OpenCloudOS-Kernel/include/net/xdp_sock.h

123 lines
2.5 KiB
C
Raw Normal View History

/* 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_buff;
struct xdp_umem {
u64 size;
u32 headroom;
xsk: Introduce AF_XDP buffer allocation API In order to simplify AF_XDP zero-copy enablement for NIC driver developers, a new AF_XDP buffer allocation API is added. The implementation is based on a single core (single producer/consumer) buffer pool for the AF_XDP UMEM. A buffer is allocated using the xsk_buff_alloc() function, and returned using xsk_buff_free(). If a buffer is disassociated with the pool, e.g. when a buffer is passed to an AF_XDP socket, a buffer is said to be released. Currently, the release function is only used by the AF_XDP internals and not visible to the driver. Drivers using this API should register the XDP memory model with the new MEM_TYPE_XSK_BUFF_POOL type. The API is defined in net/xdp_sock_drv.h. The buffer type is struct xdp_buff, and follows the lifetime of regular xdp_buffs, i.e. the lifetime of an xdp_buff is restricted to a NAPI context. In other words, the API is not replacing xdp_frames. In addition to introducing the API and implementations, the AF_XDP core is migrated to use the new APIs. rfc->v1: Fixed build errors/warnings for m68k and riscv. (kbuild test robot) Added headroom/chunk size getter. (Maxim/Björn) v1->v2: Swapped SoBs. (Maxim) v2->v3: Initialize struct xdp_buff member frame_sz. (Björn) Add API to query the DMA address of a frame. (Maxim) Do DMA sync for CPU till the end of the frame to handle possible growth (frame_sz). (Maxim) Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200520192103.355233-6-bjorn.topel@gmail.com
2020-05-21 03:20:53 +08:00
u32 chunk_size;
u32 chunks;
struct user_struct *user;
refcount_t users;
struct page **pgs;
u32 npgs;
xsk: add support for need_wakeup flag in AF_XDP rings This commit adds support for a new flag called need_wakeup in the AF_XDP Tx and fill rings. When this flag is set, it means that the application has to explicitly wake up the kernel Rx (for the bit in the fill ring) or kernel Tx (for bit in the Tx ring) processing by issuing a syscall. Poll() can wake up both depending on the flags submitted and sendto() will wake up tx processing only. The main reason for introducing this new flag is to be able to efficiently support the case when application and driver is executing on the same core. Previously, the driver was just busy-spinning on the fill ring if it ran out of buffers in the HW and there were none on the fill ring. This approach works when the application is running on another core as it can replenish the fill ring while the driver is busy-spinning. Though, this is a lousy approach if both of them are running on the same core as the probability of the fill ring getting more entries when the driver is busy-spinning is zero. With this new feature the driver now sets the need_wakeup flag and returns to the application. The application can then replenish the fill queue and then explicitly wake up the Rx processing in the kernel using the syscall poll(). For Tx, the flag is only set to one if the driver has no outstanding Tx completion interrupts. If it has some, the flag is zero as it will be woken up by a completion interrupt anyway. As a nice side effect, this new flag also improves the performance of the case where application and driver are running on two different cores as it reduces the number of syscalls to the kernel. The kernel tells user space if it needs to be woken up by a syscall, and this eliminates many of the syscalls. This flag needs some simple driver support. If the driver does not support this, the Rx flag is always zero and the Tx flag is always one. This makes any application relying on this feature default to the old behaviour of not requiring any syscalls in the Rx path and always having to call sendto() in the Tx path. For backwards compatibility reasons, this feature has to be explicitly turned on using a new bind flag (XDP_USE_NEED_WAKEUP). I recommend that you always turn it on as it so far always have had a positive performance impact. The name and inspiration of the flag has been taken from io_uring by Jens Axboe. Details about this feature in io_uring can be found in http://kernel.dk/io_uring.pdf, section 8.3. Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com> Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-08-14 15:27:17 +08:00
u8 flags;
int id;
bool zc;
spinlock_t xsk_tx_list_lock;
struct list_head xsk_tx_list;
};
struct xsk_map {
struct bpf_map map;
spinlock_t lock; /* Synchronize map updates */
struct xdp_sock *xsk_map[];
};
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;
struct xsk_buff_pool *pool;
u16 queue_id;
bool zc;
enum {
XSK_READY = 0,
XSK_BOUND,
XSK_UNBOUND,
} state;
/* Protects multiple processes in the control path */
struct mutex mutex;
struct xsk_queue *tx ____cacheline_aligned_in_smp;
struct list_head list;
xsk: fix potential race in SKB TX completion code There is a potential race in the TX completion code for the SKB case. One process enters the sendmsg code of an AF_XDP socket in order to send a frame. The execution eventually trickles down to the driver that is told to send the packet. However, it decides to drop the packet due to some error condition (e.g., rings full) and frees the SKB. This will trigger the SKB destructor and a completion will be sent to the AF_XDP user space through its single-producer/single-consumer queues. At the same time a TX interrupt has fired on another core and it dispatches the TX completion code in the driver. It does its HW specific things and ends up freeing the SKB associated with the transmitted packet. This will trigger the SKB destructor and a completion will be sent to the AF_XDP user space through its single-producer/single-consumer queues. With a pseudo call stack, it would look like this: Core 1: sendmsg() being called in the application netdev_start_xmit() Driver entered through ndo_start_xmit Driver decides to free the SKB for some reason (e.g., rings full) Destructor of SKB called xskq_produce_addr() is called to signal completion to user space Core 2: TX completion irq NAPI loop Driver irq handler for TX completions Frees the SKB Destructor of SKB called xskq_produce_addr() is called to signal completion to user space We now have a violation of the single-producer/single-consumer principle for our queues as there are two threads trying to produce at the same time on the same queue. Fixed by introducing a spin_lock in the destructor. In regards to the performance, I get around 1.74 Mpps for txonly before and after the introduction of the spinlock. There is of course some impact due to the spin lock but it is in the less significant digits that are too noisy for me to measure. But let us say that the version without the spin lock got 1.745 Mpps in the best case and the version with 1.735 Mpps in the worst case, then that would mean a maximum drop in performance of 0.5%. Fixes: 35fcde7f8deb ("xsk: support for Tx") Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-06-29 15:48:20 +08:00
/* Mutual exclusion of NAPI TX thread and sendmsg error paths
* in the SKB destructor callback.
*/
spinlock_t tx_completion_lock;
/* Protects generic receive. */
spinlock_t rx_lock;
/* Statistics */
u64 rx_dropped;
u64 rx_queue_full;
struct list_head map_list;
/* Protects map_list */
spinlock_t map_list_lock;
struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */
struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
};
#ifdef CONFIG_XDP_SOCKETS
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
void __xsk_map_flush(void);
static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
u32 key)
{
struct xsk_map *m = container_of(map, struct xsk_map, map);
struct xdp_sock *xs;
if (key >= map->max_entries)
return NULL;
xs = READ_ONCE(m->xsk_map[key]);
return xs;
}
#else
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
return -ENOTSUPP;
}
static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
{
return -EOPNOTSUPP;
}
static inline void __xsk_map_flush(void)
{
}
static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */