On Tue, Jan 28, 2025 at 12:15:30AM +0100, Stefano Brivio wrote:
> These are symmetric to write_remainder() and write_all_buf() and
> almost a copy and paste of them, with the most notable differences
> being reversed reads/writes and a couple of better-safe-than-sorry
> asserts to keep Coverity happy.

So, there's one thing that needs to be not quite symmetric for the
read() version: we need to handle EOF.  At present, I believe these
will enter an infinite loop on EOF, which is not a graceful failure
mode.

> I'll use them in the next patch. At least for the moment, they're
> going to be used for vhost-user mode only, so I'm not unconditionally
> enabling readv() in the seccomp profile: the caller has to ensure it's
> there.
> 
> Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
> ---
>  util.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  util.h |  2 ++
>  2 files changed, 72 insertions(+)
> 
> diff --git a/util.c b/util.c
> index 11973c4..085937b 100644
> --- a/util.c
> +++ b/util.c
> @@ -606,6 +606,76 @@ int write_remainder(int fd, const struct iovec *iov, size_t iovcnt, size_t skip)
>  	return 0;
>  }
>  
> +/**
> + * read_all_buf() - Fill a whole buffer from a file descriptor
> + * @fd:		File descriptor
> + * @buf:	Pointer to base of buffer
> + * @len:	Length of buffer
> + *
> + * Return: 0 on success, -1 on error (with errno set)
> + *
> + * #syscalls read
> + */
> +int read_all_buf(int fd, void *buf, size_t len)
> +{
> +	size_t left = len;
> +	char *p = buf;
> +
> +	while (left) {
> +		ssize_t rc;
> +
> +		ASSERT(left <= len);
> +
> +		do
> +			rc = read(fd, p, left);
> +		while ((rc < 0) && errno == EINTR);
> +
> +		if (rc < 0)
> +			return -1;
> +
> +		p += rc;
> +		left -= rc;
> +	}
> +	return 0;
> +}
> +
> +/**
> + * read_remainder() - Read the tail of an IO vector from a file descriptor
> + * @fd:		File descriptor
> + * @iov:	IO vector
> + * @cnt:	Number of entries in @iov
> + * @skip:	Number of bytes of the vector to skip reading
> + *
> + * Return: 0 on success, -1 on error (with errno set)
> + *
> + * Note: mode-specific seccomp profiles need to enable readv() to use this.
> + */
> +int read_remainder(int fd, struct iovec *iov, size_t cnt, size_t skip)
> +{
> +	size_t i = 0, offset;
> +
> +	while ((i += iov_skip_bytes(iov + i, cnt - i, skip, &offset)) < cnt) {
> +		ssize_t rc;
> +
> +		if (offset) {
> +			ASSERT(offset < iov[i].iov_len);
> +			/* Read the remainder of the partially read buffer */
> +			if (read_all_buf(fd, (char *)iov[i].iov_base + offset,
> +					 iov[i].iov_len - offset) < 0)
> +				return -1;
> +			i++;
> +		}
> +
> +		/* Fill as many of the remaining buffers as we can */
> +		rc = readv(fd, &iov[i], cnt - i);
> +		if (rc < 0)
> +			return -1;
> +
> +		skip = rc;
> +	}
> +	return 0;
> +}
> +
>  /** sockaddr_ntop() - Convert a socket address to text format
>   * @sa:		Socket address
>   * @dst:	output buffer, minimum SOCKADDR_STRLEN bytes
> diff --git a/util.h b/util.h
> index d02333d..73a7a33 100644
> --- a/util.h
> +++ b/util.h
> @@ -203,6 +203,8 @@ int fls(unsigned long x);
>  int write_file(const char *path, const char *buf);
>  int write_all_buf(int fd, const void *buf, size_t len);
>  int write_remainder(int fd, const struct iovec *iov, size_t iovcnt, size_t skip);
> +int read_all_buf(int fd, void *buf, size_t len);
> +int read_remainder(int fd, struct iovec *iov, size_t cnt, size_t skip);
>  void close_open_files(int argc, char **argv);
>  bool snprintf_check(char *str, size_t size, const char *format, ...);
>  

-- 
David Gibson (he or they)	| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you, not the other way
				| around.
http://www.ozlabs.org/~dgibson