1 files changed, 61 insertions, 31 deletions

diff --git a/fs/fcntl.c b/fs/fcntl.c
index c80a6acad742..300e5d9ad913 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -27,6 +27,7 @@
 #include <linux/memfd.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
+#include <linux/rw_hint.h>
 
 #include <linux/poll.h>
 #include <asm/siginfo.h>
@@ -268,8 +269,15 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
 }
 #endif
 
-static bool rw_hint_valid(enum rw_hint hint)
+static bool rw_hint_valid(u64 hint)
 {
+	BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET);
+	BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE);
+	BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT);
+	BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM);
+	BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG);
+	BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME);
+
 	switch (hint) {
 	case RWH_WRITE_LIFE_NOT_SET:
 	case RWH_WRITE_LIFE_NONE:
@@ -283,34 +291,56 @@ static bool rw_hint_valid(enum rw_hint hint)
 	}
 }
 
-static long fcntl_rw_hint(struct file *file, unsigned int cmd,
-			  unsigned long arg)
+static long fcntl_get_rw_hint(struct file *file, unsigned int cmd,
+			      unsigned long arg)
 {
 	struct inode *inode = file_inode(file);
 	u64 __user *argp = (u64 __user *)arg;
-	enum rw_hint hint;
-	u64 h;
+	u64 hint = READ_ONCE(inode->i_write_hint);
 
-	switch (cmd) {
-	case F_GET_RW_HINT:
-		h = inode->i_write_hint;
-		if (copy_to_user(argp, &h, sizeof(*argp)))
-			return -EFAULT;
-		return 0;
-	case F_SET_RW_HINT:
-		if (copy_from_user(&h, argp, sizeof(h)))
-			return -EFAULT;
-		hint = (enum rw_hint) h;
-		if (!rw_hint_valid(hint))
-			return -EINVAL;
+	if (copy_to_user(argp, &hint, sizeof(*argp)))
+		return -EFAULT;
+	return 0;
+}
 
-		inode_lock(inode);
-		inode->i_write_hint = hint;
-		inode_unlock(inode);
-		return 0;
-	default:
+static long fcntl_set_rw_hint(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	struct inode *inode = file_inode(file);
+	u64 __user *argp = (u64 __user *)arg;
+	u64 hint;
+
+	if (copy_from_user(&hint, argp, sizeof(hint)))
+		return -EFAULT;
+	if (!rw_hint_valid(hint))
 		return -EINVAL;
-	}
+
+	WRITE_ONCE(inode->i_write_hint, hint);
+
+	/*
+	 * file->f_mapping->host may differ from inode. As an example,
+	 * blkdev_open() modifies file->f_mapping.
+	 */
+	if (file->f_mapping->host != inode)
+		WRITE_ONCE(file->f_mapping->host->i_write_hint, hint);
+
+	return 0;
+}
+
+/* Is the file descriptor a dup of the file? */
+static long f_dupfd_query(int fd, struct file *filp)
+{
+	CLASS(fd_raw, f)(fd);
+
+	/*
+	 * We can do the 'fdput()' immediately, as the only thing that
+	 * matters is the pointer value which isn't changed by the fdput.
+	 *
+	 * Technically we didn't need a ref at all, and 'fdget()' was
+	 * overkill, but given our lockless file pointer lookup, the
+	 * alternatives are complicated.
+	 */
+	return f.file == filp;
 }
 
 static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
@@ -328,6 +358,9 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_DUPFD_CLOEXEC:
 		err = f_dupfd(argi, filp, O_CLOEXEC);
 		break;
+	case F_DUPFD_QUERY:
+		err = f_dupfd_query(argi, filp);
+		break;
 	case F_GETFD:
 		err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
 		break;
@@ -416,8 +449,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		err = memfd_fcntl(filp, cmd, argi);
 		break;
 	case F_GET_RW_HINT:
+		err = fcntl_get_rw_hint(filp, cmd, arg);
+		break;
 	case F_SET_RW_HINT:
-		err = fcntl_rw_hint(filp, cmd, arg);
+		err = fcntl_set_rw_hint(filp, cmd, arg);
 		break;
 	default:
 		break;
@@ -430,6 +465,7 @@ static int check_fcntl_cmd(unsigned cmd)
 	switch (cmd) {
 	case F_DUPFD:
 	case F_DUPFD_CLOEXEC:
+	case F_DUPFD_QUERY:
 	case F_GETFD:
 	case F_SETFD:
 	case F_GETFL:
@@ -846,12 +882,6 @@ int send_sigurg(struct fown_struct *fown)
 static DEFINE_SPINLOCK(fasync_lock);
 static struct kmem_cache *fasync_cache __ro_after_init;
 
-static void fasync_free_rcu(struct rcu_head *head)
-{
-	kmem_cache_free(fasync_cache,
-			container_of(head, struct fasync_struct, fa_rcu));
-}
-
 /*
  * Remove a fasync entry. If successfully removed, return
  * positive and clear the FASYNC flag. If no entry exists,
@@ -877,7 +907,7 @@ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
 		write_unlock_irq(&fa->fa_lock);
 
 		*fp = fa->fa_next;
-		call_rcu(&fa->fa_rcu, fasync_free_rcu);
+		kfree_rcu(fa, fa_rcu);
 		filp->f_flags &= ~FASYNC;
 		result = 1;
 		break;