[NET]: Size listen hash tables using backlog hint

We currently allocate a fixed size (TCP_SYNQ_HSIZE=512) slots hash table for
each LISTEN socket, regardless of various parameters (listen backlog for
example)

On x86_64, this means order-1 allocations (might fail), even for 'small'
sockets, expecting few connections. On the contrary, a huge server wanting a
backlog of 50000 is slowed down a bit because of this fixed limit.

This patch makes the sizing of listen hash table a dynamic parameter,
depending of :
- net.core.somaxconn tunable (default is 128)
- net.ipv4.tcp_max_syn_backlog tunable (default : 256, 1024 or 128)
- backlog value given by user application  (2nd parameter of listen())

For large allocations (bigger than PAGE_SIZE), we use vmalloc() instead of
kmalloc().

We still limit memory allocation with the two existing tunables (somaxconn &
tcp_max_syn_backlog). So for standard setups, this patch actually reduce RAM
usage.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 4 insertions, 5 deletions

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index f743a941a4f2..b5b023e79e5f 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -28,8 +28,8 @@ struct proto;
 
 struct request_sock_ops {
         int             family;
-        kmem_cache_t    *slab;
         int             obj_size;
+        kmem_cache_t    *slab;
         int             (*rtx_syn_ack)(struct sock *sk,
                                        struct request_sock *req,
                                        struct dst_entry *dst);
@@ -51,13 +51,13 @@ struct request_sock {
         u32                             rcv_wnd;          /* rcv_wnd offered first time */
         u32                             ts_recent;
         unsigned long                   expires;
-        struct request_sock_ops         *rsk_ops;
+        const struct request_sock_ops   *rsk_ops;
         struct sock                     *sk;
         u32                             secid;
         u32                             peer_secid;
 };
 
-static inline struct request_sock *reqsk_alloc(struct request_sock_ops *ops)
+static inline struct request_sock *reqsk_alloc(const struct request_sock_ops *ops)
 {
         struct request_sock *req = kmem_cache_alloc(ops->slab, SLAB_ATOMIC);
 
@@ -121,7 +121,7 @@ struct request_sock_queue {
 };
 
 extern int reqsk_queue_alloc(struct request_sock_queue *queue,
-                             const int nr_table_entries);
+                             unsigned int nr_table_entries);
 
 static inline struct listen_sock *reqsk_queue_yank_listen_sk(struct request_sock_queue *queue)
 {
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7a093d0aa0fe..246916c2321e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -138,7 +138,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define MAX_TCP_SYNCNT          127
 
 #define TCP_SYNQ_INTERVAL       (HZ/5)  /* Period of SYNACK timer */
-#define TCP_SYNQ_HSIZE          512     /* Size of SYNACK hash table */
 
 #define TCP_PAWS_24DAYS (60 * 60 * 24 * 24)
 #define TCP_PAWS_MSL    60              /* Per-host timestamps are invalidated