X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=arch%2Fx86%2Fkernel%2Fsmpboot.c;h=0629a8e513af48008d925e60d4d7d56f408f694e;hb=d68921f9bd148359e6d01c84aaa2e32bfbd82970;hp=50e547eac8cd4b64e9e6892410366ec3a64a7a13;hpb=bfaf245022b4b8661af2e35f467cf0e91943c24c;p=mirror_ubuntu-artful-kernel.git

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 50e547eac8cd..0629a8e513af 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -513,6 +513,27 @@ void __inquire_remote_apic(int apicid)
 	}
 }
 
+/*
+ * The Multiprocessor Specification 1.4 (1997) example code suggests
+ * that there should be a 10ms delay between the BSP asserting INIT
+ * and de-asserting INIT, when starting a remote processor.
+ * But that slows boot and resume on modern processors, which include
+ * many cores and don't require that delay.
+ *
+ * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
+ */
+#define UDELAY_10MS_DEFAULT 10000
+
+static unsigned int init_udelay = UDELAY_10MS_DEFAULT;
+
+static int __init cpu_init_udelay(char *str)
+{
+	get_option(&str, &init_udelay);
+
+	return 0;
+}
+early_param("cpu_init_udelay", cpu_init_udelay);
+
 /*
  * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
  * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
@@ -555,7 +576,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
 static int
 wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 {
-	unsigned long send_status, accept_status = 0;
+	unsigned long send_status = 0, accept_status = 0;
 	int maxlvt, num_starts, j;
 
 	maxlvt = lapic_get_maxlvt();
@@ -580,22 +601,34 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 	apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT,
 		       phys_apicid);
 
-	pr_debug("Waiting for send to finish...\n");
-	send_status = safe_apic_wait_icr_idle();
+	if (!cpu_has_x2apic) {
+		pr_debug("Waiting for send to finish...\n");
+		send_status = safe_apic_wait_icr_idle();
 
-	mdelay(10);
+		mdelay(init_udelay);
 
-	pr_debug("Deasserting INIT\n");
+		pr_debug("Deasserting INIT\n");
 
-	/* Target chip */
-	/* Send IPI */
-	apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
+		/* Target chip */
+		/* Send IPI */
+		apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
 
-	pr_debug("Waiting for send to finish...\n");
-	send_status = safe_apic_wait_icr_idle();
+		pr_debug("Waiting for send to finish...\n");
+		send_status = safe_apic_wait_icr_idle();
 
-	mb();
-	atomic_set(&init_deasserted, 1);
+		mb();
+		atomic_set(&init_deasserted, 1);
+	} else if (tboot_enabled()) {
+		/*
+		 * With tboot AP is actually spinning in a mini-guest before
+		 * receiving INIT. Upon receiving INIT ipi, AP need time to
+		 * VMExit, update VMCS to tracking SIPIs and VMResume.
+		 *
+		 * While AP is in root mode handling the INIT the CPU will drop
+		 * any SIPIs
+		 */
+		udelay(10);
+	}
 
 	/*
 	 * Should we send STARTUP IPIs ?
@@ -637,20 +670,23 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 		apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12),
 			       phys_apicid);
 
-		/*
-		 * Give the other CPU some time to accept the IPI.
-		 */
-		udelay(300);
+		if (!cpu_has_x2apic) {
+			/*
+			 * Give the other CPU some time to accept the IPI.
+			 */
+			udelay(300);
 
-		pr_debug("Startup point 1\n");
+			pr_debug("Startup point 1\n");
 
-		pr_debug("Waiting for send to finish...\n");
-		send_status = safe_apic_wait_icr_idle();
+			pr_debug("Waiting for send to finish...\n");
+			send_status = safe_apic_wait_icr_idle();
+
+			/*
+			 * Give the other CPU some time to accept the IPI.
+			 */
+			udelay(200);
+		}
 
-		/*
-		 * Give the other CPU some time to accept the IPI.
-		 */
-		udelay(200);
 		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
 			apic_write(APIC_ESR, 0);
 		accept_status = (apic_read(APIC_ESR) & 0xEF);
@@ -792,8 +828,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	clear_tsk_thread_flag(idle, TIF_FORK);
 	initial_gs = per_cpu_offset(cpu);
 #endif
-	per_cpu(kernel_stack, cpu) =
-		(unsigned long)task_stack_page(idle) + THREAD_SIZE;
 }
 
 /*