Linux-Fsdevel Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Linus Torvalds <torvalds@linux-foundation.org>,
Al Viro <viro@zeniv.linux.org.uk>,
Michael Ellerman <mpe@ellerman.id.au>,
x86@kernel.org
Cc: Alexey Dobriyan <adobriyan@gmail.com>,
Luis Chamberlain <mcgrof@kernel.org>,
Kees Cook <keescook@chromium.org>,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Subject: [PATCH 06/14] fs: don't allow splice read/write without explicit ops
Date: Thu, 3 Sep 2020 16:22:34 +0200 [thread overview]
Message-ID: <20200903142242.925828-7-hch@lst.de> (raw)
In-Reply-To: <20200903142242.925828-1-hch@lst.de>
default_file_splice_write is the last piece of generic code that uses
set_fs to make the uaccess routines operate on kernel pointers. It
implements a "fallback loop" for splicing from files that do not actually
provide a proper splice_read method. The usual file systems and other
high bandwidth instances all provide a ->splice_read, so this just removes
support for various device drivers and procfs/debugfs files. If splice
support for any of those turns out to be important it can be added back
by switching them to the iter ops and using generic_file_splice_read.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
fs/read_write.c | 2 +-
fs/splice.c | 130 +++++----------------------------------------
include/linux/fs.h | 2 -
3 files changed, 15 insertions(+), 119 deletions(-)
diff --git a/fs/read_write.c b/fs/read_write.c
index 702c4301d9eb6b..8c61f67453e3d3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1077,7 +1077,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
}
EXPORT_SYMBOL(vfs_iter_write);
-ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
+static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
diff --git a/fs/splice.c b/fs/splice.c
index d7c8a7c4db07ff..412df7b48f9eb7 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -342,89 +342,6 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = {
};
EXPORT_SYMBOL(nosteal_pipe_buf_ops);
-static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
- unsigned long vlen, loff_t offset)
-{
- mm_segment_t old_fs;
- loff_t pos = offset;
- ssize_t res;
-
- old_fs = get_fs();
- set_fs(KERNEL_DS);
- /* The cast to a user pointer is valid due to the set_fs() */
- res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
- set_fs(old_fs);
-
- return res;
-}
-
-static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t len,
- unsigned int flags)
-{
- struct kvec *vec, __vec[PIPE_DEF_BUFFERS];
- struct iov_iter to;
- struct page **pages;
- unsigned int nr_pages;
- unsigned int mask;
- size_t offset, base, copied = 0;
- ssize_t res;
- int i;
-
- if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
- return -EAGAIN;
-
- /*
- * Try to keep page boundaries matching to source pagecache ones -
- * it probably won't be much help, but...
- */
- offset = *ppos & ~PAGE_MASK;
-
- iov_iter_pipe(&to, READ, pipe, len + offset);
-
- res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
- if (res <= 0)
- return -ENOMEM;
-
- nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
-
- vec = __vec;
- if (nr_pages > PIPE_DEF_BUFFERS) {
- vec = kmalloc_array(nr_pages, sizeof(struct kvec), GFP_KERNEL);
- if (unlikely(!vec)) {
- res = -ENOMEM;
- goto out;
- }
- }
-
- mask = pipe->ring_size - 1;
- pipe->bufs[to.head & mask].offset = offset;
- pipe->bufs[to.head & mask].len -= offset;
-
- for (i = 0; i < nr_pages; i++) {
- size_t this_len = min_t(size_t, len, PAGE_SIZE - offset);
- vec[i].iov_base = page_address(pages[i]) + offset;
- vec[i].iov_len = this_len;
- len -= this_len;
- offset = 0;
- }
-
- res = kernel_readv(in, vec, nr_pages, *ppos);
- if (res > 0) {
- copied = res;
- *ppos += res;
- }
-
- if (vec != __vec)
- kfree(vec);
-out:
- for (i = 0; i < nr_pages; i++)
- put_page(pages[i]);
- kvfree(pages);
- iov_iter_advance(&to, copied); /* truncates and discards */
- return res;
-}
-
/*
* Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
* using sendpage(). Return the number of bytes sent.
@@ -788,33 +705,6 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
EXPORT_SYMBOL(iter_file_splice_write);
-static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
- struct splice_desc *sd)
-{
- int ret;
- void *data;
- loff_t tmp = sd->pos;
-
- data = kmap(buf->page);
- ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
- kunmap(buf->page);
-
- return ret;
-}
-
-static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
- struct file *out, loff_t *ppos,
- size_t len, unsigned int flags)
-{
- ssize_t ret;
-
- ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
- if (ret > 0)
- *ppos += ret;
-
- return ret;
-}
-
/**
* generic_splice_sendpage - splice data from a pipe to a socket
* @pipe: pipe to splice from
@@ -836,15 +726,23 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
EXPORT_SYMBOL(generic_splice_sendpage);
+static int warn_unsupported(struct file *file, const char *op)
+{
+ pr_debug_ratelimited(
+ "splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+ op, file, current->pid, current->comm);
+ return -EINVAL;
+}
+
/*
* Attempt to initiate a splice from pipe to file.
*/
static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
loff_t *ppos, size_t len, unsigned int flags)
{
- if (out->f_op->splice_write)
- return out->f_op->splice_write(pipe, out, ppos, len, flags);
- return default_file_splice_write(pipe, out, ppos, len, flags);
+ if (unlikely(!out->f_op->splice_write))
+ return warn_unsupported(out, "write");
+ return out->f_op->splice_write(pipe, out, ppos, len, flags);
}
/*
@@ -866,9 +764,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
if (unlikely(len > MAX_RW_COUNT))
len = MAX_RW_COUNT;
- if (in->f_op->splice_read)
- return in->f_op->splice_read(in, ppos, pipe, len, flags);
- return default_file_splice_read(in, ppos, pipe, len, flags);
+ if (unlikely(!in->f_op->splice_read))
+ return warn_unsupported(in, "read");
+ return in->f_op->splice_read(in, ppos, pipe, len, flags);
}
/**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a082c..839eeccf10174b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1894,8 +1894,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
-extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
- unsigned long, loff_t *, rwf_t);
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
loff_t, size_t, unsigned int);
extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
--
2.28.0
next prev parent reply other threads:[~2020-09-03 14:26 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-03 14:22 remove the last set_fs() in common code, and remove it for x86 and powerpc v3 Christoph Hellwig
2020-09-03 14:22 ` [PATCH 01/14] proc: remove a level of indentation in proc_get_inode Christoph Hellwig
2020-09-03 14:22 ` [PATCH 02/14] proc: cleanup the compat vs no compat file ops Christoph Hellwig
2020-09-03 14:22 ` [PATCH 03/14] proc: add a read_iter method to proc proc_ops Christoph Hellwig
2020-09-03 14:22 ` [PATCH 04/14] sysctl: Convert to iter interfaces Christoph Hellwig
2020-09-03 14:22 ` [PATCH 05/14] fs: don't allow kernel reads and writes without iter ops Christoph Hellwig
2020-10-01 22:38 ` Eric Biggers
2020-10-01 22:40 ` Al Viro
2020-10-02 16:27 ` Linus Torvalds
2020-10-09 22:06 ` Eric Biggers
2020-10-10 1:03 ` Linus Torvalds
2020-10-10 1:19 ` Eric Biggers
2020-10-10 1:29 ` Linus Torvalds
2020-10-10 1:55 ` Alexander Viro
2020-10-14 5:51 ` Christoph Hellwig
2020-09-03 14:22 ` Christoph Hellwig [this message]
2020-09-03 14:22 ` [PATCH 07/14] uaccess: add infrastructure for kernel builds with set_fs() Christoph Hellwig
2020-09-03 14:22 ` [PATCH 08/14] test_bitmap: remove user bitmap tests Christoph Hellwig
2020-09-03 14:22 ` [PATCH 09/14] lkdtm: remove set_fs-based tests Christoph Hellwig
2020-09-03 14:22 ` [PATCH 10/14] x86: move PAGE_OFFSET, TASK_SIZE & friends to page_{32,64}_types.h Christoph Hellwig
2020-09-03 14:22 ` [PATCH 11/14] x86: make TASK_SIZE_MAX usable from assembly code Christoph Hellwig
2020-09-03 14:22 ` [PATCH 12/14] x86: remove address space overrides using set_fs() Christoph Hellwig
2020-09-03 21:30 ` David Laight
2020-09-03 23:25 ` Linus Torvalds
2020-09-04 7:59 ` David Laight
2020-09-04 2:55 ` Al Viro
2020-09-04 4:41 ` Al Viro
2020-09-04 6:38 ` Christoph Hellwig
2020-09-04 7:47 ` Christoph Hellwig
2020-09-03 14:22 ` [PATCH 13/14] powerpc: use non-set_fs based maccess routines Christoph Hellwig
2020-09-03 14:22 ` [PATCH 14/14] powerpc: remove address space overrides using set_fs() Christoph Hellwig
2020-09-03 15:43 ` Christophe Leroy
2020-09-03 15:49 ` Christoph Hellwig
2020-09-03 15:56 ` Christoph Hellwig
2020-09-03 16:03 ` Christophe Leroy
2020-09-03 14:28 ` remove the last set_fs() in common code, and remove it for x86 and powerpc v3 Al Viro
2020-09-03 14:30 ` Christoph Hellwig
2020-09-03 14:36 ` Al Viro
2020-09-03 14:40 ` Christoph Hellwig
2020-09-09 17:31 ` Linus Torvalds
2020-09-09 18:40 ` Segher Boessenkool
2020-09-09 21:33 ` Linus Torvalds
2020-09-10 8:04 ` David Laight
2020-09-10 8:13 ` Christophe Leroy
2020-09-10 9:26 ` David Laight
2020-09-10 12:26 ` David Laight
2020-09-10 15:20 ` Segher Boessenkool
2020-09-10 15:31 ` David Laight
2020-09-10 17:15 ` Segher Boessenkool
2020-09-10 15:16 ` Segher Boessenkool
2020-09-10 15:44 ` Segher Boessenkool
2020-09-03 15:49 ` Linus Torvalds
2020-09-04 6:00 ` Ingo Molnar
2020-09-04 17:58 ` Alexey Dobriyan
2020-09-04 18:42 ` Linus Torvalds
2020-09-04 21:01 ` David Laight
2020-09-05 7:16 ` Christophe Leroy
2020-09-05 10:13 ` David Laight
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200903142242.925828-7-hch@lst.de \
--to=hch@lst.de \
--cc=adobriyan@gmail.com \
--cc=keescook@chromium.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mcgrof@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--cc=x86@kernel.org \
--subject='Re: [PATCH 06/14] fs: don'\''t allow splice read/write without explicit ops' \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).