From f69999b5f9b444a2443ca2b9e5976e78bb5b7c69 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Thu, 24 Oct 2024 08:52:10 +0900
Subject: [PATCH 01/16] Revert " fs/9p: mitigate inode collisions"

This reverts commit d05dcfdf5e1659b2949d13060284eff3888b644e.

This is a requirement to revert commit 724a08450f74 ("fs/9p: simplify
iget to remove unnecessary paths"), see that revert for details.

Fixes: 724a08450f74 ("fs/9p: simplify iget to remove unnecessary paths")
Reported-by: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/20240923100508.GA32066@willie-the-truck
Cc: stable@vger.kernel.org # v6.9+
Message-ID: <20241024-revert_iget-v1-1-4cac63d25f72@codewreck.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/v9fs.h           | 11 +++++------
 fs/9p/vfs_inode.c      | 37 ++++++++-----------------------------
 fs/9p/vfs_inode_dotl.c | 28 ++++++++--------------------
 fs/9p/vfs_super.c      |  2 +-
 4 files changed, 22 insertions(+), 56 deletions(-)

diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 1775fcc7f0e8..9defa12208f9 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -179,14 +179,13 @@ extern int v9fs_vfs_rename(struct mnt_idmap *idmap,
 			   struct inode *old_dir, struct dentry *old_dentry,
 			   struct inode *new_dir, struct dentry *new_dentry,
 			   unsigned int flags);
-extern struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid,
-						bool new);
+extern struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid);
 extern const struct inode_operations v9fs_dir_inode_operations_dotl;
 extern const struct inode_operations v9fs_file_inode_operations_dotl;
 extern const struct inode_operations v9fs_symlink_inode_operations_dotl;
 extern const struct netfs_request_ops v9fs_req_ops;
 extern struct inode *v9fs_fid_iget_dotl(struct super_block *sb,
-						struct p9_fid *fid, bool new);
+					struct p9_fid *fid);
 
 /* other default globals */
 #define V9FS_PORT	564
@@ -225,12 +224,12 @@ static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses)
  */
 static inline struct inode *
 v9fs_get_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
-			struct super_block *sb, bool new)
+			struct super_block *sb)
 {
 	if (v9fs_proto_dotl(v9ses))
-		return v9fs_fid_iget_dotl(sb, fid, new);
+		return v9fs_fid_iget_dotl(sb, fid);
 	else
-		return v9fs_fid_iget(sb, fid, new);
+		return v9fs_fid_iget(sb, fid);
 }
 
 #endif
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index effb3aa1f3ed..5e05ec7af42e 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -366,8 +366,7 @@ void v9fs_evict_inode(struct inode *inode)
 		clear_inode(inode);
 }
 
-struct inode *
-v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid, bool new)
+struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid)
 {
 	dev_t rdev;
 	int retval;
@@ -379,18 +378,8 @@ v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid, bool new)
 	inode = iget_locked(sb, QID2INO(&fid->qid));
 	if (unlikely(!inode))
 		return ERR_PTR(-ENOMEM);
-	if (!(inode->i_state & I_NEW)) {
-		if (!new) {
-			goto done;
-		} else {
-			p9_debug(P9_DEBUG_VFS, "WARNING: Inode collision %ld\n",
-						inode->i_ino);
-			iput(inode);
-			remove_inode_hash(inode);
-			inode = iget_locked(sb, QID2INO(&fid->qid));
-			WARN_ON(!(inode->i_state & I_NEW));
-		}
-	}
+	if (!(inode->i_state & I_NEW))
+		return inode;
 
 	/*
 	 * initialize the inode with the stat info
@@ -414,11 +403,11 @@ v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid, bool new)
 	v9fs_set_netfs_context(inode);
 	v9fs_cache_inode_get_cookie(inode);
 	unlock_new_inode(inode);
-done:
 	return inode;
 error:
 	iget_failed(inode);
 	return ERR_PTR(retval);
+
 }
 
 /**
@@ -450,15 +439,8 @@ static int v9fs_at_to_dotl_flags(int flags)
  */
 static void v9fs_dec_count(struct inode *inode)
 {
-	if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) {
-		if (inode->i_nlink) {
-			drop_nlink(inode);
-		} else {
-			p9_debug(P9_DEBUG_VFS,
-						"WARNING: unexpected i_nlink zero %d inode %ld\n",
-						inode->i_nlink, inode->i_ino);
-		}
-	}
+	if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
+		drop_nlink(inode);
 }
 
 /**
@@ -509,9 +491,6 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
 		} else
 			v9fs_dec_count(inode);
 
-		if (inode->i_nlink <= 0)	/* no more refs unhash it */
-			remove_inode_hash(inode);
-
 		v9fs_invalidate_inode_attr(inode);
 		v9fs_invalidate_inode_attr(dir);
 
@@ -577,7 +556,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 		/*
 		 * instantiate inode and assign the unopened fid to the dentry
 		 */
-		inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, true);
+		inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
 		if (IS_ERR(inode)) {
 			err = PTR_ERR(inode);
 			p9_debug(P9_DEBUG_VFS,
@@ -706,7 +685,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	else if (IS_ERR(fid))
 		inode = ERR_CAST(fid);
 	else
-		inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, false);
+		inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
 	/*
 	 * If we had a rename on the server and a parallel lookup
 	 * for the new name, then make sure we instantiate with
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index c61b97bd13b9..55dde186041a 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -52,10 +52,7 @@ static kgid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
 	return current_fsgid();
 }
 
-
-
-struct inode *
-v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid, bool new)
+struct inode *v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid)
 {
 	int retval;
 	struct inode *inode;
@@ -65,18 +62,8 @@ v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid, bool new)
 	inode = iget_locked(sb, QID2INO(&fid->qid));
 	if (unlikely(!inode))
 		return ERR_PTR(-ENOMEM);
-	if (!(inode->i_state & I_NEW)) {
-		if (!new) {
-			goto done;
-		} else { /* deal with race condition in inode number reuse */
-			p9_debug(P9_DEBUG_ERROR, "WARNING: Inode collision %lx\n",
-						inode->i_ino);
-			iput(inode);
-			remove_inode_hash(inode);
-			inode = iget_locked(sb, QID2INO(&fid->qid));
-			WARN_ON(!(inode->i_state & I_NEW));
-		}
-	}
+	if (!(inode->i_state & I_NEW))
+		return inode;
 
 	/*
 	 * initialize the inode with the stat info
@@ -103,11 +90,12 @@ v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid, bool new)
 		goto error;
 
 	unlock_new_inode(inode);
-done:
+
 	return inode;
 error:
 	iget_failed(inode);
 	return ERR_PTR(retval);
+
 }
 
 struct dotl_openflag_map {
@@ -259,7 +247,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 		p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
 		goto out;
 	}
-	inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true);
+	inode = v9fs_fid_iget_dotl(dir->i_sb, fid);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err);
@@ -352,7 +340,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap,
 	}
 
 	/* instantiate inode and assign the unopened fid to the dentry */
-	inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true);
+	inode = v9fs_fid_iget_dotl(dir->i_sb, fid);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
@@ -788,7 +776,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir,
 			 err);
 		goto error;
 	}
-	inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true);
+	inode = v9fs_fid_iget_dotl(dir->i_sb, fid);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index f52fdf42945c..55e67e36ae68 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -139,7 +139,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 	else
 		sb->s_d_op = &v9fs_dentry_operations;
 
-	inode = v9fs_get_inode_from_fid(v9ses, fid, sb, true);
+	inode = v9fs_get_inode_from_fid(v9ses, fid, sb);
 	if (IS_ERR(inode)) {
 		retval = PTR_ERR(inode);
 		goto release_sb;
-- 
2.50.1


From fedd06210b14febfa69e09d0721746749ea9ea20 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Thu, 24 Oct 2024 08:52:11 +0900
Subject: [PATCH 02/16] Revert "fs/9p: remove redundant pointer v9ses"

This reverts commit 10211b4a23cf4a3df5c11a10e5b3d371f16a906f.

This is a requirement to revert commit 724a08450f74 ("fs/9p: simplify
iget to remove unnecessary paths"), see that revert for details.

Fixes: 724a08450f74 ("fs/9p: simplify iget to remove unnecessary paths")
Reported-by: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/20240923100508.GA32066@willie-the-truck
Cc: stable@vger.kernel.org # v6.9+
Message-ID: <20241024-revert_iget-v1-2-4cac63d25f72@codewreck.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/vfs_inode_dotl.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 55dde186041a..2b313fe7003e 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -297,6 +297,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap,
 			       umode_t omode)
 {
 	int err;
+	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid = NULL, *dfid = NULL;
 	kgid_t gid;
 	const unsigned char *name;
@@ -306,6 +307,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap,
 	struct posix_acl *dacl = NULL, *pacl = NULL;
 
 	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
+	v9ses = v9fs_inode2v9ses(dir);
 
 	omode |= S_IFDIR;
 	if (dir->i_mode & S_ISGID)
@@ -737,6 +739,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir,
 	kgid_t gid;
 	const unsigned char *name;
 	umode_t mode;
+	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid = NULL, *dfid = NULL;
 	struct inode *inode;
 	struct p9_qid qid;
@@ -746,6 +749,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir,
 		 dir->i_ino, dentry, omode,
 		 MAJOR(rdev), MINOR(rdev));
 
+	v9ses = v9fs_inode2v9ses(dir);
 	dfid = v9fs_parent_fid(dentry);
 	if (IS_ERR(dfid)) {
 		err = PTR_ERR(dfid);
-- 
2.50.1


From 26f8dd2dde6864558782d91542f89483bd59a3c2 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Thu, 24 Oct 2024 08:52:12 +0900
Subject: [PATCH 03/16] Revert "fs/9p: fix uaf in in v9fs_stat2inode_dotl"

This reverts commit 11763a8598f888dec631a8a903f7ada32181001f.

This is a requirement to revert commit 724a08450f74 ("fs/9p: simplify
iget to remove unnecessary paths"), see that revert for details.

Fixes: 724a08450f74 ("fs/9p: simplify iget to remove unnecessary paths")
Reported-by: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/20240923100508.GA32066@willie-the-truck
Cc: stable@vger.kernel.org # v6.9+
Message-ID: <20241024-revert_iget-v1-3-4cac63d25f72@codewreck.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/vfs_inode_dotl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 2b313fe7003e..ef9db3e03506 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -78,11 +78,11 @@ struct inode *v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid)
 
 	retval = v9fs_init_inode(v9ses, inode, &fid->qid,
 				 st->st_mode, new_decode_dev(st->st_rdev));
-	v9fs_stat2inode_dotl(st, inode, 0);
 	kfree(st);
 	if (retval)
 		goto error;
 
+	v9fs_stat2inode_dotl(st, inode, 0);
 	v9fs_set_netfs_context(inode);
 	v9fs_cache_inode_get_cookie(inode);
 	retval = v9fs_get_acl(inode, fid);
-- 
2.50.1


From be2ca3825372085d669d322dccd0542a90e5b434 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Thu, 24 Oct 2024 08:52:13 +0900
Subject: [PATCH 04/16] Revert "fs/9p: simplify iget to remove unnecessary
 paths"

This reverts commit 724a08450f74b02bd89078a596fd24857827c012.

This code simplification introduced significant regressions on servers
that do not remap inode numbers when exporting multiple underlying
filesystems with colliding inodes, as can be illustrated with simple
tmpfs exports in qemu with remapping disabled:
```
# host side
cd /tmp/linux-test
mkdir m1 m2
mount -t tmpfs tmpfs m1
mount -t tmpfs tmpfs m2
mkdir m1/dir m2/dir
echo foo > m1/dir/foo
echo bar > m2/dir/bar

# guest side
# started with -virtfs local,path=/tmp/linux-test,mount_tag=tmp,security_model=mapped-file
mount -t 9p -o trans=virtio,debug=1 tmp /mnt/t

ls /mnt/t/m1/dir
# foo
ls /mnt/t/m2/dir
# bar (works ok if directry isn't open)

# cd to keep first dir's inode alive
cd /mnt/t/m1/dir
ls /mnt/t/m2/dir
# foo (should be bar)
```
Other examples can be crafted with regular files with fscache enabled,
in which case I/Os just happen to the wrong file leading to
corruptions, or guest failing to boot with:
  | VFS: Lookup of 'com.android.runtime' in 9p 9p would have caused loop

In theory, we'd want the servers to be smart enough and ensure they
never send us two different files with the same 'qid.path', but while
qemu has an option to remap that is recommended (and qemu prints a
warning if this case happens), there are many other servers which do
not (kvmtool, nfs-ganesha, probably diod...), we should at least ensure
we don't cause regressions on this:
- assume servers can't be trusted and operations that should get a 'new'
inode properly do so. commit d05dcfdf5e16 (" fs/9p: mitigate inode
collisions") attempted to do this, but v9fs_fid_iget_dotl() was not
called so some higher level of caching got in the way; this needs to be
fixed properly before we can re-apply the patches.
- if we ever want to really simplify this code, we will need to add some
negotiation with the server at mount time where the server could claim
they handle this properly, at which point we could optimize this out.
(but that might not be needed at all if we properly handle the 'new'
check?)

Fixes: 724a08450f74 ("fs/9p: simplify iget to remove unnecessary paths")
Reported-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/all/20240408141436.GA17022@redhat.com/
Link: https://lkml.kernel.org/r/20240923100508.GA32066@willie-the-truck
Cc: stable@vger.kernel.org # v6.9+
Message-ID: <20241024-revert_iget-v1-4-4cac63d25f72@codewreck.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/v9fs.h           | 31 ++++++++++---
 fs/9p/v9fs_vfs.h       |  2 +-
 fs/9p/vfs_inode.c      | 98 +++++++++++++++++++++++++++++++++---------
 fs/9p/vfs_inode_dotl.c | 92 +++++++++++++++++++++++++++++++--------
 fs/9p/vfs_super.c      |  2 +-
 5 files changed, 180 insertions(+), 45 deletions(-)

diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 9defa12208f9..698c43dd5dc8 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -179,13 +179,16 @@ extern int v9fs_vfs_rename(struct mnt_idmap *idmap,
 			   struct inode *old_dir, struct dentry *old_dentry,
 			   struct inode *new_dir, struct dentry *new_dentry,
 			   unsigned int flags);
-extern struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid);
+extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses,
+					 struct p9_fid *fid,
+					 struct super_block *sb, int new);
 extern const struct inode_operations v9fs_dir_inode_operations_dotl;
 extern const struct inode_operations v9fs_file_inode_operations_dotl;
 extern const struct inode_operations v9fs_symlink_inode_operations_dotl;
 extern const struct netfs_request_ops v9fs_req_ops;
-extern struct inode *v9fs_fid_iget_dotl(struct super_block *sb,
-					struct p9_fid *fid);
+extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses,
+					      struct p9_fid *fid,
+					      struct super_block *sb, int new);
 
 /* other default globals */
 #define V9FS_PORT	564
@@ -227,9 +230,27 @@ v9fs_get_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
 			struct super_block *sb)
 {
 	if (v9fs_proto_dotl(v9ses))
-		return v9fs_fid_iget_dotl(sb, fid);
+		return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 0);
 	else
-		return v9fs_fid_iget(sb, fid);
+		return v9fs_inode_from_fid(v9ses, fid, sb, 0);
+}
+
+/**
+ * v9fs_get_new_inode_from_fid - Helper routine to populate an inode by
+ * issuing a attribute request
+ * @v9ses: session information
+ * @fid: fid to issue attribute request for
+ * @sb: superblock on which to create inode
+ *
+ */
+static inline struct inode *
+v9fs_get_new_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+			    struct super_block *sb)
+{
+	if (v9fs_proto_dotl(v9ses))
+		return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 1);
+	else
+		return v9fs_inode_from_fid(v9ses, fid, sb, 1);
 }
 
 #endif
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 7923c3c347cb..d3aefbec4de6 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -42,7 +42,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb);
 void v9fs_free_inode(struct inode *inode);
 void v9fs_set_netfs_context(struct inode *inode);
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
-		    struct inode *inode, struct p9_qid *qid, umode_t mode, dev_t rdev);
+		    struct inode *inode, umode_t mode, dev_t rdev);
 void v9fs_evict_inode(struct inode *inode);
 #if (BITS_PER_LONG == 32)
 #define QID2INO(q) ((ino_t) (((q)->path+2) ^ (((q)->path) >> 32)))
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 5e05ec7af42e..e9c052b35dd9 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -256,12 +256,9 @@ void v9fs_set_netfs_context(struct inode *inode)
 }
 
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
-		    struct inode *inode, struct p9_qid *qid, umode_t mode, dev_t rdev)
+		    struct inode *inode, umode_t mode, dev_t rdev)
 {
 	int err = 0;
-	struct v9fs_inode *v9inode = V9FS_I(inode);
-
-	memcpy(&v9inode->qid, qid, sizeof(struct p9_qid));
 
 	inode_init_owner(&nop_mnt_idmap, inode, NULL, mode);
 	inode->i_blocks = 0;
@@ -366,40 +363,80 @@ void v9fs_evict_inode(struct inode *inode)
 		clear_inode(inode);
 }
 
-struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid)
+static int v9fs_test_inode(struct inode *inode, void *data)
+{
+	int umode;
+	dev_t rdev;
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct p9_wstat *st = (struct p9_wstat *)data;
+	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode);
+
+	umode = p9mode2unixmode(v9ses, st, &rdev);
+	/* don't match inode of different type */
+	if (inode_wrong_type(inode, umode))
+		return 0;
+
+	/* compare qid details */
+	if (memcmp(&v9inode->qid.version,
+		   &st->qid.version, sizeof(v9inode->qid.version)))
+		return 0;
+
+	if (v9inode->qid.type != st->qid.type)
+		return 0;
+
+	if (v9inode->qid.path != st->qid.path)
+		return 0;
+	return 1;
+}
+
+static int v9fs_test_new_inode(struct inode *inode, void *data)
+{
+	return 0;
+}
+
+static int v9fs_set_inode(struct inode *inode,  void *data)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct p9_wstat *st = (struct p9_wstat *)data;
+
+	memcpy(&v9inode->qid, &st->qid, sizeof(st->qid));
+	return 0;
+}
+
+static struct inode *v9fs_qid_iget(struct super_block *sb,
+				   struct p9_qid *qid,
+				   struct p9_wstat *st,
+				   int new)
 {
 	dev_t rdev;
 	int retval;
 	umode_t umode;
 	struct inode *inode;
-	struct p9_wstat *st;
 	struct v9fs_session_info *v9ses = sb->s_fs_info;
+	int (*test)(struct inode *inode, void *data);
+
+	if (new)
+		test = v9fs_test_new_inode;
+	else
+		test = v9fs_test_inode;
 
-	inode = iget_locked(sb, QID2INO(&fid->qid));
-	if (unlikely(!inode))
+	inode = iget5_locked(sb, QID2INO(qid), test, v9fs_set_inode, st);
+	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	if (!(inode->i_state & I_NEW))
 		return inode;
-
 	/*
 	 * initialize the inode with the stat info
 	 * FIXME!! we may need support for stale inodes
 	 * later.
 	 */
-	st = p9_client_stat(fid);
-	if (IS_ERR(st)) {
-		retval = PTR_ERR(st);
-		goto error;
-	}
-
+	inode->i_ino = QID2INO(qid);
 	umode = p9mode2unixmode(v9ses, st, &rdev);
-	retval = v9fs_init_inode(v9ses, inode, &fid->qid, umode, rdev);
-	v9fs_stat2inode(st, inode, sb, 0);
-	p9stat_free(st);
-	kfree(st);
+	retval = v9fs_init_inode(v9ses, inode, umode, rdev);
 	if (retval)
 		goto error;
 
+	v9fs_stat2inode(st, inode, sb, 0);
 	v9fs_set_netfs_context(inode);
 	v9fs_cache_inode_get_cookie(inode);
 	unlock_new_inode(inode);
@@ -410,6 +447,23 @@ error:
 
 }
 
+struct inode *
+v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+		    struct super_block *sb, int new)
+{
+	struct p9_wstat *st;
+	struct inode *inode = NULL;
+
+	st = p9_client_stat(fid);
+	if (IS_ERR(st))
+		return ERR_CAST(st);
+
+	inode = v9fs_qid_iget(sb, &st->qid, st, new);
+	p9stat_free(st);
+	kfree(st);
+	return inode;
+}
+
 /**
  * v9fs_at_to_dotl_flags- convert Linux specific AT flags to
  * plan 9 AT flag.
@@ -556,7 +610,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 		/*
 		 * instantiate inode and assign the unopened fid to the dentry
 		 */
-		inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
+		inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
 		if (IS_ERR(inode)) {
 			err = PTR_ERR(inode);
 			p9_debug(P9_DEBUG_VFS,
@@ -684,8 +738,10 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 		inode = NULL;
 	else if (IS_ERR(fid))
 		inode = ERR_CAST(fid);
-	else
+	else if (v9ses->cache & (CACHE_META|CACHE_LOOSE))
 		inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
+	else
+		inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
 	/*
 	 * If we had a rename on the server and a parallel lookup
 	 * for the new name, then make sure we instantiate with
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index ef9db3e03506..143ac03b7425 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -52,33 +52,76 @@ static kgid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
 	return current_fsgid();
 }
 
-struct inode *v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid)
+static int v9fs_test_inode_dotl(struct inode *inode, void *data)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct p9_stat_dotl *st = (struct p9_stat_dotl *)data;
+
+	/* don't match inode of different type */
+	if (inode_wrong_type(inode, st->st_mode))
+		return 0;
+
+	if (inode->i_generation != st->st_gen)
+		return 0;
+
+	/* compare qid details */
+	if (memcmp(&v9inode->qid.version,
+		   &st->qid.version, sizeof(v9inode->qid.version)))
+		return 0;
+
+	if (v9inode->qid.type != st->qid.type)
+		return 0;
+
+	if (v9inode->qid.path != st->qid.path)
+		return 0;
+	return 1;
+}
+
+/* Always get a new inode */
+static int v9fs_test_new_inode_dotl(struct inode *inode, void *data)
+{
+	return 0;
+}
+
+static int v9fs_set_inode_dotl(struct inode *inode,  void *data)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct p9_stat_dotl *st = (struct p9_stat_dotl *)data;
+
+	memcpy(&v9inode->qid, &st->qid, sizeof(st->qid));
+	inode->i_generation = st->st_gen;
+	return 0;
+}
+
+static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
+					struct p9_qid *qid,
+					struct p9_fid *fid,
+					struct p9_stat_dotl *st,
+					int new)
 {
 	int retval;
 	struct inode *inode;
-	struct p9_stat_dotl *st;
 	struct v9fs_session_info *v9ses = sb->s_fs_info;
+	int (*test)(struct inode *inode, void *data);
+
+	if (new)
+		test = v9fs_test_new_inode_dotl;
+	else
+		test = v9fs_test_inode_dotl;
 
-	inode = iget_locked(sb, QID2INO(&fid->qid));
-	if (unlikely(!inode))
+	inode = iget5_locked(sb, QID2INO(qid), test, v9fs_set_inode_dotl, st);
+	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	if (!(inode->i_state & I_NEW))
 		return inode;
-
 	/*
 	 * initialize the inode with the stat info
 	 * FIXME!! we may need support for stale inodes
 	 * later.
 	 */
-	st = p9_client_getattr_dotl(fid, P9_STATS_BASIC | P9_STATS_GEN);
-	if (IS_ERR(st)) {
-		retval = PTR_ERR(st);
-		goto error;
-	}
-
-	retval = v9fs_init_inode(v9ses, inode, &fid->qid,
+	inode->i_ino = QID2INO(qid);
+	retval = v9fs_init_inode(v9ses, inode,
 				 st->st_mode, new_decode_dev(st->st_rdev));
-	kfree(st);
 	if (retval)
 		goto error;
 
@@ -90,7 +133,6 @@ struct inode *v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid)
 		goto error;
 
 	unlock_new_inode(inode);
-
 	return inode;
 error:
 	iget_failed(inode);
@@ -98,6 +140,22 @@ error:
 
 }
 
+struct inode *
+v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+			 struct super_block *sb, int new)
+{
+	struct p9_stat_dotl *st;
+	struct inode *inode = NULL;
+
+	st = p9_client_getattr_dotl(fid, P9_STATS_BASIC | P9_STATS_GEN);
+	if (IS_ERR(st))
+		return ERR_CAST(st);
+
+	inode = v9fs_qid_iget_dotl(sb, &st->qid, fid, st, new);
+	kfree(st);
+	return inode;
+}
+
 struct dotl_openflag_map {
 	int open_flag;
 	int dotl_flag;
@@ -247,7 +305,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 		p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
 		goto out;
 	}
-	inode = v9fs_fid_iget_dotl(dir->i_sb, fid);
+	inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err);
@@ -342,7 +400,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap,
 	}
 
 	/* instantiate inode and assign the unopened fid to the dentry */
-	inode = v9fs_fid_iget_dotl(dir->i_sb, fid);
+	inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
@@ -780,7 +838,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir,
 			 err);
 		goto error;
 	}
-	inode = v9fs_fid_iget_dotl(dir->i_sb, fid);
+	inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 55e67e36ae68..489db161abc9 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -139,7 +139,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 	else
 		sb->s_d_op = &v9fs_dentry_operations;
 
-	inode = v9fs_get_inode_from_fid(v9ses, fid, sb);
+	inode = v9fs_get_new_inode_from_fid(v9ses, fid, sb);
 	if (IS_ERR(inode)) {
 		retval = PTR_ERR(inode);
 		goto release_sb;
-- 
2.50.1


From bd3734db86e01e20dd239a40b419059a0ce9c901 Mon Sep 17 00:00:00 2001
From: Li Huafei <lihuafei1@huawei.com>
Date: Thu, 24 Oct 2024 23:59:17 +0800
Subject: [PATCH 05/16] fgraph: Fix missing unlock in register_ftrace_graph()

Use guard(mutex)() to acquire and automatically release ftrace_lock,
fixing the issue of not unlocking when calling cpuhp_setup_state()
fails.

Fixes smatch warning:

kernel/trace/fgraph.c:1317 register_ftrace_graph() warn: inconsistent returns '&ftrace_lock'.

Link: https://lore.kernel.org/20241024155917.1019580-1-lihuafei1@huawei.com
Fixes: 2c02f7375e65 ("fgraph: Use CPU hotplug mechanism to initialize idle shadow stacks")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202410220121.wxg0olfd-lkp@intel.com/
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Li Huafei <lihuafei1@huawei.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fgraph.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 41e7a15dcb50..cd1c2946018c 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1252,7 +1252,7 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 	int ret = 0;
 	int i = -1;
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
 	if (!fgraph_initialized) {
 		ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph_idle_init",
@@ -1273,10 +1273,8 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 	}
 
 	i = fgraph_lru_alloc_index();
-	if (i < 0 || WARN_ON_ONCE(fgraph_array[i] != &fgraph_stub)) {
-		ret = -ENOSPC;
-		goto out;
-	}
+	if (i < 0 || WARN_ON_ONCE(fgraph_array[i] != &fgraph_stub))
+		return -ENOSPC;
 	gops->idx = i;
 
 	ftrace_graph_active++;
@@ -1313,8 +1311,6 @@ error:
 		gops->saved_func = NULL;
 		fgraph_lru_release_index(i);
 	}
-out:
-	mutex_unlock(&ftrace_lock);
 	return ret;
 }
 
-- 
2.50.1


From a574e7f80e86c740e241c762923f50077b2c2a30 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 24 Oct 2024 22:29:44 -0400
Subject: [PATCH 06/16] fgraph: Change the name of cpuhp state to
 "fgraph:online"

The cpuhp state name given to cpuhp_setup_state() is "fgraph_idle_init"
which doesn't really conform to the names that are used for cpu hotplug
setups. Instead rename it to "fgraph:online" to be in line with other
states.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/20241024222944.473d88c5@rorschach.local.home
Suggested-by: Masami Hiramatsu <mhiramat@kernel.org>
Fixes: 2c02f7375e658 ("fgraph: Use CPU hotplug mechanism to initialize idle shadow stacks")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fgraph.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index cd1c2946018c..69e226a48daa 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1255,7 +1255,7 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 	guard(mutex)(&ftrace_lock);
 
 	if (!fgraph_initialized) {
-		ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph_idle_init",
+		ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph:online",
 					fgraph_cpu_init, NULL);
 		if (ret < 0) {
 			pr_warn("fgraph: Error to init cpu hotplug support\n");
-- 
2.50.1


From d34a5575e6d2380cc375d2b4650d385a859e67bc Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Mon, 7 Oct 2024 12:43:50 +0200
Subject: [PATCH 07/16] fuse: remove stray debug line

It wasn't there when the patch was posted for review, but somehow made it
into the pull.

Link: https://lore.kernel.org/all/20240913104703.1673180-1-mszeredi@redhat.com/
Fixes: efad7153bf93 ("fuse: allow O_PATH fd for FUSE_DEV_IOC_BACKING_OPEN")
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/passthrough.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
index 7b097e332a90..bbac547dfcb3 100644
--- a/fs/fuse/passthrough.c
+++ b/fs/fuse/passthrough.c
@@ -234,7 +234,6 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map)
 		goto out;
 
 	backing_sb = file_inode(file)->i_sb;
-	pr_info("%s: %x:%pD %i\n", __func__, backing_sb->s_dev, file, backing_sb->s_stack_depth);
 	res = -ELOOP;
 	if (backing_sb->s_stack_depth >= fc->max_stack_depth)
 		goto out_fput;
-- 
2.50.1


From 86e6b1547b3d013bc392adf775b89318441403c2 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 23 Oct 2024 18:17:46 -0700
Subject: [PATCH 08/16] x86: fix user address masking non-canonical speculation
 issue
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

It turns out that AMD has a "Meltdown Lite(tm)" issue with non-canonical
accesses in kernel space.  And so using just the high bit to decide
whether an access is in user space or kernel space ends up with the good
old "leak speculative data" if you have the right gadget using the
result:

  CVE-2020-12965 “Transient Execution of Non-Canonical Accesses“

Now, the kernel surrounds the access with a STAC/CLAC pair, and those
instructions end up serializing execution on older Zen architectures,
which closes the speculation window.

But that was true only up until Zen 5, which renames the AC bit [1].
That improves performance of STAC/CLAC a lot, but also means that the
speculation window is now open.

Note that this affects not just the new address masking, but also the
regular valid_user_address() check used by access_ok(), and the asm
version of the sign bit check in the get_user() helpers.

It does not affect put_user() or clear_user() variants, since there's no
speculative result to be used in a gadget for those operations.

Reported-by: Andrew Cooper <andrew.cooper3@citrix.com>
Link: https://lore.kernel.org/all/80d94591-1297-4afb-b510-c665efd37f10@citrix.com/
Link: https://lore.kernel.org/all/20241023094448.GAZxjFkEOOF_DM83TQ@fat_crate.local/ [1]
Link: https://www.amd.com/en/resources/product-security/bulletin/amd-sb-1010.html
Link: https://arxiv.org/pdf/2108.10771
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Tested-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com> # LAM case
Fixes: 2865baf54077 ("x86: support user address masking instead of non-speculative conditional")
Fixes: 6014bc27561f ("x86-64: make access_ok() independent of LAM")
Fixes: b19b74bc99b1 ("x86/mm: Rework address range check in get_user() and put_user()")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/uaccess_64.h | 43 +++++++++++++++++--------------
 arch/x86/kernel/cpu/common.c      | 10 +++++++
 arch/x86/kernel/vmlinux.lds.S     |  1 +
 arch/x86/lib/getuser.S            |  9 +++++--
 4 files changed, 42 insertions(+), 21 deletions(-)

diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index afce8ee5d7b7..b0a887209400 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -12,6 +12,13 @@
 #include <asm/cpufeatures.h>
 #include <asm/page.h>
 #include <asm/percpu.h>
+#include <asm/runtime-const.h>
+
+/*
+ * Virtual variable: there's no actual backing store for this,
+ * it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)'
+ */
+extern unsigned long USER_PTR_MAX;
 
 #ifdef CONFIG_ADDRESS_MASKING
 /*
@@ -46,19 +53,24 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
 
 #endif
 
-/*
- * The virtual address space space is logically divided into a kernel
- * half and a user half.  When cast to a signed type, user pointers
- * are positive and kernel pointers are negative.
- */
-#define valid_user_address(x) ((__force long)(x) >= 0)
+#define valid_user_address(x) \
+	((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX))
 
 /*
  * Masking the user address is an alternative to a conditional
  * user_access_begin that can avoid the fencing. This only works
  * for dense accesses starting at the address.
  */
-#define mask_user_address(x) ((typeof(x))((long)(x)|((long)(x)>>63)))
+static inline void __user *mask_user_address(const void __user *ptr)
+{
+	unsigned long mask;
+	asm("cmp %1,%0\n\t"
+	    "sbb %0,%0"
+		:"=r" (mask)
+		:"r" (ptr),
+		 "0" (runtime_const_ptr(USER_PTR_MAX)));
+	return (__force void __user *)(mask | (__force unsigned long)ptr);
+}
 #define masked_user_access_begin(x) ({				\
 	__auto_type __masked_ptr = (x);				\
 	__masked_ptr = mask_user_address(__masked_ptr);		\
@@ -69,23 +81,16 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
  * arbitrary values in those bits rather then masking them off.
  *
  * Enforce two rules:
- * 1. 'ptr' must be in the user half of the address space
+ * 1. 'ptr' must be in the user part of the address space
  * 2. 'ptr+size' must not overflow into kernel addresses
  *
- * Note that addresses around the sign change are not valid addresses,
- * and will GP-fault even with LAM enabled if the sign bit is set (see
- * "CR3.LAM_SUP" that can narrow the canonicality check if we ever
- * enable it, but not remove it entirely).
- *
- * So the "overflow into kernel addresses" does not imply some sudden
- * exact boundary at the sign bit, and we can allow a lot of slop on the
- * size check.
+ * Note that we always have at least one guard page between the
+ * max user address and the non-canonical gap, allowing us to
+ * ignore small sizes entirely.
  *
  * In fact, we could probably remove the size check entirely, since
  * any kernel accesses will be in increasing address order starting
- * at 'ptr', and even if the end might be in kernel space, we'll
- * hit the GP faults for non-canonical accesses before we ever get
- * there.
+ * at 'ptr'.
  *
  * That's a separate optimization, for now just handle the small
  * constant case.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f1040cb64841..a5f221ea5688 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -69,6 +69,7 @@
 #include <asm/sev.h>
 #include <asm/tdx.h>
 #include <asm/posted_intr.h>
+#include <asm/runtime-const.h>
 
 #include "cpu.h"
 
@@ -2389,6 +2390,15 @@ void __init arch_cpu_finalize_init(void)
 	alternative_instructions();
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
+		unsigned long USER_PTR_MAX = TASK_SIZE_MAX-1;
+
+		/*
+		 * Enable this when LAM is gated on LASS support
+		if (cpu_feature_enabled(X86_FEATURE_LAM))
+			USER_PTR_MAX = (1ul << 63) - PAGE_SIZE - 1;
+		 */
+		runtime_const_init(ptr, USER_PTR_MAX);
+
 		/*
 		 * Make sure the first 2MB area is not mapped by huge pages
 		 * There are typically fixed size MTRRs in there and overlapping
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 6726be89b7a6..b8c5741d2fb4 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -358,6 +358,7 @@ SECTIONS
 #endif
 
 	RUNTIME_CONST_VARIABLES
+	RUNTIME_CONST(ptr, USER_PTR_MAX)
 
 	. = ALIGN(PAGE_SIZE);
 
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index d066aecf8aeb..4357ec2a0bfc 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -39,8 +39,13 @@
 
 .macro check_range size:req
 .if IS_ENABLED(CONFIG_X86_64)
-	mov %rax, %rdx
-	sar $63, %rdx
+	movq $0x0123456789abcdef,%rdx
+  1:
+  .pushsection runtime_ptr_USER_PTR_MAX,"a"
+	.long 1b - 8 - .
+  .popsection
+	cmp %rax, %rdx
+	sbb %rdx, %rdx
 	or %rdx, %rax
 .else
 	cmp $TASK_SIZE_MAX-\size+1, %eax
-- 
2.50.1


From 4dc1f31ec3f13a065c7ae2ccdec562b0123e21bb Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 24 Oct 2024 13:23:56 -0700
Subject: [PATCH 09/16] x86: fix whitespace in runtime-const assembler output

The x86 user pointer validation changes made me look at compiler output
a lot, and the wrong indentation for the ".popsection" in the generated
assembler triggered me.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/runtime-const.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h
index 24e3a53ca255..6652ebddfd02 100644
--- a/arch/x86/include/asm/runtime-const.h
+++ b/arch/x86/include/asm/runtime-const.h
@@ -6,7 +6,7 @@
 	typeof(sym) __ret;					\
 	asm_inline("mov %1,%0\n1:\n"				\
 		".pushsection runtime_ptr_" #sym ",\"a\"\n\t"	\
-		".long 1b - %c2 - .\n\t"			\
+		".long 1b - %c2 - .\n"				\
 		".popsection"					\
 		:"=r" (__ret)					\
 		:"i" ((unsigned long)0x0123456789abcdefull),	\
@@ -20,7 +20,7 @@
 	typeof(0u+(val)) __ret = (val);				\
 	asm_inline("shrl $12,%k0\n1:\n"				\
 		".pushsection runtime_shift_" #sym ",\"a\"\n\t"	\
-		".long 1b - 1 - .\n\t"				\
+		".long 1b - 1 - .\n"				\
 		".popsection"					\
 		:"+r" (__ret));					\
 	__ret; })
-- 
2.50.1


From b012170fed282151f7ba8988a347670c299f5ab3 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Fri, 25 Oct 2024 21:15:13 +0200
Subject: [PATCH 10/16] platform/x86: asus-wmi: Fix thermal profile
 initialization

When support for vivobook fan profiles was added, the initial
call to throttle_thermal_policy_set_default() was removed, which
however is necessary for full initialization.

Fix this by calling throttle_thermal_policy_set_default() again
when setting up the platform profile.

Fixes: bcbfcebda2cb ("platform/x86: asus-wmi: add support for vivobook fan profiles")
Reported-by: Michael Larabel <Michael@phoronix.com>
Closes: https://www.phoronix.com/review/lunar-lake-xe2/5
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20241025191514.15032-2-W_Armin@gmx.de
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/asus-wmi.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 7a48220b4f5a..abdca3f05c5c 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -3908,6 +3908,16 @@ static int platform_profile_setup(struct asus_wmi *asus)
 	if (!asus->throttle_thermal_policy_dev)
 		return 0;
 
+	/*
+	 * We need to set the default thermal profile during probe or otherwise
+	 * the system will often remain in silent mode, causing low performance.
+	 */
+	err = throttle_thermal_policy_set_default(asus);
+	if (err < 0) {
+		pr_warn("Failed to set default thermal profile\n");
+		return err;
+	}
+
 	dev_info(dev, "Using throttle_thermal_policy for platform_profile support\n");
 
 	asus->platform_profile_handler.profile_get = asus_wmi_platform_profile_get;
-- 
2.50.1


From f6a6780e0b9bbcf311a727afed06fee533a5e957 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Fri, 25 Oct 2024 12:41:37 +0900
Subject: [PATCH 11/16] firewire: core: fix invalid port index for parent
 device

In a commit 24b7f8e5cd65 ("firewire: core: use helper functions for self
ID sequence"), the enumeration over self ID sequence was refactored with
some helper functions with KUnit tests. These helper functions are
guaranteed to work expectedly by the KUnit tests, however their application
includes a mistake to assign invalid value to the index of port connected
to parent device.

This bug affects the case that any extra node devices which has three or
more ports are connected to 1394 OHCI controller. In the case, the path
to update the tree cache could hits WARN_ON(), and gets general protection
fault due to the access to invalid address computed by the invalid value.

This commit fixes the bug to assign correct port index.

Cc: stable@vger.kernel.org
Reported-by: Edmund Raile <edmund.raile@proton.me>
Closes: https://lore.kernel.org/lkml/8a9902a4ece9329af1e1e42f5fea76861f0bf0e8.camel@proton.me/
Fixes: 24b7f8e5cd65 ("firewire: core: use helper functions for self ID sequence")
Link: https://lore.kernel.org/r/20241025034137.99317-1-o-takashi@sakamocchi.jp
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/core-topology.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c
index 6adadb11962e..892b94cfd626 100644
--- a/drivers/firewire/core-topology.c
+++ b/drivers/firewire/core-topology.c
@@ -204,7 +204,7 @@ static struct fw_node *build_tree(struct fw_card *card, const u32 *sid, int self
 				// the node->ports array where the parent node should be.  Later,
 				// when we handle the parent node, we fix up the reference.
 				++parent_count;
-				node->color = i;
+				node->color = port_index;
 				break;
 
 			case PHY_PACKET_SELF_ID_PORT_STATUS_CHILD:
-- 
2.50.1


From 81983758430957d9a5cb3333fe324fd70cf63e7e Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 27 Oct 2024 12:52:02 -1000
Subject: [PATCH 12/16] Linux 6.12-rc5

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index a9a7d9ffaa98..5e04e4abffd8 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
2.50.1


From 3abab905b14f4ba756d413f37f1fb02b708eee93 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Mon, 28 Oct 2024 08:28:30 +0900
Subject: [PATCH 13/16] ksmbd: Fix the missing xa_store error check

xa_store() can fail, it return xa_err(-EINVAL) if the entry cannot
be stored in an XArray, or xa_err(-ENOMEM) if memory allocation failed,
so check error for xa_store() to fix it.

Cc: stable@vger.kernel.org
Fixes: b685757c7b08 ("ksmbd: Implements sess->rpc_handle_list as xarray")
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/mgmt/user_session.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c
index 1e4624e9d434..9756a4bbfe54 100644
--- a/fs/smb/server/mgmt/user_session.c
+++ b/fs/smb/server/mgmt/user_session.c
@@ -90,7 +90,7 @@ static int __rpc_method(char *rpc_name)
 
 int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name)
 {
-	struct ksmbd_session_rpc *entry;
+	struct ksmbd_session_rpc *entry, *old;
 	struct ksmbd_rpc_command *resp;
 	int method;
 
@@ -106,16 +106,19 @@ int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name)
 	entry->id = ksmbd_ipc_id_alloc();
 	if (entry->id < 0)
 		goto free_entry;
-	xa_store(&sess->rpc_handle_list, entry->id, entry, GFP_KERNEL);
+	old = xa_store(&sess->rpc_handle_list, entry->id, entry, GFP_KERNEL);
+	if (xa_is_err(old))
+		goto free_id;
 
 	resp = ksmbd_rpc_open(sess, entry->id);
 	if (!resp)
-		goto free_id;
+		goto erase_xa;
 
 	kvfree(resp);
 	return entry->id;
-free_id:
+erase_xa:
 	xa_erase(&sess->rpc_handle_list, entry->id);
+free_id:
 	ksmbd_rpc_id_free(entry->id);
 free_entry:
 	kfree(entry);
-- 
2.50.1


From 0a77715db22611df50b178374c51e2ba0d58866e Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sat, 2 Nov 2024 18:46:38 +0900
Subject: [PATCH 14/16] ksmbd: fix slab-use-after-free in
 ksmbd_smb2_session_create

There is a race condition between ksmbd_smb2_session_create and
ksmbd_expire_session. This patch add missing sessions_table_lock
while adding/deleting session from global session table.

Cc: stable@vger.kernel.org # v5.15+
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/mgmt/user_session.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c
index 9756a4bbfe54..ad02fe555fda 100644
--- a/fs/smb/server/mgmt/user_session.c
+++ b/fs/smb/server/mgmt/user_session.c
@@ -178,6 +178,7 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn)
 	unsigned long id;
 	struct ksmbd_session *sess;
 
+	down_write(&sessions_table_lock);
 	down_write(&conn->session_lock);
 	xa_for_each(&conn->sessions, id, sess) {
 		if (atomic_read(&sess->refcnt) == 0 &&
@@ -191,6 +192,7 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn)
 		}
 	}
 	up_write(&conn->session_lock);
+	up_write(&sessions_table_lock);
 }
 
 int ksmbd_session_register(struct ksmbd_conn *conn,
@@ -232,7 +234,6 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn)
 			}
 		}
 	}
-	up_write(&sessions_table_lock);
 
 	down_write(&conn->session_lock);
 	xa_for_each(&conn->sessions, id, sess) {
@@ -252,6 +253,7 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn)
 		}
 	}
 	up_write(&conn->session_lock);
+	up_write(&sessions_table_lock);
 }
 
 struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn,
-- 
2.50.1


From b8fc56fbca7482c1e5c0e3351c6ae78982e25ada Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Mon, 4 Nov 2024 13:40:41 +0900
Subject: [PATCH 15/16] ksmbd: fix slab-use-after-free in smb3_preauth_hash_rsp

ksmbd_user_session_put should be called under smb3_preauth_hash_rsp().
It will avoid freeing session before calling smb3_preauth_hash_rsp().

Cc: stable@vger.kernel.org # v5.15+
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/server.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c
index 9670c97f14b3..e7f14f8df943 100644
--- a/fs/smb/server/server.c
+++ b/fs/smb/server/server.c
@@ -238,11 +238,11 @@ static void __handle_ksmbd_work(struct ksmbd_work *work,
 	} while (is_chained == true);
 
 send:
-	if (work->sess)
-		ksmbd_user_session_put(work->sess);
 	if (work->tcon)
 		ksmbd_tree_connect_put(work->tcon);
 	smb3_preauth_hash_rsp(work);
+	if (work->sess)
+		ksmbd_user_session_put(work->sess);
 	if (work->sess && work->sess->enc && work->encrypted &&
 	    conn->ops->encrypt_resp) {
 		rc = conn->ops->encrypt_resp(work);
-- 
2.50.1


From 0a77d947f599b1f39065015bec99390d0c0022ee Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Mon, 4 Nov 2024 13:43:06 +0900
Subject: [PATCH 16/16] ksmbd: check outstanding simultaneous SMB operations
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

If Client send simultaneous SMB operations to ksmbd, It exhausts too much
memory through the "ksmbd_work_cache”. It will cause OOM issue.
ksmbd has a credit mechanism but it can't handle this problem. This patch
add the check if it exceeds max credits to prevent this problem by assuming
that one smb request consumes at least one credit.

Cc: stable@vger.kernel.org # v5.15+
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/connection.c |  1 +
 fs/smb/server/connection.h |  1 +
 fs/smb/server/server.c     | 16 ++++++++++------
 fs/smb/server/smb_common.c | 10 +++++++---
 fs/smb/server/smb_common.h |  2 +-
 5 files changed, 20 insertions(+), 10 deletions(-)

diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index aa2a37a7ce84..e6a72f75ab94 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -70,6 +70,7 @@ struct ksmbd_conn *ksmbd_conn_alloc(void)
 	atomic_set(&conn->req_running, 0);
 	atomic_set(&conn->r_count, 0);
 	atomic_set(&conn->refcnt, 1);
+	atomic_set(&conn->mux_smb_requests, 0);
 	conn->total_credits = 1;
 	conn->outstanding_credits = 0;
 
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index b379ae4fdcdf..8ddd5a3c7baf 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -107,6 +107,7 @@ struct ksmbd_conn {
 	__le16				signing_algorithm;
 	bool				binding;
 	atomic_t			refcnt;
+	atomic_t			mux_smb_requests;
 };
 
 struct ksmbd_conn_ops {
diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c
index e7f14f8df943..e6cfedba9992 100644
--- a/fs/smb/server/server.c
+++ b/fs/smb/server/server.c
@@ -270,6 +270,7 @@ static void handle_ksmbd_work(struct work_struct *wk)
 
 	ksmbd_conn_try_dequeue_request(work);
 	ksmbd_free_work_struct(work);
+	atomic_dec(&conn->mux_smb_requests);
 	/*
 	 * Checking waitqueue to dropping pending requests on
 	 * disconnection. waitqueue_active is safe because it
@@ -291,6 +292,15 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn)
 	struct ksmbd_work *work;
 	int err;
 
+	err = ksmbd_init_smb_server(conn);
+	if (err)
+		return 0;
+
+	if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) {
+		atomic_dec_return(&conn->mux_smb_requests);
+		return -ENOSPC;
+	}
+
 	work = ksmbd_alloc_work_struct();
 	if (!work) {
 		pr_err("allocation for work failed\n");
@@ -301,12 +311,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn)
 	work->request_buf = conn->request_buf;
 	conn->request_buf = NULL;
 
-	err = ksmbd_init_smb_server(work);
-	if (err) {
-		ksmbd_free_work_struct(work);
-		return 0;
-	}
-
 	ksmbd_conn_enqueue_request(work);
 	atomic_inc(&conn->r_count);
 	/* update activity on connection */
diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c
index a2ebbe604c8c..75b4eb856d32 100644
--- a/fs/smb/server/smb_common.c
+++ b/fs/smb/server/smb_common.c
@@ -388,6 +388,10 @@ static struct smb_version_ops smb1_server_ops = {
 	.set_rsp_status = set_smb1_rsp_status,
 };
 
+static struct smb_version_values smb1_server_values = {
+	.max_credits = SMB2_MAX_CREDITS,
+};
+
 static int smb1_negotiate(struct ksmbd_work *work)
 {
 	return ksmbd_smb_negotiate_common(work, SMB_COM_NEGOTIATE);
@@ -399,18 +403,18 @@ static struct smb_version_cmds smb1_server_cmds[1] = {
 
 static int init_smb1_server(struct ksmbd_conn *conn)
 {
+	conn->vals = &smb1_server_values;
 	conn->ops = &smb1_server_ops;
 	conn->cmds = smb1_server_cmds;
 	conn->max_cmds = ARRAY_SIZE(smb1_server_cmds);
 	return 0;
 }
 
-int ksmbd_init_smb_server(struct ksmbd_work *work)
+int ksmbd_init_smb_server(struct ksmbd_conn *conn)
 {
-	struct ksmbd_conn *conn = work->conn;
 	__le32 proto;
 
-	proto = *(__le32 *)((struct smb_hdr *)work->request_buf)->Protocol;
+	proto = *(__le32 *)((struct smb_hdr *)conn->request_buf)->Protocol;
 	if (conn->need_neg == false) {
 		if (proto == SMB1_PROTO_NUMBER)
 			return -EINVAL;
diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h
index cc1d6dfe29d5..a3d8a905b07e 100644
--- a/fs/smb/server/smb_common.h
+++ b/fs/smb/server/smb_common.h
@@ -427,7 +427,7 @@ bool ksmbd_smb_request(struct ksmbd_conn *conn);
 
 int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count);
 
-int ksmbd_init_smb_server(struct ksmbd_work *work);
+int ksmbd_init_smb_server(struct ksmbd_conn *conn);
 
 struct ksmbd_kstat;
 int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work,
-- 
2.50.1