From ddd65e19c60140673ea9f7249af0a672f1820623 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sat, 23 Mar 2024 17:11:19 +0100 Subject: [PATCH] block: handle BLK_OPEN_RESTRICT_WRITES correctly Last kernel release we introduce CONFIG_BLK_DEV_WRITE_MOUNTED. By default this option is set. When it is set the long-standing behavior of being able to write to mounted block devices is enabled. But in order to guard against unintended corruption by writing to the block device buffer cache CONFIG_BLK_DEV_WRITE_MOUNTED can be turned off. In that case it isn't possible to write to mounted block devices anymore. A filesystem may open its block devices with BLK_OPEN_RESTRICT_WRITES which disallows concurrent BLK_OPEN_WRITE access. When we still had the bdev handle around we could recognize BLK_OPEN_RESTRICT_WRITES because the mode was passed around. Since we managed to get rid of the bdev handle we changed that logic to recognize BLK_OPEN_RESTRICT_WRITES based on whether the file was opened writable and writes to that block device are blocked. That logic doesn't work because we do allow BLK_OPEN_RESTRICT_WRITES to be specified without BLK_OPEN_WRITE. Fix the detection logic and use an FMODE_* bit. We could've also abused O_EXCL as an indicator that BLK_OPEN_RESTRICT_WRITES has been requested. For userspace open paths O_EXCL will never be retained but for internal opens where we open files that are never installed into a file descriptor table this is fine. But it would be a gamble that this doesn't cause bugs. Note that BLK_OPEN_RESTRICT_WRITES is an internal only flag that cannot directly be raised by userspace. It is implicitly raised during mounting. Passes xftests and blktests with CONFIG_BLK_DEV_WRITE_MOUNTED set and unset. Link: https://lore.kernel.org/r/ZfyyEwu9Uq5Pgb94@casper.infradead.org Link: https://lore.kernel.org/r/20240323-zielbereich-mittragen-6fdf14876c3e@brauner Fixes: 321de651fa56 ("block: don't rely on BLK_OPEN_RESTRICT_WRITES when yielding write access") Reviewed-by: Yu Kuai Reviewed-by: Jan Kara Reported-by: Matthew Wilcox Signed-off-by: Christian Brauner --- block/bdev.c | 14 +++++++------- include/linux/fs.h | 2 ++ 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/block/bdev.c b/block/bdev.c index 7a5f611c3d2e..ab9cae0e05f1 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -821,13 +821,11 @@ static void bdev_yield_write_access(struct file *bdev_file) return; bdev = file_bdev(bdev_file); - /* Yield exclusive or shared write access. */ - if (bdev_file->f_mode & FMODE_WRITE) { - if (bdev_writes_blocked(bdev)) - bdev_unblock_writes(bdev); - else - bdev->bd_writers--; - } + + if (bdev_file->f_mode & FMODE_WRITE_RESTRICTED) + bdev_unblock_writes(bdev); + else if (bdev_file->f_mode & FMODE_WRITE) + bdev->bd_writers--; } /** @@ -907,6 +905,8 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT; if (bdev_nowait(bdev)) bdev_file->f_mode |= FMODE_NOWAIT; + if (mode & BLK_OPEN_RESTRICT_WRITES) + bdev_file->f_mode |= FMODE_WRITE_RESTRICTED; bdev_file->f_mapping = bdev->bd_inode->i_mapping; bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping); bdev_file->private_data = holder; diff --git a/include/linux/fs.h b/include/linux/fs.h index 00fc429b0af0..8dfd53b52744 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -121,6 +121,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) +/* File writes are restricted (block device specific) */ +#define FMODE_WRITE_RESTRICTED ((__force fmode_t)0x40) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */