From b0768a86585d4d951a30ff565f19598dbbd67897 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:09 +0900 Subject: net: Export skb_headers_offset_update This is needed for veth XDP which does skb_copy_expand()-like operation. v2: - Drop skb_copy_header part because it has already been exported now. Signed-off-by: Toshiaki Makita Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7ebdf158a795..e93b157f526c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1038,6 +1038,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); +void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); -- cgit v1.2.3 From a8d5b4ab353738e16e5f9d21ab1e3d44b37983d0 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:12 +0900 Subject: xdp: Helper function to clear kernel pointers in xdp_frame xdp_frame has kernel pointers which should not be readable from bpf programs. When we want to reuse xdp_frame region but it may be read by bpf programs later, we can use this helper to clear kernel pointers. This is more efficient than calling memset() for the entire struct. Signed-off-by: Toshiaki Makita Acked-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann --- include/net/xdp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index fcb033f51d8c..76b95256c266 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -84,6 +84,13 @@ struct xdp_frame { struct net_device *dev_rx; /* used by cpumap */ }; +/* Clear kernel pointers in xdp_frame */ +static inline void xdp_scrub_frame(struct xdp_frame *frame) +{ + frame->data = NULL; + frame->dev_rx = NULL; +} + /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) -- cgit v1.2.3 From 0b19cc0a8694d4295383f88bc3441765875a57bc Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:15 +0900 Subject: bpf: Make redirect_info accessible from modules We are going to add kern_flags field in redirect_info for kernel internal use. In order to avoid function call to access the flags, make redirect_info accessible from modules. Also as it is now non-static, add prefix bpf_ to redirect_info. v6: - Fix sparse warning around EXPORT_SYMBOL. Signed-off-by: Toshiaki Makita Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 10 ++++++++++ net/core/filter.c | 29 +++++++++++------------------ 2 files changed, 21 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index c73dd7396886..4717af8b95e6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -537,6 +537,16 @@ struct sk_msg_buff { struct list_head list; }; +struct bpf_redirect_info { + u32 ifindex; + u32 flags; + struct bpf_map *map; + struct bpf_map *map_to_flush; + unsigned long map_owner; +}; + +DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); + /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) diff --git a/net/core/filter.c b/net/core/filter.c index 587bbfbd7db3..2de7dd9f2a57 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2082,19 +2082,12 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; -struct redirect_info { - u32 ifindex; - u32 flags; - struct bpf_map *map; - struct bpf_map *map_to_flush; - unsigned long map_owner; -}; - -static DEFINE_PER_CPU(struct redirect_info, redirect_info); +DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); +EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely(flags & ~(BPF_F_INGRESS))) return TC_ACT_SHOT; @@ -2107,7 +2100,7 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) int skb_do_redirect(struct sk_buff *skb) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct net_device *dev; dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex); @@ -3200,7 +3193,7 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, void xdp_do_flush_map(void) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map = ri->map_to_flush; ri->map_to_flush = NULL; @@ -3245,7 +3238,7 @@ static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog, static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; u32 index = ri->ifindex; @@ -3285,7 +3278,7 @@ err: int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct net_device *fwd; u32 index = ri->ifindex; int err; @@ -3317,7 +3310,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; u32 index = ri->ifindex; @@ -3368,7 +3361,7 @@ err: int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); u32 index = ri->ifindex; struct net_device *fwd; int err = 0; @@ -3399,7 +3392,7 @@ EXPORT_SYMBOL_GPL(xdp_do_generic_redirect); BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely(flags)) return XDP_ABORTED; @@ -3423,7 +3416,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = { BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags, unsigned long, map_owner) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely(flags)) return XDP_ABORTED; -- cgit v1.2.3 From 2539650fadbf63a431e76535a9de7bff6ea5e409 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:16 +0900 Subject: xdp: Helpers for disabling napi_direct of xdp_return_frame We need some mechanism to disable napi_direct on calling xdp_return_frame_rx_napi() from some context. When veth gets support of XDP_REDIRECT, it will redirects packets which are redirected from other devices. On redirection veth will reuse xdp_mem_info of the redirection source device to make return_frame work. But in this case .ndo_xdp_xmit() called from veth redirection uses xdp_mem_info which is not guarded by NAPI, because the .ndo_xdp_xmit() is not called directly from the rxq which owns the xdp_mem_info. This approach introduces a flag in bpf_redirect_info to indicate that napi_direct should be disabled even when _rx_napi variant is used as well as helper functions to use it. A NAPI handler who wants to use this flag needs to call xdp_set_return_frame_no_direct() before processing packets, and call xdp_clear_return_frame_no_direct() after xdp_do_flush_map() before exiting NAPI. v4: - Use bpf_redirect_info for storing the flag instead of xdp_mem_info to avoid per-frame copy cost. Signed-off-by: Toshiaki Makita Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 25 +++++++++++++++++++++++++ net/core/xdp.c | 6 ++++-- 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 4717af8b95e6..2b072dab32c0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -543,10 +543,14 @@ struct bpf_redirect_info { struct bpf_map *map; struct bpf_map *map_to_flush; unsigned long map_owner; + u32 kern_flags; }; DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); +/* flags for bpf_redirect_info kern_flags */ +#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ + /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) @@ -775,6 +779,27 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +static inline bool xdp_return_frame_no_direct(void) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; +} + +static inline void xdp_set_return_frame_no_direct(void) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; +} + +static inline void xdp_clear_return_frame_no_direct(void) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; +} + static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 57285383ed00..3dd99e1c04f5 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -330,10 +330,12 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); - if (xa) + if (xa) { + napi_direct &= !xdp_return_frame_no_direct(); page_pool_put_page(xa->page_pool, page, napi_direct); - else + } else { put_page(page); + } rcu_read_unlock(); break; case MEM_TYPE_PAGE_SHARED: -- cgit v1.2.3