scst/iscsi-scst/kernel/patches/put_page_callback-3.18.patch

Subject: [PATCH] put_page_callback

---
 drivers/block/drbd/drbd_receiver.c |  2 +-
 include/linux/mm_types.h           | 11 +++++++++
 include/linux/net.h                | 40 ++++++++++++++++++++++++++++++
 include/linux/skbuff.h             |  4 +--
 net/Kconfig                        | 12 +++++++++
 net/ceph/pagevec.c                 |  2 +-
 net/core/skbuff.c                  | 14 +++++------
 net/core/sock.c                    |  4 +--
 net/ipv4/Makefile                  |  1 +
 net/ipv4/ip_output.c               |  4 +--
 net/ipv4/tcp.c                     |  4 +--
 net/ipv4/tcp_zero_copy.c           | 50 ++++++++++++++++++++++++++++++++++++++
 net/ipv6/ip6_output.c              |  2 +-
 13 files changed, 132 insertions(+), 18 deletions(-)
 create mode 100644 net/ipv4/tcp_zero_copy.c

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 6960fb0..8fa4016 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -132,7 +132,7 @@ static int page_chain_free(struct page *page)
 	struct page *tmp;
 	int i = 0;
 	page_chain_for_each_safe(page, tmp) {
-		put_page(page);
+		net_put_page(page);
 		++i;
 	}
 	return i;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e0b286..5706a4d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -196,6 +196,17 @@ struct page {
 #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
 	int _last_cpupid;
 #endif
+
+#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
 }
 /*
  * The struct page can be forced to be double word aligned so that atomic ops
diff --git a/include/linux/net.h b/include/linux/net.h
index 17d8339..f784384 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -19,6 +19,7 @@
 #define _LINUX_NET_H
 
 #include <linux/stringify.h>
+#include <linux/mm.h>
 #include <linux/random.h>
 #include <linux/wait.h>
 #include <linux/fcntl.h>	/* For O_CLOEXEC and O_NONBLOCK */
@@ -285,6 +286,45 @@ int kernel_sendpage(struct socket *sock, struct page *page, int offset,
 int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg);
 int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how);
 
+#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 */
+
 #define MODULE_ALIAS_NETPROTO(proto) \
 	MODULE_ALIAS("net-pf-" __stringify(proto))
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6c8b6f6..edf6195 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2250,7 +2250,7 @@ static inline struct page *skb_frag_page(const skb_frag_t *frag)
  */
 static inline void __skb_frag_ref(skb_frag_t *frag)
 {
-	get_page(skb_frag_page(frag));
+	net_get_page(skb_frag_page(frag));
 }
 
 /**
@@ -2273,7 +2273,7 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f)
  */
 static inline void __skb_frag_unref(skb_frag_t *frag)
 {
-	put_page(skb_frag_page(frag));
+	net_put_page(skb_frag_page(frag));
 }
 
 /**
diff --git a/net/Kconfig b/net/Kconfig
index 99815b5..ac45213 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -76,6 +76,18 @@ 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"
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 5550130..993f710 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -51,7 +51,7 @@ void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty)
 	for (i = 0; i < num_pages; i++) {
 		if (dirty)
 			set_page_dirty_lock(pages[i]);
-		put_page(pages[i]);
+		net_put_page(pages[i]);
 	}
 	if (is_vmalloc_addr(pages))
 		vfree(pages);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 32e31c2..6eb3a9e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -437,7 +437,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 		if (likely(data)) {
 			skb = build_skb(data, fragsz);
 			if (unlikely(!skb))
-				put_page(virt_to_head_page(data));
+				net_put_page(virt_to_head_page(data));
 		}
 	} else {
 		skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
@@ -495,7 +495,7 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 static void skb_free_head(struct sk_buff *skb)
 {
 	if (skb->head_frag)
-		put_page(virt_to_head_page(skb->head));
+		net_put_page(virt_to_head_page(skb->head));
 	else
 		kfree(skb->head);
 }
@@ -822,7 +822,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 		if (!page) {
 			while (head) {
 				struct page *next = (struct page *)page_private(head);
-				put_page(head);
+				net_put_page(head);
 				head = next;
 			}
 			return -ENOMEM;
@@ -1669,7 +1669,7 @@ EXPORT_SYMBOL(skb_copy_bits);
  */
 static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
 {
-	put_page(spd->pages[i]);
+	net_put_page(spd->pages[i]);
 }
 
 static struct page *linear_to_page(struct page *page, unsigned int *len,
@@ -1722,7 +1722,7 @@ static bool spd_fill_page(struct splice_pipe_desc *spd,
 		spd->partial[spd->nr_pages - 1].len += *len;
 		return false;
 	}
-	get_page(page);
+	net_get_page(page);
 	spd->pages[spd->nr_pages] = page;
 	spd->partial[spd->nr_pages].len = *len;
 	spd->partial[spd->nr_pages].offset = offset;
@@ -2181,7 +2181,7 @@ skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
 			page = virt_to_head_page(from->head);
 			offset = from->data - (unsigned char *)page_address(page);
 			__skb_fill_page_desc(to, 0, page, offset, plen);
-			get_page(page);
+			net_get_page(page);
 			j = 1;
 			len -= plen;
 		}
@@ -2835,7 +2835,7 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
 				   copy);
 		frg_cnt++;
 		pfrag->offset += copy;
-		get_page(pfrag->page);
+		net_get_page(pfrag->page);
 
 		skb->truesize += copy;
 		atomic_add(copy, &sk->sk_wmem_alloc);
diff --git a/net/core/sock.c b/net/core/sock.c
index 15e0c67..e8ea0df 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1830,7 +1830,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
 		}
 		if (pfrag->offset + sz <= pfrag->size)
 			return true;
-		put_page(pfrag->page);
+		net_put_page(pfrag->page);
 	}
 
 	pfrag->offset = 0;
@@ -2581,7 +2581,7 @@ void sk_common_release(struct sock *sk)
 	sk_refcnt_debug_release(sk);
 
 	if (sk->sk_frag.page) {
-		put_page(sk->sk_frag.page);
+		net_put_page(sk->sk_frag.page);
 		sk->sk_frag.page = NULL;
 	}
 
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 518c04e..4072a87 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -57,6 +57,7 @@ obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
 obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
 obj-$(CONFIG_GENEVE) += geneve.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 xfrm4_protocol.o
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index bc6471d..ab9e262 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1051,7 +1051,7 @@ alloc_new_skb:
 				__skb_fill_page_desc(skb, i, pfrag->page,
 						     pfrag->offset, 0);
 				skb_shinfo(skb)->nr_frags = ++i;
-				get_page(pfrag->page);
+				net_get_page(pfrag->page);
 			}
 			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 			if (getfrag(from,
@@ -1276,7 +1276,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 		if (skb_can_coalesce(skb, i, page, offset)) {
 			skb_frag_size_add(&skb_shinfo(skb)->frags[i-1], 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 --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 38c2bcb..f089a7a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -949,7 +949,7 @@ new_segment:
 		if (can_coalesce) {
 			skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 		} else {
-			get_page(page);
+			net_get_page(page);
 			skb_fill_page_desc(skb, i, page, offset, copy);
 		}
 		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
@@ -1250,7 +1250,7 @@ new_segment:
 				} else {
 					skb_fill_page_desc(skb, i, pfrag->page,
 							   pfrag->offset, copy);
-					get_page(pfrag->page);
+					net_get_page(pfrag->page);
 				}
 				pfrag->offset += copy;
 			}
diff --git a/net/ipv4/tcp_zero_copy.c b/net/ipv4/tcp_zero_copy.c
new file mode 100644
index 0000000..430147e
--- /dev/null
+++ b/net/ipv4/tcp_zero_copy.c
@@ -0,0 +1,50 @@
+/*
+ *	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 <linux/export.h>
+#include <linux/skbuff.h>
+
+net_get_page_callback_t net_get_page_callback __read_mostly;
+EXPORT_SYMBOL_GPL(net_get_page_callback);
+
+net_put_page_callback_t net_put_page_callback __read_mostly;
+EXPORT_SYMBOL_GPL(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_GPL(net_set_get_put_page_callbacks);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 8e950c2..8cb4760 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1472,7 +1472,7 @@ alloc_new_skb:
 				__skb_fill_page_desc(skb, i, pfrag->page,
 						     pfrag->offset, 0);
 				skb_shinfo(skb)->nr_frags = ++i;
-				get_page(pfrag->page);
+				net_get_page(pfrag->page);
 			}
 			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 			if (getfrag(from,
-- 
2.1.2