mirror of
https://github.com/torvalds/linux.git
synced 2026-10-07 11:06:03 +02:00
b0057c68df
AF_XDP rings are allocated from setsockopt() and can be mapped into user space. The shared xskq_create() helper allocates the ring backing memory, but the user-controlled and long-lived allocation is not charged as kmem to the allocating memory cgroup. The current implementation uses vmalloc_user(), which allocates the backing pages with GFP_KERNEL | __GFP_ZERO. Use the same VM_USERMAP vmalloc path, but pass GFP_KERNEL_ACCOUNT so the ring backing pages are attributed to memcg/kmem and can be constrained by existing cgroup memory limits. This keeps the existing zeroing and mmap semantics while avoiding AF_XDP-specific optmem or RLIMIT_MEMLOCK accounting. Signed-off-by: Zihan Xi <zihanx@nebusec.ai> Acked-by: Stanislav Fomichev <sdf@fomichev.me> Link: https://patch.msgid.link/20260731164623.4694-2-zihanx@nebusec.ai Signed-off-by: Jakub Kicinski <kuba@kernel.org>
77 lines
1.5 KiB
C
77 lines
1.5 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* XDP user-space ring structure
|
|
* Copyright(c) 2018 Intel Corporation.
|
|
*/
|
|
|
|
#include <linux/log2.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/overflow.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <net/xdp_sock_drv.h>
|
|
|
|
#include <asm/shmparam.h>
|
|
|
|
#include "xsk_queue.h"
|
|
|
|
static size_t xskq_get_ring_size(struct xsk_queue *q, bool umem_queue)
|
|
{
|
|
struct xdp_umem_ring *umem_ring;
|
|
struct xdp_rxtx_ring *rxtx_ring;
|
|
|
|
if (umem_queue)
|
|
return struct_size(umem_ring, desc, q->nentries);
|
|
return struct_size(rxtx_ring, desc, q->nentries);
|
|
}
|
|
|
|
static void *xskq_vmalloc_user(unsigned long size)
|
|
{
|
|
return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END,
|
|
GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL,
|
|
VM_USERMAP, NUMA_NO_NODE,
|
|
__builtin_return_address(0));
|
|
}
|
|
|
|
struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
|
|
{
|
|
struct xsk_queue *q;
|
|
size_t size;
|
|
|
|
q = kzalloc_obj(*q);
|
|
if (!q)
|
|
return NULL;
|
|
|
|
q->nentries = nentries;
|
|
q->ring_mask = nentries - 1;
|
|
|
|
size = xskq_get_ring_size(q, umem_queue);
|
|
|
|
/* size which is overflowing or close to SIZE_MAX will become 0 in
|
|
* PAGE_ALIGN(), checking SIZE_MAX is enough due to the previous
|
|
* is_power_of_2(), the rest will be handled by vmalloc_user()
|
|
*/
|
|
if (unlikely(size == SIZE_MAX)) {
|
|
kfree(q);
|
|
return NULL;
|
|
}
|
|
|
|
size = PAGE_ALIGN(size);
|
|
|
|
q->ring = xskq_vmalloc_user(size);
|
|
if (!q->ring) {
|
|
kfree(q);
|
|
return NULL;
|
|
}
|
|
|
|
q->ring_vmalloc_size = size;
|
|
return q;
|
|
}
|
|
|
|
void xskq_destroy(struct xsk_queue *q)
|
|
{
|
|
if (!q)
|
|
return;
|
|
|
|
vfree(q->ring);
|
|
kfree(q);
|
|
}
|