* [PATCH 2/9 next] fs: Move rw_copy_check_uvector() into lib/iov_iter.c and make static.
@ 2020-09-15 14:55 David Laight
2020-09-21 14:10 ` Christoph Hellwig
0 siblings, 1 reply; 2+ messages in thread
From: David Laight @ 2020-09-15 14:55 UTC (permalink / raw)
To: [email protected], [email protected],
[email protected], Jens Axboe, David S. Miller, Al Viro,
linux-fsdevel
This lets the compiler inline it into import_iovec() generating
much better code.
Signed-off-by: David Laight <[email protected]>
---
fs/read_write.c | 179 -----------------------------------------
include/linux/compat.h | 6 --
include/linux/fs.h | 5 --
lib/iov_iter.c | 178 ++++++++++++++++++++++++++++++++++++++++
4 files changed, 178 insertions(+), 190 deletions(-)
diff --git a/fs/read_write.c b/fs/read_write.c
index 5db58b8c78d0..e5e891a88442 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -752,185 +752,6 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
return ret;
}
-/**
- * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
- * into the kernel and check that it is valid.
- *
- * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
- * @uvector: Pointer to the userspace array.
- * @nr_segs: Number of elements in userspace array.
- * @fast_segs: Number of elements in @fast_pointer.
- * @fast_pointer: Pointer to (usually small on-stack) kernel array.
- * @ret_pointer: (output parameter) Pointer to a variable that will point to
- * either @fast_pointer, a newly allocated kernel array, or NULL,
- * depending on which array was used.
- *
- * This function copies an array of &struct iovec of @nr_segs from
- * userspace into the kernel and checks that each element is valid (e.g.
- * it does not point to a kernel address or cause overflow by being too
- * large, etc.).
- *
- * As an optimization, the caller may provide a pointer to a small
- * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
- * (the size of this array, or 0 if unused, should be given in @fast_segs).
- *
- * @ret_pointer will always point to the array that was used, so the
- * caller must take care not to call kfree() on it e.g. in case the
- * @fast_pointer array was used and it was allocated on the stack.
- *
- * Return: The total number of bytes covered by the iovec array on success
- * or a negative error code on error.
- */
-ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
- unsigned long nr_segs, unsigned long fast_segs,
- struct iovec *fast_pointer,
- struct iovec **ret_pointer)
-{
- unsigned long seg;
- ssize_t ret;
- struct iovec *iov = fast_pointer;
-
- /*
- * SuS says "The readv() function *may* fail if the iovcnt argument
- * was less than or equal to 0, or greater than {IOV_MAX}. Linux has
- * traditionally returned zero for zero segments, so...
- */
- if (nr_segs == 0) {
- ret = 0;
- goto out;
- }
-
- /*
- * First get the "struct iovec" from user memory and
- * verify all the pointers
- */
- if (nr_segs > UIO_MAXIOV) {
- ret = -EINVAL;
- goto out;
- }
- if (nr_segs > fast_segs) {
- iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
- if (iov == NULL) {
- ret = -ENOMEM;
- goto out;
- }
- }
- if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
- ret = -EFAULT;
- goto out;
- }
-
- /*
- * According to the Single Unix Specification we should return EINVAL
- * if an element length is < 0 when cast to ssize_t or if the
- * total length would overflow the ssize_t return value of the
- * system call.
- *
- * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
- * overflow case.
- */
- ret = 0;
- for (seg = 0; seg < nr_segs; seg++) {
- void __user *buf = iov[seg].iov_base;
- ssize_t len = (ssize_t)iov[seg].iov_len;
-
- /* see if we we're about to use an invalid len or if
- * it's about to overflow ssize_t */
- if (len < 0) {
- ret = -EINVAL;
- goto out;
- }
- if (type >= 0
- && unlikely(!access_ok(buf, len))) {
- ret = -EFAULT;
- goto out;
- }
- if (len > MAX_RW_COUNT - ret) {
- len = MAX_RW_COUNT - ret;
- iov[seg].iov_len = len;
- }
- ret += len;
- }
-out:
- *ret_pointer = iov;
- return ret;
-}
-
-#ifdef CONFIG_COMPAT
-ssize_t compat_rw_copy_check_uvector(int type,
- const struct compat_iovec __user *uvector, unsigned long nr_segs,
- unsigned long fast_segs, struct iovec *fast_pointer,
- struct iovec **ret_pointer)
-{
- compat_ssize_t tot_len;
- struct iovec *iov = *ret_pointer = fast_pointer;
- ssize_t ret = 0;
- int seg;
-
- /*
- * SuS says "The readv() function *may* fail if the iovcnt argument
- * was less than or equal to 0, or greater than {IOV_MAX}. Linux has
- * traditionally returned zero for zero segments, so...
- */
- if (nr_segs == 0)
- goto out;
-
- ret = -EINVAL;
- if (nr_segs > UIO_MAXIOV)
- goto out;
- if (nr_segs > fast_segs) {
- ret = -ENOMEM;
- iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
- if (iov == NULL)
- goto out;
- }
- *ret_pointer = iov;
-
- ret = -EFAULT;
- if (!access_ok(uvector, nr_segs*sizeof(*uvector)))
- goto out;
-
- /*
- * Single unix specification:
- * We should -EINVAL if an element length is not >= 0 and fitting an
- * ssize_t.
- *
- * In Linux, the total length is limited to MAX_RW_COUNT, there is
- * no overflow possibility.
- */
- tot_len = 0;
- ret = -EINVAL;
- for (seg = 0; seg < nr_segs; seg++) {
- compat_uptr_t buf;
- compat_ssize_t len;
-
- if (__get_user(len, &uvector->iov_len) ||
- __get_user(buf, &uvector->iov_base)) {
- ret = -EFAULT;
- goto out;
- }
- if (len < 0) /* size_t not fitting in compat_ssize_t .. */
- goto out;
- if (type >= 0 &&
- !access_ok(compat_ptr(buf), len)) {
- ret = -EFAULT;
- goto out;
- }
- if (len > MAX_RW_COUNT - tot_len)
- len = MAX_RW_COUNT - tot_len;
- tot_len += len;
- iov->iov_base = compat_ptr(buf);
- iov->iov_len = (compat_size_t) len;
- uvector++;
- iov++;
- }
- ret = tot_len;
-
-out:
- return ret;
-}
-#endif
-
static ssize_t do_iter_read(struct file *file, struct iov_iter *iter,
loff_t *pos, rwf_t flags)
{
diff --git a/include/linux/compat.h b/include/linux/compat.h
index b354ce58966e..64bf699e8735 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -451,12 +451,6 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
struct epoll_event; /* fortunately, this one is fixed-layout */
-extern ssize_t compat_rw_copy_check_uvector(int type,
- const struct compat_iovec __user *uvector,
- unsigned long nr_segs,
- unsigned long fast_segs, struct iovec *fast_pointer,
- struct iovec **ret_pointer);
-
extern void __user *compat_alloc_user_space(unsigned long len);
int compat_restore_altstack(const compat_stack_t __user *uss);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..9571114f5036 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1887,11 +1887,6 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
return file->f_op->mmap(file, vma);
}
-ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
- unsigned long nr_segs, unsigned long fast_segs,
- struct iovec *fast_pointer,
- struct iovec **ret_pointer);
-
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 *,
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 5e40786c8f12..59b71dc24e02 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1650,6 +1650,111 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
}
EXPORT_SYMBOL(dup_iter);
+
+/**
+ * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
+ * into the kernel and check that it is valid.
+ *
+ * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
+ * @uvector: Pointer to the userspace array.
+ * @nr_segs: Number of elements in userspace array.
+ * @fast_segs: Number of elements in @fast_pointer.
+ * @fast_pointer: Pointer to (usually small on-stack) kernel array.
+ * @ret_pointer: (output parameter) Pointer to a variable that will point to
+ * either @fast_pointer, a newly allocated kernel array, or NULL,
+ * depending on which array was used.
+ *
+ * This function copies an array of &struct iovec of @nr_segs from
+ * userspace into the kernel and checks that each element is valid (e.g.
+ * it does not point to a kernel address or cause overflow by being too
+ * large, etc.).
+ *
+ * As an optimization, the caller may provide a pointer to a small
+ * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
+ * (the size of this array, or 0 if unused, should be given in @fast_segs).
+ *
+ * @ret_pointer will always point to the array that was used, so the
+ * caller must take care not to call kfree() on it e.g. in case the
+ * @fast_pointer array was used and it was allocated on the stack.
+ *
+ * Return: The total number of bytes covered by the iovec array on success
+ * or a negative error code on error.
+ */
+static ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
+ unsigned long nr_segs, unsigned long fast_segs,
+ struct iovec *fast_pointer,
+ struct iovec **ret_pointer)
+{
+ unsigned long seg;
+ ssize_t ret;
+ struct iovec *iov = fast_pointer;
+
+ /*
+ * SuS says "The readv() function *may* fail if the iovcnt argument
+ * was less than or equal to 0, or greater than {IOV_MAX}. Linux has
+ * traditionally returned zero for zero segments, so...
+ */
+ if (nr_segs == 0) {
+ ret = 0;
+ goto out;
+ }
+
+ /*
+ * First get the "struct iovec" from user memory and
+ * verify all the pointers
+ */
+ if (nr_segs > UIO_MAXIOV) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (nr_segs > fast_segs) {
+ iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
+ if (iov == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+ if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ /*
+ * According to the Single Unix Specification we should return EINVAL
+ * if an element length is < 0 when cast to ssize_t or if the
+ * total length would overflow the ssize_t return value of the
+ * system call.
+ *
+ * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
+ * overflow case.
+ */
+ ret = 0;
+ for (seg = 0; seg < nr_segs; seg++) {
+ void __user *buf = iov[seg].iov_base;
+ ssize_t len = (ssize_t)iov[seg].iov_len;
+
+ /* see if we we're about to use an invalid len or if
+ * it's about to overflow ssize_t */
+ if (len < 0) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (type >= 0
+ && unlikely(!access_ok(buf, len))) {
+ ret = -EFAULT;
+ goto out;
+ }
+ if (len > MAX_RW_COUNT - ret) {
+ len = MAX_RW_COUNT - ret;
+ iov[seg].iov_len = len;
+ }
+ ret += len;
+ }
+out:
+ *ret_pointer = iov;
+ return ret;
+}
+
/**
* import_iovec() - Copy an array of &struct iovec from userspace
* into the kernel, check that it is valid, and initialize a new
@@ -1695,6 +1800,79 @@ EXPORT_SYMBOL(import_iovec);
#ifdef CONFIG_COMPAT
#include <linux/compat.h>
+static ssize_t compat_rw_copy_check_uvector(int type,
+ const struct compat_iovec __user *uvector, unsigned long nr_segs,
+ unsigned long fast_segs, struct iovec *fast_pointer,
+ struct iovec **ret_pointer)
+{
+ compat_ssize_t tot_len;
+ struct iovec *iov = *ret_pointer = fast_pointer;
+ ssize_t ret = 0;
+ int seg;
+
+ /*
+ * SuS says "The readv() function *may* fail if the iovcnt argument
+ * was less than or equal to 0, or greater than {IOV_MAX}. Linux has
+ * traditionally returned zero for zero segments, so...
+ */
+ if (nr_segs == 0)
+ goto out;
+
+ ret = -EINVAL;
+ if (nr_segs > UIO_MAXIOV)
+ goto out;
+ if (nr_segs > fast_segs) {
+ ret = -ENOMEM;
+ iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
+ if (iov == NULL)
+ goto out;
+ }
+ *ret_pointer = iov;
+
+ ret = -EFAULT;
+ if (!access_ok(uvector, nr_segs*sizeof(*uvector)))
+ goto out;
+
+ /*
+ * Single unix specification:
+ * We should -EINVAL if an element length is not >= 0 and fitting an
+ * ssize_t.
+ *
+ * In Linux, the total length is limited to MAX_RW_COUNT, there is
+ * no overflow possibility.
+ */
+ tot_len = 0;
+ ret = -EINVAL;
+ for (seg = 0; seg < nr_segs; seg++) {
+ compat_uptr_t buf;
+ compat_ssize_t len;
+
+ if (__get_user(len, &uvector->iov_len) ||
+ __get_user(buf, &uvector->iov_base)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ if (len < 0) /* size_t not fitting in compat_ssize_t .. */
+ goto out;
+ if (type >= 0 &&
+ !access_ok(compat_ptr(buf), len)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ if (len > MAX_RW_COUNT - tot_len)
+ len = MAX_RW_COUNT - tot_len;
+ tot_len += len;
+ iov->iov_base = compat_ptr(buf);
+ iov->iov_len = (compat_size_t) len;
+ uvector++;
+ iov++;
+ }
+ ret = tot_len;
+
+out:
+ return ret;
+}
+
ssize_t compat_import_iovec(int type,
const struct compat_iovec __user * uvector,
unsigned nr_segs, unsigned fast_segs,
--
2.25.1
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH 2/9 next] fs: Move rw_copy_check_uvector() into lib/iov_iter.c and make static.
2020-09-15 14:55 [PATCH 2/9 next] fs: Move rw_copy_check_uvector() into lib/iov_iter.c and make static David Laight
@ 2020-09-21 14:10 ` Christoph Hellwig
0 siblings, 0 replies; 2+ messages in thread
From: Christoph Hellwig @ 2020-09-21 14:10 UTC (permalink / raw)
To: David Laight
Cc: [email protected], [email protected],
[email protected], Jens Axboe, David S. Miller, Al Viro,
linux-fsdevel
On Tue, Sep 15, 2020 at 02:55:13PM +0000, David Laight wrote:
>
> This lets the compiler inline it into import_iovec() generating
> much better code.
The changelog is a bit short, but otherwise this looks good:
Reviewed-by: Christoph Hellwig <[email protected]>
I picked this up as a prep patch for the compat iovec handling.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2020-09-21 14:10 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2020-09-15 14:55 [PATCH 2/9 next] fs: Move rw_copy_check_uvector() into lib/iov_iter.c and make static David Laight
2020-09-21 14:10 ` Christoph Hellwig
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox