From 0c8c7c559740d2d8b66048162af6c4dba8f0c88c Mon Sep 17 00:00:00 2001
From: Scott Mayhew <smayhew@redhat.com>
Date: Thu, 23 May 2024 15:01:22 -0400
Subject: [PATCH] nfs: don't invalidate dentries on transient errors

This is a slight variation on a patch previously proposed by Neil Brown
that never got merged.

Prior to commit 5ceb9d7fdaaf ("NFS: Refactor nfs_lookup_revalidate()"),
any error from nfs_lookup_verify_inode() other than -ESTALE would result
in nfs_lookup_revalidate() returning that error (-ESTALE is mapped to
zero).

Since that commit, all errors result in nfs_lookup_revalidate()
returning zero, resulting in dentries being invalidated where they
previously were not (particularly in the case of -ERESTARTSYS).

Fix it by passing the actual error code to nfs_lookup_revalidate_done(),
and leaving the decision on whether to  map the error code to zero or
one to nfs_lookup_revalidate_done().

A simple reproducer is to run the following python code in a
subdirectory of an NFS mount (not in the root of the NFS mount):

---8<---
import os
import multiprocessing
import time

if __name__=="__main__":
    multiprocessing.set_start_method("spawn")

    count = 0
    while True:
        try:
            os.getcwd()
            pool = multiprocessing.Pool(10)
            pool.close()
            pool.terminate()
            count += 1
        except Exception as e:
            print(f"Failed after {count} iterations")
            print(e)
            break
---8<---

Prior to commit 5ceb9d7fdaaf, the above code would run indefinitely.
After commit 5ceb9d7fdaaf, it fails almost immediately with -ENOENT.

Signed-off-by: Scott Mayhew <smayhew@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 342930996226..788077a4feb9 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1627,7 +1627,16 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry,
 	switch (error) {
 	case 1:
 		break;
-	case 0:
+	case -ETIMEDOUT:
+		if (inode && (IS_ROOT(dentry) ||
+			      NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL))
+			error = 1;
+		break;
+	case -ESTALE:
+	case -ENOENT:
+		error = 0;
+		fallthrough;
+	default:
 		/*
 		 * We can't d_drop the root of a disconnected tree:
 		 * its d_hash is on the s_anon list and d_drop() would hide
@@ -1682,18 +1691,8 @@ static int nfs_lookup_revalidate_dentry(struct inode *dir,
 
 	dir_verifier = nfs_save_change_attribute(dir);
 	ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
-	if (ret < 0) {
-		switch (ret) {
-		case -ESTALE:
-		case -ENOENT:
-			ret = 0;
-			break;
-		case -ETIMEDOUT:
-			if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL)
-				ret = 1;
-		}
+	if (ret < 0)
 		goto out;
-	}
 
 	/* Request help from readdirplus */
 	nfs_lookup_advise_force_readdirplus(dir, flags);
@@ -1737,7 +1736,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 			 unsigned int flags)
 {
 	struct inode *inode;
-	int error;
+	int error = 0;
 
 	nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE);
 	inode = d_inode(dentry);
@@ -1782,7 +1781,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 out_bad:
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
-	return nfs_lookup_revalidate_done(dir, dentry, inode, 0);
+	return nfs_lookup_revalidate_done(dir, dentry, inode, error);
 }
 
 static int