From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- net/ipv6/reassembly.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv6/reassembly.c') diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index a555156e977..6d4292ff585 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3 From d27f9b35827ec91d71d3561c127a0a8135fb470d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 13 Jun 2010 23:02:24 +0000 Subject: ip_frag: Remove some atomic ops Instead of doing one atomic operation per frag, we can factorize them. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/ip_fragment.c | 3 +-- net/ipv6/reassembly.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'net/ipv6/reassembly.c') diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 75347ea70ea..963c3689d0a 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -556,7 +556,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, skb_shinfo(head)->frag_list = head->next; skb_push(head, head->data - skb_network_header(head)); - atomic_sub(head->truesize, &qp->q.net->mem); for (fp=head->next; fp; fp = fp->next) { head->data_len += fp->len; @@ -566,8 +565,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; - atomic_sub(fp->truesize, &qp->q.net->mem); } + atomic_sub(head->truesize, &qp->q.net->mem); head->next = NULL; head->dev = dev; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 6d4292ff585..a630506151c 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -524,7 +524,6 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, skb_shinfo(head)->frag_list = head->next; skb_reset_transport_header(head); skb_push(head, head->data - skb_network_header(head)); - atomic_sub(head->truesize, &fq->q.net->mem); for (fp=head->next; fp; fp = fp->next) { head->data_len += fp->len; @@ -534,8 +533,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; - atomic_sub(fp->truesize, &fq->q.net->mem); } + atomic_sub(head->truesize, &fq->q.net->mem); head->next = NULL; head->dev = dev; -- cgit v1.2.3 From a95d8c88bea0c93505e1d143d075f112be2b25e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 13 Jun 2010 23:22:43 +0000 Subject: ipfrag : frag_kfree_skb() cleanup Third param (work) is unused, remove it. Remove __inline__ and inline qualifiers. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/ip_fragment.c | 9 +++------ net/ipv6/reassembly.c | 7 ++----- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'net/ipv6/reassembly.c') diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 963c3689d0a..858d34648ee 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -124,11 +124,8 @@ static int ip4_frag_match(struct inet_frag_queue *q, void *a) } /* Memory Tracking Functions. */ -static __inline__ void frag_kfree_skb(struct netns_frags *nf, - struct sk_buff *skb, int *work) +static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) { - if (work) - *work -= skb->truesize; atomic_sub(skb->truesize, &nf->mem); kfree_skb(skb); } @@ -309,7 +306,7 @@ static int ip_frag_reinit(struct ipq *qp) fp = qp->q.fragments; do { struct sk_buff *xp = fp->next; - frag_kfree_skb(qp->q.net, fp, NULL); + frag_kfree_skb(qp->q.net, fp); fp = xp; } while (fp); @@ -446,7 +443,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) qp->q.fragments = next; qp->q.meat -= free_it->len; - frag_kfree_skb(qp->q.net, free_it, NULL); + frag_kfree_skb(qp->q.net, free_it); } } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index a630506151c..0b97230a325 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -150,11 +150,8 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a) EXPORT_SYMBOL(ip6_frag_match); /* Memory Tracking Functions. */ -static inline void frag_kfree_skb(struct netns_frags *nf, - struct sk_buff *skb, int *work) +static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) { - if (work) - *work -= skb->truesize; atomic_sub(skb->truesize, &nf->mem); kfree_skb(skb); } @@ -392,7 +389,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, fq->q.fragments = next; fq->q.meat -= free_it->len; - frag_kfree_skb(fq->q.net, free_it, NULL); + frag_kfree_skb(fq->q.net, free_it); } } -- cgit v1.2.3 From d6bebca92c663fb216c072193945946f3807ca7f Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Tue, 29 Jun 2010 04:39:37 +0000 Subject: fragment: add fast path for in-order fragments add fast path for in-order fragments As the fragments are sent in order in most of OSes, such as Windows, Darwin and FreeBSD, it is likely the new fragments are at the end of the inet_frag_queue. In the fast path, we check if the skb at the end of the inet_frag_queue is the prev we expect. Signed-off-by: Changli Gao ---- include/net/inet_frag.h | 1 + net/ipv4/ip_fragment.c | 12 ++++++++++++ net/ipv6/reassembly.c | 11 +++++++++++ 3 files changed, 24 insertions(+) Signed-off-by: David S. Miller --- include/net/inet_frag.h | 1 + net/ipv4/ip_fragment.c | 12 ++++++++++++ net/ipv6/reassembly.c | 11 +++++++++++ 3 files changed, 24 insertions(+) (limited to 'net/ipv6/reassembly.c') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 39f2dc94390..16ff29a7bb3 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -20,6 +20,7 @@ struct inet_frag_queue { atomic_t refcnt; struct timer_list timer; /* when will this queue expire? */ struct sk_buff *fragments; /* list of received fragments */ + struct sk_buff *fragments_tail; ktime_t stamp; int len; /* total length of orig datagram */ int meat; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 858d34648ee..dd0dbf0c6b7 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -314,6 +314,7 @@ static int ip_frag_reinit(struct ipq *qp) qp->q.len = 0; qp->q.meat = 0; qp->q.fragments = NULL; + qp->q.fragments_tail = NULL; qp->iif = 0; return 0; @@ -386,6 +387,11 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) * in the chain of fragments so far. We must know where to put * this fragment, right? */ + prev = qp->q.fragments_tail; + if (!prev || FRAG_CB(prev)->offset < offset) { + next = NULL; + goto found; + } prev = NULL; for (next = qp->q.fragments; next != NULL; next = next->next) { if (FRAG_CB(next)->offset >= offset) @@ -393,6 +399,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) prev = next; } +found: /* We found where to put this one. Check for overlap with * preceding fragment, and, if needed, align things so that * any overlaps are eliminated. @@ -451,6 +458,8 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) /* Insert this fragment in the chain of fragments. */ skb->next = next; + if (!next) + qp->q.fragments_tail = skb; if (prev) prev->next = skb; else @@ -504,6 +513,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, goto out_nomem; fp->next = head->next; + if (!fp->next) + qp->q.fragments_tail = fp; prev->next = fp; skb_morph(head, qp->q.fragments); @@ -574,6 +585,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, iph->tot_len = htons(len); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS); qp->q.fragments = NULL; + qp->q.fragments_tail = NULL; return 0; out_nomem: diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 0b97230a325..545c4141b75 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -333,6 +333,11 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, * in the chain of fragments so far. We must know where to put * this fragment, right? */ + prev = fq->q.fragments_tail; + if (!prev || FRAG6_CB(prev)->offset < offset) { + next = NULL; + goto found; + } prev = NULL; for(next = fq->q.fragments; next != NULL; next = next->next) { if (FRAG6_CB(next)->offset >= offset) @@ -340,6 +345,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, prev = next; } +found: /* We found where to put this one. Check for overlap with * preceding fragment, and, if needed, align things so that * any overlaps are eliminated. @@ -397,6 +403,8 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, /* Insert this fragment in the chain of fragments. */ skb->next = next; + if (!next) + fq->q.fragments_tail = skb; if (prev) prev->next = skb; else @@ -463,6 +471,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, goto out_oom; fp->next = head->next; + if (!fp->next) + fq->q.fragments_tail = fp; prev->next = fp; skb_morph(head, fq->q.fragments); @@ -549,6 +559,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); rcu_read_unlock(); fq->q.fragments = NULL; + fq->q.fragments_tail = NULL; return 1; out_oversize: -- cgit v1.2.3