[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAJ8uoz2yc4UNOgpqqz34ctzGHsLcO5_jxawSVpSqW4XPNC5J9g@mail.gmail.com>
Date: Mon, 13 Feb 2023 14:07:35 +0100
From: Magnus Karlsson <magnus.karlsson@...il.com>
To: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
Cc: netdev@...r.kernel.org,
Björn Töpel <bjorn@...nel.org>,
Magnus Karlsson <magnus.karlsson@...el.com>,
Maciej Fijalkowski <maciej.fijalkowski@...el.com>,
Jonathan Lemon <jonathan.lemon@...il.com>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Jesper Dangaard Brouer <hawk@...nel.org>,
John Fastabend <john.fastabend@...il.com>, bpf@...r.kernel.org,
kernel test robot <lkp@...el.com>
Subject: Re: [PATCH net-next v2] xsk: support use vaddr as ring
On Sun, 12 Feb 2023 at 04:22, Xuan Zhuo <xuanzhuo@...ux.alibaba.com> wrote:
>
> When we try to start AF_XDP on some machines with long running time, due
> to the machine's memory fragmentation problem, there is no sufficient
> continuous physical memory that will cause the start failure.
nit: contiguous
But perfectly understandable without fixing this.
> If the size of the queue is 8 * 1024, then the size of the desc[] is
> 8 * 1024 * 8 = 16 * PAGE, but we also add struct xdp_ring size, so it is
> 16page+. This is necessary to apply for a 4-order memory. If there are a
> lot of queues, it is difficult to these machine with long running time.
>
> Here, that we actually waste 15 pages. 4-Order memory is 32 pages, but
> we only use 17 pages.
>
> This patch replaces __get_free_pages() by vmalloc() to allocate memory
> to solve these problems.
Thanks for improving/fixing this.
Acked-by: Magnus Karlsson <magnus.karlsson@...el.com>
> Signed-off-by: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
> Reported-by: kernel test robot <lkp@...el.com>
> Link: https://lore.kernel.org/oe-kbuild-all/202302091850.0HBmsDAq-lkp@intel.com
> ---
>
> v2:
> 1. remove __get_free_pages() @Magnus Karlsson
>
> net/xdp/xsk.c | 9 ++-------
> net/xdp/xsk_queue.c | 10 ++++------
> net/xdp/xsk_queue.h | 1 +
> 3 files changed, 7 insertions(+), 13 deletions(-)
>
> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> index 9f0561b67c12..6a588b99b670 100644
> --- a/net/xdp/xsk.c
> +++ b/net/xdp/xsk.c
> @@ -1295,8 +1295,6 @@ static int xsk_mmap(struct file *file, struct socket *sock,
> unsigned long size = vma->vm_end - vma->vm_start;
> struct xdp_sock *xs = xdp_sk(sock->sk);
> struct xsk_queue *q = NULL;
> - unsigned long pfn;
> - struct page *qpg;
>
> if (READ_ONCE(xs->state) != XSK_READY)
> return -EBUSY;
> @@ -1319,13 +1317,10 @@ static int xsk_mmap(struct file *file, struct socket *sock,
>
> /* Matches the smp_wmb() in xsk_init_queue */
> smp_rmb();
> - qpg = virt_to_head_page(q->ring);
> - if (size > page_size(qpg))
> + if (size > PAGE_ALIGN(q->ring_size))
> return -EINVAL;
>
> - pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
> - return remap_pfn_range(vma, vma->vm_start, pfn,
> - size, vma->vm_page_prot);
> + return remap_vmalloc_range(vma, q->ring, 0);
> }
>
> static int xsk_notifier(struct notifier_block *this,
> diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c
> index 6cf9586e5027..247316bdfcbe 100644
> --- a/net/xdp/xsk_queue.c
> +++ b/net/xdp/xsk_queue.c
> @@ -7,6 +7,7 @@
> #include <linux/slab.h>
> #include <linux/overflow.h>
> #include <net/xdp_sock_drv.h>
> +#include <linux/vmalloc.h>
>
> #include "xsk_queue.h"
>
> @@ -23,7 +24,6 @@ static size_t xskq_get_ring_size(struct xsk_queue *q, bool umem_queue)
> struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
> {
> struct xsk_queue *q;
> - gfp_t gfp_flags;
> size_t size;
>
> q = kzalloc(sizeof(*q), GFP_KERNEL);
> @@ -33,12 +33,10 @@ struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
> q->nentries = nentries;
> q->ring_mask = nentries - 1;
>
> - gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN |
> - __GFP_COMP | __GFP_NORETRY;
> size = xskq_get_ring_size(q, umem_queue);
>
> - q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags,
> - get_order(size));
> + q->ring_size = size;
> + q->ring = (struct xdp_ring *)vmalloc_user(size);
> if (!q->ring) {
> kfree(q);
> return NULL;
> @@ -52,6 +50,6 @@ void xskq_destroy(struct xsk_queue *q)
> if (!q)
> return;
>
> - page_frag_free(q->ring);
> + vfree(q->ring);
> kfree(q);
> }
> diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
> index c6fb6b763658..35922b8b92a8 100644
> --- a/net/xdp/xsk_queue.h
> +++ b/net/xdp/xsk_queue.h
> @@ -45,6 +45,7 @@ struct xsk_queue {
> struct xdp_ring *ring;
> u64 invalid_descs;
> u64 queue_empty_descs;
> + size_t ring_size;
> };
>
> /* The structure of the shared state of the rings are a simple
> --
> 2.32.0.3.g01195cf9f
>
Powered by blists - more mailing lists