From cea9ba7239dcc84175041174304c6cdeae3226e5 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:27:00 -0400
Subject: NFS: Do not report EINTR/ERESTARTSYS as mapping errors

If the attempt to flush data was interrupted due to a local signal, then
just requeue the writes back for I/O.

Fixes: 6fbda89b257f ("NFS: Replace custom error reporting mechanism with generic one")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/write.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f00d45cf80ef..e437db1791ba 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1444,7 +1444,7 @@ static void nfs_async_write_error(struct list_head *head, int error)
 	while (!list_empty(head)) {
 		req = nfs_list_entry(head->next);
 		nfs_list_remove_request(req);
-		if (nfs_error_is_fatal(error))
+		if (nfs_error_is_fatal_on_server(error))
 			nfs_write_error(req, error);
 		else
 			nfs_redirty_request(req);
-- 
cgit v1.2.3


From 9641d9bc9b75f11f70646f5c6ee9f5f519a1012e Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:27:01 -0400
Subject: NFS: fsync() should report filesystem errors over EINTR/ERESTARTSYS

If the commit to disk is interrupted, we should still first check for
filesystem errors so that we can report them in preference to the error
due to the signal.

Fixes: 2197e9b06c22 ("NFS: Fix up fsync() when the server rebooted")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/file.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 150b7fa8f0a7..7c380e555224 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -204,15 +204,16 @@ static int
 nfs_file_fsync_commit(struct file *file, int datasync)
 {
 	struct inode *inode = file_inode(file);
-	int ret;
+	int ret, ret2;
 
 	dprintk("NFS: fsync file(%pD2) datasync %d\n", file, datasync);
 
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
 	ret = nfs_commit_inode(inode, FLUSH_SYNC);
-	if (ret < 0)
-		return ret;
-	return file_check_and_advance_wb_err(file);
+	ret2 = file_check_and_advance_wb_err(file);
+	if (ret2 < 0)
+		return ret2;
+	return ret;
 }
 
 int
-- 
cgit v1.2.3


From e6005436f6cc9ed13288f936903f0151e5543485 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:27:02 -0400
Subject: NFS: Don't report ENOSPC write errors twice

Any errors reported by the write() system call need to be cleared from
the file descriptor's error tracking. The current call to nfs_wb_all()
causes the error to be reported, but since it doesn't call
file_check_and_advance_wb_err(), we can end up reporting the same error
a second time when the application calls fsync().

Note that since Linux 4.13, the rule is that EIO may be reported for
write(), but it must be reported by a subsequent fsync(), so let's just
drop reporting it in write.

The check for nfs_ctx_key_to_expire() is just a duplicate to the one
already in nfs_write_end(), so let's drop that too.

Reported-by: ChenXiaoSong <chenxiaosong2@huawei.com>
Fixes: ce368536dd61 ("nfs: nfs_file_write() should check for writeback errors")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/file.c | 34 ++++++++++++++--------------------
 1 file changed, 14 insertions(+), 20 deletions(-)

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 7c380e555224..87e4cd5e8fe2 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -598,18 +598,6 @@ static const struct vm_operations_struct nfs_file_vm_ops = {
 	.page_mkwrite = nfs_vm_page_mkwrite,
 };
 
-static int nfs_need_check_write(struct file *filp, struct inode *inode,
-				int error)
-{
-	struct nfs_open_context *ctx;
-
-	ctx = nfs_file_open_context(filp);
-	if (nfs_error_is_fatal_on_server(error) ||
-	    nfs_ctx_key_to_expire(ctx, inode))
-		return 1;
-	return 0;
-}
-
 ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
@@ -637,7 +625,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	if (iocb->ki_flags & IOCB_APPEND || iocb->ki_pos > i_size_read(inode)) {
 		result = nfs_revalidate_file_size(inode, file);
 		if (result)
-			goto out;
+			return result;
 	}
 
 	nfs_clear_invalid_mapping(file->f_mapping);
@@ -656,6 +644,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 
 	written = result;
 	iocb->ki_pos += written;
+	nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
 
 	if (mntflags & NFS_MOUNT_WRITE_EAGER) {
 		result = filemap_fdatawrite_range(file->f_mapping,
@@ -673,17 +662,22 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	}
 	result = generic_write_sync(iocb, written);
 	if (result < 0)
-		goto out;
+		return result;
 
+out:
 	/* Return error values */
 	error = filemap_check_wb_err(file->f_mapping, since);
-	if (nfs_need_check_write(file, inode, error)) {
-		int err = nfs_wb_all(inode);
-		if (err < 0)
-			result = err;
+	switch (error) {
+	default:
+		break;
+	case -EDQUOT:
+	case -EFBIG:
+	case -ENOSPC:
+		nfs_wb_all(inode);
+		error = file_check_and_advance_wb_err(file);
+		if (error < 0)
+			result = error;
 	}
-	nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
-out:
 	return result;
 
 out_swapfile:
-- 
cgit v1.2.3


From d95b26650e86175e4a97698d89bc1626cd1df0c6 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:27:03 -0400
Subject: NFS: Do not report flush errors in nfs_write_end()

If we do flush cached writebacks in nfs_write_end() due to the imminent
expiration of an RPCSEC_GSS session, then we should defer reporting any
resulting errors until the calls to file_check_and_advance_wb_err() in
nfs_file_write() and nfs_file_fsync().

Fixes: 6fbda89b257f ("NFS: Replace custom error reporting mechanism with generic one")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/file.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 87e4cd5e8fe2..3f17748eaf29 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -386,11 +386,8 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 		return status;
 	NFS_I(mapping->host)->write_io += copied;
 
-	if (nfs_ctx_key_to_expire(ctx, mapping->host)) {
-		status = nfs_wb_all(mapping->host);
-		if (status < 0)
-			return status;
-	}
+	if (nfs_ctx_key_to_expire(ctx, mapping->host))
+		nfs_wb_all(mapping->host);
 
 	return copied;
 }
-- 
cgit v1.2.3


From c5e483b77cc2edb318da152abe07e33006b975fd Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:27:04 -0400
Subject: NFS: Don't report errors from nfs_pageio_complete() more than once

Since errors from nfs_pageio_complete() are already being reported
through nfs_async_write_error(), we should not be returning them to the
callers of do_writepages() as well. They will end up being reported
through the generic mechanism instead.

Fixes: 6fbda89b257f ("NFS: Replace custom error reporting mechanism with generic one")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/write.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e437db1791ba..4925d11849cd 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -681,11 +681,7 @@ static int nfs_writepage_locked(struct page *page,
 	err = nfs_do_writepage(page, wbc, &pgio);
 	pgio.pg_error = 0;
 	nfs_pageio_complete(&pgio);
-	if (err < 0)
-		return err;
-	if (nfs_error_is_fatal(pgio.pg_error))
-		return pgio.pg_error;
-	return 0;
+	return err;
 }
 
 int nfs_writepage(struct page *page, struct writeback_control *wbc)
@@ -747,9 +743,6 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 
 	if (err < 0)
 		goto out_err;
-	err = pgio.pg_error;
-	if (nfs_error_is_fatal(err))
-		goto out_err;
 	return 0;
 out_err:
 	return err;
-- 
cgit v1.2.3


From 452284407c18d8a522c3039339b1860afa0025a8 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:08:10 -0400
Subject: NFS: Memory allocation failures are not server fatal errors

We need to filter out ENOMEM in nfs_error_is_fatal_on_server(), because
running out of memory on our client is not a server error.

Reported-by: Olga Kornievskaia <aglo@umich.edu>
Fixes: 2dc23afffbca ("NFS: ENOMEM should also be a fatal error.")
Cc: stable@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/internal.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7eefa16ed381..8f8cd6e2d4db 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -841,6 +841,7 @@ static inline bool nfs_error_is_fatal_on_server(int err)
 	case 0:
 	case -ERESTARTSYS:
 	case -EINTR:
+	case -ENOMEM:
 		return false;
 	}
 	return nfs_error_is_fatal(err);
-- 
cgit v1.2.3


From 3764a17e31d579cf9b4bd0a69894b577e8d75702 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:08:11 -0400
Subject: NFSv4/pNFS: Do not fail I/O when we fail to allocate the pNFS layout

Commit 587f03deb69b caused pnfs_update_layout() to stop returning ENOMEM
when the memory allocation fails, and hence causes it to fall back to
trying to do I/O through the MDS. There is no guarantee that this will
fare any better. If we're failing the pNFS layout allocation, then we
should just redirty the page and retry later.

Reported-by: Olga Kornievskaia <aglo@umich.edu>
Fixes: 587f03deb69b ("pnfs: refactor send_layoutget")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/pnfs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 856c962273c7..68a87be3e6f9 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2000,6 +2000,7 @@ lookup_again:
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {
 		spin_unlock(&ino->i_lock);
+		lseg = ERR_PTR(-ENOMEM);
 		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				 PNFS_UPDATE_LAYOUT_NOMEM);
 		goto out;
@@ -2128,6 +2129,7 @@ lookup_again:
 
 	lgp = pnfs_alloc_init_layoutget_args(ino, ctx, &stateid, &arg, gfp_flags);
 	if (!lgp) {
+		lseg = ERR_PTR(-ENOMEM);
 		trace_pnfs_update_layout(ino, pos, count, iomode, lo, NULL,
 					 PNFS_UPDATE_LAYOUT_NOMEM);
 		nfs_layoutget_end(lo);
-- 
cgit v1.2.3


From c6fd3511c3397dd9cbc6dc5d105bbedb69bf4061 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:08:12 -0400
Subject: NFS: Further fixes to the writeback error handling

When we handle an error by redirtying the page, we're not corrupting the
mapping, so we don't want the error to be recorded in the mapping.
If the caller has specified a sync_mode of WB_SYNC_NONE, we can just
return AOP_WRITEPAGE_ACTIVATE. However if we're dealing with
WB_SYNC_ALL, we need to ensure that retries happen when the errors are
non-fatal.

Reported-by: Olga Kornievskaia <aglo@umich.edu>
Fixes: 8fc75bed96bb ("NFS: Fix up return value on fatal errors in nfs_page_async_flush()")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/write.c | 39 ++++++++++++++++++---------------------
 1 file changed, 18 insertions(+), 21 deletions(-)

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 4925d11849cd..2f41659e232e 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -603,8 +603,9 @@ static void nfs_write_error(struct nfs_page *req, int error)
  * Find an associated nfs write request, and prepare to flush it out
  * May return an error if the user signalled nfs_wait_on_request().
  */
-static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
-				struct page *page)
+static int nfs_page_async_flush(struct page *page,
+				struct writeback_control *wbc,
+				struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_page *req;
 	int ret = 0;
@@ -630,11 +631,11 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 		/*
 		 * Remove the problematic req upon fatal errors on the server
 		 */
-		if (nfs_error_is_fatal(ret)) {
-			if (nfs_error_is_fatal_on_server(ret))
-				goto out_launder;
-		} else
-			ret = -EAGAIN;
+		if (nfs_error_is_fatal_on_server(ret))
+			goto out_launder;
+		if (wbc->sync_mode == WB_SYNC_NONE)
+			ret = AOP_WRITEPAGE_ACTIVATE;
+		redirty_page_for_writepage(wbc, page);
 		nfs_redirty_request(req);
 		pgio->pg_error = 0;
 	} else
@@ -650,15 +651,8 @@ out_launder:
 static int nfs_do_writepage(struct page *page, struct writeback_control *wbc,
 			    struct nfs_pageio_descriptor *pgio)
 {
-	int ret;
-
 	nfs_pageio_cond_complete(pgio, page_index(page));
-	ret = nfs_page_async_flush(pgio, page);
-	if (ret == -EAGAIN) {
-		redirty_page_for_writepage(wbc, page);
-		ret = AOP_WRITEPAGE_ACTIVATE;
-	}
-	return ret;
+	return nfs_page_async_flush(page, wbc, pgio);
 }
 
 /*
@@ -733,12 +727,15 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 		priority = wb_priority(wbc);
 	}
 
-	nfs_pageio_init_write(&pgio, inode, priority, false,
-				&nfs_async_write_completion_ops);
-	pgio.pg_io_completion = ioc;
-	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
-	pgio.pg_error = 0;
-	nfs_pageio_complete(&pgio);
+	do {
+		nfs_pageio_init_write(&pgio, inode, priority, false,
+				      &nfs_async_write_completion_ops);
+		pgio.pg_io_completion = ioc;
+		err = write_cache_pages(mapping, wbc, nfs_writepages_callback,
+					&pgio);
+		pgio.pg_error = 0;
+		nfs_pageio_complete(&pgio);
+	} while (err < 0 && !nfs_error_is_fatal(err));
 	nfs_io_completion_put(ioc);
 
 	if (err < 0)
-- 
cgit v1.2.3


From 126966ddedb60bb7bf9f3b341e26ca8ef1019efc Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:08:13 -0400
Subject: pNFS/files: Fall back to I/O through the MDS on non-fatal layout
 errors

Only report the error when the server is returning a fatal error, such
as ESTALE, EIO, etc...

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/filelayout/filelayout.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 76deddab0a8f..2b2661582bbe 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -839,7 +839,12 @@ fl_pnfs_update_layout(struct inode *ino,
 
 	lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode,
 				  gfp_flags);
-	if (IS_ERR_OR_NULL(lseg))
+	if (IS_ERR(lseg)) {
+		/* Fall back to MDS on recoverable errors */
+		if (!nfs_error_is_fatal_on_server(PTR_ERR(lseg)))
+			lseg = NULL;
+		goto out;
+	} else if (!lseg)
 		goto out;
 
 	lo = NFS_I(ino)->layout;
-- 
cgit v1.2.3


From 6949493884fe88500de4af182588e071cf1544ee Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:08:14 -0400
Subject: NFSv4: Don't hold the layoutget locks across multiple RPC calls

When doing layoutget as part of the open() compound, we have to be
careful to release the layout locks before we can call any further RPC
calls, such as setattr(). The reason is that those calls could trigger
a recall, which could deadlock.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a79f66432bd3..bf3ba541b9fb 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3098,6 +3098,10 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	}
 
 out:
+	if (opendata->lgp) {
+		nfs4_lgopen_release(opendata->lgp);
+		opendata->lgp = NULL;
+	}
 	if (!opendata->cancelled)
 		nfs4_sequence_free_slot(&opendata->o_res.seq_res);
 	return ret;
-- 
cgit v1.2.3


From 7b8b44eb7710e34a1ea5278392417993a549fabf Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:36:58 -0400
Subject: NFSv4: Specify the type of ACL to cache

When caching a NFSv4 ACL, we want to specify whether we are caching an
NFSv4.0 type acl, the NFSv4.1 dacl or the NFSv4.1 sacl.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c       | 59 +++++++++++++++++++++++++++++++++----------------
 include/linux/nfs4.h    |  2 ++
 include/linux/nfs_xdr.h |  7 ++++++
 3 files changed, 49 insertions(+), 19 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index bf3ba541b9fb..e6c830d4db0b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5772,9 +5772,17 @@ static int nfs4_proc_renew(struct nfs_client *clp, const struct cred *cred)
 	return 0;
 }
 
-static inline int nfs4_server_supports_acls(struct nfs_server *server)
+static bool nfs4_server_supports_acls(const struct nfs_server *server,
+				      enum nfs4_acl_type type)
 {
-	return server->caps & NFS_CAP_ACLS;
+	switch (type) {
+	default:
+		return server->attr_bitmask[0] & FATTR4_WORD0_ACL;
+	case NFS4ACL_DACL:
+		return server->attr_bitmask[1] & FATTR4_WORD1_DACL;
+	case NFS4ACL_SACL:
+		return server->attr_bitmask[1] & FATTR4_WORD1_SACL;
+	}
 }
 
 /* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that
@@ -5813,6 +5821,7 @@ unwind:
 }
 
 struct nfs4_cached_acl {
+	enum nfs4_acl_type type;
 	int cached;
 	size_t len;
 	char data[];
@@ -5833,7 +5842,8 @@ static void nfs4_zap_acl_attr(struct inode *inode)
 	nfs4_set_cached_acl(inode, NULL);
 }
 
-static inline ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, size_t buflen)
+static ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf,
+				    size_t buflen, enum nfs4_acl_type type)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs4_cached_acl *acl;
@@ -5843,6 +5853,8 @@ static inline ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, size_
 	acl = nfsi->nfs4_acl;
 	if (acl == NULL)
 		goto out;
+	if (acl->type != type)
+		goto out;
 	if (buf == NULL) /* user is just asking for length */
 		goto out_len;
 	if (acl->cached == 0)
@@ -5858,7 +5870,9 @@ out:
 	return ret;
 }
 
-static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len)
+static void nfs4_write_cached_acl(struct inode *inode, struct page **pages,
+				  size_t pgbase, size_t acl_len,
+				  enum nfs4_acl_type type)
 {
 	struct nfs4_cached_acl *acl;
 	size_t buflen = sizeof(*acl) + acl_len;
@@ -5875,6 +5889,7 @@ static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size
 			goto out;
 		acl->cached = 0;
 	}
+	acl->type = type;
 	acl->len = acl_len;
 out:
 	nfs4_set_cached_acl(inode, acl);
@@ -5890,7 +5905,8 @@ out:
  * length. The next getxattr call will then produce another round trip to
  * the server, this time with the input buf of the required size.
  */
-static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
+static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf,
+				       size_t buflen, enum nfs4_acl_type type)
 {
 	struct page **pages;
 	struct nfs_getaclargs args = {
@@ -5947,7 +5963,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		ret = -ERANGE;
 		goto out_free;
 	}
-	nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len);
+	nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len,
+			      type);
 	if (buf) {
 		if (res.acl_len > buflen) {
 			ret = -ERANGE;
@@ -5967,14 +5984,15 @@ out_free:
 	return ret;
 }
 
-static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
+static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf,
+				     size_t buflen, enum nfs4_acl_type type)
 {
 	struct nfs4_exception exception = {
 		.interruptible = true,
 	};
 	ssize_t ret;
 	do {
-		ret = __nfs4_get_acl_uncached(inode, buf, buflen);
+		ret = __nfs4_get_acl_uncached(inode, buf, buflen, type);
 		trace_nfs4_get_acl(inode, ret);
 		if (ret >= 0)
 			break;
@@ -5983,27 +6001,29 @@ static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bufl
 	return ret;
 }
 
-static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
+static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen,
+				 enum nfs4_acl_type type)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	int ret;
 
-	if (!nfs4_server_supports_acls(server))
+	if (!nfs4_server_supports_acls(server, type))
 		return -EOPNOTSUPP;
 	ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
 	if (ret < 0)
 		return ret;
 	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
 		nfs_zap_acl_cache(inode);
-	ret = nfs4_read_cached_acl(inode, buf, buflen);
+	ret = nfs4_read_cached_acl(inode, buf, buflen, type);
 	if (ret != -ENOENT)
 		/* -ENOENT is returned if there is no ACL or if there is an ACL
 		 * but no cached acl data, just the acl length */
 		return ret;
-	return nfs4_get_acl_uncached(inode, buf, buflen);
+	return nfs4_get_acl_uncached(inode, buf, buflen, type);
 }
 
-static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen)
+static int __nfs4_proc_set_acl(struct inode *inode, const void *buf,
+			       size_t buflen, enum nfs4_acl_type type)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct page *pages[NFS4ACL_MAXPAGES];
@@ -6024,7 +6044,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	/* You can't remove system.nfs4_acl: */
 	if (buflen == 0)
 		return -EINVAL;
-	if (!nfs4_server_supports_acls(server))
+	if (!nfs4_server_supports_acls(server, type))
 		return -EOPNOTSUPP;
 	if (npages > ARRAY_SIZE(pages))
 		return -ERANGE;
@@ -6055,12 +6075,13 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	return ret;
 }
 
-static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen)
+static int nfs4_proc_set_acl(struct inode *inode, const void *buf,
+			     size_t buflen, enum nfs4_acl_type type)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
-		err = __nfs4_proc_set_acl(inode, buf, buflen);
+		err = __nfs4_proc_set_acl(inode, buf, buflen, type);
 		trace_nfs4_set_acl(inode, err);
 		if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) {
 			/*
@@ -7659,19 +7680,19 @@ static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler,
 				   const char *key, const void *buf,
 				   size_t buflen, int flags)
 {
-	return nfs4_proc_set_acl(inode, buf, buflen);
+	return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_ACL);
 }
 
 static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler,
 				   struct dentry *unused, struct inode *inode,
 				   const char *key, void *buf, size_t buflen)
 {
-	return nfs4_proc_get_acl(inode, buf, buflen);
+	return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_ACL);
 }
 
 static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
 {
-	return nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry)));
+	return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_ACL);
 }
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 5662d8be04eb..8d04b6a5964c 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -451,6 +451,8 @@ enum lock_type4 {
 #define FATTR4_WORD1_TIME_MODIFY        (1UL << 21)
 #define FATTR4_WORD1_TIME_MODIFY_SET    (1UL << 22)
 #define FATTR4_WORD1_MOUNTED_ON_FILEID  (1UL << 23)
+#define FATTR4_WORD1_DACL               (1UL << 26)
+#define FATTR4_WORD1_SACL               (1UL << 27)
 #define FATTR4_WORD1_FS_LAYOUT_TYPES    (1UL << 30)
 #define FATTR4_WORD2_LAYOUT_TYPES       (1UL << 0)
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 2863e5a69c6a..13d068c57d8d 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -800,6 +800,13 @@ struct nfs_setattrargs {
 	const struct nfs4_label		*label;
 };
 
+enum nfs4_acl_type {
+	NFS4ACL_NONE = 0,
+	NFS4ACL_ACL,
+	NFS4ACL_DACL,
+	NFS4ACL_SACL,
+};
+
 struct nfs_setaclargs {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *			fh;
-- 
cgit v1.2.3


From db145db021abf75aa1a5810e631425055cfbed47 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:36:59 -0400
Subject: NFSv4: Add encoders/decoders for the NFSv4.1 dacl and sacl attributes

Add the ability to set or retrieve the acl using the NFSv4.1 'dacl' and
'sacl' attributes to the NFSv4 xdr encoders/decoders.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c       |  9 +++--
 fs/nfs/nfs4xdr.c        | 95 ++++++++++++++++++++++++++++++++-----------------
 include/linux/nfs_xdr.h |  3 ++
 3 files changed, 71 insertions(+), 36 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e6c830d4db0b..b2ddbaf32a95 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5911,9 +5911,11 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf,
 	struct page **pages;
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
+		.acl_type = type,
 		.acl_len = buflen,
 	};
 	struct nfs_getaclres res = {
+		.acl_type = type,
 		.acl_len = buflen,
 	};
 	struct rpc_message msg = {
@@ -6028,9 +6030,10 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf,
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct page *pages[NFS4ACL_MAXPAGES];
 	struct nfs_setaclargs arg = {
-		.fh		= NFS_FH(inode),
-		.acl_pages	= pages,
-		.acl_len	= buflen,
+		.fh = NFS_FH(inode),
+		.acl_type = type,
+		.acl_len = buflen,
+		.acl_pages = pages,
 	};
 	struct nfs_setaclres res;
 	struct rpc_message msg = {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 86a5f6516928..0b41e00e754f 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1680,19 +1680,35 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 	encode_op_hdr(xdr, OP_RESTOREFH, decode_restorefh_maxsz, hdr);
 }
 
-static void
-encode_setacl(struct xdr_stream *xdr, const struct nfs_setaclargs *arg,
-		struct compound_hdr *hdr)
+static void nfs4_acltype_to_bitmap(enum nfs4_acl_type type, __u32 bitmap[2])
 {
-	__be32 *p;
+	switch (type) {
+	default:
+		bitmap[0] = FATTR4_WORD0_ACL;
+		bitmap[1] = 0;
+		break;
+	case NFS4ACL_DACL:
+		bitmap[0] = 0;
+		bitmap[1] = FATTR4_WORD1_DACL;
+		break;
+	case NFS4ACL_SACL:
+		bitmap[0] = 0;
+		bitmap[1] = FATTR4_WORD1_SACL;
+	}
+}
+
+static void encode_setacl(struct xdr_stream *xdr,
+			  const struct nfs_setaclargs *arg,
+			  struct compound_hdr *hdr)
+{
+	__u32 bitmap[2];
+
+	nfs4_acltype_to_bitmap(arg->acl_type, bitmap);
 
 	encode_op_hdr(xdr, OP_SETATTR, decode_setacl_maxsz, hdr);
 	encode_nfs4_stateid(xdr, &zero_stateid);
-	p = reserve_space(xdr, 2*4);
-	*p++ = cpu_to_be32(1);
-	*p = cpu_to_be32(FATTR4_WORD0_ACL);
-	p = reserve_space(xdr, 4);
-	*p = cpu_to_be32(arg->acl_len);
+	xdr_encode_bitmap4(xdr, bitmap, ARRAY_SIZE(bitmap));
+	encode_uint32(xdr, arg->acl_len);
 	xdr_write_pages(xdr, arg->acl_pages, 0, arg->acl_len);
 }
 
@@ -2587,11 +2603,11 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
-	const __u32 nfs4_acl_bitmap[1] = {
-		[0] = FATTR4_WORD0_ACL,
-	};
+	__u32 nfs4_acl_bitmap[2];
 	uint32_t replen;
 
+	nfs4_acltype_to_bitmap(args->acl_type, nfs4_acl_bitmap);
+
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
@@ -5386,7 +5402,7 @@ decode_restorefh(struct xdr_stream *xdr)
 }
 
 static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
-			 struct nfs_getaclres *res)
+			 struct nfs_getaclres *res, enum nfs4_acl_type type)
 {
 	unsigned int savep;
 	uint32_t attrlen,
@@ -5404,26 +5420,39 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 	if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
 		goto out;
 
-	if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U)))
-		return -EIO;
-	if (likely(bitmap[0] & FATTR4_WORD0_ACL)) {
-
-		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
-		 * are stored with the acl data to handle the problem of
-		 * variable length bitmaps.*/
-		res->acl_data_offset = xdr_page_pos(xdr);
-		res->acl_len = attrlen;
-
-		/* Check for receive buffer overflow */
-		if (res->acl_len > xdr_stream_remaining(xdr) ||
-		    res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
-			res->acl_flags |= NFS4_ACL_TRUNC;
-			dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
-				attrlen, xdr_stream_remaining(xdr));
-		}
-	} else
-		status = -EOPNOTSUPP;
+	switch (type) {
+	default:
+		if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U)))
+			return -EIO;
+		if (!(bitmap[0] & FATTR4_WORD0_ACL))
+			return -EOPNOTSUPP;
+		break;
+	case NFS4ACL_DACL:
+		if (unlikely(bitmap[0] || bitmap[1] & (FATTR4_WORD1_DACL - 1U)))
+			return -EIO;
+		if (!(bitmap[1] & FATTR4_WORD1_DACL))
+			return -EOPNOTSUPP;
+		break;
+	case NFS4ACL_SACL:
+		if (unlikely(bitmap[0] || bitmap[1] & (FATTR4_WORD1_SACL - 1U)))
+			return -EIO;
+		if (!(bitmap[1] & FATTR4_WORD1_SACL))
+			return -EOPNOTSUPP;
+	}
 
+	/* The bitmap (xdr len + bitmaps) and the attr xdr len words
+	 * are stored with the acl data to handle the problem of
+	 * variable length bitmaps.*/
+	res->acl_data_offset = xdr_page_pos(xdr);
+	res->acl_len = attrlen;
+
+	/* Check for receive buffer overflow */
+	if (res->acl_len > xdr_stream_remaining(xdr) ||
+	    res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
+		res->acl_flags |= NFS4_ACL_TRUNC;
+		dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
+			attrlen, xdr_stream_remaining(xdr));
+	}
 out:
 	return status;
 }
@@ -6486,7 +6515,7 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_getacl(xdr, rqstp, res);
+	status = decode_getacl(xdr, rqstp, res, res->acl_type);
 
 out:
 	return status;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 13d068c57d8d..4a8ba84f848e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -810,6 +810,7 @@ enum nfs4_acl_type {
 struct nfs_setaclargs {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *			fh;
+	enum nfs4_acl_type		acl_type;
 	size_t				acl_len;
 	struct page **			acl_pages;
 };
@@ -821,6 +822,7 @@ struct nfs_setaclres {
 struct nfs_getaclargs {
 	struct nfs4_sequence_args 	seq_args;
 	struct nfs_fh *			fh;
+	enum nfs4_acl_type		acl_type;
 	size_t				acl_len;
 	struct page **			acl_pages;
 };
@@ -829,6 +831,7 @@ struct nfs_getaclargs {
 #define NFS4_ACL_TRUNC		0x0001	/* ACL was truncated */
 struct nfs_getaclres {
 	struct nfs4_sequence_res	seq_res;
+	enum nfs4_acl_type		acl_type;
 	size_t				acl_len;
 	size_t				acl_data_offset;
 	int				acl_flags;
-- 
cgit v1.2.3


From 71342db05722907f30505afa4d845cae0f276d23 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 14 May 2022 10:37:00 -0400
Subject: NFSv4.1: Enable access to the NFSv4.1 'dacl' and 'sacl' attributes

Enable access to the NFSv4 acl via the NFSv4.1 'dacl' and 'sacl'
attributes.
This allows the server to authenticate the DACL and the SACL operations
separately, since reading and/or editing the SACL is usually considered
to be a privileged operation.
It also allows the propagation of automatic inheritance information that
was not supported by the NFSv4.0 'acl' attribute.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b2ddbaf32a95..0dfdbb406f96 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7698,6 +7698,55 @@ static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
 	return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_ACL);
 }
 
+#if defined(CONFIG_NFS_V4_1)
+#define XATTR_NAME_NFSV4_DACL "system.nfs4_dacl"
+
+static int nfs4_xattr_set_nfs4_dacl(const struct xattr_handler *handler,
+				    struct user_namespace *mnt_userns,
+				    struct dentry *unused, struct inode *inode,
+				    const char *key, const void *buf,
+				    size_t buflen, int flags)
+{
+	return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_DACL);
+}
+
+static int nfs4_xattr_get_nfs4_dacl(const struct xattr_handler *handler,
+				    struct dentry *unused, struct inode *inode,
+				    const char *key, void *buf, size_t buflen)
+{
+	return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_DACL);
+}
+
+static bool nfs4_xattr_list_nfs4_dacl(struct dentry *dentry)
+{
+	return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_DACL);
+}
+
+#define XATTR_NAME_NFSV4_SACL "system.nfs4_sacl"
+
+static int nfs4_xattr_set_nfs4_sacl(const struct xattr_handler *handler,
+				    struct user_namespace *mnt_userns,
+				    struct dentry *unused, struct inode *inode,
+				    const char *key, const void *buf,
+				    size_t buflen, int flags)
+{
+	return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_SACL);
+}
+
+static int nfs4_xattr_get_nfs4_sacl(const struct xattr_handler *handler,
+				    struct dentry *unused, struct inode *inode,
+				    const char *key, void *buf, size_t buflen)
+{
+	return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_SACL);
+}
+
+static bool nfs4_xattr_list_nfs4_sacl(struct dentry *dentry)
+{
+	return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_SACL);
+}
+
+#endif
+
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 
 static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler,
@@ -10615,6 +10664,22 @@ static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
 	.set	= nfs4_xattr_set_nfs4_acl,
 };
 
+#if defined(CONFIG_NFS_V4_1)
+static const struct xattr_handler nfs4_xattr_nfs4_dacl_handler = {
+	.name	= XATTR_NAME_NFSV4_DACL,
+	.list	= nfs4_xattr_list_nfs4_dacl,
+	.get	= nfs4_xattr_get_nfs4_dacl,
+	.set	= nfs4_xattr_set_nfs4_dacl,
+};
+
+static const struct xattr_handler nfs4_xattr_nfs4_sacl_handler = {
+	.name	= XATTR_NAME_NFSV4_SACL,
+	.list	= nfs4_xattr_list_nfs4_sacl,
+	.get	= nfs4_xattr_get_nfs4_sacl,
+	.set	= nfs4_xattr_set_nfs4_sacl,
+};
+#endif
+
 #ifdef CONFIG_NFS_V4_2
 static const struct xattr_handler nfs4_xattr_nfs4_user_handler = {
 	.prefix	= XATTR_USER_PREFIX,
@@ -10625,6 +10690,10 @@ static const struct xattr_handler nfs4_xattr_nfs4_user_handler = {
 
 const struct xattr_handler *nfs4_xattr_handlers[] = {
 	&nfs4_xattr_nfs4_acl_handler,
+#if defined(CONFIG_NFS_V4_1)
+	&nfs4_xattr_nfs4_dacl_handler,
+	&nfs4_xattr_nfs4_sacl_handler,
+#endif
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 	&nfs4_xattr_nfs4_label_handler,
 #endif
-- 
cgit v1.2.3


From 3e2910c7e23b55f6452b7130f97217ee0551a71a Mon Sep 17 00:00:00 2001
From: NeilBrown
Date: Mon, 21 Mar 2022 10:59:51 +1100
Subject: NFS: Improve warning message when locks are lost.

NFSv4 can lose locks if, for example there is a network partition for
longer than the lease period.  When this happens a warning message

  NFS: __nfs4_reclaim_open_state: Lock reclaim failed!

is generated, possibly once for each lock (though rate limited).

This is potentially misleading as is can be read as suggesting that lock
reclaim was attempted.  However the default behaviour is to not attempt
to recover locks (except due to server report).

This patch changes the reporting to produce at most one message for each
attempt to recover all state from a given server.  The message reports
the server name and the number of locks lost if that number is non-zero.
It reports that locks were lost and give no suggestion as to whether
there was an attempt or not.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4state.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9e1c987c81e7..775c58def32c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1602,7 +1602,8 @@ static inline void nfs42_complete_copies(struct nfs4_state_owner *sp,
 #endif /* CONFIG_NFS_V4_2 */
 
 static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_state *state,
-				     const struct nfs4_state_recovery_ops *ops)
+				     const struct nfs4_state_recovery_ops *ops,
+				     int *lost_locks)
 {
 	struct nfs4_lock_state *lock;
 	int status;
@@ -1620,7 +1621,7 @@ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_st
 		list_for_each_entry(lock, &state->lock_states, ls_locks) {
 			trace_nfs4_state_lock_reclaim(state, lock);
 			if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
-				pr_warn_ratelimited("NFS: %s: Lock reclaim failed!\n", __func__);
+				*lost_locks += 1;
 		}
 		spin_unlock(&state->state_lock);
 	}
@@ -1630,7 +1631,9 @@ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_st
 	return status;
 }
 
-static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops)
+static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp,
+				   const struct nfs4_state_recovery_ops *ops,
+				   int *lost_locks)
 {
 	struct nfs4_state *state;
 	unsigned int loop = 0;
@@ -1666,7 +1669,7 @@ restart:
 #endif /* CONFIG_NFS_V4_2 */
 		refcount_inc(&state->count);
 		spin_unlock(&sp->so_lock);
-		status = __nfs4_reclaim_open_state(sp, state, ops);
+		status = __nfs4_reclaim_open_state(sp, state, ops, lost_locks);
 
 		switch (status) {
 		default:
@@ -1909,6 +1912,7 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
 	struct rb_node *pos;
 	LIST_HEAD(freeme);
 	int status = 0;
+	int lost_locks = 0;
 
 restart:
 	rcu_read_lock();
@@ -1928,8 +1932,11 @@ restart:
 			spin_unlock(&clp->cl_lock);
 			rcu_read_unlock();
 
-			status = nfs4_reclaim_open_state(sp, ops);
+			status = nfs4_reclaim_open_state(sp, ops, &lost_locks);
 			if (status < 0) {
+				if (lost_locks)
+					pr_warn("NFS: %s: lost %d locks\n",
+						clp->cl_hostname, lost_locks);
 				set_bit(ops->owner_flag_bit, &sp->so_flags);
 				nfs4_put_state_owner(sp);
 				status = nfs4_recovery_handle_error(clp, status);
@@ -1943,6 +1950,9 @@ restart:
 	}
 	rcu_read_unlock();
 	nfs4_free_state_owners(&freeme);
+	if (lost_locks)
+		pr_warn("NFS: %s: lost %d locks\n",
+			clp->cl_hostname, lost_locks);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 5e12f172db9536df4720a50e8aa70c5e212c2037 Mon Sep 17 00:00:00 2001
From: NeilBrown
Date: Mon, 21 Mar 2022 16:20:43 +1100
Subject: NFS: update documentation for the nfs4_unique_id parameter

The documentation for nfs4_unique_id is out-of-date.  In particular it
claim that when nfs4_unique_id is set, the host name is not used.  since
Commit 55b592933b7d ("NFSv4: Fix nfs4_init_uniform_client_string for net
namespaces") both the unique_id AND the host name are used.

Update the documentation to match the code.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 Documentation/admin-guide/nfs/nfs-client.rst | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/Documentation/admin-guide/nfs/nfs-client.rst b/Documentation/admin-guide/nfs/nfs-client.rst
index 6adb6457bc69..36760685dd34 100644
--- a/Documentation/admin-guide/nfs/nfs-client.rst
+++ b/Documentation/admin-guide/nfs/nfs-client.rst
@@ -36,10 +36,9 @@ administrative requirements that require particular behavior that does not
 work well as part of an nfs_client_id4 string.
 
 The nfs.nfs4_unique_id boot parameter specifies a unique string that can be
-used instead of a system's node name when an NFS client identifies itself to
-a server.  Thus, if the system's node name is not unique, or it changes, its
-nfs.nfs4_unique_id stays the same, preventing collision with other clients
-or loss of state during NFS reboot recovery or transparent state migration.
+used together with  a system's node name when an NFS client identifies itself to
+a server.  Thus, if the system's node name is not unique, its
+nfs.nfs4_unique_id can help prevent collisions with other clients.
 
 The nfs.nfs4_unique_id string is typically a UUID, though it can contain
 anything that is believed to be unique across all NFS clients.  An
@@ -53,8 +52,12 @@ outstanding NFSv4 state has expired, to prevent loss of NFSv4 state.
 
 This string can be stored in an NFS client's grub.conf, or it can be provided
 via a net boot facility such as PXE.  It may also be specified as an nfs.ko
-module parameter.  Specifying a uniquifier string is not support for NFS
-clients running in containers.
+module parameter.
+
+This uniquifier string will be the same for all NFS clients running in
+containers unless it is overridden by a value written to
+/sys/fs/nfs/net/nfs_client/identifier which will be local to the network
+namespace of the process which writes.
 
 
 The DNS resolver
-- 
cgit v1.2.3


From a28faaddb2be19659701602fc7c9934ff5fc3fa5 Mon Sep 17 00:00:00 2001
From: Chuck Lever
Date: Mon, 18 Apr 2022 11:58:50 -0400
Subject: Documentation: Add an explanation of NFSv4 client identifiers

To enable NFSv4 to work correctly, NFSv4 client identifiers have
to be globally unique and persistent over client reboots. We
believe that in many cases, a good default identifier can be
chosen and set when a client system is imaged.

Because there are many different ways a system can be imaged,
provide an explanation of how NFSv4 client identifiers and
principals can be set by install scripts and imaging tools.

Additional cases, such as NFSv4 clients running in containers, also
need unique and persistent identifiers. The Linux NFS community
sets forth this explanation to aid those who create and manage
container environments.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 .../filesystems/nfs/client-identifier.rst          | 216 +++++++++++++++++++++
 Documentation/filesystems/nfs/index.rst            |   2 +
 2 files changed, 218 insertions(+)
 create mode 100644 Documentation/filesystems/nfs/client-identifier.rst

diff --git a/Documentation/filesystems/nfs/client-identifier.rst b/Documentation/filesystems/nfs/client-identifier.rst
new file mode 100644
index 000000000000..5147e15815a1
--- /dev/null
+++ b/Documentation/filesystems/nfs/client-identifier.rst
@@ -0,0 +1,216 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================
+NFSv4 client identifier
+=======================
+
+This document explains how the NFSv4 protocol identifies client
+instances in order to maintain file open and lock state during
+system restarts. A special identifier and principal are maintained
+on each client. These can be set by administrators, scripts
+provided by site administrators, or tools provided by Linux
+distributors.
+
+There are risks if a client's NFSv4 identifier and its principal
+are not chosen carefully.
+
+
+Introduction
+------------
+
+The NFSv4 protocol uses "lease-based file locking". Leases help
+NFSv4 servers provide file lock guarantees and manage their
+resources.
+
+Simply put, an NFSv4 server creates a lease for each NFSv4 client.
+The server collects each client's file open and lock state under
+the lease for that client.
+
+The client is responsible for periodically renewing its leases.
+While a lease remains valid, the server holding that lease
+guarantees the file locks the client has created remain in place.
+
+If a client stops renewing its lease (for example, if it crashes),
+the NFSv4 protocol allows the server to remove the client's open
+and lock state after a certain period of time. When a client
+restarts, it indicates to servers that open and lock state
+associated with its previous leases is no longer valid and can be
+destroyed immediately.
+
+In addition, each NFSv4 server manages a persistent list of client
+leases. When the server restarts and clients attempt to recover
+their state, the server uses this list to distinguish amongst
+clients that held state before the server restarted and clients
+sending fresh OPEN and LOCK requests. This enables file locks to
+persist safely across server restarts.
+
+NFSv4 client identifiers
+------------------------
+
+Each NFSv4 client presents an identifier to NFSv4 servers so that
+they can associate the client with its lease. Each client's
+identifier consists of two elements:
+
+  - co_ownerid: An arbitrary but fixed string.
+
+  - boot verifier: A 64-bit incarnation verifier that enables a
+    server to distinguish successive boot epochs of the same client.
+
+The NFSv4.0 specification refers to these two items as an
+"nfs_client_id4". The NFSv4.1 specification refers to these two
+items as a "client_owner4".
+
+NFSv4 servers tie this identifier to the principal and security
+flavor that the client used when presenting it. Servers use this
+principal to authorize subsequent lease modification operations
+sent by the client. Effectively this principal is a third element of
+the identifier.
+
+As part of the identity presented to servers, a good
+"co_ownerid" string has several important properties:
+
+  - The "co_ownerid" string identifies the client during reboot
+    recovery, therefore the string is persistent across client
+    reboots.
+  - The "co_ownerid" string helps servers distinguish the client
+    from others, therefore the string is globally unique. Note
+    that there is no central authority that assigns "co_ownerid"
+    strings.
+  - Because it often appears on the network in the clear, the
+    "co_ownerid" string does not reveal private information about
+    the client itself.
+  - The content of the "co_ownerid" string is set and unchanging
+    before the client attempts NFSv4 mounts after a restart.
+  - The NFSv4 protocol places a 1024-byte limit on the size of the
+    "co_ownerid" string.
+
+Protecting NFSv4 lease state
+----------------------------
+
+NFSv4 servers utilize the "client_owner4" as described above to
+assign a unique lease to each client. Under this scheme, there are
+circumstances where clients can interfere with each other. This is
+referred to as "lease stealing".
+
+If distinct clients present the same "co_ownerid" string and use
+the same principal (for example, AUTH_SYS and UID 0), a server is
+unable to tell that the clients are not the same. Each distinct
+client presents a different boot verifier, so it appears to the
+server as if there is one client that is rebooting frequently.
+Neither client can maintain open or lock state in this scenario.
+
+If distinct clients present the same "co_ownerid" string and use
+distinct principals, the server is likely to allow the first client
+to operate normally but reject subsequent clients with the same
+"co_ownerid" string.
+
+If a client's "co_ownerid" string or principal are not stable,
+state recovery after a server or client reboot is not guaranteed.
+If a client unexpectedly restarts but presents a different
+"co_ownerid" string or principal to the server, the server orphans
+the client's previous open and lock state. This blocks access to
+locked files until the server removes the orphaned state.
+
+If the server restarts and a client presents a changed "co_ownerid"
+string or principal to the server, the server will not allow the
+client to reclaim its open and lock state, and may give those locks
+to other clients in the meantime. This is referred to as "lock
+stealing".
+
+Lease stealing and lock stealing increase the potential for denial
+of service and in rare cases even data corruption.
+
+Selecting an appropriate client identifier
+------------------------------------------
+
+By default, the Linux NFSv4 client implementation constructs its
+"co_ownerid" string starting with the words "Linux NFS" followed by
+the client's UTS node name (the same node name, incidentally, that
+is used as the "machine name" in an AUTH_SYS credential). In small
+deployments, this construction is usually adequate. Often, however,
+the node name by itself is not adequately unique, and can change
+unexpectedly. Problematic situations include:
+
+  - NFS-root (diskless) clients, where the local DCHP server (or
+    equivalent) does not provide a unique host name.
+
+  - "Containers" within a single Linux host.  If each container has
+    a separate network namespace, but does not use the UTS namespace
+    to provide a unique host name, then there can be multiple NFS
+    client instances with the same host name.
+
+  - Clients across multiple administrative domains that access a
+    common NFS server. If hostnames are not assigned centrally
+    then uniqueness cannot be guaranteed unless a domain name is
+    included in the hostname.
+
+Linux provides two mechanisms to add uniqueness to its "co_ownerid"
+string:
+
+    nfs.nfs4_unique_id
+      This module parameter can set an arbitrary uniquifier string
+      via the kernel command line, or when the "nfs" module is
+      loaded.
+
+    /sys/fs/nfs/client/net/identifier
+      This virtual file, available since Linux 5.3, is local to the
+      network namespace in which it is accessed and so can provide
+      distinction between network namespaces (containers) when the
+      hostname remains uniform.
+
+Note that this file is empty on name-space creation. If the
+container system has access to some sort of per-container identity
+then that uniquifier can be used. For example, a uniquifier might
+be formed at boot using the container's internal identifier:
+
+    sha256sum /etc/machine-id | awk '{print $1}' \\
+        > /sys/fs/nfs/client/net/identifier
+
+Security considerations
+-----------------------
+
+The use of cryptographic security for lease management operations
+is strongly encouraged.
+
+If NFS with Kerberos is not configured, a Linux NFSv4 client uses
+AUTH_SYS and UID 0 as the principal part of its client identity.
+This configuration is not only insecure, it increases the risk of
+lease and lock stealing. However, it might be the only choice for
+client configurations that have no local persistent storage.
+"co_ownerid" string uniqueness and persistence is critical in this
+case.
+
+When a Kerberos keytab is present on a Linux NFS client, the client
+attempts to use one of the principals in that keytab when
+identifying itself to servers. The "sec=" mount option does not
+control this behavior. Alternately, a single-user client with a
+Kerberos principal can use that principal in place of the client's
+host principal.
+
+Using Kerberos for this purpose enables the client and server to
+use the same lease for operations covered by all "sec=" settings.
+Additionally, the Linux NFS client uses the RPCSEC_GSS security
+flavor with Kerberos and the integrity QOS to prevent in-transit
+modification of lease modification requests.
+
+Additional notes
+----------------
+The Linux NFSv4 client establishes a single lease on each NFSv4
+server it accesses. NFSv4 mounts from a Linux NFSv4 client of a
+particular server then share that lease.
+
+Once a client establishes open and lock state, the NFSv4 protocol
+enables lease state to transition to other servers, following data
+that has been migrated. This hides data migration completely from
+running applications. The Linux NFSv4 client facilitates state
+migration by presenting the same "client_owner4" to all servers it
+encounters.
+
+========
+See Also
+========
+
+  - nfs(5)
+  - kerberos(7)
+  - RFC 7530 for the NFSv4.0 specification
+  - RFC 8881 for the NFSv4.1 specification.
diff --git a/Documentation/filesystems/nfs/index.rst b/Documentation/filesystems/nfs/index.rst
index 288d8ddb2bc6..8536134f31fd 100644
--- a/Documentation/filesystems/nfs/index.rst
+++ b/Documentation/filesystems/nfs/index.rst
@@ -6,6 +6,8 @@ NFS
 .. toctree::
    :maxdepth: 1
 
+   client-identifier
+   exporting
    pnfs
    rpc-cache
    rpc-server-gss
-- 
cgit v1.2.3


From 9c4a5c75a62e83963083efd4eea5d5bd1583193c Mon Sep 17 00:00:00 2001
From: Dave Wysochanski
Date: Wed, 4 May 2022 09:21:06 -0400
Subject: NFS: Pass i_size to fscache_unuse_cookie() when a file is released

Pass updated i_size in fscache_unuse_cookie() when called
from nfs_fscache_release_file(), which ensures the size of
an fscache object gets written to the cache storage.  Failing
to do so results in unnessary reads from the NFS server, even
when the data is cached, due to a cachefiles object coherency
check failing with a trace similar to the following:
  cachefiles_coherency: o=0000000e BAD osiz B=afbb3 c=0

This problem can be reproduced as follows:
  #!/bin/bash
  v=4.2; NFS_SERVER=127.0.0.1
  set -e; trap cleanup EXIT; rc=1
  function cleanup {
          umount /mnt/nfs > /dev/null 2>&1
          RC_STR="TEST PASS"
          [ $rc -eq 1 ] && RC_STR="TEST FAIL"
          echo "$RC_STR on $(uname -r) with NFSv$v and server $NFS_SERVER"
  }
  mount -o vers=$v,fsc $NFS_SERVER:/export /mnt/nfs
  rm -f /mnt/nfs/file1.bin > /dev/null 2>&1
  dd if=/dev/zero of=/mnt/nfs/file1.bin bs=4096 count=1 > /dev/null 2>&1
  echo 3 > /proc/sys/vm/drop_caches
  echo Read file 1st time from NFS server into fscache
  dd if=/mnt/nfs/file1.bin of=/dev/null > /dev/null 2>&1
  umount /mnt/nfs && mount -o vers=$v,fsc $NFS_SERVER:/export /mnt/nfs
  echo 3 > /proc/sys/vm/drop_caches
  echo Read file 2nd time from fscache
  dd if=/mnt/nfs/file1.bin of=/dev/null > /dev/null 2>&1
  echo Check mountstats for NFS read
  grep -q "READ: 0" /proc/self/mountstats # (1st number) == 0
  [ $? -eq 0 ] && rc=0

Fixes: a6b5a28eb56c "nfs: Convert to new fscache volume/cookie API"
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Tested-by: Daire Byrne <daire@dneg.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/fscache.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index f73c09a9cf0a..e861d7bae305 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -231,11 +231,10 @@ void nfs_fscache_release_file(struct inode *inode, struct file *filp)
 {
 	struct nfs_fscache_inode_auxdata auxdata;
 	struct fscache_cookie *cookie = nfs_i_fscache(inode);
+	loff_t i_size = i_size_read(inode);
 
-	if (fscache_cookie_valid(cookie)) {
-		nfs_fscache_update_auxdata(&auxdata, inode);
-		fscache_unuse_cookie(cookie, &auxdata, NULL);
-	}
+	nfs_fscache_update_auxdata(&auxdata, inode);
+	fscache_unuse_cookie(cookie, &auxdata, &i_size);
 }
 
 /*
-- 
cgit v1.2.3


From c3ed222745d9ad7b69299b349a64ba533c64a34f Mon Sep 17 00:00:00 2001
From: Benjamin Coddington
Date: Sat, 14 May 2022 07:05:13 -0400
Subject: NFSv4: Fix free of uninitialized nfs4_label on referral lookup.

Send along the already-allocated fattr along with nfs4_fs_locations, and
drop the memcpy of fattr.  We end up growing two more allocations, but this
fixes up a crash as:

PID: 790    TASK: ffff88811b43c000  CPU: 0   COMMAND: "ls"
 #0 [ffffc90000857920] panic at ffffffff81b9bfde
 #1 [ffffc900008579c0] do_trap at ffffffff81023a9b
 #2 [ffffc90000857a10] do_error_trap at ffffffff81023b78
 #3 [ffffc90000857a58] exc_stack_segment at ffffffff81be1f45
 #4 [ffffc90000857a80] asm_exc_stack_segment at ffffffff81c009de
 #5 [ffffc90000857b08] nfs_lookup at ffffffffa0302322 [nfs]
 #6 [ffffc90000857b70] __lookup_slow at ffffffff813a4a5f
 #7 [ffffc90000857c60] walk_component at ffffffff813a86c4
 #8 [ffffc90000857cb8] path_lookupat at ffffffff813a9553
 #9 [ffffc90000857cf0] filename_lookup at ffffffff813ab86b

Suggested-by: Trond Myklebust <trondmy@hammerspace.com>
Fixes: 9558a007dbc3 ("NFS: Remove the label from the nfs4_lookup_res struct")
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4namespace.c  |  9 +++++++--
 fs/nfs/nfs4proc.c       | 15 +++++++--------
 fs/nfs/nfs4state.c      |  9 ++++++++-
 fs/nfs/nfs4xdr.c        |  4 ++--
 include/linux/nfs_xdr.h |  2 +-
 5 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 3680c8da510c..f2dbf904c598 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -417,6 +417,9 @@ static int nfs_do_refmount(struct fs_context *fc, struct rpc_clnt *client)
 	fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
 	if (!fs_locations)
 		goto out_free;
+	fs_locations->fattr = nfs_alloc_fattr();
+	if (!fs_locations->fattr)
+		goto out_free_2;
 
 	/* Get locations */
 	dentry = ctx->clone_data.dentry;
@@ -427,14 +430,16 @@ static int nfs_do_refmount(struct fs_context *fc, struct rpc_clnt *client)
 	err = nfs4_proc_fs_locations(client, d_inode(parent), &dentry->d_name, fs_locations, page);
 	dput(parent);
 	if (err != 0)
-		goto out_free_2;
+		goto out_free_3;
 
 	err = -ENOENT;
 	if (fs_locations->nlocations <= 0 ||
 	    fs_locations->fs_path.ncomponents <= 0)
-		goto out_free_2;
+		goto out_free_3;
 
 	err = nfs_follow_referral(fc, fs_locations);
+out_free_3:
+	kfree(fs_locations->fattr);
 out_free_2:
 	kfree(fs_locations);
 out_free:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0dfdbb406f96..337609befd17 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4247,6 +4247,8 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir,
 	if (locations == NULL)
 		goto out;
 
+	locations->fattr = fattr;
+
 	status = nfs4_proc_fs_locations(client, dir, name, locations, page);
 	if (status != 0)
 		goto out;
@@ -4256,17 +4258,14 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir,
 	 * referral.  Cause us to drop into the exception handler, which
 	 * will kick off migration recovery.
 	 */
-	if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) {
+	if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &fattr->fsid)) {
 		dprintk("%s: server did not return a different fsid for"
 			" a referral at %s\n", __func__, name->name);
 		status = -NFS4ERR_MOVED;
 		goto out;
 	}
 	/* Fixup attributes for the nfs_lookup() call to nfs_fhget() */
-	nfs_fixup_referral_attributes(&locations->fattr);
-
-	/* replace the lookup nfs_fattr with the locations nfs_fattr */
-	memcpy(fattr, &locations->fattr, sizeof(struct nfs_fattr));
+	nfs_fixup_referral_attributes(fattr);
 	memset(fhandle, 0, sizeof(struct nfs_fh));
 out:
 	if (page)
@@ -7979,7 +7978,7 @@ static int _nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir,
 	else
 		bitmask[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID;
 
-	nfs_fattr_init(&fs_locations->fattr);
+	nfs_fattr_init(fs_locations->fattr);
 	fs_locations->server = server;
 	fs_locations->nlocations = 0;
 	status = nfs4_call_sync(client, server, &msg, &args.seq_args, &res.seq_res, 0);
@@ -8044,7 +8043,7 @@ static int _nfs40_proc_get_locations(struct nfs_server *server,
 	unsigned long now = jiffies;
 	int status;
 
-	nfs_fattr_init(&locations->fattr);
+	nfs_fattr_init(locations->fattr);
 	locations->server = server;
 	locations->nlocations = 0;
 
@@ -8109,7 +8108,7 @@ static int _nfs41_proc_get_locations(struct nfs_server *server,
 	};
 	int status;
 
-	nfs_fattr_init(&locations->fattr);
+	nfs_fattr_init(locations->fattr);
 	locations->server = server;
 	locations->nlocations = 0;
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 775c58def32c..2540b35ec187 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2116,6 +2116,11 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
 		dprintk("<-- %s: no memory\n", __func__);
 		goto out;
 	}
+	locations->fattr = nfs_alloc_fattr();
+	if (locations->fattr == NULL) {
+		dprintk("<-- %s: no memory\n", __func__);
+		goto out;
+	}
 
 	inode = d_inode(server->super->s_root);
 	result = nfs4_proc_get_locations(server, NFS_FH(inode), locations,
@@ -2130,7 +2135,7 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
 	if (!locations->nlocations)
 		goto out;
 
-	if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
+	if (!(locations->fattr->valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
 		dprintk("<-- %s: No fs_locations data, migration skipped\n",
 			__func__);
 		goto out;
@@ -2155,6 +2160,8 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
 out:
 	if (page != NULL)
 		__free_page(page);
+	if (locations != NULL)
+		kfree(locations->fattr);
 	kfree(locations);
 	if (result) {
 		pr_err("NFS: migration recovery failed (server %s)\n",
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 0b41e00e754f..acfe5f4bda48 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7080,7 +7080,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
 	if (res->migration) {
 		xdr_enter_page(xdr, PAGE_SIZE);
 		status = decode_getfattr_generic(xdr,
-					&res->fs_locations->fattr,
+					res->fs_locations->fattr,
 					 NULL, res->fs_locations,
 					 res->fs_locations->server);
 		if (status)
@@ -7093,7 +7093,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
 			goto out;
 		xdr_enter_page(xdr, PAGE_SIZE);
 		status = decode_getfattr_generic(xdr,
-					&res->fs_locations->fattr,
+					res->fs_locations->fattr,
 					 NULL, res->fs_locations,
 					 res->fs_locations->server);
 	}
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 4a8ba84f848e..0e3aa0f5f324 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1222,7 +1222,7 @@ struct nfs4_fs_location {
 
 #define NFS4_FS_LOCATIONS_MAXENTRIES 10
 struct nfs4_fs_locations {
-	struct nfs_fattr fattr;
+	struct nfs_fattr *fattr;
 	const struct nfs_server *server;
 	struct nfs4_pathname fs_path;
 	int nlocations;
-- 
cgit v1.2.3


From 11270e7ca268e8d61b5d9e5c3a54bd1550642c9c Mon Sep 17 00:00:00 2001
From: Kinglong Mee
Date: Sun, 22 May 2022 20:36:48 +0800
Subject: xprtrdma: treat all calls not a bcall when bc_serv is NULL

When a rdma server returns a fault format reply, nfs v3 client may
treats it as a bcall when bc service is not exist.

The debug message at rpcrdma_bc_receive_call are,

[56579.837169] RPC:       rpcrdma_bc_receive_call: callback XID
00000001, length=20
[56579.837174] RPC:       rpcrdma_bc_receive_call: 00 00 00 01 00 00 00
00 00 00 00 00 00 00 00 00 00 00 00 04

After that, rpcrdma_bc_receive_call will meets NULL pointer as,

[  226.057890] BUG: unable to handle kernel NULL pointer dereference at
00000000000000c8
...
[  226.058704] RIP: 0010:_raw_spin_lock+0xc/0x20
...
[  226.059732] Call Trace:
[  226.059878]  rpcrdma_bc_receive_call+0x138/0x327 [rpcrdma]
[  226.060011]  __ib_process_cq+0x89/0x170 [ib_core]
[  226.060092]  ib_cq_poll_work+0x26/0x80 [ib_core]
[  226.060257]  process_one_work+0x1a7/0x360
[  226.060367]  ? create_worker+0x1a0/0x1a0
[  226.060440]  worker_thread+0x30/0x390
[  226.060500]  ? create_worker+0x1a0/0x1a0
[  226.060574]  kthread+0x116/0x130
[  226.060661]  ? kthread_flush_work_fn+0x10/0x10
[  226.060724]  ret_from_fork+0x35/0x40
...

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 281ddb87ac8d..190a4de239c8 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1121,6 +1121,7 @@ static bool
 rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 {
+	struct rpc_xprt *xprt = &r_xprt->rx_xprt;
 	struct xdr_stream *xdr = &rep->rr_stream;
 	__be32 *p;
 
@@ -1144,6 +1145,10 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 	if (*p != cpu_to_be32(RPC_CALL))
 		return false;
 
+	/* No bc service. */
+	if (xprt->bc_serv == NULL)
+		return false;
+
 	/* Now that we are sure this is a backchannel call,
 	 * advance to the RPC header.
 	 */
-- 
cgit v1.2.3


From 118f09eda21d392e1eeb9f8a4bee044958cccf20 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia
Date: Wed, 25 May 2022 12:12:59 -0400
Subject: NFSv4.1 mark qualified async operations as MOVEABLE tasks

Mark async operations such as RENAME, REMOVE, COMMIT MOVEABLE
for the nfsv4.1+ sessions.

Fixes: 85e39feead948 ("NFSv4.1 identify and mark RPC tasks that can move between transports")
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c         | 26 ++++++++++++++------------
 fs/nfs/pagelist.c         |  3 +++
 fs/nfs/unlink.c           |  8 ++++++++
 fs/nfs/write.c            |  4 ++++
 include/linux/nfs_fs_sb.h |  1 +
 5 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 337609befd17..c0fdcf8c0032 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1162,7 +1162,7 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
 {
 	unsigned short task_flags = 0;
 
-	if (server->nfs_client->cl_minorversion)
+	if (server->caps & NFS_CAP_MOVEABLE)
 		task_flags = RPC_TASK_MOVEABLE;
 	return nfs4_do_call_sync(clnt, server, msg, args, res, task_flags);
 }
@@ -2568,7 +2568,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data,
 	};
 	int status;
 
-	if (server->nfs_client->cl_minorversion)
+	if (nfs_server_capable(dir, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
 	kref_get(&data->kref);
@@ -3737,7 +3737,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait)
 	};
 	int status = -ENOMEM;
 
-	if (server->nfs_client->cl_minorversion)
+	if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
 	nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_CLEANUP,
@@ -4407,7 +4407,7 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
 	};
 	unsigned short task_flags = 0;
 
-	if (server->nfs_client->cl_minorversion)
+	if (nfs_server_capable(dir, NFS_CAP_MOVEABLE))
 		task_flags = RPC_TASK_MOVEABLE;
 
 	/* Is this is an attribute revalidation, subject to softreval? */
@@ -6639,10 +6639,13 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 		.rpc_client = server->client,
 		.rpc_message = &msg,
 		.callback_ops = &nfs4_delegreturn_ops,
-		.flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT | RPC_TASK_MOVEABLE,
+		.flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT,
 	};
 	int status = 0;
 
+	if (nfs_server_capable(inode, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (data == NULL)
 		return -ENOMEM;
@@ -6956,10 +6959,8 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
 		.workqueue = nfsiod_workqueue,
 		.flags = RPC_TASK_ASYNC,
 	};
-	struct nfs_client *client =
-		NFS_SERVER(lsp->ls_state->inode)->nfs_client;
 
-	if (client->cl_minorversion)
+	if (nfs_server_capable(lsp->ls_state->inode, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
 	nfs4_state_protect(NFS_SERVER(lsp->ls_state->inode)->nfs_client,
@@ -7230,9 +7231,8 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 		.flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF,
 	};
 	int ret;
-	struct nfs_client *client = NFS_SERVER(state->inode)->nfs_client;
 
-	if (client->cl_minorversion)
+	if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
 	data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file),
@@ -10467,7 +10467,8 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
-		| NFS_CAP_LGOPEN,
+		| NFS_CAP_LGOPEN
+		| NFS_CAP_MOVEABLE,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
@@ -10502,7 +10503,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_LAYOUTSTATS
 		| NFS_CAP_CLONE
 		| NFS_CAP_LAYOUTERROR
-		| NFS_CAP_READ_PLUS,
+		| NFS_CAP_READ_PLUS
+		| NFS_CAP_MOVEABLE,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 9157dd19b8b4..317cedfa52bf 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -767,6 +767,9 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
 		.flags = RPC_TASK_ASYNC | flags,
 	};
 
+	if (nfs_server_capable(hdr->inode, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
 
 	dprintk("NFS: initiated pgio call "
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 6f325e10056c..9697cd5d2561 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -102,6 +102,10 @@ static void nfs_do_call_unlink(struct inode *inode, struct nfs_unlinkdata *data)
 	};
 	struct rpc_task *task;
 	struct inode *dir = d_inode(data->dentry->d_parent);
+
+	if (nfs_server_capable(inode, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	nfs_sb_active(dir->i_sb);
 	data->args.fh = NFS_FH(dir);
 	nfs_fattr_init(data->res.dir_attr);
@@ -344,6 +348,10 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
 		.flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF,
 	};
 
+	if (nfs_server_capable(old_dir, NFS_CAP_MOVEABLE) &&
+	    nfs_server_capable(new_dir, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (data == NULL)
 		return ERR_PTR(-ENOMEM);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 2f41659e232e..1c706465d090 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1709,6 +1709,10 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 		.flags = RPC_TASK_ASYNC | flags,
 		.priority = priority,
 	};
+
+	if (nfs_server_capable(data->inode, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	/* Set up the initial task struct.  */
 	nfs_ops->commit_setup(data, &msg, &task_setup_data.rpc_client);
 	trace_nfs_initiate_commit(data);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 157d2bd6b241..ea2f7e6b1b0b 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -287,4 +287,5 @@ struct nfs_server {
 #define NFS_CAP_XATTR		(1U << 28)
 #define NFS_CAP_READ_PLUS	(1U << 29)
 #define NFS_CAP_FS_LOCATIONS	(1U << 30)
+#define NFS_CAP_MOVEABLE	(1U << 31)
 #endif
-- 
cgit v1.2.3