linux-stable/include/net/xdp_sock.h

111 lines
2.3 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/bpf.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 {
void *addrs;
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
2020-05-20 19:20:53 +00:00
u32 chunk_size;
u32 chunks;
u32 npgs;
struct user_struct *user;
refcount_t users;
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 07:27:17 +00:00
u8 flags;
bool zc;
struct page **pgs;
int id;
struct list_head xsk_dma_list;
struct work_struct work;
};
struct xsk_map {
struct bpf_map map;
spinlock_t lock; /* Synchronize map updates */
atomic_t count;
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-24 16:05:55 +00:00
struct xdp_sock __rcu *xsk_map[];
};
struct xdp_sock {
/* struct sock must be the first member of struct xdp_sock */
struct sock sk;
struct xsk_queue *rx ____cacheline_aligned_in_smp;
struct net_device *dev;
struct xdp_umem *umem;
struct list_head flush_node;
struct xsk_buff_pool *pool;
u16 queue_id;
bool zc;
bool sg;
enum {
XSK_READY = 0,
XSK_BOUND,
XSK_UNBOUND,
} state;
struct xsk_queue *tx ____cacheline_aligned_in_smp;
struct list_head tx_list;
/* Protects generic receive. */
spinlock_t rx_lock;
/* Statistics */
u64 rx_dropped;
u64 rx_queue_full;
/* When __xsk_generic_xmit() must return before it sees the EOP descriptor for the current
* packet, the partially built skb is saved here so that packet building can resume in next
* call of __xsk_generic_xmit().
*/
struct sk_buff *skb;
struct list_head map_list;
/* Protects map_list */
spinlock_t map_list_lock;
/* Protects multiple processes in the control path */
struct mutex mutex;
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);
#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)
{
}
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */