[PATCH net-next v13 11/13] net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags

[Pavel Begunkov]

On 6/25/24 03:47, Mina Almasry wrote:
> Add an interface for the user to notify the kernel that it is done
> reading the devmem dmabuf frags returned as cmsg. The kernel will
> drop the reference on the frags to make them available for reuse.

The sock_devmem_dontneed loop is a bit crude, but that can
be handled by follow up patches.

Reviewed-by: Pavel Begunkov <asml.silence at gmail.com>

> diff --git a/net/core/sock.c b/net/core/sock.c
> index 9abc4fe259535..040c66ac26244 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
...
>   
> +#ifdef CONFIG_PAGE_POOL
> +static noinline_for_stack int
> +sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
> +{
> +	unsigned int num_tokens, i, j, k, netmem_num = 0;
> +	struct dmabuf_token *tokens;
> +	netmem_ref netmems[16];
> +	int ret = 0;
> +
> +	if (sk->sk_type != SOCK_STREAM || sk->sk_protocol != IPPROTO_TCP)
> +		return -EBADF;
> +
> +	if (optlen % sizeof(struct dmabuf_token) ||
> +	    optlen > sizeof(*tokens) * 128)
> +		return -EINVAL;
> +
> +	tokens = kvmalloc_array(128, sizeof(*tokens), GFP_KERNEL);
> +	if (!tokens)
> +		return -ENOMEM;
> +
> +	num_tokens = optlen / sizeof(struct dmabuf_token);
> +	if (copy_from_sockptr(tokens, optval, optlen)) {
> +		kvfree(tokens);
> +		return -EFAULT;
> +	}
> +
> +	xa_lock_bh(&sk->sk_user_frags);
> +	for (i = 0; i < num_tokens; i++) {
> +		for (j = 0; j < tokens[i].token_count; j++) {
> +			netmem_ref netmem = (__force netmem_ref)__xa_erase(
> +				&sk->sk_user_frags, tokens[i].token_start + j);
> +
> +			if (netmem &&
> +			    !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
> +				netmems[netmem_num++] = netmem;
> +				if (netmem_num == ARRAY_SIZE(netmems)) {
> +					xa_unlock_bh(&sk->sk_user_frags);
> +					for (k = 0; k < netmem_num; k++)
> +						WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
> +					netmem_num = 0;
> +					xa_lock_bh(&sk->sk_user_frags);
> +				}
> +				ret++;
> +			}
> +		}
> +	}
> +
> +	xa_unlock_bh(&sk->sk_user_frags);
> +	for (k = 0; k < netmem_num; k++)
> +		WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
> +
> +	kvfree(tokens);
> +	return ret;
> +}
> +#endif

-- 
Pavel Begunkov