[PATCH AUTOSEL 5.12 23/37] ceph: fix fscache invalidation

[PATCH AUTOSEL 5.12 23/37] ceph: fix fscache invalidation

[Sasha Levin]

From: Jeff Layton <jlayton@kernel.org>

[ Upstream commit 10a7052c7868bc7bc72d947f5aac6f768928db87 ]

Ensure that we invalidate the fscache whenever we invalidate the
pagecache.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ceph/caps.c  | 1 +
 fs/ceph/inode.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 570731c4d019..d405ba801492 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1867,6 +1867,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
 	u32 invalidating_gen = ci->i_rdcache_gen;
 
 	spin_unlock(&ci->i_ceph_lock);
+	ceph_fscache_invalidate(inode);
 	invalidate_mapping_pages(&inode->i_data, 0, -1);
 	spin_lock(&ci->i_ceph_lock);
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 156f849f5385..4418d4be2907 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1863,6 +1863,7 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 	orig_gen = ci->i_rdcache_gen;
 	spin_unlock(&ci->i_ceph_lock);
 
+	ceph_fscache_invalidate(inode);
 	if (invalidate_inode_pages2(inode->i_mapping) < 0) {
 		pr_err("invalidate_pages %p fails\n", inode);
 	}
-- 
2.30.2

[PATCH AUTOSEL 5.12 24/37] ceph: don't clobber i_snap_caps on non-I_NEW inode

[Sasha Levin]

From: Jeff Layton <jlayton@kernel.org>

[ Upstream commit d3c51ae1b8cce5bdaf91a1ce32b33cf5626075dc ]

We want the snapdir to mirror the non-snapped directory's attributes for
most things, but i_snap_caps represents the caps granted on the snapshot
directory by the MDS itself. A misbehaving MDS could issue different
caps for the snapdir and we lose them here.

Only reset i_snap_caps when the inode is I_NEW. Also, move the setting
of i_op and i_fop inside the if block since they should never change
anyway.

Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ceph/inode.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 4418d4be2907..2fd1c48ac5d7 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -87,14 +87,15 @@ struct inode *ceph_get_snapdir(struct inode *parent)
 	inode->i_mtime = parent->i_mtime;
 	inode->i_ctime = parent->i_ctime;
 	inode->i_atime = parent->i_atime;
-	inode->i_op = &ceph_snapdir_iops;
-	inode->i_fop = &ceph_snapdir_fops;
-	ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
 	ci->i_rbytes = 0;
 	ci->i_btime = ceph_inode(parent)->i_btime;
 
-	if (inode->i_state & I_NEW)
+	if (inode->i_state & I_NEW) {
+		inode->i_op = &ceph_snapdir_iops;
+		inode->i_fop = &ceph_snapdir_fops;
+		ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
 		unlock_new_inode(inode);
+	}
 
 	return inode;
 }
-- 
2.30.2

[PATCH AUTOSEL 5.12 25/37] ceph: don't allow access to MDS-private inodes

[Sasha Levin]

From: Jeff Layton <jlayton@kernel.org>

[ Upstream commit d4f6b31d721779d91b5e2f8072478af73b196c34 ]

The MDS reserves a set of inodes for its own usage, and these should
never be accessible to clients. Add a new helper to vet a proposed
inode number against that range, and complain loudly and refuse to
create or look it up if it's in it.

Also, ensure that the MDS doesn't try to delegate inodes that are in
that range or lower. Print a warning if it does, and don't save the
range in the xarray.

URL: https://tracker.ceph.com/issues/49922
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ceph/export.c     |  8 ++++++++
 fs/ceph/inode.c      |  3 +++
 fs/ceph/mds_client.c |  7 +++++++
 fs/ceph/super.h      | 24 ++++++++++++++++++++++++
 4 files changed, 42 insertions(+)

diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index e088843a7734..80717234410f 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -129,6 +129,10 @@ static struct inode *__lookup_inode(struct super_block *sb, u64 ino)
 
 	vino.ino = ino;
 	vino.snap = CEPH_NOSNAP;
+
+	if (ceph_vino_is_reserved(vino))
+		return ERR_PTR(-ESTALE);
+
 	inode = ceph_find_inode(sb, vino);
 	if (!inode) {
 		struct ceph_mds_request *req;
@@ -212,6 +216,10 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb,
 		vino.ino = sfh->ino;
 		vino.snap = sfh->snapid;
 	}
+
+	if (ceph_vino_is_reserved(vino))
+		return ERR_PTR(-ESTALE);
+
 	inode = ceph_find_inode(sb, vino);
 	if (inode)
 		return d_obtain_alias(inode);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 2fd1c48ac5d7..179d2ef69a24 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -56,6 +56,9 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
 {
 	struct inode *inode;
 
+	if (ceph_vino_is_reserved(vino))
+		return ERR_PTR(-EREMOTEIO);
+
 	inode = iget5_locked(sb, (unsigned long)vino.ino, ceph_ino_compare,
 			     ceph_set_ino_cb, &vino);
 	if (!inode)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d87bd852ed96..298cb0b3d28c 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -433,6 +433,13 @@ static int ceph_parse_deleg_inos(void **p, void *end,
 
 		ceph_decode_64_safe(p, end, start, bad);
 		ceph_decode_64_safe(p, end, len, bad);
+
+		/* Don't accept a delegation of system inodes */
+		if (start < CEPH_INO_SYSTEM_BASE) {
+			pr_warn_ratelimited("ceph: ignoring reserved inode range delegation (start=0x%llx len=0x%llx)\n",
+					start, len);
+			continue;
+		}
 		while (len--) {
 			int err = xa_insert(&s->s_delegated_inos, ino = start++,
 					    DELEGATED_INO_AVAILABLE,
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index c48bb30c8d70..1d2fe70439bd 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -529,10 +529,34 @@ static inline int ceph_ino_compare(struct inode *inode, void *data)
 		ci->i_vino.snap == pvino->snap;
 }
 
+/*
+ * The MDS reserves a set of inodes for its own usage. These should never
+ * be accessible by clients, and so the MDS has no reason to ever hand these
+ * out. The range is CEPH_MDS_INO_MDSDIR_OFFSET..CEPH_INO_SYSTEM_BASE.
+ *
+ * These come from src/mds/mdstypes.h in the ceph sources.
+ */
+#define CEPH_MAX_MDS		0x100
+#define CEPH_NUM_STRAY		10
+#define CEPH_MDS_INO_MDSDIR_OFFSET	(1 * CEPH_MAX_MDS)
+#define CEPH_INO_SYSTEM_BASE		((6*CEPH_MAX_MDS) + (CEPH_MAX_MDS * CEPH_NUM_STRAY))
+
+static inline bool ceph_vino_is_reserved(const struct ceph_vino vino)
+{
+	if (vino.ino < CEPH_INO_SYSTEM_BASE &&
+	    vino.ino >= CEPH_MDS_INO_MDSDIR_OFFSET) {
+		WARN_RATELIMIT(1, "Attempt to access reserved inode number 0x%llx", vino.ino);
+		return true;
+	}
+	return false;
+}
 
 static inline struct inode *ceph_find_inode(struct super_block *sb,
 					    struct ceph_vino vino)
 {
+	if (ceph_vino_is_reserved(vino))
+		return NULL;
+
 	/*
 	 * NB: The hashval will be run through the fs/inode.c hash function
 	 * anyway, so there is no need to squash the inode number down to
-- 
2.30.2