Re: [PATCH v5 3/6] uaccess: Add non-pagefault user-space read functions

[Yonghong Song]

On 2/28/19 8:03 AM, Masami Hiramatsu wrote:
> Add probe_user_read(), strncpy_from_unsafe_user() and
> strnlen_unsafe_user() which allows caller to access user-space
> in IRQ context.
> 
> Current probe_kernel_read() and strncpy_from_unsafe() are
> not available for user-space memory, because it sets
> KERNEL_DS while accessing data. On some arch, user address
> space and kernel address space can be co-exist, but others
> can not. In that case, setting KERNEL_DS means given

Just curious. Given the list of arch's currently linux supports,
do you know which arch's fall into "user address space and
kernel address space" can co-exist, and which arch's cannot?

Thanks!

Yonghong


> address is treated as a kernel address space.
> Also strnlen_user() is only available from user context since
> it can sleep if pagefault is enabled.
> 
> To access user-space memory without pagefault, we need
> these new functions which sets USER_DS while accessing
> the data.
> 
> Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
> ---
>    Changes in v5:
>     - Simplify probe_user_read() (Thanks, Peter!)
>     - Add strnlen_unsafe_user()
>    Changes in v3:
>     - Use user_access_ok() for probe_user_read().
>    Changes in v2:
>     - Simplify strncpy_from_unsafe_user() using strncpy_from_user()
>       according to Linus's suggestion.
>     - Simplify probe_user_read() not using intermediate function.
> ---
>   include/linux/uaccess.h |   14 +++++
>   mm/maccess.c            |  122 +++++++++++++++++++++++++++++++++++++++++++++--
>   2 files changed, 130 insertions(+), 6 deletions(-)
> 
> diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
> index 1afd9dfabe67..5be7f9adb418 100644
> --- a/include/linux/uaccess.h
> +++ b/include/linux/uaccess.h
> @@ -258,6 +258,17 @@ extern long probe_kernel_read(void *dst, const void *src, size_t size);
>   extern long __probe_kernel_read(void *dst, const void *src, size_t size);
>   
>   /*
> + * probe_user_read(): safely attempt to read from a location in user space
> + * @dst: pointer to the buffer that shall take the data
> + * @src: address to read from
> + * @size: size of the data chunk
> + *
> + * Safely read from address @src to the buffer at @dst.  If a kernel fault
> + * happens, handle that and return -EFAULT.
> + */
> +extern long probe_user_read(void *dst, const void __user *src, size_t size);
> +
> +/*
>    * probe_kernel_write(): safely attempt to write to a location
>    * @dst: address to write to
>    * @src: pointer to the data that shall be written
> @@ -270,6 +281,9 @@ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
>   extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
>   
>   extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
> +extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
> +				     long count);
> +extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
>   
>   /**
>    * probe_kernel_address(): safely attempt to read from a location
> diff --git a/mm/maccess.c b/mm/maccess.c
> index ec00be51a24f..d1b2ec78d9ef 100644
> --- a/mm/maccess.c
> +++ b/mm/maccess.c
> @@ -5,8 +5,20 @@
>   #include <linux/mm.h>
>   #include <linux/uaccess.h>
>   
> +static __always_inline long
> +probe_read_common(void *dst, const void __user *src, size_t size)
> +{
> +	long ret;
> +
> +	pagefault_disable();
> +	ret = __copy_from_user_inatomic(dst, src, size);
> +	pagefault_enable();
> +
> +	return ret ? -EFAULT : 0;
> +}
> +
>   /**
> - * probe_kernel_read(): safely attempt to read from a location
> + * probe_kernel_read(): safely attempt to read from a kernel-space location
>    * @dst: pointer to the buffer that shall take the data
>    * @src: address to read from
>    * @size: size of the data chunk
> @@ -29,17 +41,45 @@ long __probe_kernel_read(void *dst, const void *src, size_t size)
>   	mm_segment_t old_fs = get_fs();
>   
>   	set_fs(KERNEL_DS);
> -	pagefault_disable();
> -	ret = __copy_from_user_inatomic(dst,
> -			(__force const void __user *)src, size);
> -	pagefault_enable();
> +	ret = probe_read_common(dst, (__force const void __user *)src, size);
>   	set_fs(old_fs);
>   
> -	return ret ? -EFAULT : 0;
> +	return ret;
>   }
>   EXPORT_SYMBOL_GPL(probe_kernel_read);
>   
>   /**
> + * probe_user_read(): safely attempt to read from a user-space location
> + * @dst: pointer to the buffer that shall take the data
> + * @src: address to read from. This must be a user address.
> + * @size: size of the data chunk
> + *
> + * Safely read from user address @src to the buffer at @dst. If a kernel fault
> + * happens, handle that and return -EFAULT.
> + */
> +
> +long __weak probe_user_read(void *dst, const void __user *src, size_t size)
> +    __attribute__((alias("__probe_user_read")));
> +
> +long __probe_user_read(void *dst, const void __user *src, size_t size)
> +{
> +	long ret = -EFAULT;
> +	mm_segment_t old_fs = get_fs();
> +
> +	/*
> +	 * Since this can be called in IRQ context, we carefully set the
> +	 * USER_DS and use user_access_ok() which checks segment setting
> +	 * instead of task context.
> +	 */
> +	set_fs(USER_DS);
> +	if (user_access_ok(src, size))
> +		ret = probe_read_common(dst, src, size);
> +	set_fs(old_fs);
> +	return ret;
> +}
> +EXPORT_SYMBOL_GPL(probe_user_read);
> +
> +/**
>    * probe_kernel_write(): safely attempt to write to a location
>    * @dst: address to write to
>    * @src: pointer to the data that shall be written
> @@ -66,6 +106,7 @@ long __probe_kernel_write(void *dst, const void *src, size_t size)
>   }
>   EXPORT_SYMBOL_GPL(probe_kernel_write);
>   
> +
>   /**
>    * strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address.
>    * @dst:   Destination address, in kernel space.  This buffer must be at
> @@ -105,3 +146,72 @@ long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
>   
>   	return ret ? -EFAULT : src - unsafe_addr;
>   }
> +
> +/**
> + * strncpy_from_unsafe_user: - Copy a NUL terminated string from unsafe user
> + *				address.
> + * @dst:   Destination address, in kernel space.  This buffer must be at
> + *         least @count bytes long.
> + * @unsafe_addr: Unsafe user address.
> + * @count: Maximum number of bytes to copy, including the trailing NUL.
> + *
> + * Copies a NUL-terminated string from unsafe user address to kernel buffer.
> + *
> + * On success, returns the length of the string INCLUDING the trailing NUL.
> + *
> + * If access fails, returns -EFAULT (some data may have been copied
> + * and the trailing NUL added).
> + *
> + * If @count is smaller than the length of the string, copies @count-1 bytes,
> + * sets the last byte of @dst buffer to NUL and returns @count.
> + */
> +long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
> +			      long count)
> +{
> +	mm_segment_t old_fs = get_fs();
> +	long ret;
> +
> +	if (unlikely(count <= 0))
> +		return 0;
> +
> +	set_fs(USER_DS);
> +	pagefault_disable();
> +	ret = strncpy_from_user(dst, unsafe_addr, count);
> +	pagefault_enable();
> +	set_fs(old_fs);
> +	if (ret >= count) {
> +		ret = count;
> +		dst[ret - 1] = '\0';
> +	} else if (ret > 0)
> +		ret++;
> +	return ret;
> +}
> +
> +/**
> + * strnlen_unsafe_user: - Get the size of a user string INCLUDING final NUL.
> + * @unsafe_addr: The string to measure.
> + * @count: Maximum count (including NUL character)
> + *
> + * Get the size of a NUL-terminated string in user space without pagefault.
> + *
> + * Returns the size of the string INCLUDING the terminating NUL.
> + *
> + * If the string is too long, returns a number larger than @count. User
> + * has to check the return value against "> count".
> + * On exception (or invalid count), returns 0.
> + *
> + * Unlike strnlen_user, this can be used from IRQ handler etc. because
> + * it disables pagefaults.
> + */
> +long strnlen_unsafe_user(const void __user *unsafe_addr, long count)
> +{
> +	mm_segment_t old_fs = get_fs();
> +	int ret;
> +
> +	set_fs(USER_DS);
> +	pagefault_disable();
> +	ret = strnlen_user(unsafe_addr, count);
> +	pagefault_enable();
> +	set_fs(old_fs);
> +	return ret;
> +}
>