[PATCH] Fix sync_tsc hang

sync_tsc was using smp_call_function to ask the boot processor to report
it's tsc value.  smp_call_function performs an IPI_send_allbutself which is
a broadcast ipi.  There is a window during processor startup during which
the target cpu has started and before it has initialized it's interrupt
vectors so it can properly process an interrupt.  Receveing an interrupt
during that window will triple fault the cpu and do other nasty things.

Why cli does not protect us from that is beyond me.

The simple fix is to match ia64 and provide a smp_call_function_single.
Which avoids the broadcast and is more efficient.

This certainly fixes the problem of getting stuck on boot which was
very easy to trigger on my SMP Hyperthreaded Xeon, and I think
it fixes it for the right reasons.

Minor changes by AK

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 78 insertions, 9 deletions

diff --git a/arch/x86_64/kernel/smp.c b/arch/x86_64/kernel/smp.c
index 6ee74db5230..e5958220d6b 100644
--- a/arch/x86_64/kernel/smp.c
+++ b/arch/x86_64/kernel/smp.c
@@ -293,6 +293,69 @@ void unlock_ipi_call_lock(void)
 }
 
 /*
+ * this function sends a 'generic call function' IPI to one other CPU
+ * in the system.
+ */
+static void __smp_call_function_single (int cpu, void (*func) (void *info), void *info,
+				int nonatomic, int wait)
+{
+	struct call_data_struct data;
+	int cpus = 1;
+
+	data.func = func;
+	data.info = info;
+	atomic_set(&data.started, 0);
+	data.wait = wait;
+	if (wait)
+		atomic_set(&data.finished, 0);
+
+	call_data = &data;
+	wmb();
+	/* Send a message to all other CPUs and wait for them to respond */
+	send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_VECTOR);
+
+	/* Wait for response */
+	while (atomic_read(&data.started) != cpus)
+		cpu_relax();
+
+	if (!wait)
+		return;
+
+	while (atomic_read(&data.finished) != cpus)
+		cpu_relax();
+}
+
+/*
+ * smp_call_function_single - Run a function on another CPU
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @nonatomic: Currently unused.
+ * @wait: If true, wait until function has completed on other CPUs.
+ *
+ * Retrurns 0 on success, else a negative status code.
+ *
+ * Does not return until the remote CPU is nearly ready to execute <func>
+ * or is or has executed.
+ */
+
+int smp_call_function_single (int cpu, void (*func) (void *info), void *info,
+	int nonatomic, int wait)
+{
+	/* prevent preemption and reschedule on another processor */
+	int me = get_cpu();
+	if (cpu == me) {
+		WARN_ON(1);
+		put_cpu();
+		return -EBUSY;
+	}
+	spin_lock_bh(&call_lock);
+	__smp_call_function_single(cpu, func, info, nonatomic, wait);
+	spin_unlock_bh(&call_lock);
+	put_cpu();
+	return 0;
+}
+
+/*
  * this function sends a 'generic call function' IPI to all other CPUs
  * in the system.
  */
diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index 6d23354443c..6e4807d64d4 100644
--- a/arch/x86_64/kernel/smpboot.c
+++ b/arch/x86_64/kernel/smpboot.c
@@ -211,9 +211,6 @@ static __cpuinit void sync_master(void *arg)
 {
 	unsigned long flags, i;
 
-	if (smp_processor_id() != 0)
-		return;
-
 	go[MASTER] = 0;
 
 	local_irq_save(flags);
@@ -262,7 +259,7 @@ get_delta(long *rt, long *master)
 	return tcenter - best_tm;
 }
 
-static __cpuinit void sync_tsc(void)
+static __cpuinit void sync_tsc(unsigned int master)
 {
 	int i, done = 0;
 	long delta, adj, adjust_latency = 0;
@@ -276,9 +273,17 @@ static __cpuinit void sync_tsc(void)
 	} t[NUM_ROUNDS] __cpuinitdata;
 #endif
 
+	printk(KERN_INFO "CPU %d: Syncing TSC to CPU %u.\n",
+		smp_processor_id(), master);
+
 	go[MASTER] = 1;
 
-	smp_call_function(sync_master, NULL, 1, 0);
+	/* It is dangerous to broadcast IPI as cpus are coming up,
+	 * as they may not be ready to accept them.  So since
+	 * we only need to send the ipi to the boot cpu direct
+	 * the message, and avoid the race.
+	 */
+	smp_call_function_single(master, sync_master, NULL, 1, 0);
 
 	while (go[MASTER])	/* wait for master to be ready */
 		no_cpu_relax();
@@ -322,16 +327,14 @@ static __cpuinit void sync_tsc(void)
 	printk(KERN_INFO
 	       "CPU %d: synchronized TSC with CPU %u (last diff %ld cycles, "
 	       "maxerr %lu cycles)\n",
-	       smp_processor_id(), boot_cpu_id, delta, rt);
+	       smp_processor_id(), master, delta, rt);
 }
 
 static void __cpuinit tsc_sync_wait(void)
 {
 	if (notscsync || !cpu_has_tsc)
 		return;
-	printk(KERN_INFO "CPU %d: Syncing TSC to CPU %u.\n", smp_processor_id(),
-			boot_cpu_id);
-	sync_tsc();
+	sync_tsc(boot_cpu_id);
 }
 
 static __init int notscsync_setup(char *s)
diff --git a/include/asm-x86_64/smp.h b/include/asm-x86_64/smp.h
index 18ac762e1ab..de8b57b2b62 100644
--- a/include/asm-x86_64/smp.h
+++ b/include/asm-x86_64/smp.h
@@ -49,6 +49,9 @@ extern int smp_num_siblings;
 extern void smp_send_reschedule(int cpu);
 extern void zap_low_mappings(void);
 void smp_stop_cpu(void);
+extern int smp_call_function_single(int cpuid, void (*func) (void *info),
+				void *info, int retry, int wait);
+
 extern cpumask_t cpu_sibling_map[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 extern u8 phys_proc_id[NR_CPUS];