aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile5
-rw-r--r--arch/x86/kernel/acpi/boot.c156
-rw-r--r--arch/x86/kernel/amd_iommu_init.c16
-rw-r--r--arch/x86/kernel/apic/apic.c317
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c8
-rw-r--r--arch/x86/kernel/apic/es7000_32.c10
-rw-r--r--arch/x86/kernel/apic/io_apic.c901
-rw-r--r--arch/x86/kernel/apic/nmi.c7
-rw-r--r--arch/x86/kernel/apic/probe_32.c1
-rw-r--r--arch/x86/kernel/apic/probe_64.c2
-rw-r--r--arch/x86/kernel/apic/summit_32.c7
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c36
-rw-r--r--arch/x86/kernel/asm-offsets_32.c1
-rw-r--r--arch/x86/kernel/asm-offsets_64.c1
-rw-r--r--arch/x86/kernel/bios_uv.c3
-rw-r--r--arch/x86/kernel/cpu/addon_cpuid_features.c1
-rw-r--r--arch/x86/kernel/cpu/amd.c2
-rw-r--r--arch/x86/kernel/cpu/common.c32
-rw-r--r--[-rwxr-xr-x]arch/x86/kernel/cpu/cpu_debug.c431
-rw-r--r--arch/x86/kernel/cpu/cpufreq/Kconfig9
-rw-r--r--arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c109
-rw-r--r--arch/x86/kernel/cpu/cpufreq/longhaul.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/p4-clockmod.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k7.c4
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k8.c57
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c2
-rw-r--r--arch/x86/kernel/cpu/intel.c6
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c153
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_64.c35
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel_64.c11
-rw-r--r--arch/x86/kernel/cpu/mtrr/cleanup.c4
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c30
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c2
-rw-r--r--arch/x86/kernel/cpu/mtrr/mtrr.h15
-rw-r--r--arch/x86/kernel/cpu/mtrr/state.c6
-rw-r--r--arch/x86/kernel/cpu/proc.c2
-rw-r--r--arch/x86/kernel/dumpstack.h1
-rw-r--r--arch/x86/kernel/e820.c11
-rw-r--r--arch/x86/kernel/early-quirks.c2
-rw-r--r--arch/x86/kernel/entry_64.S3
-rw-r--r--arch/x86/kernel/ftrace.c4
-rw-r--r--arch/x86/kernel/head_32.S7
-rw-r--r--arch/x86/kernel/hpet.c24
-rw-r--r--arch/x86/kernel/i8253.c2
-rw-r--r--arch/x86/kernel/irq.c22
-rw-r--r--arch/x86/kernel/irqinit.c (renamed from arch/x86/kernel/irqinit_32.c)149
-rw-r--r--arch/x86/kernel/irqinit_64.c177
-rw-r--r--arch/x86/kernel/kgdb.c5
-rw-r--r--arch/x86/kernel/kvmclock.c7
-rw-r--r--arch/x86/kernel/machine_kexec_32.c4
-rw-r--r--arch/x86/kernel/machine_kexec_64.c4
-rw-r--r--arch/x86/kernel/microcode_core.c35
-rw-r--r--arch/x86/kernel/mpparse.c41
-rw-r--r--arch/x86/kernel/paravirt.c2
-rw-r--r--arch/x86/kernel/pci-swiotlb.c2
-rw-r--r--arch/x86/kernel/process.c1
-rw-r--r--arch/x86/kernel/ptrace.c3
-rw-r--r--arch/x86/kernel/quirks.c39
-rw-r--r--arch/x86/kernel/reboot.c16
-rw-r--r--arch/x86/kernel/setup.c28
-rw-r--r--arch/x86/kernel/setup_percpu.c4
-rw-r--r--arch/x86/kernel/smp.c20
-rw-r--r--arch/x86/kernel/smpboot.c22
-rw-r--r--arch/x86/kernel/tlb_uv.c191
-rw-r--r--arch/x86/kernel/traps.c5
-rw-r--r--arch/x86/kernel/tsc.c10
-rw-r--r--arch/x86/kernel/tsc_sync.c14
-rw-r--r--arch/x86/kernel/uv_sysfs.c4
-rw-r--r--arch/x86/kernel/uv_time.c10
-rw-r--r--arch/x86/kernel/vm86_32.c4
-rw-r--r--arch/x86/kernel/vmiclock_32.c2
-rw-r--r--arch/x86/kernel/vmlinux.lds.S430
-rw-r--r--arch/x86/kernel/vmlinux_32.lds.S229
-rw-r--r--arch/x86/kernel/vmlinux_64.lds.S298
-rw-r--r--arch/x86/kernel/xsave.c6
76 files changed, 2000 insertions, 2224 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 145cce75cda..235f5927bb9 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -28,7 +28,7 @@ CFLAGS_paravirt.o := $(nostackp)
obj-y := process_$(BITS).o signal.o entry_$(BITS).o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y += setup.o i8259.o irqinit_$(BITS).o
+obj-y += setup.o i8259.o irqinit.o
obj-$(CONFIG_X86_VISWS) += visws_quirks.o
obj-$(CONFIG_X86_32) += probe_roms_32.o
obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
@@ -89,7 +89,8 @@ obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o
obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o
obj-$(CONFIG_KVM_GUEST) += kvm.o
obj-$(CONFIG_KVM_CLOCK) += kvmclock.o
-obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o paravirt-spinlocks.o
+obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o
+obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 723989d7f80..631086159c5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -33,6 +33,7 @@
#include <linux/irq.h>
#include <linux/bootmem.h>
#include <linux/ioport.h>
+#include <linux/pci.h>
#include <asm/pgtable.h>
#include <asm/io_apic.h>
@@ -522,7 +523,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
* success: return IRQ number (>=0)
* failure: return < 0
*/
-int acpi_register_gsi(u32 gsi, int triggering, int polarity)
+int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
{
unsigned int irq;
unsigned int plat_gsi = gsi;
@@ -532,14 +533,14 @@ int acpi_register_gsi(u32 gsi, int triggering, int polarity)
* Make sure all (legacy) PCI IRQs are set as level-triggered.
*/
if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
- if (triggering == ACPI_LEVEL_SENSITIVE)
+ if (trigger == ACPI_LEVEL_SENSITIVE)
eisa_set_level_irq(gsi);
}
#endif
#ifdef CONFIG_X86_IO_APIC
if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) {
- plat_gsi = mp_register_gsi(gsi, triggering, polarity);
+ plat_gsi = mp_register_gsi(dev, gsi, trigger, polarity);
}
#endif
acpi_gsi_to_irq(plat_gsi, &irq);
@@ -903,10 +904,8 @@ extern int es7000_plat;
#endif
static struct {
- int apic_id;
int gsi_base;
int gsi_end;
- DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
} mp_ioapic_routing[MAX_IO_APICS];
int mp_find_ioapic(int gsi)
@@ -986,16 +985,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
mp_ioapics[idx].apicid = uniq_ioapic_id(id);
-#ifdef CONFIG_X86_32
mp_ioapics[idx].apicver = io_apic_get_version(idx);
-#else
- mp_ioapics[idx].apicver = 0;
-#endif
+
/*
* Build basic GSI lookup table to facilitate gsi->io_apic lookups
* and to prevent reprogramming of IOAPIC pins (PCI GSIs).
*/
- mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].apicid;
mp_ioapic_routing[idx].gsi_base = gsi_base;
mp_ioapic_routing[idx].gsi_end = gsi_base +
io_apic_get_redir_entries(idx);
@@ -1158,26 +1153,52 @@ void __init mp_config_acpi_legacy_irqs(void)
}
}
-int mp_register_gsi(u32 gsi, int triggering, int polarity)
+static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
+ int polarity)
{
+#ifdef CONFIG_X86_MPPARSE
+ struct mpc_intsrc mp_irq;
+ struct pci_dev *pdev;
+ unsigned char number;
+ unsigned int devfn;
int ioapic;
- int ioapic_pin;
-#ifdef CONFIG_X86_32
-#define MAX_GSI_NUM 4096
-#define IRQ_COMPRESSION_START 64
+ u8 pin;
- static int pci_irq = IRQ_COMPRESSION_START;
- /*
- * Mapping between Global System Interrupts, which
- * represent all possible interrupts, and IRQs
- * assigned to actual devices.
- */
- static int gsi_to_irq[MAX_GSI_NUM];
-#else
+ if (!acpi_ioapic)
+ return 0;
+ if (!dev)
+ return 0;
+ if (dev->bus != &pci_bus_type)
+ return 0;
+
+ pdev = to_pci_dev(dev);
+ number = pdev->bus->number;
+ devfn = pdev->devfn;
+ pin = pdev->pin;
+ /* print the entry should happen on mptable identically */
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+ (polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
+ mp_irq.srcbus = number;
+ mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+ ioapic = mp_find_ioapic(gsi);
+ mp_irq.dstapic = mp_ioapics[ioapic].apicid;
+ mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
+
+ save_mp_irq(&mp_irq);
+#endif
+ return 0;
+}
+
+int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
+{
+ int ioapic;
+ int ioapic_pin;
+ struct io_apic_irq_attr irq_attr;
if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
return gsi;
-#endif
/* Don't set up the ACPI SCI because it's already set up */
if (acpi_gbl_FADT.sci_interrupt == gsi)
@@ -1196,93 +1217,22 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity)
gsi = ioapic_renumber_irq(ioapic, gsi);
#endif
- /*
- * Avoid pin reprogramming. PRTs typically include entries
- * with redundant pin->gsi mappings (but unique PCI devices);
- * we only program the IOAPIC on the first.
- */
if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
printk(KERN_ERR "Invalid reference to IOAPIC pin "
- "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
+ "%d-%d\n", mp_ioapics[ioapic].apicid,
ioapic_pin);
return gsi;
}
- if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) {
- pr_debug("Pin %d-%d already programmed\n",
- mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
-#ifdef CONFIG_X86_32
- return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]);
-#else
- return gsi;
-#endif
- }
-
- set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed);
-#ifdef CONFIG_X86_32
- /*
- * For GSI >= 64, use IRQ compression
- */
- if ((gsi >= IRQ_COMPRESSION_START)
- && (triggering == ACPI_LEVEL_SENSITIVE)) {
- /*
- * For PCI devices assign IRQs in order, avoiding gaps
- * due to unused I/O APIC pins.
- */
- int irq = gsi;
- if (gsi < MAX_GSI_NUM) {
- /*
- * Retain the VIA chipset work-around (gsi > 15), but
- * avoid a problem where the 8254 timer (IRQ0) is setup
- * via an override (so it's not on pin 0 of the ioapic),
- * and at the same time, the pin 0 interrupt is a PCI
- * type. The gsi > 15 test could cause these two pins
- * to be shared as IRQ0, and they are not shareable.
- * So test for this condition, and if necessary, avoid
- * the pin collision.
- */
- gsi = pci_irq++;
- /*
- * Don't assign IRQ used by ACPI SCI
- */
- if (gsi == acpi_gbl_FADT.sci_interrupt)
- gsi = pci_irq++;
- gsi_to_irq[irq] = gsi;
- } else {
- printk(KERN_ERR "GSI %u is too high\n", gsi);
- return gsi;
- }
- }
-#endif
- io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
- triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
- polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
- return gsi;
-}
-int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
- u32 gsi, int triggering, int polarity)
-{
-#ifdef CONFIG_X86_MPPARSE
- struct mpc_intsrc mp_irq;
- int ioapic;
+ if (enable_update_mptable)
+ mp_config_acpi_gsi(dev, gsi, trigger, polarity);
- if (!acpi_ioapic)
- return 0;
+ set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
+ trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
+ polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+ io_apic_set_pci_routing(dev, gsi, &irq_attr);
- /* print the entry should happen on mptable identically */
- mp_irq.type = MP_INTSRC;
- mp_irq.irqtype = mp_INT;
- mp_irq.irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
- (polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
- mp_irq.srcbus = number;
- mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
- ioapic = mp_find_ioapic(gsi);
- mp_irq.dstapic = mp_ioapic_routing[ioapic].apic_id;
- mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
-
- save_mp_irq(&mp_irq);
-#endif
- return 0;
+ return gsi;
}
/*
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 42c33cebf00..8c0be0902da 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -49,10 +49,10 @@
#define IVHD_DEV_EXT_SELECT 0x46
#define IVHD_DEV_EXT_SELECT_RANGE 0x47
-#define IVHD_FLAG_HT_TUN_EN 0x00
-#define IVHD_FLAG_PASSPW_EN 0x01
-#define IVHD_FLAG_RESPASSPW_EN 0x02
-#define IVHD_FLAG_ISOC_EN 0x03
+#define IVHD_FLAG_HT_TUN_EN_MASK 0x01
+#define IVHD_FLAG_PASSPW_EN_MASK 0x02
+#define IVHD_FLAG_RESPASSPW_EN_MASK 0x04
+#define IVHD_FLAG_ISOC_EN_MASK 0x08
#define IVMD_FLAG_EXCL_RANGE 0x08
#define IVMD_FLAG_UNITY_MAP 0x01
@@ -569,19 +569,19 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
* First set the recommended feature enable bits from ACPI
* into the IOMMU control registers
*/
- h->flags & IVHD_FLAG_HT_TUN_EN ?
+ h->flags & IVHD_FLAG_HT_TUN_EN_MASK ?
iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
- h->flags & IVHD_FLAG_PASSPW_EN ?
+ h->flags & IVHD_FLAG_PASSPW_EN_MASK ?
iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
- h->flags & IVHD_FLAG_RESPASSPW_EN ?
+ h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
- h->flags & IVHD_FLAG_ISOC_EN ?
+ h->flags & IVHD_FLAG_ISOC_EN_MASK ?
iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
iommu_feature_disable(iommu, CONTROL_ISOC_EN);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 098ec84b8c0..a4c9cf0bf70 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -98,6 +98,29 @@ early_param("lapic", parse_lapic);
/* Local APIC was disabled by the BIOS and enabled by the kernel */
static int enabled_via_apicbase;
+/*
+ * Handle interrupt mode configuration register (IMCR).
+ * This register controls whether the interrupt signals
+ * that reach the BSP come from the master PIC or from the
+ * local APIC. Before entering Symmetric I/O Mode, either
+ * the BIOS or the operating system must switch out of
+ * PIC Mode by changing the IMCR.
+ */
+static inline void imcr_pic_to_apic(void)
+{
+ /* select IMCR register */
+ outb(0x70, 0x22);
+ /* NMI and 8259 INTR go through APIC */
+ outb(0x01, 0x23);
+}
+
+static inline void imcr_apic_to_pic(void)
+{
+ /* select IMCR register */
+ outb(0x70, 0x22);
+ /* NMI and 8259 INTR go directly to BSP */
+ outb(0x00, 0x23);
+}
#endif
#ifdef CONFIG_X86_64
@@ -111,13 +134,19 @@ static __init int setup_apicpmtimer(char *s)
__setup("apicpmtimer", setup_apicpmtimer);
#endif
+int x2apic_mode;
#ifdef CONFIG_X86_X2APIC
-int x2apic;
/* x2apic enabled before OS handover */
static int x2apic_preenabled;
static int disable_x2apic;
static __init int setup_nox2apic(char *str)
{
+ if (x2apic_enabled()) {
+ pr_warning("Bios already enabled x2apic, "
+ "can't enforce nox2apic");
+ return 0;
+ }
+
disable_x2apic = 1;
setup_clear_cpu_cap(X86_FEATURE_X2APIC);
return 0;
@@ -209,6 +238,31 @@ static int modern_apic(void)
return lapic_get_version() >= 0x14;
}
+/*
+ * bare function to substitute write operation
+ * and it's _that_ fast :)
+ */
+static void native_apic_write_dummy(u32 reg, u32 v)
+{
+ WARN_ON_ONCE((cpu_has_apic || !disable_apic));
+}
+
+static u32 native_apic_read_dummy(u32 reg)
+{
+ WARN_ON_ONCE((cpu_has_apic && !disable_apic));
+ return 0;
+}
+
+/*
+ * right after this call apic->write/read doesn't do anything
+ * note that there is no restore operation it works one way
+ */
+void apic_disable(void)
+{
+ apic->read = native_apic_read_dummy;
+ apic->write = native_apic_write_dummy;
+}
+
void native_apic_wait_icr_idle(void)
{
while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
@@ -348,7 +402,7 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
{
- unsigned long reg = (lvt_off << 4) + APIC_EILVT0;
+ unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
unsigned int v = (mask << 16) | (msg_type << 8) | vector;
apic_write(reg, v);
@@ -431,6 +485,12 @@ static void __cpuinit setup_APIC_timer(void)
{
struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+ if (cpu_has(&current_cpu_data, X86_FEATURE_ARAT)) {
+ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
+ /* Make LAPIC timer preferrable over percpu HPET */
+ lapic_clockevent.rating = 150;
+ }
+
memcpy(levt, &lapic_clockevent, sizeof(*levt));
levt->cpumask = cpumask_of(smp_processor_id());
@@ -809,7 +869,7 @@ void clear_local_APIC(void)
u32 v;
/* APIC hasn't been mapped yet */
- if (!x2apic && !apic_phys)
+ if (!x2apic_mode && !apic_phys)
return;
maxlvt = lapic_get_maxlvt();
@@ -1281,7 +1341,7 @@ void check_x2apic(void)
{
if (x2apic_enabled()) {
pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
- x2apic_preenabled = x2apic = 1;
+ x2apic_preenabled = x2apic_mode = 1;
}
}
@@ -1289,7 +1349,7 @@ void enable_x2apic(void)
{
int msr, msr2;
- if (!x2apic)
+ if (!x2apic_mode)
return;
rdmsr(MSR_IA32_APICBASE, msr, msr2);
@@ -1298,6 +1358,7 @@ void enable_x2apic(void)
wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
}
}
+#endif /* CONFIG_X86_X2APIC */
void __init enable_IR_x2apic(void)
{
@@ -1306,32 +1367,21 @@ void __init enable_IR_x2apic(void)
unsigned long flags;
struct IO_APIC_route_entry **ioapic_entries = NULL;
- if (!cpu_has_x2apic)
- return;
-
- if (!x2apic_preenabled && disable_x2apic) {
- pr_info("Skipped enabling x2apic and Interrupt-remapping "
- "because of nox2apic\n");
- return;
+ ret = dmar_table_init();
+ if (ret) {
+ pr_debug("dmar_table_init() failed with %d:\n", ret);
+ goto ir_failed;
}
- if (x2apic_preenabled && disable_x2apic)
- panic("Bios already enabled x2apic, can't enforce nox2apic");
-
- if (!x2apic_preenabled && skip_ioapic_setup) {
- pr_info("Skipped enabling x2apic and Interrupt-remapping "
- "because of skipping io-apic setup\n");
- return;
+ if (!intr_remapping_supported()) {
+ pr_debug("intr-remapping not supported\n");
+ goto ir_failed;
}
- ret = dmar_table_init();
- if (ret) {
- pr_info("dmar_table_init() failed with %d:\n", ret);
- if (x2apic_preenabled)
- panic("x2apic enabled by bios. But IR enabling failed");
- else
- pr_info("Not enabling x2apic,Intr-remapping\n");
+ if (!x2apic_preenabled && skip_ioapic_setup) {
+ pr_info("Skipped enabling intr-remap because of skipping "
+ "io-apic setup\n");
return;
}
@@ -1351,19 +1401,16 @@ void __init enable_IR_x2apic(void)
mask_IO_APIC_setup(ioapic_entries);
mask_8259A();
- ret = enable_intr_remapping(EIM_32BIT_APIC_ID);
-
- if (ret && x2apic_preenabled) {
- local_irq_restore(flags);
- panic("x2apic enabled by bios. But IR enabling failed");
- }
-
+ ret = enable_intr_remapping(x2apic_supported());
if (ret)
goto end_restore;
- if (!x2apic) {
- x2apic = 1;
+ pr_info("Enabled Interrupt-remapping\n");
+
+ if (x2apic_supported() && !x2apic_mode) {
+ x2apic_mode = 1;
enable_x2apic();
+ pr_info("Enabled x2apic\n");
}
end_restore:
@@ -1372,37 +1419,34 @@ end_restore:
* IR enabling failed
*/
restore_IO_APIC_setup(ioapic_entries);
- else
- reinit_intr_remapped_IO_APIC(x2apic_preenabled, ioapic_entries);
unmask_8259A();
local_irq_restore(flags);
end:
- if (!ret) {
- if (!x2apic_preenabled)
- pr_info("Enabled x2apic and interrupt-remapping\n");
- else
- pr_info("Enabled Interrupt-remapping\n");
- } else
- pr_err("Failed to enable Interrupt-remapping and x2apic\n");
if (ioapic_entries)
free_ioapic_entries(ioapic_entries);
+
+ if (!ret)
+ return;
+
+ir_failed:
+ if (x2apic_preenabled)
+ panic("x2apic enabled by bios. But IR enabling failed");
+ else if (cpu_has_x2apic)
+ pr_info("Not enabling x2apic,Intr-remapping\n");
#else
if (!cpu_has_x2apic)
return;
if (x2apic_preenabled)
panic("x2apic enabled prior OS handover,"
- " enable CONFIG_INTR_REMAP");
-
- pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
- " and x2apic\n");
+ " enable CONFIG_X86_X2APIC, CONFIG_INTR_REMAP");
#endif
return;
}
-#endif /* CONFIG_X86_X2APIC */
+
#ifdef CONFIG_X86_64
/*
@@ -1419,7 +1463,6 @@ static int __init detect_init_APIC(void)
}
mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
- boot_cpu_physical_apicid = 0;
return 0;
}
#else
@@ -1533,32 +1576,49 @@ void __init early_init_lapic_mapping(void)
*/
void __init init_apic_mappings(void)
{
- if (x2apic) {
+ unsigned int new_apicid;
+
+ if (x2apic_mode) {
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
- * one for the IO-APIC.
- */
+ /* If no local APIC can be found return early */
if (!smp_found_config && detect_init_APIC()) {
- apic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
- apic_phys = __pa(apic_phys);
- } else
+ /* lets NOP'ify apic operations */
+ pr_info("APIC: disable apic facility\n");
+ apic_disable();
+ } else {
apic_phys = mp_lapic_addr;
- set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
- apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
- APIC_BASE, apic_phys);
+ /*
+ * acpi lapic path already maps that address in
+ * acpi_register_lapic_address()
+ */
+ if (!acpi_lapic)
+ set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
+
+ apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
+ APIC_BASE, apic_phys);
+ }
/*
* Fetch the APIC ID of the BSP in case we have a
* default configuration (or the MP table is broken).
*/
- if (boot_cpu_physical_apicid == -1U)
- boot_cpu_physical_apicid = read_apic_id();
+ new_apicid = read_apic_id();
+ if (boot_cpu_physical_apicid != new_apicid) {
+ boot_cpu_physical_apicid = new_apicid;
+ /*
+ * yeah -- we lie about apic_version
+ * in case if apic was disabled via boot option
+ * but it's not a problem for SMP compiled kernel
+ * since smp_sanity_check is prepared for such a case
+ * and disable smp mode
+ */
+ apic_version[new_apicid] =
+ GET_APIC_VERSION(apic_read(APIC_LVR));
+ }
}
/*
@@ -1727,8 +1787,7 @@ void __init connect_bsp_APIC(void)
*/
apic_printk(APIC_VERBOSE, "leaving PIC mode, "
"enabling APIC mode.\n");
- outb(0x70, 0x22);
- outb(0x01, 0x23);
+ imcr_pic_to_apic();
}
#endif
if (apic->enable_apic_mode)
@@ -1756,8 +1815,7 @@ void disconnect_bsp_APIC(int virt_wire_setup)
*/
apic_printk(APIC_VERBOSE, "disabling APIC mode, "
"entering PIC mode.\n");
- outb(0x70, 0x22);
- outb(0x00, 0x23);
+ imcr_apic_to_pic();
return;
}
#endif
@@ -1963,10 +2021,10 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
local_irq_save(flags);
disable_local_APIC();
-#ifdef CONFIG_INTR_REMAP
+
if (intr_remapping_enabled)
disable_intr_remapping();
-#endif
+
local_irq_restore(flags);
return 0;
}
@@ -1976,42 +2034,34 @@ static int lapic_resume(struct sys_device *dev)
unsigned int l, h;
unsigned long flags;
int maxlvt;
-
-#ifdef CONFIG_INTR_REMAP
- int ret;
+ int ret = 0;
struct IO_APIC_route_entry **ioapic_entries = NULL;
if (!apic_pm_state.active)
return 0;
local_irq_save(flags);
- if (x2apic) {
+ if (intr_remapping_enabled) {
ioapic_entries = alloc_ioapic_entries();
if (!ioapic_entries) {
WARN(1, "Alloc ioapic_entries in lapic resume failed.");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto restore;
}
ret = save_IO_APIC_setup(ioapic_entries);
if (ret) {
WARN(1, "Saving IO-APIC state failed: %d\n", ret);
free_ioapic_entries(ioapic_entries);
- return ret;
+ goto restore;
}
mask_IO_APIC_setup(ioapic_entries);
mask_8259A();
- enable_x2apic();
}
-#else
- if (!apic_pm_state.active)
- return 0;
- local_irq_save(flags);
- if (x2apic)
+ if (x2apic_mode)
enable_x2apic();
-#endif
-
else {
/*
* Make sure the APICBASE points to the right address
@@ -2049,21 +2099,16 @@ static int lapic_resume(struct sys_device *dev)
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
-#ifdef CONFIG_INTR_REMAP
- if (intr_remapping_enabled)
- reenable_intr_remapping(EIM_32BIT_APIC_ID);
-
- if (x2apic) {
+ if (intr_remapping_enabled) {
+ reenable_intr_remapping(x2apic_mode);
unmask_8259A();
restore_IO_APIC_setup(ioapic_entries);
free_ioapic_entries(ioapic_entries);
}
-#endif
-
+restore:
local_irq_restore(flags);
-
- return 0;
+ return ret;
}
/*
@@ -2111,31 +2156,14 @@ static void apic_pm_activate(void) { }
#endif /* CONFIG_PM */
#ifdef CONFIG_X86_64
-/*
- * apic_is_clustered_box() -- Check if we can expect good TSC
- *
- * Thus far, the major user of this is IBM's Summit2 series:
- *
- * Clustered boxes may have unsynced TSC problems if they are
- * multi-chassis. Use available data to take a good guess.
- * If in doubt, go HPET.
- */
-__cpuinit int apic_is_clustered_box(void)
+
+static int __cpuinit apic_cluster_num(void)
{
int i, clusters, zeros;
unsigned id;
u16 *bios_cpu_apicid;
DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
- /*
- * there is not this kind of box with AMD CPU yet.
- * Some AMD box with quadcore cpu and 8 sockets apicid
- * will be [4, 0x23] or [8, 0x27] could be thought to
- * vsmp box still need checking...
- */
- if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
- return 0;
-
bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
@@ -2171,18 +2199,67 @@ __cpuinit int apic_is_clustered_box(void)
++zeros;
}
- /* ScaleMP vSMPowered boxes have one cluster per board and TSCs are
- * not guaranteed to be synced between boards
- */
- if (is_vsmp_box() && clusters > 1)
+ return clusters;
+}
+
+static int __cpuinitdata multi_checked;
+static int __cpuinitdata multi;
+
+static int __cpuinit set_multi(const struct dmi_system_id *d)
+{
+ if (multi)
+ return 0;
+ pr_info("APIC: %s detected, Multi Chassis\n", d->ident);
+ multi = 1;
+ return 0;
+}
+
+static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
+ {
+ .callback = set_multi,
+ .ident = "IBM System Summit2",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Summit2"),
+ },
+ },
+ {}
+};
+
+static void __cpuinit dmi_check_multi(void)
+{
+ if (multi_checked)
+ return;
+
+ dmi_check_system(multi_dmi_table);
+ multi_checked = 1;
+}
+
+/*
+ * apic_is_clustered_box() -- Check if we can expect good TSC
+ *
+ * Thus far, the major user of this is IBM's Summit2 series:
+ * Clustered boxes may have unsynced TSC problems if they are
+ * multi-chassis.
+ * Use DMI to check them
+ */
+__cpuinit int apic_is_clustered_box(void)
+{
+ dmi_check_multi();
+ if (multi)
return 1;
+ if (!is_vsmp_box())
+ return 0;
+
/*
- * If clusters > 2, then should be multi-chassis.
- * May have to revisit this when multi-core + hyperthreaded CPUs come
- * out, but AFAIK this will work even for them.
+ * ScaleMP vSMPowered boxes have one cluster per board and TSCs are
+ * not guaranteed to be synced between boards
*/
- return (clusters > 2);
+ if (apic_cluster_num() > 1)
+ return 1;
+
+ return 0;
}
#endif
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 0014714ea97..d0c99abc26c 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -161,7 +161,7 @@ static int flat_apic_id_registered(void)
static int flat_phys_pkg_id(int initial_apic_id, int index_msb)
{
- return hard_smp_processor_id() >> index_msb;
+ return initial_apic_id >> index_msb;
}
struct apic apic_flat = {
@@ -212,7 +212,7 @@ struct apic apic_flat = {
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
.wait_for_init_deassert = NULL,
.smp_callin_clear_local_apic = NULL,
- .inquire_remote_apic = NULL,
+ .inquire_remote_apic = default_inquire_remote_apic,
.read = native_apic_mem_read,
.write = native_apic_mem_write,
@@ -235,7 +235,7 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
* regardless of how many processors are present (x86_64 ES7000
* is an example).
*/
- if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
+ if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
printk(KERN_DEBUG "system APIC only can use physical flat");
return 1;
@@ -362,7 +362,7 @@ struct apic apic_physflat = {
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
.wait_for_init_deassert = NULL,
.smp_callin_clear_local_apic = NULL,
- .inquire_remote_apic = NULL,
+ .inquire_remote_apic = default_inquire_remote_apic,
.read = native_apic_mem_read,
.write = native_apic_mem_write,
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 1c11b819f24..69328ac8de9 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -145,7 +145,7 @@ es7000_rename_gsi(int ioapic, int gsi)
return gsi;
}
-static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
+static int __cpuinit wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
{
unsigned long vect = 0, psaival = 0;
@@ -254,7 +254,7 @@ static int parse_unisys_oem(char *oemptr)
}
#ifdef CONFIG_ACPI
-static int find_unisys_acpi_oem_table(unsigned long *oem_addr)
+static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr)
{
struct acpi_table_header *header = NULL;
struct es7000_oem_table *table;
@@ -285,7 +285,7 @@ static int find_unisys_acpi_oem_table(unsigned long *oem_addr)
return 0;
}
-static void unmap_unisys_acpi_oem_table(unsigned long oem_addr)
+static void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr)
{
if (!oem_addr)
return;
@@ -306,7 +306,7 @@ static int es7000_check_dsdt(void)
static int es7000_acpi_ret;
/* Hook from generic ACPI tables.c */
-static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
unsigned long oem_addr = 0;
int check_dsdt;
@@ -717,7 +717,7 @@ struct apic apic_es7000_cluster = {
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
};
-struct apic apic_es7000 = {
+struct apic __refdata apic_es7000 = {
.name = "es7000",
.probe = probe_es7000,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 767fe7e46d6..1946fac42ab 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -59,6 +59,7 @@
#include <asm/setup.h>
#include <asm/irq_remapping.h>
#include <asm/hpet.h>
+#include <asm/hw_irq.h>
#include <asm/uv/uv_hub.h>
#include <asm/uv/uv_irq.h>
@@ -129,12 +130,9 @@ struct irq_pin_list {
struct irq_pin_list *next;
};
-static struct irq_pin_list *get_one_free_irq_2_pin(int cpu)
+static struct irq_pin_list *get_one_free_irq_2_pin(int node)
{
struct irq_pin_list *pin;
- int node;
-
- node = cpu_to_node(cpu);
pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
@@ -148,9 +146,6 @@ struct irq_cfg {
unsigned move_cleanup_count;
u8 vector;
u8 move_in_progress : 1;
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
- u8 move_desc_pending : 1;
-#endif
};
/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -212,12 +207,9 @@ static struct irq_cfg *irq_cfg(unsigned int irq)
return cfg;
}
-static struct irq_cfg *get_one_free_irq_cfg(int cpu)
+static struct irq_cfg *get_one_free_irq_cfg(int node)
{
struct irq_cfg *cfg;
- int node;
-
- node = cpu_to_node(cpu);
cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
if (cfg) {
@@ -238,13 +230,13 @@ static struct irq_cfg *get_one_free_irq_cfg(int cpu)
return cfg;
}
-int arch_init_chip_data(struct irq_desc *desc, int cpu)
+int arch_init_chip_data(struct irq_desc *desc, int node)
{
struct irq_cfg *cfg;
cfg = desc->chip_data;
if (!cfg) {
- desc->chip_data = get_one_free_irq_cfg(cpu);
+ desc->chip_data = get_one_free_irq_cfg(node);
if (!desc->chip_data) {
printk(KERN_ERR "can not alloc irq_cfg\n");
BUG_ON(1);
@@ -254,10 +246,9 @@ int arch_init_chip_data(struct irq_desc *desc, int cpu)
return 0;
}
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-
+/* for move_irq_desc */
static void
-init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
+init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int node)
{
struct irq_pin_list *old_entry, *head, *tail, *entry;
@@ -266,7 +257,7 @@ init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
if (!old_entry)
return;
- entry = get_one_free_irq_2_pin(cpu);
+ entry = get_one_free_irq_2_pin(node);
if (!entry)
return;
@@ -276,7 +267,7 @@ init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
tail = entry;
old_entry = old_entry->next;
while (old_entry) {
- entry = get_one_free_irq_2_pin(cpu);
+ entry = get_one_free_irq_2_pin(node);
if (!entry) {
entry = head;
while (entry) {
@@ -316,12 +307,12 @@ static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
}
void arch_init_copy_chip_data(struct irq_desc *old_desc,
- struct irq_desc *desc, int cpu)
+ struct irq_desc *desc, int node)
{
struct irq_cfg *cfg;
struct irq_cfg *old_cfg;
- cfg = get_one_free_irq_cfg(cpu);
+ cfg = get_one_free_irq_cfg(node);
if (!cfg)
return;
@@ -332,7 +323,7 @@ void arch_init_copy_chip_data(struct irq_desc *old_desc,
memcpy(cfg, old_cfg, sizeof(struct irq_cfg));
- init_copy_irq_2_pin(old_cfg, cfg, cpu);
+ init_copy_irq_2_pin(old_cfg, cfg, node);
}
static void free_irq_cfg(struct irq_cfg *old_cfg)
@@ -356,19 +347,7 @@ void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
old_desc->chip_data = NULL;
}
}
-
-static void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
- struct irq_cfg *cfg = desc->chip_data;
-
- if (!cfg->move_in_progress) {
- /* it means that domain is not changed */
- if (!cpumask_intersects(desc->affinity, mask))
- cfg->move_desc_pending = 1;
- }
-}
-#endif
+/* end for move_irq_desc */
#else
static struct irq_cfg *irq_cfg(unsigned int irq)
@@ -378,13 +357,6 @@ static struct irq_cfg *irq_cfg(unsigned int irq)
#endif
-#ifndef CONFIG_NUMA_MIGRATE_IRQ_DESC
-static inline void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-}
-#endif
-
struct io_apic {
unsigned int index;
unsigned int unused[3];
@@ -518,132 +490,18 @@ static void ioapic_mask_entry(int apic, int pin)
spin_unlock_irqrestore(&ioapic_lock, flags);
}
-#ifdef CONFIG_SMP
-static void send_cleanup_vector(struct irq_cfg *cfg)
-{
- cpumask_var_t cleanup_mask;
-
- if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
- unsigned int i;
- cfg->move_cleanup_count = 0;
- for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
- cfg->move_cleanup_count++;
- for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
- apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
- } else {
- cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
- cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
- apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
- free_cpumask_var(cleanup_mask);
- }
- cfg->move_in_progress = 0;
-}
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
- int apic, pin;
- struct irq_pin_list *entry;
- u8 vector = cfg->vector;
-
- entry = cfg->irq_2_pin;
- for (;;) {
- unsigned int reg;
-
- if (!entry)
- break;
-
- apic = entry->apic;
- pin = entry->pin;
- /*
- * 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;
- io_apic_modify(apic, 0x10 + pin*2, reg);
- if (!entry->next)
- break;
- entry = entry->next;
- }
-}
-
-static int
-assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
-
-/*
- * Either sets desc->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
- * leaves desc->affinity untouched.
- */
-static unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
-{
- struct irq_cfg *cfg;
- unsigned int irq;
-
- if (!cpumask_intersects(mask, cpu_online_mask))
- return BAD_APICID;
-
- irq = desc->irq;
- cfg = desc->chip_data;
- if (assign_irq_vector(irq, cfg, mask))
- return BAD_APICID;
-
- /* check that before desc->addinity get updated */
- set_extra_move_desc(desc, mask);
-
- cpumask_copy(desc->affinity, mask);
-
- return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
-}
-
-static void
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
- struct irq_cfg *cfg;
- unsigned long flags;
- unsigned int dest;
- unsigned int irq;
-
- irq = desc->irq;
- cfg = desc->chip_data;
-
- spin_lock_irqsave(&ioapic_lock, flags);
- dest = set_desc_affinity(desc, mask);
- if (dest != BAD_APICID) {
- /* Only the high 8 bits are valid. */
- dest = SET_APIC_LOGICAL_ID(dest);
- __target_IO_APIC_irq(irq, dest, cfg);
- }
- spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-static void
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
- struct irq_desc *desc;
-
- desc = irq_to_desc(irq);
-
- set_ioapic_affinity_irq_desc(desc, mask);
-}
-#endif /* CONFIG_SMP */
-
/*
* The common case is 1:1 IRQ<->pin mappings. Sometimes there are
* shared ISA-space IRQs, so we have to support them. We are super
* fast in the common case, and fast for shared ISA-space IRQs.
*/
-static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
+static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
{
struct irq_pin_list *entry;
entry = cfg->irq_2_pin;
if (!entry) {
- entry = get_one_free_irq_2_pin(cpu);
+ entry = get_one_free_irq_2_pin(node);
if (!entry) {
printk(KERN_ERR "can not alloc irq_2_pin to add %d - %d\n",
apic, pin);
@@ -663,7 +521,7 @@ static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
entry = entry->next;
}
- entry->next = get_one_free_irq_2_pin(cpu);
+ entry->next = get_one_free_irq_2_pin(node);
entry = entry->next;
entry->apic = apic;
entry->pin = pin;
@@ -672,7 +530,7 @@ static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
/*
* Reroute an IRQ to a different pin.
*/
-static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
+static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
int oldapic, int oldpin,
int newapic, int newpin)
{
@@ -692,7 +550,7 @@ static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
/* why? call replace before add? */
if (!replaced)
- add_pin_to_irq_cpu(cfg, cpu, newapic, newpin);
+ add_pin_to_irq_node(cfg, node, newapic, newpin);
}
static inline void io_apic_modify_irq(struct irq_cfg *cfg,
@@ -850,7 +708,6 @@ static int __init ioapic_pirq_setup(char *str)
__setup("pirq=", ioapic_pirq_setup);
#endif /* CONFIG_X86_32 */
-#ifdef CONFIG_INTR_REMAP
struct IO_APIC_route_entry **alloc_ioapic_entries(void)
{
int apic;
@@ -948,20 +805,6 @@ int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries)
return 0;
}
-void reinit_intr_remapped_IO_APIC(int intr_remapping,
- struct IO_APIC_route_entry **ioapic_entries)
-
-{
- /*
- * 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(ioapic_entries);
-}
-
void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
{
int apic;
@@ -971,7 +814,6 @@ void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
kfree(ioapic_entries);
}
-#endif
/*
* Find the IRQ entry number of a certain pin.
@@ -1032,54 +874,6 @@ static int __init find_isa_irq_apic(int irq, int type)
return -1;
}
-/*
- * Find a specific PCI IRQ entry.
- * Not an __init, possibly needed by modules
- */
-static int pin_2_irq(int idx, int apic, int pin);
-
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
-{
- int apic, i, best_guess = -1;
-
- apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
- bus, slot, pin);
- if (test_bit(bus, mp_bus_not_pci)) {
- apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
- return -1;
- }
- for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].srcbus;
-
- for (apic = 0; apic < nr_ioapics; apic++)
- if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
- mp_irqs[i].dstapic == MP_APIC_ALL)
- break;
-
- if (!test_bit(lbus, mp_bus_not_pci) &&
- !mp_irqs[i].irqtype &&
- (bus == lbus) &&
- (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
-
- if (!(apic || IO_APIC_IRQ(irq)))
- continue;
-
- if (pin == (mp_irqs[i].srcbusirq & 3))
- return irq;
- /*
- * Use the first all-but-pin matching entry as a
- * best-guess fuzzy result for broken mptables.
- */
- if (best_guess < 0)
- best_guess = irq;
- }
- }
- return best_guess;
-}
-
-EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-
#if defined(CONFIG_EISA) || defined(CONFIG_MCA)
/*
* EISA Edge/Level control register, ELCR
@@ -1298,6 +1092,64 @@ static int pin_2_irq(int idx, int apic, int pin)
return irq;
}
+/*
+ * Find a specific PCI IRQ entry.
+ * Not an __init, possibly needed by modules
+ */
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
+ struct io_apic_irq_attr *irq_attr)
+{
+ int apic, i, best_guess = -1;
+
+ apic_printk(APIC_DEBUG,
+ "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
+ bus, slot, pin);
+ if (test_bit(bus, mp_bus_not_pci)) {
+ apic_printk(APIC_VERBOSE,
+ "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
+ return -1;
+ }
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].srcbus;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
+ mp_irqs[i].dstapic == MP_APIC_ALL)
+ break;
+
+ if (!test_bit(lbus, mp_bus_not_pci) &&
+ !mp_irqs[i].irqtype &&
+ (bus == lbus) &&
+ (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
+
+ if (!(apic || IO_APIC_IRQ(irq)))
+ continue;
+
+ if (pin == (mp_irqs[i].srcbusirq & 3)) {
+ set_io_apic_irq_attr(irq_attr, apic,
+ mp_irqs[i].dstirq,
+ irq_trigger(i),
+ irq_polarity(i));
+ return irq;
+ }
+ /*
+ * Use the first all-but-pin matching entry as a
+ * best-guess fuzzy result for broken mptables.
+ */
+ if (best_guess < 0) {
+ set_io_apic_irq_attr(irq_attr, apic,
+ mp_irqs[i].dstirq,
+ irq_trigger(i),
+ irq_polarity(i));
+ best_guess = irq;
+ }
+ }
+ }
+ return best_guess;
+}
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
+
void lock_vector_lock(void)
{
/* Used to the online set of cpus does not change
@@ -1628,58 +1480,70 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
ioapic_write_entry(apic_id, pin, entry);
}
+static struct {
+ DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+} mp_ioapic_routing[MAX_IO_APICS];
+
static void __init setup_IO_APIC_irqs(void)
{
- int apic_id, pin, idx, irq;
+ int apic_id = 0, pin, idx, irq;
int notcon = 0;
struct irq_desc *desc;
struct irq_cfg *cfg;
- int cpu = boot_cpu_id;
+ int node = cpu_to_node(boot_cpu_id);
apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
- for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
- for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
-
- idx = find_irq_entry(apic_id, pin, mp_INT);
- if (idx == -1) {
- if (!notcon) {
- notcon = 1;
- apic_printk(APIC_VERBOSE,
- KERN_DEBUG " %d-%d",
- mp_ioapics[apic_id].apicid, pin);
- } else
- apic_printk(APIC_VERBOSE, " %d-%d",
- mp_ioapics[apic_id].apicid, pin);
- continue;
- }
- if (notcon) {
- apic_printk(APIC_VERBOSE,
- " (apicid-pin) not connected\n");
- notcon = 0;
- }
+#ifdef CONFIG_ACPI
+ if (!acpi_disabled && acpi_ioapic) {
+ apic_id = mp_find_ioapic(0);
+ if (apic_id < 0)
+ apic_id = 0;
+ }
+#endif
- irq = pin_2_irq(idx, apic_id, pin);
+ for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
+ idx = find_irq_entry(apic_id, pin, mp_INT);
+ if (idx == -1) {
+ if (!notcon) {
+ notcon = 1;
+ apic_printk(APIC_VERBOSE,
+ KERN_DEBUG " %d-%d",
+ mp_ioapics[apic_id].apicid, pin);
+ } else
+ apic_printk(APIC_VERBOSE, " %d-%d",
+ mp_ioapics[apic_id].apicid, pin);
+ continue;
+ }
+ if (notcon) {
+ apic_printk(APIC_VERBOSE,
+ " (apicid-pin) not connected\n");
+ notcon = 0;
+ }
- /*
- * Skip the timer IRQ if there's a quirk handler
- * installed and if it returns 1:
- */
- if (apic->multi_timer_check &&
- apic->multi_timer_check(apic_id, irq))
- continue;
+ irq = pin_2_irq(idx, apic_id, pin);
- desc = irq_to_desc_alloc_cpu(irq, cpu);
- if (!desc) {
- printk(KERN_INFO "can not get irq_desc for %d\n", irq);
- continue;
- }
- cfg = desc->chip_data;
- add_pin_to_irq_cpu(cfg, cpu, apic_id, pin);
+ /*
+ * Skip the timer IRQ if there's a quirk handler
+ * installed and if it returns 1:
+ */
+ if (apic->multi_timer_check &&
+ apic->multi_timer_check(apic_id, irq))
+ continue;
- setup_IO_APIC_irq(apic_id, pin, irq, desc,
- irq_trigger(idx), irq_polarity(idx));
+ desc = irq_to_desc_alloc_node(irq, node);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+ continue;
}
+ cfg = desc->chip_data;
+ add_pin_to_irq_node(cfg, node, apic_id, pin);
+ /*
+ * don't mark it in pin_programmed, so later acpi could
+ * set it correctly when irq < 16
+ */
+ setup_IO_APIC_irq(apic_id, pin, irq, desc,
+ irq_trigger(idx), irq_polarity(idx));
}
if (notcon)
@@ -1869,7 +1733,7 @@ __apicdebuginit(void) print_APIC_bitfield(int base)
__apicdebuginit(void) print_local_APIC(void *dummy)
{
- unsigned int v, ver, maxlvt;
+ unsigned int i, v, ver, maxlvt;
u64 icr;
if (apic_verbosity == APIC_QUIET)
@@ -1957,6 +1821,18 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
v = apic_read(APIC_TDCR);
printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
+
+ if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+ v = apic_read(APIC_EFEAT);
+ maxlvt = (v >> 16) & 0xff;
+ printk(KERN_DEBUG "... APIC EFEAT: %08x\n", v);
+ v = apic_read(APIC_ECTRL);
+ printk(KERN_DEBUG "... APIC ECTRL: %08x\n", v);
+ for (i = 0; i < maxlvt; i++) {
+ v = apic_read(APIC_EILVTn(i));
+ printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v);
+ }
+ }
printk("\n");
}
@@ -2005,6 +1881,11 @@ __apicdebuginit(void) print_PIC(void)
__apicdebuginit(int) print_all_ICs(void)
{
print_PIC();
+
+ /* don't print out if apic is not there */
+ if (!cpu_has_apic || disable_apic)
+ return 0;
+
print_all_local_APICs();
print_IO_APIC();
@@ -2360,6 +2241,118 @@ static int ioapic_retrigger_irq(unsigned int irq)
*/
#ifdef CONFIG_SMP
+static void send_cleanup_vector(struct irq_cfg *cfg)
+{
+ cpumask_var_t cleanup_mask;
+
+ if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
+ unsigned int i;
+ cfg->move_cleanup_count = 0;
+ for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ cfg->move_cleanup_count++;
+ for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
+ } else {
+ cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+ cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
+ apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+ free_cpumask_var(cleanup_mask);
+ }
+ cfg->move_in_progress = 0;
+}
+
+static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
+{
+ int apic, pin;
+ struct irq_pin_list *entry;
+ u8 vector = cfg->vector;
+
+ entry = cfg->irq_2_pin;
+ for (;;) {
+ unsigned int reg;
+
+ if (!entry)
+ break;
+
+ apic = entry->apic;
+ pin = entry->pin;
+ /*
+ * 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;
+ io_apic_modify(apic, 0x10 + pin*2, reg);
+ if (!entry->next)
+ break;
+ entry = entry->next;
+ }
+}
+
+static int
+assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
+
+/*
+ * Either sets desc->affinity to a valid value, and returns
+ * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
+ * leaves desc->affinity untouched.
+ */
+static unsigned int
+set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
+{
+ struct irq_cfg *cfg;
+ unsigned int irq;
+
+ if (!cpumask_intersects(mask, cpu_online_mask))
+ return BAD_APICID;
+
+ irq = desc->irq;
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
+ return BAD_APICID;
+
+ cpumask_copy(desc->affinity, mask);
+
+ return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+}
+
+static int
+set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+ struct irq_cfg *cfg;
+ unsigned long flags;
+ unsigned int dest;
+ unsigned int irq;
+ int ret = -1;
+
+ irq = desc->irq;
+ cfg = desc->chip_data;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ dest = set_desc_affinity(desc, mask);
+ if (dest != BAD_APICID) {
+ /* Only the high 8 bits are valid. */
+ dest = SET_APIC_LOGICAL_ID(dest);
+ __target_IO_APIC_irq(irq, dest, cfg);
+ ret = 0;
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return ret;
+}
+
+static int
+set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
+{
+ struct irq_desc *desc;
+
+ desc = irq_to_desc(irq);
+
+ return set_ioapic_affinity_irq_desc(desc, mask);
+}
#ifdef CONFIG_INTR_REMAP
@@ -2374,26 +2367,25 @@ static int ioapic_retrigger_irq(unsigned int irq)
* Real vector that is used for interrupting cpu will be coming from
* the interrupt-remapping table entry.
*/
-static void
+static int
migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
{
struct irq_cfg *cfg;
struct irte irte;
unsigned int dest;
unsigned int irq;
+ int ret = -1;
if (!cpumask_intersects(mask, cpu_online_mask))
- return;
+ return ret;
irq = desc->irq;
if (get_irte(irq, &irte))
- return;
+ return ret;
cfg = desc->chip_data;
if (assign_irq_vector(irq, cfg, mask))
- return;
-
- set_extra_move_desc(desc, mask);
+ return ret;
dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
@@ -2409,27 +2401,30 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
send_cleanup_vector(cfg);
cpumask_copy(desc->affinity, mask);
+
+ return 0;
}
/*
* Migrates the IRQ destination in the process context.
*/
-static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
const struct cpumask *mask)
{
- migrate_ioapic_irq_desc(desc, mask);
+ return migrate_ioapic_irq_desc(desc, mask);
}
-static void set_ir_ioapic_affinity_irq(unsigned int irq,
+static int set_ir_ioapic_affinity_irq(unsigned int irq,
const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
- set_ir_ioapic_affinity_irq_desc(desc, mask);
+ return set_ir_ioapic_affinity_irq_desc(desc, mask);
}
#else
-static inline void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static inline int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
const struct cpumask *mask)
{
+ return 0;
}
#endif
@@ -2491,86 +2486,19 @@ static void irq_complete_move(struct irq_desc **descp)
struct irq_cfg *cfg = desc->chip_data;
unsigned vector, me;
- if (likely(!cfg->move_in_progress)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
- if (likely(!cfg->move_desc_pending))
- return;
-
- /* domain has not changed, but affinity did */
- me = smp_processor_id();
- if (cpumask_test_cpu(me, desc->affinity)) {
- *descp = desc = move_irq_desc(desc, me);
- /* get the new one */
- cfg = desc->chip_data;
- cfg->move_desc_pending = 0;
- }
-#endif
+ if (likely(!cfg->move_in_progress))
return;
- }
vector = ~get_irq_regs()->orig_ax;
me = smp_processor_id();
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
- *descp = desc = move_irq_desc(desc, me);
- /* get the new one */
- cfg = desc->chip_data;
-#endif
+ if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
send_cleanup_vector(cfg);
- }
}
#else
static inline void irq_complete_move(struct irq_desc **descp) {}
#endif
-#ifdef CONFIG_X86_X2APIC
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
-{
- int apic, pin;
- struct irq_pin_list *entry;
-
- entry = cfg->irq_2_pin;
- for (;;) {
-
- if (!entry)
- break;
-
- apic = entry->apic;
- pin = entry->pin;
- io_apic_eoi(apic, pin);
- entry = entry->next;
- }
-}
-
-static void
-eoi_ioapic_irq(struct irq_desc *desc)
-{
- struct irq_cfg *cfg;
- unsigned long flags;
- unsigned int irq;
-
- irq = desc->irq;
- cfg = desc->chip_data;
-
- spin_lock_irqsave(&ioapic_lock, flags);
- __eoi_ioapic_irq(irq, cfg);
- spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-static void ack_x2apic_level(unsigned int irq)
-{
- struct irq_desc *desc = irq_to_desc(irq);
- ack_x2APIC_irq();
- eoi_ioapic_irq(desc);
-}
-
-static void ack_x2apic_edge(unsigned int irq)
-{
- ack_x2APIC_irq();
-}
-#endif
-
static void ack_apic_edge(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
@@ -2680,22 +2608,50 @@ static void ack_apic_level(unsigned int irq)
}
#ifdef CONFIG_INTR_REMAP
+static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+{
+ int apic, pin;
+ struct irq_pin_list *entry;
+
+ entry = cfg->irq_2_pin;
+ for (;;) {
+
+ if (!entry)
+ break;
+
+ apic = entry->apic;
+ pin = entry->pin;
+ io_apic_eoi(apic, pin);
+ entry = entry->next;
+ }
+}
+
+static void
+eoi_ioapic_irq(struct irq_desc *desc)
+{
+ struct irq_cfg *cfg;
+ unsigned long flags;
+ unsigned int irq;
+
+ irq = desc->irq;
+ cfg = desc->chip_data;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __eoi_ioapic_irq(irq, cfg);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
static void ir_ack_apic_edge(unsigned int irq)
{
-#ifdef CONFIG_X86_X2APIC
- if (x2apic_enabled())
- return ack_x2apic_edge(irq);
-#endif
- return ack_apic_edge(irq);
+ ack_APIC_irq();
}
static void ir_ack_apic_level(unsigned int irq)
{
-#ifdef CONFIG_X86_X2APIC
- if (x2apic_enabled())
- return ack_x2apic_level(irq);
-#endif
- return ack_apic_level(irq);
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ ack_APIC_irq();
+ eoi_ioapic_irq(desc);
}
#endif /* CONFIG_INTR_REMAP */
@@ -2900,7 +2856,7 @@ static inline void __init check_timer(void)
{
struct irq_desc *desc = irq_to_desc(0);
struct irq_cfg *cfg = desc->chip_data;
- int cpu = boot_cpu_id;
+ int node = cpu_to_node(boot_cpu_id);
int apic1, pin1, apic2, pin2;
unsigned long flags;
int no_pin1 = 0;
@@ -2966,7 +2922,7 @@ static inline void __init check_timer(void)
* Ok, does IRQ0 through the IOAPIC work?
*/
if (no_pin1) {
- add_pin_to_irq_cpu(cfg, cpu, apic1, pin1);
+ add_pin_to_irq_node(cfg, node, apic1, pin1);
setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
} else {
/* for edge trigger, setup_IO_APIC_irq already
@@ -3003,7 +2959,7 @@ static inline void __init check_timer(void)
/*
* legacy devices should be connected to IO APIC #0
*/
- replace_pin_at_irq_cpu(cfg, cpu, apic1, pin1, apic2, pin2);
+ replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
enable_8259A_irq(0);
if (timer_irq_works()) {
@@ -3215,14 +3171,13 @@ static int nr_irqs_gsi = NR_IRQS_LEGACY;
/*
* Dynamic irq allocate and deallocation
*/
-unsigned int create_irq_nr(unsigned int irq_want)
+unsigned int create_irq_nr(unsigned int irq_want, int node)
{
/* Allocate an unused irq */
unsigned int irq;
unsigned int new;
unsigned long flags;
struct irq_cfg *cfg_new = NULL;
- int cpu = boot_cpu_id;
struct irq_desc *desc_new = NULL;
irq = 0;
@@ -3231,7 +3186,7 @@ unsigned int create_irq_nr(unsigned int irq_want)
spin_lock_irqsave(&vector_lock, flags);
for (new = irq_want; new < nr_irqs; new++) {
- desc_new = irq_to_desc_alloc_cpu(new, cpu);
+ desc_new = irq_to_desc_alloc_node(new, node);
if (!desc_new) {
printk(KERN_INFO "can not get irq_desc for %d\n", new);
continue;
@@ -3240,6 +3195,9 @@ unsigned int create_irq_nr(unsigned int irq_want)
if (cfg_new->vector != 0)
continue;
+
+ desc_new = move_irq_desc(desc_new, node);
+
if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
irq = new;
break;
@@ -3257,11 +3215,12 @@ unsigned int create_irq_nr(unsigned int irq_want)
int create_irq(void)
{
+ int node = cpu_to_node(boot_cpu_id);
unsigned int irq_want;
int irq;
irq_want = nr_irqs_gsi;
- irq = create_irq_nr(irq_want);
+ irq = create_irq_nr(irq_want, node);
if (irq == 0)
irq = -1;
@@ -3363,7 +3322,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
}
#ifdef CONFIG_SMP
-static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
@@ -3372,7 +3331,7 @@ static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
cfg = desc->chip_data;
@@ -3384,13 +3343,15 @@ static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
msg.address_lo |= MSI_ADDR_DEST_ID(dest);
write_msi_msg_desc(desc, &msg);
+
+ return 0;
}
#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
+static int
ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
@@ -3399,11 +3360,11 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
struct irte irte;
if (get_irte(irq, &irte))
- return;
+ return -1;
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
irte.vector = cfg->vector;
irte.dest_id = IRTE_DEST(dest);
@@ -3420,6 +3381,8 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
*/
if (cfg->move_in_progress)
send_cleanup_vector(cfg);
+
+ return 0;
}
#endif
@@ -3515,15 +3478,17 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
unsigned int irq_want;
struct intel_iommu *iommu = NULL;
int index = 0;
+ int node;
/* x86 doesn't support multiple MSI yet */
if (type == PCI_CAP_ID_MSI && nvec > 1)
return 1;
+ node = dev_to_node(&dev->dev);
irq_want = nr_irqs_gsi;
sub_handle = 0;
list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = create_irq_nr(irq_want);
+ irq = create_irq_nr(irq_want, node);
if (irq == 0)
return -1;
irq_want = irq + 1;
@@ -3573,7 +3538,7 @@ void arch_teardown_msi_irq(unsigned int irq)
#if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
#ifdef CONFIG_SMP
-static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
@@ -3582,7 +3547,7 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
cfg = desc->chip_data;
@@ -3594,6 +3559,8 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
msg.address_lo |= MSI_ADDR_DEST_ID(dest);
dmar_msi_write(irq, &msg);
+
+ return 0;
}
#endif /* CONFIG_SMP */
@@ -3627,7 +3594,7 @@ int arch_setup_dmar_msi(unsigned int irq)
#ifdef CONFIG_HPET_TIMER
#ifdef CONFIG_SMP
-static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
@@ -3636,7 +3603,7 @@ static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
cfg = desc->chip_data;
@@ -3648,6 +3615,8 @@ static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
msg.address_lo |= MSI_ADDR_DEST_ID(dest);
hpet_msi_write(irq, &msg);
+
+ return 0;
}
#endif /* CONFIG_SMP */
@@ -3667,12 +3636,14 @@ int arch_setup_hpet_msi(unsigned int irq)
{
int ret;
struct msi_msg msg;
+ struct irq_desc *desc = irq_to_desc(irq);
ret = msi_compose_msg(NULL, irq, &msg);
if (ret < 0)
return ret;
hpet_msi_write(irq, &msg);
+ desc->status |= IRQ_MOVE_PCNTXT;
set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq,
"edge");
@@ -3702,7 +3673,7 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
write_ht_irq_msg(irq, &msg);
}
-static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
@@ -3710,11 +3681,13 @@ static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
cfg = desc->chip_data;
target_ht_irq(irq, dest, cfg->vector);
+
+ return 0;
}
#endif
@@ -3789,6 +3762,8 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
unsigned long flags;
int err;
+ BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
cfg = irq_cfg(irq);
err = assign_irq_vector(irq, cfg, eligible_cpu);
@@ -3802,15 +3777,13 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
mmr_value = 0;
entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
- BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
- entry->vector = cfg->vector;
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->polarity = 0;
- entry->trigger = 0;
- entry->mask = 0;
- entry->dest = apic->cpu_mask_to_apicid(eligible_cpu);
+ entry->vector = cfg->vector;
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->polarity = 0;
+ entry->trigger = 0;
+ entry->mask = 0;
+ entry->dest = apic->cpu_mask_to_apicid(eligible_cpu);
mmr_pnode = uv_blade_to_pnode(mmr_blade);
uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
@@ -3828,10 +3801,10 @@ void arch_disable_uv_irq(int mmr_blade, unsigned long mmr_offset)
struct uv_IO_APIC_route_entry *entry;
int mmr_pnode;
+ BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
mmr_value = 0;
entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
- BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
entry->mask = 1;
mmr_pnode = uv_blade_to_pnode(mmr_blade);
@@ -3895,6 +3868,71 @@ int __init arch_probe_nr_irqs(void)
}
#endif
+static int __io_apic_set_pci_routing(struct device *dev, int irq,
+ struct io_apic_irq_attr *irq_attr)
+{
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+ int node;
+ int ioapic, pin;
+ int trigger, polarity;
+
+ ioapic = irq_attr->ioapic;
+ if (!IO_APIC_IRQ(irq)) {
+ apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
+ ioapic);
+ return -EINVAL;
+ }
+
+ if (dev)
+ node = dev_to_node(dev);
+ else
+ node = cpu_to_node(boot_cpu_id);
+
+ desc = irq_to_desc_alloc_node(irq, node);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc %d\n", irq);
+ return 0;
+ }
+
+ pin = irq_attr->ioapic_pin;
+ trigger = irq_attr->trigger;
+ polarity = irq_attr->polarity;
+
+ /*
+ * IRQs < 16 are already in the irq_2_pin[] map
+ */
+ if (irq >= NR_IRQS_LEGACY) {
+ cfg = desc->chip_data;
+ add_pin_to_irq_node(cfg, node, ioapic, pin);
+ }
+
+ setup_IO_APIC_irq(ioapic, pin, irq, desc, trigger, polarity);
+
+ return 0;
+}
+
+int io_apic_set_pci_routing(struct device *dev, int irq,
+ struct io_apic_irq_attr *irq_attr)
+{
+ int ioapic, pin;
+ /*
+ * Avoid pin reprogramming. PRTs typically include entries
+ * with redundant pin->gsi mappings (but unique PCI devices);
+ * we only program the IOAPIC on the first.
+ */
+ ioapic = irq_attr->ioapic;
+ pin = irq_attr->ioapic_pin;
+ if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) {
+ pr_debug("Pin %d-%d already programmed\n",
+ mp_ioapics[ioapic].apicid, pin);
+ return 0;
+ }
+ set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed);
+
+ return __io_apic_set_pci_routing(dev, irq, irq_attr);
+}
+
/* --------------------------------------------------------------------------
ACPI-based IOAPIC Configuration
-------------------------------------------------------------------------- */
@@ -3975,6 +4013,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
return apic_id;
}
+#endif
int __init io_apic_get_version(int ioapic)
{
@@ -3987,39 +4026,6 @@ int __init io_apic_get_version(int ioapic)
return reg_01.bits.version;
}
-#endif
-
-int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int polarity)
-{
- struct irq_desc *desc;
- struct irq_cfg *cfg;
- int cpu = boot_cpu_id;
-
- if (!IO_APIC_IRQ(irq)) {
- apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
- ioapic);
- return -EINVAL;
- }
-
- desc = irq_to_desc_alloc_cpu(irq, cpu);
- if (!desc) {
- printk(KERN_INFO "can not get irq_desc %d\n", irq);
- return 0;
- }
-
- /*
- * IRQs < 16 are already in the irq_2_pin[] map
- */
- if (irq >= NR_IRQS_LEGACY) {
- cfg = desc->chip_data;
- add_pin_to_irq_cpu(cfg, cpu, ioapic, pin);
- }
-
- setup_IO_APIC_irq(ioapic, pin, irq, desc, triggering, polarity);
-
- return 0;
-}
-
int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
{
@@ -4050,51 +4056,44 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
#ifdef CONFIG_SMP
void __init setup_ioapic_dest(void)
{
- int pin, ioapic, irq, irq_entry;
+ int pin, ioapic = 0, irq, irq_entry;
struct irq_desc *desc;
- struct irq_cfg *cfg;
const struct cpumask *mask;
if (skip_ioapic_setup == 1)
return;
- for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
- for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
- irq_entry = find_irq_entry(ioapic, pin, mp_INT);
- if (irq_entry == -1)
- continue;
- irq = pin_2_irq(irq_entry, ioapic, pin);
-
- /* setup_IO_APIC_irqs could fail to get vector for some device
- * when you have too many devices, because at that time only boot
- * cpu is online.
- */
- desc = irq_to_desc(irq);
- cfg = desc->chip_data;
- if (!cfg->vector) {
- setup_IO_APIC_irq(ioapic, pin, irq, desc,
- irq_trigger(irq_entry),
- irq_polarity(irq_entry));
- continue;
+#ifdef CONFIG_ACPI
+ if (!acpi_disabled && acpi_ioapic) {
+ ioapic = mp_find_ioapic(0);
+ if (ioapic < 0)
+ ioapic = 0;
+ }
+#endif
- }
+ for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+ irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+ if (irq_entry == -1)
+ continue;
+ irq = pin_2_irq(irq_entry, ioapic, pin);
- /*
- * Honour affinities which have been set in early boot
- */
- if (desc->status &
- (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
- mask = desc->affinity;
- else
- mask = apic->target_cpus();
+ desc = irq_to_desc(irq);
- if (intr_remapping_enabled)
- set_ir_ioapic_affinity_irq_desc(desc, mask);
- else
- set_ioapic_affinity_irq_desc(desc, mask);
- }
+ /*
+ * Honour affinities which have been set in early boot
+ */
+ if (desc->status &
+ (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
+ mask = desc->affinity;
+ else
+ mask = apic->target_cpus();
+ if (intr_remapping_enabled)
+ set_ir_ioapic_affinity_irq_desc(desc, mask);
+ else
+ set_ioapic_affinity_irq_desc(desc, mask);
}
+
}
#endif
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index d6bd6240715..a691302dc3f 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -104,7 +104,7 @@ static __init void nmi_cpu_busy(void *data)
}
#endif
-static void report_broken_nmi(int cpu, int *prev_nmi_count)
+static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count)
{
printk(KERN_CONT "\n");
@@ -138,7 +138,7 @@ int __init check_nmi_watchdog(void)
if (!prev_nmi_count)
goto error;
- alloc_cpumask_var(&backtrace_mask, GFP_KERNEL);
+ alloc_cpumask_var(&backtrace_mask, GFP_KERNEL|__GFP_ZERO);
printk(KERN_INFO "Testing NMI watchdog ... ");
#ifdef CONFIG_SMP
@@ -414,7 +414,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
touched = 1;
}
- if (cpumask_test_cpu(cpu, backtrace_mask)) {
+ /* We can be called before check_nmi_watchdog, hence NULL check. */
+ if (backtrace_mask != NULL && cpumask_test_cpu(cpu, backtrace_mask)) {
static DEFINE_SPINLOCK(lock); /* Serialise the printks */
spin_lock(&lock);
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 01eda2ac65e..440a8bccd91 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -160,7 +160,6 @@ extern struct apic apic_summit;
extern struct apic apic_bigsmp;
extern struct apic apic_es7000;
extern struct apic apic_es7000_cluster;
-extern struct apic apic_default;
struct apic *apic = &apic_default;
EXPORT_SYMBOL_GPL(apic);
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 1783652bb0e..bc3e880f9b8 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -50,7 +50,7 @@ static struct apic *apic_probe[] __initdata = {
void __init default_setup_apic_routing(void)
{
#ifdef CONFIG_X86_X2APIC
- if (x2apic && (apic != &apic_x2apic_phys &&
+ if (x2apic_mode && (apic != &apic_x2apic_phys &&
#ifdef CONFIG_X86_UV
apic != &apic_x2apic_uv_x &&
#endif
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 9cfe1f415d8..344eee4ac0a 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -173,13 +173,6 @@ static inline int is_WPEG(struct rio_detail *rio){
rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
}
-
-/* In clustered mode, the high nibble of APIC ID is a cluster number.
- * The low nibble is a 4-bit bitmap. */
-#define XAPIC_DEST_CPUS_SHIFT 4
-#define XAPIC_DEST_CPUS_MASK ((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK (XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-
#define SUMMIT_APIC_DFR_VALUE (APIC_DFR_CLUSTER)
static const struct cpumask *summit_target_cpus(void)
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 4a903e2f0d1..8e4cbb255c3 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -10,7 +10,7 @@
#include <asm/apic.h>
#include <asm/ipi.h>
-DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1248318436e..780a733a5e7 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -19,6 +19,7 @@
#include <linux/timer.h>
#include <linux/cpu.h>
#include <linux/init.h>
+#include <linux/io.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
@@ -34,6 +35,17 @@ DEFINE_PER_CPU(int, x2apic_extra_bits);
static enum uv_system_type uv_system_type;
+static int early_get_nodeid(void)
+{
+ union uvh_node_id_u node_id;
+ unsigned long *mmr;
+
+ mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr));
+ node_id.v = *mmr;
+ early_iounmap(mmr, sizeof(*mmr));
+ return node_id.s.node_id;
+}
+
static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
if (!strcmp(oem_id, "SGI")) {
@@ -42,6 +54,8 @@ static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
else if (!strcmp(oem_table_id, "UVX"))
uv_system_type = UV_X2APIC;
else if (!strcmp(oem_table_id, "UVH")) {
+ __get_cpu_var(x2apic_extra_bits) =
+ early_get_nodeid() << (UV_APIC_PNODE_SHIFT - 1);
uv_system_type = UV_NON_UNIQUE_APIC;
return 1;
}
@@ -91,7 +105,7 @@ static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask)
cpumask_set_cpu(cpu, retmask);
}
-static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
{
#ifdef CONFIG_SMP
unsigned long val;
@@ -549,7 +563,8 @@ void __init uv_system_init(void)
unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
int max_pnode = 0;
- unsigned long mmr_base, present;
+ unsigned long mmr_base, present, paddr;
+ unsigned short pnode_mask;
map_low_mmrs();
@@ -568,15 +583,18 @@ void __init uv_system_init(void)
bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
uv_blade_info = kmalloc(bytes, GFP_KERNEL);
+ BUG_ON(!uv_blade_info);
get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
+ BUG_ON(!uv_node_to_blade);
memset(uv_node_to_blade, 255, bytes);
bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
+ BUG_ON(!uv_cpu_to_blade);
memset(uv_cpu_to_blade, 255, bytes);
blade = 0;
@@ -592,6 +610,7 @@ void __init uv_system_init(void)
}
}
+ pnode_mask = (1 << n_val) - 1;
node_id.v = uv_read_local_mmr(UVH_NODE_ID);
gnode_upper = (((unsigned long)node_id.s.node_id) &
~((1 << n_val) - 1)) << m_val;
@@ -615,7 +634,7 @@ void __init uv_system_init(void)
uv_cpu_hub_info(cpu)->numa_blade_id = blade;
uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
uv_cpu_hub_info(cpu)->pnode = pnode;
- uv_cpu_hub_info(cpu)->pnode_mask = (1 << n_val) - 1;
+ uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
@@ -631,6 +650,17 @@ void __init uv_system_init(void)
lcpu, blade);
}
+ /* Add blade/pnode info for nodes without cpus */
+ for_each_online_node(nid) {
+ if (uv_node_to_blade[nid] >= 0)
+ continue;
+ paddr = node_start_pfn(nid) << PAGE_SHIFT;
+ paddr = uv_soc_phys_ram_to_gpa(paddr);
+ pnode = (paddr >> m_val) & pnode_mask;
+ blade = boot_pnode_to_blade(pnode);
+ uv_node_to_blade[nid] = blade;
+ }
+
map_gru_high(max_pnode);
map_mmr_high(max_pnode);
map_config_high(max_pnode);
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 5a6aa1c1162..1a830cbd701 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -146,4 +146,5 @@ void foo(void)
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
+ OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
}
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index e72f062fb4b..898ecc47e12 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -125,6 +125,7 @@ int main(void)
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
+ OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
BLANK();
DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c
index f63882728d9..63a88e1f987 100644
--- a/arch/x86/kernel/bios_uv.c
+++ b/arch/x86/kernel/bios_uv.c
@@ -182,7 +182,8 @@ void uv_bios_init(void)
memcpy(&uv_systab, tab, sizeof(struct uv_systab));
iounmap(tab);
- printk(KERN_INFO "EFI UV System Table Revision %d\n", tab->revision);
+ printk(KERN_INFO "EFI UV System Table Revision %d\n",
+ uv_systab.revision);
}
#else /* !CONFIG_EFI */
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 8220ae69849..c965e521271 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -31,6 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
{ X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 },
+ { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 },
{ 0, 0, 0, 0 }
};
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7e4a459daa6..728b3750a3e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -272,7 +272,7 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
int cpu = smp_processor_id();
int node;
- unsigned apicid = hard_smp_processor_id();
+ unsigned apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
node = c->phys_proc_id;
if (apicid_to_node[apicid] != NUMA_NO_NODE)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c4f667896c2..b0517aa2bd3 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -114,6 +114,13 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
+static int __init x86_xsave_setup(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+ return 1;
+}
+__setup("noxsave", x86_xsave_setup);
+
#ifdef CONFIG_X86_32
static int cachesize_override __cpuinitdata = -1;
static int disable_x86_serial_nr __cpuinitdata = 1;
@@ -292,7 +299,8 @@ static const char *__cpuinit table_lookup_model(struct cpuinfo_x86 *c)
return NULL; /* Not found */
}
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_cleared[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_set[NCAPINTS] __cpuinitdata;
void load_percpu_segment(int cpu)
{
@@ -761,6 +769,12 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
if (this_cpu->c_identify)
this_cpu->c_identify(c);
+ /* Clear/Set all flags overriden by options, after probe */
+ for (i = 0; i < NCAPINTS; i++) {
+ c->x86_capability[i] &= ~cpu_caps_cleared[i];
+ c->x86_capability[i] |= cpu_caps_set[i];
+ }
+
#ifdef CONFIG_X86_64
c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
#endif
@@ -806,6 +820,16 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
#endif
init_hypervisor(c);
+
+ /*
+ * Clear/Set all flags overriden by options, need do it
+ * before following smp all cpus cap AND.
+ */
+ for (i = 0; i < NCAPINTS; i++) {
+ c->x86_capability[i] &= ~cpu_caps_cleared[i];
+ c->x86_capability[i] |= cpu_caps_set[i];
+ }
+
/*
* On SMP, boot_cpu_data holds the common feature set between
* all CPUs; so make sure that we indicate which features are
@@ -818,10 +842,6 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
}
- /* Clear all flags overriden by options */
- for (i = 0; i < NCAPINTS; i++)
- c->x86_capability[i] &= ~cleared_cpu_caps[i];
-
#ifdef CONFIG_X86_MCE
/* Init Machine Check Exception if available. */
mcheck_init(c);
@@ -1203,6 +1223,8 @@ void __cpuinit cpu_init(void)
load_TR_desc();
load_LDT(&init_mm.context);
+ t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+
#ifdef CONFIG_DOUBLEFAULT
/* Set up doublefault TSS pointer in the GDT */
__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
index 46e29ab96c6..6b2a52dd040 100755..100644
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -32,9 +32,7 @@
static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]);
static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]);
-static DEFINE_PER_CPU(unsigned, cpu_modelflag);
static DEFINE_PER_CPU(int, cpu_priv_count);
-static DEFINE_PER_CPU(unsigned, cpu_model);
static DEFINE_MUTEX(cpu_debug_lock);
@@ -80,302 +78,102 @@ static struct cpu_file_base cpu_file[] = {
{ "value", CPU_REG_ALL, 1 },
};
-/* Intel Registers Range */
-static struct cpu_debug_range cpu_intel_range[] = {
- { 0x00000000, 0x00000001, CPU_MC, CPU_INTEL_ALL },
- { 0x00000006, 0x00000007, CPU_MONITOR, CPU_CX_AT_XE },
- { 0x00000010, 0x00000010, CPU_TIME, CPU_INTEL_ALL },
- { 0x00000011, 0x00000013, CPU_PMC, CPU_INTEL_PENTIUM },
- { 0x00000017, 0x00000017, CPU_PLATFORM, CPU_PX_CX_AT_XE },
- { 0x0000001B, 0x0000001B, CPU_APIC, CPU_P6_CX_AT_XE },
-
- { 0x0000002A, 0x0000002A, CPU_POWERON, CPU_PX_CX_AT_XE },
- { 0x0000002B, 0x0000002B, CPU_POWERON, CPU_INTEL_XEON },
- { 0x0000002C, 0x0000002C, CPU_FREQ, CPU_INTEL_XEON },
- { 0x0000003A, 0x0000003A, CPU_CONTROL, CPU_CX_AT_XE },
-
- { 0x00000040, 0x00000043, CPU_LBRANCH, CPU_PM_CX_AT_XE },
- { 0x00000044, 0x00000047, CPU_LBRANCH, CPU_PM_CO_AT },
- { 0x00000060, 0x00000063, CPU_LBRANCH, CPU_C2_AT },
- { 0x00000064, 0x00000067, CPU_LBRANCH, CPU_INTEL_ATOM },
-
- { 0x00000079, 0x00000079, CPU_BIOS, CPU_P6_CX_AT_XE },
- { 0x00000088, 0x0000008A, CPU_CACHE, CPU_INTEL_P6 },
- { 0x0000008B, 0x0000008B, CPU_BIOS, CPU_P6_CX_AT_XE },
- { 0x0000009B, 0x0000009B, CPU_MONITOR, CPU_INTEL_XEON },
-
- { 0x000000C1, 0x000000C2, CPU_PMC, CPU_P6_CX_AT },
- { 0x000000CD, 0x000000CD, CPU_FREQ, CPU_CX_AT },
- { 0x000000E7, 0x000000E8, CPU_PERF, CPU_CX_AT },
- { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_P6_CX_XE },
-
- { 0x00000116, 0x00000116, CPU_CACHE, CPU_INTEL_P6 },
- { 0x00000118, 0x00000118, CPU_CACHE, CPU_INTEL_P6 },
- { 0x00000119, 0x00000119, CPU_CACHE, CPU_INTEL_PX },
- { 0x0000011A, 0x0000011B, CPU_CACHE, CPU_INTEL_P6 },
- { 0x0000011E, 0x0000011E, CPU_CACHE, CPU_PX_CX_AT },
-
- { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_P6_CX_AT_XE },
- { 0x00000179, 0x0000017A, CPU_MC, CPU_PX_CX_AT_XE },
- { 0x0000017B, 0x0000017B, CPU_MC, CPU_P6_XE },
- { 0x00000186, 0x00000187, CPU_PMC, CPU_P6_CX_AT },
- { 0x00000198, 0x00000199, CPU_PERF, CPU_PM_CX_AT_XE },
- { 0x0000019A, 0x0000019A, CPU_TIME, CPU_PM_CX_AT_XE },
- { 0x0000019B, 0x0000019D, CPU_THERM, CPU_PM_CX_AT_XE },
- { 0x000001A0, 0x000001A0, CPU_MISC, CPU_PM_CX_AT_XE },
-
- { 0x000001C9, 0x000001C9, CPU_LBRANCH, CPU_PM_CX_AT },
- { 0x000001D7, 0x000001D8, CPU_LBRANCH, CPU_INTEL_XEON },
- { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_CX_AT_XE },
- { 0x000001DA, 0x000001DA, CPU_LBRANCH, CPU_INTEL_XEON },
- { 0x000001DB, 0x000001DB, CPU_LBRANCH, CPU_P6_XE },
- { 0x000001DC, 0x000001DC, CPU_LBRANCH, CPU_INTEL_P6 },
- { 0x000001DD, 0x000001DE, CPU_LBRANCH, CPU_PX_CX_AT_XE },
- { 0x000001E0, 0x000001E0, CPU_LBRANCH, CPU_INTEL_P6 },
-
- { 0x00000200, 0x0000020F, CPU_MTRR, CPU_P6_CX_XE },
- { 0x00000250, 0x00000250, CPU_MTRR, CPU_P6_CX_XE },
- { 0x00000258, 0x00000259, CPU_MTRR, CPU_P6_CX_XE },
- { 0x00000268, 0x0000026F, CPU_MTRR, CPU_P6_CX_XE },
- { 0x00000277, 0x00000277, CPU_PAT, CPU_C2_AT_XE },
- { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_P6_CX_XE },
-
- { 0x00000300, 0x00000308, CPU_PMC, CPU_INTEL_XEON },
- { 0x00000309, 0x0000030B, CPU_PMC, CPU_C2_AT_XE },
- { 0x0000030C, 0x00000311, CPU_PMC, CPU_INTEL_XEON },
- { 0x00000345, 0x00000345, CPU_PMC, CPU_C2_AT },
- { 0x00000360, 0x00000371, CPU_PMC, CPU_INTEL_XEON },
- { 0x0000038D, 0x00000390, CPU_PMC, CPU_C2_AT },
- { 0x000003A0, 0x000003BE, CPU_PMC, CPU_INTEL_XEON },
- { 0x000003C0, 0x000003CD, CPU_PMC, CPU_INTEL_XEON },
- { 0x000003E0, 0x000003E1, CPU_PMC, CPU_INTEL_XEON },
- { 0x000003F0, 0x000003F0, CPU_PMC, CPU_INTEL_XEON },
- { 0x000003F1, 0x000003F1, CPU_PMC, CPU_C2_AT_XE },
- { 0x000003F2, 0x000003F2, CPU_PMC, CPU_INTEL_XEON },
-
- { 0x00000400, 0x00000402, CPU_MC, CPU_PM_CX_AT_XE },
- { 0x00000403, 0x00000403, CPU_MC, CPU_INTEL_XEON },
- { 0x00000404, 0x00000406, CPU_MC, CPU_PM_CX_AT_XE },
- { 0x00000407, 0x00000407, CPU_MC, CPU_INTEL_XEON },
- { 0x00000408, 0x0000040A, CPU_MC, CPU_PM_CX_AT_XE },
- { 0x0000040B, 0x0000040B, CPU_MC, CPU_INTEL_XEON },
- { 0x0000040C, 0x0000040E, CPU_MC, CPU_PM_CX_XE },
- { 0x0000040F, 0x0000040F, CPU_MC, CPU_INTEL_XEON },
- { 0x00000410, 0x00000412, CPU_MC, CPU_PM_CX_AT_XE },
- { 0x00000413, 0x00000417, CPU_MC, CPU_CX_AT_XE },
- { 0x00000480, 0x0000048B, CPU_VMX, CPU_CX_AT_XE },
-
- { 0x00000600, 0x00000600, CPU_DEBUG, CPU_PM_CX_AT_XE },
- { 0x00000680, 0x0000068F, CPU_LBRANCH, CPU_INTEL_XEON },
- { 0x000006C0, 0x000006CF, CPU_LBRANCH, CPU_INTEL_XEON },
-
- { 0x000107CC, 0x000107D3, CPU_PMC, CPU_INTEL_XEON_MP },
-
- { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_INTEL_XEON },
- { 0xC0000081, 0xC0000082, CPU_CALL, CPU_INTEL_XEON },
- { 0xC0000084, 0xC0000084, CPU_CALL, CPU_INTEL_XEON },
- { 0xC0000100, 0xC0000102, CPU_BASE, CPU_INTEL_XEON },
+/* CPU Registers Range */
+static struct cpu_debug_range cpu_reg_range[] = {
+ { 0x00000000, 0x00000001, CPU_MC, },
+ { 0x00000006, 0x00000007, CPU_MONITOR, },
+ { 0x00000010, 0x00000010, CPU_TIME, },
+ { 0x00000011, 0x00000013, CPU_PMC, },
+ { 0x00000017, 0x00000017, CPU_PLATFORM, },
+ { 0x0000001B, 0x0000001B, CPU_APIC, },
+ { 0x0000002A, 0x0000002B, CPU_POWERON, },
+ { 0x0000002C, 0x0000002C, CPU_FREQ, },
+ { 0x0000003A, 0x0000003A, CPU_CONTROL, },
+ { 0x00000040, 0x00000047, CPU_LBRANCH, },
+ { 0x00000060, 0x00000067, CPU_LBRANCH, },
+ { 0x00000079, 0x00000079, CPU_BIOS, },
+ { 0x00000088, 0x0000008A, CPU_CACHE, },
+ { 0x0000008B, 0x0000008B, CPU_BIOS, },
+ { 0x0000009B, 0x0000009B, CPU_MONITOR, },
+ { 0x000000C1, 0x000000C4, CPU_PMC, },
+ { 0x000000CD, 0x000000CD, CPU_FREQ, },
+ { 0x000000E7, 0x000000E8, CPU_PERF, },
+ { 0x000000FE, 0x000000FE, CPU_MTRR, },
+
+ { 0x00000116, 0x0000011E, CPU_CACHE, },
+ { 0x00000174, 0x00000176, CPU_SYSENTER, },
+ { 0x00000179, 0x0000017B, CPU_MC, },
+ { 0x00000186, 0x00000189, CPU_PMC, },
+ { 0x00000198, 0x00000199, CPU_PERF, },
+ { 0x0000019A, 0x0000019A, CPU_TIME, },
+ { 0x0000019B, 0x0000019D, CPU_THERM, },
+ { 0x000001A0, 0x000001A0, CPU_MISC, },
+ { 0x000001C9, 0x000001C9, CPU_LBRANCH, },
+ { 0x000001D7, 0x000001D8, CPU_LBRANCH, },
+ { 0x000001D9, 0x000001D9, CPU_DEBUG, },
+ { 0x000001DA, 0x000001E0, CPU_LBRANCH, },
+
+ { 0x00000200, 0x0000020F, CPU_MTRR, },
+ { 0x00000250, 0x00000250, CPU_MTRR, },
+ { 0x00000258, 0x00000259, CPU_MTRR, },
+ { 0x00000268, 0x0000026F, CPU_MTRR, },
+ { 0x00000277, 0x00000277, CPU_PAT, },
+ { 0x000002FF, 0x000002FF, CPU_MTRR, },
+
+ { 0x00000300, 0x00000311, CPU_PMC, },
+ { 0x00000345, 0x00000345, CPU_PMC, },
+ { 0x00000360, 0x00000371, CPU_PMC, },
+ { 0x0000038D, 0x00000390, CPU_PMC, },
+ { 0x000003A0, 0x000003BE, CPU_PMC, },
+ { 0x000003C0, 0x000003CD, CPU_PMC, },
+ { 0x000003E0, 0x000003E1, CPU_PMC, },
+ { 0x000003F0, 0x000003F2, CPU_PMC, },
+
+ { 0x00000400, 0x00000417, CPU_MC, },
+ { 0x00000480, 0x0000048B, CPU_VMX, },
+
+ { 0x00000600, 0x00000600, CPU_DEBUG, },
+ { 0x00000680, 0x0000068F, CPU_LBRANCH, },
+ { 0x000006C0, 0x000006CF, CPU_LBRANCH, },
+
+ { 0x000107CC, 0x000107D3, CPU_PMC, },
+
+ { 0xC0000080, 0xC0000080, CPU_FEATURES, },
+ { 0xC0000081, 0xC0000084, CPU_CALL, },
+ { 0xC0000100, 0xC0000102, CPU_BASE, },
+ { 0xC0000103, 0xC0000103, CPU_TIME, },
+
+ { 0xC0010000, 0xC0010007, CPU_PMC, },
+ { 0xC0010010, 0xC0010010, CPU_CONF, },
+ { 0xC0010015, 0xC0010015, CPU_CONF, },
+ { 0xC0010016, 0xC001001A, CPU_MTRR, },
+ { 0xC001001D, 0xC001001D, CPU_MTRR, },
+ { 0xC001001F, 0xC001001F, CPU_CONF, },
+ { 0xC0010030, 0xC0010035, CPU_BIOS, },
+ { 0xC0010044, 0xC0010048, CPU_MC, },
+ { 0xC0010050, 0xC0010056, CPU_SMM, },
+ { 0xC0010058, 0xC0010058, CPU_CONF, },
+ { 0xC0010060, 0xC0010060, CPU_CACHE, },
+ { 0xC0010061, 0xC0010068, CPU_SMM, },
+ { 0xC0010069, 0xC001006B, CPU_SMM, },
+ { 0xC0010070, 0xC0010071, CPU_SMM, },
+ { 0xC0010111, 0xC0010113, CPU_SMM, },
+ { 0xC0010114, 0xC0010118, CPU_SVM, },
+ { 0xC0010140, 0xC0010141, CPU_OSVM, },
+ { 0xC0011022, 0xC0011023, CPU_CONF, },
};
-/* AMD Registers Range */
-static struct cpu_debug_range cpu_amd_range[] = {
- { 0x00000000, 0x00000001, CPU_MC, CPU_K10_PLUS, },
- { 0x00000010, 0x00000010, CPU_TIME, CPU_K8_PLUS, },
- { 0x0000001B, 0x0000001B, CPU_APIC, CPU_K8_PLUS, },
- { 0x0000002A, 0x0000002A, CPU_POWERON, CPU_K7_PLUS },
- { 0x0000008B, 0x0000008B, CPU_VER, CPU_K8_PLUS },
- { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_K8_PLUS, },
-
- { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_K8_PLUS, },
- { 0x00000179, 0x0000017B, CPU_MC, CPU_K8_PLUS, },
- { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_K8_PLUS, },
- { 0x000001DB, 0x000001DE, CPU_LBRANCH, CPU_K8_PLUS, },
-
- { 0x00000200, 0x0000020F, CPU_MTRR, CPU_K8_PLUS, },
- { 0x00000250, 0x00000250, CPU_MTRR, CPU_K8_PLUS, },
- { 0x00000258, 0x00000259, CPU_MTRR, CPU_K8_PLUS, },
- { 0x00000268, 0x0000026F, CPU_MTRR, CPU_K8_PLUS, },
- { 0x00000277, 0x00000277, CPU_PAT, CPU_K8_PLUS, },
- { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_K8_PLUS, },
-
- { 0x00000400, 0x00000413, CPU_MC, CPU_K8_PLUS, },
-
- { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_AMD_ALL, },
- { 0xC0000081, 0xC0000084, CPU_CALL, CPU_K8_PLUS, },
- { 0xC0000100, 0xC0000102, CPU_BASE, CPU_K8_PLUS, },
- { 0xC0000103, 0xC0000103, CPU_TIME, CPU_K10_PLUS, },
-
- { 0xC0010000, 0xC0010007, CPU_PMC, CPU_K8_PLUS, },
- { 0xC0010010, 0xC0010010, CPU_CONF, CPU_K7_PLUS, },
- { 0xC0010015, 0xC0010015, CPU_CONF, CPU_K7_PLUS, },
- { 0xC0010016, 0xC001001A, CPU_MTRR, CPU_K8_PLUS, },
- { 0xC001001D, 0xC001001D, CPU_MTRR, CPU_K8_PLUS, },
- { 0xC001001F, 0xC001001F, CPU_CONF, CPU_K8_PLUS, },
- { 0xC0010030, 0xC0010035, CPU_BIOS, CPU_K8_PLUS, },
- { 0xC0010044, 0xC0010048, CPU_MC, CPU_K8_PLUS, },
- { 0xC0010050, 0xC0010056, CPU_SMM, CPU_K0F_PLUS, },
- { 0xC0010058, 0xC0010058, CPU_CONF, CPU_K10_PLUS, },
- { 0xC0010060, 0xC0010060, CPU_CACHE, CPU_AMD_11, },
- { 0xC0010061, 0xC0010068, CPU_SMM, CPU_K10_PLUS, },
- { 0xC0010069, 0xC001006B, CPU_SMM, CPU_AMD_11, },
- { 0xC0010070, 0xC0010071, CPU_SMM, CPU_K10_PLUS, },
- { 0xC0010111, 0xC0010113, CPU_SMM, CPU_K8_PLUS, },
- { 0xC0010114, 0xC0010118, CPU_SVM, CPU_K10_PLUS, },
- { 0xC0010140, 0xC0010141, CPU_OSVM, CPU_K10_PLUS, },
- { 0xC0011022, 0xC0011023, CPU_CONF, CPU_K10_PLUS, },
-};
-
-
-/* Intel */
-static int get_intel_modelflag(unsigned model)
-{
- int flag;
-
- switch (model) {
- case 0x0501:
- case 0x0502:
- case 0x0504:
- flag = CPU_INTEL_PENTIUM;
- break;
- case 0x0601:
- case 0x0603:
- case 0x0605:
- case 0x0607:
- case 0x0608:
- case 0x060A:
- case 0x060B:
- flag = CPU_INTEL_P6;
- break;
- case 0x0609:
- case 0x060D:
- flag = CPU_INTEL_PENTIUM_M;
- break;
- case 0x060E:
- flag = CPU_INTEL_CORE;
- break;
- case 0x060F:
- case 0x0617:
- flag = CPU_INTEL_CORE2;
- break;
- case 0x061C:
- flag = CPU_INTEL_ATOM;
- break;
- case 0x0F00:
- case 0x0F01:
- case 0x0F02:
- case 0x0F03:
- case 0x0F04:
- flag = CPU_INTEL_XEON_P4;
- break;
- case 0x0F06:
- flag = CPU_INTEL_XEON_MP;
- break;
- default:
- flag = CPU_NONE;
- break;
- }
-
- return flag;
-}
-
-/* AMD */
-static int get_amd_modelflag(unsigned model)
-{
- int flag;
-
- switch (model >> 8) {
- case 0x6:
- flag = CPU_AMD_K6;
- break;
- case 0x7:
- flag = CPU_AMD_K7;
- break;
- case 0x8:
- flag = CPU_AMD_K8;
- break;
- case 0xf:
- flag = CPU_AMD_0F;
- break;
- case 0x10:
- flag = CPU_AMD_10;
- break;
- case 0x11:
- flag = CPU_AMD_11;
- break;
- default:
- flag = CPU_NONE;
- break;
- }
-
- return flag;
-}
-
-static int get_cpu_modelflag(unsigned cpu)
-{
- int flag;
-
- flag = per_cpu(cpu_model, cpu);
-
- switch (flag >> 16) {
- case X86_VENDOR_INTEL:
- flag = get_intel_modelflag(flag);
- break;
- case X86_VENDOR_AMD:
- flag = get_amd_modelflag(flag & 0xffff);
- break;
- default:
- flag = CPU_NONE;
- break;
- }
-
- return flag;
-}
-
-static int get_cpu_range_count(unsigned cpu)
-{
- int index;
-
- switch (per_cpu(cpu_model, cpu) >> 16) {
- case X86_VENDOR_INTEL:
- index = ARRAY_SIZE(cpu_intel_range);
- break;
- case X86_VENDOR_AMD:
- index = ARRAY_SIZE(cpu_amd_range);
- break;
- default:
- index = 0;
- break;
- }
-
- return index;
-}
-
static int is_typeflag_valid(unsigned cpu, unsigned flag)
{
- unsigned vendor, modelflag;
- int i, index;
+ int i;
/* Standard Registers should be always valid */
if (flag >= CPU_TSS)
return 1;
- modelflag = per_cpu(cpu_modelflag, cpu);
- vendor = per_cpu(cpu_model, cpu) >> 16;
- index = get_cpu_range_count(cpu);
-
- for (i = 0; i < index; i++) {
- switch (vendor) {
- case X86_VENDOR_INTEL:
- if ((cpu_intel_range[i].model & modelflag) &&
- (cpu_intel_range[i].flag & flag))
- return 1;
- break;
- case X86_VENDOR_AMD:
- if ((cpu_amd_range[i].model & modelflag) &&
- (cpu_amd_range[i].flag & flag))
- return 1;
- break;
- }
+ for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
+ if (cpu_reg_range[i].flag == flag)
+ return 1;
}
/* Invalid */
@@ -385,26 +183,11 @@ static int is_typeflag_valid(unsigned cpu, unsigned flag)
static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max,
int index, unsigned flag)
{
- unsigned modelflag;
-
- modelflag = per_cpu(cpu_modelflag, cpu);
- *max = 0;
- switch (per_cpu(cpu_model, cpu) >> 16) {
- case X86_VENDOR_INTEL:
- if ((cpu_intel_range[index].model & modelflag) &&
- (cpu_intel_range[index].flag & flag)) {
- *min = cpu_intel_range[index].min;
- *max = cpu_intel_range[index].max;
- }
- break;
- case X86_VENDOR_AMD:
- if ((cpu_amd_range[index].model & modelflag) &&
- (cpu_amd_range[index].flag & flag)) {
- *min = cpu_amd_range[index].min;
- *max = cpu_amd_range[index].max;
- }
- break;
- }
+ if (cpu_reg_range[index].flag == flag) {
+ *min = cpu_reg_range[index].min;
+ *max = cpu_reg_range[index].max;
+ } else
+ *max = 0;
return *max;
}
@@ -434,7 +217,7 @@ static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag)
unsigned msr, msr_min, msr_max;
struct cpu_private *priv;
u32 low, high;
- int i, range;
+ int i;
if (seq) {
priv = seq->private;
@@ -446,9 +229,7 @@ static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag)
}
}
- range = get_cpu_range_count(cpu);
-
- for (i = 0; i < range; i++) {
+ for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag))
continue;
@@ -588,8 +369,20 @@ static void print_apic(void *arg)
seq_printf(seq, " TMICT\t\t: %08x\n", apic_read(APIC_TMICT));
seq_printf(seq, " TMCCT\t\t: %08x\n", apic_read(APIC_TMCCT));
seq_printf(seq, " TDCR\t\t: %08x\n", apic_read(APIC_TDCR));
-#endif /* CONFIG_X86_LOCAL_APIC */
+ if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+ unsigned int i, v, maxeilvt;
+
+ v = apic_read(APIC_EFEAT);
+ maxeilvt = (v >> 16) & 0xff;
+ seq_printf(seq, " EFEAT\t\t: %08x\n", v);
+ seq_printf(seq, " ECTRL\t\t: %08x\n", apic_read(APIC_ECTRL));
+ for (i = 0; i < maxeilvt; i++) {
+ v = apic_read(APIC_EILVTn(i));
+ seq_printf(seq, " EILVT%d\t\t: %08x\n", i, v);
+ }
+ }
+#endif /* CONFIG_X86_LOCAL_APIC */
seq_printf(seq, "\n MSR\t:\n");
}
@@ -788,13 +581,11 @@ static int cpu_init_msr(unsigned cpu, unsigned type, struct dentry *dentry)
{
struct dentry *cpu_dentry = NULL;
unsigned reg, reg_min, reg_max;
- int i, range, err = 0;
+ int i, err = 0;
char reg_dir[12];
u32 low, high;
- range = get_cpu_range_count(cpu);
-
- for (i = 0; i < range; i++) {
+ for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
if (!get_cpu_range(cpu, &reg_min, &reg_max, i,
cpu_base[type].flag))
continue;
@@ -850,10 +641,6 @@ static int cpu_init_cpu(void)
cpui = &cpu_data(cpu);
if (!cpu_has(cpui, X86_FEATURE_MSR))
continue;
- per_cpu(cpu_model, cpu) = ((cpui->x86_vendor << 16) |
- (cpui->x86 << 8) |
- (cpui->x86_model));
- per_cpu(cpu_modelflag, cpu) = get_cpu_modelflag(cpu);
sprintf(cpu_dir, "cpu%d", cpu);
cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir);
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index 52c83987547..f138c6c389b 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -220,11 +220,14 @@ config X86_LONGHAUL
If in doubt, say N.
config X86_E_POWERSAVER
- tristate "VIA C7 Enhanced PowerSaver"
+ tristate "VIA C7 Enhanced PowerSaver (DANGEROUS)"
select CPU_FREQ_TABLE
- depends on X86_32
+ depends on X86_32 && EXPERIMENTAL
help
- This adds the CPUFreq driver for VIA C7 processors.
+ This adds the CPUFreq driver for VIA C7 processors. However, this driver
+ does not have any safeguards to prevent operating the CPU out of spec
+ and is thus considered dangerous. Please use the regular ACPI cpufreq
+ driver, enabled by CONFIG_X86_ACPI_CPUFREQ.
If in doubt, say N.
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 19f6b9d27e8..ae9b503220c 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -65,13 +65,18 @@ enum {
struct acpi_cpufreq_data {
struct acpi_processor_performance *acpi_data;
struct cpufreq_frequency_table *freq_table;
- unsigned int max_freq;
unsigned int resume;
unsigned int cpu_feature;
};
static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
+struct acpi_msr_data {
+ u64 saved_aperf, saved_mperf;
+};
+
+static DEFINE_PER_CPU(struct acpi_msr_data, msr_data);
+
DEFINE_TRACE(power_mark);
/* acpi_perf_data is a pointer to percpu data. */
@@ -85,11 +90,7 @@ static int check_est_cpu(unsigned int cpuid)
{
struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
- if (cpu->x86_vendor != X86_VENDOR_INTEL ||
- !cpu_has(cpu, X86_FEATURE_EST))
- return 0;
-
- return 1;
+ return cpu_has(cpu, X86_FEATURE_EST);
}
static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
@@ -152,7 +153,8 @@ struct drv_cmd {
u32 val;
};
-static long do_drv_read(void *_cmd)
+/* Called via smp_call_function_single(), on the target CPU */
+static void do_drv_read(void *_cmd)
{
struct drv_cmd *cmd = _cmd;
u32 h;
@@ -169,10 +171,10 @@ static long do_drv_read(void *_cmd)
default:
break;
}
- return 0;
}
-static long do_drv_write(void *_cmd)
+/* Called via smp_call_function_many(), on the target CPUs */
+static void do_drv_write(void *_cmd)
{
struct drv_cmd *cmd = _cmd;
u32 lo, hi;
@@ -191,23 +193,24 @@ static long do_drv_write(void *_cmd)
default:
break;
}
- return 0;
}
static void drv_read(struct drv_cmd *cmd)
{
cmd->val = 0;
- work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
+ smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1);
}
static void drv_write(struct drv_cmd *cmd)
{
- unsigned int i;
+ int this_cpu;
- for_each_cpu(i, cmd->mask) {
- work_on_cpu(i, do_drv_write, cmd);
- }
+ this_cpu = get_cpu();
+ if (cpumask_test_cpu(this_cpu, cmd->mask))
+ do_drv_write(cmd);
+ smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
+ put_cpu();
}
static u32 get_cur_val(const struct cpumask *mask)
@@ -241,28 +244,23 @@ static u32 get_cur_val(const struct cpumask *mask)
return cmd.val;
}
-struct perf_cur {
+struct perf_pair {
union {
struct {
u32 lo;
u32 hi;
} split;
u64 whole;
- } aperf_cur, mperf_cur;
+ } aperf, mperf;
};
-
-static long read_measured_perf_ctrs(void *_cur)
+/* Called via smp_call_function_single(), on the target CPU */
+static void read_measured_perf_ctrs(void *_cur)
{
- struct perf_cur *cur = _cur;
-
- rdmsr(MSR_IA32_APERF, cur->aperf_cur.split.lo, cur->aperf_cur.split.hi);
- rdmsr(MSR_IA32_MPERF, cur->mperf_cur.split.lo, cur->mperf_cur.split.hi);
-
- wrmsr(MSR_IA32_APERF, 0, 0);
- wrmsr(MSR_IA32_MPERF, 0, 0);
+ struct perf_pair *cur = _cur;
- return 0;
+ rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi);
+ rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi);
}
/*
@@ -281,58 +279,63 @@ static long read_measured_perf_ctrs(void *_cur)
static unsigned int get_measured_perf(struct cpufreq_policy *policy,
unsigned int cpu)
{
- struct perf_cur cur;
+ struct perf_pair readin, cur;
unsigned int perf_percent;
unsigned int retval;
- if (!work_on_cpu(cpu, read_measured_perf_ctrs, &cur))
+ if (smp_call_function_single(cpu, read_measured_perf_ctrs, &readin, 1))
return 0;
+ cur.aperf.whole = readin.aperf.whole -
+ per_cpu(msr_data, cpu).saved_aperf;
+ cur.mperf.whole = readin.mperf.whole -
+ per_cpu(msr_data, cpu).saved_mperf;
+ per_cpu(msr_data, cpu).saved_aperf = readin.aperf.whole;
+ per_cpu(msr_data, cpu).saved_mperf = readin.mperf.whole;
+
#ifdef __i386__
/*
* We dont want to do 64 bit divide with 32 bit kernel
* Get an approximate value. Return failure in case we cannot get
* an approximate value.
*/
- if (unlikely(cur.aperf_cur.split.hi || cur.mperf_cur.split.hi)) {
+ if (unlikely(cur.aperf.split.hi || cur.mperf.split.hi)) {
int shift_count;
u32 h;
- h = max_t(u32, cur.aperf_cur.split.hi, cur.mperf_cur.split.hi);
+ h = max_t(u32, cur.aperf.split.hi, cur.mperf.split.hi);
shift_count = fls(h);
- cur.aperf_cur.whole >>= shift_count;
- cur.mperf_cur.whole >>= shift_count;
+ cur.aperf.whole >>= shift_count;
+ cur.mperf.whole >>= shift_count;
}
- if (((unsigned long)(-1) / 100) < cur.aperf_cur.split.lo) {
+ if (((unsigned long)(-1) / 100) < cur.aperf.split.lo) {
int shift_count = 7;
- cur.aperf_cur.split.lo >>= shift_count;
- cur.mperf_cur.split.lo >>= shift_count;
+ cur.aperf.split.lo >>= shift_count;
+ cur.mperf.split.lo >>= shift_count;
}
- if (cur.aperf_cur.split.lo && cur.mperf_cur.split.lo)
- perf_percent = (cur.aperf_cur.split.lo * 100) /
- cur.mperf_cur.split.lo;
+ if (cur.aperf.split.lo && cur.mperf.split.lo)
+ perf_percent = (cur.aperf.split.lo * 100) / cur.mperf.split.lo;
else
perf_percent = 0;
#else
- if (unlikely(((unsigned long)(-1) / 100) < cur.aperf_cur.whole)) {
+ if (unlikely(((unsigned long)(-1) / 100) < cur.aperf.whole)) {
int shift_count = 7;
- cur.aperf_cur.whole >>= shift_count;
- cur.mperf_cur.whole >>= shift_count;
+ cur.aperf.whole >>= shift_count;
+ cur.mperf.whole >>= shift_count;
}
- if (cur.aperf_cur.whole && cur.mperf_cur.whole)
- perf_percent = (cur.aperf_cur.whole * 100) /
- cur.mperf_cur.whole;
+ if (cur.aperf.whole && cur.mperf.whole)
+ perf_percent = (cur.aperf.whole * 100) / cur.mperf.whole;
else
perf_percent = 0;
#endif
- retval = per_cpu(drv_data, policy->cpu)->max_freq * perf_percent / 100;
+ retval = (policy->cpuinfo.max_freq * perf_percent) / 100;
return retval;
}
@@ -543,7 +546,7 @@ static int __init acpi_cpufreq_early_init(void)
return -ENOMEM;
}
for_each_possible_cpu(i) {
- if (!alloc_cpumask_var_node(
+ if (!zalloc_cpumask_var_node(
&per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map,
GFP_KERNEL, cpu_to_node(i))) {
@@ -685,16 +688,11 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
/* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
policy->cpuinfo.transition_latency > 20 * 1000) {
- static int print_once;
policy->cpuinfo.transition_latency = 20 * 1000;
- if (!print_once) {
- print_once = 1;
- printk(KERN_INFO "Capping off P-state tranision latency"
- " at 20 uS\n");
- }
+ printk_once(KERN_INFO
+ "P-state transition latency capped at 20 uS\n");
}
- data->max_freq = perf->states[0].core_frequency * 1000;
/* table init */
for (i = 0; i < perf->state_count; i++) {
if (i > 0 && perf->states[i].core_frequency >=
@@ -713,6 +711,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
if (result)
goto err_freqfree;
+ if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
+ printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n");
+
switch (perf->control_register.space_id) {
case ACPI_ADR_SPACE_SYSTEM_IO:
/* Current speed is unknown and not detectable by IO port */
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c
index 0bd48e65a0c..ce2ed3e4aad 100644
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c
@@ -33,7 +33,6 @@
#include <linux/timex.h>
#include <linux/io.h>
#include <linux/acpi.h>
-#include <linux/kernel.h>
#include <asm/msr.h>
#include <acpi/processor.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 6ac55bd341a..86961519372 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -168,6 +168,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c)
case 0x0E: /* Core */
case 0x0F: /* Core Duo */
case 0x16: /* Celeron Core */
+ case 0x1C: /* Atom */
p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS;
return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE);
case 0x0D: /* Pentium M (Dothan) */
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
index 3c28ccd4974..d47c775eb0a 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
@@ -168,10 +168,12 @@ static int check_powernow(void)
return 1;
}
+#ifdef CONFIG_X86_POWERNOW_K7_ACPI
static void invalidate_entry(unsigned int entry)
{
powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID;
}
+#endif
static int get_ranges(unsigned char *pst)
{
@@ -320,7 +322,7 @@ static int powernow_acpi_init(void)
goto err0;
}
- if (!alloc_cpumask_var(&acpi_processor_perf->shared_cpu_map,
+ if (!zalloc_cpumask_var(&acpi_processor_perf->shared_cpu_map,
GFP_KERNEL)) {
retval = -ENOMEM;
goto err05;
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 4709ead2db5..cf52215d9eb 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -649,6 +649,20 @@ static void print_basics(struct powernow_k8_data *data)
data->batps);
}
+static u32 freq_from_fid_did(u32 fid, u32 did)
+{
+ u32 mhz = 0;
+
+ if (boot_cpu_data.x86 == 0x10)
+ mhz = (100 * (fid + 0x10)) >> did;
+ else if (boot_cpu_data.x86 == 0x11)
+ mhz = (100 * (fid + 8)) >> did;
+ else
+ BUG();
+
+ return mhz * 1000;
+}
+
static int fill_powernow_table(struct powernow_k8_data *data,
struct pst_s *pst, u8 maxvid)
{
@@ -821,7 +835,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
{
struct cpufreq_frequency_table *powernow_table;
int ret_val = -ENODEV;
- acpi_integer space_id;
+ acpi_integer control, status;
if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) {
dprintk("register performance failed: bad ACPI data\n");
@@ -834,12 +848,13 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
goto err_out;
}
- space_id = data->acpi_data.control_register.space_id;
- if ((space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
- (space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
+ control = data->acpi_data.control_register.space_id;
+ status = data->acpi_data.status_register.space_id;
+
+ if ((control != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
+ (status != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
dprintk("Invalid control/status registers (%x - %x)\n",
- data->acpi_data.control_register.space_id,
- space_id);
+ control, status);
goto err_out;
}
@@ -872,7 +887,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
/* notify BIOS that we exist */
acpi_processor_notify_smm(THIS_MODULE);
- if (!alloc_cpumask_var(&data->acpi_data.shared_cpu_map, GFP_KERNEL)) {
+ if (!zalloc_cpumask_var(&data->acpi_data.shared_cpu_map, GFP_KERNEL)) {
printk(KERN_ERR PFX
"unable to alloc powernow_k8_data cpumask\n");
ret_val = -ENOMEM;
@@ -923,8 +938,13 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
powernow_table[i].index = index;
- powernow_table[i].frequency =
- data->acpi_data.states[i].core_frequency * 1000;
+ /* Frequency may be rounded for these */
+ if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) {
+ powernow_table[i].frequency =
+ freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
+ } else
+ powernow_table[i].frequency =
+ data->acpi_data.states[i].core_frequency * 1000;
}
return 0;
}
@@ -1215,13 +1235,16 @@ static int powernowk8_verify(struct cpufreq_policy *pol)
return cpufreq_frequency_table_verify(pol, data->powernow_table);
}
+static const char ACPI_PSS_BIOS_BUG_MSG[] =
+ KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n"
+ KERN_ERR FW_BUG PFX "Try again with latest BIOS.\n";
+
/* per CPU init entry point to the driver */
static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
{
struct powernow_k8_data *data;
cpumask_t oldmask;
int rc;
- static int print_once;
if (!cpu_online(pol->cpu))
return -ENODEV;
@@ -1244,19 +1267,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
* an UP version, and is deprecated by AMD.
*/
if (num_online_cpus() != 1) {
- /*
- * Replace this one with print_once as soon as such a
- * thing gets introduced
- */
- if (!print_once) {
- WARN_ONCE(1, KERN_ERR FW_BUG PFX "Your BIOS "
- "does not provide ACPI _PSS objects "
- "in a way that Linux understands. "
- "Please report this to the Linux ACPI"
- " maintainers and complain to your "
- "BIOS vendor.\n");
- print_once++;
- }
+ printk_once(ACPI_PSS_BIOS_BUG_MSG);
goto err_out;
}
if (pol->cpu != 0) {
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index c9f1fdc0283..55c831ed71c 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -471,7 +471,7 @@ static int centrino_target (struct cpufreq_policy *policy,
if (unlikely(!alloc_cpumask_var(&saved_mask, GFP_KERNEL)))
return -ENOMEM;
- if (unlikely(!alloc_cpumask_var(&covered_cpus, GFP_KERNEL))) {
+ if (unlikely(!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))) {
free_cpumask_var(saved_mask);
return -ENOMEM;
}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 7437fa133c0..daed39ba261 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -229,12 +229,12 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
}
#endif
-static void __cpuinit srat_detect_node(void)
+static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
{
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
unsigned node;
int cpu = smp_processor_id();
- int apicid = hard_smp_processor_id();
+ int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
@@ -400,7 +400,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
}
/* Work around errata */
- srat_detect_node();
+ srat_detect_node(c);
if (cpu_has(c, X86_FEATURE_VMX))
detect_vmx_virtcap(c);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 483eda96e10..789efe217e1 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -17,6 +17,7 @@
#include <asm/processor.h>
#include <asm/smp.h>
+#include <asm/k8.h>
#define LVL_1_INST 1
#define LVL_1_DATA 2
@@ -159,14 +160,6 @@ struct _cpuid4_info_regs {
unsigned long can_disable;
};
-#if defined(CONFIG_PCI) && defined(CONFIG_SYSFS)
-static struct pci_device_id k8_nb_id[] = {
- { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
- { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
- {}
-};
-#endif
-
unsigned short num_cache_leaves;
/* AMD doesn't have CPUID4. Emulate it here to report the same
@@ -207,10 +200,17 @@ union l3_cache {
};
static const unsigned short __cpuinitconst assocs[] = {
- [1] = 1, [2] = 2, [4] = 4, [6] = 8,
- [8] = 16, [0xa] = 32, [0xb] = 48,
+ [1] = 1,
+ [2] = 2,
+ [4] = 4,
+ [6] = 8,
+ [8] = 16,
+ [0xa] = 32,
+ [0xb] = 48,
[0xc] = 64,
- [0xf] = 0xffff // ??
+ [0xd] = 96,
+ [0xe] = 128,
+ [0xf] = 0xffff /* fully associative - no way to show this currently */
};
static const unsigned char __cpuinitconst levels[] = { 1, 1, 2, 3 };
@@ -271,7 +271,8 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
eax->split.type = types[leaf];
eax->split.level = levels[leaf];
if (leaf == 3)
- eax->split.num_threads_sharing = current_cpu_data.x86_max_cores - 1;
+ eax->split.num_threads_sharing =
+ current_cpu_data.x86_max_cores - 1;
else
eax->split.num_threads_sharing = 0;
eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
@@ -291,6 +292,14 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
{
if (index < 3)
return;
+
+ if (boot_cpu_data.x86 == 0x11)
+ return;
+
+ /* see erratum #382 */
+ if ((boot_cpu_data.x86 == 0x10) && (boot_cpu_data.x86_model < 0x8))
+ return;
+
this_leaf->can_disable = 1;
}
@@ -696,97 +705,75 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
#define to_object(k) container_of(k, struct _index_kobject, kobj)
#define to_attr(a) container_of(a, struct _cache_attr, attr)
-#ifdef CONFIG_PCI
-static struct pci_dev *get_k8_northbridge(int node)
-{
- struct pci_dev *dev = NULL;
- int i;
-
- for (i = 0; i <= node; i++) {
- do {
- dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
- if (!dev)
- break;
- } while (!pci_match_id(&k8_nb_id[0], dev));
- if (!dev)
- break;
- }
- return dev;
-}
-#else
-static struct pci_dev *get_k8_northbridge(int node)
-{
- return NULL;
-}
-#endif
-
-static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
+ unsigned int index)
{
- const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
- int node = cpu_to_node(cpumask_first(mask));
- struct pci_dev *dev = NULL;
- ssize_t ret = 0;
- int i;
+ int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+ int node = cpu_to_node(cpu);
+ struct pci_dev *dev = node_to_k8_nb_misc(node);
+ unsigned int reg = 0;
if (!this_leaf->can_disable)
- return sprintf(buf, "Feature not enabled\n");
-
- dev = get_k8_northbridge(node);
- if (!dev) {
- printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
return -EINVAL;
- }
- for (i = 0; i < 2; i++) {
- unsigned int reg;
+ if (!dev)
+ return -EINVAL;
- pci_read_config_dword(dev, 0x1BC + i * 4, &reg);
+ pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
+ return sprintf(buf, "%x\n", reg);
+}
- ret += sprintf(buf, "%sEntry: %d\n", buf, i);
- ret += sprintf(buf, "%sReads: %s\tNew Entries: %s\n",
- buf,
- reg & 0x80000000 ? "Disabled" : "Allowed",
- reg & 0x40000000 ? "Disabled" : "Allowed");
- ret += sprintf(buf, "%sSubCache: %x\tIndex: %x\n",
- buf, (reg & 0x30000) >> 16, reg & 0xfff);
- }
- return ret;
+#define SHOW_CACHE_DISABLE(index) \
+static ssize_t \
+show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \
+{ \
+ return show_cache_disable(this_leaf, buf, index); \
}
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
-static ssize_t
-store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
- size_t count)
+static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
+ const char *buf, size_t count, unsigned int index)
{
- const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
- int node = cpu_to_node(cpumask_first(mask));
- struct pci_dev *dev = NULL;
- unsigned int ret, index, val;
+ int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+ int node = cpu_to_node(cpu);
+ struct pci_dev *dev = node_to_k8_nb_misc(node);
+ unsigned long val = 0;
+ unsigned int scrubber = 0;
if (!this_leaf->can_disable)
- return 0;
-
- if (strlen(buf) > 15)
return -EINVAL;
- ret = sscanf(buf, "%x %x", &index, &val);
- if (ret != 2)
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!dev)
return -EINVAL;
- if (index > 1)
+
+ if (strict_strtoul(buf, 10, &val) < 0)
return -EINVAL;
val |= 0xc0000000;
- dev = get_k8_northbridge(node);
- if (!dev) {
- printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
- return -EINVAL;
- }
+
+ pci_read_config_dword(dev, 0x58, &scrubber);
+ scrubber &= ~0x1f000000;
+ pci_write_config_dword(dev, 0x58, scrubber);
pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000);
wbinvd();
pci_write_config_dword(dev, 0x1BC + index * 4, val);
+ return count;
+}
- return 1;
+#define STORE_CACHE_DISABLE(index) \
+static ssize_t \
+store_cache_disable_##index(struct _cpuid4_info *this_leaf, \
+ const char *buf, size_t count) \
+{ \
+ return store_cache_disable(this_leaf, buf, count, index); \
}
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
struct _cache_attr {
struct attribute attr;
@@ -808,7 +795,10 @@ define_one_ro(size);
define_one_ro(shared_cpu_map);
define_one_ro(shared_cpu_list);
-static struct _cache_attr cache_disable = __ATTR(cache_disable, 0644, show_cache_disable, store_cache_disable);
+static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
+ show_cache_disable_0, store_cache_disable_0);
+static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
+ show_cache_disable_1, store_cache_disable_1);
static struct attribute * default_attrs[] = {
&type.attr,
@@ -820,7 +810,8 @@ static struct attribute * default_attrs[] = {
&size.attr,
&shared_cpu_map.attr,
&shared_cpu_list.attr,
- &cache_disable.attr,
+ &cache_disable_0.attr,
+ &cache_disable_1.attr,
NULL
};
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 863f89568b1..09dd1d414fc 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -239,9 +239,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
* Don't get the IP here because it's unlikely to
* have anything to do with the actual error location.
*/
-
- mce_log(&m);
- add_taint(TAINT_MACHINE_CHECK);
+ if (!(flags & MCP_DONTLOG)) {
+ mce_log(&m);
+ add_taint(TAINT_MACHINE_CHECK);
+ }
/*
* Clear state for this bank.
@@ -452,13 +453,14 @@ void mce_log_therm_throt_event(__u64 status)
*/
static int check_interval = 5 * 60; /* 5 minutes */
-static int next_interval; /* in jiffies */
+static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
static void mcheck_timer(unsigned long);
static DEFINE_PER_CPU(struct timer_list, mce_timer);
static void mcheck_timer(unsigned long data)
{
struct timer_list *t = &per_cpu(mce_timer, data);
+ int *n;
WARN_ON(smp_processor_id() != data);
@@ -470,14 +472,14 @@ static void mcheck_timer(unsigned long data)
* Alert userspace if needed. If we logged an MCE, reduce the
* polling interval, otherwise increase the polling interval.
*/
+ n = &__get_cpu_var(next_interval);
if (mce_notify_user()) {
- next_interval = max(next_interval/2, HZ/100);
+ *n = max(*n/2, HZ/100);
} else {
- next_interval = min(next_interval * 2,
- (int)round_jiffies_relative(check_interval*HZ));
+ *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
}
- t->expires = jiffies + next_interval;
+ t->expires = jiffies + *n;
add_timer(t);
}
@@ -584,7 +586,7 @@ static void mce_init(void *dummy)
* Log the machine checks left over from the previous reset.
*/
bitmap_fill(all_banks, MAX_NR_BANKS);
- machine_check_poll(MCP_UC, &all_banks);
+ machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks);
set_in_cr4(X86_CR4_MCE);
@@ -632,14 +634,13 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
static void mce_init_timer(void)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
+ int *n = &__get_cpu_var(next_interval);
- /* data race harmless because everyone sets to the same value */
- if (!next_interval)
- next_interval = check_interval * HZ;
- if (!next_interval)
+ *n = check_interval * HZ;
+ if (!*n)
return;
setup_timer(t, mcheck_timer, smp_processor_id());
- t->expires = round_jiffies(jiffies + next_interval);
+ t->expires = round_jiffies(jiffies + *n);
add_timer(t);
}
@@ -907,7 +908,6 @@ static void mce_cpu_restart(void *data)
/* Reinit MCEs after user configuration changes */
static void mce_restart(void)
{
- next_interval = check_interval * HZ;
on_each_cpu(mce_cpu_restart, NULL, 1);
}
@@ -1110,7 +1110,8 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb,
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
- t->expires = round_jiffies(jiffies + next_interval);
+ t->expires = round_jiffies(jiffies +
+ __get_cpu_var(next_interval));
add_timer_on(t, cpu);
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
break;
@@ -1162,7 +1163,7 @@ static __init int mce_init_device(void)
if (!mce_available(&boot_cpu_data))
return -EIO;
- alloc_cpumask_var(&mce_device_initialized, GFP_KERNEL);
+ zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL);
err = mce_init_banks();
if (err)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index d6b72df89d6..65a0fceedcd 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -15,7 +15,6 @@
#include <asm/hw_irq.h>
#include <asm/idle.h>
#include <asm/therm_throt.h>
-#include <asm/apic.h>
asmlinkage void smp_thermal_interrupt(void)
{
@@ -151,10 +150,11 @@ static void print_update(char *type, int *hdr, int num)
static void cmci_discover(int banks, int boot)
{
unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
+ unsigned long flags;
int hdr = 0;
int i;
- spin_lock(&cmci_discover_lock);
+ spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++) {
u64 val;
@@ -184,7 +184,7 @@ static void cmci_discover(int banks, int boot)
WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
}
}
- spin_unlock(&cmci_discover_lock);
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
if (hdr)
printk(KERN_CONT "\n");
}
@@ -211,13 +211,14 @@ void cmci_recheck(void)
*/
void cmci_clear(void)
{
+ unsigned long flags;
int i;
int banks;
u64 val;
if (!cmci_supported(&banks))
return;
- spin_lock(&cmci_discover_lock);
+ spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++) {
if (!test_bit(i, __get_cpu_var(mce_banks_owned)))
continue;
@@ -227,7 +228,7 @@ void cmci_clear(void)
wrmsrl(MSR_IA32_MC0_CTL2 + i, val);
__clear_bit(i, __get_cpu_var(mce_banks_owned));
}
- spin_unlock(&cmci_discover_lock);
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
/*
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index ce0fe4b5c04..1d584a18a50 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -808,7 +808,7 @@ int __init mtrr_cleanup(unsigned address_bits)
if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
return 0;
- rdmsr(MTRRdefType_MSR, def, dummy);
+ rdmsr(MSR_MTRRdefType, def, dummy);
def &= 0xff;
if (def != MTRR_TYPE_UNCACHABLE)
return 0;
@@ -1003,7 +1003,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
*/
if (!is_cpu(INTEL) || disable_mtrr_trim)
return 0;
- rdmsr(MTRRdefType_MSR, def, dummy);
+ rdmsr(MSR_MTRRdefType, def, dummy);
def &= 0xff;
if (def != MTRR_TYPE_UNCACHABLE)
return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 0b776c09aff..0543f69f0b2 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -20,9 +20,9 @@ struct fixed_range_block {
};
static struct fixed_range_block fixed_range_blocks[] = {
- { MTRRfix64K_00000_MSR, 1 }, /* one 64k MTRR */
- { MTRRfix16K_80000_MSR, 2 }, /* two 16k MTRRs */
- { MTRRfix4K_C0000_MSR, 8 }, /* eight 4k MTRRs */
+ { MSR_MTRRfix64K_00000, 1 }, /* one 64k MTRR */
+ { MSR_MTRRfix16K_80000, 2 }, /* two 16k MTRRs */
+ { MSR_MTRRfix4K_C0000, 8 }, /* eight 4k MTRRs */
{}
};
@@ -194,12 +194,12 @@ get_fixed_ranges(mtrr_type * frs)
k8_check_syscfg_dram_mod_en();
- rdmsr(MTRRfix64K_00000_MSR, p[0], p[1]);
+ rdmsr(MSR_MTRRfix64K_00000, p[0], p[1]);
for (i = 0; i < 2; i++)
- rdmsr(MTRRfix16K_80000_MSR + i, p[2 + i * 2], p[3 + i * 2]);
+ rdmsr(MSR_MTRRfix16K_80000 + i, p[2 + i * 2], p[3 + i * 2]);
for (i = 0; i < 8; i++)
- rdmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2], p[7 + i * 2]);
+ rdmsr(MSR_MTRRfix4K_C0000 + i, p[6 + i * 2], p[7 + i * 2]);
}
void mtrr_save_fixed_ranges(void *info)
@@ -275,7 +275,11 @@ static void __init print_mtrr_state(void)
}
printk(KERN_DEBUG "MTRR variable ranges %sabled:\n",
mtrr_state.enabled & 2 ? "en" : "dis");
- high_width = ((size_or_mask ? ffs(size_or_mask) - 1 : 32) - (32 - PAGE_SHIFT) + 3) / 4;
+ if (size_or_mask & 0xffffffffUL)
+ high_width = ffs(size_or_mask & 0xffffffffUL) - 1;
+ else
+ high_width = ffs(size_or_mask>>32) + 32 - 1;
+ high_width = (high_width - (32 - PAGE_SHIFT) + 3) / 4;
for (i = 0; i < num_var_ranges; ++i) {
if (mtrr_state.var_ranges[i].mask_lo & (1 << 11))
printk(KERN_DEBUG " %u base %0*X%05X000 mask %0*X%05X000 %s\n",
@@ -306,7 +310,7 @@ void __init get_mtrr_state(void)
vrs = mtrr_state.var_ranges;
- rdmsr(MTRRcap_MSR, lo, dummy);
+ rdmsr(MSR_MTRRcap, lo, dummy);
mtrr_state.have_fixed = (lo >> 8) & 1;
for (i = 0; i < num_var_ranges; i++)
@@ -314,7 +318,7 @@ void __init get_mtrr_state(void)
if (mtrr_state.have_fixed)
get_fixed_ranges(mtrr_state.fixed_ranges);
- rdmsr(MTRRdefType_MSR, lo, dummy);
+ rdmsr(MSR_MTRRdefType, lo, dummy);
mtrr_state.def_type = (lo & 0xff);
mtrr_state.enabled = (lo & 0xc00) >> 10;
@@ -579,10 +583,10 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
__flush_tlb();
/* Save MTRR state */
- rdmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
+ rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
/* Disable MTRRs, and set the default type to uncached */
- mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & ~0xcff, deftype_hi);
+ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
}
static void post_set(void) __releases(set_atomicity_lock)
@@ -591,7 +595,7 @@ static void post_set(void) __releases(set_atomicity_lock)
__flush_tlb();
/* Intel (P6) standard MTRRs */
- mtrr_wrmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
+ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
/* Enable caches */
write_cr0(read_cr0() & 0xbfffffff);
@@ -703,7 +707,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, unsigned i
static int generic_have_wrcomb(void)
{
unsigned long config, dummy;
- rdmsr(MTRRcap_MSR, config, dummy);
+ rdmsr(MSR_MTRRcap, config, dummy);
return (config & (1 << 10));
}
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 03cda01f57c..8fc248b5aea 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -104,7 +104,7 @@ static void __init set_num_var_ranges(void)
unsigned long config = 0, dummy;
if (use_intel()) {
- rdmsr(MTRRcap_MSR, config, dummy);
+ rdmsr(MSR_MTRRcap, config, dummy);
} else if (is_cpu(AMD))
config = 2;
else if (is_cpu(CYRIX) || is_cpu(CENTAUR))
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 77f67f7b347..7538b767f20 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -5,21 +5,6 @@
#include <linux/types.h>
#include <linux/stddef.h>
-#define MTRRcap_MSR 0x0fe
-#define MTRRdefType_MSR 0x2ff
-
-#define MTRRfix64K_00000_MSR 0x250
-#define MTRRfix16K_80000_MSR 0x258
-#define MTRRfix16K_A0000_MSR 0x259
-#define MTRRfix4K_C0000_MSR 0x268
-#define MTRRfix4K_C8000_MSR 0x269
-#define MTRRfix4K_D0000_MSR 0x26a
-#define MTRRfix4K_D8000_MSR 0x26b
-#define MTRRfix4K_E0000_MSR 0x26c
-#define MTRRfix4K_E8000_MSR 0x26d
-#define MTRRfix4K_F0000_MSR 0x26e
-#define MTRRfix4K_F8000_MSR 0x26f
-
#define MTRR_CHANGE_MASK_FIXED 0x01
#define MTRR_CHANGE_MASK_VARIABLE 0x02
#define MTRR_CHANGE_MASK_DEFTYPE 0x04
diff --git a/arch/x86/kernel/cpu/mtrr/state.c b/arch/x86/kernel/cpu/mtrr/state.c
index 7f7e2753685..1f5fb1588d1 100644
--- a/arch/x86/kernel/cpu/mtrr/state.c
+++ b/arch/x86/kernel/cpu/mtrr/state.c
@@ -35,7 +35,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt)
if (use_intel())
/* Save MTRR state */
- rdmsr(MTRRdefType_MSR, ctxt->deftype_lo, ctxt->deftype_hi);
+ rdmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi);
else
/* Cyrix ARRs - everything else were excluded at the top */
ctxt->ccr3 = getCx86(CX86_CCR3);
@@ -46,7 +46,7 @@ void set_mtrr_cache_disable(struct set_mtrr_context *ctxt)
{
if (use_intel())
/* Disable MTRRs, and set the default type to uncached */
- mtrr_wrmsr(MTRRdefType_MSR, ctxt->deftype_lo & 0xf300UL,
+ mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo & 0xf300UL,
ctxt->deftype_hi);
else if (is_cpu(CYRIX))
/* Cyrix ARRs - everything else were excluded at the top */
@@ -64,7 +64,7 @@ void set_mtrr_done(struct set_mtrr_context *ctxt)
/* Restore MTRRdefType */
if (use_intel())
/* Intel (P6) standard MTRRs */
- mtrr_wrmsr(MTRRdefType_MSR, ctxt->deftype_lo, ctxt->deftype_hi);
+ mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi);
else
/* Cyrix ARRs - everything else was excluded at the top */
setCx86(CX86_CCR3, ctxt->ccr3);
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index f93047fed79..d5e30397246 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
if (c->x86_max_cores * smp_num_siblings > 1) {
seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
seq_printf(m, "siblings\t: %d\n",
- cpumask_weight(cpu_sibling_mask(cpu)));
+ cpumask_weight(cpu_core_mask(cpu)));
seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
seq_printf(m, "apicid\t\t: %d\n", c->apicid);
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index da87590b869..81086c227ab 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -29,7 +29,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *sp, unsigned long bp, char *log_lvl);
extern unsigned int code_bytes;
-extern int kstack_depth_to_print;
/* The form of the top of the frame on the stack */
struct stack_frame {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index ef2c3563357..00628130292 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1074,12 +1074,13 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
u64 addr;
u64 start;
- start = startt;
- while (size < sizet && (start + 1))
+ for (start = startt; ; start += size) {
start = find_e820_area_size(start, &size, align);
-
- if (size < sizet)
- return 0;
+ if (!(start + 1))
+ return 0;
+ if (size >= sizet)
+ break;
+ }
#ifdef CONFIG_X86_32
if (start >= MAXMEM)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 76b8cd953de..ebdb85cf268 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -97,6 +97,7 @@ static void __init nvidia_bugs(int num, int slot, int func)
}
#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
+#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
{
u32 d;
@@ -114,6 +115,7 @@ static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
d &= 0xff;
return d;
}
+#endif
static void __init ati_bugs(int num, int slot, int func)
{
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a331ec38af9..38946c6e843 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1410,7 +1410,10 @@ ENTRY(paranoid_exit)
paranoid_swapgs:
TRACE_IRQS_IRETQ 0
SWAPGS_UNSAFE_STACK
+ RESTORE_ALL 8
+ jmp irq_return
paranoid_restore:
+ TRACE_IRQS_IRETQ 0
RESTORE_ALL 8
jmp irq_return
paranoid_userspace:
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 70a10ca100f..b79c5533c42 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -18,6 +18,8 @@
#include <linux/init.h>
#include <linux/list.h>
+#include <trace/syscall.h>
+
#include <asm/cacheflush.h>
#include <asm/ftrace.h>
#include <asm/nops.h>
@@ -440,7 +442,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
_ASM_EXTABLE(1b, 4b)
_ASM_EXTABLE(2b, 4b)
- : [old] "=r" (old), [faulted] "=r" (faulted)
+ : [old] "=&r" (old), [faulted] "=r" (faulted)
: [parent] "r" (parent), [return_hooker] "r" (return_hooker)
: "memory"
);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 30683883e0c..dc5ed4bdd88 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -608,13 +608,6 @@ ignore_int:
ENTRY(initial_code)
.long i386_start_kernel
-.section .text
-/*
- * Real beginning of normal "text" segment
- */
-ENTRY(stext)
-ENTRY(_stext)
-
/*
* BSS section
*/
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 648b3a2a3a4..81408b93f88 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -236,6 +236,10 @@ static void hpet_stop_counter(void)
unsigned long cfg = hpet_readl(HPET_CFG);
cfg &= ~HPET_CFG_ENABLE;
hpet_writel(cfg, HPET_CFG);
+}
+
+static void hpet_reset_counter(void)
+{
hpet_writel(0, HPET_COUNTER);
hpet_writel(0, HPET_COUNTER + 4);
}
@@ -250,6 +254,7 @@ static void hpet_start_counter(void)
static void hpet_restart_counter(void)
{
hpet_stop_counter();
+ hpet_reset_counter();
hpet_start_counter();
}
@@ -309,7 +314,7 @@ static int hpet_setup_msi_irq(unsigned int irq);
static void hpet_set_mode(enum clock_event_mode mode,
struct clock_event_device *evt, int timer)
{
- unsigned long cfg;
+ unsigned long cfg, cmp, now;
uint64_t delta;
switch (mode) {
@@ -317,12 +322,23 @@ static void hpet_set_mode(enum clock_event_mode mode,
hpet_stop_counter();
delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
delta >>= evt->shift;
+ now = hpet_readl(HPET_COUNTER);
+ cmp = now + (unsigned long) delta;
cfg = hpet_readl(HPET_Tn_CFG(timer));
/* Make sure we use edge triggered interrupts */
cfg &= ~HPET_TN_LEVEL;
cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
HPET_TN_SETVAL | HPET_TN_32BIT;
hpet_writel(cfg, HPET_Tn_CFG(timer));
+ hpet_writel(cmp, HPET_Tn_CMP(timer));
+ udelay(1);
+ /*
+ * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL
+ * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL
+ * bit is automatically cleared after the first write.
+ * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
+ * Publication # 24674)
+ */
hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer));
hpet_start_counter();
hpet_print_config();
@@ -722,7 +738,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
/*
* Clock source related code
*/
-static cycle_t read_hpet(void)
+static cycle_t read_hpet(struct clocksource *cs)
{
return (cycle_t)hpet_readl(HPET_COUNTER);
}
@@ -756,7 +772,7 @@ static int hpet_clocksource_register(void)
hpet_restart_counter();
/* Verify whether hpet counter works */
- t1 = read_hpet();
+ t1 = hpet_readl(HPET_COUNTER);
rdtscll(start);
/*
@@ -770,7 +786,7 @@ static int hpet_clocksource_register(void)
rdtscll(now);
} while ((now - start) < 200000UL);
- if (t1 == read_hpet()) {
+ if (t1 == hpet_readl(HPET_COUNTER)) {
printk(KERN_WARNING
"HPET counter not counting. HPET disabled\n");
return -ENODEV;
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 3475440baa5..c2e0bb0890d 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -129,7 +129,7 @@ void __init setup_pit_timer(void)
* to just read by itself. So use jiffies to emulate a free
* running counter:
*/
-static cycle_t pit_read(void)
+static cycle_t pit_read(struct clocksource *cs)
{
static int old_count;
static u32 old_jifs;
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 3aaf7b9e3a8..9a391bbb8ba 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -12,6 +12,7 @@
#include <asm/io_apic.h>
#include <asm/irq.h>
#include <asm/idle.h>
+#include <asm/hw_irq.h>
atomic_t irq_err_count;
@@ -24,9 +25,9 @@ void (*generic_interrupt_extension)(void) = NULL;
*/
void ack_bad_irq(unsigned int irq)
{
- printk(KERN_ERR "unexpected IRQ trap at vector %02x\n", irq);
+ if (printk_ratelimit())
+ pr_err("unexpected IRQ trap at vector %02x\n", irq);
-#ifdef CONFIG_X86_LOCAL_APIC
/*
* Currently unexpected vectors happen only on SMP and APIC.
* We _must_ ack these because every local APIC has only N
@@ -36,9 +37,7 @@ void ack_bad_irq(unsigned int irq)
* completely.
* But only ack when the APIC is enabled -AK
*/
- if (cpu_has_apic)
- ack_APIC_irq();
-#endif
+ ack_APIC_irq();
}
#define irq_stats(x) (&per_cpu(irq_stat, x))
@@ -65,7 +64,7 @@ static int show_other_interrupts(struct seq_file *p, int prec)
seq_printf(p, " Spurious interrupts\n");
#endif
if (generic_interrupt_extension) {
- seq_printf(p, "PLT: ");
+ seq_printf(p, "%*s: ", prec, "PLT");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->generic_irqs);
seq_printf(p, " Platform interrupts\n");
@@ -178,7 +177,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
sum += irq_stats(cpu)->irq_thermal_count;
# ifdef CONFIG_X86_64
sum += irq_stats(cpu)->irq_threshold_count;
-#endif
+# endif
#endif
return sum;
}
@@ -213,14 +212,11 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
irq = __get_cpu_var(vector_irq)[vector];
if (!handle_irq(irq, regs)) {
-#ifdef CONFIG_X86_64
- if (!disable_apic)
- ack_APIC_irq();
-#endif
+ ack_APIC_irq();
if (printk_ratelimit())
- printk(KERN_EMERG "%s: %d.%d No irq handler for vector (irq %d)\n",
- __func__, smp_processor_id(), vector, irq);
+ pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n",
+ __func__, smp_processor_id(), vector, irq);
}
irq_exit();
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit.c
index 368b0a8836f..2e08b10ad51 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit.c
@@ -1,20 +1,25 @@
+#include <linux/linkage.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/ioport.h>
#include <linux/interrupt.h>
+#include <linux/timex.h>
#include <linux/slab.h>
#include <linux/random.h>
+#include <linux/kprobes.h>
#include <linux/init.h>
#include <linux/kernel_stat.h>
#include <linux/sysdev.h>
#include <linux/bitops.h>
+#include <linux/acpi.h>
#include <linux/io.h>
#include <linux/delay.h>
#include <asm/atomic.h>
#include <asm/system.h>
#include <asm/timer.h>
+#include <asm/hw_irq.h>
#include <asm/pgtable.h>
#include <asm/desc.h>
#include <asm/apic.h>
@@ -22,7 +27,23 @@
#include <asm/i8259.h>
#include <asm/traps.h>
+/*
+ * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
+ * (these are usually mapped to vectors 0x30-0x3f)
+ */
+
+/*
+ * The IO-APIC gives us many more interrupt sources. Most of these
+ * are unused but an SMP system is supposed to have enough memory ...
+ * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
+ * across the spectrum, so we really want to be prepared to get all
+ * of these. Plus, more powerful systems might have more than 64
+ * IO-APIC registers.
+ *
+ * (these are usually mapped into the 0x30-0xff vector range)
+ */
+#ifdef CONFIG_X86_32
/*
* Note that on a 486, we don't want to do a SIGFPE on an irq13
* as the irq is unreliable, and exception 16 works correctly
@@ -52,30 +73,7 @@ static struct irqaction fpu_irq = {
.handler = math_error_irq,
.name = "fpu",
};
-
-void __init init_ISA_irqs(void)
-{
- int i;
-
-#ifdef CONFIG_X86_LOCAL_APIC
- init_bsp_APIC();
#endif
- init_8259A(0);
-
- /*
- * 16 old-style INTA-cycle interrupts:
- */
- for (i = 0; i < NR_IRQS_LEGACY; i++) {
- struct irq_desc *desc = irq_to_desc(i);
-
- desc->status = IRQ_DISABLED;
- desc->action = NULL;
- desc->depth = 1;
-
- set_irq_chip_and_handler_name(i, &i8259A_chip,
- handle_level_irq, "XT");
- }
-}
/*
* IRQ2 is cascade interrupt to second interrupt controller
@@ -118,29 +116,37 @@ int vector_used_by_percpu_irq(unsigned int vector)
return 0;
}
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
+static void __init init_ISA_irqs(void)
{
int i;
- /* Execute any quirks before the call gates are initialised: */
- x86_quirk_pre_intr_init();
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+ init_bsp_APIC();
+#endif
+ init_8259A(0);
/*
- * Cover the whole vector space, no vector can escape
- * us. (some of these will be overridden and become
- * 'special' SMP interrupts)
+ * 16 old-style INTA-cycle interrupts:
*/
- for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
- /* SYSCALL_VECTOR was reserved in trap_init. */
- if (i != SYSCALL_VECTOR)
- set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
+ for (i = 0; i < NR_IRQS_LEGACY; i++) {
+ struct irq_desc *desc = irq_to_desc(i);
+
+ desc->status = IRQ_DISABLED;
+ desc->action = NULL;
+ desc->depth = 1;
+
+ set_irq_chip_and_handler_name(i, &i8259A_chip,
+ handle_level_irq, "XT");
}
+}
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_SMP)
+static void __init smp_intr_init(void)
+{
+#ifdef CONFIG_SMP
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
/*
* The reschedule interrupt is a CPU-to-CPU reschedule-helper
* IPI, driven by wakeup.
@@ -160,16 +166,27 @@ void __init native_init_IRQ(void)
/* IPI for generic function call */
alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
- /* IPI for single call function */
+ /* IPI for generic single function call */
alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
- call_function_single_interrupt);
+ call_function_single_interrupt);
/* Low priority IPI to cleanup after moving an irq */
set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
#endif
+#endif /* CONFIG_SMP */
+}
+
+static void __init apic_intr_init(void)
+{
+ smp_intr_init();
+
+#ifdef CONFIG_X86_64
+ alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+ alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+#endif
-#ifdef CONFIG_X86_LOCAL_APIC
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
/* self generated IPI for local APIC timer */
alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
@@ -179,16 +196,67 @@ void __init native_init_IRQ(void)
/* IPI vectors for APIC spurious and error interrupts */
alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+
+ /* Performance monitoring interrupts: */
+# ifdef CONFIG_PERF_COUNTERS
+ alloc_intr_gate(LOCAL_PERF_VECTOR, perf_counter_interrupt);
+ alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt);
+# endif
+
#endif
+#ifdef CONFIG_X86_32
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_MCE_P4THERMAL)
/* thermal monitor LVT interrupt */
alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
#endif
+#endif
+}
+
+/**
+ * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
+ *
+ * Description:
+ * Perform any necessary interrupt initialisation prior to setting up
+ * the "ordinary" interrupt call gates. For legacy reasons, the ISA
+ * interrupts should be initialised here if the machine emulates a PC
+ * in any way.
+ **/
+static void __init x86_quirk_pre_intr_init(void)
+{
+#ifdef CONFIG_X86_32
+ if (x86_quirks->arch_pre_intr_init) {
+ if (x86_quirks->arch_pre_intr_init())
+ return;
+ }
+#endif
+ init_ISA_irqs();
+}
+
+void __init native_init_IRQ(void)
+{
+ int i;
+
+ /* Execute any quirks before the call gates are initialised: */
+ x86_quirk_pre_intr_init();
+
+ apic_intr_init();
+
+ /*
+ * Cover the whole vector space, no vector can escape
+ * us. (some of these will be overridden and become
+ * 'special' SMP interrupts)
+ */
+ for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
+ /* IA32_SYSCALL_VECTOR could be used in trap_init already. */
+ if (!test_bit(i, used_vectors))
+ set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
+ }
if (!acpi_ioapic)
setup_irq(2, &irq2);
+#ifdef CONFIG_X86_32
/*
* Call quirks after call gates are initialised (usually add in
* the architecture specific gates):
@@ -203,4 +271,5 @@ void __init native_init_IRQ(void)
setup_irq(FPU_IRQ, &fpu_irq);
irq_ctx_init(smp_processor_id());
+#endif
}
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
deleted file mode 100644
index 8cd10537fd4..00000000000
--- a/arch/x86/kernel/irqinit_64.c
+++ /dev/null
@@ -1,177 +0,0 @@
-#include <linux/linkage.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-#include <linux/acpi.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/hw_irq.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/i8259.h>
-
-/*
- * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
- * (these are usually mapped to vectors 0x30-0x3f)
- */
-
-/*
- * The IO-APIC gives us many more interrupt sources. Most of these
- * are unused but an SMP system is supposed to have enough memory ...
- * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
- * across the spectrum, so we really want to be prepared to get all
- * of these. Plus, more powerful systems might have more than 64
- * IO-APIC registers.
- *
- * (these are usually mapped into the 0x30-0xff vector range)
- */
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-
-static struct irqaction irq2 = {
- .handler = no_action,
- .name = "cascade",
-};
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
- [0 ... IRQ0_VECTOR - 1] = -1,
- [IRQ0_VECTOR] = 0,
- [IRQ1_VECTOR] = 1,
- [IRQ2_VECTOR] = 2,
- [IRQ3_VECTOR] = 3,
- [IRQ4_VECTOR] = 4,
- [IRQ5_VECTOR] = 5,
- [IRQ6_VECTOR] = 6,
- [IRQ7_VECTOR] = 7,
- [IRQ8_VECTOR] = 8,
- [IRQ9_VECTOR] = 9,
- [IRQ10_VECTOR] = 10,
- [IRQ11_VECTOR] = 11,
- [IRQ12_VECTOR] = 12,
- [IRQ13_VECTOR] = 13,
- [IRQ14_VECTOR] = 14,
- [IRQ15_VECTOR] = 15,
- [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
-};
-
-int vector_used_by_percpu_irq(unsigned int vector)
-{
- int cpu;
-
- for_each_online_cpu(cpu) {
- if (per_cpu(vector_irq, cpu)[vector] != -1)
- return 1;
- }
-
- return 0;
-}
-
-static void __init init_ISA_irqs(void)
-{
- int i;
-
- init_bsp_APIC();
- init_8259A(0);
-
- for (i = 0; i < NR_IRQS_LEGACY; i++) {
- struct irq_desc *desc = irq_to_desc(i);
-
- desc->status = IRQ_DISABLED;
- desc->action = NULL;
- desc->depth = 1;
-
- /*
- * 16 old-style INTA-cycle interrupts:
- */
- set_irq_chip_and_handler_name(i, &i8259A_chip,
- handle_level_irq, "XT");
- }
-}
-
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-static void __init smp_intr_init(void)
-{
-#ifdef CONFIG_SMP
- /*
- * The reschedule interrupt is a CPU-to-CPU reschedule-helper
- * IPI, driven by wakeup.
- */
- alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-
- /* IPIs for invalidation */
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
-
- /* IPI for generic function call */
- alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-
- /* IPI for generic single function call */
- alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
- call_function_single_interrupt);
-
- /* Low priority IPI to cleanup after moving an irq */
- set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
- set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
-#endif
-}
-
-static void __init apic_intr_init(void)
-{
- smp_intr_init();
-
- alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
- alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
-
- /* self generated IPI for local APIC timer */
- alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-
- /* generic IPI for platform specific use */
- alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt);
-
- /* IPI vectors for APIC spurious and error interrupts */
- alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
- alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-}
-
-void __init native_init_IRQ(void)
-{
- int i;
-
- init_ISA_irqs();
- /*
- * Cover the whole vector space, no vector can escape
- * us. (some of these will be overridden and become
- * 'special' SMP interrupts)
- */
- for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
- int vector = FIRST_EXTERNAL_VECTOR + i;
- if (vector != IA32_SYSCALL_VECTOR)
- set_intr_gate(vector, interrupt[i]);
- }
-
- apic_intr_init();
-
- if (!acpi_ioapic)
- setup_irq(2, &irq2);
-}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index eedfaebe106..8d82a77a3f3 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -88,6 +88,7 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
gdb_regs[GDB_SS] = __KERNEL_DS;
gdb_regs[GDB_FS] = 0xFFFF;
gdb_regs[GDB_GS] = 0xFFFF;
+ gdb_regs[GDB_SP] = (int)&regs->sp;
#else
gdb_regs[GDB_R8] = regs->r8;
gdb_regs[GDB_R9] = regs->r9;
@@ -100,8 +101,8 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
gdb_regs32[GDB_PS] = regs->flags;
gdb_regs32[GDB_CS] = regs->cs;
gdb_regs32[GDB_SS] = regs->ss;
-#endif
gdb_regs[GDB_SP] = regs->sp;
+#endif
}
/**
@@ -141,7 +142,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
gdb_regs32[GDB_PS] = *(unsigned long *)(p->thread.sp + 8);
gdb_regs32[GDB_CS] = __KERNEL_CS;
gdb_regs32[GDB_SS] = __KERNEL_DS;
- gdb_regs[GDB_PC] = p->thread.ip;
+ gdb_regs[GDB_PC] = 0;
gdb_regs[GDB_R8] = 0;
gdb_regs[GDB_R9] = 0;
gdb_regs[GDB_R10] = 0;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 137f2e8132d..223af43f152 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -77,6 +77,11 @@ static cycle_t kvm_clock_read(void)
return ret;
}
+static cycle_t kvm_clock_get_cycles(struct clocksource *cs)
+{
+ return kvm_clock_read();
+}
+
/*
* If we don't do that, there is the possibility that the guest
* will calibrate under heavy load - thus, getting a lower lpj -
@@ -107,7 +112,7 @@ static void kvm_get_preset_lpj(void)
static struct clocksource kvm_clock = {
.name = "kvm-clock",
- .read = kvm_clock_read,
+ .read = kvm_clock_get_cycles,
.rating = 400,
.mask = CLOCKSOURCE_MASK(64),
.mult = 1 << KVM_SCALE,
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index e7368c1da01..c1c429d0013 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -194,7 +194,7 @@ void machine_kexec(struct kimage *image)
unsigned int preserve_context);
#ifdef CONFIG_KEXEC_JUMP
- if (kexec_image->preserve_context)
+ if (image->preserve_context)
save_processor_state();
#endif
@@ -253,7 +253,7 @@ void machine_kexec(struct kimage *image)
image->preserve_context);
#ifdef CONFIG_KEXEC_JUMP
- if (kexec_image->preserve_context)
+ if (image->preserve_context)
restore_processor_state();
#endif
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 89cea4d4467..84c3bf209e9 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -274,7 +274,7 @@ void machine_kexec(struct kimage *image)
int save_ftrace_enabled;
#ifdef CONFIG_KEXEC_JUMP
- if (kexec_image->preserve_context)
+ if (image->preserve_context)
save_processor_state();
#endif
@@ -333,7 +333,7 @@ void machine_kexec(struct kimage *image)
image->preserve_context);
#ifdef CONFIG_KEXEC_JUMP
- if (kexec_image->preserve_context)
+ if (image->preserve_context)
restore_processor_state();
#endif
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index a0f3851ef31..98c470c069d 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -108,40 +108,29 @@ struct ucode_cpu_info ucode_cpu_info[NR_CPUS];
EXPORT_SYMBOL_GPL(ucode_cpu_info);
#ifdef CONFIG_MICROCODE_OLD_INTERFACE
-struct update_for_cpu {
- const void __user *buf;
- size_t size;
-};
-
-static long update_for_cpu(void *_ufc)
-{
- struct update_for_cpu *ufc = _ufc;
- int error;
-
- error = microcode_ops->request_microcode_user(smp_processor_id(),
- ufc->buf, ufc->size);
- if (error < 0)
- return error;
- if (!error)
- microcode_ops->apply_microcode(smp_processor_id());
- return error;
-}
-
static int do_microcode_update(const void __user *buf, size_t size)
{
+ cpumask_t old;
int error = 0;
int cpu;
- struct update_for_cpu ufc = { .buf = buf, .size = size };
+
+ old = current->cpus_allowed;
for_each_online_cpu(cpu) {
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
if (!uci->valid)
continue;
- error = work_on_cpu(cpu, update_for_cpu, &ufc);
+
+ set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ error = microcode_ops->request_microcode_user(cpu, buf, size);
if (error < 0)
- break;
+ goto out;
+ if (!error)
+ microcode_ops->apply_microcode(cpu);
}
+out:
+ set_cpus_allowed_ptr(current, &old);
return error;
}
@@ -391,8 +380,6 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
return err;
err = microcode_init_cpu(cpu);
- if (err)
- sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
return err;
}
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index dce99dca6cf..651c93b2886 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -17,6 +17,7 @@
#include <linux/acpi.h>
#include <linux/module.h>
#include <linux/smp.h>
+#include <linux/pci.h>
#include <asm/mtrr.h>
#include <asm/mpspec.h>
@@ -679,7 +680,7 @@ void __init get_smp_config(void)
__get_smp_config(0);
}
-static void smp_reserve_bootmem(struct mpf_intel *mpf)
+static void __init smp_reserve_bootmem(struct mpf_intel *mpf)
{
unsigned long size = get_mpc_size(mpf->physptr);
#ifdef CONFIG_X86_32
@@ -838,7 +839,7 @@ static int __init get_MP_intsrc_index(struct mpc_intsrc *m)
static struct mpc_intsrc __initdata *m_spare[SPARE_SLOT_NUM];
-static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
+static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
{
int i;
@@ -866,27 +867,21 @@ static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
}
}
#else /* CONFIG_X86_IO_APIC */
-static inline void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
+static
+inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
#endif /* CONFIG_X86_IO_APIC */
-static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length,
- int count)
+static int
+check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
{
- if (!mpc_new_phys) {
- pr_info("No spare slots, try to append...take your risk, "
- "new mpc_length %x\n", count);
- } else {
- if (count <= mpc_new_length)
- pr_info("No spare slots, try to append..., "
- "new mpc_length %x\n", count);
- else {
- pr_err("mpc_new_length %lx is too small\n",
- mpc_new_length);
- return -1;
- }
+ int ret = 0;
+
+ if (!mpc_new_phys || count <= mpc_new_length) {
+ WARN(1, "update_mptable: No spare slots (length: %x)\n", count);
+ return -1;
}
- return 0;
+ return ret;
}
static int __init replace_intsrc_all(struct mpc_table *mpc,
@@ -945,7 +940,7 @@ static int __init replace_intsrc_all(struct mpc_table *mpc,
} else {
struct mpc_intsrc *m = (struct mpc_intsrc *)mpt;
count += sizeof(struct mpc_intsrc);
- if (!check_slot(mpc_new_phys, mpc_new_length, count))
+ if (check_slot(mpc_new_phys, mpc_new_length, count) < 0)
goto out;
assign_to_mpc_intsrc(&mp_irqs[i], m);
mpc->length = count;
@@ -962,11 +957,14 @@ out:
return 0;
}
-static int __initdata enable_update_mptable;
+int enable_update_mptable;
static int __init update_mptable_setup(char *str)
{
enable_update_mptable = 1;
+#ifdef CONFIG_PCI
+ pci_routeirq = 1;
+#endif
return 0;
}
early_param("update_mptable", update_mptable_setup);
@@ -979,6 +977,9 @@ static int __initdata alloc_mptable;
static int __init parse_alloc_mptable_opt(char *p)
{
enable_update_mptable = 1;
+#ifdef CONFIG_PCI
+ pci_routeirq = 1;
+#endif
alloc_mptable = 1;
if (!p)
return 0;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 8e45f446488..9faf43bea33 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -134,7 +134,9 @@ static void *get_call_destination(u8 type)
.pv_irq_ops = pv_irq_ops,
.pv_apic_ops = pv_apic_ops,
.pv_mmu_ops = pv_mmu_ops,
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
.pv_lock_ops = pv_lock_ops,
+#endif
};
return *((void **)&tmpl + type);
}
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 34f12e9996e..221a3853e26 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -50,7 +50,7 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
}
-struct dma_map_ops swiotlb_dma_ops = {
+static struct dma_map_ops swiotlb_dma_ops = {
.mapping_error = swiotlb_dma_mapping_error,
.alloc_coherent = x86_swiotlb_alloc_coherent,
.free_coherent = swiotlb_free_coherent,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ca989158e84..3e21e38d7e3 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -11,6 +11,7 @@
#include <trace/power.h>
#include <asm/system.h>
#include <asm/apic.h>
+#include <asm/syscalls.h>
#include <asm/idle.h>
#include <asm/uaccess.h>
#include <asm/i387.h>
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index fe9345c967d..23b7c8f017e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,7 +21,6 @@
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>
-#include <linux/ftrace.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -35,6 +34,8 @@
#include <asm/proto.h>
#include <asm/ds.h>
+#include <trace/syscall.h>
+
#include "tls.h"
enum x86_regset {
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index e95022e4f5d..af71d06624b 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -261,8 +261,6 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev)
{
if (hpet_force_user)
old_ich_force_enable_hpet(dev);
- else
- hpet_print_force_info();
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_1,
@@ -493,5 +491,42 @@ void force_hpet_resume(void)
break;
}
}
+#endif
+
+#if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
+/* Set correct numa_node information for AMD NB functions */
+static void __init quirk_amd_nb_node(struct pci_dev *dev)
+{
+ struct pci_dev *nb_ht;
+ unsigned int devfn;
+ u32 val;
+
+ devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0);
+ nb_ht = pci_get_slot(dev->bus, devfn);
+ if (!nb_ht)
+ return;
+
+ pci_read_config_dword(nb_ht, 0x60, &val);
+ set_dev_node(&dev->dev, val & 7);
+ pci_dev_put(dev);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MEMCTL,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_HT,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MAP,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_DRAM,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_LINK,
+ quirk_amd_nb_node);
#endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 2aef36d8aca..667188e0b5a 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -224,6 +224,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"),
},
},
+ { /* Handle problems with rebooting on Dell DXP061 */
+ .callback = set_bios_reboot,
+ .ident = "Dell DXP061",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"),
+ },
+ },
+ { /* Handle problems with rebooting on Sony VGN-Z540N */
+ .callback = set_bios_reboot,
+ .ident = "Sony VGN-Z540N",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"),
+ },
+ },
{ }
};
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b4158439bf6..7791eef95b9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -214,8 +214,8 @@ unsigned long mmu_cr4_features;
unsigned long mmu_cr4_features = X86_CR4_PAE;
#endif
-/* Boot loader ID as an integer, for the benefit of proc_dointvec */
-int bootloader_type;
+/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
+int bootloader_type, bootloader_version;
/*
* Setup options
@@ -706,6 +706,12 @@ void __init setup_arch(char **cmdline_p)
#endif
saved_video_mode = boot_params.hdr.vid_mode;
bootloader_type = boot_params.hdr.type_of_loader;
+ if ((bootloader_type >> 4) == 0xe) {
+ bootloader_type &= 0xf;
+ bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
+ }
+ bootloader_version = bootloader_type & 0xf;
+ bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
#ifdef CONFIG_BLK_DEV_RAM
rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
@@ -997,24 +1003,6 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_X86_32
/**
- * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
- *
- * Description:
- * Perform any necessary interrupt initialisation prior to setting up
- * the "ordinary" interrupt call gates. For legacy reasons, the ISA
- * interrupts should be initialised here if the machine emulates a PC
- * in any way.
- **/
-void __init x86_quirk_pre_intr_init(void)
-{
- if (x86_quirks->arch_pre_intr_init) {
- if (x86_quirks->arch_pre_intr_init())
- return;
- }
- init_ISA_irqs();
-}
-
-/**
* x86_quirk_intr_init - post gate setup interrupt initialisation
*
* Description:
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 3a97a4cf187..8f0e13be36b 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -160,8 +160,10 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
/*
* If large page isn't supported, there's no benefit in doing
* this. Also, on non-NUMA, embedding is better.
+ *
+ * NOTE: disabled for now.
*/
- if (!cpu_has_pse || !pcpu_need_numa())
+ if (true || !cpu_has_pse || !pcpu_need_numa())
return -EINVAL;
/*
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 13f33ea8cca..f6db48c405b 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -193,19 +193,19 @@ void smp_call_function_single_interrupt(struct pt_regs *regs)
}
struct smp_ops smp_ops = {
- .smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
- .smp_prepare_cpus = native_smp_prepare_cpus,
- .smp_cpus_done = native_smp_cpus_done,
+ .smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
+ .smp_prepare_cpus = native_smp_prepare_cpus,
+ .smp_cpus_done = native_smp_cpus_done,
- .smp_send_stop = native_smp_send_stop,
- .smp_send_reschedule = native_smp_send_reschedule,
+ .smp_send_stop = native_smp_send_stop,
+ .smp_send_reschedule = native_smp_send_reschedule,
- .cpu_up = native_cpu_up,
- .cpu_die = native_cpu_die,
- .cpu_disable = native_cpu_disable,
- .play_dead = native_play_dead,
+ .cpu_up = native_cpu_up,
+ .cpu_die = native_cpu_die,
+ .cpu_disable = native_cpu_disable,
+ .play_dead = native_play_dead,
- .send_call_func_ipi = native_send_call_func_ipi,
+ .send_call_func_ipi = native_send_call_func_ipi,
.send_call_func_single_ipi = native_send_call_func_single_ipi,
};
EXPORT_SYMBOL_GPL(smp_ops);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 58d24ef917d..7c80007ea5f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -504,7 +504,7 @@ void __inquire_remote_apic(int apicid)
* INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
* won't ... remember to clear down the APIC, etc later.
*/
-int __devinit
+int __cpuinit
wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
{
unsigned long send_status, accept_status = 0;
@@ -538,7 +538,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
return (send_status | accept_status);
}
-int __devinit
+static int __cpuinit
wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
{
unsigned long send_status, accept_status = 0;
@@ -822,10 +822,12 @@ do_rest:
/* mark "stuck" area as not stuck */
*((volatile unsigned long *)trampoline_base) = 0;
- /*
- * Cleanup possible dangling ends...
- */
- smpboot_restore_warm_reset_vector();
+ if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+ /*
+ * Cleanup possible dangling ends...
+ */
+ smpboot_restore_warm_reset_vector();
+ }
return boot_error;
}
@@ -990,10 +992,12 @@ static int __init smp_sanity_check(unsigned max_cpus)
*/
if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
!cpu_has_apic) {
- printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
- boot_cpu_physical_apicid);
- printk(KERN_ERR "... forcing use of dummy APIC emulation."
+ if (!disable_apic) {
+ pr_err("BIOS bug, local APIC #%d not detected!...\n",
+ boot_cpu_physical_apicid);
+ pr_err("... forcing use of dummy APIC emulation."
"(tell your hw vendor)\n");
+ }
smpboot_clear_io_apic();
arch_disable_smp_support();
return -1;
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index deb5ebb32c3..8c7b03b0cfc 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -25,6 +25,8 @@ static int uv_bau_retry_limit __read_mostly;
/* position of pnode (which is nasid>>1): */
static int uv_nshift __read_mostly;
+/* base pnode in this partition */
+static int uv_partition_base_pnode __read_mostly;
static unsigned long uv_mmask __read_mostly;
@@ -32,6 +34,34 @@ static DEFINE_PER_CPU(struct ptc_stats, ptcstats);
static DEFINE_PER_CPU(struct bau_control, bau_control);
/*
+ * Determine the first node on a blade.
+ */
+static int __init blade_to_first_node(int blade)
+{
+ int node, b;
+
+ for_each_online_node(node) {
+ b = uv_node_to_blade_id(node);
+ if (blade == b)
+ return node;
+ }
+ return -1; /* shouldn't happen */
+}
+
+/*
+ * Determine the apicid of the first cpu on a blade.
+ */
+static int __init blade_to_first_apicid(int blade)
+{
+ int cpu;
+
+ for_each_present_cpu(cpu)
+ if (blade == uv_cpu_to_blade_id(cpu))
+ return per_cpu(x86_cpu_to_apicid, cpu);
+ return -1;
+}
+
+/*
* Free a software acknowledge hardware resource by clearing its Pending
* bit. This will return a reply to the sender.
* If the message has timed out, a reply has already been sent by the
@@ -67,7 +97,7 @@ static void uv_bau_process_message(struct bau_payload_queue_entry *msg,
msp = __get_cpu_var(bau_control).msg_statuses + msg_slot;
cpu = uv_blade_processor_id();
msg->number_of_cpus =
- uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id()));
+ uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id()));
this_cpu_mask = 1UL << cpu;
if (msp->seen_by.bits & this_cpu_mask)
return;
@@ -215,14 +245,14 @@ static int uv_wait_completion(struct bau_desc *bau_desc,
* Returns @flush_mask if some remote flushing remains to be done. The
* mask will have some bits still set.
*/
-const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
+const struct cpumask *uv_flush_send_and_wait(int cpu, int this_pnode,
struct bau_desc *bau_desc,
struct cpumask *flush_mask)
{
int completion_status = 0;
int right_shift;
int tries = 0;
- int blade;
+ int pnode;
int bit;
unsigned long mmr_offset;
unsigned long index;
@@ -265,8 +295,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
* use the IPI method of shootdown on them.
*/
for_each_cpu(bit, flush_mask) {
- blade = uv_cpu_to_blade_id(bit);
- if (blade == this_blade)
+ pnode = uv_cpu_to_pnode(bit);
+ if (pnode == this_pnode)
continue;
cpumask_clear_cpu(bit, flush_mask);
}
@@ -309,16 +339,16 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask);
int i;
int bit;
- int blade;
+ int pnode;
int uv_cpu;
- int this_blade;
+ int this_pnode;
int locals = 0;
struct bau_desc *bau_desc;
cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu));
uv_cpu = uv_blade_processor_id();
- this_blade = uv_numa_blade_id();
+ this_pnode = uv_hub_info->pnode;
bau_desc = __get_cpu_var(bau_control).descriptor_base;
bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu;
@@ -326,13 +356,14 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
i = 0;
for_each_cpu(bit, flush_mask) {
- blade = uv_cpu_to_blade_id(bit);
- BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1));
- if (blade == this_blade) {
+ pnode = uv_cpu_to_pnode(bit);
+ BUG_ON(pnode > (UV_DISTRIBUTION_SIZE - 1));
+ if (pnode == this_pnode) {
locals++;
continue;
}
- bau_node_set(blade, &bau_desc->distribution);
+ bau_node_set(pnode - uv_partition_base_pnode,
+ &bau_desc->distribution);
i++;
}
if (i == 0) {
@@ -350,7 +381,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
bau_desc->payload.address = va;
bau_desc->payload.sending_cpu = cpu;
- return uv_flush_send_and_wait(uv_cpu, this_blade, bau_desc, flush_mask);
+ return uv_flush_send_and_wait(uv_cpu, this_pnode, bau_desc, flush_mask);
}
/*
@@ -418,24 +449,58 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
set_irq_regs(old_regs);
}
+/*
+ * uv_enable_timeouts
+ *
+ * Each target blade (i.e. blades that have cpu's) needs to have
+ * shootdown message timeouts enabled. The timeout does not cause
+ * an interrupt, but causes an error message to be returned to
+ * the sender.
+ */
static void uv_enable_timeouts(void)
{
- int i;
int blade;
- int last_blade;
+ int nblades;
int pnode;
- int cur_cpu = 0;
- unsigned long apicid;
+ unsigned long mmr_image;
- last_blade = -1;
- for_each_online_node(i) {
- blade = uv_node_to_blade_id(i);
- if (blade == last_blade)
+ nblades = uv_num_possible_blades();
+
+ for (blade = 0; blade < nblades; blade++) {
+ if (!uv_blade_nr_possible_cpus(blade))
continue;
- last_blade = blade;
- apicid = per_cpu(x86_cpu_to_apicid, cur_cpu);
+
pnode = uv_blade_to_pnode(blade);
- cur_cpu += uv_blade_nr_possible_cpus(i);
+ mmr_image =
+ uv_read_global_mmr64(pnode, UVH_LB_BAU_MISC_CONTROL);
+ /*
+ * Set the timeout period and then lock it in, in three
+ * steps; captures and locks in the period.
+ *
+ * To program the period, the SOFT_ACK_MODE must be off.
+ */
+ mmr_image &= ~((unsigned long)1 <<
+ UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT);
+ uv_write_global_mmr64
+ (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+ /*
+ * Set the 4-bit period.
+ */
+ mmr_image &= ~((unsigned long)0xf <<
+ UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT);
+ mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD <<
+ UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT);
+ uv_write_global_mmr64
+ (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+ /*
+ * Subsequent reversals of the timebase bit (3) cause an
+ * immediate timeout of one or all INTD resources as
+ * indicated in bits 2:0 (7 causes all of them to timeout).
+ */
+ mmr_image |= ((unsigned long)1 <<
+ UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT);
+ uv_write_global_mmr64
+ (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
}
}
@@ -482,8 +547,7 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
stat->requestee, stat->onetlb, stat->alltlb,
stat->s_retry, stat->d_retry, stat->ptc_i);
seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld\n",
- uv_read_global_mmr64(uv_blade_to_pnode
- (uv_cpu_to_blade_id(cpu)),
+ uv_read_global_mmr64(uv_cpu_to_pnode(cpu),
UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE),
stat->sflush, stat->dflush,
stat->retriesok, stat->nomsg,
@@ -617,16 +681,18 @@ static struct bau_control * __init uv_table_bases_init(int blade, int node)
* finish the initialization of the per-blade control structures
*/
static void __init
-uv_table_bases_finish(int blade, int node, int cur_cpu,
+uv_table_bases_finish(int blade,
struct bau_control *bau_tablesp,
struct bau_desc *adp)
{
struct bau_control *bcp;
- int i;
+ int cpu;
- for (i = cur_cpu; i < cur_cpu + uv_blade_nr_possible_cpus(blade); i++) {
- bcp = (struct bau_control *)&per_cpu(bau_control, i);
+ for_each_present_cpu(cpu) {
+ if (blade != uv_cpu_to_blade_id(cpu))
+ continue;
+ bcp = (struct bau_control *)&per_cpu(bau_control, cpu);
bcp->bau_msg_head = bau_tablesp->va_queue_first;
bcp->va_queue_first = bau_tablesp->va_queue_first;
bcp->va_queue_last = bau_tablesp->va_queue_last;
@@ -649,11 +715,10 @@ uv_activation_descriptor_init(int node, int pnode)
struct bau_desc *adp;
struct bau_desc *ad2;
- adp = (struct bau_desc *)
- kmalloc_node(16384, GFP_KERNEL, node);
+ adp = (struct bau_desc *)kmalloc_node(16384, GFP_KERNEL, node);
BUG_ON(!adp);
- pa = __pa((unsigned long)adp);
+ pa = uv_gpa(adp); /* need the real nasid*/
n = pa >> uv_nshift;
m = pa & uv_mmask;
@@ -667,8 +732,12 @@ uv_activation_descriptor_init(int node, int pnode)
for (i = 0, ad2 = adp; i < UV_ACTIVATION_DESCRIPTOR_SIZE; i++, ad2++) {
memset(ad2, 0, sizeof(struct bau_desc));
ad2->header.sw_ack_flag = 1;
- ad2->header.base_dest_nodeid =
- uv_blade_to_pnode(uv_cpu_to_blade_id(0));
+ /*
+ * base_dest_nodeid is the first node in the partition, so
+ * the bit map will indicate partition-relative node numbers.
+ * note that base_dest_nodeid is actually a nasid.
+ */
+ ad2->header.base_dest_nodeid = uv_partition_base_pnode << 1;
ad2->header.command = UV_NET_ENDPOINT_INTD;
ad2->header.int_both = 1;
/*
@@ -686,6 +755,8 @@ static struct bau_payload_queue_entry * __init
uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp)
{
struct bau_payload_queue_entry *pqp;
+ unsigned long pa;
+ int pn;
char *cp;
pqp = (struct bau_payload_queue_entry *) kmalloc_node(
@@ -696,10 +767,14 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp)
cp = (char *)pqp + 31;
pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5);
bau_tablesp->va_queue_first = pqp;
+ /*
+ * need the pnode of where the memory was really allocated
+ */
+ pa = uv_gpa(pqp);
+ pn = pa >> uv_nshift;
uv_write_global_mmr64(pnode,
UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST,
- ((unsigned long)pnode <<
- UV_PAYLOADQ_PNODE_SHIFT) |
+ ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) |
uv_physnodeaddr(pqp));
uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL,
uv_physnodeaddr(pqp));
@@ -715,8 +790,9 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp)
/*
* Initialization of each UV blade's structures
*/
-static int __init uv_init_blade(int blade, int node, int cur_cpu)
+static int __init uv_init_blade(int blade)
{
+ int node;
int pnode;
unsigned long pa;
unsigned long apicid;
@@ -724,16 +800,17 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu)
struct bau_payload_queue_entry *pqp;
struct bau_control *bau_tablesp;
+ node = blade_to_first_node(blade);
bau_tablesp = uv_table_bases_init(blade, node);
pnode = uv_blade_to_pnode(blade);
adp = uv_activation_descriptor_init(node, pnode);
pqp = uv_payload_queue_init(node, pnode, bau_tablesp);
- uv_table_bases_finish(blade, node, cur_cpu, bau_tablesp, adp);
+ uv_table_bases_finish(blade, bau_tablesp, adp);
/*
* the below initialization can't be in firmware because the
* messaging IRQ will be determined by the OS
*/
- apicid = per_cpu(x86_cpu_to_apicid, cur_cpu);
+ apicid = blade_to_first_apicid(blade);
pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG);
if ((pa & 0xff) != UV_BAU_MESSAGE) {
uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
@@ -748,44 +825,34 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu)
static int __init uv_bau_init(void)
{
int blade;
- int node;
int nblades;
- int last_blade;
int cur_cpu;
if (!is_uv_system())
return 0;
for_each_possible_cpu(cur_cpu)
- alloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu),
+ zalloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu),
GFP_KERNEL, cpu_to_node(cur_cpu));
uv_bau_retry_limit = 1;
uv_nshift = uv_hub_info->n_val;
uv_mmask = (1UL << uv_hub_info->n_val) - 1;
- nblades = 0;
- last_blade = -1;
- cur_cpu = 0;
- for_each_online_node(node) {
- blade = uv_node_to_blade_id(node);
- if (blade == last_blade)
- continue;
- last_blade = blade;
- nblades++;
- }
+ nblades = uv_num_possible_blades();
+
uv_bau_table_bases = (struct bau_control **)
kmalloc(nblades * sizeof(struct bau_control *), GFP_KERNEL);
BUG_ON(!uv_bau_table_bases);
- last_blade = -1;
- for_each_online_node(node) {
- blade = uv_node_to_blade_id(node);
- if (blade == last_blade)
- continue;
- last_blade = blade;
- uv_init_blade(blade, node, cur_cpu);
- cur_cpu += uv_blade_nr_possible_cpus(blade);
- }
+ uv_partition_base_pnode = 0x7fffffff;
+ for (blade = 0; blade < nblades; blade++)
+ if (uv_blade_nr_possible_cpus(blade) &&
+ (uv_blade_to_pnode(blade) < uv_partition_base_pnode))
+ uv_partition_base_pnode = uv_blade_to_pnode(blade);
+ for (blade = 0; blade < nblades; blade++)
+ if (uv_blade_nr_possible_cpus(blade))
+ uv_init_blade(blade);
+
alloc_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1);
uv_enable_timeouts();
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d696145855b..ede024531f8 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -966,11 +966,8 @@ void __init trap_init(void)
for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
set_bit(i, used_vectors);
-#ifdef CONFIG_X86_64
set_bit(IA32_SYSCALL_VECTOR, used_vectors);
-#else
- set_bit(SYSCALL_VECTOR, used_vectors);
-#endif
+
/*
* Should be a barrier for any external CPU state:
*/
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 7a567ebe636..84d27356c3d 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -384,13 +384,13 @@ unsigned long native_calibrate_tsc(void)
{
u64 tsc1, tsc2, delta, ref1, ref2;
unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
- unsigned long flags, latch, ms, fast_calibrate, tsc_khz;
+ unsigned long flags, latch, ms, fast_calibrate, hv_tsc_khz;
int hpet = is_hpet_enabled(), i, loopmin;
- tsc_khz = get_hypervisor_tsc_freq();
- if (tsc_khz) {
+ hv_tsc_khz = get_hypervisor_tsc_freq();
+ if (hv_tsc_khz) {
printk(KERN_INFO "TSC: Frequency read from the hypervisor\n");
- return tsc_khz;
+ return hv_tsc_khz;
}
local_irq_save(flags);
@@ -699,7 +699,7 @@ static struct clocksource clocksource_tsc;
* code, which is necessary to support wrapping clocksources like pm
* timer.
*/
-static cycle_t read_tsc(void)
+static cycle_t read_tsc(struct clocksource *cs)
{
cycle_t ret = (cycle_t)get_cycles();
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index bf36328f6ef..027b5b49899 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -34,6 +34,7 @@ static __cpuinitdata atomic_t stop_count;
* of a critical section, to be able to prove TSC time-warps:
*/
static __cpuinitdata raw_spinlock_t sync_lock = __RAW_SPIN_LOCK_UNLOCKED;
+
static __cpuinitdata cycles_t last_tsc;
static __cpuinitdata cycles_t max_warp;
static __cpuinitdata int nr_warps;
@@ -113,13 +114,12 @@ void __cpuinit check_tsc_sync_source(int cpu)
return;
if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
- printk(KERN_INFO
- "Skipping synchronization checks as TSC is reliable.\n");
+ pr_info("Skipping synchronization checks as TSC is reliable.\n");
return;
}
- printk(KERN_INFO "checking TSC synchronization [CPU#%d -> CPU#%d]:",
- smp_processor_id(), cpu);
+ pr_info("checking TSC synchronization [CPU#%d -> CPU#%d]:",
+ smp_processor_id(), cpu);
/*
* Reset it - in case this is a second bootup:
@@ -143,8 +143,8 @@ void __cpuinit check_tsc_sync_source(int cpu)
if (nr_warps) {
printk("\n");
- printk(KERN_WARNING "Measured %Ld cycles TSC warp between CPUs,"
- " turning off TSC clock.\n", max_warp);
+ pr_warning("Measured %Ld cycles TSC warp between CPUs, "
+ "turning off TSC clock.\n", max_warp);
mark_tsc_unstable("check_tsc_sync_source failed");
} else {
printk(" passed.\n");
@@ -195,5 +195,3 @@ void __cpuinit check_tsc_sync_target(void)
while (atomic_read(&stop_count) != cpus)
cpu_relax();
}
-#undef NR_LOOPS
-
diff --git a/arch/x86/kernel/uv_sysfs.c b/arch/x86/kernel/uv_sysfs.c
index 67f9b9dbf80..36afb98675a 100644
--- a/arch/x86/kernel/uv_sysfs.c
+++ b/arch/x86/kernel/uv_sysfs.c
@@ -21,6 +21,7 @@
#include <linux/sysdev.h>
#include <asm/uv/bios.h>
+#include <asm/uv/uv.h>
struct kobject *sgi_uv_kobj;
@@ -47,6 +48,9 @@ static int __init sgi_uv_sysfs_init(void)
{
unsigned long ret;
+ if (!is_uv_system())
+ return -ENODEV;
+
if (!sgi_uv_kobj)
sgi_uv_kobj = kobject_create_and_add("sgi_uv", firmware_kobj);
if (!sgi_uv_kobj) {
diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 2ffb6c53326..583f11d5c48 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -29,7 +29,7 @@
#define RTC_NAME "sgi_rtc"
-static cycle_t uv_read_rtc(void);
+static cycle_t uv_read_rtc(struct clocksource *cs);
static int uv_rtc_next_event(unsigned long, struct clock_event_device *);
static void uv_rtc_timer_setup(enum clock_event_mode,
struct clock_event_device *);
@@ -123,7 +123,7 @@ static int uv_setup_intr(int cpu, u64 expires)
/* Initialize comparator value */
uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires);
- return (expires < uv_read_rtc() && !uv_intr_pending(pnode));
+ return (expires < uv_read_rtc(NULL) && !uv_intr_pending(pnode));
}
/*
@@ -256,7 +256,7 @@ static int uv_rtc_unset_timer(int cpu)
spin_lock_irqsave(&head->lock, flags);
- if (head->next_cpu == bcpu && uv_read_rtc() >= *t)
+ if (head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t)
rc = 1;
*t = ULLONG_MAX;
@@ -278,7 +278,7 @@ static int uv_rtc_unset_timer(int cpu)
/*
* Read the RTC.
*/
-static cycle_t uv_read_rtc(void)
+static cycle_t uv_read_rtc(struct clocksource *cs)
{
return (cycle_t)uv_read_local_mmr(UVH_RTC);
}
@@ -291,7 +291,7 @@ static int uv_rtc_next_event(unsigned long delta,
{
int ced_cpu = cpumask_first(ced->cpumask);
- return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc());
+ return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc(NULL));
}
/*
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index d7ac84e7fc1..b8035a0f404 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -318,9 +318,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
}
/*
- * Save old state, set default return value (%ax) to 0
+ * Save old state, set default return value (%ax) to 0 (VM86_SIGNAL)
*/
- info->regs32->ax = 0;
+ info->regs32->ax = VM86_SIGNAL;
tsk->thread.saved_sp0 = tsk->thread.sp0;
tsk->thread.saved_fs = info->regs32->fs;
tsk->thread.saved_gs = get_user_gs(info->regs32);
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index d303369a7ba..2b3eb82efee 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -283,7 +283,7 @@ void __devinit vmi_time_ap_init(void)
/** vmi clocksource */
static struct clocksource clocksource_vmi;
-static cycle_t read_real_cycles(void)
+static cycle_t read_real_cycles(struct clocksource *cs)
{
cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
return max(ret, clocksource_vmi.cycle_last);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 849ee611f01..4c85b2e2bb6 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -1,5 +1,431 @@
+/*
+ * ld script for the x86 kernel
+ *
+ * Historic 32-bit version written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *
+ * Modernisation, unification and other changes and fixes:
+ * Copyright (C) 2007-2009 Sam Ravnborg <sam@ravnborg.org>
+ *
+ *
+ * Don't define absolute symbols until and unless you know that symbol
+ * value is should remain constant even if kernel image is relocated
+ * at run time. Absolute symbols are not relocated. If symbol value should
+ * change if kernel is relocated, make the symbol section relative and
+ * put it inside the section definition.
+ */
+
#ifdef CONFIG_X86_32
-# include "vmlinux_32.lds.S"
+#define LOAD_OFFSET __PAGE_OFFSET
#else
-# include "vmlinux_64.lds.S"
+#define LOAD_OFFSET __START_KERNEL_map
#endif
+
+#include <asm-generic/vmlinux.lds.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page_types.h>
+#include <asm/cache.h>
+#include <asm/boot.h>
+
+#undef i386 /* in case the preprocessor is a 32bit one */
+
+OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
+
+#ifdef CONFIG_X86_32
+OUTPUT_ARCH(i386)
+ENTRY(phys_startup_32)
+jiffies = jiffies_64;
+#else
+OUTPUT_ARCH(i386:x86-64)
+ENTRY(phys_startup_64)
+jiffies_64 = jiffies;
+#endif
+
+PHDRS {
+ text PT_LOAD FLAGS(5); /* R_E */
+ data PT_LOAD FLAGS(7); /* RWE */
+#ifdef CONFIG_X86_64
+ user PT_LOAD FLAGS(7); /* RWE */
+ data.init PT_LOAD FLAGS(7); /* RWE */
+#ifdef CONFIG_SMP
+ percpu PT_LOAD FLAGS(7); /* RWE */
+#endif
+ data.init2 PT_LOAD FLAGS(7); /* RWE */
+#endif
+ note PT_NOTE FLAGS(0); /* ___ */
+}
+
+SECTIONS
+{
+#ifdef CONFIG_X86_32
+ . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
+ phys_startup_32 = startup_32 - LOAD_OFFSET;
+#else
+ . = __START_KERNEL;
+ phys_startup_64 = startup_64 - LOAD_OFFSET;
+#endif
+
+ /* Text and read-only data */
+
+ /* bootstrapping code */
+ .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
+ _text = .;
+ *(.text.head)
+ } :text = 0x9090
+
+ /* The rest of the text */
+ .text : AT(ADDR(.text) - LOAD_OFFSET) {
+#ifdef CONFIG_X86_32
+ /* not really needed, already page aligned */
+ . = ALIGN(PAGE_SIZE);
+ *(.text.page_aligned)
+#endif
+ . = ALIGN(8);
+ _stext = .;
+ TEXT_TEXT
+ SCHED_TEXT
+ LOCK_TEXT
+ KPROBES_TEXT
+ IRQENTRY_TEXT
+ *(.fixup)
+ *(.gnu.warning)
+ /* End of text section */
+ _etext = .;
+ } :text = 0x9090
+
+ NOTES :text :note
+
+ /* Exception table */
+ . = ALIGN(16);
+ __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
+ __start___ex_table = .;
+ *(__ex_table)
+ __stop___ex_table = .;
+ } :text = 0x9090
+
+ RODATA
+
+ /* Data */
+ . = ALIGN(PAGE_SIZE);
+ .data : AT(ADDR(.data) - LOAD_OFFSET) {
+ DATA_DATA
+ CONSTRUCTORS
+
+#ifdef CONFIG_X86_64
+ /* End of data section */
+ _edata = .;
+#endif
+ } :data
+
+#ifdef CONFIG_X86_32
+ /* 32 bit has nosave before _edata */
+ . = ALIGN(PAGE_SIZE);
+ .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+ __nosave_begin = .;
+ *(.data.nosave)
+ . = ALIGN(PAGE_SIZE);
+ __nosave_end = .;
+ }
+#endif
+
+ . = ALIGN(PAGE_SIZE);
+ .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
+ *(.data.page_aligned)
+ *(.data.idt)
+ }
+
+#ifdef CONFIG_X86_32
+ . = ALIGN(32);
+#else
+ . = ALIGN(PAGE_SIZE);
+ . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+#endif
+ .data.cacheline_aligned :
+ AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
+ *(.data.cacheline_aligned)
+ }
+
+ /* rarely changed data like cpu maps */
+#ifdef CONFIG_X86_32
+ . = ALIGN(32);
+#else
+ . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
+#endif
+ .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
+ *(.data.read_mostly)
+
+#ifdef CONFIG_X86_32
+ /* End of data section */
+ _edata = .;
+#endif
+ }
+
+#ifdef CONFIG_X86_64
+
+#define VSYSCALL_ADDR (-10*1024*1024)
+#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + \
+ SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + \
+ SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+
+#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
+#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
+
+#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
+#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
+
+ . = VSYSCALL_ADDR;
+ .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) {
+ *(.vsyscall_0)
+ } :user
+
+ __vsyscall_0 = VSYSCALL_VIRT_ADDR;
+
+ . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
+ *(.vsyscall_fn)
+ }
+
+ . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) {
+ *(.vsyscall_gtod_data)
+ }
+
+ vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
+ .vsyscall_clock : AT(VLOAD(.vsyscall_clock)) {
+ *(.vsyscall_clock)
+ }
+ vsyscall_clock = VVIRT(.vsyscall_clock);
+
+
+ .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) {
+ *(.vsyscall_1)
+ }
+ .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2)) {
+ *(.vsyscall_2)
+ }
+
+ .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) {
+ *(.vgetcpu_mode)
+ }
+ vgetcpu_mode = VVIRT(.vgetcpu_mode);
+
+ . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ .jiffies : AT(VLOAD(.jiffies)) {
+ *(.jiffies)
+ }
+ jiffies = VVIRT(.jiffies);
+
+ .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) {
+ *(.vsyscall_3)
+ }
+
+ . = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
+
+#undef VSYSCALL_ADDR
+#undef VSYSCALL_PHYS_ADDR
+#undef VSYSCALL_VIRT_ADDR
+#undef VLOAD_OFFSET
+#undef VLOAD
+#undef VVIRT_OFFSET
+#undef VVIRT
+
+#endif /* CONFIG_X86_64 */
+
+ /* init_task */
+ . = ALIGN(THREAD_SIZE);
+ .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
+ *(.data.init_task)
+ }
+#ifdef CONFIG_X86_64
+ :data.init
+#endif
+
+ /*
+ * smp_locks might be freed after init
+ * start/end must be page aligned
+ */
+ . = ALIGN(PAGE_SIZE);
+ .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
+ __smp_locks = .;
+ *(.smp_locks)
+ __smp_locks_end = .;
+ . = ALIGN(PAGE_SIZE);
+ }
+
+ /* Init code and data - will be freed after init */
+ . = ALIGN(PAGE_SIZE);
+ .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+ __init_begin = .; /* paired with __init_end */
+ _sinittext = .;
+ INIT_TEXT
+ _einittext = .;
+ }
+
+ .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
+ INIT_DATA
+ }
+
+ . = ALIGN(16);
+ .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
+ __setup_start = .;
+ *(.init.setup)
+ __setup_end = .;
+ }
+ .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
+ __initcall_start = .;
+ INITCALLS
+ __initcall_end = .;
+ }
+
+ .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
+ __con_initcall_start = .;
+ *(.con_initcall.init)
+ __con_initcall_end = .;
+ }
+
+ .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
+ __x86_cpu_dev_start = .;
+ *(.x86_cpu_dev.init)
+ __x86_cpu_dev_end = .;
+ }
+
+ SECURITY_INIT
+
+ . = ALIGN(8);
+ .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
+ __parainstructions = .;
+ *(.parainstructions)
+ __parainstructions_end = .;
+ }
+
+ . = ALIGN(8);
+ .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
+ __alt_instructions = .;
+ *(.altinstructions)
+ __alt_instructions_end = .;
+ }
+
+ .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
+ *(.altinstr_replacement)
+ }
+
+ /*
+ * .exit.text is discard at runtime, not link time, to deal with
+ * references from .altinstructions and .eh_frame
+ */
+ .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+ EXIT_TEXT
+ }
+
+ .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
+ EXIT_DATA
+ }
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ . = ALIGN(PAGE_SIZE);
+ .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
+ __initramfs_start = .;
+ *(.init.ramfs)
+ __initramfs_end = .;
+ }
+#endif
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
+ /*
+ * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
+ * output PHDR, so the next output section - __data_nosave - should
+ * start another section data.init2. Also, pda should be at the head of
+ * percpu area. Preallocate it and define the percpu offset symbol
+ * so that it can be accessed as a percpu variable.
+ */
+ . = ALIGN(PAGE_SIZE);
+ PERCPU_VADDR(0, :percpu)
+#else
+ PERCPU(PAGE_SIZE)
+#endif
+
+ . = ALIGN(PAGE_SIZE);
+
+ /* freed after init ends here */
+ .init.end : AT(ADDR(.init.end) - LOAD_OFFSET) {
+ __init_end = .;
+ }
+
+#ifdef CONFIG_X86_64
+ .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+ . = ALIGN(PAGE_SIZE);
+ __nosave_begin = .;
+ *(.data.nosave)
+ . = ALIGN(PAGE_SIZE);
+ __nosave_end = .;
+ } :data.init2
+ /* use another section data.init2, see PERCPU_VADDR() above */
+#endif
+
+ /* BSS */
+ . = ALIGN(PAGE_SIZE);
+ .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
+ __bss_start = .;
+ *(.bss.page_aligned)
+ *(.bss)
+ . = ALIGN(4);
+ __bss_stop = .;
+ }
+
+ . = ALIGN(PAGE_SIZE);
+ .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
+ __brk_base = .;
+ . += 64 * 1024; /* 64k alignment slop space */
+ *(.brk_reservation) /* areas brk users have reserved */
+ __brk_limit = .;
+ }
+
+ .end : AT(ADDR(.end) - LOAD_OFFSET) {
+ _end = .;
+ }
+
+ /* Sections to be discarded */
+ /DISCARD/ : {
+ *(.exitcall.exit)
+ *(.eh_frame)
+ *(.discard)
+ }
+
+ STABS_DEBUG
+ DWARF_DEBUG
+}
+
+
+#ifdef CONFIG_X86_32
+ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
+ "kernel image bigger than KERNEL_IMAGE_SIZE")
+#else
+/*
+ * Per-cpu symbols which need to be offset from __per_cpu_load
+ * for the boot processor.
+ */
+#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
+INIT_PER_CPU(gdt_page);
+INIT_PER_CPU(irq_stack_union);
+
+/*
+ * Build-time check on the image size:
+ */
+ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
+ "kernel image bigger than KERNEL_IMAGE_SIZE")
+
+#ifdef CONFIG_SMP
+ASSERT((per_cpu__irq_stack_union == 0),
+ "irq_stack_union is not at start of per-cpu area");
+#endif
+
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_KEXEC
+#include <asm/kexec.h>
+
+ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
+ "kexec control code size is too big")
+#endif
+
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
deleted file mode 100644
index 62ad500d55f..00000000000
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ /dev/null
@@ -1,229 +0,0 @@
-/* ld script to make i386 Linux kernel
- * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
- *
- * Don't define absolute symbols until and unless you know that symbol
- * value is should remain constant even if kernel image is relocated
- * at run time. Absolute symbols are not relocated. If symbol value should
- * change if kernel is relocated, make the symbol section relative and
- * put it inside the section definition.
- */
-
-#define LOAD_OFFSET __PAGE_OFFSET
-
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/thread_info.h>
-#include <asm/page_types.h>
-#include <asm/cache.h>
-#include <asm/boot.h>
-
-OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
-OUTPUT_ARCH(i386)
-ENTRY(phys_startup_32)
-jiffies = jiffies_64;
-
-PHDRS {
- text PT_LOAD FLAGS(5); /* R_E */
- data PT_LOAD FLAGS(7); /* RWE */
- note PT_NOTE FLAGS(0); /* ___ */
-}
-SECTIONS
-{
- . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
- phys_startup_32 = startup_32 - LOAD_OFFSET;
-
- .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
- _text = .; /* Text and read-only data */
- *(.text.head)
- } :text = 0x9090
-
- /* read-only */
- .text : AT(ADDR(.text) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE); /* not really needed, already page aligned */
- *(.text.page_aligned)
- TEXT_TEXT
- SCHED_TEXT
- LOCK_TEXT
- KPROBES_TEXT
- IRQENTRY_TEXT
- *(.fixup)
- *(.gnu.warning)
- _etext = .; /* End of text section */
- } :text = 0x9090
-
- NOTES :text :note
-
- . = ALIGN(16); /* Exception table */
- __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
- __start___ex_table = .;
- *(__ex_table)
- __stop___ex_table = .;
- } :text = 0x9090
-
- RODATA
-
- /* writeable */
- . = ALIGN(PAGE_SIZE);
- .data : AT(ADDR(.data) - LOAD_OFFSET) { /* Data */
- DATA_DATA
- CONSTRUCTORS
- } :data
-
- . = ALIGN(PAGE_SIZE);
- .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
- __nosave_begin = .;
- *(.data.nosave)
- . = ALIGN(PAGE_SIZE);
- __nosave_end = .;
- }
-
- . = ALIGN(PAGE_SIZE);
- .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
- *(.data.page_aligned)
- *(.data.idt)
- }
-
- . = ALIGN(32);
- .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
- *(.data.cacheline_aligned)
- }
-
- /* rarely changed data like cpu maps */
- . = ALIGN(32);
- .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
- *(.data.read_mostly)
- _edata = .; /* End of data section */
- }
-
- . = ALIGN(THREAD_SIZE); /* init_task */
- .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
- *(.data.init_task)
- }
-
- /* might get freed after init */
- . = ALIGN(PAGE_SIZE);
- .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
- __smp_locks = .;
- *(.smp_locks)
- __smp_locks_end = .;
- }
- /* will be freed after init
- * Following ALIGN() is required to make sure no other data falls on the
- * same page where __smp_alt_end is pointing as that page might be freed
- * after boot. Always make sure that ALIGN() directive is present after
- * the section which contains __smp_alt_end.
- */
- . = ALIGN(PAGE_SIZE);
-
- /* will be freed after init */
- . = ALIGN(PAGE_SIZE); /* Init code and data */
- .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
- __init_begin = .;
- _sinittext = .;
- INIT_TEXT
- _einittext = .;
- }
- .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
- INIT_DATA
- }
- . = ALIGN(16);
- .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
- __setup_start = .;
- *(.init.setup)
- __setup_end = .;
- }
- .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
- __initcall_start = .;
- INITCALLS
- __initcall_end = .;
- }
- .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
- __con_initcall_start = .;
- *(.con_initcall.init)
- __con_initcall_end = .;
- }
- .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
- __x86_cpu_dev_start = .;
- *(.x86_cpu_dev.init)
- __x86_cpu_dev_end = .;
- }
- SECURITY_INIT
- . = ALIGN(4);
- .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
- __alt_instructions = .;
- *(.altinstructions)
- __alt_instructions_end = .;
- }
- .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
- *(.altinstr_replacement)
- }
- . = ALIGN(4);
- .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
- __parainstructions = .;
- *(.parainstructions)
- __parainstructions_end = .;
- }
- /* .exit.text is discard at runtime, not link time, to deal with references
- from .altinstructions and .eh_frame */
- .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
- EXIT_TEXT
- }
- .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
- EXIT_DATA
- }
-#if defined(CONFIG_BLK_DEV_INITRD)
- . = ALIGN(PAGE_SIZE);
- .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
- __initramfs_start = .;
- *(.init.ramfs)
- __initramfs_end = .;
- }
-#endif
- PERCPU(PAGE_SIZE)
- . = ALIGN(PAGE_SIZE);
- /* freed after init ends here */
-
- .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
- __init_end = .;
- __bss_start = .; /* BSS */
- *(.bss.page_aligned)
- *(.bss)
- . = ALIGN(4);
- __bss_stop = .;
- }
-
- .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __brk_base = . ;
- . += 64 * 1024 ; /* 64k alignment slop space */
- *(.brk_reservation) /* areas brk users have reserved */
- __brk_limit = . ;
- }
-
- .end : AT(ADDR(.end) - LOAD_OFFSET) {
- _end = . ;
- }
-
- /* Sections to be discarded */
- /DISCARD/ : {
- *(.exitcall.exit)
- *(.discard)
- }
-
- STABS_DEBUG
-
- DWARF_DEBUG
-}
-
-/*
- * Build-time check on the image size:
- */
-ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
- "kernel image bigger than KERNEL_IMAGE_SIZE")
-
-#ifdef CONFIG_KEXEC
-/* Link time checks */
-#include <asm/kexec.h>
-
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
- "kexec control code size is too big")
-#endif
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
deleted file mode 100644
index c8742507b03..00000000000
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ /dev/null
@@ -1,298 +0,0 @@
-/* ld script to make x86-64 Linux kernel
- * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
- */
-
-#define LOAD_OFFSET __START_KERNEL_map
-
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/asm-offsets.h>
-#include <asm/page_types.h>
-
-#undef i386 /* in case the preprocessor is a 32bit one */
-
-OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
-OUTPUT_ARCH(i386:x86-64)
-ENTRY(phys_startup_64)
-jiffies_64 = jiffies;
-PHDRS {
- text PT_LOAD FLAGS(5); /* R_E */
- data PT_LOAD FLAGS(7); /* RWE */
- user PT_LOAD FLAGS(7); /* RWE */
- data.init PT_LOAD FLAGS(7); /* RWE */
-#ifdef CONFIG_SMP
- percpu PT_LOAD FLAGS(7); /* RWE */
-#endif
- data.init2 PT_LOAD FLAGS(7); /* RWE */
- note PT_NOTE FLAGS(0); /* ___ */
-}
-SECTIONS
-{
- . = __START_KERNEL;
- phys_startup_64 = startup_64 - LOAD_OFFSET;
- .text : AT(ADDR(.text) - LOAD_OFFSET) {
- _text = .; /* Text and read-only data */
- /* First the code that has to be first for bootstrapping */
- *(.text.head)
- _stext = .;
- /* Then the rest */
- TEXT_TEXT
- SCHED_TEXT
- LOCK_TEXT
- KPROBES_TEXT
- IRQENTRY_TEXT
- *(.fixup)
- *(.gnu.warning)
- _etext = .; /* End of text section */
- } :text = 0x9090
-
- NOTES :text :note
-
- . = ALIGN(16); /* Exception table */
- __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
- __start___ex_table = .;
- *(__ex_table)
- __stop___ex_table = .;
- } :text = 0x9090
-
- RODATA
-
- . = ALIGN(PAGE_SIZE); /* Align data segment to page size boundary */
- /* Data */
- .data : AT(ADDR(.data) - LOAD_OFFSET) {
- DATA_DATA
- CONSTRUCTORS
- _edata = .; /* End of data section */
- } :data
-
-
- .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- *(.data.cacheline_aligned)
- }
- . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
- .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
- *(.data.read_mostly)
- }
-
-#define VSYSCALL_ADDR (-10*1024*1024)
-#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-
-#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
-#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
-
-#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
-#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
-
- . = VSYSCALL_ADDR;
- .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) { *(.vsyscall_0) } :user
- __vsyscall_0 = VSYSCALL_VIRT_ADDR;
-
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) }
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data))
- { *(.vsyscall_gtod_data) }
- vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
- .vsyscall_clock : AT(VLOAD(.vsyscall_clock))
- { *(.vsyscall_clock) }
- vsyscall_clock = VVIRT(.vsyscall_clock);
-
-
- .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
- { *(.vsyscall_1) }
- .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2))
- { *(.vsyscall_2) }
-
- .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) }
- vgetcpu_mode = VVIRT(.vgetcpu_mode);
-
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- .jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) }
- jiffies = VVIRT(.jiffies);
-
- .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3))
- { *(.vsyscall_3) }
-
- . = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
-
-#undef VSYSCALL_ADDR
-#undef VSYSCALL_PHYS_ADDR
-#undef VSYSCALL_VIRT_ADDR
-#undef VLOAD_OFFSET
-#undef VLOAD
-#undef VVIRT_OFFSET
-#undef VVIRT
-
- .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
- . = ALIGN(THREAD_SIZE); /* init_task */
- *(.data.init_task)
- }:data.init
-
- .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- *(.data.page_aligned)
- }
-
- .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
- /* might get freed after init */
- . = ALIGN(PAGE_SIZE);
- __smp_alt_begin = .;
- __smp_locks = .;
- *(.smp_locks)
- __smp_locks_end = .;
- . = ALIGN(PAGE_SIZE);
- __smp_alt_end = .;
- }
-
- . = ALIGN(PAGE_SIZE); /* Init code and data */
- __init_begin = .; /* paired with __init_end */
- .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
- _sinittext = .;
- INIT_TEXT
- _einittext = .;
- }
- .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
- __initdata_begin = .;
- INIT_DATA
- __initdata_end = .;
- }
-
- .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
- . = ALIGN(16);
- __setup_start = .;
- *(.init.setup)
- __setup_end = .;
- }
- .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
- __initcall_start = .;
- INITCALLS
- __initcall_end = .;
- }
- .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
- __con_initcall_start = .;
- *(.con_initcall.init)
- __con_initcall_end = .;
- }
- .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
- __x86_cpu_dev_start = .;
- *(.x86_cpu_dev.init)
- __x86_cpu_dev_end = .;
- }
- SECURITY_INIT
-
- . = ALIGN(8);
- .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
- __parainstructions = .;
- *(.parainstructions)
- __parainstructions_end = .;
- }
-
- .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
- . = ALIGN(8);
- __alt_instructions = .;
- *(.altinstructions)
- __alt_instructions_end = .;
- }
- .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
- *(.altinstr_replacement)
- }
- /* .exit.text is discard at runtime, not link time, to deal with references
- from .altinstructions and .eh_frame */
- .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
- EXIT_TEXT
- }
- .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
- EXIT_DATA
- }
-
-#ifdef CONFIG_BLK_DEV_INITRD
- . = ALIGN(PAGE_SIZE);
- .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
- __initramfs_start = .;
- *(.init.ramfs)
- __initramfs_end = .;
- }
-#endif
-
-#ifdef CONFIG_SMP
- /*
- * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
- * output PHDR, so the next output section - __data_nosave - should
- * start another section data.init2. Also, pda should be at the head of
- * percpu area. Preallocate it and define the percpu offset symbol
- * so that it can be accessed as a percpu variable.
- */
- . = ALIGN(PAGE_SIZE);
- PERCPU_VADDR(0, :percpu)
-#else
- PERCPU(PAGE_SIZE)
-#endif
-
- . = ALIGN(PAGE_SIZE);
- __init_end = .;
-
- .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __nosave_begin = .;
- *(.data.nosave)
- . = ALIGN(PAGE_SIZE);
- __nosave_end = .;
- } :data.init2 /* use another section data.init2, see PERCPU_VADDR() above */
-
- .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __bss_start = .; /* BSS */
- *(.bss.page_aligned)
- *(.bss)
- __bss_stop = .;
- }
-
- .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __brk_base = . ;
- . += 64 * 1024 ; /* 64k alignment slop space */
- *(.brk_reservation) /* areas brk users have reserved */
- __brk_limit = . ;
- }
-
- _end = . ;
-
- /* Sections to be discarded */
- /DISCARD/ : {
- *(.exitcall.exit)
- *(.eh_frame)
- *(.discard)
- }
-
- STABS_DEBUG
-
- DWARF_DEBUG
-}
-
- /*
- * Per-cpu symbols which need to be offset from __per_cpu_load
- * for the boot processor.
- */
-#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
-INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_union);
-
-/*
- * Build-time check on the image size:
- */
-ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
- "kernel image bigger than KERNEL_IMAGE_SIZE")
-
-#ifdef CONFIG_SMP
-ASSERT((per_cpu__irq_stack_union == 0),
- "irq_stack_union is not at start of per-cpu area");
-#endif
-
-#ifdef CONFIG_KEXEC
-#include <asm/kexec.h>
-
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
- "kexec control code size is too big")
-#endif
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 2b54fe002e9..c5ee17e8c6d 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -89,7 +89,7 @@ int save_i387_xstate(void __user *buf)
if (!used_math())
return 0;
- clear_used_math(); /* trigger finit */
+
if (task_thread_info(tsk)->status & TS_USEDFPU) {
/*
* Start with clearing the user buffer. This will present a
@@ -114,6 +114,8 @@ int save_i387_xstate(void __user *buf)
return -1;
}
+ clear_used_math(); /* trigger finit */
+
if (task_thread_info(tsk)->status & TS_XSAVE) {
struct _fpstate __user *fx = buf;
struct _xstate __user *x = buf;
@@ -324,7 +326,7 @@ void __ref xsave_cntxt_init(void)
}
/*
- * for now OS knows only about FP/SSE
+ * Support only the state known to OS.
*/
pcntxt_mask = pcntxt_mask & XCNTXT_MASK;
xsave_init();