x86/mce: Rework cmci_rediscover() to play well with CPU hotplug

Dave Jones reports that offlining a CPU leads to this trace: numa_remove_cpu cpu 1 node 0: mask now 0,2-3 smpboot: CPU 1 is now offline BUG: using smp_processor_id() in preemptible [00000000] code: cpu-offline.sh/10591 caller is cmci_rediscover+0x6a/0xe0 Pid: 10591, comm: cpu-offline.sh Not tainted 3.9.0-rc3+ #2 Call Trace: [<ffffffff81333bbd>] debug_smp_processor_id+0xdd/0x100 [<ffffffff8101edba>] cmci_rediscover+0x6a/0xe0 [<ffffffff815f5b9f>] mce_cpu_callback+0x19d/0x1ae [<ffffffff8160ea66>] notifier_call_chain+0x66/0x150 [<ffffffff8107ad7e>] __raw_notifier_call_chain+0xe/0x10 [<ffffffff8104c2e3>] cpu_notify+0x23/0x50 [<ffffffff8104c31e>] cpu_notify_nofail+0xe/0x20 [<ffffffff815ef082>] _cpu_down+0x302/0x350 [<ffffffff815ef106>] cpu_down+0x36/0x50 [<ffffffff815f1c9d>] store_online+0x8d/0xd0 [<ffffffff813edc48>] dev_attr_store+0x18/0x30 [<ffffffff81226eeb>] sysfs_write_file+0xdb/0x150 [<ffffffff811adfb2>] vfs_write+0xa2/0x170 [<ffffffff811ae16c>] sys_write+0x4c/0xa0 [<ffffffff81613019>] system_call_fastpath+0x16/0x1b However, a look at cmci_rediscover shows that it can be simplified quite a bit, apart from solving the above issue. It invokes functions that take spin locks with interrupts disabled, and hence it can run in atomic context. Also, it is run in the CPU_POST_DEAD phase, so the dying CPU is already dead and out of the cpu_online_mask. So take these points into account and simplify the code, and thereby also fix the above issue. Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
git-mirror · Apr 2, 2013 · 7a0c819 · 7a0c819
1 parent 07961ac
commit 7a0c819
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 23 deletions.
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
@@ -146,13 +146,13 @@ DECLARE_PER_CPU(struct device *, mce_device);
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
 void cmci_clear(void);
 void cmci_reenable(void);
-void cmci_rediscover(int dying);
+void cmci_rediscover(void);
 void cmci_recheck(void);
 #else
 static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
 static inline void cmci_clear(void) {}
 static inline void cmci_reenable(void) {}
-static inline void cmci_rediscover(int dying) {}
+static inline void cmci_rediscover(void) {}
 static inline void cmci_recheck(void) {}
 #endif
 

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2358,7 +2358,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
 	if (action == CPU_POST_DEAD) {
 		/* intentionally ignoring frozen here */
-		cmci_rediscover(cpu);
+		cmci_rediscover();
 	}
 
 	return NOTIFY_OK;

diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -285,39 +285,24 @@ void cmci_clear(void)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
-static long cmci_rediscover_work_func(void *arg)
+static void cmci_rediscover_work_func(void *arg)
 {
 	int banks;
 
 	/* Recheck banks in case CPUs don't all have the same */
 	if (cmci_supported(&banks))
 		cmci_discover(banks);
-
-	return 0;
 }
 
-/*
- * After a CPU went down cycle through all the others and rediscover
- * Must run in process context.
- */
-void cmci_rediscover(int dying)
+/* After a CPU went down cycle through all the others and rediscover */
+void cmci_rediscover(void)
 {
-	int cpu, banks;
+	int banks;
 
 	if (!cmci_supported(&banks))
 		return;
 
-	for_each_online_cpu(cpu) {
-		if (cpu == dying)
-			continue;
-
-		if (cpu == smp_processor_id()) {
-			cmci_rediscover_work_func(NULL);
-			continue;
-		}
-
-		work_on_cpu(cpu, cmci_rediscover_work_func, NULL);
-	}
+	on_each_cpu(cmci_rediscover_work_func, NULL, 1);
 }
 
 /*