if (wsize < wdata->bytes) {
 			add_credits_and_wake_if(server, credits, 0);
 			msleep(1000);
-			wait_retry++;
 		}
-	} while (wsize < wdata->bytes && wait_retry < 3);
-
-	if (wsize < wdata->bytes) {
-		rc = -EBUSY;
-		goto out;
-	}
+	} while (wsize < wdata->bytes);
 
 	rc = -EAGAIN;
 	while (rc == -EAGAIN) {
@@ -3234,14 +3227,13 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata,
 			struct list_head *rdata_list,
 			struct cifs_aio_ctx *ctx)
 {
-	int wait_retry = 0;
 	unsigned int rsize, credits;
 	int rc;
 	struct TCP_Server_Info *server =
 		tlink_tcon(rdata->cfile->tlink)->ses->server;
 
 	/*
-	 * Try to resend this rdata, waiting for credits up to 3 seconds.
+	 * Wait for credits to resend this rdata.
 	 * Note: we are attempting to resend the whole rdata not in segments
 	 */
 	do {
@@ -3249,24 +3241,13 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata,
 						&rsize, &credits);
 
 		if (rc)
-			break;
+			goto out;
 
 		if (rsize < rdata->bytes) {
 			add_credits_and_wake_if(server, credits, 0);
 			msleep(1000);
-			wait_retry++;
 		}
-	} while (rsize < rdata->bytes && wait_retry < 3);
-
-	/*
-	 * If we can't find enough credits to send this rdata
-	 * release the rdata and return failure, this will pass
-	 * whatever I/O amount we have finished to VFS.
-	 */
-	if (rsize < rdata->bytes) {
-		rc = -EBUSY;
-		goto out;
-	}
+	} while (rsize < rdata->bytes);
 
 	rc = -EAGAIN;
 	while (rc == -EAGAIN) {
diff --git a/fs/dax.c b/fs/dax.c
index 9bcce89ea18e..48132eca3761 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -232,6 +232,34 @@ static void *get_unlocked_entry(struct xa_state *xas)
 	}
 }
 
+/*
+ * The only thing keeping the address space around is the i_pages lock
+ * (it's cycled in clear_inode() after removing the entries from i_pages)
+ * After we call xas_unlock_irq(), we cannot touch xas->xa.
+ */
+static void wait_entry_unlocked(struct xa_state *xas, void *entry)
+{
+	struct wait_exceptional_entry_queue ewait;
+	wait_queue_head_t *wq;
+
+	init_wait(&ewait.wait);
+	ewait.wait.func = wake_exceptional_entry_func;
+
+	wq = dax_entry_waitqueue(xas, entry, &ewait.key);
+	prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);
+	xas_unlock_irq(xas);
+	schedule();
+	finish_wait(wq, &ewait.wait);
+
+	/*
+	 * Entry lock waits are exclusive. Wake up the next waiter since
+	 * we aren't sure we will acquire the entry lock and thus wake
+	 * the next waiter up on unlock.
+	 */
+	if (waitqueue_active(wq))
+		__wake_up(wq, TASK_NORMAL, 1, &ewait.key);
+}
+
 static void put_unlocked_entry(struct xa_state *xas, void *entry)
 {
 	/* If we were the only waiter woken, wake the next one */
@@ -351,21 +379,21 @@ static struct page *dax_busy_page(void *entry)
  * @page: The page whose entry we want to lock
  *
  * Context: Process context.
- * Return: %true if the entry was locked or does not need to be locked.
+ * Return: A cookie to pass to dax_unlock_page() or 0 if the entry could
+ * not be locked.
  */
-bool dax_lock_mapping_entry(struct page *page)
+dax_entry_t dax_lock_page(struct page *page)
 {
 	XA_STATE(xas, NULL, 0);
 	void *entry;
-	bool locked;
 
 	/* Ensure page->mapping isn't freed while we look at it */
 	rcu_read_lock();
 	for (;;) {
 		struct address_space *mapping = READ_ONCE(page->mapping);
 
-		locked = false;
-		if (!dax_mapping(mapping))
+		entry = NULL;
+		if (!mapping || !dax_mapping(mapping))
 			break;
 
 		/*
@@ -375,7 +403,7 @@ bool dax_lock_mapping_entry(struct page *page)
 		 * otherwise we would not have a valid pfn_to_page()
 		 * translation.
 		 */
-		locked = true;
+		entry = (void *)~0UL;
 		if (S_ISCHR(mapping->host->i_mode))
 			break;
 
@@ -389,9 +417,7 @@ bool dax_lock_mapping_entry(struct page *page)
 		entry = xas_load(&xas);
 		if (dax_is_locked(entry)) {
 			rcu_read_unlock();
-			entry = get_unlocked_entry(&xas);
-			xas_unlock_irq(&xas);
-			put_unlocked_entry(&xas, entry);
+			wait_entry_unlocked(&xas, entry);
 			rcu_read_lock();
 			continue;
 		}
@@ -400,23 +426,18 @@ bool dax_lock_mapping_entry(struct page *page)
 		break;
 	}
 	rcu_read_unlock();
-	return locked;
+	return (dax_entry_t)entry;
 }
 
-void dax_unlock_mapping_entry(struct page *page)
+void dax_unlock_page(struct page *page, dax_entry_t cookie)
 {
 	struct address_space *mapping = page->mapping;
 	XA_STATE(xas, &mapping->i_pages, page->index);
-	void *entry;
 
 	if (S_ISCHR(mapping->host->i_mode))
 		return;
 
-	rcu_read_lock();
-	entry = xas_load(&xas);
-	rcu_read_unlock();
-	entry = dax_make_entry(page_to_pfn_t(page), dax_is_pmd_entry(entry));
-	dax_unlock_entry(&xas, entry);
+	dax_unlock_entry(&xas, (void *)cookie);
 }
 
 /*
diff --git a/fs/exec.c b/fs/exec.c
index acc3a5536384..fc281b738a98 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -62,7 +62,6 @@
 #include <linux/oom.h>
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
-#include <linux/freezer.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1084,7 +1083,7 @@ static int de_thread(struct task_struct *tsk)
 	while (sig->notify_count) {
 		__set_current_state(TASK_KILLABLE);
 		spin_unlock_irq(lock);
-		freezable_schedule();
+		schedule();
 		if (unlikely(__fatal_signal_pending(tsk)))
 			goto killed;
 		spin_lock_irq(lock);
@@ -1112,7 +1111,7 @@ static int de_thread(struct task_struct *tsk)
 			__set_current_state(TASK_KILLABLE);
 			write_unlock_irq(&tasklist_lock);
 			cgroup_threadgroup_change_end(tsk);
-			freezable_schedule();
+			schedule();
 			if (unlikely(__fatal_signal_pending(tsk)))
 				goto killed;
 		}
diff --git a/fs/iomap.c b/fs/iomap.c
index d094e5688bd3..9a5bf1e8925b 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1884,15 +1884,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 				dio->wait_for_completion = true;
 				ret = 0;
 			}
-
-			/*
-			 * Splicing to pipes can fail on a full pipe. We have to
-			 * swallow this to make it look like a short IO
-			 * otherwise the higher splice layers will completely
-			 * mishandle the error and stop moving data.
-			 */
-			if (ret == -EFAULT)
-				ret = 0;
 			break;
 		}
 		pos += ret;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index aa12c3063bae..33824a0a57bf 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -98,8 +98,11 @@ struct nfs_direct_req {
 	struct pnfs_ds_commit_info ds_cinfo;	/* Storage for cinfo */
 	struct work_struct	work;
 	int			flags;
+	/* for write */
 #define NFS_ODIRECT_DO_COMMIT		(1)	/* an unstable reply was received */
 #define NFS_ODIRECT_RESCHED_WRITES	(2)	/* write verification failed */
+	/* for read */
+#define NFS_ODIRECT_SHOULD_DIRTY	(3)	/* dirty user-space page after read */
 	struct nfs_writeverf	verf;		/* unstable write verifier */
 };
 
@@ -412,7 +415,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 		struct page *page = req->wb_page;
 
-		if (!PageCompound(page) && bytes < hdr->good_bytes)
+		if (!PageCompound(page) && bytes < hdr->good_bytes &&
+		    (dreq->flags == NFS_ODIRECT_SHOULD_DIRTY))
 			set_page_dirty(page);
 		bytes += req->wb_bytes;
 		nfs_list_remove_request(req);
@@ -587,6 +591,9 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
+	if (iter_is_iovec(iter))
+		dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;
+
 	nfs_start_io_direct(inode);
 
 	NFS_I(inode)->read_io += count;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 74b36ed883ca..310d7500f665 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1733,7 +1733,8 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	if (fh)
 		hdr->args.fh = fh;
 
-	if (!nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
+	if (vers == 4 &&
+		!nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
 		goto out_failed;
 
 	/*
@@ -1798,7 +1799,8 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	if (fh)
 		hdr->args.fh = fh;
 
-	if (!nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
+	if (vers == 4 &&
+		!nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
 		goto out_failed;
 
 	/*
diff --git a/fs/read_write.c b/fs/read_write.c
index 4dae0399c75a..58f30537c47a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1956,7 +1956,7 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 	struct inode *inode_out = file_inode(file_out);
 	loff_t ret;
 
-	WARN_ON_ONCE(remap_flags);
+	WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP);
 
 	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
 		return -EISDIR;
diff --git a/fs/splice.c b/fs/splice.c
index 3553f1956508..de2ede048473 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -945,11 +945,16 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 	sd->flags &= ~SPLICE_F_NONBLOCK;
 	more = sd->flags & SPLICE_F_MORE;
 
+	WARN_ON_ONCE(pipe->nrbufs != 0);
+
 	while (len) {
 		size_t read_len;
 		loff_t pos = sd->pos, prev_pos = pos;
 
-		ret = do_splice_to(in, &pos, pipe, len, flags);
+		/* Don't try to read more the pipe has space for. */
+		read_len = min_t(size_t, len,
+				 (pipe->buffers - pipe->nrbufs) << PAGE_SHIFT);
+		ret = do_splice_to(in, &pos, pipe, read_len, flags);
 		if (unlikely(ret <= 0))
 			goto out_release;
 
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 34c6d7bd4d18..bbdae2b4559f 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -330,7 +330,7 @@ xfs_btree_sblock_verify_crc(
 
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.s.bb_lsn)))
-			return __this_address;
+			return false;
 		return xfs_buf_verify_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF);
 	}
 
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 404e581f1ea1..1ee8c5539fa4 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1126,9 +1126,9 @@ xfs_free_file_space(
 	 * page could be mmap'd and iomap_zero_range doesn't do that for us.
 	 * Writeback of the eof page will do this, albeit clumsily.
 	 */
-	if (offset + len >= XFS_ISIZE(ip) && ((offset + len) & PAGE_MASK)) {
+	if (offset + len >= XFS_ISIZE(ip) && offset_in_page(offset + len) > 0) {
 		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
-				(offset + len) & ~PAGE_MASK, LLONG_MAX);
+				round_down(offset + len, PAGE_SIZE), LLONG_MAX);
 	}
 
 	return error;
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 73a1d77ec187..3091e4bc04ef 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -40,7 +40,7 @@ xfs_fill_statvfs_from_dquot(
 		statp->f_files = limit;
 		statp->f_ffree =
 			(statp->f_files > dqp->q_res_icount) ?
-			 (statp->f_ffree - dqp->q_res_icount) : 0;
+			 (statp->f_files - dqp->q_res_icount) : 0;
 	}
 }