[Devel] [PATCH RHEL8 COMMIT] ve/fs/binfmt: fix EBUSY on mounting second binfmt_misc in CT

[Konstantin Khorenko]

The commit is pushed to "branch-rh8-4.18.0-305.3.1.vz8.7.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh8-4.18.0-305.3.1.vz8.7.5
------>
commit e2072ac2b9460e6e87eac30396bbd3295e5e6230
Author: Alexander Mikhalitsyn <alexander.mikhalitsyn at virtuozzo.com>
Date:   Fri Aug 13 10:32:43 2021 +0300

    ve/fs/binfmt: fix EBUSY on mounting second binfmt_misc in CT
    
    After rebase to RHEL 8.4 binfmt_misc fs uses new fscontext API,
    our implementation is incorrect. We have to use get_tree_keyed()
    helper instead of get_tree_single() which allows only one
    superblock per HN.
    
    Fixes: 90fb0e274 ("ve/fs/binfmt: virtualization")
    
    https://jira.sw.ru/browse/PSBM-132709
    
    v2: comments fixed :) Thanks to Pavel for notices
    v3: bm_umount -> bm_kill_super
    
    Signed-off-by: Alexander Mikhalitsyn <alexander.mikhalitsyn at virtuozzo.com>
    Reviewed-by: Pavel Tikhomirov <ptikhomirov at virtuozzo.com>
---
 fs/binfmt_misc.c | 45 +++++++++++++++++++++++++++++++++++++++------
 1 file changed, 39 insertions(+), 6 deletions(-)

diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index c21d03fd3f15..2b586d61f4a9 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -833,10 +833,8 @@ static const struct file_operations bm_status_operations = {
 static void bm_put_super(struct super_block *sb)
 {
 	struct binfmt_misc *bm_data = BINFMT_MISC(sb);
-	struct ve_struct *ve = sb->s_fs_info;
 
 	bm_data->enabled = 0;
-	put_ve(ve);
 }
 
 static const struct super_operations s_ops = {
@@ -875,8 +873,6 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc)
 	}
 
 	sb->s_op = &s_ops;
-	sb->s_fs_info = ve;
-	get_ve(ve);
 
 	bm_data->enabled = 1;
 
@@ -885,10 +881,39 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc)
 
 static int bm_get_tree(struct fs_context *fc)
 {
-	return get_tree_single(fc, bm_fill_super);
+	struct ve_struct *ve = get_exec_env();
+
+	/*
+	 * We need one binfmt_misc superblock per VE,
+	 * use get_tree_keyed() helper to get vfs_tree.
+	 *
+	 * It allows us to find sb by key (in our case ve is the key),
+	 * and if it doesn't exists creates new.
+	 *
+	 * Important: we take ve refcnt here. It will be put
+	 * in one of two places:
+	 * 1. bm_free_fc()
+	 * on error path (wrong mnt opt provided for instance)
+	 * if sb exists and initialized already
+	 * 2. bm_kill_sb() when sb refcnt becomes zero (last mount umounted)
+	 */
+	return get_tree_keyed(fc, bm_fill_super, get_ve(ve));
+}
+
+static void bm_free_fc(struct fs_context *fc)
+{
+	/*
+	 * fc->s_fs_info will be NULL if bm_fill_super() was called and
+	 * no error occured (it means that new sb was allocated successfuly)
+	 * see fs/super.c sget_fc() helper
+	 */
+	if (fc->s_fs_info)
+		put_ve(fc->s_fs_info);
 }
 
+
 static const struct fs_context_operations bm_context_ops = {
+	.free		= bm_free_fc,
 	.get_tree	= bm_get_tree,
 };
 
@@ -898,6 +923,14 @@ static int bm_init_fs_context(struct fs_context *fc)
 	return 0;
 }
 
+static void bm_kill_sb(struct super_block *sb)
+{
+	struct ve_struct *ve = sb->s_fs_info;
+
+	kill_litter_super(sb);
+	put_ve(ve);
+}
+
 static struct linux_binfmt misc_format = {
 	.module = THIS_MODULE,
 	.load_binary = load_misc_binary,
@@ -907,7 +940,7 @@ static struct file_system_type bm_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "binfmt_misc",
 	.init_fs_context = bm_init_fs_context,
-	.kill_sb	= kill_litter_super,
+	.kill_sb	= bm_kill_sb,
 	.fs_flags	= FS_VIRTUALIZED | FS_VE_MOUNT,
 };
 MODULE_ALIAS_FS("binfmt_misc");