[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230209092436.87795-1-xuanzhuo@linux.alibaba.com>
Date: Thu, 9 Feb 2023 17:24:36 +0800
From: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
To: netdev@...r.kernel.org
Cc: 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
Subject: [PATCH net-next] xsk: support use vaddr as ring
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.
After AF_XDP fails to apply for continuous physical memory, this patch
tries to use vmalloc() to allocate memory to solve this problem.
Signed-off-by: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
---
net/xdp/xsk.c | 8 +++++---
net/xdp/xsk_queue.c | 20 ++++++++++++++------
net/xdp/xsk_queue.h | 1 +
3 files changed, 20 insertions(+), 9 deletions(-)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9f0561b67c12..33db57548ee3 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1296,7 +1296,6 @@ static int xsk_mmap(struct file *file, struct socket *sock,
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;
@@ -1319,10 +1318,13 @@ 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 (PAGE_ALIGN(q->ring_size) < size)
return -EINVAL;
+ if (is_vmalloc_addr(q->ring))
+ return remap_vmalloc_range(vma, q->ring, 0);
+
pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
return remap_pfn_range(vma, vma->vm_start, pfn,
size, vma->vm_page_prot);
diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c
index 6cf9586e5027..6582d394b7e2 100644
--- a/net/xdp/xsk_queue.c
+++ b/net/xdp/xsk_queue.c
@@ -37,14 +37,18 @@ struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
__GFP_COMP | __GFP_NORETRY;
size = xskq_get_ring_size(q, umem_queue);
+ q->ring_size = size;
q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags,
get_order(size));
- if (!q->ring) {
- kfree(q);
- return NULL;
- }
+ if (q->ring)
+ return q;
+
+ q->ring = vmalloc_user(size);
+ if (q->ring)
+ return q;
- return q;
+ kfree(q);
+ return NULL;
}
void xskq_destroy(struct xsk_queue *q)
@@ -52,6 +56,10 @@ void xskq_destroy(struct xsk_queue *q)
if (!q)
return;
- page_frag_free(q->ring);
+ if (is_vmalloc_addr(q->ring))
+ vfree(q->ring);
+ else
+ page_frag_free(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