From 25a91d8d91911f84a03a039339b29537e7f1970d Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:54:23 +0800 Subject: skbuff: Introduce skb_to_sgvec_nomark to map skb without mark new end As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given sglist without mark the sg which contain last skb data as the end. So the caller can mannipulate sg list as will when padding new data after the first call without calling sg_unmark_end to expend sg list. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af8cbf..c574bf3bd6f6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -691,6 +691,8 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); +int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len); int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); -- cgit v1.2.1 From 363ec392352e55c61ce2799c3f15f89f9429bba7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 26 Feb 2014 14:02:11 -0800 Subject: net: add skb_mstamp infrastructure ktime_get() is too expensive on some cases, and we'd like to get usec resolution timestamps in TCP stack. This patch adds a light weight facility using a combination of local_clock() and jiffies samples. Instead of : u64 t0, t1; t0 = ktime_get(); // stuff t1 = ktime_get(); delta_us = ktime_us_delta(t1, t0); use : struct skb_mstamp t0, t1; skb_mstamp_get(&t0); // stuff skb_mstamp_get(&t1); delta_us = skb_mstamp_us_delta(&t1, &t0); Note : local_clock() might have a (bounded) drift between cpus. Do not use this infra in place of ktime_get() without understanding the issues. Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Larry Brakmo Cc: Julian Anastasov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 57 insertions(+), 2 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 11b6925f0e96..6d8ed22accb4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -32,6 +32,7 @@ #include #include #include +#include #include /* A. Checksumming of received packets by device. @@ -356,11 +357,62 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +/** + * struct skb_mstamp - multi resolution time stamps + * @stamp_us: timestamp in us resolution + * @stamp_jiffies: timestamp in jiffies + */ +struct skb_mstamp { + union { + u64 v64; + struct { + u32 stamp_us; + u32 stamp_jiffies; + }; + }; +}; + +/** + * skb_mstamp_get - get current timestamp + * @cl: place to store timestamps + */ +static inline void skb_mstamp_get(struct skb_mstamp *cl) +{ + u64 val = local_clock(); + + do_div(val, NSEC_PER_USEC); + cl->stamp_us = (u32)val; + cl->stamp_jiffies = (u32)jiffies; +} + +/** + * skb_mstamp_delta - compute the difference in usec between two skb_mstamp + * @t1: pointer to newest sample + * @t0: pointer to oldest sample + */ +static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, + const struct skb_mstamp *t0) +{ + s32 delta_us = t1->stamp_us - t0->stamp_us; + u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies; + + /* If delta_us is negative, this might be because interval is too big, + * or local_clock() drift is too big : fallback using jiffies. + */ + if (delta_us <= 0 || + delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ))) + + delta_us = jiffies_to_usecs(delta_jiffies); + + return delta_us; +} + + /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list - * @tstamp: Time we arrived + * @tstamp: Time we arrived/left * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @cb: Control buffer. Free for use by every layer. Put private vars here @@ -429,7 +481,10 @@ struct sk_buff { struct sk_buff *next; struct sk_buff *prev; - ktime_t tstamp; + union { + ktime_t tstamp; + struct skb_mstamp skb_mstamp; + }; struct sock *sk; struct net_device *dev; -- cgit v1.2.1 From 61b905da33ae25edb6b9d2a5de21e34c3a77efe3 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 24 Mar 2014 15:34:47 -0700 Subject: net: Rename skb->rxhash to skb->hash The packet hash can be considered a property of the packet, not just on RX path. This patch changes name of rxhash and l4_rxhash skbuff fields to be hash and l4_hash respectively. This includes changing uses of the field in the code which don't call the access functions. Signed-off-by: Tom Herbert Signed-off-by: Eric Dumazet Cc: Mahesh Bandewar Signed-off-by: David S. Miller --- include/linux/skbuff.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 03db95ab8a8c..aa2c22cb8158 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -444,11 +444,11 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @tc_verd: traffic control verdict - * @rxhash: the packet hash computed on receive + * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed - * @l4_rxhash: indicate rxhash is a canonical 4-tuple hash over transport + * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not @@ -537,7 +537,7 @@ struct sk_buff { int skb_iif; - __u32 rxhash; + __u32 hash; __be16 vlan_proto; __u16 vlan_tci; @@ -556,7 +556,7 @@ struct sk_buff { #endif __u8 pfmemalloc:1; __u8 ooo_okay:1; - __u8 l4_rxhash:1; + __u8 l4_hash:1; __u8 wifi_acked_valid:1; __u8 wifi_acked:1; __u8 no_fcs:1; @@ -815,40 +815,40 @@ enum pkt_hash_types { static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { - skb->l4_rxhash = (type == PKT_HASH_TYPE_L4); - skb->rxhash = hash; + skb->l4_hash = (type == PKT_HASH_TYPE_L4); + skb->hash = hash; } void __skb_get_hash(struct sk_buff *skb); static inline __u32 skb_get_hash(struct sk_buff *skb) { - if (!skb->l4_rxhash) + if (!skb->l4_hash) __skb_get_hash(skb); - return skb->rxhash; + return skb->hash; } static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { - return skb->rxhash; + return skb->hash; } static inline void skb_clear_hash(struct sk_buff *skb) { - skb->rxhash = 0; - skb->l4_rxhash = 0; + skb->hash = 0; + skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { - if (!skb->l4_rxhash) + if (!skb->l4_hash) skb_clear_hash(skb); } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { - to->rxhash = from->rxhash; - to->l4_rxhash = from->l4_rxhash; + to->hash = from->hash; + to->l4_hash = from->l4_hash; }; #ifdef NET_SKBUFF_DATA_USES_OFFSET -- cgit v1.2.1 From 408eccce32044ee3285a7f6a812723ba3540c3e7 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 1 Apr 2014 16:20:23 +0200 Subject: net: ptp: move PTP classifier in its own file This commit fixes a build error reported by Fengguang, that is triggered when CONFIG_NETWORK_PHY_TIMESTAMPING is not set: ERROR: "ptp_classify_raw" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined! The fix is to introduce its own file for the PTP BPF classifier, so that PTP_1588_CLOCK and/or NETWORK_PHY_TIMESTAMPING can select it independently from each other. IXP4xx driver on ARM needs to select it as well since it does not seem to select PTP_1588_CLOCK or similar that would pull it in automatically. This also allows for hiding all of the internals of the BPF PTP program inside that file, and only exporting relevant API bits to drivers. This patch also adds a kdoc documentation of ptp_classify_raw() API to make it clear that it can return PTP_CLASS_* defines. Also, the BPF program has been translated into bpf_asm code, so that it can be more easily read and altered (extensively documented in [1]). In the kernel tree under tools/net/ we have bpf_asm and bpf_dbg tools, so the commented program can simply be translated via `./bpf_asm -c prog` where prog is a file that contains the commented code. This makes it easily readable/verifiable and when there's a need to change something, jump offsets etc do not need to be replaced manually which can be very error prone. Instead, a newly translated version via bpf_asm can simply replace the old code. I have checked opcode diffs before/after and it's the very same filter. [1] Documentation/networking/filter.txt Fixes: 164d8c666521 ("net: ptp: do not reimplement PTP/BPF classifier") Reported-by: Fengguang Wu Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Richard Cochran Cc: Jiri Benc Acked-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 18ef0224fb6a..31edf63937a1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2630,8 +2630,6 @@ static inline ktime_t net_invalid_timestamp(void) return ktime_set(0, 0); } -void skb_timestamping_init(void); - #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); -- cgit v1.2.1 From 574f7194f693cd80de96a39f0c43dbb346c38a15 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 1 Apr 2014 12:20:24 -0700 Subject: net: Add a test to see if a skb is freeable in irq context Currently netpoll and skb_release_head_state assume that a skb is freeable in hard irq context except when skb->destructor is set. The reality is far from this. So add a function skb_irq_freeable to compute the full test and in the process be the living documentation of what the requirements are of actually freeing a skb in hard irq context. Signed-off-by: "Eric W. Biederman" Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 31edf63937a1..350eebe770d9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2831,6 +2831,19 @@ static inline void skb_init_secmark(struct sk_buff *skb) { } #endif +static inline bool skb_irq_freeable(const struct sk_buff *skb) +{ + return !skb->destructor && +#if IS_ENABLED(CONFIG_XFRM) + !skb->sp && +#endif +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + !skb->nfct && +#endif + !skb->_skb_refdst && + !skb_has_frag_list(skb); +} + static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; -- cgit v1.2.1