PKT_SCHED related fixes and a meta ematch completion

PATCH In review Thomas Graf 2 participants 6 messages Jun 3, 2005 – Jun 6, 2005

Subsystems (3)

Networking Network drivers Traffic control (tc)

lore

Share & tools

lore

Thomas Graf

author

2005-06-03 21:12 UTC #0 lore raw

PATCH 1/1 PKT_SCHED related fixes and a meta ematch completion

Dave,

The following patchset fixes some serious bugs that prevent the basic classifier and the meta ematch from working properly. Patch 2 adds a few new meta collectors for socket attribtues which I'd like to have in 2.6.12 as well. If you think this is too intrusive (it isn't ;->) I'll resend patch 4 with offsets fixed.

Thanks.

Thomas Graf

author

2005-06-03 21:12 UTC #1 lore raw

PATCH 1/4 Fix typo in NET_EMATCH_STACK help text

Spotted by Geert Uytterhoeven <[email protected]>.

Signed-off-by Thomas Graf <[email protected]>

net/sched/Kconfig +1 -1

Index: ematch/net/sched/Kconfig
===================================================================
@@ -405,7 +405,7 @@ config NET_EMATCH_STACK
 	---help---
 	  Size of the local stack variable used while evaluating the tree of
 	  ematches. Limits the depth of the tree, i.e. the number of
-	  encapsulated precedences. Every level requires 4 bytes of addtional
+	  encapsulated precedences. Every level requires 4 bytes of additional
 	  stack space.
 
 config NET_EMATCH_CMP

Thomas Graf

author

2005-06-03 21:12 UTC #2 lore raw

PATCH 2/4 Allow socket attributes to be matched on via meta ematch

In reply to Thomas Graf

Adds meta collectors for all socket attributes that make sense to be filtered upon. Some of them are only useful for debugging but having them doesn't hurt.

Signed-off-by Thomas Graf <[email protected]>

net/sched/em_meta.c +267 ~~-24~~

Index: ematch/net/sched/em_meta.c
===================================================================
@@ -32,7 +32,7 @@
  * 	      +-----------+                           +-----------+
  * 	            |                                       |
  * 	            ---> meta_ops[INT][INDEV](...)          |
- *                            |                            |
+ *	                      |                             |
  * 	            -----------                             |
  * 	            V                                       V
  * 	      +-----------+                           +-----------+

@@ -70,6 +70,7 @@
 #include <net/dst.h>
 #include <net/route.h>
 #include <net/pkt_cls.h>
+#include <net/sock.h>
 
 struct meta_obj
 {

@@ -284,6 +285,214 @@ META_COLLECTOR(int_rtiif)
 }
 
 /**************************************************************************
+ * Socket Attributes
+ **************************************************************************/
+
+#define SKIP_NONLOCAL(skb)			\
+	if (unlikely(skb->sk == NULL)) {	\
+		*err = -1;			\
+		return;				\
+	}
+
+META_COLLECTOR(int_sk_family)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_family;
+}
+
+META_COLLECTOR(int_sk_state)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_state;
+}
+
+META_COLLECTOR(int_sk_reuse)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_reuse;
+}
+
+META_COLLECTOR(int_sk_bound_if)
+{
+	SKIP_NONLOCAL(skb);
+	/* No error if bound_dev_if is 0, legal userspace check */
+	dst->value = skb->sk->sk_bound_dev_if;
+}
+
+META_COLLECTOR(var_sk_bound_if)
+{
+	SKIP_NONLOCAL(skb);
+
+	 if (skb->sk->sk_bound_dev_if == 0) {
+		dst->value = (unsigned long) "any";
+		dst->len = 3;
+	 } else  {
+		struct net_device *dev;
+		
+		dev = dev_get_by_index(skb->sk->sk_bound_dev_if);
+		*err = var_dev(dev, dst);
+		if (dev)
+			dev_put(dev);
+	 }
+}
+
+META_COLLECTOR(int_sk_refcnt)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = atomic_read(&skb->sk->sk_refcnt);
+}
+
+META_COLLECTOR(int_sk_rcvbuf)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_rcvbuf;
+}
+
+META_COLLECTOR(int_sk_shutdown)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_shutdown;
+}
+
+META_COLLECTOR(int_sk_proto)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_protocol;
+}
+
+META_COLLECTOR(int_sk_type)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_type;
+}
+
+META_COLLECTOR(int_sk_rmem_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = atomic_read(&skb->sk->sk_rmem_alloc);
+}
+
+META_COLLECTOR(int_sk_wmem_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = atomic_read(&skb->sk->sk_wmem_alloc);
+}
+
+META_COLLECTOR(int_sk_omem_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = atomic_read(&skb->sk->sk_omem_alloc);
+}
+
+META_COLLECTOR(int_sk_rcv_qlen)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_receive_queue.qlen;
+}
+
+META_COLLECTOR(int_sk_snd_qlen)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_write_queue.qlen;
+}
+
+META_COLLECTOR(int_sk_wmem_queued)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_wmem_queued;
+}
+
+META_COLLECTOR(int_sk_fwd_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_forward_alloc;
+}
+
+META_COLLECTOR(int_sk_sndbuf)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_sndbuf;
+}
+
+META_COLLECTOR(int_sk_alloc)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_allocation;
+}
+
+META_COLLECTOR(int_sk_route_caps)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_route_caps;
+}
+
+META_COLLECTOR(int_sk_hashent)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_hashent;
+}
+
+META_COLLECTOR(int_sk_lingertime)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_lingertime / HZ;
+}
+
+META_COLLECTOR(int_sk_err_qlen)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_error_queue.qlen;
+}
+
+META_COLLECTOR(int_sk_ack_bl)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_ack_backlog;
+}
+
+META_COLLECTOR(int_sk_max_ack_bl)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_max_ack_backlog;
+}
+
+META_COLLECTOR(int_sk_prio)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_priority;
+}
+
+META_COLLECTOR(int_sk_rcvlowat)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_rcvlowat;
+}
+
+META_COLLECTOR(int_sk_rcvtimeo)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_rcvtimeo / HZ;
+}
+
+META_COLLECTOR(int_sk_sndtimeo)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_sndtimeo / HZ;
+}
+
+META_COLLECTOR(int_sk_sendmsg_off)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_sndmsg_off;
+}
+
+META_COLLECTOR(int_sk_write_pend)
+{
+	SKIP_NONLOCAL(skb);
+	dst->value = skb->sk->sk_write_pending;
+}
+
+/**************************************************************************
  * Meta value collectors assignment table
  **************************************************************************/

@@ -293,41 +502,75 @@ struct meta_ops
 			       struct meta_value *, struct meta_obj *, int *);
 };
 
+#define META_ID(name) TCF_META_ID_##name
+#define META_FUNC(name) { .get = meta_##name }
+
 /* Meta value operations table listing all meta value collectors and
  * assigns them to a type and meta id. */
 static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = {
 	[TCF_META_TYPE_VAR] = {
-		[TCF_META_ID_DEV]	= { .get = meta_var_dev },
-		[TCF_META_ID_INDEV]	= { .get = meta_var_indev },
-		[TCF_META_ID_REALDEV]	= { .get = meta_var_realdev }
+		[META_ID(DEV)]			= META_FUNC(var_dev),
+		[META_ID(INDEV)]		= META_FUNC(var_indev),
+		[META_ID(REALDEV)]		= META_FUNC(var_realdev),
+		[META_ID(SK_BOUND_IF)] 		= META_FUNC(var_sk_bound_if),
 	},
 	[TCF_META_TYPE_INT] = {
-		[TCF_META_ID_RANDOM]	= { .get = meta_int_random },
-		[TCF_META_ID_LOADAVG_0]	= { .get = meta_int_loadavg_0 },
-		[TCF_META_ID_LOADAVG_1]	= { .get = meta_int_loadavg_1 },
-		[TCF_META_ID_LOADAVG_2]	= { .get = meta_int_loadavg_2 },
-		[TCF_META_ID_DEV]	= { .get = meta_int_dev },
-		[TCF_META_ID_INDEV]	= { .get = meta_int_indev },
-		[TCF_META_ID_REALDEV]	= { .get = meta_int_realdev },
-		[TCF_META_ID_PRIORITY]	= { .get = meta_int_priority },
-		[TCF_META_ID_PROTOCOL]	= { .get = meta_int_protocol },
-		[TCF_META_ID_SECURITY]	= { .get = meta_int_security },
-		[TCF_META_ID_PKTTYPE]	= { .get = meta_int_pkttype },
-		[TCF_META_ID_PKTLEN]	= { .get = meta_int_pktlen },
-		[TCF_META_ID_DATALEN]	= { .get = meta_int_datalen },
-		[TCF_META_ID_MACLEN]	= { .get = meta_int_maclen },
+		[META_ID(RANDOM)]		= META_FUNC(int_random),
+		[META_ID(LOADAVG_0)]		= META_FUNC(int_loadavg_0),
+		[META_ID(LOADAVG_1)]		= META_FUNC(int_loadavg_1),
+		[META_ID(LOADAVG_2)]		= META_FUNC(int_loadavg_2),
+		[META_ID(DEV)]			= META_FUNC(int_dev),
+		[META_ID(INDEV)]		= META_FUNC(int_indev),
+		[META_ID(REALDEV)]		= META_FUNC(int_realdev),
+		[META_ID(PRIORITY)]		= META_FUNC(int_priority),
+		[META_ID(PROTOCOL)]		= META_FUNC(int_protocol),
+		[META_ID(SECURITY)]		= META_FUNC(int_security),
+		[META_ID(PKTTYPE)]		= META_FUNC(int_pkttype),
+		[META_ID(PKTLEN)]		= META_FUNC(int_pktlen),
+		[META_ID(DATALEN)]		= META_FUNC(int_datalen),
+		[META_ID(MACLEN)]		= META_FUNC(int_maclen),
 #ifdef CONFIG_NETFILTER
-		[TCF_META_ID_NFMARK]	= { .get = meta_int_nfmark },
+		[META_ID(NFMARK)]		= META_FUNC(int_nfmark),
 #endif
-		[TCF_META_ID_TCINDEX]	= { .get = meta_int_tcindex },
+		[META_ID(TCINDEX)]		= META_FUNC(int_tcindex),
 #ifdef CONFIG_NET_CLS_ACT
-		[TCF_META_ID_TCVERDICT]	= { .get = meta_int_tcverd },
-		[TCF_META_ID_TCCLASSID]	= { .get = meta_int_tcclassid },
+		[META_ID(TCVERDICT)]		= META_FUNC(int_tcverd),
+		[META_ID(TCCLASSID)]		= META_FUNC(int_tcclassid),
 #endif
 #ifdef CONFIG_NET_CLS_ROUTE
-		[TCF_META_ID_RTCLASSID]	= { .get = meta_int_rtclassid },
+		[META_ID(RTCLASSID)]		= META_FUNC(int_rtclassid),
 #endif
-		[TCF_META_ID_RTIIF]	= { .get = meta_int_rtiif }
+		[META_ID(RTIIF)]		= META_FUNC(int_rtiif),
+		[META_ID(SK_FAMILY)]		= META_FUNC(int_sk_family),
+		[META_ID(SK_STATE)]		= META_FUNC(int_sk_state),
+		[META_ID(SK_REUSE)]		= META_FUNC(int_sk_reuse),
+		[META_ID(SK_BOUND_IF)]		= META_FUNC(int_sk_bound_if),
+		[META_ID(SK_REFCNT)]		= META_FUNC(int_sk_refcnt),
+		[META_ID(SK_RCVBUF)]		= META_FUNC(int_sk_rcvbuf),
+		[META_ID(SK_SNDBUF)]		= META_FUNC(int_sk_sndbuf),
+		[META_ID(SK_SHUTDOWN)]		= META_FUNC(int_sk_shutdown),
+		[META_ID(SK_PROTO)]		= META_FUNC(int_sk_proto),
+		[META_ID(SK_TYPE)]		= META_FUNC(int_sk_type),
+		[META_ID(SK_RMEM_ALLOC)]	= META_FUNC(int_sk_rmem_alloc),
+		[META_ID(SK_WMEM_ALLOC)]	= META_FUNC(int_sk_wmem_alloc),
+		[META_ID(SK_OMEM_ALLOC)]	= META_FUNC(int_sk_omem_alloc),
+		[META_ID(SK_WMEM_QUEUED)]	= META_FUNC(int_sk_wmem_queued),
+		[META_ID(SK_RCV_QLEN)]		= META_FUNC(int_sk_rcv_qlen),
+		[META_ID(SK_SND_QLEN)]		= META_FUNC(int_sk_snd_qlen),
+		[META_ID(SK_ERR_QLEN)]		= META_FUNC(int_sk_err_qlen),
+		[META_ID(SK_FORWARD_ALLOCS)]	= META_FUNC(int_sk_fwd_alloc),
+		[META_ID(SK_ALLOCS)]		= META_FUNC(int_sk_alloc),
+		[META_ID(SK_ROUTE_CAPS)]	= META_FUNC(int_sk_route_caps),
+		[META_ID(SK_HASHENT)]		= META_FUNC(int_sk_hashent),
+		[META_ID(SK_LINGERTIME)]	= META_FUNC(int_sk_lingertime),
+		[META_ID(SK_ACK_BACKLOG)]	= META_FUNC(int_sk_ack_bl),
+		[META_ID(SK_MAX_ACK_BACKLOG)]	= META_FUNC(int_sk_max_ack_bl),
+		[META_ID(SK_PRIO)]		= META_FUNC(int_sk_prio),
+		[META_ID(SK_RCVLOWAT)]		= META_FUNC(int_sk_rcvlowat),
+		[META_ID(SK_RCVTIMEO)]		= META_FUNC(int_sk_rcvtimeo),
+		[META_ID(SK_SNDTIMEO)]		= META_FUNC(int_sk_sndtimeo),
+		[META_ID(SK_SENDMSG_OFF)]	= META_FUNC(int_sk_sendmsg_off),
+		[META_ID(SK_WRITE_PENDING)]	= META_FUNC(int_sk_write_pend),
 	}
 };

include/linux/tc_ematch/tc_em_meta.h +30 -0

Index: ematch/include/linux/tc_ematch/tc_em_meta.h
===================================================================
@@ -56,6 +56,36 @@ enum
 	TCF_META_ID_TCCLASSID,
 	TCF_META_ID_RTCLASSID,
 	TCF_META_ID_RTIIF,
+	TCF_META_ID_SK_FAMILY,
+	TCF_META_ID_SK_STATE,
+	TCF_META_ID_SK_REUSE,
+	TCF_META_ID_SK_BOUND_IF,
+	TCF_META_ID_SK_REFCNT,
+	TCF_META_ID_SK_SHUTDOWN,
+	TCF_META_ID_SK_PROTO,
+	TCF_META_ID_SK_TYPE,
+	TCF_META_ID_SK_RCVBUF,
+	TCF_META_ID_SK_RMEM_ALLOC,
+	TCF_META_ID_SK_WMEM_ALLOC,
+	TCF_META_ID_SK_OMEM_ALLOC,
+	TCF_META_ID_SK_WMEM_QUEUED,
+	TCF_META_ID_SK_RCV_QLEN,
+	TCF_META_ID_SK_SND_QLEN,
+ 	TCF_META_ID_SK_ERR_QLEN,
+	TCF_META_ID_SK_FORWARD_ALLOCS,
+	TCF_META_ID_SK_SNDBUF,
+ 	TCF_META_ID_SK_ALLOCS,
+ 	TCF_META_ID_SK_ROUTE_CAPS,
+ 	TCF_META_ID_SK_HASHENT,
+ 	TCF_META_ID_SK_LINGERTIME,
+ 	TCF_META_ID_SK_ACK_BACKLOG,
+ 	TCF_META_ID_SK_MAX_ACK_BACKLOG,
+ 	TCF_META_ID_SK_PRIO,
+ 	TCF_META_ID_SK_RCVLOWAT,
+ 	TCF_META_ID_SK_RCVTIMEO,
+ 	TCF_META_ID_SK_SNDTIMEO,
+ 	TCF_META_ID_SK_SENDMSG_OFF,
+ 	TCF_META_ID_SK_WRITE_PENDING,
 	__TCF_META_ID_MAX
 };
 #define TCF_META_ID_MAX (__TCF_META_ID_MAX - 1)

Thomas Graf

author

2005-06-03 21:12 UTC #3 lore raw

PATCH 3/4 Dump classification result for basic classifier

In reply to Thomas Graf

Signed-off-by Thomas Graf <[email protected]>

net/sched/cls_basic.c +3 -0

Index: ematch/net/sched/cls_basic.c
===================================================================
@@ -261,6 +261,9 @@ static int basic_dump(struct tcf_proto *
 	rta = (struct rtattr *) b;
 	RTA_PUT(skb, TCA_OPTIONS, 0, NULL);
 
+	if (f->res.classid)
+		RTA_PUT_U32(skb, TCA_BASIC_CLASSID, f->res.classid);
+
 	if (tcf_exts_dump(skb, &f->exts, &basic_ext_map) < 0 ||
 	    tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0)
 		goto rtattr_failure;

Thomas Graf

author

2005-06-03 21:12 UTC #4 lore raw

PATCH 4/4 Fix numeric comparison in meta ematch

In reply to Thomas Graf

This patch is brought to you by the department of applied stupidity.

Signed-off-by Thomas Graf <[email protected]>

net/sched/em_meta.c +2 -2

Index: ematch/net/sched/em_meta.c
===================================================================
@@ -639,9 +639,9 @@ static int meta_int_compare(struct meta_
 	/* Let gcc optimize it, the unlikely is not really based on
 	 * some numbers but jump free code for mismatches seems
 	 * more logical. */
-	if (unlikely(a == b))
+	if (unlikely(a->value == b->value))
 		return 0;
-	else if (a < b)
+	else if (a->value < b->value)
 		return -1;
 	else
 		return 1;

David S. Miller

maintainer

2005-06-06 22:29 UTC #5 lore raw

In reply to Thomas Graf

From: Thomas Graf <[email protected]>
Date: Fri, 03 Jun 2005 23:12:41 +0200

Quoted 5 lines

The following patchset fixes some serious bugs that prevent the basic classifier and the meta ematch from working properly. Patch 2 adds a few new meta collectors for socket attribtues which I'd like to have in 2.6.12 as well. If you think this is too intrusive (it isn't ;->) I'll resend patch 4 with offsets fixed.

I'll try to get these 4 patches into 2.6.12, they all look straight forward and sane to me.

Thanks Thomas.