diff -upr linux-2.6.26/include/linux/mm_types.h linux-2.6.26/include/linux/mm_types.h --- linux-2.6.26/include/linux/mm_types.h 2008-07-14 01:51:29.000000000 +0400 +++ linux-2.6.26/include/linux/mm_types.h 2008-07-22 20:30:21.000000000 +0400 @@ -91,6 +91,18 @@ struct page { void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ + +#if defined(CONFIG_TCP_ZERO_COPY_TRANSFER_COMPLETION_NOTIFICATION) + /* + * Used to implement support for notification on zero-copy TCP transfer + * completion. It might look as not good to have this field here and + * it's better to have it in struct sk_buff, but it would make the code + * much more complicated and fragile, since all skb then would have to + * contain only pages with the same value in this field. + */ + void *net_priv; +#endif + #ifdef CONFIG_CGROUP_MEM_RES_CTLR unsigned long page_cgroup; #endif diff -upr linux-2.6.26/include/linux/net.h linux-2.6.26/include/linux/net.h --- linux-2.6.26/include/linux/net.h 2008-07-14 01:51:29.000000000 +0400 +++ linux-2.6.26/include/linux/net.h 2008-07-29 20:48:07.000000000 +0400 @@ -60,6 +60,7 @@ typedef enum { #ifdef __KERNEL__ #include #include +#include #define SOCK_ASYNC_NOSPACE 0 #define SOCK_ASYNC_WAITDATA 1 @@ -342,5 +343,44 @@ extern int net_msg_cost; extern int net_msg_burst; #endif +#if defined(CONFIG_TCP_ZERO_COPY_TRANSFER_COMPLETION_NOTIFICATION) +/* Support for notification on zero-copy TCP transfer completion */ +typedef void (*net_get_page_callback_t)(struct page *page); +typedef void (*net_put_page_callback_t)(struct page *page); + +extern net_get_page_callback_t net_get_page_callback; +extern net_put_page_callback_t net_put_page_callback; + +extern int net_set_get_put_page_callbacks( + net_get_page_callback_t get_callback, + net_put_page_callback_t put_callback); + +/* + * See comment for net_set_get_put_page_callbacks() why those functions + * don't need any protection. + */ +static inline void net_get_page(struct page *page) +{ + if (page->net_priv != 0) + net_get_page_callback(page); + get_page(page); +} +static inline void net_put_page(struct page *page) +{ + if (page->net_priv != 0) + net_put_page_callback(page); + put_page(page); +} +#else +static inline void net_get_page(struct page *page) +{ + get_page(page); +} +static inline void net_put_page(struct page *page) +{ + put_page(page); +} +#endif /* CONFIG_TCP_ZERO_COPY_TRANSFER_COMPLETION_NOTIFICATION */ + #endif /* __KERNEL__ */ #endif /* _LINUX_NET_H */ diff -upr linux-2.6.26/net/core/skbuff.c linux-2.6.26/net/core/skbuff.c --- linux-2.6.26/net/core/skbuff.c 2008-07-14 01:51:29.000000000 +0400 +++ linux-2.6.26/net/core/skbuff.c 2008-07-22 20:28:41.000000000 +0400 @@ -321,7 +321,7 @@ static void skb_release_data(struct sk_b if (skb_shinfo(skb)->nr_frags) { int i; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - put_page(skb_shinfo(skb)->frags[i].page); + net_put_page(skb_shinfo(skb)->frags[i].page); } if (skb_shinfo(skb)->frag_list) @@ -655,7 +655,7 @@ struct sk_buff *pskb_copy(struct sk_buff for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; - get_page(skb_shinfo(n)->frags[i].page); + net_get_page(skb_shinfo(n)->frags[i].page); } skb_shinfo(n)->nr_frags = i; } @@ -718,7 +718,7 @@ int pskb_expand_head(struct sk_buff *skb sizeof(struct skb_shared_info)); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - get_page(skb_shinfo(skb)->frags[i].page); + net_get_page(skb_shinfo(skb)->frags[i].page); if (skb_shinfo(skb)->frag_list) skb_clone_fraglist(skb); @@ -987,7 +987,7 @@ drop_pages: skb_shinfo(skb)->nr_frags = i; for (; i < nfrags; i++) - put_page(skb_shinfo(skb)->frags[i].page); + net_put_page(skb_shinfo(skb)->frags[i].page); if (skb_shinfo(skb)->frag_list) skb_drop_fraglist(skb); @@ -1156,7 +1156,7 @@ pull_pages: k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { if (skb_shinfo(skb)->frags[i].size <= eat) { - put_page(skb_shinfo(skb)->frags[i].page); + net_put_page(skb_shinfo(skb)->frags[i].page); eat -= skb_shinfo(skb)->frags[i].size; } else { skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; @@ -1944,7 +1944,7 @@ static inline void skb_split_no_header(s * where splitting is expensive. * 2. Split is accurately. We make this. */ - get_page(skb_shinfo(skb)->frags[i].page); + net_get_page(skb_shinfo(skb)->frags[i].page); skb_shinfo(skb1)->frags[0].page_offset += len - pos; skb_shinfo(skb1)->frags[0].size -= len - pos; skb_shinfo(skb)->frags[i].size = len - pos; @@ -2319,7 +2319,7 @@ struct sk_buff *skb_segment(struct sk_bu BUG_ON(i >= nfrags); *frag = skb_shinfo(skb)->frags[i]; - get_page(frag->page); + net_get_page(frag->page); size = frag->size; if (pos < offset) { diff -upr linux-2.6.26/net/ipv4/ip_output.c linux-2.6.26/net/ipv4/ip_output.c --- linux-2.6.26/net/ipv4/ip_output.c 2008-07-14 01:51:29.000000000 +0400 +++ linux-2.6.26/net/ipv4/ip_output.c 2008-07-22 20:28:41.000000000 +0400 @@ -1009,7 +1009,7 @@ alloc_new_skb: err = -EMSGSIZE; goto error; } - get_page(page); + net_get_page(page); skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0); frag = &skb_shinfo(skb)->frags[i]; } @@ -1167,7 +1167,7 @@ ssize_t ip_append_page(struct sock *sk, if (skb_can_coalesce(skb, i, page, offset)) { skb_shinfo(skb)->frags[i-1].size += len; } else if (i < MAX_SKB_FRAGS) { - get_page(page); + net_get_page(page); skb_fill_page_desc(skb, i, page, offset, len); } else { err = -EMSGSIZE; diff -upr linux-2.6.26/net/ipv4/Makefile linux-2.6.26/net/ipv4/Makefile --- linux-2.6.26/net/ipv4/Makefile 2008-07-14 01:51:29.000000000 +0400 +++ linux-2.6.26/net/ipv4/Makefile 2008-07-22 20:35:05.000000000 +0400 @@ -50,6 +50,7 @@ obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o +obj-$(CONFIG_TCP_ZERO_COPY_TRANSFER_COMPLETION_NOTIFICATION) += tcp_zero_copy.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o diff -upr linux-2.6.26/net/ipv4/tcp.c linux-2.6.26/net/ipv4/tcp.c --- linux-2.6.26/net/ipv4/tcp.c 2008-07-14 01:51:29.000000000 +0400 +++ linux-2.6.26/net/ipv4/tcp.c 2008-07-22 20:28:41.000000000 +0400 @@ -716,7 +716,7 @@ new_segment: if (can_coalesce) { skb_shinfo(skb)->frags[i - 1].size += copy; } else { - get_page(page); + net_get_page(page); skb_fill_page_desc(skb, i, page, offset, copy); } @@ -921,7 +921,7 @@ new_segment: goto new_segment; } else if (page) { if (off == PAGE_SIZE) { - put_page(page); + net_put_page(page); TCP_PAGE(sk) = page = NULL; off = 0; } @@ -962,9 +962,9 @@ new_segment: } else { skb_fill_page_desc(skb, i, page, off, copy); if (TCP_PAGE(sk)) { - get_page(page); + net_get_page(page); } else if (off + copy < PAGE_SIZE) { - get_page(page); + net_get_page(page); TCP_PAGE(sk) = page; } } diff -upr linux-2.6.26/net/ipv4/tcp_output.c linux-2.6.26/net/ipv4/tcp_output.c --- linux-2.6.26/net/ipv4/tcp_output.c 2008-07-14 01:51:29.000000000 +0400 +++ linux-2.6.26/net/ipv4/tcp_output.c 2008-07-22 20:28:41.000000000 +0400 @@ -805,7 +805,7 @@ static void __pskb_trim_head(struct sk_b k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { if (skb_shinfo(skb)->frags[i].size <= eat) { - put_page(skb_shinfo(skb)->frags[i].page); + net_put_page(skb_shinfo(skb)->frags[i].page); eat -= skb_shinfo(skb)->frags[i].size; } else { skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; diff -upr linux-2.6.26/net/ipv4/tcp_zero_copy.c linux-2.6.26/net/ipv4/tcp_zero_copy.c --- linux-2.6.26/net/ipv4/tcp_zero_copy.c 2008-07-22 20:12:35.000000000 +0400 +++ linux-2.6.26/net/ipv4/tcp_zero_copy.c 2008-07-31 21:21:13.000000000 +0400 @@ -0,0 +1,49 @@ +/* + * Support routines for TCP zero copy transmit + * + * Created by Vladislav Bolkhovitin + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include + +net_get_page_callback_t net_get_page_callback __read_mostly; +EXPORT_SYMBOL(net_get_page_callback); + +net_put_page_callback_t net_put_page_callback __read_mostly; +EXPORT_SYMBOL(net_put_page_callback); + +/* + * Caller of this function must ensure that at the moment when it's called + * there are no pages in the system with net_priv field set to non-zero + * value. Hence, this function, as well as net_get_page() and net_put_page(), + * don't need any protection. + */ +int net_set_get_put_page_callbacks( + net_get_page_callback_t get_callback, + net_put_page_callback_t put_callback) +{ + int res = 0; + + if ((net_get_page_callback != NULL) && (get_callback != NULL) && + (net_get_page_callback != get_callback)) { + res = -EBUSY; + goto out; + } + + if ((net_put_page_callback != NULL) && (put_callback != NULL) && + (net_put_page_callback != put_callback)) { + res = -EBUSY; + goto out; + } + + net_get_page_callback = get_callback; + net_put_page_callback = put_callback; + +out: + return res; +} +EXPORT_SYMBOL(net_set_get_put_page_callbacks); diff -upr linux-2.6.26/net/ipv6/ip6_output.c linux-2.6.26/net/ipv6/ip6_output.c --- linux-2.6.26/net/ipv6/ip6_output.c 2008-07-14 01:51:29.000000000 +0400 +++ linux-2.6.26/net/ipv6/ip6_output.c 2008-07-22 20:28:41.000000000 +0400 @@ -1336,7 +1336,7 @@ alloc_new_skb: err = -EMSGSIZE; goto error; } - get_page(page); + net_get_page(page); skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0); frag = &skb_shinfo(skb)->frags[i]; } diff -upr linux-2.6.26/net/Kconfig linux-2.6.26/net/Kconfig --- linux-2.6.26/net/Kconfig 2008-07-14 01:51:29.000000000 +0400 +++ linux-2.6.26/net/Kconfig 2008-07-29 21:15:39.000000000 +0400 @@ -62,6 +62,18 @@ config INET Short answer: say Y. +config TCP_ZERO_COPY_TRANSFER_COMPLETION_NOTIFICATION + bool "TCP/IP zero-copy transfer completion notification" + depends on INET + default SCST_ISCSI + ---help--- + Adds support for sending a notification upon completion of a + zero-copy TCP/IP transfer. This can speed up certain TCP/IP + software. Currently this is only used by the iSCSI target driver + iSCSI-SCST. + + If unsure, say N. + if INET source "net/ipv4/Kconfig" source "net/ipv6/Kconfig"