[Devel] [PATCH RHEL8 COMMIT] ms/ext4: add a new ioctl EXT4_IOC_CLEAR_ES_CACHE

[Konstantin Khorenko]

The commit is pushed to "branch-rh8-4.18.0-193.6.3.vz8.4.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh8-4.18.0-193.6.3.vz8.4.7
------>
commit 198aa9ded209deb9c91a3fba651d9543c5da45ca
Author: Theodore Ts'o <tytso at mit.edu>
Date:   Sun Aug 11 16:30:41 2019 -0400

    ms/ext4: add a new ioctl EXT4_IOC_CLEAR_ES_CACHE
    
    The new ioctl EXT4_IOC_CLEAR_ES_CACHE will force an inode's extent
    status cache to be cleared out.  This is intended for use for
    debugging.
    
    Signed-off-by: Theodore Ts'o <tytso at mit.edu>
    
    https://jira.sw.ru/browse/PSBM-105347
    
    ext4_fiemap() on 3.10 uses information from cached extent tree
    only for checks of delayed extent status, while every of
    the checks waste much time iterating over all extents in tree
    (many rb_next). We will use this ioctl before filefrag (which
    populates the tree from start to end of file, so every iteration
    rb_next() path is rather short).
    
    Signed-off-by: Kirill Tkhai <ktkhai at virtuozzo.com>
    
    (cherry picked from commit b0c013e2928d3696ceb6401311dbc1d7fcccd6dd)
    Signed-off-by: Konstantin Khorenko <khorenko at virtuozzo.com>
---
 fs/ext4/ext4.h           |  2 ++
 fs/ext4/extents_status.c | 28 ++++++++++++++++++++++++++++
 fs/ext4/extents_status.h |  1 +
 fs/ext4/ioctl.c          |  9 +++++++++
 4 files changed, 40 insertions(+)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 5c1091503eb6..028832d858fc 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -651,6 +651,8 @@ enum {
 #define EXT4_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
 #define EXT4_IOC_GET_ENCRYPTION_PWSALT	FS_IOC_GET_ENCRYPTION_PWSALT
 #define EXT4_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
+/* ioctl codes 19--39 are reserved for fscrypt */
+#define EXT4_IOC_CLEAR_ES_CACHE		_IO('f', 40)
 
 #define EXT4_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
 #define EXT4_IOC_FSSETXATTR		FS_IOC_FSSETXATTR
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 023a3eb3afa3..b0a49c5e081c 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -1375,6 +1375,34 @@ static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan)
 	return nr_shrunk;
 }
 
+/*
+ * Called to support EXT4_IOC_CLEAR_ES_CACHE.  We can only remove
+ * discretionary entries from the extent status cache.  (Some entries
+ * must be present for proper operations.)
+ */
+void ext4_clear_inode_es(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct extent_status *es;
+	struct ext4_es_tree *tree;
+	struct rb_node *node;
+
+	write_lock(&ei->i_es_lock);
+	tree = &EXT4_I(inode)->i_es_tree;
+	tree->cache_es = NULL;
+	node = rb_first(&tree->root);
+	while (node) {
+		es = rb_entry(node, struct extent_status, rb_node);
+		node = rb_next(node);
+		if (!ext4_es_is_delayed(es)) {
+			rb_erase(&es->rb_node, &tree->root);
+			ext4_es_free_extent(inode, es);
+		}
+	}
+	ext4_clear_inode_state(inode, EXT4_STATE_EXT_PRECACHED);
+	write_unlock(&ei->i_es_lock);
+}
+
 #ifdef ES_DEBUG__
 static void ext4_print_pending_tree(struct inode *inode)
 {
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 131a8b7df265..e16785f431e7 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -248,5 +248,6 @@ extern unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk,
 					ext4_lblk_t len);
 extern void ext4_es_remove_blks(struct inode *inode, ext4_lblk_t lblk,
 				ext4_lblk_t len);
+extern void ext4_clear_inode_es(struct inode *inode);
 
 #endif /* _EXT4_EXTENTS_STATUS_H */
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 81d1dfa57918..6b305c0898dc 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1115,6 +1115,14 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC_GET_ENCRYPTION_POLICY:
 		return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
 
+	case EXT4_IOC_CLEAR_ES_CACHE:
+	{
+		if (!inode_owner_or_capable(inode))
+			return -EACCES;
+		ext4_clear_inode_es(inode);
+		return 0;
+	}
+
 	case EXT4_IOC_FSGETXATTR:
 	{
 		struct fsxattr fa;
@@ -1294,6 +1302,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC_GET_ENCRYPTION_POLICY:
 	case EXT4_IOC_SHUTDOWN:
 	case FS_IOC_GETFSMAP:
+	case EXT4_IOC_CLEAR_ES_CACHE:
 		break;
 	default:
 		return -ENOIOCTLCMD;