[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>

1 files changed, 12 insertions, 9 deletions

diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index 6d23354443c0..6e4807d64d46 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)