Revert "x86/smpboot: Initialize secondary CPU only if master CPU will wait for it"

This reverts commit 3e1a878b7ccdb31da6d9d2b855c72ad87afeba3f.

It came in very late, and already has one reported failure: Sitsofe
reports that the current tree fails to boot on his EeePC, and bisected
it down to this.  Rather than waste time trying to figure out what's
wrong, just revert it.

Reported-by: Sitsofe Wheeler <sitsofe@gmail.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a4bcbacdbe0bc9e62e66e6530dbdae9cadbb18c4..a135239badb7fd4762ebf939ae755183660641b2 100644 (file)
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1221,17 +1221,6 @@ static void dbg_restore_debug_regs(void)
 #define dbg_restore_debug_regs()
 #endif /* ! CONFIG_KGDB */
 
-static void wait_for_master_cpu(int cpu)
-{
-       /*
-        * wait for ACK from master CPU before continuing
-        * with AP initialization
-        */
-       WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask));
-       while (!cpumask_test_cpu(cpu, cpu_callout_mask))
-               cpu_relax();
-}
-
 /*
  * cpu_init() initializes state that is per-CPU. Some data is already
  * initialized (naturally) in the bootstrap process, such as the GDT
@@ -1247,17 +1236,16 @@ void cpu_init(void)
        struct task_struct *me;
        struct tss_struct *t;
        unsigned long v;
-       int cpu = stack_smp_processor_id();
+       int cpu;
        int i;
 
-       wait_for_master_cpu(cpu);
-
        /*
         * Load microcode on this cpu if a valid microcode is available.
         * This is early microcode loading procedure.
         */
        load_ucode_ap();
 
+       cpu = stack_smp_processor_id();
        t = &per_cpu(init_tss, cpu);
        oist = &per_cpu(orig_ist, cpu);
 
@@ -1269,6 +1257,9 @@ void cpu_init(void)
 
        me = current;
 
+       if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask))
+               panic("CPU#%d already initialized!\n", cpu);
+
        pr_debug("Initializing CPU#%d\n", cpu);
 
        clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
@@ -1345,10 +1336,14 @@ void cpu_init(void)
        struct tss_struct *t = &per_cpu(init_tss, cpu);
        struct thread_struct *thread = &curr->thread;
 
-       wait_for_master_cpu(cpu);
-
        show_ucode_info_early();
 
+       if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) {
+               printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
+               for (;;)
+                       local_irq_enable();
+       }
+
        printk(KERN_INFO "Initializing CPU#%d\n", cpu);
 
        if (cpu_has_vme || cpu_has_tsc || cpu_has_de)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index bc52fac39dd3175a84d81b88378de04450ad5e88..ae2fd975b7824cc3caf125d11e3587094a31e1b3 100644 (file)
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -111,6 +111,7 @@ atomic_t init_deasserted;
 static void smp_callin(void)
 {
        int cpuid, phys_id;
+       unsigned long timeout;
 
        /*
         * If waken up by an INIT in an 82489DX configuration
@@ -129,6 +130,37 @@ static void smp_callin(void)
         * (This works even if the APIC is not enabled.)
         */
        phys_id = read_apic_id();
+       if (cpumask_test_cpu(cpuid, cpu_callin_mask)) {
+               panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
+                                       phys_id, cpuid);
+       }
+       pr_debug("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);
+
+       /*
+        * STARTUP IPIs are fragile beasts as they might sometimes
+        * trigger some glue motherboard logic. Complete APIC bus
+        * silence for 1 second, this overestimates the time the
+        * boot CPU is spending to send the up to 2 STARTUP IPIs
+        * by a factor of two. This should be enough.
+        */
+
+       /*
+        * Waiting 2s total for startup (udelay is not yet working)
+        */
+       timeout = jiffies + 2*HZ;
+       while (time_before(jiffies, timeout)) {
+               /*
+                * Has the boot CPU finished it's STARTUP sequence?
+                */
+               if (cpumask_test_cpu(cpuid, cpu_callout_mask))
+                       break;
+               cpu_relax();
+       }
+
+       if (!time_before(jiffies, timeout)) {
+               panic("%s: CPU%d started up but did not get a callout!\n",
+                     __func__, cpuid);
+       }
 
        /*
         * the boot CPU has finished the init stage and is spinning
@@ -718,8 +750,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
        unsigned long start_ip = real_mode_header->trampoline_start;
 
        unsigned long boot_error = 0;
+       int timeout;
        int cpu0_nmi_registered = 0;
-       unsigned long timeout;
 
        /* Just in case we booted with a single CPU. */
        alternatives_enable_smp();
@@ -766,15 +798,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
                }
        }
 
-       /*
-        * AP might wait on cpu_callout_mask in cpu_init() with
-        * cpu_initialized_mask set if previous attempt to online
-        * it timed-out. Clear cpu_initialized_mask so that after
-        * INIT/SIPI it could start with a clean state.
-        */
-       cpumask_clear_cpu(cpu, cpu_initialized_mask);
-       smp_mb();
-
        /*
         * Wake up a CPU in difference cases:
         * - Use the method in the APIC driver if it's defined
@@ -787,41 +810,55 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
                boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
                                                     &cpu0_nmi_registered);
 
-
        if (!boot_error) {
                /*
-                * Wait 10s total for a response from AP
+                * allow APs to start initializing.
                 */
-               boot_error = -1;
-               timeout = jiffies + 10*HZ;
-               while (time_before(jiffies, timeout)) {
-                       if (cpumask_test_cpu(cpu, cpu_initialized_mask)) {
-                               /*
-                                * Tell AP to proceed with initialization
-                                */
-                               cpumask_set_cpu(cpu, cpu_callout_mask);
-                               boot_error = 0;
-                               break;
-                       }
-                       udelay(100);
-                       schedule();
-               }
-       }
+               pr_debug("Before Callout %d\n", cpu);
+               cpumask_set_cpu(cpu, cpu_callout_mask);
+               pr_debug("After Callout %d\n", cpu);
 
-       if (!boot_error) {
                /*
-                * Wait till AP completes initial initialization
+                * Wait 5s total for a response
                 */
-               while (!cpumask_test_cpu(cpu, cpu_callin_mask)) {
+               for (timeout = 0; timeout < 50000; timeout++) {
+                       if (cpumask_test_cpu(cpu, cpu_callin_mask))
+                               break;  /* It has booted */
+                       udelay(100);
                        /*
                         * Allow other tasks to run while we wait for the
                         * AP to come online. This also gives a chance
                         * for the MTRR work(triggered by the AP coming online)
                         * to be completed in the stop machine context.
                         */
-                       udelay(100);
                        schedule();
                }
+
+               if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
+                       print_cpu_msr(&cpu_data(cpu));
+                       pr_debug("CPU%d: has booted.\n", cpu);
+               } else {
+                       boot_error = 1;
+                       if (*trampoline_status == 0xA5A5A5A5)
+                               /* trampoline started but...? */
+                               pr_err("CPU%d: Stuck ??\n", cpu);
+                       else
+                               /* trampoline code not run */
+                               pr_err("CPU%d: Not responding\n", cpu);
+                       if (apic->inquire_remote_apic)
+                               apic->inquire_remote_apic(apicid);
+               }
+       }
+
+       if (boot_error) {
+               /* Try to put things back the way they were before ... */
+               numa_remove_cpu(cpu); /* was set by numa_add_cpu */
+
+               /* was set by do_boot_cpu() */
+               cpumask_clear_cpu(cpu, cpu_callout_mask);
+
+               /* was set by cpu_init() */
+               cpumask_clear_cpu(cpu, cpu_initialized_mask);
        }
 
        /* mark "stuck" area as not stuck */