Initial import of modified Linux 2.6.28 tree

Original upstream URL:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git | branch linux-2.6.28.y

1 files changed, 132 insertions, 0 deletions

diff --git a/net/core/request_sock.c b/net/core/request_sock.c
new file mode 100644
index 0000000..7552495
--- /dev/null
+++ b/net/core/request_sock.c
@@ -0,0 +1,132 @@
+/*
+ * NET		Generic infrastructure for Network protocols.
+ *
+ * Authors:	Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ *
+ * 		From code originally in include/net/tcp.h
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+
+#include <net/request_sock.h>
+
+/*
+ * Maximum number of SYN_RECV sockets in queue per LISTEN socket.
+ * One SYN_RECV socket costs about 80bytes on a 32bit machine.
+ * It would be better to replace it with a global counter for all sockets
+ * but then some measure against one socket starving all other sockets
+ * would be needed.
+ *
+ * It was 128 by default. Experiments with real servers show, that
+ * it is absolutely not enough even at 100conn/sec. 256 cures most
+ * of problems. This value is adjusted to 128 for very small machines
+ * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb).
+ * Note : Dont forget somaxconn that may limit backlog too.
+ */
+int sysctl_max_syn_backlog = 256;
+
+int reqsk_queue_alloc(struct request_sock_queue *queue,
+		      unsigned int nr_table_entries)
+{
+	size_t lopt_size = sizeof(struct listen_sock);
+	struct listen_sock *lopt;
+
+	nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog);
+	nr_table_entries = max_t(u32, nr_table_entries, 8);
+	nr_table_entries = roundup_pow_of_two(nr_table_entries + 1);
+	lopt_size += nr_table_entries * sizeof(struct request_sock *);
+	if (lopt_size > PAGE_SIZE)
+		lopt = __vmalloc(lopt_size,
+			GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+			PAGE_KERNEL);
+	else
+		lopt = kzalloc(lopt_size, GFP_KERNEL);
+	if (lopt == NULL)
+		return -ENOMEM;
+
+	for (lopt->max_qlen_log = 3;
+	     (1 << lopt->max_qlen_log) < nr_table_entries;
+	     lopt->max_qlen_log++);
+
+	get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd));
+	rwlock_init(&queue->syn_wait_lock);
+	queue->rskq_accept_head = NULL;
+	lopt->nr_table_entries = nr_table_entries;
+
+	write_lock_bh(&queue->syn_wait_lock);
+	queue->listen_opt = lopt;
+	write_unlock_bh(&queue->syn_wait_lock);
+
+	return 0;
+}
+
+void __reqsk_queue_destroy(struct request_sock_queue *queue)
+{
+	struct listen_sock *lopt;
+	size_t lopt_size;
+
+	/*
+	 * this is an error recovery path only
+	 * no locking needed and the lopt is not NULL
+	 */
+
+	lopt = queue->listen_opt;
+	lopt_size = sizeof(struct listen_sock) +
+		lopt->nr_table_entries * sizeof(struct request_sock *);
+
+	if (lopt_size > PAGE_SIZE)
+		vfree(lopt);
+	else
+		kfree(lopt);
+}
+
+static inline struct listen_sock *reqsk_queue_yank_listen_sk(
+		struct request_sock_queue *queue)
+{
+	struct listen_sock *lopt;
+
+	write_lock_bh(&queue->syn_wait_lock);
+	lopt = queue->listen_opt;
+	queue->listen_opt = NULL;
+	write_unlock_bh(&queue->syn_wait_lock);
+
+	return lopt;
+}
+
+void reqsk_queue_destroy(struct request_sock_queue *queue)
+{
+	/* make all the listen_opt local to us */
+	struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue);
+	size_t lopt_size = sizeof(struct listen_sock) +
+		lopt->nr_table_entries * sizeof(struct request_sock *);
+
+	if (lopt->qlen != 0) {
+		unsigned int i;
+
+		for (i = 0; i < lopt->nr_table_entries; i++) {
+			struct request_sock *req;
+
+			while ((req = lopt->syn_table[i]) != NULL) {
+				lopt->syn_table[i] = req->dl_next;
+				lopt->qlen--;
+				reqsk_free(req);
+			}
+		}
+	}
+
+	WARN_ON(lopt->qlen != 0);
+	if (lopt_size > PAGE_SIZE)
+		vfree(lopt);
+	else
+		kfree(lopt);
+}
+