Re: [PATCH bpf-next 03/15] xsk: add umem fill queue support and mmap

["Michael S. Tsirkin" <mst@redhat.com>]

On Mon, Apr 23, 2018 at 03:56:07PM +0200, Björn Töpel wrote:
> From: Magnus Karlsson <magnus.karlsson@intel.com>
> 
> Here, we add another setsockopt for registered user memory (umem)
> called XDP_UMEM_FILL_QUEUE. Using this socket option, the process can
> ask the kernel to allocate a queue (ring buffer) and also mmap it
> (XDP_UMEM_PGOFF_FILL_QUEUE) into the process.
> 
> The queue is used to explicitly pass ownership of umem frames from the
> user process to the kernel. These frames will in a later patch be
> filled in with Rx packet data by the kernel.
> 
> Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
> ---
>  include/uapi/linux/if_xdp.h | 15 +++++++++++
>  net/xdp/Makefile            |  2 +-
>  net/xdp/xdp_umem.c          |  5 ++++
>  net/xdp/xdp_umem.h          |  2 ++
>  net/xdp/xsk.c               | 62 ++++++++++++++++++++++++++++++++++++++++++++-
>  net/xdp/xsk_queue.c         | 58 ++++++++++++++++++++++++++++++++++++++++++
>  net/xdp/xsk_queue.h         | 38 +++++++++++++++++++++++++++
>  7 files changed, 180 insertions(+), 2 deletions(-)
>  create mode 100644 net/xdp/xsk_queue.c
>  create mode 100644 net/xdp/xsk_queue.h
> 
> diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
> index 41252135a0fe..975661e1baca 100644
> --- a/include/uapi/linux/if_xdp.h
> +++ b/include/uapi/linux/if_xdp.h
> @@ -23,6 +23,7 @@
>  
>  /* XDP socket options */
>  #define XDP_UMEM_REG			3
> +#define XDP_UMEM_FILL_RING		4
>  
>  struct xdp_umem_reg {
>  	__u64 addr; /* Start of packet data area */
> @@ -31,4 +32,18 @@ struct xdp_umem_reg {
>  	__u32 frame_headroom; /* Frame head room */
>  };
>  
> +/* Pgoff for mmaping the rings */
> +#define XDP_UMEM_PGOFF_FILL_RING	0x100000000
> +
> +struct xdp_ring {
> +	__u32 producer __attribute__((aligned(64)));
> +	__u32 consumer __attribute__((aligned(64)));
> +};

Why 64? And do you still need these guys in uapi?

> +
> +/* Used for the fill and completion queues for buffers */
> +struct xdp_umem_ring {
> +	struct xdp_ring ptrs;
> +	__u32 desc[0] __attribute__((aligned(64)));
> +};
> +
>  #endif /* _LINUX_IF_XDP_H */
> diff --git a/net/xdp/Makefile b/net/xdp/Makefile
> index a5d736640a0f..074fb2b2d51c 100644
> --- a/net/xdp/Makefile
> +++ b/net/xdp/Makefile
> @@ -1,2 +1,2 @@
> -obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o
> +obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o
>  
> diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
> index bff058f5a769..6fc233e03f30 100644
> --- a/net/xdp/xdp_umem.c
> +++ b/net/xdp/xdp_umem.c
> @@ -62,6 +62,11 @@ static void xdp_umem_release(struct xdp_umem *umem)
>  	struct mm_struct *mm;
>  	unsigned long diff;
>  
> +	if (umem->fq) {
> +		xskq_destroy(umem->fq);
> +		umem->fq = NULL;
> +	}
> +
>  	if (umem->pgs) {
>  		xdp_umem_unpin_pages(umem);
>  
> diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
> index 58714f4f7f25..3086091aebdd 100644
> --- a/net/xdp/xdp_umem.h
> +++ b/net/xdp/xdp_umem.h
> @@ -18,9 +18,11 @@
>  #include <linux/mm.h>
>  #include <linux/if_xdp.h>
>  
> +#include "xsk_queue.h"
>  #include "xdp_umem_props.h"
>  
>  struct xdp_umem {
> +	struct xsk_queue *fq;
>  	struct page **pgs;
>  	struct xdp_umem_props props;
>  	u32 npgs;
> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> index 19fc719cbe0d..bf6a1151df28 100644
> --- a/net/xdp/xsk.c
> +++ b/net/xdp/xsk.c
> @@ -32,6 +32,7 @@
>  #include <linux/netdevice.h>
>  #include <net/sock.h>
>  
> +#include "xsk_queue.h"
>  #include "xdp_umem.h"
>  
>  struct xdp_sock {
> @@ -47,6 +48,21 @@ static struct xdp_sock *xdp_sk(struct sock *sk)
>  	return (struct xdp_sock *)sk;
>  }
>  
> +static int xsk_init_queue(u32 entries, struct xsk_queue **queue)
> +{
> +	struct xsk_queue *q;
> +
> +	if (entries == 0 || *queue || !is_power_of_2(entries))
> +		return -EINVAL;
> +
> +	q = xskq_create(entries);
> +	if (!q)
> +		return -ENOMEM;
> +
> +	*queue = q;
> +	return 0;
> +}
> +
>  static int xsk_release(struct socket *sock)
>  {
>  	struct sock *sk = sock->sk;
> @@ -109,6 +125,23 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
>  		mutex_unlock(&xs->mutex);
>  		return 0;
>  	}
> +	case XDP_UMEM_FILL_RING:
> +	{
> +		struct xsk_queue **q;
> +		int entries;
> +
> +		if (!xs->umem)
> +			return -EINVAL;
> +
> +		if (copy_from_user(&entries, optval, sizeof(entries)))
> +			return -EFAULT;
> +
> +		mutex_lock(&xs->mutex);
> +		q = &xs->umem->fq;
> +		err = xsk_init_queue(entries, q);
> +		mutex_unlock(&xs->mutex);
> +		return err;
> +	}
>  	default:
>  		break;
>  	}
> @@ -116,6 +149,33 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
>  	return -ENOPROTOOPT;
>  }
>  
> +static int xsk_mmap(struct file *file, struct socket *sock,
> +		    struct vm_area_struct *vma)
> +{
> +	unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
> +	unsigned long size = vma->vm_end - vma->vm_start;
> +	struct xdp_sock *xs = xdp_sk(sock->sk);
> +	struct xsk_queue *q;
> +	unsigned long pfn;
> +	struct page *qpg;
> +
> +	if (!xs->umem)
> +		return -EINVAL;
> +
> +	if (offset == XDP_UMEM_PGOFF_FILL_RING)
> +		q = xs->umem->fq;
> +	else
> +		return -EINVAL;
> +
> +	qpg = virt_to_head_page(q->ring);
> +	if (size > (PAGE_SIZE << compound_order(qpg)))
> +		return -EINVAL;
> +
> +	pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
> +	return remap_pfn_range(vma, vma->vm_start, pfn,
> +			       size, vma->vm_page_prot);
> +}
> +
>  static struct proto xsk_proto = {
>  	.name =		"XDP",
>  	.owner =	THIS_MODULE,
> @@ -139,7 +199,7 @@ static const struct proto_ops xsk_proto_ops = {
>  	.getsockopt =	sock_no_getsockopt,
>  	.sendmsg =	sock_no_sendmsg,
>  	.recvmsg =	sock_no_recvmsg,
> -	.mmap =		sock_no_mmap,
> +	.mmap =		xsk_mmap,
>  	.sendpage =	sock_no_sendpage,
>  };
>  
> diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c
> new file mode 100644
> index 000000000000..23da4f29d3fb
> --- /dev/null
> +++ b/net/xdp/xsk_queue.c
> @@ -0,0 +1,58 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* XDP user-space ring structure
> + * Copyright(c) 2018 Intel Corporation.
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms and conditions of the GNU General Public License,
> + * version 2, as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope it will be useful, but WITHOUT
> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
> + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
> + * more details.
> + */
> +
> +#include <linux/slab.h>
> +
> +#include "xsk_queue.h"
> +
> +static u32 xskq_umem_get_ring_size(struct xsk_queue *q)
> +{
> +	return sizeof(struct xdp_umem_ring) + q->nentries * sizeof(u32);
> +}
> +
> +struct xsk_queue *xskq_create(u32 nentries)
> +{
> +	struct xsk_queue *q;
> +	gfp_t gfp_flags;
> +	size_t size;
> +
> +	q = kzalloc(sizeof(*q), GFP_KERNEL);
> +	if (!q)
> +		return NULL;
> +
> +	q->nentries = nentries;
> +	q->ring_mask = nentries - 1;
> +
> +	gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN |
> +		    __GFP_COMP  | __GFP_NORETRY;
> +	size = xskq_umem_get_ring_size(q);
> +
> +	q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags,
> +						      get_order(size));
> +	if (!q->ring) {
> +		kfree(q);
> +		return NULL;
> +	}
> +
> +	return q;
> +}
> +
> +void xskq_destroy(struct xsk_queue *q)
> +{
> +	if (!q)
> +		return;
> +
> +	page_frag_free(q->ring);
> +	kfree(q);
> +}
> diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
> new file mode 100644
> index 000000000000..7eb556bf73be
> --- /dev/null
> +++ b/net/xdp/xsk_queue.h
> @@ -0,0 +1,38 @@
> +/* SPDX-License-Identifier: GPL-2.0
> + * XDP user-space ring structure
> + * Copyright(c) 2018 Intel Corporation.
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms and conditions of the GNU General Public License,
> + * version 2, as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope it will be useful, but WITHOUT
> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
> + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
> + * more details.
> + */
> +
> +#ifndef _LINUX_XSK_QUEUE_H
> +#define _LINUX_XSK_QUEUE_H
> +
> +#include <linux/types.h>
> +#include <linux/if_xdp.h>
> +
> +#include "xdp_umem_props.h"
> +
> +struct xsk_queue {
> +	struct xdp_umem_props umem_props;
> +	u32 ring_mask;
> +	u32 nentries;
> +	u32 prod_head;
> +	u32 prod_tail;
> +	u32 cons_head;
> +	u32 cons_tail;
> +	struct xdp_ring *ring;
> +	u64 invalid_descs;
> +};
> +
> +struct xsk_queue *xskq_create(u32 nentries);
> +void xskq_destroy(struct xsk_queue *q);
> +
> +#endif /* _LINUX_XSK_QUEUE_H */
> -- 
> 2.14.1