Merge rsync://rsync.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Documentation/connector/connector.txt

@@ -131,3 +131,47 @@ Netlink itself is not reliable protocol, that means that messages can
 be lost due to memory pressure or process' receiving queue overflowed,
 so caller is warned must be prepared. That is why struct cn_msg [main
 connector's message header] contains u32 seq and u32 ack fields.
+
+/*****************************************/
+Userspace usage.
+/*****************************************/
+2.6.14 has a new netlink socket implementation, which by default does not
+allow to send data to netlink groups other than 1.
+So, if to use netlink socket (for example using connector) 
+with different group number userspace application must subscribe to 
+that group. It can be achieved by following pseudocode:
+
+s = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR);
+
+l_local.nl_family = AF_NETLINK;
+l_local.nl_groups = 12345;
+l_local.nl_pid = 0;
+
+if (bind(s, (struct sockaddr *)&l_local, sizeof(struct sockaddr_nl)) == -1) {
+	perror("bind");
+	close(s);
+	return -1;
+}
+
+{
+	int on = l_local.nl_groups;
+	setsockopt(s, 270, 1, &on, sizeof(on));
+}
+
+Where 270 above is SOL_NETLINK, and 1 is a NETLINK_ADD_MEMBERSHIP socket
+option. To drop multicast subscription one should call above socket option
+with NETLINK_DROP_MEMBERSHIP parameter which is defined as 0.
+
+2.6.14 netlink code only allows to select a group which is less or equal to
+the maximum group number, which is used at netlink_kernel_create() time.
+In case of connector it is CN_NETLINK_USERS + 0xf, so if you want to use
+group number 12345, you must increment CN_NETLINK_USERS to that number.
+Additional 0xf numbers are allocated to be used by non-in-kernel users.
+
+Due to this limitation, group 0xffffffff does not work now, so one can
+not use add/remove connector's group notifications, but as far as I know, 
+only cn_test.c test module used it.
+
+Some work in netlink area is still being done, so things can be changed in
+2.6.15 timeframe, if it will happen, documentation will be updated for that
+kernel.

arch/cris/arch-v32/kernel/smp.c

@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
+#include <linux/module.h>
 
 #define IPI_SCHEDULE 1
 #define IPI_CALL 2
@@ -28,6 +29,7 @@ spinlock_t cris_atomic_locks[] = { [0 ... LOCK_COUNT - 1] = SPIN_LOCK_UNLOCKED};
 /* CPU masks */
 cpumask_t cpu_online_map = CPU_MASK_NONE;
 cpumask_t phys_cpu_present_map = CPU_MASK_NONE;
+EXPORT_SYMBOL(phys_cpu_present_map);
 
 /* Variables used during SMP boot */
 volatile int cpu_now_booting = 0;

arch/sh/kernel/smp.c

@@ -22,6 +22,7 @@
 #include <linux/time.h>
 #include <linux/timex.h>
 #include <linux/sched.h>
+#include <linux/module.h>
 
 #include <asm/atomic.h>
 #include <asm/processor.h>
@@ -39,6 +40,8 @@ struct sh_cpuinfo cpu_data[NR_CPUS];
 extern void per_cpu_trap_init(void);
 
 cpumask_t cpu_possible_map;
+EXPORT_SYMBOL(cpu_possible_map);
+
 cpumask_t cpu_online_map;
 static atomic_t cpus_booted = ATOMIC_INIT(0);
 

include/linux/cpumask.h

@@ -392,4 +392,16 @@ extern cpumask_t cpu_present_map;
 #define for_each_online_cpu(cpu)  for_each_cpu_mask((cpu), cpu_online_map)
 #define for_each_present_cpu(cpu) for_each_cpu_mask((cpu), cpu_present_map)
 
+/* Find the highest possible smp_processor_id() */
+static inline unsigned int highest_possible_processor_id(void)
+{
+	unsigned int cpu, highest = 0;
+
+	for_each_cpu_mask(cpu, cpu_possible_map)
+		highest = cpu;
+
+	return highest;
+}
+
+
 #endif /* __LINUX_CPUMASK_H */

net/bridge/netfilter/ebtables.c

@@ -26,6 +26,7 @@
 #include <linux/spinlock.h>
 #include <asm/uaccess.h>
 #include <linux/smp.h>
+#include <linux/cpumask.h>
 #include <net/sock.h>
 /* needed for logical [in,out]-dev filtering */
 #include "../br_private.h"
@@ -823,10 +824,11 @@ static int translate_table(struct ebt_replace *repl,
 		/* this will get free'd in do_replace()/ebt_register_table()
 		   if an error occurs */
 		newinfo->chainstack = (struct ebt_chainstack **)
-		   vmalloc(num_possible_cpus() * sizeof(struct ebt_chainstack));
+		   vmalloc((highest_possible_processor_id()+1) 
+				   		* sizeof(struct ebt_chainstack));
 		if (!newinfo->chainstack)
 			return -ENOMEM;
-		for (i = 0; i < num_possible_cpus(); i++) {
+		for_each_cpu(i) {
 			newinfo->chainstack[i] =
 			   vmalloc(udc_cnt * sizeof(struct ebt_chainstack));
 			if (!newinfo->chainstack[i]) {
@@ -895,9 +897,12 @@ static void get_counters(struct ebt_counter *oldcounters,
 
 	/* counters of cpu 0 */
 	memcpy(counters, oldcounters,
-	   sizeof(struct ebt_counter) * nentries);
+	       sizeof(struct ebt_counter) * nentries);
+
 	/* add other counters to those of cpu 0 */
-	for (cpu = 1; cpu < num_possible_cpus(); cpu++) {
+	for_each_cpu(cpu) {
+		if (cpu == 0)
+			continue;
 		counter_base = COUNTER_BASE(oldcounters, nentries, cpu);
 		for (i = 0; i < nentries; i++) {
 			counters[i].pcnt += counter_base[i].pcnt;
@@ -929,7 +934,8 @@ static int do_replace(void __user *user, unsigned int len)
 		BUGPRINT("Entries_size never zero\n");
 		return -EINVAL;
 	}
-	countersize = COUNTER_OFFSET(tmp.nentries) * num_possible_cpus();
+	countersize = COUNTER_OFFSET(tmp.nentries) * 
+					(highest_possible_processor_id()+1);
 	newinfo = (struct ebt_table_info *)
 	   vmalloc(sizeof(struct ebt_table_info) + countersize);
 	if (!newinfo)
@@ -1022,7 +1028,7 @@ static int do_replace(void __user *user, unsigned int len)
 
 	vfree(table->entries);
 	if (table->chainstack) {
-		for (i = 0; i < num_possible_cpus(); i++)
+		for_each_cpu(i)
 			vfree(table->chainstack[i]);
 		vfree(table->chainstack);
 	}
@@ -1040,7 +1046,7 @@ free_counterstmp:
 	vfree(counterstmp);
 	/* can be initialized in translate_table() */
 	if (newinfo->chainstack) {
-		for (i = 0; i < num_possible_cpus(); i++)
+		for_each_cpu(i)
 			vfree(newinfo->chainstack[i]);
 		vfree(newinfo->chainstack);
 	}
@@ -1132,7 +1138,8 @@ int ebt_register_table(struct ebt_table *table)
 		return -EINVAL;
 	}
 
-	countersize = COUNTER_OFFSET(table->table->nentries) * num_possible_cpus();
+	countersize = COUNTER_OFFSET(table->table->nentries) *
+					(highest_possible_processor_id()+1);
 	newinfo = (struct ebt_table_info *)
 	   vmalloc(sizeof(struct ebt_table_info) + countersize);
 	ret = -ENOMEM;
@@ -1186,7 +1193,7 @@ free_unlock:
 	up(&ebt_mutex);
 free_chainstack:
 	if (newinfo->chainstack) {
-		for (i = 0; i < num_possible_cpus(); i++)
+		for_each_cpu(i)
 			vfree(newinfo->chainstack[i]);
 		vfree(newinfo->chainstack);
 	}
@@ -1209,7 +1216,7 @@ void ebt_unregister_table(struct ebt_table *table)
 	up(&ebt_mutex);
 	vfree(table->private->entries);
 	if (table->private->chainstack) {
-		for (i = 0; i < num_possible_cpus(); i++)
+		for_each_cpu(i)
 			vfree(table->private->chainstack[i]);
 		vfree(table->private->chainstack);
 	}

net/ipv4/netfilter/arp_tables.c

@@ -716,8 +716,10 @@ static int translate_table(const char *name,
 	}
 
 	/* And one copy for every other CPU */
-	for (i = 1; i < num_possible_cpus(); i++) {
+	for_each_cpu(i) {
-		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size)*i,
+		if (i == 0)
+			continue;
+		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size) * i,
 		       newinfo->entries,
 		       SMP_ALIGN(newinfo->size));
 	}
@@ -767,7 +769,7 @@ static void get_counters(const struct arpt_table_info *t,
 	unsigned int cpu;
 	unsigned int i;
 
-	for (cpu = 0; cpu < num_possible_cpus(); cpu++) {
+	for_each_cpu(cpu) {
 		i = 0;
 		ARPT_ENTRY_ITERATE(t->entries + TABLE_OFFSET(t, cpu),
 				   t->size,
@@ -885,7 +887,8 @@ static int do_replace(void __user *user, unsigned int len)
 		return -ENOMEM;
 
 	newinfo = vmalloc(sizeof(struct arpt_table_info)
-			  + SMP_ALIGN(tmp.size) * num_possible_cpus());
+			  + SMP_ALIGN(tmp.size) *
+			  		(highest_possible_processor_id()+1));
 	if (!newinfo)
 		return -ENOMEM;
 
@@ -1158,7 +1161,8 @@ int arpt_register_table(struct arpt_table *table,
 		= { 0, 0, 0, { 0 }, { 0 }, { } };
 
 	newinfo = vmalloc(sizeof(struct arpt_table_info)
-			  + SMP_ALIGN(repl->size) * num_possible_cpus());
+			  + SMP_ALIGN(repl->size) *
+			  		(highest_possible_processor_id()+1));
 	if (!newinfo) {
 		ret = -ENOMEM;
 		return ret;

net/ipv4/netfilter/ip_tables.c

@@ -27,6 +27,7 @@
 #include <asm/semaphore.h>
 #include <linux/proc_fs.h>
 #include <linux/err.h>
+#include <linux/cpumask.h>
 
 #include <linux/netfilter_ipv4/ip_tables.h>
 
@@ -921,8 +922,10 @@ translate_table(const char *name,
 	}
 
 	/* And one copy for every other CPU */
-	for (i = 1; i < num_possible_cpus(); i++) {
+	for_each_cpu(i) {
-		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size)*i,
+		if (i == 0)
+			continue;
+		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size) * i,
 		       newinfo->entries,
 		       SMP_ALIGN(newinfo->size));
 	}
@@ -943,7 +946,7 @@ replace_table(struct ipt_table *table,
 		struct ipt_entry *table_base;
 		unsigned int i;
 
-		for (i = 0; i < num_possible_cpus(); i++) {
+		for_each_cpu(i) {
 			table_base =
 				(void *)newinfo->entries
 				+ TABLE_OFFSET(newinfo, i);
@@ -990,7 +993,7 @@ get_counters(const struct ipt_table_info *t,
 	unsigned int cpu;
 	unsigned int i;
 
-	for (cpu = 0; cpu < num_possible_cpus(); cpu++) {
+	for_each_cpu(cpu) {
 		i = 0;
 		IPT_ENTRY_ITERATE(t->entries + TABLE_OFFSET(t, cpu),
 				  t->size,
@@ -1128,7 +1131,8 @@ do_replace(void __user *user, unsigned int len)
 		return -ENOMEM;
 
 	newinfo = vmalloc(sizeof(struct ipt_table_info)
-			  + SMP_ALIGN(tmp.size) * num_possible_cpus());
+			  + SMP_ALIGN(tmp.size) * 
+			  	(highest_possible_processor_id()+1));
 	if (!newinfo)
 		return -ENOMEM;
 
@@ -1458,7 +1462,8 @@ int ipt_register_table(struct ipt_table *table, const struct ipt_replace *repl)
 		= { 0, 0, 0, { 0 }, { 0 }, { } };
 
 	newinfo = vmalloc(sizeof(struct ipt_table_info)
-			  + SMP_ALIGN(repl->size) * num_possible_cpus());
+			  + SMP_ALIGN(repl->size) * 
+			  		(highest_possible_processor_id()+1));
 	if (!newinfo)
 		return -ENOMEM;
 

net/ipv4/tcp_output.c

@@ -436,11 +436,13 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss
 	u16 flags;
 
 	if (unlikely(len >= skb->len)) {
-		printk(KERN_DEBUG "TCP: seg_size=%u, mss=%u, seq=%u, "
+		if (net_ratelimit()) {
-		       "end_seq=%u, skb->len=%u.\n", len, mss_now,
+			printk(KERN_DEBUG "TCP: seg_size=%u, mss=%u, seq=%u, "
-		       TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
+			       "end_seq=%u, skb->len=%u.\n", len, mss_now,
-		       skb->len);
+			       TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
-		WARN_ON(1);
+			       skb->len);
+			WARN_ON(1);
+		}
 		return 0;
 	}
 

net/ipv6/netfilter/ip6_tables.c

@@ -28,6 +28,7 @@
 #include <asm/uaccess.h>
 #include <asm/semaphore.h>
 #include <linux/proc_fs.h>
+#include <linux/cpumask.h>
 
 #include <linux/netfilter_ipv6/ip6_tables.h>
 
@@ -950,8 +951,10 @@ translate_table(const char *name,
 	}
 
 	/* And one copy for every other CPU */
-	for (i = 1; i < num_possible_cpus(); i++) {
+	for_each_cpu(i) {
-		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size)*i,
+		if (i == 0)
+			continue;
+		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size) * i,
 		       newinfo->entries,
 		       SMP_ALIGN(newinfo->size));
 	}
@@ -973,6 +976,7 @@ replace_table(struct ip6t_table *table,
 		unsigned int i;
 
 		for (i = 0; i < num_possible_cpus(); i++) {
+		for_each_cpu(i) {
 			table_base =
 				(void *)newinfo->entries
 				+ TABLE_OFFSET(newinfo, i);
@@ -1019,7 +1023,7 @@ get_counters(const struct ip6t_table_info *t,
 	unsigned int cpu;
 	unsigned int i;
 
-	for (cpu = 0; cpu < num_possible_cpus(); cpu++) {
+	for_each_cpu(cpu) {
 		i = 0;
 		IP6T_ENTRY_ITERATE(t->entries + TABLE_OFFSET(t, cpu),
 				  t->size,
@@ -1153,7 +1157,8 @@ do_replace(void __user *user, unsigned int len)
 		return -ENOMEM;
 
 	newinfo = vmalloc(sizeof(struct ip6t_table_info)
-			  + SMP_ALIGN(tmp.size) * num_possible_cpus());
+			  + SMP_ALIGN(tmp.size) *
+			  		(highest_possible_processor_id()+1));
 	if (!newinfo)
 		return -ENOMEM;
 
@@ -1467,7 +1472,8 @@ int ip6t_register_table(struct ip6t_table *table,
 		= { 0, 0, 0, { 0 }, { 0 }, { } };
 
 	newinfo = vmalloc(sizeof(struct ip6t_table_info)
-			  + SMP_ALIGN(repl->size) * num_possible_cpus());
+			  + SMP_ALIGN(repl->size) *
+			  		(highest_possible_processor_id()+1));
 	if (!newinfo)
 		return -ENOMEM;
 

net/sched/Kconfig

@@ -72,9 +72,11 @@ config NET_SCH_CLK_GETTIMEOFDAY
 	  Choose this if you need a high resolution clock source but can't use
 	  the CPU's cycle counter.
 
+# don't allow on SMP x86 because they can have unsynchronized TSCs.
+# gettimeofday is a good alternative
 config NET_SCH_CLK_CPU
 	bool "CPU cycle counter"
-	depends on X86_TSC || X86_64 || ALPHA || SPARC64 || PPC64 || IA64
+	depends on ((X86_TSC || X86_64) && !SMP) || ALPHA || SPARC64 || PPC64 || IA64
 	help
 	  Say Y here if you want to use the CPU's cycle counter as clock source.
 	  This is a cheap and high resolution clock source, but on some