From b4bf07771faaf959b0a916d35b1b930c030e30a8 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 6 Aug 2013 17:45:03 +0800 Subject: net: move iov_pages() to net/core/iovec.c To let it be reused and reduce code duplication. Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'drivers/net/macvtap.c') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index a98fb0ed6aef..dfec20df17ba 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -698,29 +698,6 @@ static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, return 0; } -static unsigned long iov_pages(const struct iovec *iv, int offset, - unsigned long nr_segs) -{ - unsigned long seg, base; - int pages = 0, len, size; - - while (nr_segs && (offset >= iv->iov_len)) { - offset -= iv->iov_len; - ++iv; - --nr_segs; - } - - for (seg = 0; seg < nr_segs; seg++) { - base = (unsigned long)iv[seg].iov_base + offset; - len = iv[seg].iov_len - offset; - size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; - pages += size; - offset = 0; - } - - return pages; -} - /* Get packet from user space buffer */ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, const struct iovec *iv, unsigned long total_len, -- cgit v1.2.3 From c3bdeb5c7cc073ccf5ff9624642022a8613a956e Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 6 Aug 2013 17:45:04 +0800 Subject: net: move zerocopy_sg_from_iovec() to net/core/datagram.c To let it be reused and reduce code duplication. Also document this function. Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 80 --------------------------------------------------- 1 file changed, 80 deletions(-) (limited to 'drivers/net/macvtap.c') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index dfec20df17ba..182364abfa35 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -536,86 +536,6 @@ static inline struct sk_buff *macvtap_alloc_skb(struct sock *sk, size_t prepad, return skb; } -/* set skb frags from iovec, this can move to core network code for reuse */ -static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, - int offset, size_t count) -{ - int len = iov_length(from, count) - offset; - int copy = skb_headlen(skb); - int size, offset1 = 0; - int i = 0; - - /* Skip over from offset */ - while (count && (offset >= from->iov_len)) { - offset -= from->iov_len; - ++from; - --count; - } - - /* copy up to skb headlen */ - while (count && (copy > 0)) { - size = min_t(unsigned int, copy, from->iov_len - offset); - if (copy_from_user(skb->data + offset1, from->iov_base + offset, - size)) - return -EFAULT; - if (copy > size) { - ++from; - --count; - offset = 0; - } else - offset += size; - copy -= size; - offset1 += size; - } - - if (len == offset1) - return 0; - - while (count--) { - struct page *page[MAX_SKB_FRAGS]; - int num_pages; - unsigned long base; - unsigned long truesize; - - len = from->iov_len - offset; - if (!len) { - offset = 0; - ++from; - continue; - } - base = (unsigned long)from->iov_base + offset; - size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; - if (i + size > MAX_SKB_FRAGS) - return -EMSGSIZE; - num_pages = get_user_pages_fast(base, size, 0, &page[i]); - if (num_pages != size) { - int j; - - for (j = 0; j < num_pages; j++) - put_page(page[i + j]); - return -EFAULT; - } - truesize = size * PAGE_SIZE; - skb->data_len += len; - skb->len += len; - skb->truesize += truesize; - atomic_add(truesize, &skb->sk->sk_wmem_alloc); - while (len) { - int off = base & ~PAGE_MASK; - int size = min_t(int, len, PAGE_SIZE - off); - __skb_fill_page_desc(skb, i, page[i], off, size); - skb_shinfo(skb)->nr_frags++; - /* increase sk_wmem_alloc */ - base += size; - len -= size; - i++; - } - offset = 0; - ++from; - } - return 0; -} - /* * macvtap_skb_from_vnet_hdr and macvtap_skb_to_vnet_hdr should * be shared with the tun/tap driver. -- cgit v1.2.3 From 28d6427109d13b0f447cba5761f88d3548e83605 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Aug 2013 14:38:47 -0700 Subject: net: attempt high order allocations in sock_alloc_send_pskb() Adding paged frags skbs to af_unix sockets introduced a performance regression on large sends because of additional page allocations, even if each skb could carry at least 100% more payload than before. We can instruct sock_alloc_send_pskb() to attempt high order allocations. Most of the time, it does a single page allocation instead of 8. I added an additional parameter to sock_alloc_send_pskb() to let other users to opt-in for this new feature on followup patches. Tested: Before patch : $ netperf -t STREAM_STREAM STREAM STREAM TEST Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 2304 212992 212992 10.00 46861.15 After patch : $ netperf -t STREAM_STREAM STREAM STREAM TEST Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 2304 212992 212992 10.00 57981.11 Signed-off-by: Eric Dumazet Cc: David Rientjes Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/macvtap.c') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 182364abfa35..8f6056d9ba97 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -524,7 +524,7 @@ static inline struct sk_buff *macvtap_alloc_skb(struct sock *sk, size_t prepad, linear = len; skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, - err); + err, 0); if (!skb) return NULL; -- cgit v1.2.3