aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/Kconfig8
-rw-r--r--arch/x86/Kconfig.cpu4
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/acpi/boot.c4
-rw-r--r--arch/x86/kernel/apic_32.c212
-rw-r--r--arch/x86/kernel/apic_64.c263
-rw-r--r--arch/x86/kernel/cpu/bugs.c23
-rw-r--r--arch/x86/kernel/cpu/common_64.c2
-rw-r--r--arch/x86/kernel/cpu/feature_names.c2
-rw-r--r--arch/x86/kernel/cpu/intel.c10
-rw-r--r--arch/x86/kernel/cpu/mcheck/p4.c4
-rw-r--r--arch/x86/kernel/genapic_64.c30
-rw-r--r--arch/x86/kernel/genapic_flat_64.c36
-rw-r--r--arch/x86/kernel/genx2apic_cluster.c153
-rw-r--r--arch/x86/kernel/genx2apic_phys.c140
-rw-r--r--arch/x86/kernel/genx2apic_uv_x.c36
-rw-r--r--arch/x86/kernel/i8259.c24
-rw-r--r--arch/x86/kernel/io_apic_32.c58
-rw-r--r--arch/x86/kernel/io_apic_64.c649
-rw-r--r--arch/x86/kernel/ipi.c6
-rw-r--r--arch/x86/kernel/mpparse.c2
-rw-r--r--arch/x86/kernel/nmi.c4
-rw-r--r--arch/x86/kernel/paravirt.c3
-rw-r--r--arch/x86/kernel/setup.c2
-rw-r--r--arch/x86/kernel/smpboot.c65
-rw-r--r--arch/x86/kernel/vmi_32.c5
-rw-r--r--arch/x86/lguest/boot.c38
-rw-r--r--arch/x86/mach-generic/bigsmp.c5
-rw-r--r--arch/x86/mach-generic/es7000.c3
-rw-r--r--arch/x86/mach-generic/numaq.c4
-rw-r--r--arch/x86/mach-generic/summit.c5
-rw-r--r--arch/x86/xen/enlighten.c45
32 files changed, 1544 insertions, 303 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 96e0c2ebc38..baca5545500 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1650,6 +1650,14 @@ config DMAR_FLOPPY_WA
workaround will setup a 1:1 mapping for the first
16M to make floppy (an ISA device) work.
+config INTR_REMAP
+ bool "Support for Interrupt Remapping (EXPERIMENTAL)"
+ depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL
+ help
+ Supports Interrupt remapping for IO-APIC and MSI devices.
+ To use x2apic mode in the CPU's which support x2APIC enhancements or
+ to support platforms with CPU's having > 8 bit APIC ID, say Y.
+
source "drivers/pci/pcie/Kconfig"
source "drivers/pci/Kconfig"
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index abff1b84ed5..54b8c02c71e 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -362,10 +362,6 @@ config X86_ALIGNMENT_16
def_bool y
depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
-config X86_GOOD_APIC
- def_bool y
- depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || MK8 || MEFFICEON || MCORE2 || MVIAC7 || X86_64
-
config X86_INTEL_USERCOPY
def_bool y
depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b78a17b1281..ea000467553 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -103,6 +103,8 @@ obj-$(CONFIG_OLPC) += olpc.o
ifeq ($(CONFIG_X86_64),y)
obj-y += genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
obj-y += bios_uv.o
+ obj-y += genx2apic_cluster.o
+ obj-y += genx2apic_phys.o
obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o
obj-$(CONFIG_AUDIT) += audit_64.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index f489d7a9be9..b41b27af33e 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -761,7 +761,7 @@ static void __init acpi_register_lapic_address(unsigned long address)
set_fixmap_nocache(FIX_APIC_BASE, address);
if (boot_cpu_physical_apicid == -1U) {
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
#ifdef CONFIG_X86_32
apic_version[boot_cpu_physical_apicid] =
GET_APIC_VERSION(apic_read(APIC_LVR));
@@ -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_32.c b/arch/x86/kernel/apic_32.c
index a437d027f20..dcb897f22aa 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -75,7 +75,7 @@ char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
/*
* Debug level, exported for io_apic.c
*/
-int apic_verbosity;
+unsigned int apic_verbosity;
int pic_mode;
@@ -145,13 +145,18 @@ static int modern_apic(void)
return lapic_get_version() >= 0x14;
}
-void apic_wait_icr_idle(void)
+/*
+ * Paravirt kernels also might be using these below ops. So we still
+ * use generic apic_read()/apic_write(), which might be pointing to different
+ * ops in PARAVIRT case.
+ */
+void xapic_wait_icr_idle(void)
{
while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
cpu_relax();
}
-u32 safe_apic_wait_icr_idle(void)
+u32 safe_xapic_wait_icr_idle(void)
{
u32 send_status;
int timeout;
@@ -167,6 +172,35 @@ u32 safe_apic_wait_icr_idle(void)
return send_status;
}
+void xapic_icr_write(u32 low, u32 id)
+{
+ apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(id));
+ apic_write_around(APIC_ICR, low);
+}
+
+u64 xapic_icr_read(void)
+{
+ u32 icr1, icr2;
+
+ icr2 = apic_read(APIC_ICR2);
+ icr1 = apic_read(APIC_ICR);
+
+ return icr1 | ((u64)icr2 << 32);
+}
+
+static struct apic_ops xapic_ops = {
+ .read = native_apic_mem_read,
+ .write = native_apic_mem_write,
+ .write_atomic = native_apic_mem_write_atomic,
+ .icr_read = xapic_icr_read,
+ .icr_write = xapic_icr_write,
+ .wait_icr_idle = xapic_wait_icr_idle,
+ .safe_wait_icr_idle = safe_xapic_wait_icr_idle,
+};
+
+struct apic_ops __read_mostly *apic_ops = &xapic_ops;
+EXPORT_SYMBOL_GPL(apic_ops);
+
/**
* enable_NMI_through_LVT0 - enable NMI through local vector table 0
*/
@@ -177,7 +211,7 @@ void __cpuinit enable_NMI_through_LVT0(void)
/* Level triggered for 82489DX */
if (!lapic_is_integrated())
v |= APIC_LVT_LEVEL_TRIGGER;
- apic_write_around(APIC_LVT0, v);
+ apic_write(APIC_LVT0, v);
}
/**
@@ -212,9 +246,6 @@ int lapic_get_maxlvt(void)
* this function twice on the boot CPU, once with a bogus timeout
* value, second time for real. The other (noncalibrating) CPUs
* call this function only once, with the real, calibrated value.
- *
- * We do reads before writes even if unnecessary, to get around the
- * P5 APIC double write bug.
*/
static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
{
@@ -229,18 +260,18 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
if (!irqen)
lvtt_value |= APIC_LVT_MASKED;
- apic_write_around(APIC_LVTT, lvtt_value);
+ apic_write(APIC_LVTT, lvtt_value);
/*
* Divide PICLK by 16
*/
tmp_value = apic_read(APIC_TDCR);
- apic_write_around(APIC_TDCR, (tmp_value
- & ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
- | APIC_TDR_DIV_16);
+ apic_write(APIC_TDCR,
+ (tmp_value & ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE)) |
+ APIC_TDR_DIV_16);
if (!oneshot)
- apic_write_around(APIC_TMICT, clocks/APIC_DIVISOR);
+ apic_write(APIC_TMICT, clocks / APIC_DIVISOR);
}
/*
@@ -249,7 +280,7 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
static int lapic_next_event(unsigned long delta,
struct clock_event_device *evt)
{
- apic_write_around(APIC_TMICT, delta);
+ apic_write(APIC_TMICT, delta);
return 0;
}
@@ -278,7 +309,7 @@ static void lapic_timer_setup(enum clock_event_mode mode,
case CLOCK_EVT_MODE_SHUTDOWN:
v = apic_read(APIC_LVTT);
v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
- apic_write_around(APIC_LVTT, v);
+ apic_write(APIC_LVTT, v);
break;
case CLOCK_EVT_MODE_RESUME:
/* Nothing to do here */
@@ -372,12 +403,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
}
}
-/*
- * Setup the boot APIC
- *
- * Calibrate and verify the result.
- */
-void __init setup_boot_APIC_clock(void)
+static int __init calibrate_APIC_clock(void)
{
struct clock_event_device *levt = &__get_cpu_var(lapic_events);
const long pm_100ms = PMTMR_TICKS_PER_SEC/10;
@@ -387,24 +413,6 @@ void __init setup_boot_APIC_clock(void)
long delta, deltapm;
int pm_referenced = 0;
- /*
- * The local apic timer can be disabled via the kernel
- * commandline or from the CPU detection code. Register the lapic
- * timer as a dummy clock event source on SMP systems, so the
- * broadcast mechanism is used. On UP systems simply ignore it.
- */
- if (local_apic_timer_disabled) {
- /* No broadcast on UP ! */
- if (num_possible_cpus() > 1) {
- lapic_clockevent.mult = 1;
- setup_APIC_timer();
- }
- return;
- }
-
- apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
- "calibrating APIC timer ...\n");
-
local_irq_disable();
/* Replace the global interrupt handler */
@@ -489,8 +497,6 @@ void __init setup_boot_APIC_clock(void)
calibration_result / (1000000 / HZ),
calibration_result % (1000000 / HZ));
- local_apic_timer_verify_ok = 1;
-
/*
* Do a sanity check on the APIC calibration result
*/
@@ -498,12 +504,11 @@ void __init setup_boot_APIC_clock(void)
local_irq_enable();
printk(KERN_WARNING
"APIC frequency too slow, disabling apic timer\n");
- /* No broadcast on UP ! */
- if (num_possible_cpus() > 1)
- setup_APIC_timer();
- return;
+ return -1;
}
+ local_apic_timer_verify_ok = 1;
+
/* We trust the pm timer based calibration */
if (!pm_referenced) {
apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
@@ -543,22 +548,55 @@ void __init setup_boot_APIC_clock(void)
if (!local_apic_timer_verify_ok) {
printk(KERN_WARNING
"APIC timer disabled due to verification failure.\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+/*
+ * Setup the boot APIC
+ *
+ * Calibrate and verify the result.
+ */
+void __init setup_boot_APIC_clock(void)
+{
+ /*
+ * The local apic timer can be disabled via the kernel
+ * commandline or from the CPU detection code. Register the lapic
+ * timer as a dummy clock event source on SMP systems, so the
+ * broadcast mechanism is used. On UP systems simply ignore it.
+ */
+ if (local_apic_timer_disabled) {
/* No broadcast on UP ! */
- if (num_possible_cpus() == 1)
- return;
- } else {
- /*
- * If nmi_watchdog is set to IO_APIC, we need the
- * PIT/HPET going. Otherwise register lapic as a dummy
- * device.
- */
- if (nmi_watchdog != NMI_IO_APIC)
- lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
- else
- printk(KERN_WARNING "APIC timer registered as dummy,"
- " due to nmi_watchdog=%d!\n", nmi_watchdog);
+ if (num_possible_cpus() > 1) {
+ lapic_clockevent.mult = 1;
+ setup_APIC_timer();
+ }
+ return;
+ }
+
+ apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
+ "calibrating APIC timer ...\n");
+
+ if (calibrate_APIC_clock()) {
+ /* No broadcast on UP ! */
+ if (num_possible_cpus() > 1)
+ setup_APIC_timer();
+ return;
}
+ /*
+ * If nmi_watchdog is set to IO_APIC, we need the
+ * PIT/HPET going. Otherwise register lapic as a dummy
+ * device.
+ */
+ if (nmi_watchdog != NMI_IO_APIC)
+ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+ else
+ printk(KERN_WARNING "APIC timer registered as dummy,"
+ " due to nmi_watchdog=%d!\n", nmi_watchdog);
+
/* Setup the lapic or request the broadcast */
setup_APIC_timer();
}
@@ -693,44 +731,44 @@ void clear_local_APIC(void)
*/
if (maxlvt >= 3) {
v = ERROR_APIC_VECTOR; /* any non-zero vector will do */
- apic_write_around(APIC_LVTERR, v | APIC_LVT_MASKED);
+ apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
}
/*
* Careful: we have to set masks only first to deassert
* any level-triggered sources.
*/
v = apic_read(APIC_LVTT);
- apic_write_around(APIC_LVTT, v | APIC_LVT_MASKED);
+ apic_write(APIC_LVTT, v | APIC_LVT_MASKED);
v = apic_read(APIC_LVT0);
- apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
+ apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
v = apic_read(APIC_LVT1);
- apic_write_around(APIC_LVT1, v | APIC_LVT_MASKED);
+ apic_write(APIC_LVT1, v | APIC_LVT_MASKED);
if (maxlvt >= 4) {
v = apic_read(APIC_LVTPC);
- apic_write_around(APIC_LVTPC, v | APIC_LVT_MASKED);
+ apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);
}
/* lets not touch this if we didn't frob it */
#ifdef CONFIG_X86_MCE_P4THERMAL
if (maxlvt >= 5) {
v = apic_read(APIC_LVTTHMR);
- apic_write_around(APIC_LVTTHMR, v | APIC_LVT_MASKED);
+ apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
}
#endif
/*
* Clean APIC state for other OSs:
*/
- apic_write_around(APIC_LVTT, APIC_LVT_MASKED);
- apic_write_around(APIC_LVT0, APIC_LVT_MASKED);
- apic_write_around(APIC_LVT1, APIC_LVT_MASKED);
+ apic_write(APIC_LVTT, APIC_LVT_MASKED);
+ apic_write(APIC_LVT0, APIC_LVT_MASKED);
+ apic_write(APIC_LVT1, APIC_LVT_MASKED);
if (maxlvt >= 3)
- apic_write_around(APIC_LVTERR, APIC_LVT_MASKED);
+ apic_write(APIC_LVTERR, APIC_LVT_MASKED);
if (maxlvt >= 4)
- apic_write_around(APIC_LVTPC, APIC_LVT_MASKED);
+ apic_write(APIC_LVTPC, APIC_LVT_MASKED);
#ifdef CONFIG_X86_MCE_P4THERMAL
if (maxlvt >= 5)
- apic_write_around(APIC_LVTTHMR, APIC_LVT_MASKED);
+ apic_write(APIC_LVTTHMR, APIC_LVT_MASKED);
#endif
/* Integrated APIC (!82489DX) ? */
if (lapic_is_integrated()) {
@@ -756,7 +794,7 @@ void disable_local_APIC(void)
*/
value = apic_read(APIC_SPIV);
value &= ~APIC_SPIV_APIC_ENABLED;
- apic_write_around(APIC_SPIV, value);
+ apic_write(APIC_SPIV, value);
/*
* When LAPIC was disabled by the BIOS and enabled by the kernel,
@@ -865,8 +903,8 @@ void __init sync_Arb_IDs(void)
apic_wait_icr_idle();
apic_printk(APIC_DEBUG, "Synchronizing Arb IDs.\n");
- apic_write_around(APIC_ICR, APIC_DEST_ALLINC | APIC_INT_LEVELTRIG
- | APIC_DM_INIT);
+ apic_write(APIC_ICR,
+ APIC_DEST_ALLINC | APIC_INT_LEVELTRIG | APIC_DM_INIT);
}
/*
@@ -902,16 +940,16 @@ void __init init_bsp_APIC(void)
else
value |= APIC_SPIV_FOCUS_DISABLED;
value |= SPURIOUS_APIC_VECTOR;
- apic_write_around(APIC_SPIV, value);
+ apic_write(APIC_SPIV, value);
/*
* Set up the virtual wire mode.
*/
- apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
+ apic_write(APIC_LVT0, APIC_DM_EXTINT);
value = APIC_DM_NMI;
if (!lapic_is_integrated()) /* 82489DX */
value |= APIC_LVT_LEVEL_TRIGGER;
- apic_write_around(APIC_LVT1, value);
+ apic_write(APIC_LVT1, value);
}
static void __cpuinit lapic_setup_esr(void)
@@ -926,7 +964,7 @@ static void __cpuinit lapic_setup_esr(void)
/* enables sending errors */
value = ERROR_APIC_VECTOR;
- apic_write_around(APIC_LVTERR, value);
+ apic_write(APIC_LVTERR, value);
/*
* spec says clear errors after enabling vector.
*/
@@ -989,7 +1027,7 @@ void __cpuinit setup_local_APIC(void)
*/
value = apic_read(APIC_TASKPRI);
value &= ~APIC_TPRI_MASK;
- apic_write_around(APIC_TASKPRI, value);
+ apic_write(APIC_TASKPRI, value);
/*
* After a crash, we no longer service the interrupts and a pending
@@ -1047,7 +1085,7 @@ void __cpuinit setup_local_APIC(void)
* Set spurious IRQ vector
*/
value |= SPURIOUS_APIC_VECTOR;
- apic_write_around(APIC_SPIV, value);
+ apic_write(APIC_SPIV, value);
/*
* Set up LVT0, LVT1:
@@ -1069,7 +1107,7 @@ void __cpuinit setup_local_APIC(void)
apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n",
smp_processor_id());
}
- apic_write_around(APIC_LVT0, value);
+ apic_write(APIC_LVT0, value);
/*
* only the BP should see the LINT1 NMI signal, obviously.
@@ -1080,7 +1118,7 @@ void __cpuinit setup_local_APIC(void)
value = APIC_DM_NMI | APIC_LVT_MASKED;
if (!integrated) /* 82489DX */
value |= APIC_LVT_LEVEL_TRIGGER;
- apic_write_around(APIC_LVT1, value);
+ apic_write(APIC_LVT1, value);
}
void __cpuinit end_local_APIC_setup(void)
@@ -1091,7 +1129,7 @@ void __cpuinit end_local_APIC_setup(void)
/* Disable the local apic timer */
value = apic_read(APIC_LVTT);
value |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
- apic_write_around(APIC_LVTT, value);
+ apic_write(APIC_LVTT, value);
setup_apic_nmi_watchdog(NULL);
apic_pm_activate();
@@ -1201,7 +1239,7 @@ void __init init_apic_mappings(void)
* default configuration (or the MP table is broken).
*/
if (boot_cpu_physical_apicid == -1U)
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
}
@@ -1241,7 +1279,7 @@ int __init APIC_init_uniprocessor(void)
* might be zero if read from MP tables. Get it from LAPIC.
*/
#ifdef CONFIG_CRASH_DUMP
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
#endif
physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
@@ -1419,7 +1457,7 @@ void disconnect_bsp_APIC(int virt_wire_setup)
value &= ~APIC_VECTOR_MASK;
value |= APIC_SPIV_APIC_ENABLED;
value |= 0xf;
- apic_write_around(APIC_SPIV, value);
+ apic_write(APIC_SPIV, value);
if (!virt_wire_setup) {
/*
@@ -1432,10 +1470,10 @@ void disconnect_bsp_APIC(int virt_wire_setup)
APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
- apic_write_around(APIC_LVT0, value);
+ apic_write(APIC_LVT0, value);
} else {
/* Disable LVT0 */
- apic_write_around(APIC_LVT0, APIC_LVT_MASKED);
+ apic_write(APIC_LVT0, APIC_LVT_MASKED);
}
/*
@@ -1449,7 +1487,7 @@ void disconnect_bsp_APIC(int virt_wire_setup)
APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI);
- apic_write_around(APIC_LVT1, value);
+ apic_write(APIC_LVT1, value);
}
}
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 1e3d32e27c1..46e612408ac 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>
@@ -46,6 +48,11 @@
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;
@@ -54,7 +61,7 @@ EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
/*
* Debug level, exported for io_apic.c
*/
-int apic_verbosity;
+unsigned int apic_verbosity;
/* Have we found an MP table */
int smp_found_config;
@@ -119,13 +126,13 @@ static int modern_apic(void)
return lapic_get_version() >= 0x14;
}
-void apic_wait_icr_idle(void)
+void xapic_wait_icr_idle(void)
{
while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
cpu_relax();
}
-u32 safe_apic_wait_icr_idle(void)
+u32 safe_xapic_wait_icr_idle(void)
{
u32 send_status;
int timeout;
@@ -141,6 +148,71 @@ u32 safe_apic_wait_icr_idle(void)
return send_status;
}
+void xapic_icr_write(u32 low, u32 id)
+{
+ apic_write(APIC_ICR2, id << 24);
+ apic_write(APIC_ICR, low);
+}
+
+u64 xapic_icr_read(void)
+{
+ u32 icr1, icr2;
+
+ icr2 = apic_read(APIC_ICR2);
+ icr1 = apic_read(APIC_ICR);
+
+ return (icr1 | ((u64)icr2 << 32));
+}
+
+static struct apic_ops xapic_ops = {
+ .read = native_apic_mem_read,
+ .write = native_apic_mem_write,
+ .write_atomic = native_apic_mem_write_atomic,
+ .icr_read = xapic_icr_read,
+ .icr_write = xapic_icr_write,
+ .wait_icr_idle = xapic_wait_icr_idle,
+ .safe_wait_icr_idle = safe_xapic_wait_icr_idle,
+};
+
+struct apic_ops __read_mostly *apic_ops = &xapic_ops;
+
+EXPORT_SYMBOL_GPL(apic_ops);
+
+static void x2apic_wait_icr_idle(void)
+{
+ /* no need to wait for icr idle in x2apic */
+ return;
+}
+
+static u32 safe_x2apic_wait_icr_idle(void)
+{
+ /* no need to wait for icr idle in x2apic */
+ return 0;
+}
+
+void x2apic_icr_write(u32 low, u32 id)
+{
+ wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
+}
+
+u64 x2apic_icr_read(void)
+{
+ unsigned long val;
+
+ rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val);
+ return val;
+}
+
+static struct apic_ops x2apic_ops = {
+ .read = native_apic_msr_read,
+ .write = native_apic_msr_write,
+ .write_atomic = native_apic_msr_write,
+ .icr_read = x2apic_icr_read,
+ .icr_write = x2apic_icr_write,
+ .wait_icr_idle = x2apic_wait_icr_idle,
+ .safe_wait_icr_idle = safe_x2apic_wait_icr_idle,
+};
+
/**
* enable_NMI_through_LVT0 - enable NMI through local vector table 0
*/
@@ -314,7 +386,7 @@ static void setup_APIC_timer(void)
#define TICK_COUNT 100000000
-static void __init calibrate_APIC_clock(void)
+static int __init calibrate_APIC_clock(void)
{
unsigned apic, apic_start;
unsigned long tsc, tsc_start;
@@ -368,6 +440,17 @@ static void __init calibrate_APIC_clock(void)
clockevent_delta2ns(0xF, &lapic_clockevent);
calibration_result = result / HZ;
+
+ /*
+ * Do a sanity check on the APIC calibration result
+ */
+ if (calibration_result < (1000000 / HZ)) {
+ printk(KERN_WARNING
+ "APIC frequency too slow, disabling apic timer\n");
+ return -1;
+ }
+
+ return 0;
}
/*
@@ -394,14 +477,7 @@ void __init setup_boot_APIC_clock(void)
}
printk(KERN_INFO "Using local APIC timer interrupts.\n");
- calibrate_APIC_clock();
-
- /*
- * Do a sanity check on the APIC calibration result
- */
- if (calibration_result < (1000000 / HZ)) {
- printk(KERN_WARNING
- "APIC frequency too slow, disabling apic timer\n");
+ if (calibrate_APIC_clock()) {
/* No broadcast on UP ! */
if (num_possible_cpus() > 1)
setup_APIC_timer();
@@ -626,10 +702,10 @@ int __init verify_local_APIC(void)
/*
* The ID register is read/write in a real APIC.
*/
- reg0 = read_apic_id();
+ reg0 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
apic_write(APIC_ID, reg0 ^ APIC_ID_MASK);
- reg1 = read_apic_id();
+ reg1 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
apic_write(APIC_ID, reg0);
if (reg1 != (reg0 ^ APIC_ID_MASK))
@@ -830,6 +906,125 @@ 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.
@@ -869,7 +1064,7 @@ void __init early_init_lapic_mapping(void)
* Fetch the APIC ID of the BSP in case we have a
* default configuration (or the MP table is broken).
*/
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
}
/**
@@ -877,6 +1072,11 @@ void __init early_init_lapic_mapping(void)
*/
void __init init_apic_mappings(void)
{
+ if (x2apic) {
+ boot_cpu_physical_apicid = 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
@@ -896,7 +1096,7 @@ void __init init_apic_mappings(void)
* Fetch the APIC ID of the BSP in case we have a
* default configuration (or the MP table is broken).
*/
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
}
/*
@@ -915,6 +1115,9 @@ int __init APIC_init_uniprocessor(void)
return -1;
}
+ enable_IR_x2apic();
+ setup_apic_routing();
+
verify_local_APIC();
connect_bsp_APIC();
@@ -1096,6 +1299,11 @@ void __cpuinit generic_processor_info(int apicid, int version)
cpu_set(cpu, cpu_present_map);
}
+int hard_smp_processor_id(void)
+{
+ return read_apic_id();
+}
+
/*
* Power management
*/
@@ -1132,7 +1340,7 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
maxlvt = lapic_get_maxlvt();
- apic_pm_state.apic_id = read_apic_id();
+ apic_pm_state.apic_id = apic_read(APIC_ID);
apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
apic_pm_state.apic_ldr = apic_read(APIC_LDR);
apic_pm_state.apic_dfr = apic_read(APIC_DFR);
@@ -1167,10 +1375,14 @@ 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);
@@ -1310,6 +1522,15 @@ __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/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1b1c56bb338..c9b58a806e8 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -131,13 +131,7 @@ static void __init check_popad(void)
* (for due to lack of "invlpg" and working WP on a i386)
* - In order to run on anything without a TSC, we need to be
* compiled for a i486.
- * - In order to support the local APIC on a buggy Pentium machine,
- * we need to be compiled with CONFIG_X86_GOOD_APIC disabled,
- * which happens implicitly if compiled for a Pentium or lower
- * (unless an advanced selection of CPU features is used) as an
- * otherwise config implies a properly working local APIC without
- * the need to do extra reads from the APIC.
-*/
+ */
static void __init check_config(void)
{
@@ -151,21 +145,6 @@ static void __init check_config(void)
if (boot_cpu_data.x86 == 3)
panic("Kernel requires i486+ for 'invlpg' and other features");
#endif
-
-/*
- * If we were told we had a good local APIC, check for buggy Pentia,
- * i.e. all B steppings and the C2 stepping of P54C when using their
- * integrated APIC (see 11AP erratum in "Pentium Processor
- * Specification Update").
- */
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_GOOD_APIC)
- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL
- && cpu_has_apic
- && boot_cpu_data.x86 == 5
- && boot_cpu_data.x86_model == 2
- && (boot_cpu_data.x86_mask < 6 || boot_cpu_data.x86_mask == 11))
- panic("Kernel compiled for PMMX+, assumes a local APIC without the read-before-write bug!");
-#endif
}
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
index 7b8cc72feb4..c6bee77ca9e 100644
--- a/arch/x86/kernel/cpu/common_64.c
+++ b/arch/x86/kernel/cpu/common_64.c
@@ -608,6 +608,8 @@ 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/cpu/feature_names.c b/arch/x86/kernel/cpu/feature_names.c
index e43ad4ad4cb..0bf4d37a048 100644
--- a/arch/x86/kernel/cpu/feature_names.c
+++ b/arch/x86/kernel/cpu/feature_names.c
@@ -45,7 +45,7 @@ const char * const x86_cap_flags[NCAPINTS*32] = {
/* Intel-defined (#2) */
"pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est",
"tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL,
- NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt",
+ NULL, NULL, "dca", "sse4_1", "sse4_2", "x2apic", NULL, "popcnt",
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
/* VIA/Cyrix/Centaur-defined */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 70609efdf1d..b75f2569b8f 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -227,6 +227,16 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
if (cpu_has_bts)
ds_init_intel(c);
+ /*
+ * See if we have a good local APIC by checking for buggy Pentia,
+ * i.e. all B steppings and the C2 stepping of P54C when using their
+ * integrated APIC (see 11AP erratum in "Pentium Processor
+ * Specification Update").
+ */
+ if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
+ (c->x86_mask < 0x6 || c->x86_mask == 0xb))
+ set_cpu_cap(c, X86_FEATURE_11AP);
+
#ifdef CONFIG_X86_NUMAQ
numaq_tsc_disable();
#endif
diff --git a/arch/x86/kernel/cpu/mcheck/p4.c b/arch/x86/kernel/cpu/mcheck/p4.c
index eef001ad3bd..9b60fce09f7 100644
--- a/arch/x86/kernel/cpu/mcheck/p4.c
+++ b/arch/x86/kernel/cpu/mcheck/p4.c
@@ -102,7 +102,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
/* The temperature transition interrupt handler setup */
h = THERMAL_APIC_VECTOR; /* our delivery vector */
h |= (APIC_DM_FIXED | APIC_LVT_MASKED); /* we'll mask till we're ready */
- apic_write_around(APIC_LVTTHMR, h);
+ apic_write(APIC_LVTTHMR, h);
rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x03 , h);
@@ -114,7 +114,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h);
l = apic_read(APIC_LVTTHMR);
- apic_write_around(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+ apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
printk(KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu);
/* enable thermal throttle processing */
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index 1fa8be5bd21..3940d8161f8 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>
@@ -29,6 +30,15 @@ DEFINE_PER_CPU(int, x2apic_extra_bits);
struct genapic __read_mostly *genapic = &apic_flat;
+static int x2apic_phys = 0;
+
+static int set_x2apic_phys_mode(char *arg)
+{
+ x2apic_phys = 1;
+ return 0;
+}
+early_param("x2apic_phys", set_x2apic_phys_mode);
+
static enum uv_system_type uv_system_type;
/*
@@ -38,7 +48,12 @@ void __init setup_apic_routing(void)
{
if (uv_system_type == UV_NON_UNIQUE_APIC)
genapic = &apic_x2apic_uv_x;
- else
+ else if (cpu_has_x2apic && intr_remapping_enabled) {
+ if (x2apic_phys)
+ genapic = &apic_x2apic_phys;
+ else
+ genapic = &apic_x2apic_cluster;
+ } else
#ifdef CONFIG_ACPI
/*
* Quirk: some x86_64 machines can only use physical APIC mode
@@ -61,7 +76,7 @@ void __init setup_apic_routing(void)
/* Same for both flat and physical. */
-void send_IPI_self(int vector)
+void apic_send_IPI_self(int vector)
{
__send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
}
@@ -79,17 +94,6 @@ int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
return 0;
}
-unsigned int read_apic_id(void)
-{
- unsigned int id;
-
- WARN_ON(preemptible() && num_online_cpus() > 1);
- id = apic_read(APIC_ID);
- if (uv_system_type >= UV_X2APIC)
- id |= __get_cpu_var(x2apic_extra_bits);
- return id;
-}
-
enum uv_system_type get_uv_system_type(void)
{
return uv_system_type;
diff --git a/arch/x86/kernel/genapic_flat_64.c b/arch/x86/kernel/genapic_flat_64.c
index 1a9c68845ee..2c973cbf054 100644
--- a/arch/x86/kernel/genapic_flat_64.c
+++ b/arch/x86/kernel/genapic_flat_64.c
@@ -15,9 +15,11 @@
#include <linux/kernel.h>
#include <linux/ctype.h>
#include <linux/init.h>
+#include <linux/hardirq.h>
#include <asm/smp.h>
#include <asm/ipi.h>
#include <asm/genapic.h>
+#include <mach_apicdef.h>
static cpumask_t flat_target_cpus(void)
{
@@ -95,9 +97,33 @@ static void flat_send_IPI_all(int vector)
__send_IPI_shortcut(APIC_DEST_ALLINC, vector, APIC_DEST_LOGICAL);
}
+static unsigned int get_apic_id(unsigned long x)
+{
+ unsigned int id;
+
+ id = (((x)>>24) & 0xFFu);
+ return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+ unsigned long x;
+
+ x = ((id & 0xFFu)<<24);
+ return x;
+}
+
+static unsigned int read_xapic_id(void)
+{
+ unsigned int id;
+
+ id = get_apic_id(apic_read(APIC_ID));
+ return id;
+}
+
static int flat_apic_id_registered(void)
{
- return physid_isset(GET_APIC_ID(read_apic_id()), phys_cpu_present_map);
+ return physid_isset(read_xapic_id(), phys_cpu_present_map);
}
static unsigned int flat_cpu_mask_to_apicid(cpumask_t cpumask)
@@ -121,8 +147,12 @@ struct genapic apic_flat = {
.send_IPI_all = flat_send_IPI_all,
.send_IPI_allbutself = flat_send_IPI_allbutself,
.send_IPI_mask = flat_send_IPI_mask,
+ .send_IPI_self = apic_send_IPI_self,
.cpu_mask_to_apicid = flat_cpu_mask_to_apicid,
.phys_pkg_id = phys_pkg_id,
+ .get_apic_id = get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = (0xFFu<<24),
};
/*
@@ -185,6 +215,10 @@ struct genapic apic_physflat = {
.send_IPI_all = physflat_send_IPI_all,
.send_IPI_allbutself = physflat_send_IPI_allbutself,
.send_IPI_mask = physflat_send_IPI_mask,
+ .send_IPI_self = apic_send_IPI_self,
.cpu_mask_to_apicid = physflat_cpu_mask_to_apicid,
.phys_pkg_id = phys_pkg_id,
+ .get_apic_id = get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = (0xFFu<<24),
};
diff --git a/arch/x86/kernel/genx2apic_cluster.c b/arch/x86/kernel/genx2apic_cluster.c
new file mode 100644
index 00000000000..40bc0140d89
--- /dev/null
+++ b/arch/x86/kernel/genx2apic_cluster.c
@@ -0,0 +1,153 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <asm/smp.h>
+#include <asm/ipi.h>
+#include <asm/genapic.h>
+
+DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+
+/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */
+
+static cpumask_t x2apic_target_cpus(void)
+{
+ return cpumask_of_cpu(0);
+}
+
+/*
+ * for now each logical cpu is in its own vector allocation domain.
+ */
+static cpumask_t x2apic_vector_allocation_domain(int cpu)
+{
+ cpumask_t domain = CPU_MASK_NONE;
+ cpu_set(cpu, domain);
+ return domain;
+}
+
+static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
+ unsigned int dest)
+{
+ unsigned long cfg;
+
+ cfg = __prepare_ICR(0, vector, dest);
+
+ /*
+ * send the IPI.
+ */
+ x2apic_icr_write(cfg, apicid);
+}
+
+/*
+ * for now, we send the IPI's one by one in the cpumask.
+ * TBD: Based on the cpu mask, we can send the IPI's to the cluster group
+ * at once. We have 16 cpu's in a cluster. This will minimize IPI register
+ * writes.
+ */
+static void x2apic_send_IPI_mask(cpumask_t mask, int vector)
+{
+ unsigned long flags;
+ unsigned long query_cpu;
+
+ local_irq_save(flags);
+ for_each_cpu_mask(query_cpu, mask) {
+ __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+ vector, APIC_DEST_LOGICAL);
+ }
+ local_irq_restore(flags);
+}
+
+static void x2apic_send_IPI_allbutself(int vector)
+{
+ cpumask_t mask = cpu_online_map;
+
+ cpu_clear(smp_processor_id(), mask);
+
+ if (!cpus_empty(mask))
+ x2apic_send_IPI_mask(mask, vector);
+}
+
+static void x2apic_send_IPI_all(int vector)
+{
+ x2apic_send_IPI_mask(cpu_online_map, vector);
+}
+
+static int x2apic_apic_id_registered(void)
+{
+ return 1;
+}
+
+static unsigned int x2apic_cpu_mask_to_apicid(cpumask_t cpumask)
+{
+ int cpu;
+
+ /*
+ * We're using fixed IRQ delivery, can only return one phys APIC ID.
+ * May as well be the first.
+ */
+ cpu = first_cpu(cpumask);
+ if ((unsigned)cpu < NR_CPUS)
+ return per_cpu(x86_cpu_to_logical_apicid, cpu);
+ else
+ return BAD_APICID;
+}
+
+static unsigned int get_apic_id(unsigned long x)
+{
+ unsigned int id;
+
+ id = x;
+ return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+ unsigned long x;
+
+ x = id;
+ return x;
+}
+
+static unsigned int x2apic_read_id(void)
+{
+ return apic_read(APIC_ID);
+}
+
+static unsigned int phys_pkg_id(int index_msb)
+{
+ return x2apic_read_id() >> index_msb;
+}
+
+static void x2apic_send_IPI_self(int vector)
+{
+ apic_write(APIC_SELF_IPI, vector);
+}
+
+static void init_x2apic_ldr(void)
+{
+ int cpu = smp_processor_id();
+
+ per_cpu(x86_cpu_to_logical_apicid, cpu) = apic_read(APIC_LDR);
+ return;
+}
+
+struct genapic apic_x2apic_cluster = {
+ .name = "cluster x2apic",
+ .int_delivery_mode = dest_LowestPrio,
+ .int_dest_mode = (APIC_DEST_LOGICAL != 0),
+ .target_cpus = x2apic_target_cpus,
+ .vector_allocation_domain = x2apic_vector_allocation_domain,
+ .apic_id_registered = x2apic_apic_id_registered,
+ .init_apic_ldr = init_x2apic_ldr,
+ .send_IPI_all = x2apic_send_IPI_all,
+ .send_IPI_allbutself = x2apic_send_IPI_allbutself,
+ .send_IPI_mask = x2apic_send_IPI_mask,
+ .send_IPI_self = x2apic_send_IPI_self,
+ .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+ .phys_pkg_id = phys_pkg_id,
+ .get_apic_id = get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = (0xFFFFFFFFu),
+};
diff --git a/arch/x86/kernel/genx2apic_phys.c b/arch/x86/kernel/genx2apic_phys.c
new file mode 100644
index 00000000000..2f3c6ca19de
--- /dev/null
+++ b/arch/x86/kernel/genx2apic_phys.c
@@ -0,0 +1,140 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <asm/smp.h>
+#include <asm/ipi.h>
+#include <asm/genapic.h>
+
+
+/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */
+
+static cpumask_t x2apic_target_cpus(void)
+{
+ return cpumask_of_cpu(0);
+}
+
+static cpumask_t x2apic_vector_allocation_domain(int cpu)
+{
+ cpumask_t domain = CPU_MASK_NONE;
+ cpu_set(cpu, domain);
+ return domain;
+}
+
+static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
+ unsigned int dest)
+{
+ unsigned long cfg;
+
+ cfg = __prepare_ICR(0, vector, dest);
+
+ /*
+ * send the IPI.
+ */
+ x2apic_icr_write(cfg, apicid);
+}
+
+static void x2apic_send_IPI_mask(cpumask_t mask, int vector)
+{
+ unsigned long flags;
+ unsigned long query_cpu;
+
+ local_irq_save(flags);
+ for_each_cpu_mask(query_cpu, mask) {
+ __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu),
+ vector, APIC_DEST_PHYSICAL);
+ }
+ local_irq_restore(flags);
+}
+
+static void x2apic_send_IPI_allbutself(int vector)
+{
+ cpumask_t mask = cpu_online_map;
+
+ cpu_clear(smp_processor_id(), mask);
+
+ if (!cpus_empty(mask))
+ x2apic_send_IPI_mask(mask, vector);
+}
+
+static void x2apic_send_IPI_all(int vector)
+{
+ x2apic_send_IPI_mask(cpu_online_map, vector);
+}
+
+static int x2apic_apic_id_registered(void)
+{
+ return 1;
+}
+
+static unsigned int x2apic_cpu_mask_to_apicid(cpumask_t cpumask)
+{
+ int cpu;
+
+ /*
+ * We're using fixed IRQ delivery, can only return one phys APIC ID.
+ * May as well be the first.
+ */
+ cpu = first_cpu(cpumask);
+ if ((unsigned)cpu < NR_CPUS)
+ return per_cpu(x86_cpu_to_apicid, cpu);
+ else
+ return BAD_APICID;
+}
+
+static unsigned int get_apic_id(unsigned long x)
+{
+ unsigned int id;
+
+ id = x;
+ return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+ unsigned long x;
+
+ x = id;
+ return x;
+}
+
+static unsigned int x2apic_read_id(void)
+{
+ return apic_read(APIC_ID);
+}
+
+static unsigned int phys_pkg_id(int index_msb)
+{
+ return x2apic_read_id() >> index_msb;
+}
+
+void x2apic_send_IPI_self(int vector)
+{
+ apic_write(APIC_SELF_IPI, vector);
+}
+
+void init_x2apic_ldr(void)
+{
+ return;
+}
+
+struct genapic apic_x2apic_phys = {
+ .name = "physical x2apic",
+ .int_delivery_mode = dest_Fixed,
+ .int_dest_mode = (APIC_DEST_PHYSICAL != 0),
+ .target_cpus = x2apic_target_cpus,
+ .vector_allocation_domain = x2apic_vector_allocation_domain,
+ .apic_id_registered = x2apic_apic_id_registered,
+ .init_apic_ldr = init_x2apic_ldr,
+ .send_IPI_all = x2apic_send_IPI_all,
+ .send_IPI_allbutself = x2apic_send_IPI_allbutself,
+ .send_IPI_mask = x2apic_send_IPI_mask,
+ .send_IPI_self = x2apic_send_IPI_self,
+ .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+ .phys_pkg_id = phys_pkg_id,
+ .get_apic_id = get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = (0xFFFFFFFFu),
+};
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index 3c392934069..a8e5cb4c4d4 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -18,6 +18,7 @@
#include <linux/sched.h>
#include <linux/bootmem.h>
#include <linux/module.h>
+#include <linux/hardirq.h>
#include <asm/smp.h>
#include <asm/ipi.h>
#include <asm/genapic.h>
@@ -123,6 +124,10 @@ static int uv_apic_id_registered(void)
return 1;
}
+static void uv_init_apic_ldr(void)
+{
+}
+
static unsigned int uv_cpu_mask_to_apicid(cpumask_t cpumask)
{
int cpu;
@@ -138,9 +143,34 @@ static unsigned int uv_cpu_mask_to_apicid(cpumask_t cpumask)
return BAD_APICID;
}
+static unsigned int get_apic_id(unsigned long x)
+{
+ unsigned int id;
+
+ WARN_ON(preemptible() && num_online_cpus() > 1);
+ id = x | __get_cpu_var(x2apic_extra_bits);
+
+ return id;
+}
+
+static long set_apic_id(unsigned int id)
+{
+ unsigned long x;
+
+ /* maskout x2apic_extra_bits ? */
+ x = id;
+ return x;
+}
+
+static unsigned int uv_read_apic_id(void)
+{
+
+ return get_apic_id(apic_read(APIC_ID));
+}
+
static unsigned int phys_pkg_id(int index_msb)
{
- return GET_APIC_ID(read_apic_id()) >> index_msb;
+ return uv_read_apic_id() >> index_msb;
}
#ifdef ZZZ /* Needs x2apic patch */
@@ -157,12 +187,16 @@ struct genapic apic_x2apic_uv_x = {
.target_cpus = uv_target_cpus,
.vector_allocation_domain = uv_vector_allocation_domain,/* Fixme ZZZ */
.apic_id_registered = uv_apic_id_registered,
+ .init_apic_ldr = uv_init_apic_ldr,
.send_IPI_all = uv_send_IPI_all,
.send_IPI_allbutself = uv_send_IPI_allbutself,
.send_IPI_mask = uv_send_IPI_mask,
/* ZZZ.send_IPI_self = uv_send_IPI_self, */
.cpu_mask_to_apicid = uv_cpu_mask_to_apicid,
.phys_pkg_id = phys_pkg_id, /* Fixme ZZZ */
+ .get_apic_id = get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = (0xFFFFFFFFu),
};
static __cpuinit void set_x2apic_extra_bits(int pnode)
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index dc92b49d920..4b8a53d841f 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -282,6 +282,30 @@ static int __init i8259A_init_sysfs(void)
device_initcall(i8259A_init_sysfs);
+void mask_8259A(void)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&i8259A_lock, flags);
+
+ outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */
+ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */
+
+ spin_unlock_irqrestore(&i8259A_lock, flags);
+}
+
+void unmask_8259A(void)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&i8259A_lock, flags);
+
+ outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
+ outb(cached_slave_mask, PIC_SLAVE_IMR); /* restore slave IRQ mask */
+
+ spin_unlock_irqrestore(&i8259A_lock, flags);
+}
+
void init_8259A(int auto_eoi)
{
unsigned long flags;
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 558abf4c796..98e4db5373f 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -756,7 +756,7 @@ void send_IPI_self(int vector)
/*
* Send the IPI. The write to APIC_ICR fires this off.
*/
- apic_write_around(APIC_ICR, cfg);
+ apic_write(APIC_ICR, cfg);
}
#endif /* !CONFIG_SMP */
@@ -1494,7 +1494,7 @@ void /*__init*/ print_local_APIC(void *dummy)
smp_processor_id(), hard_smp_processor_id());
v = apic_read(APIC_ID);
printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v,
- GET_APIC_ID(read_apic_id()));
+ GET_APIC_ID(v));
v = apic_read(APIC_LVR);
printk(KERN_INFO "... APIC VERSION: %08x\n", v);
ver = GET_APIC_VERSION(v);
@@ -1702,8 +1702,7 @@ void disable_IO_APIC(void)
entry.dest_mode = 0; /* Physical */
entry.delivery_mode = dest_ExtINT; /* ExtInt */
entry.vector = 0;
- entry.dest.physical.physical_dest =
- GET_APIC_ID(read_apic_id());
+ entry.dest.physical.physical_dest = read_apic_id();
/*
* Add it to the IO-APIC irq-routing table:
@@ -2030,7 +2029,7 @@ static void mask_lapic_irq(unsigned int irq)
unsigned long v;
v = apic_read(APIC_LVT0);
- apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
+ apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
}
static void unmask_lapic_irq(unsigned int irq)
@@ -2038,7 +2037,7 @@ static void unmask_lapic_irq(unsigned int irq)
unsigned long v;
v = apic_read(APIC_LVT0);
- apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED);
+ apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
}
static struct irq_chip lapic_chip __read_mostly = {
@@ -2168,7 +2167,7 @@ static inline void __init check_timer(void)
* The AEOI mode will finish them in the 8259A
* automatically.
*/
- apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+ apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
init_8259A(1);
timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
@@ -2177,8 +2176,9 @@ static inline void __init check_timer(void)
pin2 = ioapic_i8259.pin;
apic2 = ioapic_i8259.apic;
- printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
- vector, apic1, pin1, apic2, pin2);
+ apic_printk(APIC_QUIET, KERN_INFO "..TIMER: vector=0x%02X "
+ "apic1=%d pin1=%d apic2=%d pin2=%d\n",
+ vector, apic1, pin1, apic2, pin2);
/*
* Some BIOS writers are clueless and report the ExtINTA
@@ -2216,12 +2216,13 @@ static inline void __init check_timer(void)
}
clear_IO_APIC_pin(apic1, pin1);
if (!no_pin1)
- printk(KERN_ERR "..MP-BIOS bug: "
- "8254 timer not connected to IO-APIC\n");
+ apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: "
+ "8254 timer not connected to IO-APIC\n");
- printk(KERN_INFO "...trying to set up timer (IRQ0) "
- "through the 8259A ... ");
- printk("\n..... (found pin %d) ...", pin2);
+ apic_printk(APIC_QUIET, KERN_INFO "...trying to set up timer "
+ "(IRQ0) through the 8259A ...\n");
+ apic_printk(APIC_QUIET, KERN_INFO
+ "..... (found apic %d pin %d) ...\n", apic2, pin2);
/*
* legacy devices should be connected to IO APIC #0
*/
@@ -2230,7 +2231,7 @@ static inline void __init check_timer(void)
unmask_IO_APIC_irq(0);
enable_8259A_irq(0);
if (timer_irq_works()) {
- printk("works.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
timer_through_8259 = 1;
if (nmi_watchdog == NMI_IO_APIC) {
disable_8259A_irq(0);
@@ -2244,44 +2245,47 @@ static inline void __init check_timer(void)
*/
disable_8259A_irq(0);
clear_IO_APIC_pin(apic2, pin2);
- printk(" failed.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
}
if (nmi_watchdog == NMI_IO_APIC) {
- printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
+ apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work "
+ "through the IO-APIC - disabling NMI Watchdog!\n");
nmi_watchdog = NMI_NONE;
}
timer_ack = 0;
- printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
+ apic_printk(APIC_QUIET, KERN_INFO
+ "...trying to set up timer as Virtual Wire IRQ...\n");
lapic_register_intr(0, vector);
- apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */
+ apic_write(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */
enable_8259A_irq(0);
if (timer_irq_works()) {
- printk(" works.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
goto out;
}
disable_8259A_irq(0);
- apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
- printk(" failed.\n");
+ apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
+ apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
- printk(KERN_INFO "...trying to set up timer as ExtINT IRQ...");
+ apic_printk(APIC_QUIET, KERN_INFO
+ "...trying to set up timer as ExtINT IRQ...\n");
init_8259A(0);
make_8259A_irq(0);
- apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
+ apic_write(APIC_LVT0, APIC_DM_EXTINT);
unlock_ExtINT_logic();
if (timer_irq_works()) {
- printk(" works.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
goto out;
}
- printk(" failed :(.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "..... failed :(.\n");
panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a "
- "report. Then try booting with the 'noapic' option");
+ "report. Then try booting with the 'noapic' option.\n");
out:
local_irq_restore(flags);
}
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 6510cde36b3..116aac36598 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -37,6 +37,7 @@
#include <acpi/acpi_bus.h>
#endif
#include <linux/bootmem.h>
+#include <linux/dmar.h>
#include <asm/idle.h>
#include <asm/io.h>
@@ -45,9 +46,11 @@
#include <asm/proto.h>
#include <asm/acpi.h>
#include <asm/dma.h>
+#include <asm/i8259.h>
#include <asm/nmi.h>
#include <asm/msidef.h>
#include <asm/hypertransport.h>
+#include <asm/irq_remapping.h>
#include <mach_ipi.h>
#include <mach_apic.h>
@@ -107,6 +110,9 @@ DEFINE_SPINLOCK(vector_lock);
*/
int nr_ioapic_registers[MAX_IO_APICS];
+/* I/O APIC RTE contents at the OS boot up */
+struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS];
+
/* I/O APIC entries */
struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
int nr_ioapics;
@@ -302,7 +308,12 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
pin = entry->pin;
if (pin == -1)
break;
- io_apic_write(apic, 0x11 + pin*2, dest);
+ /*
+ * With interrupt-remapping, destination information comes
+ * from interrupt-remapping table entry.
+ */
+ if (!irq_remapped(irq))
+ io_apic_write(apic, 0x11 + pin*2, dest);
reg = io_apic_read(apic, 0x10 + pin*2);
reg &= ~IO_APIC_REDIR_VECTOR_MASK;
reg |= vector;
@@ -439,6 +450,69 @@ static void clear_IO_APIC (void)
clear_IO_APIC_pin(apic, pin);
}
+/*
+ * Saves and masks all the unmasked IO-APIC RTE's
+ */
+int save_mask_IO_APIC_setup(void)
+{
+ union IO_APIC_reg_01 reg_01;
+ unsigned long flags;
+ int apic, pin;
+
+ /*
+ * The number of IO-APIC IRQ registers (== #pins):
+ */
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(apic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ nr_ioapic_registers[apic] = reg_01.bits.entries+1;
+ }
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ early_ioapic_entries[apic] =
+ kzalloc(sizeof(struct IO_APIC_route_entry) *
+ nr_ioapic_registers[apic], GFP_KERNEL);
+ if (!early_ioapic_entries[apic])
+ return -ENOMEM;
+ }
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+ struct IO_APIC_route_entry entry;
+
+ entry = early_ioapic_entries[apic][pin] =
+ ioapic_read_entry(apic, pin);
+ if (!entry.mask) {
+ entry.mask = 1;
+ ioapic_write_entry(apic, pin, entry);
+ }
+ }
+ return 0;
+}
+
+void restore_IO_APIC_setup(void)
+{
+ int apic, pin;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+ ioapic_write_entry(apic, pin,
+ early_ioapic_entries[apic][pin]);
+}
+
+void reinit_intr_remapped_IO_APIC(int intr_remapping)
+{
+ /*
+ * for now plain restore of previous settings.
+ * TBD: In the case of OS enabling interrupt-remapping,
+ * IO-APIC RTE's need to be setup to point to interrupt-remapping
+ * table entries. for now, do a plain restore, and wait for
+ * the setup_IO_APIC_irqs() to do proper initialization.
+ */
+ restore_IO_APIC_setup();
+}
+
int skip_ioapic_setup;
int ioapic_force;
@@ -833,18 +907,98 @@ void setup_vector_irq(int cpu)
static struct irq_chip ioapic_chip;
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip;
+#endif
static void ioapic_register_intr(int irq, unsigned long trigger)
{
- if (trigger) {
+ if (trigger)
irq_desc[irq].status |= IRQ_LEVEL;
- set_irq_chip_and_handler_name(irq, &ioapic_chip,
- handle_fasteoi_irq, "fasteoi");
- } else {
+ else
irq_desc[irq].status &= ~IRQ_LEVEL;
+
+#ifdef CONFIG_INTR_REMAP
+ if (irq_remapped(irq)) {
+ irq_desc[irq].status |= IRQ_MOVE_PCNTXT;
+ if (trigger)
+ set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+ handle_fasteoi_irq,
+ "fasteoi");
+ else
+ set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+ handle_edge_irq, "edge");
+ return;
+ }
+#endif
+ if (trigger)
+ set_irq_chip_and_handler_name(irq, &ioapic_chip,
+ handle_fasteoi_irq,
+ "fasteoi");
+ else
set_irq_chip_and_handler_name(irq, &ioapic_chip,
handle_edge_irq, "edge");
+}
+
+static int setup_ioapic_entry(int apic, int irq,
+ struct IO_APIC_route_entry *entry,
+ unsigned int destination, int trigger,
+ int polarity, int vector)
+{
+ /*
+ * add it to the IO-APIC irq-routing table:
+ */
+ memset(entry,0,sizeof(*entry));
+
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled) {
+ struct intel_iommu *iommu = map_ioapic_to_ir(apic);
+ struct irte irte;
+ struct IR_IO_APIC_route_entry *ir_entry =
+ (struct IR_IO_APIC_route_entry *) entry;
+ int index;
+
+ if (!iommu)
+ panic("No mapping iommu for ioapic %d\n", apic);
+
+ index = alloc_irte(iommu, irq, 1);
+ if (index < 0)
+ panic("Failed to allocate IRTE for ioapic %d\n", apic);
+
+ memset(&irte, 0, sizeof(irte));
+
+ irte.present = 1;
+ irte.dst_mode = INT_DEST_MODE;
+ irte.trigger_mode = trigger;
+ irte.dlvry_mode = INT_DELIVERY_MODE;
+ irte.vector = vector;
+ irte.dest_id = IRTE_DEST(destination);
+
+ modify_irte(irq, &irte);
+
+ ir_entry->index2 = (index >> 15) & 0x1;
+ ir_entry->zero = 0;
+ ir_entry->format = 1;
+ ir_entry->index = (index & 0x7fff);
+ } else
+#endif
+ {
+ entry->delivery_mode = INT_DELIVERY_MODE;
+ entry->dest_mode = INT_DEST_MODE;
+ entry->dest = destination;
}
+
+ entry->mask = 0; /* enable IRQ */
+ entry->trigger = trigger;
+ entry->polarity = polarity;
+ entry->vector = vector;
+
+ /* Mask level triggered irqs.
+ * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
+ */
+ if (trigger)
+ entry->mask = 1;
+ return 0;
}
static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
@@ -869,24 +1023,15 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
irq, trigger, polarity);
- /*
- * add it to the IO-APIC irq-routing table:
- */
- memset(&entry,0,sizeof(entry));
- entry.delivery_mode = INT_DELIVERY_MODE;
- entry.dest_mode = INT_DEST_MODE;
- entry.dest = cpu_mask_to_apicid(mask);
- entry.mask = 0; /* enable IRQ */
- entry.trigger = trigger;
- entry.polarity = polarity;
- entry.vector = cfg->vector;
-
- /* Mask level triggered irqs.
- * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
- */
- if (trigger)
- entry.mask = 1;
+ if (setup_ioapic_entry(mp_ioapics[apic].mp_apicid, irq, &entry,
+ cpu_mask_to_apicid(mask), trigger, polarity,
+ cfg->vector)) {
+ printk("Failed to setup ioapic entry for ioapic %d, pin %d\n",
+ mp_ioapics[apic].mp_apicid, pin);
+ __clear_irq_vector(irq);
+ return;
+ }
ioapic_register_intr(irq, trigger);
if (irq < 16)
@@ -938,6 +1083,9 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
{
struct IO_APIC_route_entry entry;
+ if (intr_remapping_enabled)
+ return;
+
memset(&entry, 0, sizeof(entry));
/*
@@ -1084,6 +1232,7 @@ static __apicdebuginit void print_APIC_bitfield (int base)
void __apicdebuginit print_local_APIC(void * dummy)
{
unsigned int v, ver, maxlvt;
+ unsigned long icr;
if (apic_verbosity == APIC_QUIET)
return;
@@ -1091,7 +1240,7 @@ void __apicdebuginit print_local_APIC(void * dummy)
printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
smp_processor_id(), hard_smp_processor_id());
v = apic_read(APIC_ID);
- printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
+ printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, read_apic_id());
v = apic_read(APIC_LVR);
printk(KERN_INFO "... APIC VERSION: %08x\n", v);
ver = GET_APIC_VERSION(v);
@@ -1127,10 +1276,9 @@ void __apicdebuginit print_local_APIC(void * dummy)
v = apic_read(APIC_ESR);
printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
- v = apic_read(APIC_ICR);
- printk(KERN_DEBUG "... APIC ICR: %08x\n", v);
- v = apic_read(APIC_ICR2);
- printk(KERN_DEBUG "... APIC ICR2: %08x\n", v);
+ icr = apic_icr_read();
+ printk(KERN_DEBUG "... APIC ICR: %08x\n", icr);
+ printk(KERN_DEBUG "... APIC ICR2: %08x\n", icr >> 32);
v = apic_read(APIC_LVTT);
printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
@@ -1285,7 +1433,7 @@ void disable_IO_APIC(void)
entry.dest_mode = 0; /* Physical */
entry.delivery_mode = dest_ExtINT; /* ExtInt */
entry.vector = 0;
- entry.dest = GET_APIC_ID(read_apic_id());
+ entry.dest = read_apic_id();
/*
* Add it to the IO-APIC irq-routing table:
@@ -1393,6 +1541,147 @@ static int ioapic_retrigger_irq(unsigned int irq)
*/
#ifdef CONFIG_SMP
+
+#ifdef CONFIG_INTR_REMAP
+static void ir_irq_migration(struct work_struct *work);
+
+static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration);
+
+/*
+ * Migrate the IO-APIC irq in the presence of intr-remapping.
+ *
+ * For edge triggered, irq migration is a simple atomic update(of vector
+ * and cpu destination) of IRTE and flush the hardware cache.
+ *
+ * For level triggered, we need to modify the io-apic RTE aswell with the update
+ * vector information, along with modifying IRTE with vector and destination.
+ * So irq migration for level triggered is little bit more complex compared to
+ * edge triggered migration. But the good news is, we use the same algorithm
+ * for level triggered migration as we have today, only difference being,
+ * we now initiate the irq migration from process context instead of the
+ * interrupt context.
+ *
+ * In future, when we do a directed EOI (combined with cpu EOI broadcast
+ * suppression) to the IO-APIC, level triggered irq migration will also be
+ * as simple as edge triggered migration and we can do the irq migration
+ * with a simple atomic update to IO-APIC RTE.
+ */
+static void migrate_ioapic_irq(int irq, cpumask_t mask)
+{
+ struct irq_cfg *cfg = irq_cfg + irq;
+ struct irq_desc *desc = irq_desc + irq;
+ cpumask_t tmp, cleanup_mask;
+ struct irte irte;
+ int modify_ioapic_rte = desc->status & IRQ_LEVEL;
+ unsigned int dest;
+ unsigned long flags;
+
+ cpus_and(tmp, mask, cpu_online_map);
+ if (cpus_empty(tmp))
+ return;
+
+ if (get_irte(irq, &irte))
+ return;
+
+ if (assign_irq_vector(irq, mask))
+ return;
+
+ cpus_and(tmp, cfg->domain, mask);
+ dest = cpu_mask_to_apicid(tmp);
+
+ if (modify_ioapic_rte) {
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __target_IO_APIC_irq(irq, dest, cfg->vector);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ }
+
+ irte.vector = cfg->vector;
+ irte.dest_id = IRTE_DEST(dest);
+
+ /*
+ * Modified the IRTE and flushes the Interrupt entry cache.
+ */
+ modify_irte(irq, &irte);
+
+ if (cfg->move_in_progress) {
+ cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+ cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+ send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+ cfg->move_in_progress = 0;
+ }
+
+ irq_desc[irq].affinity = mask;
+}
+
+static int migrate_irq_remapped_level(int irq)
+{
+ int ret = -1;
+
+ mask_IO_APIC_irq(irq);
+
+ if (io_apic_level_ack_pending(irq)) {
+ /*
+ * Interrupt in progress. Migrating irq now will change the
+ * vector information in the IO-APIC RTE and that will confuse
+ * the EOI broadcast performed by cpu.
+ * So, delay the irq migration to the next instance.
+ */
+ schedule_delayed_work(&ir_migration_work, 1);
+ goto unmask;
+ }
+
+ /* everthing is clear. we have right of way */
+ migrate_ioapic_irq(irq, irq_desc[irq].pending_mask);
+
+ ret = 0;
+ irq_desc[irq].status &= ~IRQ_MOVE_PENDING;
+ cpus_clear(irq_desc[irq].pending_mask);
+
+unmask:
+ unmask_IO_APIC_irq(irq);
+ return ret;
+}
+
+static void ir_irq_migration(struct work_struct *work)
+{
+ int irq;
+
+ for (irq = 0; irq < NR_IRQS; irq++) {
+ struct irq_desc *desc = irq_desc + irq;
+ if (desc->status & IRQ_MOVE_PENDING) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ if (!desc->chip->set_affinity ||
+ !(desc->status & IRQ_MOVE_PENDING)) {
+ desc->status &= ~IRQ_MOVE_PENDING;
+ spin_unlock_irqrestore(&desc->lock, flags);
+ continue;
+ }
+
+ desc->chip->set_affinity(irq,
+ irq_desc[irq].pending_mask);
+ spin_unlock_irqrestore(&desc->lock, flags);
+ }
+ }
+}
+
+/*
+ * Migrates the IRQ destination in the process context.
+ */
+static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+ if (irq_desc[irq].status & IRQ_LEVEL) {
+ irq_desc[irq].status |= IRQ_MOVE_PENDING;
+ irq_desc[irq].pending_mask = mask;
+ migrate_irq_remapped_level(irq);
+ return;
+ }
+
+ migrate_ioapic_irq(irq, mask);
+}
+#endif
+
asmlinkage void smp_irq_move_cleanup_interrupt(void)
{
unsigned vector, me;
@@ -1449,6 +1738,17 @@ static void irq_complete_move(unsigned int irq)
#else
static inline void irq_complete_move(unsigned int irq) {}
#endif
+#ifdef CONFIG_INTR_REMAP
+static void ack_x2apic_level(unsigned int irq)
+{
+ ack_x2APIC_irq();
+}
+
+static void ack_x2apic_edge(unsigned int irq)
+{
+ ack_x2APIC_irq();
+}
+#endif
static void ack_apic_edge(unsigned int irq)
{
@@ -1523,6 +1823,21 @@ static struct irq_chip ioapic_chip __read_mostly = {
.retrigger = ioapic_retrigger_irq,
};
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip __read_mostly = {
+ .name = "IR-IO-APIC",
+ .startup = startup_ioapic_irq,
+ .mask = mask_IO_APIC_irq,
+ .unmask = unmask_IO_APIC_irq,
+ .ack = ack_x2apic_edge,
+ .eoi = ack_x2apic_level,
+#ifdef CONFIG_SMP
+ .set_affinity = set_ir_ioapic_affinity_irq,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+#endif
+
static inline void init_IO_APIC_traps(void)
{
int irq;
@@ -1696,8 +2011,9 @@ static inline void __init check_timer(void)
pin2 = ioapic_i8259.pin;
apic2 = ioapic_i8259.apic;
- apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
- cfg->vector, apic1, pin1, apic2, pin2);
+ apic_printk(APIC_QUIET, KERN_INFO "..TIMER: vector=0x%02X "
+ "apic1=%d pin1=%d apic2=%d pin2=%d\n",
+ cfg->vector, apic1, pin1, apic2, pin2);
/*
* Some BIOS writers are clueless and report the ExtINTA
@@ -1707,6 +2023,8 @@ static inline void __init check_timer(void)
* 8259A.
*/
if (pin1 == -1) {
+ if (intr_remapping_enabled)
+ panic("BIOS bug: timer not connected to IO-APIC");
pin1 = pin2;
apic1 = apic2;
no_pin1 = 1;
@@ -1733,16 +2051,17 @@ static inline void __init check_timer(void)
clear_IO_APIC_pin(0, pin1);
goto out;
}
+ if (intr_remapping_enabled)
+ panic("timer doesn't work through Interrupt-remapped IO-APIC");
clear_IO_APIC_pin(apic1, pin1);
if (!no_pin1)
- apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: "
+ apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: "
"8254 timer not connected to IO-APIC\n");
- apic_printk(APIC_VERBOSE,KERN_INFO
- "...trying to set up timer (IRQ0) "
- "through the 8259A ... ");
- apic_printk(APIC_VERBOSE,"\n..... (found apic %d pin %d) ...",
- apic2, pin2);
+ apic_printk(APIC_QUIET, KERN_INFO "...trying to set up timer "
+ "(IRQ0) through the 8259A ...\n");
+ apic_printk(APIC_QUIET, KERN_INFO
+ "..... (found apic %d pin %d) ...\n", apic2, pin2);
/*
* legacy devices should be connected to IO APIC #0
*/
@@ -1751,7 +2070,7 @@ static inline void __init check_timer(void)
unmask_IO_APIC_irq(0);
enable_8259A_irq(0);
if (timer_irq_works()) {
- apic_printk(APIC_VERBOSE," works.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
timer_through_8259 = 1;
if (nmi_watchdog == NMI_IO_APIC) {
disable_8259A_irq(0);
@@ -1765,29 +2084,32 @@ static inline void __init check_timer(void)
*/
disable_8259A_irq(0);
clear_IO_APIC_pin(apic2, pin2);
- apic_printk(APIC_VERBOSE," failed.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
}
if (nmi_watchdog == NMI_IO_APIC) {
- printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
+ apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work "
+ "through the IO-APIC - disabling NMI Watchdog!\n");
nmi_watchdog = NMI_NONE;
}
- apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
+ apic_printk(APIC_QUIET, KERN_INFO
+ "...trying to set up timer as Virtual Wire IRQ...\n");
lapic_register_intr(0);
apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */
enable_8259A_irq(0);
if (timer_irq_works()) {
- apic_printk(APIC_VERBOSE," works.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
goto out;
}
disable_8259A_irq(0);
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
- apic_printk(APIC_VERBOSE," failed.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
- apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as ExtINT IRQ...");
+ apic_printk(APIC_QUIET, KERN_INFO
+ "...trying to set up timer as ExtINT IRQ...\n");
init_8259A(0);
make_8259A_irq(0);
@@ -1796,11 +2118,12 @@ static inline void __init check_timer(void)
unlock_ExtINT_logic();
if (timer_irq_works()) {
- apic_printk(APIC_VERBOSE," works.\n");
+ apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
goto out;
}
- apic_printk(APIC_VERBOSE," failed :(.\n");
- panic("IO-APIC + timer doesn't work! Try using the 'noapic' kernel parameter\n");
+ apic_printk(APIC_QUIET, KERN_INFO "..... failed :(.\n");
+ panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a "
+ "report. Then try booting with the 'noapic' option.\n");
out:
local_irq_restore(flags);
}
@@ -1969,6 +2292,9 @@ void destroy_irq(unsigned int irq)
dynamic_irq_cleanup(irq);
+#ifdef CONFIG_INTR_REMAP
+ free_irte(irq);
+#endif
spin_lock_irqsave(&vector_lock, flags);
__clear_irq_vector(irq);
spin_unlock_irqrestore(&vector_lock, flags);
@@ -1987,11 +2313,42 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
tmp = TARGET_CPUS;
err = assign_irq_vector(irq, tmp);
- if (!err) {
- cpus_and(tmp, cfg->domain, tmp);
- dest = cpu_mask_to_apicid(tmp);
+ if (err)
+ return err;
+
+ cpus_and(tmp, cfg->domain, tmp);
+ dest = cpu_mask_to_apicid(tmp);
+
+#ifdef CONFIG_INTR_REMAP
+ if (irq_remapped(irq)) {
+ struct irte irte;
+ int ir_index;
+ u16 sub_handle;
+
+ ir_index = map_irq_to_irte_handle(irq, &sub_handle);
+ BUG_ON(ir_index == -1);
+
+ memset (&irte, 0, sizeof(irte));
+
+ irte.present = 1;
+ irte.dst_mode = INT_DEST_MODE;
+ irte.trigger_mode = 0; /* edge */
+ irte.dlvry_mode = INT_DELIVERY_MODE;
+ irte.vector = cfg->vector;
+ irte.dest_id = IRTE_DEST(dest);
+
+ modify_irte(irq, &irte);
msg->address_hi = MSI_ADDR_BASE_HI;
+ msg->data = sub_handle;
+ msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+ MSI_ADDR_IR_SHV |
+ MSI_ADDR_IR_INDEX1(ir_index) |
+ MSI_ADDR_IR_INDEX2(ir_index);
+ } else
+#endif
+ {
+ msg->address_hi = MSI_ADDR_BASE_HI;
msg->address_lo =
MSI_ADDR_BASE_LO |
((INT_DEST_MODE == 0) ?
@@ -2041,6 +2398,55 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
write_msi_msg(irq, &msg);
irq_desc[irq].affinity = mask;
}
+
+#ifdef CONFIG_INTR_REMAP
+/*
+ * Migrate the MSI irq to another cpumask. This migration is
+ * done in the process context using interrupt-remapping hardware.
+ */
+static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+{
+ struct irq_cfg *cfg = irq_cfg + irq;
+ unsigned int dest;
+ cpumask_t tmp, cleanup_mask;
+ struct irte irte;
+
+ cpus_and(tmp, mask, cpu_online_map);
+ if (cpus_empty(tmp))
+ return;
+
+ if (get_irte(irq, &irte))
+ return;
+
+ if (assign_irq_vector(irq, mask))
+ return;
+
+ cpus_and(tmp, cfg->domain, mask);
+ dest = cpu_mask_to_apicid(tmp);
+
+ irte.vector = cfg->vector;
+ irte.dest_id = IRTE_DEST(dest);
+
+ /*
+ * atomically update the IRTE with the new destination and vector.
+ */
+ modify_irte(irq, &irte);
+
+ /*
+ * After this point, all the interrupts will start arriving
+ * at the new destination. So, time to cleanup the previous
+ * vector allocation.
+ */
+ if (cfg->move_in_progress) {
+ cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+ cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+ send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+ cfg->move_in_progress = 0;
+ }
+
+ irq_desc[irq].affinity = mask;
+}
+#endif
#endif /* CONFIG_SMP */
/*
@@ -2058,26 +2464,157 @@ static struct irq_chip msi_chip = {
.retrigger = ioapic_retrigger_irq,
};
-int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip msi_ir_chip = {
+ .name = "IR-PCI-MSI",
+ .unmask = unmask_msi_irq,
+ .mask = mask_msi_irq,
+ .ack = ack_x2apic_edge,
+#ifdef CONFIG_SMP
+ .set_affinity = ir_set_msi_irq_affinity,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+
+/*
+ * Map the PCI dev to the corresponding remapping hardware unit
+ * and allocate 'nvec' consecutive interrupt-remapping table entries
+ * in it.
+ */
+static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
+{
+ struct intel_iommu *iommu;
+ int index;
+
+ iommu = map_dev_to_ir(dev);
+ if (!iommu) {
+ printk(KERN_ERR
+ "Unable to map PCI %s to iommu\n", pci_name(dev));
+ return -ENOENT;
+ }
+
+ index = alloc_irte(iommu, irq, nvec);
+ if (index < 0) {
+ printk(KERN_ERR
+ "Unable to allocate %d IRTE for PCI %s\n", nvec,
+ pci_name(dev));
+ return -ENOSPC;
+ }
+ return index;
+}
+#endif
+
+static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
{
+ int ret;
struct msi_msg msg;
+
+ ret = msi_compose_msg(dev, irq, &msg);
+ if (ret < 0)
+ return ret;
+
+ set_irq_msi(irq, desc);
+ write_msi_msg(irq, &msg);
+
+#ifdef CONFIG_INTR_REMAP
+ if (irq_remapped(irq)) {
+ struct irq_desc *desc = irq_desc + irq;
+ /*
+ * irq migration in process context
+ */
+ desc->status |= IRQ_MOVE_PCNTXT;
+ set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
+ } else
+#endif
+ set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+
+ return 0;
+}
+
+int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+{
int irq, ret;
+
irq = create_irq();
if (irq < 0)
return irq;
- ret = msi_compose_msg(dev, irq, &msg);
+#ifdef CONFIG_INTR_REMAP
+ if (!intr_remapping_enabled)
+ goto no_ir;
+
+ ret = msi_alloc_irte(dev, irq, 1);
+ if (ret < 0)
+ goto error;
+no_ir:
+#endif
+ ret = setup_msi_irq(dev, desc, irq);
if (ret < 0) {
destroy_irq(irq);
return ret;
}
+ return 0;
- set_irq_msi(irq, desc);
- write_msi_msg(irq, &msg);
+#ifdef CONFIG_INTR_REMAP
+error:
+ destroy_irq(irq);
+ return ret;
+#endif
+}
- set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ int irq, ret, sub_handle;
+ struct msi_desc *desc;
+#ifdef CONFIG_INTR_REMAP
+ struct intel_iommu *iommu = 0;
+ int index = 0;
+#endif
+ sub_handle = 0;
+ list_for_each_entry(desc, &dev->msi_list, list) {
+ irq = create_irq();
+ if (irq < 0)
+ return irq;
+#ifdef CONFIG_INTR_REMAP
+ if (!intr_remapping_enabled)
+ goto no_ir;
+
+ if (!sub_handle) {
+ /*
+ * allocate the consecutive block of IRTE's
+ * for 'nvec'
+ */
+ index = msi_alloc_irte(dev, irq, nvec);
+ if (index < 0) {
+ ret = index;
+ goto error;
+ }
+ } else {
+ iommu = map_dev_to_ir(dev);
+ if (!iommu) {
+ ret = -ENOENT;
+ goto error;
+ }
+ /*
+ * setup the mapping between the irq and the IRTE
+ * base index, the sub_handle pointing to the
+ * appropriate interrupt remap table entry.
+ */
+ set_irte_irq(irq, iommu, index, sub_handle);
+ }
+no_ir:
+#endif
+ ret = setup_msi_irq(dev, desc, irq);
+ if (ret < 0)
+ goto error;
+ sub_handle++;
+ }
return 0;
+
+error:
+ destroy_irq(irq);
+ return ret;
}
void arch_teardown_msi_irq(unsigned int irq)
@@ -2325,6 +2862,10 @@ void __init setup_ioapic_dest(void)
setup_IO_APIC_irq(ioapic, pin, irq,
irq_trigger(irq_entry),
irq_polarity(irq_entry));
+#ifdef CONFIG_INTR_REMAP
+ else if (intr_remapping_enabled)
+ set_ir_ioapic_affinity_irq(irq, TARGET_CPUS);
+#endif
else
set_ioapic_affinity_irq(irq, TARGET_CPUS);
}
diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c
index 9d98cda39ad..3f7537b669d 100644
--- a/arch/x86/kernel/ipi.c
+++ b/arch/x86/kernel/ipi.c
@@ -70,7 +70,7 @@ void __send_IPI_shortcut(unsigned int shortcut, int vector)
/*
* Send the IPI. The write to APIC_ICR fires this off.
*/
- apic_write_around(APIC_ICR, cfg);
+ apic_write(APIC_ICR, cfg);
}
void send_IPI_self(int vector)
@@ -98,7 +98,7 @@ static inline void __send_IPI_dest_field(unsigned long mask, int vector)
* prepare target chip field
*/
cfg = __prepare_ICR2(mask);
- apic_write_around(APIC_ICR2, cfg);
+ apic_write(APIC_ICR2, cfg);
/*
* program the ICR
@@ -108,7 +108,7 @@ static inline void __send_IPI_dest_field(unsigned long mask, int vector)
/*
* Send the IPI. The write to APIC_ICR fires this off.
*/
- apic_write_around(APIC_ICR, cfg);
+ apic_write(APIC_ICR, cfg);
}
/*
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 3b25e49380c..70e1f3e287f 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/nmi.c b/arch/x86/kernel/nmi.c
index ec024b3baad..384b49fed59 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -263,7 +263,7 @@ late_initcall(init_lapic_nmi_sysfs);
static void __acpi_nmi_enable(void *__unused)
{
- apic_write_around(APIC_LVT0, APIC_DM_NMI);
+ apic_write(APIC_LVT0, APIC_DM_NMI);
}
/*
@@ -277,7 +277,7 @@ void acpi_nmi_enable(void)
static void __acpi_nmi_disable(void *__unused)
{
- apic_write_around(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
+ apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
}
/*
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index e0f571d58c1..e0f139106c7 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -360,9 +360,6 @@ struct pv_cpu_ops pv_cpu_ops = {
struct pv_apic_ops pv_apic_ops = {
#ifdef CONFIG_X86_LOCAL_APIC
- .apic_write = native_apic_write,
- .apic_write_atomic = native_apic_write_atomic,
- .apic_read = native_apic_read,
.setup_boot_clock = setup_boot_APIC_clock,
.setup_secondary_clock = setup_secondary_APIC_clock,
.startup_ipi_hook = paravirt_nop,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 531b55b8e81..6121ffd46b9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -735,6 +735,8 @@ 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 687376ab07e..a4f2d8f06e4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -123,7 +123,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
static atomic_t init_deasserted;
-static int boot_cpu_logical_apicid;
/* representing cpus for which sibling maps can be computed */
static cpumask_t cpu_sibling_setup_map;
@@ -165,6 +164,8 @@ static void unmap_cpu_to_node(int cpu)
#endif
#ifdef CONFIG_X86_32
+static int boot_cpu_logical_apicid;
+
u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
{ [0 ... NR_CPUS-1] = BAD_APICID };
@@ -210,7 +211,7 @@ static void __cpuinit smp_callin(void)
/*
* (This works even if the APIC is not enabled.)
*/
- phys_id = GET_APIC_ID(read_apic_id());
+ phys_id = read_apic_id();
cpuid = smp_processor_id();
if (cpu_isset(cpuid, cpu_callin_map)) {
panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
@@ -546,8 +547,7 @@ static inline void __inquire_remote_apic(int apicid)
printk(KERN_CONT
"a previous APIC delivery may have failed\n");
- apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
- apic_write_around(APIC_ICR, APIC_DM_REMRD | regs[i]);
+ apic_icr_write(APIC_DM_REMRD | regs[i], apicid);
timeout = 0;
do {
@@ -579,11 +579,9 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
int maxlvt;
/* Target chip */
- apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid));
-
/* Boot on the stack */
/* Kick the second */
- apic_write_around(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL);
+ apic_icr_write(APIC_DM_NMI | APIC_DEST_LOGICAL, logical_apicid);
Dprintk("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
@@ -592,14 +590,9 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
- /*
- * Due to the Pentium erratum 3AP.
- */
maxlvt = lapic_get_maxlvt();
- if (maxlvt > 3) {
- apic_read_around(APIC_SPIV);
+ if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
- }
accept_status = (apic_read(APIC_ESR) & 0xEF);
Dprintk("NMI sent.\n");
@@ -625,12 +618,14 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
return send_status;
}
+ maxlvt = lapic_get_maxlvt();
+
/*
* Be paranoid about clearing APIC errors.
*/
if (APIC_INTEGRATED(apic_version[phys_apicid])) {
- apic_read_around(APIC_SPIV);
- apic_write(APIC_ESR, 0);
+ if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
+ apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
}
@@ -639,13 +634,11 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
/*
* Turn INIT on target chip
*/
- apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
/*
* Send IPI
*/
- apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_INT_ASSERT
- | APIC_DM_INIT);
+ apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT,
+ phys_apicid);
Dprintk("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
@@ -655,10 +648,8 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
Dprintk("Deasserting INIT.\n");
/* Target chip */
- apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
/* Send IPI */
- apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);
+ apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
Dprintk("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
@@ -689,12 +680,10 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
*/
Dprintk("#startup loops: %d.\n", num_starts);
- maxlvt = lapic_get_maxlvt();
-
for (j = 1; j <= num_starts; j++) {
Dprintk("Sending STARTUP #%d.\n", j);
- apic_read_around(APIC_SPIV);
- apic_write(APIC_ESR, 0);
+ if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
+ apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
Dprintk("After apic_write.\n");
@@ -703,12 +692,10 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
*/
/* Target chip */
- apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
/* Boot on the stack */
/* Kick the second */
- apic_write_around(APIC_ICR, APIC_DM_STARTUP
- | (start_eip >> 12));
+ apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12),
+ phys_apicid);
/*
* Give the other CPU some time to accept the IPI.
@@ -724,13 +711,8 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
- /*
- * Due to the Pentium erratum 3AP.
- */
- if (maxlvt > 3) {
- apic_read_around(APIC_SPIV);
+ if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
- }
accept_status = (apic_read(APIC_ESR) & 0xEF);
if (send_status || accept_status)
break;
@@ -1147,10 +1129,17 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
* Setup boot CPU information
*/
smp_store_cpu_info(0); /* Final full version of the data */
+#ifdef CONFIG_X86_32
boot_cpu_logical_apicid = logical_smp_processor_id();
+#endif
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();
@@ -1158,9 +1147,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
}
preempt_disable();
- if (GET_APIC_ID(read_apic_id()) != boot_cpu_physical_apicid) {
+ if (read_apic_id() != boot_cpu_physical_apicid) {
panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
- GET_APIC_ID(read_apic_id()), boot_cpu_physical_apicid);
+ read_apic_id(), boot_cpu_physical_apicid);
/* Or can we switch back to PIC here? */
}
preempt_enable();
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index b15346092b7..45c27c4e2a6 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -904,9 +904,8 @@ static inline int __init activate_vmi(void)
#endif
#ifdef CONFIG_X86_LOCAL_APIC
- para_fill(pv_apic_ops.apic_read, APICRead);
- para_fill(pv_apic_ops.apic_write, APICWrite);
- para_fill(pv_apic_ops.apic_write_atomic, APICWrite);
+ para_fill(apic_ops->read, APICRead);
+ para_fill(apic_ops->write, APICWrite);
#endif
/*
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 50dad44fb54..35c4349cd66 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -783,14 +783,44 @@ static void lguest_wbinvd(void)
* code qualifies for Advanced. It will also never interrupt anything. It
* does, however, allow us to get through the Linux boot code. */
#ifdef CONFIG_X86_LOCAL_APIC
-static void lguest_apic_write(unsigned long reg, u32 v)
+static void lguest_apic_write(u32 reg, u32 v)
{
}
-static u32 lguest_apic_read(unsigned long reg)
+static u32 lguest_apic_read(u32 reg)
{
return 0;
}
+
+static u64 lguest_apic_icr_read(void)
+{
+ return 0;
+}
+
+static void lguest_apic_icr_write(u32 low, u32 id)
+{
+ /* Warn to see if there's any stray references */
+ WARN_ON(1);
+}
+
+static void lguest_apic_wait_icr_idle(void)
+{
+ return;
+}
+
+static u32 lguest_apic_safe_wait_icr_idle(void)
+{
+ return 0;
+}
+
+static struct apic_ops lguest_basic_apic_ops = {
+ .read = lguest_apic_read,
+ .write = lguest_apic_write,
+ .icr_read = lguest_apic_icr_read,
+ .icr_write = lguest_apic_icr_write,
+ .wait_icr_idle = lguest_apic_wait_icr_idle,
+ .safe_wait_icr_idle = lguest_apic_safe_wait_icr_idle,
+};
#endif
/* STOP! Until an interrupt comes in. */
@@ -990,9 +1020,7 @@ __init void lguest_init(void)
#ifdef CONFIG_X86_LOCAL_APIC
/* apic read/write intercepts */
- pv_apic_ops.apic_write = lguest_apic_write;
- pv_apic_ops.apic_write_atomic = lguest_apic_write;
- pv_apic_ops.apic_read = lguest_apic_read;
+ apic_ops = &lguest_basic_apic_ops;
#endif
/* time operations */
diff --git a/arch/x86/mach-generic/bigsmp.c b/arch/x86/mach-generic/bigsmp.c
index 59d77171455..b31f2800638 100644
--- a/arch/x86/mach-generic/bigsmp.c
+++ b/arch/x86/mach-generic/bigsmp.c
@@ -5,17 +5,16 @@
#define APIC_DEFINITION 1
#include <linux/threads.h>
#include <linux/cpumask.h>
-#include <asm/smp.h>
#include <asm/mpspec.h>
#include <asm/genapic.h>
#include <asm/fixmap.h>
#include <asm/apicdef.h>
#include <linux/kernel.h>
-#include <linux/smp.h>
#include <linux/init.h>
#include <linux/dmi.h>
-#include <asm/mach-bigsmp/mach_apic.h>
#include <asm/mach-bigsmp/mach_apicdef.h>
+#include <linux/smp.h>
+#include <asm/mach-bigsmp/mach_apic.h>
#include <asm/mach-bigsmp/mach_ipi.h>
#include <asm/mach-default/mach_mpparse.h>
diff --git a/arch/x86/mach-generic/es7000.c b/arch/x86/mach-generic/es7000.c
index 4742626f08c..9b30547d746 100644
--- a/arch/x86/mach-generic/es7000.c
+++ b/arch/x86/mach-generic/es7000.c
@@ -4,16 +4,15 @@
#define APIC_DEFINITION 1
#include <linux/threads.h>
#include <linux/cpumask.h>
-#include <asm/smp.h>
#include <asm/mpspec.h>
#include <asm/genapic.h>
#include <asm/fixmap.h>
#include <asm/apicdef.h>
#include <linux/kernel.h>
#include <linux/string.h>
-#include <linux/smp.h>
#include <linux/init.h>
#include <asm/mach-es7000/mach_apicdef.h>
+#include <linux/smp.h>
#include <asm/mach-es7000/mach_apic.h>
#include <asm/mach-es7000/mach_ipi.h>
#include <asm/mach-es7000/mach_mpparse.h>
diff --git a/arch/x86/mach-generic/numaq.c b/arch/x86/mach-generic/numaq.c
index 8091e68764c..95c07efff6b 100644
--- a/arch/x86/mach-generic/numaq.c
+++ b/arch/x86/mach-generic/numaq.c
@@ -4,7 +4,6 @@
#define APIC_DEFINITION 1
#include <linux/threads.h>
#include <linux/cpumask.h>
-#include <linux/smp.h>
#include <asm/mpspec.h>
#include <asm/genapic.h>
#include <asm/fixmap.h>
@@ -12,8 +11,9 @@
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/init.h>
-#include <asm/mach-numaq/mach_apic.h>
#include <asm/mach-numaq/mach_apicdef.h>
+#include <linux/smp.h>
+#include <asm/mach-numaq/mach_apic.h>
#include <asm/mach-numaq/mach_ipi.h>
#include <asm/mach-numaq/mach_mpparse.h>
#include <asm/mach-numaq/mach_wakecpu.h>
diff --git a/arch/x86/mach-generic/summit.c b/arch/x86/mach-generic/summit.c
index a97ea0f35b1..752edd96b1b 100644
--- a/arch/x86/mach-generic/summit.c
+++ b/arch/x86/mach-generic/summit.c
@@ -4,17 +4,16 @@
#define APIC_DEFINITION 1
#include <linux/threads.h>
#include <linux/cpumask.h>
-#include <asm/smp.h>
#include <asm/mpspec.h>
#include <asm/genapic.h>
#include <asm/fixmap.h>
#include <asm/apicdef.h>
#include <linux/kernel.h>
#include <linux/string.h>
-#include <linux/smp.h>
#include <linux/init.h>
-#include <asm/mach-summit/mach_apic.h>
#include <asm/mach-summit/mach_apicdef.h>
+#include <linux/smp.h>
+#include <asm/mach-summit/mach_apic.h>
#include <asm/mach-summit/mach_ipi.h>
#include <asm/mach-summit/mach_mpparse.h>
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bb508456ef5..008b7b69581 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -548,16 +548,47 @@ static void xen_io_delay(void)
}
#ifdef CONFIG_X86_LOCAL_APIC
-static u32 xen_apic_read(unsigned long reg)
+static u32 xen_apic_read(u32 reg)
{
return 0;
}
-static void xen_apic_write(unsigned long reg, u32 val)
+static void xen_apic_write(u32 reg, u32 val)
{
/* Warn to see if there's any stray references */
WARN_ON(1);
}
+
+static u64 xen_apic_icr_read(void)
+{
+ return 0;
+}
+
+static void xen_apic_icr_write(u32 low, u32 id)
+{
+ /* Warn to see if there's any stray references */
+ WARN_ON(1);
+}
+
+static void xen_apic_wait_icr_idle(void)
+{
+ return;
+}
+
+static u32 xen_safe_apic_wait_icr_idle(void)
+{
+ return 0;
+}
+
+static struct apic_ops xen_basic_apic_ops = {
+ .read = xen_apic_read,
+ .write = xen_apic_write,
+ .icr_read = xen_apic_icr_read,
+ .icr_write = xen_apic_icr_write,
+ .wait_icr_idle = xen_apic_wait_icr_idle,
+ .safe_wait_icr_idle = xen_safe_apic_wait_icr_idle,
+};
+
#endif
static void xen_flush_tlb(void)
@@ -1130,9 +1161,6 @@ static const struct pv_irq_ops xen_irq_ops __initdata = {
static const struct pv_apic_ops xen_apic_ops __initdata = {
#ifdef CONFIG_X86_LOCAL_APIC
- .apic_write = xen_apic_write,
- .apic_write_atomic = xen_apic_write,
- .apic_read = xen_apic_read,
.setup_boot_clock = paravirt_nop,
.setup_secondary_clock = paravirt_nop,
.startup_ipi_hook = paravirt_nop,
@@ -1294,6 +1322,13 @@ asmlinkage void __init xen_start_kernel(void)
pv_apic_ops = xen_apic_ops;
pv_mmu_ops = xen_mmu_ops;
+#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * set up the basic apic ops.
+ */
+ apic_ops = &xen_basic_apic_ops;
+#endif
+
if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;