x64, x2apic/intr-remap: add x2apic support, including enabling interrupt-remapping

x2apic support.  Interrupt-remapping must be enabled before enabling x2apic,
this is needed to ensure that IO interrupts continue to work properly after the
cpu mode is changed to x2apic(which uses 32bit extended physical/cluster
apic id).

On systems where apicid's are > 255, BIOS can handover the control to OS in
x2apic mode. Or if the OS handover was in legacy xapic mode, check
if it is capable of x2apic mode. And if we succeed in enabling
Interrupt-remapping, then we can enable x2apic mode in the CPU.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: akpm@linux-foundation.org
Cc: arjan@linux.intel.com
Cc: andi@firstfloor.org
Cc: ebiederm@xmission.com
Cc: jbarnes@virtuousgeek.org
Cc: steiner@sgi.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

9 files changed, 171 insertions, 4 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 795c487af8e4..56689ef1a159 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1377,6 +1377,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
         nolapic_timer   [X86-32,APIC] Do not use the local APIC timer.
 
+        nox2apic        [X86-64,APIC] Do not enable x2APIC mode.
+
         noltlbs         [PPC] Do not use large page/tlb entries for kernel
                         lowmem mapping on PPC40x.
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 785700a08e9d..8705262ddcda 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1337,7 +1337,9 @@ static void __init acpi_process_madt(void)
                                 acpi_ioapic = 1;
 
                                 smp_found_config = 1;
+#ifdef CONFIG_X86_32
                                 setup_apic_routing();
+#endif
                         }
                 }
                 if (error == -EINVAL) {
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index d5c06917b5b1..dd0501039f09 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -27,6 +27,7 @@
 #include <linux/clockchips.h>
 #include <linux/acpi_pmtmr.h>
 #include <linux/module.h>
+#include <linux/dmar.h>
 
 #include <asm/atomic.h>
 #include <asm/smp.h>
@@ -39,6 +40,7 @@
 #include <asm/proto.h>
 #include <asm/timex.h>
 #include <asm/apic.h>
+#include <asm/i8259.h>
 
 #include <mach_ipi.h>
 #include <mach_apic.h>
@@ -46,8 +48,12 @@
 static int disable_apic_timer __cpuinitdata;
 static int apic_calibrate_pmtmr __initdata;
 int disable_apic;
+int disable_x2apic;
 int x2apic;
 
+/* x2apic enabled before OS handover */
+int x2apic_preenabled;
+
 /* Local APIC timer works in C2 */
 int local_apic_timer_c2_ok;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
@@ -896,6 +902,125 @@ void __cpuinit end_local_APIC_setup(void)
         apic_pm_activate();
 }
 
+void check_x2apic(void)
+{
+        int msr, msr2;
+
+        rdmsr(MSR_IA32_APICBASE, msr, msr2);
+
+        if (msr & X2APIC_ENABLE) {
+                printk("x2apic enabled by BIOS, switching to x2apic ops\n");
+                x2apic_preenabled = x2apic = 1;
+                apic_ops = &x2apic_ops;
+        }
+}
+
+void enable_x2apic(void)
+{
+        int msr, msr2;
+
+        rdmsr(MSR_IA32_APICBASE, msr, msr2);
+        if (!(msr & X2APIC_ENABLE)) {
+                printk("Enabling x2apic\n");
+                wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
+        }
+}
+
+void enable_IR_x2apic(void)
+{
+#ifdef CONFIG_INTR_REMAP
+        int ret;
+        unsigned long flags;
+
+        if (!cpu_has_x2apic)
+                return;
+
+        if (!x2apic_preenabled && disable_x2apic) {
+                printk(KERN_INFO
+                       "Skipped enabling x2apic and Interrupt-remapping "
+                       "because of nox2apic\n");
+                return;
+        }
+
+        if (x2apic_preenabled && disable_x2apic)
+                panic("Bios already enabled x2apic, can't enforce nox2apic");
+
+        if (!x2apic_preenabled && skip_ioapic_setup) {
+                printk(KERN_INFO
+                       "Skipped enabling x2apic and Interrupt-remapping "
+                       "because of skipping io-apic setup\n");
+                return;
+        }
+
+        ret = dmar_table_init();
+        if (ret) {
+                printk(KERN_INFO
+                       "dmar_table_init() failed with %d:\n", ret);
+
+                if (x2apic_preenabled)
+                        panic("x2apic enabled by bios. But IR enabling failed");
+                else
+                        printk(KERN_INFO
+                               "Not enabling x2apic,Intr-remapping\n");
+                return;
+        }
+
+        local_irq_save(flags);
+        mask_8259A();
+        save_mask_IO_APIC_setup();
+
+        ret = enable_intr_remapping(1);
+
+        if (ret && x2apic_preenabled) {
+                local_irq_restore(flags);
+                panic("x2apic enabled by bios. But IR enabling failed");
+        }
+
+        if (ret)
+                goto end;
+
+        if (!x2apic) {
+                x2apic = 1;
+                apic_ops = &x2apic_ops;
+                enable_x2apic();
+        }
+end:
+        if (ret)
+                /*
+                 * IR enabling failed
+                 */
+                restore_IO_APIC_setup();
+        else
+                reinit_intr_remapped_IO_APIC(x2apic_preenabled);
+
+        unmask_8259A();
+        local_irq_restore(flags);
+
+        if (!ret) {
+                if (!x2apic_preenabled)
+                        printk(KERN_INFO
+                               "Enabled x2apic and interrupt-remapping\n");
+                else
+                        printk(KERN_INFO
+                               "Enabled Interrupt-remapping\n");
+        } else
+                printk(KERN_ERR
+                       "Failed to enable Interrupt-remapping and x2apic\n");
+#else
+        if (!cpu_has_x2apic)
+                return;
+
+        if (x2apic_preenabled)
+                panic("x2apic enabled prior OS handover,"
+                      " enable CONFIG_INTR_REMAP");
+
+        printk(KERN_INFO "Enable CONFIG_INTR_REMAP for enabling intr-remapping "
+               " and x2apic\n");
+#endif
+
+        return;
+}
+
 /*
  * Detect and enable local APICs on non-SMP boards.
  * Original code written by Keir Fraser.
@@ -943,6 +1068,11 @@ void __init early_init_lapic_mapping(void)
  */
 void __init init_apic_mappings(void)
 {
+        if (x2apic) {
+                boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+                return;
+        }
+
         /*
          * If no local APIC can be found then set up a fake all
          * zeroes page to simulate the local APIC and another
@@ -981,6 +1111,9 @@ int __init APIC_init_uniprocessor(void)
                 return -1;
         }
 
+        enable_IR_x2apic();
+        setup_apic_routing();
+
         verify_local_APIC();
 
         connect_bsp_APIC();
@@ -1238,10 +1371,14 @@ static int lapic_resume(struct sys_device *dev)
         maxlvt = lapic_get_maxlvt();
 
         local_irq_save(flags);
-        rdmsr(MSR_IA32_APICBASE, l, h);
-        l &= ~MSR_IA32_APICBASE_BASE;
-        l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
-        wrmsr(MSR_IA32_APICBASE, l, h);
+        if (!x2apic) {
+                rdmsr(MSR_IA32_APICBASE, l, h);
+                l &= ~MSR_IA32_APICBASE_BASE;
+                l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+                wrmsr(MSR_IA32_APICBASE, l, h);
+        } else
+                enable_x2apic();
+
         apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
         apic_write(APIC_ID, apic_pm_state.apic_id);
         apic_write(APIC_DFR, apic_pm_state.apic_dfr);
@@ -1381,6 +1518,15 @@ __cpuinit int apic_is_clustered_box(void)
         return (clusters > 2);
 }
 
+static __init int setup_nox2apic(char *str)
+{
+        disable_x2apic = 1;
+        clear_cpu_cap(&boot_cpu_data, X86_FEATURE_X2APIC);
+        return 0;
+}
+early_param("nox2apic", setup_nox2apic);
+
+
 /*
  * APIC command line parameters
  */
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
index 36537ab9e56a..e7bf3c2dc5fe 100644
--- a/arch/x86/kernel/cpu/common_64.c
+++ b/arch/x86/kernel/cpu/common_64.c
@@ -606,6 +606,8 @@ void __cpuinit cpu_init(void)
         barrier();
 
         check_efer();
+        if (cpu != 0 && x2apic)
+                enable_x2apic();
 
         /*
          * set up and load the per-CPU TSS
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index 1029e178cdf7..792e21ba1a81 100644
--- a/arch/x86/kernel/genapic_64.c
+++ b/arch/x86/kernel/genapic_64.c
@@ -16,6 +16,7 @@
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/hardirq.h>
+#include <linux/dmar.h>
 
 #include <asm/smp.h>
 #include <asm/ipi.h>
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 3b25e49380c6..70e1f3e287fb 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -545,7 +545,9 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early)
        generic_bigsmp_probe();
 #endif
 
+#ifdef CONFIG_X86_32
         setup_apic_routing();
+#endif
         if (!num_processors)
                 printk(KERN_ERR "MPTABLE: no processors registered!\n");
         return num_processors;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 987b6fde3a99..2e78a143dec3 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -730,6 +730,8 @@ void __init setup_arch(char **cmdline_p)
         num_physpages = max_pfn;
 
         check_efer();
+        if (cpu_has_x2apic)
+                check_x2apic();
 
         /* How many end-of-memory variables you have, grandma! */
         /* need this before calling reserve_initrd */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c55263b3df02..0c43e1f2e7d3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1145,6 +1145,11 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
         current_thread_info()->cpu = 0;  /* needed? */
         set_cpu_sibling_map(0);
 
+#ifdef CONFIG_X86_64
+        enable_IR_x2apic();
+        setup_apic_routing();
+#endif
+
         if (smp_sanity_check(max_cpus) < 0) {
                 printk(KERN_INFO "SMP disabled\n");
                 disable_smp();
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index aa746704a5c9..129752dd2525 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -100,6 +100,11 @@ extern void apic_wait_icr_idle(void);
 extern u32 safe_apic_wait_icr_idle(void);
 extern void apic_icr_write(u32 low, u32 id);
 #else
+extern int x2apic, x2apic_preenabled;
+extern void check_x2apic(void);
+extern void enable_x2apic(void);
+extern void enable_IR_x2apic(void);
+extern void x2apic_icr_write(u32 low, u32 id);
 
 struct apic_ops {
         u32 (*read)(u32 reg);