From 9db97752244919c604eb21df7ef2da3bf58aec73 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 13 May 2020 08:47:17 +0200 Subject: fs: unexport __kernel_write This is a very special interface that skips sb_writes protection, and not used by modules anymore. Signed-off-by: Christoph Hellwig --- fs/read_write.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/read_write.c') diff --git a/fs/read_write.c b/fs/read_write.c index bbfa9b12b15e..2c601d853ff3 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -522,7 +522,6 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t inc_syscw(current); return ret; } -EXPORT_SYMBOL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) -- cgit From a01ac27be4729f80176a45c54611b768dfbdc840 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 8 May 2020 08:55:03 +0200 Subject: fs: check FMODE_WRITE in __kernel_write Add a WARN_ON_ONCE if the file isn't actually open for write. This matches the check done in vfs_write, but actually warn warns as a kernel user calling write on a file not opened for writing is a pretty obvious programming error. Signed-off-by: Christoph Hellwig --- fs/read_write.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/read_write.c') diff --git a/fs/read_write.c b/fs/read_write.c index 2c601d853ff3..8f9fc05990ae 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -505,6 +505,8 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t const char __user *p; ssize_t ret; + if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) + return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; -- cgit From 81238b2cff1469ff5b94390d026cd075105d6dcd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 7 May 2020 19:33:03 +0200 Subject: fs: implement kernel_write using __kernel_write Consolidate the two in-kernel write helpers to make upcoming changes easier. The only difference are the missing call to rw_verify_area in kernel_write, and an access_ok check that doesn't make sense for kernel buffers to start with. Signed-off-by: Christoph Hellwig --- fs/read_write.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'fs/read_write.c') diff --git a/fs/read_write.c b/fs/read_write.c index 8f9fc05990ae..5110cd1e6e27 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -499,6 +499,7 @@ static ssize_t __vfs_write(struct file *file, const char __user *p, return -EINVAL; } +/* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { mm_segment_t old_fs; @@ -528,16 +529,16 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { - mm_segment_t old_fs; - ssize_t res; + ssize_t ret; - old_fs = get_fs(); - set_fs(KERNEL_DS); - /* The cast to a user pointer is valid due to the set_fs() */ - res = vfs_write(file, (__force const char __user *)buf, count, pos); - set_fs(old_fs); + ret = rw_verify_area(WRITE, file, pos, count); + if (ret) + return ret; - return res; + file_start_write(file); + ret = __kernel_write(file, buf, count, pos); + file_end_write(file); + return ret; } EXPORT_SYMBOL(kernel_write); -- cgit From 53ad86266bda973b526078227997ca3fcb92c9be Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 13 May 2020 08:51:46 +0200 Subject: fs: remove __vfs_write Fold it into the two callers. Signed-off-by: Christoph Hellwig --- fs/read_write.c | 46 ++++++++++++++++++++++------------------------ 1 file changed, 22 insertions(+), 24 deletions(-) (limited to 'fs/read_write.c') diff --git a/fs/read_write.c b/fs/read_write.c index 5110cd1e6e27..96e8e354f99b 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -488,17 +488,6 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t return ret; } -static ssize_t __vfs_write(struct file *file, const char __user *p, - size_t count, loff_t *pos) -{ - if (file->f_op->write) - return file->f_op->write(file, p, count, pos); - else if (file->f_op->write_iter) - return new_sync_write(file, p, count, pos); - else - return -EINVAL; -} - /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { @@ -516,7 +505,12 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t p = (__force const char __user *)buf; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; - ret = __vfs_write(file, p, count, pos); + if (file->f_op->write) + ret = file->f_op->write(file, p, count, pos); + else if (file->f_op->write_iter) + ret = new_sync_write(file, p, count, pos); + else + ret = -EINVAL; set_fs(old_fs); if (ret > 0) { fsnotify_modify(file); @@ -554,19 +548,23 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); - if (!ret) { - if (count > MAX_RW_COUNT) - count = MAX_RW_COUNT; - file_start_write(file); - ret = __vfs_write(file, buf, count, pos); - if (ret > 0) { - fsnotify_modify(file); - add_wchar(current, ret); - } - inc_syscw(current); - file_end_write(file); + if (ret) + return ret; + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; + file_start_write(file); + if (file->f_op->write) + ret = file->f_op->write(file, buf, count, pos); + else if (file->f_op->write_iter) + ret = new_sync_write(file, buf, count, pos); + else + ret = -EINVAL; + if (ret > 0) { + fsnotify_modify(file); + add_wchar(current, ret); } - + inc_syscw(current); + file_end_write(file); return ret; } -- cgit From 61a707c543e2afe3aa7e88f87267c5dafa4b5afa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 8 May 2020 08:54:16 +0200 Subject: fs: add a __kernel_read helper This is the counterpart to __kernel_write, and skip the rw_verify_area call compared to kernel_read. Signed-off-by: Christoph Hellwig --- fs/read_write.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'fs/read_write.c') diff --git a/fs/read_write.c b/fs/read_write.c index 96e8e354f99b..21c9d90a257e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -430,6 +430,29 @@ ssize_t __vfs_read(struct file *file, char __user *buf, size_t count, return -EINVAL; } +ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) +{ + mm_segment_t old_fs = get_fs(); + ssize_t ret; + + if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) + return -EINVAL; + if (!(file->f_mode & FMODE_CAN_READ)) + return -EINVAL; + + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; + set_fs(KERNEL_DS); + ret = __vfs_read(file, (void __user *)buf, count, pos); + set_fs(old_fs); + if (ret > 0) { + fsnotify_access(file); + add_rchar(current, ret); + } + inc_syscr(current); + return ret; +} + ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { mm_segment_t old_fs; -- cgit From 6209dd9132e8ea5545cffc84483841e88ea8cc5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 8 May 2020 09:00:28 +0200 Subject: fs: implement kernel_read using __kernel_read Consolidate the two in-kernel read helpers to make upcoming changes easier. The only difference are the missing call to rw_verify_area in kernel_read, and an access_ok check that doesn't make sense for kernel buffers to start with. Signed-off-by: Christoph Hellwig --- fs/read_write.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'fs/read_write.c') diff --git a/fs/read_write.c b/fs/read_write.c index 21c9d90a257e..42a027719324 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -455,15 +455,12 @@ ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { - mm_segment_t old_fs; - ssize_t result; + ssize_t ret; - old_fs = get_fs(); - set_fs(KERNEL_DS); - /* The cast to a user pointer is valid due to the set_fs() */ - result = vfs_read(file, (void __user *)buf, count, pos); - set_fs(old_fs); - return result; + ret = rw_verify_area(READ, file, pos, count); + if (ret) + return ret; + return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); -- cgit From 775802c0571fb438cd4f6548a323f9e4cb89f5aa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 8 May 2020 11:17:46 +0200 Subject: fs: remove __vfs_read Fold it into the two callers. Signed-off-by: Christoph Hellwig --- fs/read_write.c | 43 +++++++++++++++++++++---------------------- 1 file changed, 21 insertions(+), 22 deletions(-) (limited to 'fs/read_write.c') diff --git a/fs/read_write.c b/fs/read_write.c index 42a027719324..4fb797822567 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -419,17 +419,6 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo return ret; } -ssize_t __vfs_read(struct file *file, char __user *buf, size_t count, - loff_t *pos) -{ - if (file->f_op->read) - return file->f_op->read(file, buf, count, pos); - else if (file->f_op->read_iter) - return new_sync_read(file, buf, count, pos); - else - return -EINVAL; -} - ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { mm_segment_t old_fs = get_fs(); @@ -443,7 +432,12 @@ ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; set_fs(KERNEL_DS); - ret = __vfs_read(file, (void __user *)buf, count, pos); + if (file->f_op->read) + ret = file->f_op->read(file, (void __user *)buf, count, pos); + else if (file->f_op->read_iter) + ret = new_sync_read(file, (void __user *)buf, count, pos); + else + ret = -EINVAL; set_fs(old_fs); if (ret > 0) { fsnotify_access(file); @@ -476,17 +470,22 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); - if (!ret) { - if (count > MAX_RW_COUNT) - count = MAX_RW_COUNT; - ret = __vfs_read(file, buf, count, pos); - if (ret > 0) { - fsnotify_access(file); - add_rchar(current, ret); - } - inc_syscr(current); - } + if (ret) + return ret; + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; + if (file->f_op->read) + ret = file->f_op->read(file, buf, count, pos); + else if (file->f_op->read_iter) + ret = new_sync_read(file, buf, count, pos); + else + ret = -EINVAL; + if (ret > 0) { + fsnotify_access(file); + add_rchar(current, ret); + } + inc_syscr(current); return ret; } -- cgit From bef173299613404f55b11180d9a865861637f31d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 6 Jun 2020 14:49:58 +0200 Subject: initrd: switch initrd loading to struct file based APIs There is no good reason to mess with file descriptors from in-kernel code, switch the initrd loading to struct file based read and writes instead. Also Pass an explicit offset instead of ->f_pos, and to make that easier, use file scope file structs and offsets everywhere except for identify_ramdisk_image instead of the current strange mix. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- fs/read_write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/read_write.c') diff --git a/fs/read_write.c b/fs/read_write.c index 4fb797822567..5db58b8c78d0 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -301,7 +301,7 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence) } EXPORT_SYMBOL(vfs_llseek); -off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) +static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; struct fd f = fdget_pos(fd); -- cgit