1 files changed, 93 insertions, 8 deletions

diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index a1d804bcd48..b99b9ad8540 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -15,6 +15,8 @@
 #include <linux/init.h>
 #include <linux/pci_ids.h>
 #include <linux/pci_regs.h>
+#include <linux/smp.h>
+#include <linux/irq.h>
 
 #include <asm/apic.h>
 #include <asm/pci-direct.h>
@@ -22,6 +24,11 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 
+#define TOPOLOGY_REGISTER_OFFSET 0x10
+
+/* Flag below is initialized once during vSMP PCI initialization. */
+static int irq_routing_comply = 1;
+
 #if defined CONFIG_PCI && defined CONFIG_PARAVIRT
 /*
  * Interrupt control on vSMPowered systems:
@@ -29,7 +36,7 @@
  * and vice versa.
  */
 
-static unsigned long vsmp_save_fl(void)
+asmlinkage __visible unsigned long vsmp_save_fl(void)
 {
 	unsigned long flags = native_save_fl();
 
@@ -39,7 +46,7 @@ static unsigned long vsmp_save_fl(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl);
 
-static void vsmp_restore_fl(unsigned long flags)
+__visible void vsmp_restore_fl(unsigned long flags)
 {
 	if (flags & X86_EFLAGS_IF)
 		flags &= ~X86_EFLAGS_AC;
@@ -49,7 +56,7 @@ static void vsmp_restore_fl(unsigned long flags)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
 
-static void vsmp_irq_disable(void)
+asmlinkage __visible void vsmp_irq_disable(void)
 {
 	unsigned long flags = native_save_fl();
 
@@ -57,7 +64,7 @@ static void vsmp_irq_disable(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
 
-static void vsmp_irq_enable(void)
+asmlinkage __visible void vsmp_irq_enable(void)
 {
 	unsigned long flags = native_save_fl();
 
@@ -92,6 +99,22 @@ static void __init set_vsmp_pv_ops(void)
 	ctl = readl(address + 4);
 	printk(KERN_INFO "vSMP CTL: capabilities:0x%08x  control:0x%08x\n",
 	       cap, ctl);
+
+	/* If possible, let the vSMP foundation route the interrupt optimally */
+#ifdef CONFIG_SMP
+	if (cap & ctl & BIT(8)) {
+		ctl &= ~BIT(8);
+
+		/* Interrupt routing set to ignore */
+		irq_routing_comply = 0;
+
+#ifdef CONFIG_PROC_FS
+		/* Don't let users change irq affinity via procfs */
+		no_irq_affinity = 1;
+#endif
+	}
+#endif
+
 	if (cap & ctl & (1 << 4)) {
 		/* Setup irq ops and turn on vSMP  IRQ fastpath handling */
 		pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
@@ -99,12 +122,11 @@ static void __init set_vsmp_pv_ops(void)
 		pv_irq_ops.save_fl  = PV_CALLEE_SAVE(vsmp_save_fl);
 		pv_irq_ops.restore_fl  = PV_CALLEE_SAVE(vsmp_restore_fl);
 		pv_init_ops.patch = vsmp_patch;
-
 		ctl &= ~(1 << 4);
-		writel(ctl, address + 4);
-		ctl = readl(address + 4);
-		printk(KERN_INFO "vSMP CTL: control set to:0x%08x\n", ctl);
 	}
+	writel(ctl, address + 4);
+	ctl = readl(address + 4);
+	pr_info("vSMP CTL: control set to:0x%08x\n", ctl);
 
 	early_iounmap(address, 8);
 }
@@ -149,12 +171,75 @@ int is_vsmp_box(void)
 	return 0;
 }
 #endif
+
+static void __init vsmp_cap_cpus(void)
+{
+#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP)
+	void __iomem *address;
+	unsigned int cfg, topology, node_shift, maxcpus;
+
+	/*
+	 * CONFIG_X86_VSMP is not configured, so limit the number CPUs to the
+	 * ones present in the first board, unless explicitly overridden by
+	 * setup_max_cpus
+	 */
+	if (setup_max_cpus != NR_CPUS)
+		return;
+
+	/* Read the vSMP Foundation topology register */
+	cfg = read_pci_config(0, 0x1f, 0, PCI_BASE_ADDRESS_0);
+	address = early_ioremap(cfg + TOPOLOGY_REGISTER_OFFSET, 4);
+	if (WARN_ON(!address))
+		return;
+
+	topology = readl(address);
+	node_shift = (topology >> 16) & 0x7;
+	if (!node_shift)
+		/* The value 0 should be decoded as 8 */
+		node_shift = 8;
+	maxcpus = (topology & ((1 << node_shift) - 1)) + 1;
+
+	pr_info("vSMP CTL: Capping CPUs to %d (CONFIG_X86_VSMP is unset)\n",
+		maxcpus);
+	setup_max_cpus = maxcpus;
+	early_iounmap(address, 4);
+#endif
+}
+
+static int apicid_phys_pkg_id(int initial_apic_id, int index_msb)
+{
+	return hard_smp_processor_id() >> index_msb;
+}
+
+/*
+ * In vSMP, all cpus should be capable of handling interrupts, regardless of
+ * the APIC used.
+ */
+static void fill_vector_allocation_domain(int cpu, struct cpumask *retmask,
+					  const struct cpumask *mask)
+{
+	cpumask_setall(retmask);
+}
+
+static void vsmp_apic_post_init(void)
+{
+	/* need to update phys_pkg_id */
+	apic->phys_pkg_id = apicid_phys_pkg_id;
+
+	if (!irq_routing_comply)
+		apic->vector_allocation_domain = fill_vector_allocation_domain;
+}
+
 void __init vsmp_init(void)
 {
 	detect_vsmp_box();
 	if (!is_vsmp_box())
 		return;
 
+	x86_platform.apic_post_init = vsmp_apic_post_init;
+
+	vsmp_cap_cpus();
+
 	set_vsmp_pv_ops();
 	return;
 }