linux-stable/include/net/xdp.h

296 lines
8.5 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/* include/net/xdp.h
*
* Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
*/
#ifndef __LINUX_NET_XDP_H__
#define __LINUX_NET_XDP_H__
#include <linux/skbuff.h> /* skb_shared_info */
/**
* DOC: XDP RX-queue information
*
* The XDP RX-queue info (xdp_rxq_info) is associated with the driver
* level RX-ring queues. It is information that is specific to how
* the driver have configured a given RX-ring queue.
*
* Each xdp_buff frame received in the driver carries a (pointer)
* reference to this xdp_rxq_info structure. This provides the XDP
* data-path read-access to RX-info for both kernel and bpf-side
* (limited subset).
*
* For now, direct access is only safe while running in NAPI/softirq
* context. Contents are read-mostly and must not be updated during
* driver NAPI/softirq poll.
*
* The driver usage API is a register and unregister API.
*
* The struct is not directly tied to the XDP prog. A new XDP prog
* can be attached as long as it doesn't change the underlying
* RX-ring. If the RX-ring does change significantly, the NIC driver
* naturally need to stop the RX-ring before purging and reallocating
* memory. In that process the driver MUST call unregister (which
* also applies for driver shutdown and unload). The register API is
* also mandatory during RX-ring setup.
*/
enum xdp_mem_type {
MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */
MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */
MEM_TYPE_PAGE_POOL,
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
MEM_TYPE_XSK_BUFF_POOL,
MEM_TYPE_MAX,
};
/* XDP flags for ndo_xdp_xmit */
#define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */
#define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH
struct xdp_mem_info {
u32 type; /* enum xdp_mem_type, but known size type */
xdp: rhashtable with allocator ID to pointer mapping Use the IDA infrastructure for getting a cyclic increasing ID number, that is used for keeping track of each registered allocator per RX-queue xdp_rxq_info. Instead of using the IDR infrastructure, which uses a radix tree, use a dynamic rhashtable, for creating ID to pointer lookup table, because this is faster. The problem that is being solved here is that, the xdp_rxq_info pointer (stored in xdp_buff) cannot be used directly, as the guaranteed lifetime is too short. The info is needed on a (potentially) remote CPU during DMA-TX completion time . In an xdp_frame the xdp_mem_info is stored, when it got converted from an xdp_buff, which is sufficient for the simple page refcnt based recycle schemes. For more advanced allocators there is a need to store a pointer to the registered allocator. Thus, there is a need to guard the lifetime or validity of the allocator pointer, which is done through this rhashtable ID map to pointer. The removal and validity of of the allocator and helper struct xdp_mem_allocator is guarded by RCU. The allocator will be created by the driver, and registered with xdp_rxq_info_reg_mem_model(). It is up-to debate who is responsible for freeing the allocator pointer or invoking the allocator destructor function. In any case, this must happen via RCU freeing. Use the IDA infrastructure for getting a cyclic increasing ID number, that is used for keeping track of each registered allocator per RX-queue xdp_rxq_info. V4: Per req of Jason Wang - Use xdp_rxq_info_reg_mem_model() in all drivers implementing XDP_REDIRECT, even-though it's not strictly necessary when allocator==NULL for type MEM_TYPE_PAGE_SHARED (given it's zero). V6: Per req of Alex Duyck - Introduce rhashtable_lookup() call in later patch V8: Address sparse should be static warnings (from kbuild test robot) Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-17 14:46:12 +00:00
u32 id;
};
struct page_pool;
struct xdp_rxq_info {
struct net_device *dev;
u32 queue_index;
u32 reg_state;
struct xdp_mem_info mem;
unsigned int napi_id;
} ____cacheline_aligned; /* perf critical, avoid false-sharing */
struct xdp_txq_info {
struct net_device *dev;
};
struct xdp_buff {
void *data;
void *data_end;
void *data_meta;
void *data_hard_start;
struct xdp_rxq_info *rxq;
struct xdp_txq_info *txq;
u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
};
static __always_inline void
xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq)
{
xdp->frame_sz = frame_sz;
xdp->rxq = rxq;
}
static __always_inline void
xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start,
int headroom, int data_len, const bool meta_valid)
{
unsigned char *data = hard_start + headroom;
xdp->data_hard_start = hard_start;
xdp->data = data;
xdp->data_end = data + data_len;
xdp->data_meta = meta_valid ? data : data + 1;
}
/* Reserve memory area at end-of data area.
*
* This macro reserves tailroom in the XDP buffer by limiting the
* XDP/BPF data access to data_hard_end. Notice same area (and size)
* is used for XDP_PASS, when constructing the SKB via build_skb().
*/
#define xdp_data_hard_end(xdp) \
((xdp)->data_hard_start + (xdp)->frame_sz - \
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
static inline struct skb_shared_info *
xdp_get_shared_info_from_buff(struct xdp_buff *xdp)
{
return (struct skb_shared_info *)xdp_data_hard_end(xdp);
}
struct xdp_frame {
void *data;
u16 len;
u16 headroom;
u32 metasize:8;
u32 frame_sz:24;
/* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time,
* while mem info is valid on remote CPU.
*/
struct xdp_mem_info mem;
struct net_device *dev_rx; /* used by cpumap */
};
#define XDP_BULK_QUEUE_SIZE 16
struct xdp_frame_bulk {
int count;
void *xa;
void *q[XDP_BULK_QUEUE_SIZE];
};
static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq)
{
/* bq->count will be zero'ed when bq->xa gets updated */
bq->xa = NULL;
}
static inline struct skb_shared_info *
xdp_get_shared_info_from_frame(struct xdp_frame *frame)
{
void *data_hard_start = frame->data - frame->headroom - sizeof(*frame);
return (struct skb_shared_info *)(data_hard_start + frame->frame_sz -
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
}
struct xdp_cpumap_stats {
unsigned int redirect;
unsigned int pass;
unsigned int drop;
};
/* Clear kernel pointers in xdp_frame */
static inline void xdp_scrub_frame(struct xdp_frame *frame)
{
frame->data = NULL;
frame->dev_rx = NULL;
}
/* Avoids inlining WARN macro in fast-path */
void xdp_warn(const char *msg, const char *func, const int line);
#define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
struct sk_buff *skb,
struct net_device *dev);
struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
struct net_device *dev);
int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 09:07:45 +00:00
struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf);
static inline
void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
{
xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame);
xdp->data = frame->data;
xdp->data_end = frame->data + frame->len;
xdp->data_meta = frame->data - frame->metasize;
xdp->frame_sz = frame->frame_sz;
}
static inline
int xdp_update_frame_from_buff(struct xdp_buff *xdp,
struct xdp_frame *xdp_frame)
{
int metasize, headroom;
/* Assure headroom is available for storing info */
headroom = xdp->data - xdp->data_hard_start;
metasize = xdp->data - xdp->data_meta;
metasize = metasize > 0 ? metasize : 0;
if (unlikely((headroom - metasize) < sizeof(*xdp_frame)))
return -ENOSPC;
/* Catch if driver didn't reserve tailroom for skb_shared_info */
if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) {
XDP_WARN("Driver BUG: missing reserved tailroom");
return -ENOSPC;
}
xdp_frame->data = xdp->data;
xdp_frame->len = xdp->data_end - xdp->data;
xdp_frame->headroom = headroom - sizeof(*xdp_frame);
xdp_frame->metasize = metasize;
xdp_frame->frame_sz = xdp->frame_sz;
return 0;
}
/* Convert xdp_buff to xdp_frame */
static inline
struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
{
struct xdp_frame *xdp_frame;
if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
return xdp_convert_zc_to_xdp_frame(xdp);
/* Store info in top of packet */
xdp_frame = xdp->data_hard_start;
if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0))
return NULL;
/* rxq only valid until napi_schedule ends, convert to xdp_mem_info */
xdp_frame->mem = xdp->rxq->mem;
return xdp_frame;
}
xdp: transition into using xdp_frame for return API Changing API xdp_return_frame() to take struct xdp_frame as argument, seems like a natural choice. But there are some subtle performance details here that needs extra care, which is a deliberate choice. When de-referencing xdp_frame on a remote CPU during DMA-TX completion, result in the cache-line is change to "Shared" state. Later when the page is reused for RX, then this xdp_frame cache-line is written, which change the state to "Modified". This situation already happens (naturally) for, virtio_net, tun and cpumap as the xdp_frame pointer is the queued object. In tun and cpumap, the ptr_ring is used for efficiently transferring cache-lines (with pointers) between CPUs. Thus, the only option is to de-referencing xdp_frame. It is only the ixgbe driver that had an optimization, in which it can avoid doing the de-reference of xdp_frame. The driver already have TX-ring queue, which (in case of remote DMA-TX completion) have to be transferred between CPUs anyhow. In this data area, we stored a struct xdp_mem_info and a data pointer, which allowed us to avoid de-referencing xdp_frame. To compensate for this, a prefetchw is used for telling the cache coherency protocol about our access pattern. My benchmarks show that this prefetchw is enough to compensate the ixgbe driver. V7: Adjust for commit d9314c474d4f ("i40e: add support for XDP_REDIRECT") V8: Adjust for commit bd658dda4237 ("net/mlx5e: Separate dma base address and offset in dma_sync call") Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-17 14:46:32 +00:00
void xdp_return_frame(struct xdp_frame *xdpf);
void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
void xdp_return_buff(struct xdp_buff *xdp);
void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq);
void xdp_return_frame_bulk(struct xdp_frame *xdpf,
struct xdp_frame_bulk *bq);
/* When sending xdp_frame into the network stack, then there is no
* return point callback, which is needed to release e.g. DMA-mapping
* resources with page_pool. Thus, have explicit function to release
* frame resources.
*/
void __xdp_release_frame(void *data, struct xdp_mem_info *mem);
static inline void xdp_release_frame(struct xdp_frame *xdpf)
{
struct xdp_mem_info *mem = &xdpf->mem;
/* Curr only page_pool needs this */
if (mem->type == MEM_TYPE_PAGE_POOL)
__xdp_release_frame(xdpf->data, mem);
}
int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
struct net_device *dev, u32 queue_index, unsigned int napi_id);
void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq);
void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq);
bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq);
int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
enum xdp_mem_type type, void *allocator);
void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq);
/* Drivers not supporting XDP metadata can use this helper, which
* rejects any room expansion for metadata as a result.
*/
static __always_inline void
xdp_set_data_meta_invalid(struct xdp_buff *xdp)
{
xdp->data_meta = xdp->data + 1;
}
static __always_inline bool
xdp_data_meta_unsupported(const struct xdp_buff *xdp)
{
return unlikely(xdp->data_meta > xdp->data);
}
static inline bool xdp_metalen_invalid(unsigned long metalen)
{
return (metalen & (sizeof(__u32) - 1)) || (metalen > 32);
}
struct xdp_attachment_info {
struct bpf_prog *prog;
u32 flags;
};
struct netdev_bpf;
void xdp_attachment_setup(struct xdp_attachment_info *info,
struct netdev_bpf *bpf);
#define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE
#endif /* __LINUX_NET_XDP_H__ */