linux_dsm_epyc7002/include/net/xdp_sock.h
Ilya Maximets 455302d1c9 xdp: fix hang while unregistering device bound to xdp socket
Device that bound to XDP socket will not have zero refcount until the
userspace application will not close it. This leads to hang inside
'netdev_wait_allrefs()' if device unregistering requested:

  # ip link del p1
  < hang on recvmsg on netlink socket >

  # ps -x | grep ip
  5126  pts/0    D+   0:00 ip link del p1

  # journalctl -b

  Jun 05 07:19:16 kernel:
  unregister_netdevice: waiting for p1 to become free. Usage count = 1

  Jun 05 07:19:27 kernel:
  unregister_netdevice: waiting for p1 to become free. Usage count = 1
  ...

Fix that by implementing NETDEV_UNREGISTER event notification handler
to properly clean up all the resources and unref device.

This should also allow socket killing via ss(8) utility.

Fixes: 965a990984 ("xsk: add support for bind for Rx")
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-07-03 15:10:55 +02:00

224 lines
4.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/* AF_XDP internal functions
* Copyright(c) 2018 Intel Corporation.
*/
#ifndef _LINUX_XDP_SOCK_H
#define _LINUX_XDP_SOCK_H
#include <linux/workqueue.h>
#include <linux/if_xdp.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <net/sock.h>
struct net_device;
struct xsk_queue;
struct xdp_umem_page {
void *addr;
dma_addr_t dma;
};
struct xdp_umem_fq_reuse {
u32 nentries;
u32 length;
u64 handles[];
};
struct xdp_umem {
struct xsk_queue *fq;
struct xsk_queue *cq;
struct xdp_umem_page *pages;
u64 chunk_mask;
u64 size;
u32 headroom;
u32 chunk_size_nohr;
struct user_struct *user;
unsigned long address;
refcount_t users;
struct work_struct work;
struct page **pgs;
u32 npgs;
int id;
struct net_device *dev;
struct xdp_umem_fq_reuse *fq_reuse;
u16 queue_id;
bool zc;
spinlock_t xsk_list_lock;
struct list_head xsk_list;
};
struct xdp_sock {
/* struct sock must be the first member of struct xdp_sock */
struct sock sk;
struct xsk_queue *rx;
struct net_device *dev;
struct xdp_umem *umem;
struct list_head flush_node;
u16 queue_id;
struct xsk_queue *tx ____cacheline_aligned_in_smp;
struct list_head list;
bool zc;
enum {
XSK_READY = 0,
XSK_BOUND,
XSK_UNBOUND,
} state;
/* Protects multiple processes in the control path */
struct mutex mutex;
/* Mutual exclusion of NAPI TX thread and sendmsg error paths
* in the SKB destructor callback.
*/
spinlock_t tx_completion_lock;
u64 rx_dropped;
};
struct xdp_buff;
#ifdef CONFIG_XDP_SOCKETS
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
void xsk_flush(struct xdp_sock *xs);
bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
/* Used from netdev driver */
u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr);
void xsk_umem_discard_addr(struct xdp_umem *umem);
void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len);
void xsk_umem_consume_tx_done(struct xdp_umem *umem);
struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries);
struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
struct xdp_umem_fq_reuse *newq);
void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq);
struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
{
return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1));
}
static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
{
return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1));
}
/* Reuse-queue aware version of FILL queue helpers */
static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
{
struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
if (!rq->length)
return xsk_umem_peek_addr(umem, addr);
*addr = rq->handles[rq->length - 1];
return addr;
}
static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem)
{
struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
if (!rq->length)
xsk_umem_discard_addr(umem);
else
rq->length--;
}
static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
{
struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
rq->handles[rq->length++] = addr;
}
#else
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
return -ENOTSUPP;
}
static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
return -ENOTSUPP;
}
static inline void xsk_flush(struct xdp_sock *xs)
{
}
static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
{
return false;
}
static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
{
return NULL;
}
static inline void xsk_umem_discard_addr(struct xdp_umem *umem)
{
}
static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
{
}
static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma,
u32 *len)
{
return false;
}
static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
{
}
static inline struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries)
{
return NULL;
}
static inline struct xdp_umem_fq_reuse *xsk_reuseq_swap(
struct xdp_umem *umem,
struct xdp_umem_fq_reuse *newq)
{
return NULL;
}
static inline void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq)
{
}
static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
u16 queue_id)
{
return NULL;
}
static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
{
return NULL;
}
static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
{
return 0;
}
static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
{
return NULL;
}
static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem)
{
}
static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
{
}
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */