summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile25
-rw-r--r--arch/x86/kernel/acpi/boot.c121
-rw-r--r--arch/x86/kernel/acpi/sleep.c1
-rw-r--r--arch/x86/kernel/apic.c142
-rw-r--r--arch/x86/kernel/apm_32.c2
-rw-r--r--arch/x86/kernel/asm-offsets_64.c11
-rw-r--r--arch/x86/kernel/bigsmp_32.c266
-rw-r--r--arch/x86/kernel/cpu/addon_cpuid_features.c54
-rw-r--r--arch/x86/kernel/cpu/amd.c2
-rw-r--r--arch/x86/kernel/cpu/common.c223
-rw-r--r--arch/x86/kernel/cpu/intel.c14
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c63
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd_64.c21
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel_64.c1
-rw-r--r--arch/x86/kernel/crash.c4
-rw-r--r--arch/x86/kernel/dumpstack_64.c35
-rw-r--r--arch/x86/kernel/efi.c2
-rw-r--r--arch/x86/kernel/efi_64.c1
-rw-r--r--arch/x86/kernel/entry_32.S8
-rw-r--r--arch/x86/kernel/entry_64.S45
-rw-r--r--arch/x86/kernel/es7000_32.c468
-rw-r--r--arch/x86/kernel/genapic_64.c24
-rw-r--r--arch/x86/kernel/genapic_flat_64.c176
-rw-r--r--arch/x86/kernel/genx2apic_cluster.c133
-rw-r--r--arch/x86/kernel/genx2apic_phys.c125
-rw-r--r--arch/x86/kernel/genx2apic_uv_x.c112
-rw-r--r--arch/x86/kernel/head64.c23
-rw-r--r--arch/x86/kernel/head_32.S19
-rw-r--r--arch/x86/kernel/head_64.S36
-rw-r--r--arch/x86/kernel/io_apic.c369
-rw-r--r--arch/x86/kernel/ipi.c176
-rw-r--r--arch/x86/kernel/irq.c6
-rw-r--r--arch/x86/kernel/irq_32.c4
-rw-r--r--arch/x86/kernel/irq_64.c9
-rw-r--r--arch/x86/kernel/irqinit_32.c23
-rw-r--r--arch/x86/kernel/kgdb.c4
-rw-r--r--arch/x86/kernel/microcode_intel.c10
-rw-r--r--arch/x86/kernel/module_32.c6
-rw-r--r--arch/x86/kernel/module_64.c32
-rw-r--r--arch/x86/kernel/mpparse.c172
-rw-r--r--arch/x86/kernel/msr.c2
-rw-r--r--arch/x86/kernel/nmi.c12
-rw-r--r--arch/x86/kernel/numaq_32.c278
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c10
-rw-r--r--arch/x86/kernel/paravirt.c1
-rw-r--r--arch/x86/kernel/probe_32.c411
-rw-r--r--arch/x86/kernel/probe_roms_32.c2
-rw-r--r--arch/x86/kernel/process.c2
-rw-r--r--arch/x86/kernel/process_32.c6
-rw-r--r--arch/x86/kernel/process_64.c43
-rw-r--r--arch/x86/kernel/reboot.c5
-rw-r--r--arch/x86/kernel/setup.c32
-rw-r--r--arch/x86/kernel/setup_percpu.c412
-rw-r--r--arch/x86/kernel/signal.c291
-rw-r--r--arch/x86/kernel/smp.c15
-rw-r--r--arch/x86/kernel/smpboot.c115
-rw-r--r--arch/x86/kernel/smpcommon.c30
-rw-r--r--arch/x86/kernel/stacktrace.c2
-rw-r--r--arch/x86/kernel/summit_32.c416
-rw-r--r--arch/x86/kernel/time_32.c2
-rw-r--r--arch/x86/kernel/tlb_32.c256
-rw-r--r--arch/x86/kernel/tlb_64.c284
-rw-r--r--arch/x86/kernel/tlb_uv.c70
-rw-r--r--arch/x86/kernel/traps.c3
-rw-r--r--arch/x86/kernel/tsc.c2
-rw-r--r--arch/x86/kernel/visws_quirks.c6
-rw-r--r--arch/x86/kernel/vmiclock_32.c2
-rw-r--r--arch/x86/kernel/vmlinux_32.lds.S9
-rw-r--r--arch/x86/kernel/vmlinux_64.lds.S26
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c2
70 files changed, 3421 insertions, 2294 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d364df03c1d6..24f357e7557a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -23,13 +23,14 @@ nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp)
CFLAGS_hpet.o := $(nostackp)
CFLAGS_tsc.o := $(nostackp)
+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_$(BITS).o setup_percpu.o
+obj-y += setup.o i8259.o irqinit_$(BITS).o
obj-$(CONFIG_X86_VISWS) += visws_quirks.o
-obj-$(CONFIG_X86_32) += probe_roms_32.o
+obj-$(CONFIG_X86_32) += probe_32.o probe_roms_32.o
obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o
@@ -49,20 +50,20 @@ obj-y += step.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += cpu/
obj-y += acpi/
-obj-$(CONFIG_X86_BIOS_REBOOT) += reboot.o
+obj-y += reboot.o
obj-$(CONFIG_MCA) += mca_32.o
obj-$(CONFIG_X86_MSR) += msr.o
obj-$(CONFIG_X86_CPUID) += cpuid.o
obj-$(CONFIG_PCI) += early-quirks.o
apm-y := apm_32.o
obj-$(CONFIG_APM) += apm.o
-obj-$(CONFIG_X86_SMP) += smp.o
-obj-$(CONFIG_X86_SMP) += smpboot.o tsc_sync.o ipi.o tlb_$(BITS).o
-obj-$(CONFIG_X86_32_SMP) += smpcommon.o
-obj-$(CONFIG_X86_64_SMP) += tsc_sync.o smpcommon.o
+obj-$(CONFIG_SMP) += smp.o
+obj-$(CONFIG_SMP) += smpboot.o tsc_sync.o ipi.o
+obj-$(CONFIG_SMP) += setup_percpu.o
+obj-$(CONFIG_X86_64_SMP) += tsc_sync.o
obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_$(BITS).o
obj-$(CONFIG_X86_MPPARSE) += mpparse.o
-obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o
+obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o ipi.o
obj-$(CONFIG_X86_IO_APIC) += io_apic.o
obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
@@ -70,9 +71,10 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o
obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
+obj-$(CONFIG_X86_BIGSMP) += bigsmp_32.o
obj-$(CONFIG_X86_NUMAQ) += numaq_32.o
obj-$(CONFIG_X86_ES7000) += es7000_32.o
-obj-$(CONFIG_X86_SUMMIT_NUMA) += summit_32.o
+obj-$(CONFIG_X86_SUMMIT) += summit_32.o
obj-y += vsmp_64.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_MODULES) += module_$(BITS).o
@@ -114,10 +116,11 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o # NB rename without _64
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
- obj-y += genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
- obj-y += bios_uv.o uv_irq.o uv_sysfs.o
+ obj-y += genapic_64.o genapic_flat_64.o
obj-y += genx2apic_cluster.o
obj-y += genx2apic_phys.o
+ obj-$(CONFIG_X86_UV) += genx2apic_uv_x.o tlb_uv.o
+ obj-$(CONFIG_X86_UV) += bios_uv.o uv_irq.o uv_sysfs.o
obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o
obj-$(CONFIG_AUDIT) += audit_64.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d37593c2f438..3efa996b036c 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -42,10 +42,6 @@
#include <asm/mpspec.h>
#include <asm/smp.h>
-#ifdef CONFIG_X86_LOCAL_APIC
-# include <mach_apic.h>
-#endif
-
static int __initdata acpi_force = 0;
u32 acpi_rsdt_forced;
#ifdef CONFIG_ACPI
@@ -56,16 +52,7 @@ int acpi_disabled = 1;
EXPORT_SYMBOL(acpi_disabled);
#ifdef CONFIG_X86_64
-
-#include <asm/proto.h>
-
-#else /* X86 */
-
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <mach_apic.h>
-#include <mach_mpparse.h>
-#endif /* CONFIG_X86_LOCAL_APIC */
-
+# include <asm/proto.h>
#endif /* X86 */
#define BAD_MADT_ENTRY(entry, end) ( \
@@ -239,7 +226,8 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
madt->address);
}
- acpi_madt_oem_check(madt->header.oem_id, madt->header.oem_table_id);
+ default_acpi_madt_oem_check(madt->header.oem_id,
+ madt->header.oem_table_id);
return 0;
}
@@ -912,8 +900,8 @@ static u8 __init uniq_ioapic_id(u8 id)
DECLARE_BITMAP(used, 256);
bitmap_zero(used, 256);
for (i = 0; i < nr_ioapics; i++) {
- struct mp_config_ioapic *ia = &mp_ioapics[i];
- __set_bit(ia->mp_apicid, used);
+ struct mpc_ioapic *ia = &mp_ioapics[i];
+ __set_bit(ia->apicid, used);
}
if (!test_bit(id, used))
return id;
@@ -945,47 +933,47 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
idx = nr_ioapics;
- mp_ioapics[idx].mp_type = MP_IOAPIC;
- mp_ioapics[idx].mp_flags = MPC_APIC_USABLE;
- mp_ioapics[idx].mp_apicaddr = address;
+ mp_ioapics[idx].type = MP_IOAPIC;
+ mp_ioapics[idx].flags = MPC_APIC_USABLE;
+ mp_ioapics[idx].apicaddr = address;
set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
- mp_ioapics[idx].mp_apicid = uniq_ioapic_id(id);
+ mp_ioapics[idx].apicid = uniq_ioapic_id(id);
#ifdef CONFIG_X86_32
- mp_ioapics[idx].mp_apicver = io_apic_get_version(idx);
+ mp_ioapics[idx].apicver = io_apic_get_version(idx);
#else
- mp_ioapics[idx].mp_apicver = 0;
+ 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].mp_apicid;
+ 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);
- printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%lx, "
- "GSI %d-%d\n", idx, mp_ioapics[idx].mp_apicid,
- mp_ioapics[idx].mp_apicver, mp_ioapics[idx].mp_apicaddr,
+ printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, "
+ "GSI %d-%d\n", idx, mp_ioapics[idx].apicid,
+ mp_ioapics[idx].apicver, mp_ioapics[idx].apicaddr,
mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end);
nr_ioapics++;
}
-static void assign_to_mp_irq(struct mp_config_intsrc *m,
- struct mp_config_intsrc *mp_irq)
+static void assign_to_mp_irq(struct mpc_intsrc *m,
+ struct mpc_intsrc *mp_irq)
{
- memcpy(mp_irq, m, sizeof(struct mp_config_intsrc));
+ memcpy(mp_irq, m, sizeof(struct mpc_intsrc));
}
-static int mp_irq_cmp(struct mp_config_intsrc *mp_irq,
- struct mp_config_intsrc *m)
+static int mp_irq_cmp(struct mpc_intsrc *mp_irq,
+ struct mpc_intsrc *m)
{
- return memcmp(mp_irq, m, sizeof(struct mp_config_intsrc));
+ return memcmp(mp_irq, m, sizeof(struct mpc_intsrc));
}
-static void save_mp_irq(struct mp_config_intsrc *m)
+static void save_mp_irq(struct mpc_intsrc *m)
{
int i;
@@ -1003,7 +991,7 @@ void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
{
int ioapic;
int pin;
- struct mp_config_intsrc mp_irq;
+ struct mpc_intsrc mp_irq;
/*
* Convert 'gsi' to 'ioapic.pin'.
@@ -1021,13 +1009,13 @@ void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
if ((bus_irq == 0) && (trigger == 3))
trigger = 1;
- mp_irq.mp_type = MP_INTSRC;
- mp_irq.mp_irqtype = mp_INT;
- mp_irq.mp_irqflag = (trigger << 2) | polarity;
- mp_irq.mp_srcbus = MP_ISA_BUS;
- mp_irq.mp_srcbusirq = bus_irq; /* IRQ */
- mp_irq.mp_dstapic = mp_ioapics[ioapic].mp_apicid; /* APIC ID */
- mp_irq.mp_dstirq = pin; /* INTIN# */
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.irqflag = (trigger << 2) | polarity;
+ mp_irq.srcbus = MP_ISA_BUS;
+ mp_irq.srcbusirq = bus_irq; /* IRQ */
+ mp_irq.dstapic = mp_ioapics[ioapic].apicid; /* APIC ID */
+ mp_irq.dstirq = pin; /* INTIN# */
save_mp_irq(&mp_irq);
}
@@ -1037,7 +1025,7 @@ void __init mp_config_acpi_legacy_irqs(void)
int i;
int ioapic;
unsigned int dstapic;
- struct mp_config_intsrc mp_irq;
+ struct mpc_intsrc mp_irq;
#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
/*
@@ -1062,7 +1050,7 @@ void __init mp_config_acpi_legacy_irqs(void)
ioapic = mp_find_ioapic(0);
if (ioapic < 0)
return;
- dstapic = mp_ioapics[ioapic].mp_apicid;
+ dstapic = mp_ioapics[ioapic].apicid;
/*
* Use the default configuration for the IRQs 0-15. Unless
@@ -1072,16 +1060,14 @@ void __init mp_config_acpi_legacy_irqs(void)
int idx;
for (idx = 0; idx < mp_irq_entries; idx++) {
- struct mp_config_intsrc *irq = mp_irqs + idx;
+ struct mpc_intsrc *irq = mp_irqs + idx;
/* Do we already have a mapping for this ISA IRQ? */
- if (irq->mp_srcbus == MP_ISA_BUS
- && irq->mp_srcbusirq == i)
+ if (irq->srcbus == MP_ISA_BUS && irq->srcbusirq == i)
break;
/* Do we already have a mapping for this IOAPIC pin */
- if (irq->mp_dstapic == dstapic &&
- irq->mp_dstirq == i)
+ if (irq->dstapic == dstapic && irq->dstirq == i)
break;
}
@@ -1090,13 +1076,13 @@ void __init mp_config_acpi_legacy_irqs(void)
continue; /* IRQ already used */
}
- mp_irq.mp_type = MP_INTSRC;
- mp_irq.mp_irqflag = 0; /* Conforming */
- mp_irq.mp_srcbus = MP_ISA_BUS;
- mp_irq.mp_dstapic = dstapic;
- mp_irq.mp_irqtype = mp_INT;
- mp_irq.mp_srcbusirq = i; /* Identity mapped */
- mp_irq.mp_dstirq = i;
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqflag = 0; /* Conforming */
+ mp_irq.srcbus = MP_ISA_BUS;
+ mp_irq.dstapic = dstapic;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.srcbusirq = i; /* Identity mapped */
+ mp_irq.dstirq = i;
save_mp_irq(&mp_irq);
}
@@ -1207,22 +1193,22 @@ int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
u32 gsi, int triggering, int polarity)
{
#ifdef CONFIG_X86_MPPARSE
- struct mp_config_intsrc mp_irq;
+ struct mpc_intsrc mp_irq;
int ioapic;
if (!acpi_ioapic)
return 0;
/* print the entry should happen on mptable identically */
- mp_irq.mp_type = MP_INTSRC;
- mp_irq.mp_irqtype = mp_INT;
- mp_irq.mp_irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+ 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.mp_srcbus = number;
- mp_irq.mp_srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+ mp_irq.srcbus = number;
+ mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
ioapic = mp_find_ioapic(gsi);
- mp_irq.mp_dstapic = mp_ioapic_routing[ioapic].apic_id;
- mp_irq.mp_dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base;
+ mp_irq.dstapic = mp_ioapic_routing[ioapic].apic_id;
+ mp_irq.dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base;
save_mp_irq(&mp_irq);
#endif
@@ -1349,7 +1335,7 @@ static void __init acpi_process_madt(void)
if (!error) {
acpi_lapic = 1;
-#ifdef CONFIG_X86_GENERICARCH
+#ifdef CONFIG_X86_BIGSMP
generic_bigsmp_probe();
#endif
/*
@@ -1361,9 +1347,8 @@ static void __init acpi_process_madt(void)
acpi_ioapic = 1;
smp_found_config = 1;
-#ifdef CONFIG_X86_32
- setup_apic_routing();
-#endif
+ if (apic->setup_apic_routing)
+ apic->setup_apic_routing();
}
}
if (error == -EINVAL) {
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 707c1f6f95fa..4abff454c55b 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -101,6 +101,7 @@ int acpi_save_state_mem(void)
stack_start.sp = temp_stack + sizeof(temp_stack);
early_gdt_descr.address =
(unsigned long)get_cpu_gdt_table(smp_processor_id());
+ initial_gs = per_cpu_offset(smp_processor_id());
#endif
initial_code = (unsigned long)wakeup_long64;
saved_magic = 0x123456789abcdef0;
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 115449f869ee..8bd801db24d9 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -1,7 +1,7 @@
/*
* Local APIC handling, local APIC timers
*
- * (c) 1999, 2000 Ingo Molnar <mingo@redhat.com>
+ * (c) 1999, 2000, 2009 Ingo Molnar <mingo@redhat.com>
*
* Fixes
* Maciej W. Rozycki : Bits for genuine 82489DX APICs;
@@ -14,51 +14,71 @@
* Mikael Pettersson : PM converted to driver model.
*/
-#include <linux/init.h>
-
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/bootmem.h>
-#include <linux/interrupt.h>
-#include <linux/mc146818rtc.h>
#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/ioport.h>
-#include <linux/cpu.h>
-#include <linux/clockchips.h>
+#include <linux/mc146818rtc.h>
#include <linux/acpi_pmtmr.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/bootmem.h>
+#include <linux/ftrace.h>
+#include <linux/ioport.h>
#include <linux/module.h>
-#include <linux/dmi.h>
+#include <linux/sysdev.h>
+#include <linux/delay.h>
+#include <linux/timex.h>
#include <linux/dmar.h>
-#include <linux/ftrace.h>
-#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/dmi.h>
#include <linux/nmi.h>
-#include <linux/timex.h>
+#include <linux/smp.h>
+#include <linux/mm.h>
-#include <asm/atomic.h>
-#include <asm/mtrr.h>
-#include <asm/mpspec.h>
-#include <asm/desc.h>
#include <asm/arch_hooks.h>
-#include <asm/hpet.h>
#include <asm/pgalloc.h>
+#include <asm/genapic.h>
+#include <asm/atomic.h>
+#include <asm/mpspec.h>
#include <asm/i8253.h>
-#include <asm/idle.h>
+#include <asm/i8259.h>
#include <asm/proto.h>
#include <asm/apic.h>
-#include <asm/i8259.h>
+#include <asm/desc.h>
+#include <asm/hpet.h>
+#include <asm/idle.h>
+#include <asm/mtrr.h>
#include <asm/smp.h>
-#include <mach_apic.h>
-#include <mach_apicdef.h>
-#include <mach_ipi.h>
+unsigned int num_processors;
+
+unsigned disabled_cpus __cpuinitdata;
+
+/* Processor that is doing the boot up */
+unsigned int boot_cpu_physical_apicid = -1U;
/*
- * Sanity check
+ * The highest APIC ID seen during enumeration.
+ *
+ * This determines the messaging protocol we can use: if all APIC IDs
+ * are in the 0 ... 7 range, then we can use logical addressing which
+ * has some performance advantages (better broadcasting).
+ *
+ * If there's an APIC ID above 8, we use physical addressing.
*/
-#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F)
-# error SPURIOUS_APIC_VECTOR definition error
-#endif
+unsigned int max_physical_apicid;
+
+/*
+ * Bitmask of physically existing CPUs:
+ */
+physid_mask_t phys_cpu_present_map;
+
+/*
+ * Map cpu index to physical APIC ID
+ */
+DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
#ifdef CONFIG_X86_32
/*
@@ -457,7 +477,7 @@ static void lapic_timer_setup(enum clock_event_mode mode,
static void lapic_timer_broadcast(const struct cpumask *mask)
{
#ifdef CONFIG_SMP
- send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
+ apic->send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
#endif
}
@@ -991,11 +1011,11 @@ int __init verify_local_APIC(void)
*/
reg0 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
- apic_write(APIC_ID, reg0 ^ APIC_ID_MASK);
+ apic_write(APIC_ID, reg0 ^ apic->apic_id_mask);
reg1 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
apic_write(APIC_ID, reg0);
- if (reg1 != (reg0 ^ APIC_ID_MASK))
+ if (reg1 != (reg0 ^ apic->apic_id_mask))
return 0;
/*
@@ -1089,7 +1109,7 @@ static void __cpuinit lapic_setup_esr(void)
return;
}
- if (esr_disable) {
+ if (apic->disable_esr) {
/*
* Something untraceable is creating bad interrupts on
* secondary quads ... for the moment, just leave the
@@ -1130,9 +1150,14 @@ void __cpuinit setup_local_APIC(void)
unsigned int value;
int i, j;
+ if (disable_apic) {
+ arch_disable_smp_support();
+ return;
+ }
+
#ifdef CONFIG_X86_32
/* Pound the ESR really hard over the head with a big hammer - mbligh */
- if (lapic_is_integrated() && esr_disable) {
+ if (lapic_is_integrated() && apic->disable_esr) {
apic_write(APIC_ESR, 0);
apic_write(APIC_ESR, 0);
apic_write(APIC_ESR, 0);
@@ -1146,7 +1171,7 @@ void __cpuinit setup_local_APIC(void)
* Double-check whether this APIC is really registered.
* This is meaningless in clustered apic mode, so we skip it.
*/
- if (!apic_id_registered())
+ if (!apic->apic_id_registered())
BUG();
/*
@@ -1154,7 +1179,7 @@ void __cpuinit setup_local_APIC(void)
* an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
* document number 292116). So here it goes...
*/
- init_apic_ldr();
+ apic->init_apic_ldr();
/*
* Set Task Priority to 'accept all'. We never change this
@@ -1570,11 +1595,11 @@ int apic_version[MAX_APICS];
int __init APIC_init_uniprocessor(void)
{
-#ifdef CONFIG_X86_64
if (disable_apic) {
pr_info("Apic disabled\n");
return -1;
}
+#ifdef CONFIG_X86_64
if (!cpu_has_apic) {
disable_apic = 1;
pr_info("Apic disabled by BIOS\n");
@@ -1600,7 +1625,7 @@ int __init APIC_init_uniprocessor(void)
enable_IR_x2apic();
#endif
#ifdef CONFIG_X86_64
- setup_apic_routing();
+ default_setup_apic_routing();
#endif
verify_local_APIC();
@@ -1738,7 +1763,8 @@ void __init connect_bsp_APIC(void)
outb(0x01, 0x23);
}
#endif
- enable_apic_mode();
+ if (apic->enable_apic_mode)
+ apic->enable_apic_mode();
}
/**
@@ -1876,29 +1902,39 @@ void __cpuinit generic_processor_info(int apicid, int version)
}
#endif
-#if defined(CONFIG_X86_SMP) || defined(CONFIG_X86_64)
- /* are we being called early in kernel startup? */
- if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
- u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
- u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
-
- cpu_to_apicid[cpu] = apicid;
- bios_cpu_apicid[cpu] = apicid;
- } else {
- per_cpu(x86_cpu_to_apicid, cpu) = apicid;
- per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
- }
+#if defined(CONFIG_SMP) || defined(CONFIG_X86_64)
+ early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
+ early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
#endif
set_cpu_possible(cpu, true);
set_cpu_present(cpu, true);
}
-#ifdef CONFIG_X86_64
int hard_smp_processor_id(void)
{
return read_apic_id();
}
+
+void default_init_apic_ldr(void)
+{
+ unsigned long val;
+
+ apic_write(APIC_DFR, APIC_DFR_VALUE);
+ val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+ val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
+ apic_write(APIC_LDR, val);
+}
+
+#ifdef CONFIG_X86_32
+int default_apicid_to_node(int logical_apicid)
+{
+#ifdef CONFIG_SMP
+ return apicid_2_node[hard_smp_processor_id()];
+#else
+ return 0;
+#endif
+}
#endif
/*
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 98807bb095ad..37ba5f85b718 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -301,7 +301,7 @@ extern int (*console_blank_hook)(int);
*/
#define APM_ZERO_SEGS
-#include "apm.h"
+#include <asm/apm.h>
/*
* Define to re-initialize the interrupt 0 timer to 100 Hz after a suspend.
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 1d41d3f1edbc..8793ab33e2c1 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -11,7 +11,6 @@
#include <linux/hardirq.h>
#include <linux/suspend.h>
#include <linux/kbuild.h>
-#include <asm/pda.h>
#include <asm/processor.h>
#include <asm/segment.h>
#include <asm/thread_info.h>
@@ -48,16 +47,6 @@ int main(void)
#endif
BLANK();
#undef ENTRY
-#define ENTRY(entry) DEFINE(pda_ ## entry, offsetof(struct x8664_pda, entry))
- ENTRY(kernelstack);
- ENTRY(oldrsp);
- ENTRY(pcurrent);
- ENTRY(irqcount);
- ENTRY(cpunumber);
- ENTRY(irqstackptr);
- ENTRY(data_offset);
- BLANK();
-#undef ENTRY
#ifdef CONFIG_PARAVIRT
BLANK();
OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
diff --git a/arch/x86/kernel/bigsmp_32.c b/arch/x86/kernel/bigsmp_32.c
new file mode 100644
index 000000000000..47a62f46afdb
--- /dev/null
+++ b/arch/x86/kernel/bigsmp_32.c
@@ -0,0 +1,266 @@
+/*
+ * APIC driver for "bigsmp" XAPIC machines with more than 8 virtual CPUs.
+ * Drives the local APIC in "clustered mode".
+ */
+#define APIC_DEFINITION 1
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <asm/mpspec.h>
+#include <asm/genapic.h>
+#include <asm/fixmap.h>
+#include <asm/apicdef.h>
+#include <asm/ipi.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/dmi.h>
+#include <linux/smp.h>
+
+
+static inline unsigned bigsmp_get_apic_id(unsigned long x)
+{
+ return (x >> 24) & 0xFF;
+}
+
+#define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu))
+
+static inline int bigsmp_apic_id_registered(void)
+{
+ return 1;
+}
+
+static inline const cpumask_t *bigsmp_target_cpus(void)
+{
+#ifdef CONFIG_SMP
+ return &cpu_online_map;
+#else
+ return &cpumask_of_cpu(0);
+#endif
+}
+
+#define APIC_DFR_VALUE (APIC_DFR_FLAT)
+
+static inline unsigned long
+bigsmp_check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+ return 0;
+}
+
+static inline unsigned long bigsmp_check_apicid_present(int bit)
+{
+ return 1;
+}
+
+static inline unsigned long calculate_ldr(int cpu)
+{
+ unsigned long val, id;
+ val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+ id = xapic_phys_to_log_apicid(cpu);
+ val |= SET_APIC_LOGICAL_ID(id);
+ return val;
+}
+
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LDR and TPR before enabling
+ * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116). So here it goes...
+ */
+static inline void bigsmp_init_apic_ldr(void)
+{
+ unsigned long val;
+ int cpu = smp_processor_id();
+
+ apic_write(APIC_DFR, APIC_DFR_VALUE);
+ val = calculate_ldr(cpu);
+ apic_write(APIC_LDR, val);
+}
+
+static inline void bigsmp_setup_apic_routing(void)
+{
+ printk("Enabling APIC mode: %s. Using %d I/O APICs\n",
+ "Physflat", nr_ioapics);
+}
+
+static inline int bigsmp_apicid_to_node(int logical_apicid)
+{
+ return apicid_2_node[hard_smp_processor_id()];
+}
+
+static inline int bigsmp_cpu_present_to_apicid(int mps_cpu)
+{
+ if (mps_cpu < nr_cpu_ids)
+ return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
+
+ return BAD_APICID;
+}
+
+static inline physid_mask_t bigsmp_apicid_to_cpu_present(int phys_apicid)
+{
+ return physid_mask_of_physid(phys_apicid);
+}
+
+extern u8 cpu_2_logical_apicid[];
+/* Mapping from cpu number to logical apicid */
+static inline int bigsmp_cpu_to_logical_apicid(int cpu)
+{
+ if (cpu >= nr_cpu_ids)
+ return BAD_APICID;
+ return cpu_physical_id(cpu);
+}
+
+static inline physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map)
+{
+ /* For clustered we don't have a good way to do this yet - hack */
+ return physids_promote(0xFFL);
+}
+
+static inline void bigsmp_setup_portio_remap(void)
+{
+}
+
+static inline int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+ return 1;
+}
+
+/* As we are using single CPU as destination, pick only one CPU here */
+static inline unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask)
+{
+ return bigsmp_cpu_to_logical_apicid(first_cpu(*cpumask));
+}
+
+static inline unsigned int
+bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
+{
+ int cpu;
+
+ /*
+ * We're using fixed IRQ delivery, can only return one phys APIC ID.
+ * May as well be the first.
+ */
+ for_each_cpu_and(cpu, cpumask, andmask) {
+ if (cpumask_test_cpu(cpu, cpu_online_mask))
+ break;
+ }
+ if (cpu < nr_cpu_ids)
+ return bigsmp_cpu_to_logical_apicid(cpu);
+
+ return BAD_APICID;
+}
+
+static inline int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb)
+{
+ return cpuid_apic >> index_msb;
+}
+
+static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector)
+{
+ default_send_IPI_mask_sequence_phys(mask, vector);
+}
+
+static inline void bigsmp_send_IPI_allbutself(int vector)
+{
+ default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
+}
+
+static inline void bigsmp_send_IPI_all(int vector)
+{
+ bigsmp_send_IPI_mask(cpu_online_mask, vector);
+}
+
+static int dmi_bigsmp; /* can be set by dmi scanners */
+
+static int hp_ht_bigsmp(const struct dmi_system_id *d)
+{
+ printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident);
+ dmi_bigsmp = 1;
+ return 0;
+}
+
+
+static const struct dmi_system_id bigsmp_dmi_table[] = {
+ { hp_ht_bigsmp, "HP ProLiant DL760 G2",
+ { DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
+ DMI_MATCH(DMI_BIOS_VERSION, "P44-"),}
+ },
+
+ { hp_ht_bigsmp, "HP ProLiant DL740",
+ { DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
+ DMI_MATCH(DMI_BIOS_VERSION, "P47-"),}
+ },
+ { }
+};
+
+static void bigsmp_vector_allocation_domain(int cpu, cpumask_t *retmask)
+{
+ cpus_clear(*retmask);
+ cpu_set(cpu, *retmask);
+}
+
+static int probe_bigsmp(void)
+{
+ if (def_to_bigsmp)
+ dmi_bigsmp = 1;
+ else
+ dmi_check_system(bigsmp_dmi_table);
+ return dmi_bigsmp;
+}
+
+struct genapic apic_bigsmp = {
+
+ .name = "bigsmp",
+ .probe = probe_bigsmp,
+ .acpi_madt_oem_check = NULL,
+ .apic_id_registered = bigsmp_apic_id_registered,
+
+ .irq_delivery_mode = dest_Fixed,
+ /* phys delivery to target CPU: */
+ .irq_dest_mode = 0,
+
+ .target_cpus = bigsmp_target_cpus,
+ .disable_esr = 1,
+ .dest_logical = 0,
+ .check_apicid_used = bigsmp_check_apicid_used,
+ .check_apicid_present = bigsmp_check_apicid_present,
+
+ .vector_allocation_domain = bigsmp_vector_allocation_domain,
+ .init_apic_ldr = bigsmp_init_apic_ldr,
+
+ .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map,
+ .setup_apic_routing = bigsmp_setup_apic_routing,
+ .multi_timer_check = NULL,
+ .apicid_to_node = bigsmp_apicid_to_node,
+ .cpu_to_logical_apicid = bigsmp_cpu_to_logical_apicid,
+ .cpu_present_to_apicid = bigsmp_cpu_present_to_apicid,
+ .apicid_to_cpu_present = bigsmp_apicid_to_cpu_present,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = bigsmp_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = bigsmp_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = bigsmp_get_apic_id,
+ .set_apic_id = NULL,
+ .apic_id_mask = 0xFF << 24,
+
+ .cpu_mask_to_apicid = bigsmp_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = bigsmp_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = bigsmp_send_IPI_mask,
+ .send_IPI_mask_allbutself = NULL,
+ .send_IPI_allbutself = bigsmp_send_IPI_allbutself,
+ .send_IPI_all = bigsmp_send_IPI_all,
+ .send_IPI_self = default_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+
+ .wait_for_init_deassert = default_wait_for_init_deassert,
+
+ .smp_callin_clear_local_apic = NULL,
+ .store_NMI_vector = NULL,
+ .inquire_remote_apic = default_inquire_remote_apic,
+};
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 2cf23634b6d9..e48640cfac0c 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -7,7 +7,7 @@
#include <asm/pat.h>
#include <asm/processor.h>
-#include <mach_apic.h>
+#include <asm/genapic.h>
struct cpuid_bit {
u16 feature;
@@ -69,7 +69,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
*/
void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
unsigned int eax, ebx, ecx, edx, sub_index;
unsigned int ht_mask_width, core_plus_mask_width;
unsigned int core_select_mask, core_level_siblings;
@@ -116,22 +116,14 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c)
core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
-#ifdef CONFIG_X86_32
- c->cpu_core_id = phys_pkg_id(c->initial_apicid, ht_mask_width)
+ c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width)
& core_select_mask;
- c->phys_proc_id = phys_pkg_id(c->initial_apicid, core_plus_mask_width);
+ c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, core_plus_mask_width);
/*
* Reinit the apicid, now that we have extended initial_apicid.
*/
- c->apicid = phys_pkg_id(c->initial_apicid, 0);
-#else
- c->cpu_core_id = phys_pkg_id(ht_mask_width) & core_select_mask;
- c->phys_proc_id = phys_pkg_id(core_plus_mask_width);
- /*
- * Reinit the apicid, now that we have extended initial_apicid.
- */
- c->apicid = phys_pkg_id(0);
-#endif
+ c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+
c->x86_max_cores = (core_level_siblings / smp_num_siblings);
@@ -143,37 +135,3 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c)
return;
#endif
}
-
-#ifdef CONFIG_X86_PAT
-void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
-{
- if (!cpu_has_pat)
- pat_disable("PAT not supported by CPU.");
-
- switch (c->x86_vendor) {
- case X86_VENDOR_INTEL:
- /*
- * There is a known erratum on Pentium III and Core Solo
- * and Core Duo CPUs.
- * " Page with PAT set to WC while associated MTRR is UC
- * may consolidate to UC "
- * Because of this erratum, it is better to stick with
- * setting WC in MTRR rather than using PAT on these CPUs.
- *
- * Enable PAT WC only on P4, Core 2 or later CPUs.
- */
- if (c->x86 > 0x6 || (c->x86 == 6 && c->x86_model >= 15))
- return;
-
- pat_disable("PAT WC disabled due to known CPU erratum.");
- return;
-
- case X86_VENDOR_AMD:
- case X86_VENDOR_CENTAUR:
- case X86_VENDOR_TRANSMETA:
- return;
- }
-
- pat_disable("PAT disabled. Not yet verified on this CPU type.");
-}
-#endif
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7c878f6aa919..ff4d7b9e32e4 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -12,7 +12,7 @@
# include <asm/cacheflush.h>
#endif
-#include <mach_apic.h>
+#include <asm/genapic.h>
#include "cpu.h"
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 83492b1f93b1..c4bdc7f00207 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -21,14 +21,16 @@
#include <asm/asm.h>
#include <asm/numa.h>
#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/cpumask.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/mpspec.h>
#include <asm/apic.h>
-#include <mach_apic.h>
#include <asm/genapic.h>
+#include <asm/genapic.h>
+#include <asm/uv/uv.h>
#endif
-#include <asm/pda.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/desc.h>
@@ -50,6 +52,15 @@ cpumask_var_t cpu_initialized_mask;
/* representing cpus for which sibling maps can be computed */
cpumask_var_t cpu_sibling_setup_mask;
+/* correctly size the local cpu masks */
+void __init setup_cpu_local_masks(void)
+{
+ alloc_bootmem_cpumask_var(&cpu_initialized_mask);
+ alloc_bootmem_cpumask_var(&cpu_callin_mask);
+ alloc_bootmem_cpumask_var(&cpu_callout_mask);
+ alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
+}
+
#else /* CONFIG_X86_32 */
cpumask_t cpu_callin_map;
@@ -62,23 +73,23 @@ cpumask_t cpu_sibling_setup_map;
static struct cpu_dev *this_cpu __cpuinitdata;
+DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
#ifdef CONFIG_X86_64
-/* We need valid kernel segments for data and code in long mode too
- * IRET will check the segment types kkeil 2000/10/28
- * Also sysret mandates a special GDT layout
- */
-/* The TLS descriptors are currently at a different place compared to i386.
- Hopefully nobody expects them at a fixed place (Wine?) */
-DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
+ /*
+ * We need valid kernel segments for data and code in long mode too
+ * IRET will check the segment types kkeil 2000/10/28
+ * Also sysret mandates a special GDT layout
+ *
+ * The TLS descriptors are currently at a different place compared to i386.
+ * Hopefully nobody expects them at a fixed place (Wine?)
+ */
[GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
[GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
[GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
-} };
#else
-DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
@@ -110,9 +121,9 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
[GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } },
[GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
- [GDT_ENTRY_PERCPU] = { { { 0x00000000, 0x00000000 } } },
-} };
+ [GDT_ENTRY_PERCPU] = { { { 0x0000ffff, 0x00cf9200 } } },
#endif
+} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
#ifdef CONFIG_X86_32
@@ -213,6 +224,49 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
#endif
/*
+ * Some CPU features depend on higher CPUID levels, which may not always
+ * be available due to CPUID level capping or broken virtualization
+ * software. Add those features to this table to auto-disable them.
+ */
+struct cpuid_dependent_feature {
+ u32 feature;
+ u32 level;
+};
+static const struct cpuid_dependent_feature __cpuinitconst
+cpuid_dependent_features[] = {
+ { X86_FEATURE_MWAIT, 0x00000005 },
+ { X86_FEATURE_DCA, 0x00000009 },
+ { X86_FEATURE_XSAVE, 0x0000000d },
+ { 0, 0 }
+};
+
+static void __cpuinit filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
+{
+ const struct cpuid_dependent_feature *df;
+ for (df = cpuid_dependent_features; df->feature; df++) {
+ /*
+ * Note: cpuid_level is set to -1 if unavailable, but
+ * extended_extended_level is set to 0 if unavailable
+ * and the legitimate extended levels are all negative
+ * when signed; hence the weird messing around with
+ * signs here...
+ */
+ if (cpu_has(c, df->feature) &&
+ ((s32)df->feature < 0 ?
+ (u32)df->feature > (u32)c->extended_cpuid_level :
+ (s32)df->feature > (s32)c->cpuid_level)) {
+ clear_cpu_cap(c, df->feature);
+ if (warn)
+ printk(KERN_WARNING
+ "CPU: CPU feature %s disabled "
+ "due to lack of CPUID level 0x%x\n",
+ x86_cap_flags[df->feature],
+ df->level);
+ }
+ }
+}
+
+/*
* Naming convention should be: <Name> [(<Codename>)]
* This table only is used unless init_<vendor>() below doesn't set it;
* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used
@@ -247,12 +301,17 @@ __u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
void switch_to_new_gdt(void)
{
struct desc_ptr gdt_descr;
+ int cpu = smp_processor_id();
- gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
+ gdt_descr.address = (long)get_cpu_gdt_table(cpu);
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
+ /* Reload the per-cpu base */
#ifdef CONFIG_X86_32
- asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
+ loadsegment(fs, __KERNEL_PERCPU);
+#else
+ loadsegment(gs, 0);
+ wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
#endif
}
@@ -383,11 +442,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
}
index_msb = get_count_order(smp_num_siblings);
-#ifdef CONFIG_X86_64
- c->phys_proc_id = phys_pkg_id(index_msb);
-#else
- c->phys_proc_id = phys_pkg_id(c->initial_apicid, index_msb);
-#endif
+ c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
smp_num_siblings = smp_num_siblings / c->x86_max_cores;
@@ -395,13 +450,8 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
core_bits = get_count_order(c->x86_max_cores);
-#ifdef CONFIG_X86_64
- c->cpu_core_id = phys_pkg_id(index_msb) &
- ((1 << core_bits) - 1);
-#else
- c->cpu_core_id = phys_pkg_id(c->initial_apicid, index_msb) &
+ c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
((1 << core_bits) - 1);
-#endif
}
out:
@@ -570,11 +620,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
if (this_cpu->c_early_init)
this_cpu->c_early_init(c);
- validate_pat_support(c);
-
#ifdef CONFIG_SMP
c->cpu_index = boot_cpu_id;
#endif
+ filter_cpuid_features(c, false);
}
void __init early_cpu_init(void)
@@ -637,7 +686,7 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
# ifdef CONFIG_X86_HT
- c->apicid = phys_pkg_id(c->initial_apicid, 0);
+ c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
# else
c->apicid = c->initial_apicid;
# endif
@@ -684,7 +733,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
this_cpu->c_identify(c);
#ifdef CONFIG_X86_64
- c->apicid = phys_pkg_id(0);
+ c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
#endif
/*
@@ -708,6 +757,9 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
* we do "generic changes."
*/
+ /* Filter out anything that depends on CPUID levels we don't have */
+ filter_cpuid_features(c, true);
+
/* If the model name is still unset, do table lookup. */
if (!c->x86_model_id[0]) {
char *p;
@@ -877,54 +929,26 @@ static __init int setup_disablecpuid(char *arg)
__setup("clearcpuid=", setup_disablecpuid);
#ifdef CONFIG_X86_64
-struct x8664_pda **_cpu_pda __read_mostly;
-EXPORT_SYMBOL(_cpu_pda);
-
struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
-static char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
-
-void __cpuinit pda_init(int cpu)
-{
- struct x8664_pda *pda = cpu_pda(cpu);
+DEFINE_PER_CPU_FIRST(union irq_stack_union,
+ irq_stack_union) __aligned(PAGE_SIZE);
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(char *, irq_stack_ptr); /* will be set during per cpu init */
+#else
+DEFINE_PER_CPU(char *, irq_stack_ptr) =
+ per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
+#endif
- /* Setup up data that may be needed in __get_free_pages early */
- loadsegment(fs, 0);
- loadsegment(gs, 0);
- /* Memory clobbers used to order PDA accessed */
- mb();
- wrmsrl(MSR_GS_BASE, pda);
- mb();
-
- pda->cpunumber = cpu;
- pda->irqcount = -1;
- pda->kernelstack = (unsigned long)stack_thread_info() -
- PDA_STACKOFFSET + THREAD_SIZE;
- pda->active_mm = &init_mm;
- pda->mmu_state = 0;
-
- if (cpu == 0) {
- /* others are initialized in smpboot.c */
- pda->pcurrent = &init_task;
- pda->irqstackptr = boot_cpu_stack;
- pda->irqstackptr += IRQSTACKSIZE - 64;
- } else {
- if (!pda->irqstackptr) {
- pda->irqstackptr = (char *)
- __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
- if (!pda->irqstackptr)
- panic("cannot allocate irqstack for cpu %d",
- cpu);
- pda->irqstackptr += IRQSTACKSIZE - 64;
- }
+DEFINE_PER_CPU(unsigned long, kernel_stack) =
+ (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+EXPORT_PER_CPU_SYMBOL(kernel_stack);
- if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
- pda->nodenumber = cpu_to_node(cpu);
- }
-}
+DEFINE_PER_CPU(unsigned int, irq_count) = -1;
-static char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
- DEBUG_STKSZ] __page_aligned_bss;
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+ [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ])
+ __aligned(PAGE_SIZE);
extern asmlinkage void ignore_sysret(void);
@@ -982,15 +1006,14 @@ void __cpuinit cpu_init(void)
struct tss_struct *t = &per_cpu(init_tss, cpu);
struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
unsigned long v;
- char *estacks = NULL;
struct task_struct *me;
int i;
- /* CPU 0 is initialised in head64.c */
- if (cpu != 0)
- pda_init(cpu);
- else
- estacks = boot_exception_stacks;
+#ifdef CONFIG_NUMA
+ if (cpu != 0 && percpu_read(node_number) == 0 &&
+ cpu_to_node(cpu) != NUMA_NO_NODE)
+ percpu_write(node_number, cpu_to_node(cpu));
+#endif
me = current;
@@ -1007,6 +1030,8 @@ void __cpuinit cpu_init(void)
*/
switch_to_new_gdt();
+ loadsegment(fs, 0);
+
load_idt((const struct desc_ptr *)&idt_descr);
memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
@@ -1024,18 +1049,13 @@ void __cpuinit cpu_init(void)
* set up and load the per-CPU TSS
*/
if (!orig_ist->ist[0]) {
- static const unsigned int order[N_EXCEPTION_STACKS] = {
- [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
- [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
+ static const unsigned int sizes[N_EXCEPTION_STACKS] = {
+ [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
+ [DEBUG_STACK - 1] = DEBUG_STKSZ
};
+ char *estacks = per_cpu(exception_stacks, cpu);
for (v = 0; v < N_EXCEPTION_STACKS; v++) {
- if (cpu) {
- estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
- if (!estacks)
- panic("Cannot allocate exception "
- "stack %ld %d\n", v, cpu);
- }
- estacks += PAGE_SIZE << order[v];
+ estacks += sizes[v];
orig_ist->ist[v] = t->x86_tss.ist[v] =
(unsigned long)estacks;
}
@@ -1069,22 +1089,19 @@ void __cpuinit cpu_init(void)
*/
if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
arch_kgdb_ops.correct_hw_break();
- else {
+ else
#endif
- /*
- * Clear all 6 debug registers:
- */
-
- set_debugreg(0UL, 0);
- set_debugreg(0UL, 1);
- set_debugreg(0UL, 2);
- set_debugreg(0UL, 3);
- set_debugreg(0UL, 6);
- set_debugreg(0UL, 7);
-#ifdef CONFIG_KGDB
- /* If the kgdb is connected no debug regs should be altered. */
+ {
+ /*
+ * Clear all 6 debug registers:
+ */
+ set_debugreg(0UL, 0);
+ set_debugreg(0UL, 1);
+ set_debugreg(0UL, 2);
+ set_debugreg(0UL, 3);
+ set_debugreg(0UL, 6);
+ set_debugreg(0UL, 7);
}
-#endif
fpu_init();
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 430e5c38a544..1cef0aa5e5dc 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -24,7 +24,7 @@
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/mpspec.h>
#include <asm/apic.h>
-#include <mach_apic.h>
+#include <asm/genapic.h>
#endif
static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
@@ -63,6 +63,18 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
}
+ /*
+ * There is a known erratum on Pentium III and Core Solo
+ * and Core Duo CPUs.
+ * " Page with PAT set to WC while associated MTRR is UC
+ * may consolidate to UC "
+ * Because of this erratum, it is better to stick with
+ * setting WC in MTRR rather than using PAT on these CPUs.
+ *
+ * Enable PAT WC only on P4, Core 2 or later CPUs.
+ */
+ if (c->x86 == 6 && c->x86_model < 15)
+ clear_cpu_cap(c, X86_FEATURE_PAT);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index da299eb85fc0..7293508d8f5c 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -147,7 +147,16 @@ struct _cpuid4_info {
union _cpuid4_leaf_ecx ecx;
unsigned long size;
unsigned long can_disable;
- cpumask_t shared_cpu_map; /* future?: only cpus/node is needed */
+ DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
+};
+
+/* subset of above _cpuid4_info w/o shared_cpu_map */
+struct _cpuid4_info_regs {
+ union _cpuid4_leaf_eax eax;
+ union _cpuid4_leaf_ebx ebx;
+ union _cpuid4_leaf_ecx ecx;
+ unsigned long size;
+ unsigned long can_disable;
};
#ifdef CONFIG_PCI
@@ -278,7 +287,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
}
static void __cpuinit
-amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf)
+amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
{
if (index < 3)
return;
@@ -286,7 +295,8 @@ amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf)
}
static int
-__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+__cpuinit cpuid4_cache_lookup_regs(int index,
+ struct _cpuid4_info_regs *this_leaf)
{
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
@@ -314,6 +324,15 @@ __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
return 0;
}
+static int
+__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+{
+ struct _cpuid4_info_regs *leaf_regs =
+ (struct _cpuid4_info_regs *)this_leaf;
+
+ return cpuid4_cache_lookup_regs(index, leaf_regs);
+}
+
static int __cpuinit find_num_cache_leaves(void)
{
unsigned int eax, ebx, ecx, edx;
@@ -353,11 +372,10 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
* parameters cpuid leaf to find the cache details
*/
for (i = 0; i < num_cache_leaves; i++) {
- struct _cpuid4_info this_leaf;
-
+ struct _cpuid4_info_regs this_leaf;
int retval;
- retval = cpuid4_cache_lookup(i, &this_leaf);
+ retval = cpuid4_cache_lookup_regs(i, &this_leaf);
if (retval >= 0) {
switch(this_leaf.eax.split.level) {
case 1:
@@ -506,17 +524,20 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
if (num_threads_sharing == 1)
- cpu_set(cpu, this_leaf->shared_cpu_map);
+ cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map));
else {
index_msb = get_count_order(num_threads_sharing);
for_each_online_cpu(i) {
if (cpu_data(i).apicid >> index_msb ==
c->apicid >> index_msb) {
- cpu_set(i, this_leaf->shared_cpu_map);
+ cpumask_set_cpu(i,
+ to_cpumask(this_leaf->shared_cpu_map));
if (i != cpu && per_cpu(cpuid4_info, i)) {
- sibling_leaf = CPUID4_INFO_IDX(i, index);
- cpu_set(cpu, sibling_leaf->shared_cpu_map);
+ sibling_leaf =
+ CPUID4_INFO_IDX(i, index);
+ cpumask_set_cpu(cpu, to_cpumask(
+ sibling_leaf->shared_cpu_map));
}
}
}
@@ -528,9 +549,10 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
int sibling;
this_leaf = CPUID4_INFO_IDX(cpu, index);
- for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) {
+ for_each_cpu(sibling, to_cpumask(this_leaf->shared_cpu_map)) {
sibling_leaf = CPUID4_INFO_IDX(sibling, index);
- cpu_clear(cpu, sibling_leaf->shared_cpu_map);
+ cpumask_clear_cpu(cpu,
+ to_cpumask(sibling_leaf->shared_cpu_map));
}
}
#else
@@ -635,8 +657,9 @@ static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
int n = 0;
if (len > 1) {
- cpumask_t *mask = &this_leaf->shared_cpu_map;
+ const struct cpumask *mask;
+ mask = to_cpumask(this_leaf->shared_cpu_map);
n = type?
cpulist_scnprintf(buf, len-2, mask) :
cpumask_scnprintf(buf, len-2, mask);
@@ -699,7 +722,8 @@ static struct pci_dev *get_k8_northbridge(int node)
static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
{
- int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+ 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;
@@ -733,7 +757,8 @@ static ssize_t
store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
size_t count)
{
- int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+ 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;
@@ -878,7 +903,7 @@ err_out:
return -ENOMEM;
}
-static cpumask_t cache_dev_map = CPU_MASK_NONE;
+static DECLARE_BITMAP(cache_dev_map, NR_CPUS);
/* Add/Remove cache interface for CPU device */
static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
@@ -918,7 +943,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
}
kobject_uevent(&(this_object->kobj), KOBJ_ADD);
}
- cpu_set(cpu, cache_dev_map);
+ cpumask_set_cpu(cpu, to_cpumask(cache_dev_map));
kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
return 0;
@@ -931,9 +956,9 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
if (per_cpu(cpuid4_info, cpu) == NULL)
return;
- if (!cpu_isset(cpu, cache_dev_map))
+ if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map)))
return;
- cpu_clear(cpu, cache_dev_map);
+ cpumask_clear_cpu(cpu, to_cpumask(cache_dev_map));
for (i = 0; i < num_cache_leaves; i++)
kobject_put(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 8ae8c4ff094d..4772e91e8246 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -67,7 +67,7 @@ static struct threshold_block threshold_defaults = {
struct threshold_bank {
struct kobject *kobj;
struct threshold_block *blocks;
- cpumask_t cpus;
+ cpumask_var_t cpus;
};
static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]);
@@ -481,7 +481,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
#ifdef CONFIG_SMP
if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */
- i = first_cpu(per_cpu(cpu_core_map, cpu));
+ i = cpumask_first(&per_cpu(cpu_core_map, cpu));
/* first core not up yet */
if (cpu_data(i).cpu_core_id)
@@ -501,7 +501,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
if (err)
goto out;
- b->cpus = per_cpu(cpu_core_map, cpu);
+ cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
per_cpu(threshold_banks, cpu)[bank] = b;
goto out;
}
@@ -512,15 +512,20 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
err = -ENOMEM;
goto out;
}
+ if (!alloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
+ kfree(b);
+ err = -ENOMEM;
+ goto out;
+ }
b->kobj = kobject_create_and_add(name, &per_cpu(device_mce, cpu).kobj);
if (!b->kobj)
goto out_free;
#ifndef CONFIG_SMP
- b->cpus = CPU_MASK_ALL;
+ cpumask_setall(b->cpus);
#else
- b->cpus = per_cpu(cpu_core_map, cpu);
+ cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
#endif
per_cpu(threshold_banks, cpu)[bank] = b;
@@ -529,7 +534,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
if (err)
goto out_free;
- for_each_cpu_mask_nr(i, b->cpus) {
+ for_each_cpu(i, b->cpus) {
if (i == cpu)
continue;
@@ -545,6 +550,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
out_free:
per_cpu(threshold_banks, cpu)[bank] = NULL;
+ free_cpumask_var(b->cpus);
kfree(b);
out:
return err;
@@ -619,7 +625,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
#endif
/* remove all sibling symlinks before unregistering */
- for_each_cpu_mask_nr(i, b->cpus) {
+ for_each_cpu(i, b->cpus) {
if (i == cpu)
continue;
@@ -632,6 +638,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
free_out:
kobject_del(b->kobj);
kobject_put(b->kobj);
+ free_cpumask_var(b->cpus);
kfree(b);
per_cpu(threshold_banks, cpu)[bank] = NULL;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index 4b48f251fd39..5e8c79e748a6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -7,6 +7,7 @@
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <asm/processor.h>
+#include <asm/apic.h>
#include <asm/msr.h>
#include <asm/mce.h>
#include <asm/hw_irq.h>
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c689d19e35ab..ad7f2a696f4a 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -24,11 +24,11 @@
#include <asm/apic.h>
#include <asm/hpet.h>
#include <linux/kdebug.h>
-#include <asm/smp.h>
+#include <asm/cpu.h>
#include <asm/reboot.h>
#include <asm/virtext.h>
-#include <mach_ipi.h>
+#include <asm/genapic.h>
#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index c302d0707048..d35db5993fd6 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -106,7 +106,8 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
const struct stacktrace_ops *ops, void *data)
{
const unsigned cpu = get_cpu();
- unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
+ unsigned long *irq_stack_end =
+ (unsigned long *)per_cpu(irq_stack_ptr, cpu);
unsigned used = 0;
struct thread_info *tinfo;
int graph = 0;
@@ -160,23 +161,23 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
stack = (unsigned long *) estack_end[-2];
continue;
}
- if (irqstack_end) {
- unsigned long *irqstack;
- irqstack = irqstack_end -
- (IRQSTACKSIZE - 64) / sizeof(*irqstack);
+ if (irq_stack_end) {
+ unsigned long *irq_stack;
+ irq_stack = irq_stack_end -
+ (IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);
- if (stack >= irqstack && stack < irqstack_end) {
+ if (stack >= irq_stack && stack < irq_stack_end) {
if (ops->stack(data, "IRQ") < 0)
break;
bp = print_context_stack(tinfo, stack, bp,
- ops, data, irqstack_end, &graph);
+ ops, data, irq_stack_end, &graph);
/*
* We link to the next stack (which would be
* the process stack normally) the last
* pointer (index -1 to end) in the IRQ stack:
*/
- stack = (unsigned long *) (irqstack_end[-1]);
- irqstack_end = NULL;
+ stack = (unsigned long *) (irq_stack_end[-1]);
+ irq_stack_end = NULL;
ops->stack(data, "EOI");
continue;
}
@@ -199,10 +200,10 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack;
int i;
const int cpu = smp_processor_id();
- unsigned long *irqstack_end =
- (unsigned long *) (cpu_pda(cpu)->irqstackptr);
- unsigned long *irqstack =
- (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
+ unsigned long *irq_stack_end =
+ (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
+ unsigned long *irq_stack =
+ (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE);
/*
* debugging aid: "show_stack(NULL, NULL);" prints the
@@ -218,9 +219,9 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
stack = sp;
for (i = 0; i < kstack_depth_to_print; i++) {
- if (stack >= irqstack && stack <= irqstack_end) {
- if (stack == irqstack_end) {
- stack = (unsigned long *) (irqstack_end[-1]);
+ if (stack >= irq_stack && stack <= irq_stack_end) {
+ if (stack == irq_stack_end) {
+ stack = (unsigned long *) (irq_stack_end[-1]);
printk(" <EOI> ");
}
} else {
@@ -241,7 +242,7 @@ void show_registers(struct pt_regs *regs)
int i;
unsigned long sp;
const int cpu = smp_processor_id();
- struct task_struct *cur = cpu_pda(cpu)->pcurrent;
+ struct task_struct *cur = current;
sp = regs->sp;
printk("CPU %d ", cpu);
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 1119d247fe11..b205272ad394 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -366,10 +366,12 @@ void __init efi_init(void)
SMBIOS_TABLE_GUID)) {
efi.smbios = config_tables[i].table;
printk(" SMBIOS=0x%lx ", config_tables[i].table);
+#ifdef CONFIG_X86_UV
} else if (!efi_guidcmp(config_tables[i].guid,
UV_SYSTEM_TABLE_GUID)) {
efi.uv_systab = config_tables[i].table;
printk(" UVsystab=0x%lx ", config_tables[i].table);
+#endif
} else if (!efi_guidcmp(config_tables[i].guid,
HCDP_TABLE_GUID)) {
efi.hcdp = config_tables[i].table;
diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c
index 652c5287215f..a4ee29127fdf 100644
--- a/arch/x86/kernel/efi_64.c
+++ b/arch/x86/kernel/efi_64.c
@@ -36,6 +36,7 @@
#include <asm/proto.h>
#include <asm/efi.h>
#include <asm/cacheflush.h>
+#include <asm/fixmap.h>
static pgd_t save_pgd __initdata;
static unsigned long efi_flags __initdata;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 46469029e9d3..65efd42454be 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -672,7 +672,7 @@ common_interrupt:
ENDPROC(common_interrupt)
CFI_ENDPROC
-#define BUILD_INTERRUPT(name, nr) \
+#define BUILD_INTERRUPT3(name, nr, fn) \
ENTRY(name) \
RING0_INT_FRAME; \
pushl $~(nr); \
@@ -680,13 +680,15 @@ ENTRY(name) \
SAVE_ALL; \
TRACE_IRQS_OFF \
movl %esp,%eax; \
- call smp_##name; \
+ call fn; \
jmp ret_from_intr; \
CFI_ENDPROC; \
ENDPROC(name)
+#define BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(name, nr, smp_##name)
+
/* The include is where all of the SMP etc. interrupts come from */
-#include "entry_arch.h"
+#include <asm/entry_arch.h>
ENTRY(coprocessor_error)
RING0_INT_FRAME
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a1346217e43c..1f7d697b5c00 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -52,6 +52,7 @@
#include <asm/irqflags.h>
#include <asm/paravirt.h>
#include <asm/ftrace.h>
+#include <asm/percpu.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
@@ -209,7 +210,7 @@ ENTRY(native_usergs_sysret64)
/* %rsp:at FRAMEEND */
.macro FIXUP_TOP_OF_STACK tmp offset=0
- movq %gs:pda_oldrsp,\tmp
+ movq PER_CPU_VAR(old_rsp),\tmp
movq \tmp,RSP+\offset(%rsp)
movq $__USER_DS,SS+\offset(%rsp)
movq $__USER_CS,CS+\offset(%rsp)
@@ -220,7 +221,7 @@ ENTRY(native_usergs_sysret64)
.macro RESTORE_TOP_OF_STACK tmp offset=0
movq RSP+\offset(%rsp),\tmp
- movq \tmp,%gs:pda_oldrsp
+ movq \tmp,PER_CPU_VAR(old_rsp)
movq EFLAGS+\offset(%rsp),\tmp
movq \tmp,R11+\offset(%rsp)
.endm
@@ -336,15 +337,15 @@ ENTRY(save_args)
je 1f
SWAPGS
/*
- * irqcount is used to check if a CPU is already on an interrupt stack
+ * irq_count is used to check if a CPU is already on an interrupt stack
* or not. While this is essentially redundant with preempt_count it is
* a little cheaper to use a separate counter in the PDA (short of
* moving irq_enter into assembly, which would be too much work)
*/
-1: incl %gs:pda_irqcount
+1: incl PER_CPU_VAR(irq_count)
jne 2f
popq_cfi %rax /* move return address... */
- mov %gs:pda_irqstackptr,%rsp
+ mov PER_CPU_VAR(irq_stack_ptr),%rsp
EMPTY_FRAME 0
pushq_cfi %rbp /* backlink for unwinder */
pushq_cfi %rax /* ... to the new stack */
@@ -409,6 +410,8 @@ END(save_paranoid)
ENTRY(ret_from_fork)
DEFAULT_FRAME
+ LOCK ; btr $TIF_FORK,TI_flags(%r8)
+
push kernel_eflags(%rip)
CFI_ADJUST_CFA_OFFSET 8
popf # reset kernel eflags
@@ -468,7 +471,7 @@ END(ret_from_fork)
ENTRY(system_call)
CFI_STARTPROC simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,PDA_STACKOFFSET
+ CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
SWAPGS_UNSAFE_STACK
@@ -479,8 +482,8 @@ ENTRY(system_call)
*/
ENTRY(system_call_after_swapgs)
- movq %rsp,%gs:pda_oldrsp
- movq %gs:pda_kernelstack,%rsp
+ movq %rsp,PER_CPU_VAR(old_rsp)
+ movq PER_CPU_VAR(kernel_stack),%rsp
/*
* No need to follow this irqs off/on section - it's straight
* and short:
@@ -523,7 +526,7 @@ sysret_check:
CFI_REGISTER rip,rcx
RESTORE_ARGS 0,-ARG_SKIP,1
/*CFI_REGISTER rflags,r11*/
- movq %gs:pda_oldrsp, %rsp
+ movq PER_CPU_VAR(old_rsp), %rsp
USERGS_SYSRET64
CFI_RESTORE_STATE
@@ -833,11 +836,11 @@ common_interrupt:
XCPT_FRAME
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
- /* 0(%rsp): oldrsp-ARGOFFSET */
+ /* 0(%rsp): old_rsp-ARGOFFSET */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
leaveq
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET -8
@@ -982,8 +985,10 @@ apicinterrupt IRQ_MOVE_CLEANUP_VECTOR \
irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
#endif
+#ifdef CONFIG_X86_UV
apicinterrupt UV_BAU_MESSAGE \
uv_bau_message_intr1 uv_bau_message_interrupt
+#endif
apicinterrupt LOCAL_TIMER_VECTOR \
apic_timer_interrupt smp_apic_timer_interrupt
@@ -1073,10 +1078,10 @@ ENTRY(\sym)
TRACE_IRQS_OFF
movq %rsp,%rdi /* pt_regs pointer */
xorl %esi,%esi /* no error code */
- movq %gs:pda_data_offset, %rbp
- subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ PER_CPU(init_tss, %rbp)
+ subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
call \do_sym
- addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
jmp paranoid_exit /* %ebx: no swapgs flag */
CFI_ENDPROC
END(\sym)
@@ -1260,14 +1265,14 @@ ENTRY(call_softirq)
CFI_REL_OFFSET rbp,0
mov %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
- incl %gs:pda_irqcount
- cmove %gs:pda_irqstackptr,%rsp
+ incl PER_CPU_VAR(irq_count)
+ cmove PER_CPU_VAR(irq_stack_ptr),%rsp
push %rbp # backlink for old unwinder
call __do_softirq
leaveq
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET -8
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
ret
CFI_ENDPROC
END(call_softirq)
@@ -1297,15 +1302,15 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs)
movq %rdi, %rsp # we don't return, adjust the stack frame
CFI_ENDPROC
DEFAULT_FRAME
-11: incl %gs:pda_irqcount
+11: incl PER_CPU_VAR(irq_count)
movq %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
- cmovzq %gs:pda_irqstackptr,%rsp
+ cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
pushq %rbp # backlink for old unwinder
call xen_evtchn_do_upcall
popq %rsp
CFI_DEF_CFA_REGISTER rsp
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
jmp error_exit
CFI_ENDPROC
END(do_hypervisor_callback)
diff --git a/arch/x86/kernel/es7000_32.c b/arch/x86/kernel/es7000_32.c
index 53699c931ad4..d6184c12a182 100644
--- a/arch/x86/kernel/es7000_32.c
+++ b/arch/x86/kernel/es7000_32.c
@@ -40,7 +40,6 @@
#include <asm/smp.h>
#include <asm/atomic.h>
#include <asm/apicdef.h>
-#include <mach_mpparse.h>
#include <asm/genapic.h>
#include <asm/setup.h>
@@ -182,20 +181,16 @@ static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
return 0;
}
-static void noop_wait_for_deassert(atomic_t *deassert_not_used)
-{
-}
-
static int __init es7000_update_genapic(void)
{
- genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
+ apic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
/* MPENTIUMIII */
if (boot_cpu_data.x86 == 6 &&
(boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) {
es7000_update_genapic_to_cluster();
- genapic->wait_for_init_deassert = noop_wait_for_deassert;
- genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
+ apic->wait_for_init_deassert = NULL;
+ apic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
}
return 0;
@@ -359,20 +354,449 @@ es7000_mip_write(struct mip_reg *mip_reg)
return status;
}
-void __init
-es7000_sw_apic(void)
-{
- if (es7000_plat) {
- int mip_status;
- struct mip_reg es7000_mip_reg;
-
- printk("ES7000: Enabling APIC mode.\n");
- memset(&es7000_mip_reg, 0, sizeof(struct mip_reg));
- es7000_mip_reg.off_0 = MIP_SW_APIC;
- es7000_mip_reg.off_38 = (MIP_VALID);
- while ((mip_status = es7000_mip_write(&es7000_mip_reg)) != 0)
- printk("es7000_sw_apic: command failed, status = %x\n",
- mip_status);
+void __init es7000_enable_apic_mode(void)
+{
+ struct mip_reg es7000_mip_reg;
+ int mip_status;
+
+ if (!es7000_plat)
return;
+
+ printk("ES7000: Enabling APIC mode.\n");
+ memset(&es7000_mip_reg, 0, sizeof(struct mip_reg));
+ es7000_mip_reg.off_0 = MIP_SW_APIC;
+ es7000_mip_reg.off_38 = MIP_VALID;
+
+ while ((mip_status = es7000_mip_write(&es7000_mip_reg)) != 0) {
+ printk("es7000_enable_apic_mode: command failed, status = %x\n",
+ mip_status);
+ }
+}
+
+/*
+ * APIC driver for the Unisys ES7000 chipset.
+ */
+#define APIC_DEFINITION 1
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <asm/mpspec.h>
+#include <asm/genapic.h>
+#include <asm/fixmap.h>
+#include <asm/apicdef.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/smp.h>
+#include <asm/ipi.h>
+
+#define APIC_DFR_VALUE_CLUSTER (APIC_DFR_CLUSTER)
+#define INT_DELIVERY_MODE_CLUSTER (dest_LowestPrio)
+#define INT_DEST_MODE_CLUSTER (1) /* logical delivery broadcast to all procs */
+
+#define APIC_DFR_VALUE (APIC_DFR_FLAT)
+
+extern void es7000_enable_apic_mode(void);
+extern int apic_version [MAX_APICS];
+extern u8 cpu_2_logical_apicid[];
+extern unsigned int boot_cpu_physical_apicid;
+
+extern int parse_unisys_oem (char *oemptr);
+extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
+extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr);
+extern void setup_unisys(void);
+
+#define apicid_cluster(apicid) (apicid & 0xF0)
+#define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
+
+static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask)
+{
+ /* Careful. Some cpus do not strictly honor the set of cpus
+ * specified in the interrupt destination when using lowest
+ * priority interrupt delivery mode.
+ *
+ * In particular there was a hyperthreading cpu observed to
+ * deliver interrupts to the wrong hyperthread when only one
+ * hyperthread was specified in the interrupt desitination.
+ */
+ *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+}
+
+
+static void es7000_wait_for_init_deassert(atomic_t *deassert)
+{
+#ifndef CONFIG_ES7000_CLUSTERED_APIC
+ while (!atomic_read(deassert))
+ cpu_relax();
+#endif
+ return;
+}
+
+static unsigned int es7000_get_apic_id(unsigned long x)
+{
+ return (x >> 24) & 0xFF;
+}
+
+#ifdef CONFIG_ACPI
+static int es7000_check_dsdt(void)
+{
+ struct acpi_table_header header;
+
+ if (ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_DSDT, 0, &header)) &&
+ !strncmp(header.oem_id, "UNISYS", 6))
+ return 1;
+ return 0;
+}
+#endif
+
+static void es7000_send_IPI_mask(const struct cpumask *mask, int vector)
+{
+ default_send_IPI_mask_sequence_phys(mask, vector);
+}
+
+static void es7000_send_IPI_allbutself(int vector)
+{
+ default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
+}
+
+static void es7000_send_IPI_all(int vector)
+{
+ es7000_send_IPI_mask(cpu_online_mask, vector);
+}
+
+static int es7000_apic_id_registered(void)
+{
+ return 1;
+}
+
+static const cpumask_t *target_cpus_cluster(void)
+{
+ return &CPU_MASK_ALL;
+}
+
+static const cpumask_t *es7000_target_cpus(void)
+{
+ return &cpumask_of_cpu(smp_processor_id());
+}
+
+static unsigned long
+es7000_check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+ return 0;
+}
+static unsigned long es7000_check_apicid_present(int bit)
+{
+ return physid_isset(bit, phys_cpu_present_map);
+}
+
+static unsigned long calculate_ldr(int cpu)
+{
+ unsigned long id = xapic_phys_to_log_apicid(cpu);
+
+ return (SET_APIC_LOGICAL_ID(id));
+}
+
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LdR and TPR before enabling
+ * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116). So here it goes...
+ */
+static void es7000_init_apic_ldr_cluster(void)
+{
+ unsigned long val;
+ int cpu = smp_processor_id();
+
+ apic_write(APIC_DFR, APIC_DFR_VALUE_CLUSTER);
+ val = calculate_ldr(cpu);
+ apic_write(APIC_LDR, val);
+}
+
+static void es7000_init_apic_ldr(void)
+{
+ unsigned long val;
+ int cpu = smp_processor_id();
+
+ apic_write(APIC_DFR, APIC_DFR_VALUE);
+ val = calculate_ldr(cpu);
+ apic_write(APIC_LDR, val);
+}
+
+static void es7000_setup_apic_routing(void)
+{
+ int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
+ printk("Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n",
+ (apic_version[apic] == 0x14) ?
+ "Physical Cluster" : "Logical Cluster",
+ nr_ioapics, cpus_addr(*es7000_target_cpus())[0]);
+}
+
+static int es7000_apicid_to_node(int logical_apicid)
+{
+ return 0;
+}
+
+
+static int es7000_cpu_present_to_apicid(int mps_cpu)
+{
+ if (!mps_cpu)
+ return boot_cpu_physical_apicid;
+ else if (mps_cpu < nr_cpu_ids)
+ return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
+ else
+ return BAD_APICID;
+}
+
+static physid_mask_t es7000_apicid_to_cpu_present(int phys_apicid)
+{
+ static int id = 0;
+ physid_mask_t mask;
+
+ mask = physid_mask_of_physid(id);
+ ++id;
+
+ return mask;
+}
+
+/* Mapping from cpu number to logical apicid */
+static int es7000_cpu_to_logical_apicid(int cpu)
+{
+#ifdef CONFIG_SMP
+ if (cpu >= nr_cpu_ids)
+ return BAD_APICID;
+ return (int)cpu_2_logical_apicid[cpu];
+#else
+ return logical_smp_processor_id();
+#endif
+}
+
+static physid_mask_t es7000_ioapic_phys_id_map(physid_mask_t phys_map)
+{
+ /* For clustered we don't have a good way to do this yet - hack */
+ return physids_promote(0xff);
+}
+
+static int es7000_check_phys_apicid_present(int cpu_physical_apicid)
+{
+ boot_cpu_physical_apicid = read_apic_id();
+ return (1);
+}
+
+static unsigned int
+es7000_cpu_mask_to_apicid_cluster(const struct cpumask *cpumask)
+{
+ int cpus_found = 0;
+ int num_bits_set;
+ int apicid;
+ int cpu;
+
+ num_bits_set = cpumask_weight(cpumask);
+ /* Return id to all */
+ if (num_bits_set == nr_cpu_ids)
+ return 0xFF;
+ /*
+ * The cpus in the mask must all be on the apic cluster. If are not
+ * on the same apicid cluster return default value of target_cpus():
+ */
+ cpu = cpumask_first(cpumask);
+ apicid = es7000_cpu_to_logical_apicid(cpu);
+
+ while (cpus_found < num_bits_set) {
+ if (cpumask_test_cpu(cpu, cpumask)) {
+ int new_apicid = es7000_cpu_to_logical_apicid(cpu);
+
+ if (apicid_cluster(apicid) !=
+ apicid_cluster(new_apicid)) {
+ printk ("%s: Not a valid mask!\n", __func__);
+
+ return 0xFF;
+ }
+ apicid = new_apicid;
+ cpus_found++;
+ }
+ cpu++;
}
+ return apicid;
}
+
+static unsigned int es7000_cpu_mask_to_apicid(const cpumask_t *cpumask)
+{
+ int cpus_found = 0;
+ int num_bits_set;
+ int apicid;
+ int cpu;
+
+ num_bits_set = cpus_weight(*cpumask);
+ /* Return id to all */
+ if (num_bits_set == nr_cpu_ids)
+ return es7000_cpu_to_logical_apicid(0);
+ /*
+ * The cpus in the mask must all be on the apic cluster. If are not
+ * on the same apicid cluster return default value of target_cpus():
+ */
+ cpu = first_cpu(*cpumask);
+ apicid = es7000_cpu_to_logical_apicid(cpu);
+ while (cpus_found < num_bits_set) {
+ if (cpu_isset(cpu, *cpumask)) {
+ int new_apicid = es7000_cpu_to_logical_apicid(cpu);
+
+ if (apicid_cluster(apicid) !=
+ apicid_cluster(new_apicid)) {
+ printk ("%s: Not a valid mask!\n", __func__);
+
+ return es7000_cpu_to_logical_apicid(0);
+ }
+ apicid = new_apicid;
+ cpus_found++;
+ }
+ cpu++;
+ }
+ return apicid;
+}
+
+static unsigned int
+es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask,
+ const struct cpumask *andmask)
+{
+ int apicid = es7000_cpu_to_logical_apicid(0);
+ cpumask_var_t cpumask;
+
+ if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
+ return apicid;
+
+ cpumask_and(cpumask, inmask, andmask);
+ cpumask_and(cpumask, cpumask, cpu_online_mask);
+ apicid = es7000_cpu_mask_to_apicid(cpumask);
+
+ free_cpumask_var(cpumask);
+
+ return apicid;
+}
+
+static int es7000_phys_pkg_id(int cpuid_apic, int index_msb)
+{
+ return cpuid_apic >> index_msb;
+}
+
+void __init es7000_update_genapic_to_cluster(void)
+{
+ apic->target_cpus = target_cpus_cluster;
+ apic->irq_delivery_mode = INT_DELIVERY_MODE_CLUSTER;
+ apic->irq_dest_mode = INT_DEST_MODE_CLUSTER;
+
+ apic->init_apic_ldr = es7000_init_apic_ldr_cluster;
+
+ apic->cpu_mask_to_apicid = es7000_cpu_mask_to_apicid_cluster;
+}
+
+static int probe_es7000(void)
+{
+ /* probed later in mptable/ACPI hooks */
+ return 0;
+}
+
+static __init int
+es7000_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid)
+{
+ if (mpc->oemptr) {
+ struct mpc_oemtable *oem_table =
+ (struct mpc_oemtable *)mpc->oemptr;
+
+ if (!strncmp(oem, "UNISYS", 6))
+ return parse_unisys_oem((char *)oem_table);
+ }
+ return 0;
+}
+
+#ifdef CONFIG_ACPI
+/* Hook from generic ACPI tables.c */
+static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ unsigned long oem_addr = 0;
+ int check_dsdt;
+ int ret = 0;
+
+ /* check dsdt at first to avoid clear fix_map for oem_addr */
+ check_dsdt = es7000_check_dsdt();
+
+ if (!find_unisys_acpi_oem_table(&oem_addr)) {
+ if (check_dsdt)
+ ret = parse_unisys_oem((char *)oem_addr);
+ else {
+ setup_unisys();
+ ret = 1;
+ }
+ /*
+ * we need to unmap it
+ */
+ unmap_unisys_acpi_oem_table(oem_addr);
+ }
+ return ret;
+}
+#else
+static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ return 0;
+}
+#endif
+
+
+struct genapic apic_es7000 = {
+
+ .name = "es7000",
+ .probe = probe_es7000,
+ .acpi_madt_oem_check = es7000_acpi_madt_oem_check,
+ .apic_id_registered = es7000_apic_id_registered,
+
+ .irq_delivery_mode = dest_Fixed,
+ /* phys delivery to target CPUs: */
+ .irq_dest_mode = 0,
+
+ .target_cpus = es7000_target_cpus,
+ .disable_esr = 1,
+ .dest_logical = 0,
+ .check_apicid_used = es7000_check_apicid_used,
+ .check_apicid_present = es7000_check_apicid_present,
+
+ .vector_allocation_domain = es7000_vector_allocation_domain,
+ .init_apic_ldr = es7000_init_apic_ldr,
+
+ .ioapic_phys_id_map = es7000_ioapic_phys_id_map,
+ .setup_apic_routing = es7000_setup_apic_routing,
+ .multi_timer_check = NULL,
+ .apicid_to_node = es7000_apicid_to_node,
+ .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid,
+ .cpu_present_to_apicid = es7000_cpu_present_to_apicid,
+ .apicid_to_cpu_present = es7000_apicid_to_cpu_present,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = es7000_check_phys_apicid_present,
+ .enable_apic_mode = es7000_enable_apic_mode,
+ .phys_pkg_id = es7000_phys_pkg_id,
+ .mps_oem_check = es7000_mps_oem_check,
+
+ .get_apic_id = es7000_get_apic_id,
+ .set_apic_id = NULL,
+ .apic_id_mask = 0xFF << 24,
+
+ .cpu_mask_to_apicid = es7000_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = es7000_send_IPI_mask,
+ .send_IPI_mask_allbutself = NULL,
+ .send_IPI_allbutself = es7000_send_IPI_allbutself,
+ .send_IPI_all = es7000_send_IPI_all,
+ .send_IPI_self = default_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+
+ .trampoline_phys_low = 0x467,
+ .trampoline_phys_high = 0x469,
+
+ .wait_for_init_deassert = es7000_wait_for_init_deassert,
+
+ /* Nothing to do for most platforms, since cleared by the INIT cycle: */
+ .smp_callin_clear_local_apic = NULL,
+ .store_NMI_vector = NULL,
+ .inquire_remote_apic = default_inquire_remote_apic,
+};
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index 2bced78b0b8e..820dea5d0ebe 100644
--- a/arch/x86/kernel/genapic_64.c
+++ b/arch/x86/kernel/genapic_64.c
@@ -29,10 +29,12 @@ extern struct genapic apic_x2xpic_uv_x;
extern struct genapic apic_x2apic_phys;
extern struct genapic apic_x2apic_cluster;
-struct genapic __read_mostly *genapic = &apic_flat;
+struct genapic __read_mostly *apic = &apic_flat;
static struct genapic *apic_probe[] __initdata = {
+#ifdef CONFIG_X86_UV
&apic_x2apic_uv_x,
+#endif
&apic_x2apic_phys,
&apic_x2apic_cluster,
&apic_physflat,
@@ -42,17 +44,17 @@ static struct genapic *apic_probe[] __initdata = {
/*
* Check the APIC IDs in bios_cpu_apicid and choose the APIC mode.
*/
-void __init setup_apic_routing(void)
+void __init default_setup_apic_routing(void)
{
- if (genapic == &apic_x2apic_phys || genapic == &apic_x2apic_cluster) {
+ if (apic == &apic_x2apic_phys || apic == &apic_x2apic_cluster) {
if (!intr_remapping_enabled)
- genapic = &apic_flat;
+ apic = &apic_flat;
}
- if (genapic == &apic_flat) {
+ if (apic == &apic_flat) {
if (max_physical_apicid >= 8)
- genapic = &apic_physflat;
- printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name);
+ apic = &apic_physflat;
+ printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
}
if (x86_quirks->update_genapic)
@@ -63,18 +65,18 @@ void __init setup_apic_routing(void)
void apic_send_IPI_self(int vector)
{
- __send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
+ __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
}
-int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
int i;
for (i = 0; apic_probe[i]; ++i) {
if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) {
- genapic = apic_probe[i];
+ apic = apic_probe[i];
printk(KERN_INFO "Setting APIC routing to %s.\n",
- genapic->name);
+ apic->name);
return 1;
}
}
diff --git a/arch/x86/kernel/genapic_flat_64.c b/arch/x86/kernel/genapic_flat_64.c
index 34185488e4fb..249d2d3c034c 100644
--- a/arch/x86/kernel/genapic_flat_64.c
+++ b/arch/x86/kernel/genapic_flat_64.c
@@ -19,7 +19,6 @@
#include <asm/smp.h>
#include <asm/ipi.h>
#include <asm/genapic.h>
-#include <mach_apicdef.h>
#ifdef CONFIG_ACPI
#include <acpi/acpi_bus.h>
@@ -74,7 +73,7 @@ static inline void _flat_send_IPI_mask(unsigned long mask, int vector)
unsigned long flags;
local_irq_save(flags);
- __send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL);
+ __default_send_IPI_dest_field(mask, vector, apic->dest_logical);
local_irq_restore(flags);
}
@@ -85,14 +84,15 @@ static void flat_send_IPI_mask(const struct cpumask *cpumask, int vector)
_flat_send_IPI_mask(mask, vector);
}
-static void flat_send_IPI_mask_allbutself(const struct cpumask *cpumask,
- int vector)
+static void
+ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector)
{
unsigned long mask = cpumask_bits(cpumask)[0];
int cpu = smp_processor_id();
if (cpu < BITS_PER_LONG)
clear_bit(cpu, &mask);
+
_flat_send_IPI_mask(mask, vector);
}
@@ -114,23 +114,27 @@ static void flat_send_IPI_allbutself(int vector)
_flat_send_IPI_mask(mask, vector);
}
} else if (num_online_cpus() > 1) {
- __send_IPI_shortcut(APIC_DEST_ALLBUT, vector,APIC_DEST_LOGICAL);
+ __default_send_IPI_shortcut(APIC_DEST_ALLBUT,
+ vector, apic->dest_logical);
}
}
static void flat_send_IPI_all(int vector)
{
- if (vector == NMI_VECTOR)
+ if (vector == NMI_VECTOR) {
flat_send_IPI_mask(cpu_online_mask, vector);
- else
- __send_IPI_shortcut(APIC_DEST_ALLINC, vector, APIC_DEST_LOGICAL);
+ } else {
+ __default_send_IPI_shortcut(APIC_DEST_ALLINC,
+ vector, apic->dest_logical);
+ }
}
-static unsigned int get_apic_id(unsigned long x)
+static unsigned int flat_get_apic_id(unsigned long x)
{
unsigned int id;
id = (((x)>>24) & 0xFFu);
+
return id;
}
@@ -146,7 +150,7 @@ static unsigned int read_xapic_id(void)
{
unsigned int id;
- id = get_apic_id(apic_read(APIC_ID));
+ id = flat_get_apic_id(apic_read(APIC_ID));
return id;
}
@@ -169,31 +173,62 @@ static unsigned int flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
return mask1 & mask2;
}
-static unsigned int phys_pkg_id(int index_msb)
+static int flat_phys_pkg_id(int initial_apic_id, int index_msb)
{
return hard_smp_processor_id() >> index_msb;
}
struct genapic apic_flat = {
- .name = "flat",
- .acpi_madt_oem_check = flat_acpi_madt_oem_check,
- .int_delivery_mode = dest_LowestPrio,
- .int_dest_mode = (APIC_DEST_LOGICAL != 0),
- .target_cpus = flat_target_cpus,
- .vector_allocation_domain = flat_vector_allocation_domain,
- .apic_id_registered = flat_apic_id_registered,
- .init_apic_ldr = flat_init_apic_ldr,
- .send_IPI_all = flat_send_IPI_all,
- .send_IPI_allbutself = flat_send_IPI_allbutself,
- .send_IPI_mask = flat_send_IPI_mask,
- .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself,
- .send_IPI_self = apic_send_IPI_self,
- .cpu_mask_to_apicid = flat_cpu_mask_to_apicid,
- .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and,
- .phys_pkg_id = phys_pkg_id,
- .get_apic_id = get_apic_id,
- .set_apic_id = set_apic_id,
- .apic_id_mask = (0xFFu<<24),
+ .name = "flat",
+ .probe = NULL,
+ .acpi_madt_oem_check = flat_acpi_madt_oem_check,
+ .apic_id_registered = flat_apic_id_registered,
+
+ .irq_delivery_mode = dest_LowestPrio,
+ .irq_dest_mode = 1, /* logical */
+
+ .target_cpus = flat_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = APIC_DEST_LOGICAL,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = flat_vector_allocation_domain,
+ .init_apic_ldr = flat_init_apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = flat_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = flat_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFu << 24,
+
+ .cpu_mask_to_apicid = flat_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = flat_send_IPI_mask,
+ .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = flat_send_IPI_allbutself,
+ .send_IPI_all = flat_send_IPI_all,
+ .send_IPI_self = apic_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .store_NMI_vector = NULL,
+ .inquire_remote_apic = NULL,
};
/*
@@ -232,18 +267,18 @@ static void physflat_vector_allocation_domain(int cpu, struct cpumask *retmask)
static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector)
{
- send_IPI_mask_sequence(cpumask, vector);
+ default_send_IPI_mask_sequence_phys(cpumask, vector);
}
static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask,
int vector)
{
- send_IPI_mask_allbutself(cpumask, vector);
+ default_send_IPI_mask_allbutself_phys(cpumask, vector);
}
static void physflat_send_IPI_allbutself(int vector)
{
- send_IPI_mask_allbutself(cpu_online_mask, vector);
+ default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
}
static void physflat_send_IPI_all(int vector)
@@ -276,32 +311,67 @@ physflat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
* We're using fixed IRQ delivery, can only return one phys APIC ID.
* May as well be the first.
*/
- for_each_cpu_and(cpu, cpumask, andmask)
+ for_each_cpu_and(cpu, cpumask, andmask) {
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
+ }
if (cpu < nr_cpu_ids)
return per_cpu(x86_cpu_to_apicid, cpu);
+
return BAD_APICID;
}
struct genapic apic_physflat = {
- .name = "physical flat",
- .acpi_madt_oem_check = physflat_acpi_madt_oem_check,
- .int_delivery_mode = dest_Fixed,
- .int_dest_mode = (APIC_DEST_PHYSICAL != 0),
- .target_cpus = physflat_target_cpus,
- .vector_allocation_domain = physflat_vector_allocation_domain,
- .apic_id_registered = flat_apic_id_registered,
- .init_apic_ldr = flat_init_apic_ldr,/*not needed, but shouldn't hurt*/
- .send_IPI_all = physflat_send_IPI_all,
- .send_IPI_allbutself = physflat_send_IPI_allbutself,
- .send_IPI_mask = physflat_send_IPI_mask,
- .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself,
- .send_IPI_self = apic_send_IPI_self,
- .cpu_mask_to_apicid = physflat_cpu_mask_to_apicid,
- .cpu_mask_to_apicid_and = physflat_cpu_mask_to_apicid_and,
- .phys_pkg_id = phys_pkg_id,
- .get_apic_id = get_apic_id,
- .set_apic_id = set_apic_id,
- .apic_id_mask = (0xFFu<<24),
+
+ .name = "physical flat",
+ .probe = NULL,
+ .acpi_madt_oem_check = physflat_acpi_madt_oem_check,
+ .apic_id_registered = flat_apic_id_registered,
+
+ .irq_delivery_mode = dest_Fixed,
+ .irq_dest_mode = 0, /* physical */
+
+ .target_cpus = physflat_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = 0,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = physflat_vector_allocation_domain,
+ /* not needed, but shouldn't hurt: */
+ .init_apic_ldr = flat_init_apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = flat_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = flat_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFu << 24,
+
+ .cpu_mask_to_apicid = physflat_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = physflat_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = physflat_send_IPI_mask,
+ .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = physflat_send_IPI_allbutself,
+ .send_IPI_all = physflat_send_IPI_all,
+ .send_IPI_self = apic_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .store_NMI_vector = NULL,
+ .inquire_remote_apic = NULL,
};
diff --git a/arch/x86/kernel/genx2apic_cluster.c b/arch/x86/kernel/genx2apic_cluster.c
index 6ce497cc372d..7c87156b6411 100644
--- a/arch/x86/kernel/genx2apic_cluster.c
+++ b/arch/x86/kernel/genx2apic_cluster.c
@@ -36,8 +36,8 @@ static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)
cpumask_set_cpu(cpu, retmask);
}
-static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
- unsigned int dest)
+static void
+ __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest)
{
unsigned long cfg;
@@ -57,45 +57,50 @@ static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
*/
static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
{
- unsigned long flags;
unsigned long query_cpu;
+ unsigned long flags;
local_irq_save(flags);
- for_each_cpu(query_cpu, mask)
+ for_each_cpu(query_cpu, mask) {
__x2apic_send_IPI_dest(
per_cpu(x86_cpu_to_logical_apicid, query_cpu),
- vector, APIC_DEST_LOGICAL);
+ vector, apic->dest_logical);
+ }
local_irq_restore(flags);
}
-static void x2apic_send_IPI_mask_allbutself(const struct cpumask *mask,
- int vector)
+static void
+ x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
{
- unsigned long flags;
- unsigned long query_cpu;
unsigned long this_cpu = smp_processor_id();
+ unsigned long query_cpu;
+ unsigned long flags;
local_irq_save(flags);
- for_each_cpu(query_cpu, mask)
- if (query_cpu != this_cpu)
- __x2apic_send_IPI_dest(
+ for_each_cpu(query_cpu, mask) {
+ if (query_cpu == this_cpu)
+ continue;
+ __x2apic_send_IPI_dest(
per_cpu(x86_cpu_to_logical_apicid, query_cpu),
- vector, APIC_DEST_LOGICAL);
+ vector, apic->dest_logical);
+ }
local_irq_restore(flags);
}
static void x2apic_send_IPI_allbutself(int vector)
{
- unsigned long flags;
- unsigned long query_cpu;
unsigned long this_cpu = smp_processor_id();
+ unsigned long query_cpu;
+ unsigned long flags;
local_irq_save(flags);
- for_each_online_cpu(query_cpu)
- if (query_cpu != this_cpu)
- __x2apic_send_IPI_dest(
+ for_each_online_cpu(query_cpu) {
+ if (query_cpu == this_cpu)
+ continue;
+ __x2apic_send_IPI_dest(
per_cpu(x86_cpu_to_logical_apicid, query_cpu),
- vector, APIC_DEST_LOGICAL);
+ vector, apic->dest_logical);
+ }
local_irq_restore(flags);
}
@@ -111,21 +116,21 @@ static int x2apic_apic_id_registered(void)
static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask)
{
- int cpu;
-
/*
* We're using fixed IRQ delivery, can only return one logical APIC ID.
* May as well be the first.
*/
- cpu = cpumask_first(cpumask);
+ int cpu = cpumask_first(cpumask);
+
if ((unsigned)cpu < nr_cpu_ids)
return per_cpu(x86_cpu_to_logical_apicid, cpu);
else
return BAD_APICID;
}
-static unsigned int x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
- const struct cpumask *andmask)
+static unsigned int
+x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
{
int cpu;
@@ -133,15 +138,18 @@ static unsigned int x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
* We're using fixed IRQ delivery, can only return one logical APIC ID.
* May as well be the first.
*/
- for_each_cpu_and(cpu, cpumask, andmask)
+ for_each_cpu_and(cpu, cpumask, andmask) {
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
+ }
+
if (cpu < nr_cpu_ids)
return per_cpu(x86_cpu_to_logical_apicid, cpu);
+
return BAD_APICID;
}
-static unsigned int get_apic_id(unsigned long x)
+static unsigned int x2apic_cluster_phys_get_apic_id(unsigned long x)
{
unsigned int id;
@@ -157,7 +165,7 @@ static unsigned long set_apic_id(unsigned int id)
return x;
}
-static unsigned int phys_pkg_id(int index_msb)
+static int x2apic_cluster_phys_pkg_id(int initial_apicid, int index_msb)
{
return current_cpu_data.initial_apicid >> index_msb;
}
@@ -172,27 +180,58 @@ static void init_x2apic_ldr(void)
int cpu = smp_processor_id();
per_cpu(x86_cpu_to_logical_apicid, cpu) = apic_read(APIC_LDR);
- return;
}
struct genapic apic_x2apic_cluster = {
- .name = "cluster x2apic",
- .acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
- .int_delivery_mode = dest_LowestPrio,
- .int_dest_mode = (APIC_DEST_LOGICAL != 0),
- .target_cpus = x2apic_target_cpus,
- .vector_allocation_domain = x2apic_vector_allocation_domain,
- .apic_id_registered = x2apic_apic_id_registered,
- .init_apic_ldr = init_x2apic_ldr,
- .send_IPI_all = x2apic_send_IPI_all,
- .send_IPI_allbutself = x2apic_send_IPI_allbutself,
- .send_IPI_mask = x2apic_send_IPI_mask,
- .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
- .send_IPI_self = x2apic_send_IPI_self,
- .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
- .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
- .phys_pkg_id = phys_pkg_id,
- .get_apic_id = get_apic_id,
- .set_apic_id = set_apic_id,
- .apic_id_mask = (0xFFFFFFFFu),
+
+ .name = "cluster x2apic",
+ .probe = NULL,
+ .acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
+ .apic_id_registered = x2apic_apic_id_registered,
+
+ .irq_delivery_mode = dest_LowestPrio,
+ .irq_dest_mode = 1, /* logical */
+
+ .target_cpus = x2apic_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = APIC_DEST_LOGICAL,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = x2apic_vector_allocation_domain,
+ .init_apic_ldr = init_x2apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = x2apic_cluster_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = x2apic_cluster_phys_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFFFFFFFu,
+
+ .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = x2apic_send_IPI_mask,
+ .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = x2apic_send_IPI_allbutself,
+ .send_IPI_all = x2apic_send_IPI_all,
+ .send_IPI_self = x2apic_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .store_NMI_vector = NULL,
+ .inquire_remote_apic = NULL,
};
diff --git a/arch/x86/kernel/genx2apic_phys.c b/arch/x86/kernel/genx2apic_phys.c
index 21bcc0e098ba..5cbae8aa0408 100644
--- a/arch/x86/kernel/genx2apic_phys.c
+++ b/arch/x86/kernel/genx2apic_phys.c
@@ -55,8 +55,8 @@ static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
{
- unsigned long flags;
unsigned long query_cpu;
+ unsigned long flags;
local_irq_save(flags);
for_each_cpu(query_cpu, mask) {
@@ -66,12 +66,12 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
local_irq_restore(flags);
}
-static void x2apic_send_IPI_mask_allbutself(const struct cpumask *mask,
- int vector)
+static void
+ x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
{
- unsigned long flags;
- unsigned long query_cpu;
unsigned long this_cpu = smp_processor_id();
+ unsigned long query_cpu;
+ unsigned long flags;
local_irq_save(flags);
for_each_cpu(query_cpu, mask) {
@@ -85,16 +85,17 @@ static void x2apic_send_IPI_mask_allbutself(const struct cpumask *mask,
static void x2apic_send_IPI_allbutself(int vector)
{
- unsigned long flags;
- unsigned long query_cpu;
unsigned long this_cpu = smp_processor_id();
+ unsigned long query_cpu;
+ unsigned long flags;
local_irq_save(flags);
- for_each_online_cpu(query_cpu)
- if (query_cpu != this_cpu)
- __x2apic_send_IPI_dest(
- per_cpu(x86_cpu_to_apicid, query_cpu),
- vector, APIC_DEST_PHYSICAL);
+ for_each_online_cpu(query_cpu) {
+ if (query_cpu == this_cpu)
+ continue;
+ __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu),
+ vector, APIC_DEST_PHYSICAL);
+ }
local_irq_restore(flags);
}
@@ -110,21 +111,21 @@ static int x2apic_apic_id_registered(void)
static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask)
{
- int cpu;
-
/*
* We're using fixed IRQ delivery, can only return one phys APIC ID.
* May as well be the first.
*/
- cpu = cpumask_first(cpumask);
+ int cpu = cpumask_first(cpumask);
+
if ((unsigned)cpu < nr_cpu_ids)
return per_cpu(x86_cpu_to_apicid, cpu);
else
return BAD_APICID;
}
-static unsigned int x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
- const struct cpumask *andmask)
+static unsigned int
+x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
{
int cpu;
@@ -132,31 +133,28 @@ static unsigned int x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
* We're using fixed IRQ delivery, can only return one phys APIC ID.
* May as well be the first.
*/
- for_each_cpu_and(cpu, cpumask, andmask)
+ for_each_cpu_and(cpu, cpumask, andmask) {
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
+ }
+
if (cpu < nr_cpu_ids)
return per_cpu(x86_cpu_to_apicid, cpu);
+
return BAD_APICID;
}
-static unsigned int get_apic_id(unsigned long x)
+static unsigned int x2apic_phys_get_apic_id(unsigned long x)
{
- unsigned int id;
-
- id = x;
- return id;
+ return x;
}
static unsigned long set_apic_id(unsigned int id)
{
- unsigned long x;
-
- x = id;
- return x;
+ return id;
}
-static unsigned int phys_pkg_id(int index_msb)
+static int x2apic_phys_pkg_id(int initial_apicid, int index_msb)
{
return current_cpu_data.initial_apicid >> index_msb;
}
@@ -168,27 +166,58 @@ static void x2apic_send_IPI_self(int vector)
static void init_x2apic_ldr(void)
{
- return;
}
struct genapic apic_x2apic_phys = {
- .name = "physical x2apic",
- .acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
- .int_delivery_mode = dest_Fixed,
- .int_dest_mode = (APIC_DEST_PHYSICAL != 0),
- .target_cpus = x2apic_target_cpus,
- .vector_allocation_domain = x2apic_vector_allocation_domain,
- .apic_id_registered = x2apic_apic_id_registered,
- .init_apic_ldr = init_x2apic_ldr,
- .send_IPI_all = x2apic_send_IPI_all,
- .send_IPI_allbutself = x2apic_send_IPI_allbutself,
- .send_IPI_mask = x2apic_send_IPI_mask,
- .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
- .send_IPI_self = x2apic_send_IPI_self,
- .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
- .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
- .phys_pkg_id = phys_pkg_id,
- .get_apic_id = get_apic_id,
- .set_apic_id = set_apic_id,
- .apic_id_mask = (0xFFFFFFFFu),
+
+ .name = "physical x2apic",
+ .probe = NULL,
+ .acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
+ .apic_id_registered = x2apic_apic_id_registered,
+
+ .irq_delivery_mode = dest_Fixed,
+ .irq_dest_mode = 0, /* physical */
+
+ .target_cpus = x2apic_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = 0,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = x2apic_vector_allocation_domain,
+ .init_apic_ldr = init_x2apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = x2apic_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = x2apic_phys_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFFFFFFFu,
+
+ .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = x2apic_send_IPI_mask,
+ .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = x2apic_send_IPI_allbutself,
+ .send_IPI_all = x2apic_send_IPI_all,
+ .send_IPI_self = x2apic_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .store_NMI_vector = NULL,
+ .inquire_remote_apic = NULL,
};
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index b193e082f6ce..6adb5e6f4d92 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -25,6 +25,7 @@
#include <asm/ipi.h>
#include <asm/genapic.h>
#include <asm/pgtable.h>
+#include <asm/uv/uv.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
#include <asm/uv/bios.h>
@@ -117,12 +118,13 @@ static void uv_send_IPI_one(int cpu, int vector)
int pnode;
apicid = per_cpu(x86_cpu_to_apicid, cpu);
- lapicid = apicid & 0x3f; /* ZZZ macro needed */
+ lapicid = apicid & 0x3f; /* ZZZ macro needed */
pnode = uv_apicid_to_pnode(apicid);
- val =
- (1UL << UVH_IPI_INT_SEND_SHFT) | (lapicid <<
- UVH_IPI_INT_APIC_ID_SHFT) |
- (vector << UVH_IPI_INT_VECTOR_SHFT);
+
+ val = ( 1UL << UVH_IPI_INT_SEND_SHFT ) |
+ ( lapicid << UVH_IPI_INT_APIC_ID_SHFT ) |
+ ( vector << UVH_IPI_INT_VECTOR_SHFT );
+
uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
}
@@ -136,22 +138,24 @@ static void uv_send_IPI_mask(const struct cpumask *mask, int vector)
static void uv_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
{
- unsigned int cpu;
unsigned int this_cpu = smp_processor_id();
+ unsigned int cpu;
- for_each_cpu(cpu, mask)
+ for_each_cpu(cpu, mask) {
if (cpu != this_cpu)
uv_send_IPI_one(cpu, vector);
+ }
}
static void uv_send_IPI_allbutself(int vector)
{
- unsigned int cpu;
unsigned int this_cpu = smp_processor_id();
+ unsigned int cpu;
- for_each_online_cpu(cpu)
+ for_each_online_cpu(cpu) {
if (cpu != this_cpu)
uv_send_IPI_one(cpu, vector);
+ }
}
static void uv_send_IPI_all(int vector)
@@ -170,21 +174,21 @@ static void uv_init_apic_ldr(void)
static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask)
{
- int cpu;
-
/*
* We're using fixed IRQ delivery, can only return one phys APIC ID.
* May as well be the first.
*/
- cpu = cpumask_first(cpumask);
+ int cpu = cpumask_first(cpumask);
+
if ((unsigned)cpu < nr_cpu_ids)
return per_cpu(x86_cpu_to_apicid, cpu);
else
return BAD_APICID;
}
-static unsigned int uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
- const struct cpumask *andmask)
+static unsigned int
+uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
{
int cpu;
@@ -192,15 +196,17 @@ static unsigned int uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
* We're using fixed IRQ delivery, can only return one phys APIC ID.
* May as well be the first.
*/
- for_each_cpu_and(cpu, cpumask, andmask)
+ for_each_cpu_and(cpu, cpumask, andmask) {
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
+ }
if (cpu < nr_cpu_ids)
return per_cpu(x86_cpu_to_apicid, cpu);
+
return BAD_APICID;
}
-static unsigned int get_apic_id(unsigned long x)
+static unsigned int x2apic_get_apic_id(unsigned long x)
{
unsigned int id;
@@ -222,10 +228,10 @@ static unsigned long set_apic_id(unsigned int id)
static unsigned int uv_read_apic_id(void)
{
- return get_apic_id(apic_read(APIC_ID));
+ return x2apic_get_apic_id(apic_read(APIC_ID));
}
-static unsigned int phys_pkg_id(int index_msb)
+static int uv_phys_pkg_id(int initial_apicid, int index_msb)
{
return uv_read_apic_id() >> index_msb;
}
@@ -236,25 +242,57 @@ static void uv_send_IPI_self(int vector)
}
struct genapic apic_x2apic_uv_x = {
- .name = "UV large system",
- .acpi_madt_oem_check = uv_acpi_madt_oem_check,
- .int_delivery_mode = dest_Fixed,
- .int_dest_mode = (APIC_DEST_PHYSICAL != 0),
- .target_cpus = uv_target_cpus,
- .vector_allocation_domain = uv_vector_allocation_domain,
- .apic_id_registered = uv_apic_id_registered,
- .init_apic_ldr = uv_init_apic_ldr,
- .send_IPI_all = uv_send_IPI_all,
- .send_IPI_allbutself = uv_send_IPI_allbutself,
- .send_IPI_mask = uv_send_IPI_mask,
- .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself,
- .send_IPI_self = uv_send_IPI_self,
- .cpu_mask_to_apicid = uv_cpu_mask_to_apicid,
- .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and,
- .phys_pkg_id = phys_pkg_id,
- .get_apic_id = get_apic_id,
- .set_apic_id = set_apic_id,
- .apic_id_mask = (0xFFFFFFFFu),
+
+ .name = "UV large system",
+ .probe = NULL,
+ .acpi_madt_oem_check = uv_acpi_madt_oem_check,
+ .apic_id_registered = uv_apic_id_registered,
+
+ .irq_delivery_mode = dest_Fixed,
+ .irq_dest_mode = 1, /* logical */
+
+ .target_cpus = uv_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = APIC_DEST_LOGICAL,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = uv_vector_allocation_domain,
+ .init_apic_ldr = uv_init_apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = uv_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = x2apic_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFFFFFFFu,
+
+ .cpu_mask_to_apicid = uv_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = uv_send_IPI_mask,
+ .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = uv_send_IPI_allbutself,
+ .send_IPI_all = uv_send_IPI_all,
+ .send_IPI_self = uv_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .store_NMI_vector = NULL,
+ .inquire_remote_apic = NULL,
};
static __cpuinit void set_x2apic_extra_bits(int pnode)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b9a4d8c4b935..f5b272247690 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -26,27 +26,6 @@
#include <asm/bios_ebda.h>
#include <asm/trampoline.h>
-/* boot cpu pda */
-static struct x8664_pda _boot_cpu_pda;
-
-#ifdef CONFIG_SMP
-/*
- * We install an empty cpu_pda pointer table to indicate to early users
- * (numa_set_node) that the cpu_pda pointer table for cpus other than
- * the boot cpu is not yet setup.
- */
-static struct x8664_pda *__cpu_pda[NR_CPUS] __initdata;
-#else
-static struct x8664_pda *__cpu_pda[NR_CPUS] __read_mostly;
-#endif
-
-void __init x86_64_init_pda(void)
-{
- _cpu_pda = __cpu_pda;
- cpu_pda(0) = &_boot_cpu_pda;
- pda_init(0);
-}
-
static void __init zap_identity_mappings(void)
{
pgd_t *pgd = pgd_offset_k(0UL);
@@ -112,8 +91,6 @@ void __init x86_64_start_kernel(char * real_mode_data)
if (console_loglevel == 10)
early_printk("Kernel alive\n");
- x86_64_init_pda();
-
x86_64_start_reservations(real_mode_data);
}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index e835b4eea70b..722464c520cf 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -429,12 +429,14 @@ is386: movl $2,%ecx # set MP
ljmp $(__KERNEL_CS),$1f
1: movl $(__KERNEL_DS),%eax # reload all the segment registers
movl %eax,%ss # after changing gdt.
- movl %eax,%fs # gets reset once there's real percpu
movl $(__USER_DS),%eax # DS/ES contains default USER segment
movl %eax,%ds
movl %eax,%es
+ movl $(__KERNEL_PERCPU), %eax
+ movl %eax,%fs # set this cpu's percpu
+
xorl %eax,%eax # Clear GS and LDT
movl %eax,%gs
lldt %ax
@@ -446,8 +448,6 @@ is386: movl $2,%ecx # set MP
movb $1, ready
cmpb $0,%cl # the first CPU calls start_kernel
je 1f
- movl $(__KERNEL_PERCPU), %eax
- movl %eax,%fs # set this cpu's percpu
movl (stack_start), %esp
1:
#endif /* CONFIG_SMP */
@@ -548,12 +548,8 @@ early_fault:
pushl %eax
pushl %edx /* trapno */
pushl $fault_msg
-#ifdef CONFIG_EARLY_PRINTK
- call early_printk
-#else
call printk
#endif
-#endif
call dump_stack
hlt_loop:
hlt
@@ -580,11 +576,10 @@ ignore_int:
pushl 32(%esp)
pushl 40(%esp)
pushl $int_msg
-#ifdef CONFIG_EARLY_PRINTK
- call early_printk
-#else
call printk
-#endif
+
+ call dump_stack
+
addl $(5*4),%esp
popl %ds
popl %es
@@ -660,7 +655,7 @@ early_recursion_flag:
.long 0
int_msg:
- .asciz "Unknown interrupt or fault at EIP %p %p %p\n"
+ .asciz "Unknown interrupt or fault at: %p %p %p\n"
fault_msg:
/* fault info: */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 0e275d495563..a0a2b5ca9b7d 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -19,6 +19,7 @@
#include <asm/msr.h>
#include <asm/cache.h>
#include <asm/processor-flags.h>
+#include <asm/percpu.h>
#ifdef CONFIG_PARAVIRT
#include <asm/asm-offsets.h>
@@ -204,6 +205,19 @@ ENTRY(secondary_startup_64)
pushq $0
popfq
+#ifdef CONFIG_SMP
+ /*
+ * Fix up static pointers that need __per_cpu_load added. The assembler
+ * is unable to do this directly. This is only needed for the boot cpu.
+ * These values are set up with the correct base addresses by C code for
+ * secondary cpus.
+ */
+ movq initial_gs(%rip), %rax
+ cmpl $0, per_cpu__cpu_number(%rax)
+ jne 1f
+ addq %rax, early_gdt_descr_base(%rip)
+1:
+#endif
/*
* We must switch to a new descriptor in kernel space for the GDT
* because soon the kernel won't have access anymore to the userspace
@@ -226,12 +240,15 @@ ENTRY(secondary_startup_64)
movl %eax,%fs
movl %eax,%gs
- /*
- * Setup up a dummy PDA. this is just for some early bootup code
- * that does in_interrupt()
- */
+ /* Set up %gs.
+ *
+ * The base of %gs always points to the bottom of the irqstack
+ * union. If the stack protector canary is enabled, it is
+ * located at %gs:40. Note that, on SMP, the boot cpu uses
+ * init data section till per cpu areas are set up.
+ */
movl $MSR_GS_BASE,%ecx
- movq $empty_zero_page,%rax
+ movq initial_gs(%rip),%rax
movq %rax,%rdx
shrq $32,%rdx
wrmsr
@@ -257,6 +274,12 @@ ENTRY(secondary_startup_64)
.align 8
ENTRY(initial_code)
.quad x86_64_start_kernel
+ ENTRY(initial_gs)
+#ifdef CONFIG_SMP
+ .quad __per_cpu_load
+#else
+ .quad PER_CPU_VAR(irq_stack_union)
+#endif
__FINITDATA
ENTRY(stack_start)
@@ -401,7 +424,8 @@ NEXT_PAGE(level2_spare_pgt)
.globl early_gdt_descr
early_gdt_descr:
.word GDT_ENTRIES*8-1
- .quad per_cpu__gdt_page
+early_gdt_descr_base:
+ .quad per_cpu__gdt_page
ENTRY(phys_base)
/* This must match the first entry in level2_kernel_pgt */
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 9b0c480c383b..9578d33f20a0 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -1,7 +1,7 @@
/*
* Intel IO-APIC support for multi-Pentium hosts.
*
- * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo
+ * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
*
* Many thanks to Stig Venaas for trying out countless experimental
* patches and reporting/debugging problems patiently!
@@ -46,6 +46,7 @@
#include <asm/idle.h>
#include <asm/io.h>
#include <asm/smp.h>
+#include <asm/cpu.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/acpi.h>
@@ -61,9 +62,7 @@
#include <asm/uv/uv_hub.h>
#include <asm/uv/uv_irq.h>
-#include <mach_ipi.h>
-#include <mach_apic.h>
-#include <mach_apicdef.h>
+#include <asm/genapic.h>
#define __apicdebuginit(type) static type __init
@@ -82,11 +81,11 @@ static DEFINE_SPINLOCK(vector_lock);
int nr_ioapic_registers[MAX_IO_APICS];
/* I/O APIC entries */
-struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
int nr_ioapics;
/* MP IRQ source entries */
-struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
/* # of MP IRQ source entries */
int mp_irq_entries;
@@ -99,10 +98,19 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
int skip_ioapic_setup;
+void arch_disable_smp_support(void)
+{
+#ifdef CONFIG_PCI
+ noioapicquirk = 1;
+ noioapicreroute = -1;
+#endif
+ skip_ioapic_setup = 1;
+}
+
static int __init parse_noapic(char *str)
{
/* disable IO-APIC */
- disable_ioapic_setup();
+ arch_disable_smp_support();
return 0;
}
early_param("noapic", parse_noapic);
@@ -356,7 +364,7 @@ set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
if (!cfg->move_in_progress) {
/* it means that domain is not changed */
- if (!cpumask_intersects(&desc->affinity, mask))
+ if (!cpumask_intersects(desc->affinity, mask))
cfg->move_desc_pending = 1;
}
}
@@ -386,7 +394,7 @@ struct io_apic {
static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
{
return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
- + (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK);
+ + (mp_ioapics[idx].apicaddr & ~PAGE_MASK);
}
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
@@ -513,11 +521,11 @@ static void send_cleanup_vector(struct irq_cfg *cfg)
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)
- send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
+ 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);
- send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+ apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
free_cpumask_var(cleanup_mask);
}
cfg->move_in_progress = 0;
@@ -562,8 +570,9 @@ 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.
+ * 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)
@@ -579,9 +588,10 @@ set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
if (assign_irq_vector(irq, cfg, mask))
return BAD_APICID;
- cpumask_and(&desc->affinity, cfg->domain, mask);
+ cpumask_and(desc->affinity, cfg->domain, mask);
set_extra_move_desc(desc, mask);
- return cpu_mask_to_apicid_and(&desc->affinity, cpu_online_mask);
+
+ return apic->cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask);
}
static void
@@ -796,23 +806,6 @@ static void clear_IO_APIC (void)
clear_IO_APIC_pin(apic, pin);
}
-#if !defined(CONFIG_SMP) && defined(CONFIG_X86_32)
-void send_IPI_self(int vector)
-{
- unsigned int cfg;
-
- /*
- * Wait for idle.
- */
- apic_wait_icr_idle();
- cfg = APIC_DM_FIXED | APIC_DEST_SELF | vector | APIC_DEST_LOGICAL;
- /*
- * Send the IPI. The write to APIC_ICR fires this off.
- */
- apic_write(APIC_ICR, cfg);
-}
-#endif /* !CONFIG_SMP && CONFIG_X86_32*/
-
#ifdef CONFIG_X86_32
/*
* support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to
@@ -944,10 +937,10 @@ static int find_irq_entry(int apic, int pin, int type)
int i;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mp_irqtype == type &&
- (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid ||
- mp_irqs[i].mp_dstapic == MP_APIC_ALL) &&
- mp_irqs[i].mp_dstirq == pin)
+ if (mp_irqs[i].irqtype == type &&
+ (mp_irqs[i].dstapic == mp_ioapics[apic].apicid ||
+ mp_irqs[i].dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].dstirq == pin)
return i;
return -1;
@@ -961,13 +954,13 @@ static int __init find_isa_irq_pin(int irq, int type)
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mp_srcbus;
+ int lbus = mp_irqs[i].srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mp_irqtype == type) &&
- (mp_irqs[i].mp_srcbusirq == irq))
+ (mp_irqs[i].irqtype == type) &&
+ (mp_irqs[i].srcbusirq == irq))
- return mp_irqs[i].mp_dstirq;
+ return mp_irqs[i].dstirq;
}
return -1;
}
@@ -977,17 +970,17 @@ static int __init find_isa_irq_apic(int irq, int type)
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mp_srcbus;
+ int lbus = mp_irqs[i].srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mp_irqtype == type) &&
- (mp_irqs[i].mp_srcbusirq == irq))
+ (mp_irqs[i].irqtype == type) &&
+ (mp_irqs[i].srcbusirq == irq))
break;
}
if (i < mp_irq_entries) {
int apic;
for(apic = 0; apic < nr_ioapics; apic++) {
- if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
+ if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic)
return apic;
}
}
@@ -1012,23 +1005,23 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
return -1;
}
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mp_srcbus;
+ int lbus = mp_irqs[i].srcbus;
for (apic = 0; apic < nr_ioapics; apic++)
- if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic ||
- mp_irqs[i].mp_dstapic == MP_APIC_ALL)
+ 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].mp_irqtype &&
+ !mp_irqs[i].irqtype &&
(bus == lbus) &&
- (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq);
+ (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].mp_srcbusirq & 3))
+ if (pin == (mp_irqs[i].srcbusirq & 3))
return irq;
/*
* Use the first all-but-pin matching entry as a
@@ -1071,7 +1064,7 @@ static int EISA_ELCR(unsigned int irq)
* EISA conforming in the MP table, that means its trigger type must
* be read in from the ELCR */
-#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mp_srcbusirq))
+#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq))
#define default_EISA_polarity(idx) default_ISA_polarity(idx)
/* PCI interrupts are always polarity one level triggered,
@@ -1088,13 +1081,13 @@ static int EISA_ELCR(unsigned int irq)
static int MPBIOS_polarity(int idx)
{
- int bus = mp_irqs[idx].mp_srcbus;
+ int bus = mp_irqs[idx].srcbus;
int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].mp_irqflag & 3)
+ switch (mp_irqs[idx].irqflag & 3)
{
case 0: /* conforms, ie. bus-type dependent polarity */
if (test_bit(bus, mp_bus_not_pci))
@@ -1130,13 +1123,13 @@ static int MPBIOS_polarity(int idx)
static int MPBIOS_trigger(int idx)
{
- int bus = mp_irqs[idx].mp_srcbus;
+ int bus = mp_irqs[idx].srcbus;
int trigger;
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].mp_irqflag>>2) & 3)
+ switch ((mp_irqs[idx].irqflag>>2) & 3)
{
case 0: /* conforms, ie. bus-type dependent */
if (test_bit(bus, mp_bus_not_pci))
@@ -1214,16 +1207,16 @@ int (*ioapic_renumber_irq)(int ioapic, int irq);
static int pin_2_irq(int idx, int apic, int pin)
{
int irq, i;
- int bus = mp_irqs[idx].mp_srcbus;
+ int bus = mp_irqs[idx].srcbus;
/*
* Debugging check, we are in big trouble if this message pops up!
*/
- if (mp_irqs[idx].mp_dstirq != pin)
+ if (mp_irqs[idx].dstirq != pin)
printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
if (test_bit(bus, mp_bus_not_pci)) {
- irq = mp_irqs[idx].mp_srcbusirq;
+ irq = mp_irqs[idx].srcbusirq;
} else {
/*
* PCI IRQs are mapped in order
@@ -1315,7 +1308,7 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
int new_cpu;
int vector, offset;
- vector_allocation_domain(cpu, tmp_mask);
+ apic->vector_allocation_domain(cpu, tmp_mask);
vector = current_vector;
offset = current_offset;
@@ -1485,7 +1478,7 @@ static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long t
handle_edge_irq, "edge");
}
-static int setup_ioapic_entry(int apic, int irq,
+static int setup_ioapic_entry(int apic_id, int irq,
struct IO_APIC_route_entry *entry,
unsigned int destination, int trigger,
int polarity, int vector)
@@ -1497,25 +1490,25 @@ static int setup_ioapic_entry(int apic, int irq,
#ifdef CONFIG_INTR_REMAP
if (intr_remapping_enabled) {
- struct intel_iommu *iommu = map_ioapic_to_ir(apic);
+ struct intel_iommu *iommu = map_ioapic_to_ir(apic_id);
struct irte irte;
struct IR_IO_APIC_route_entry *ir_entry =
(struct IR_IO_APIC_route_entry *) entry;
int index;
if (!iommu)
- panic("No mapping iommu for ioapic %d\n", apic);
+ panic("No mapping iommu for ioapic %d\n", apic_id);
index = alloc_irte(iommu, irq, 1);
if (index < 0)
- panic("Failed to allocate IRTE for ioapic %d\n", apic);
+ panic("Failed to allocate IRTE for ioapic %d\n", apic_id);
memset(&irte, 0, sizeof(irte));
irte.present = 1;
- irte.dst_mode = INT_DEST_MODE;
+ irte.dst_mode = apic->irq_dest_mode;
irte.trigger_mode = trigger;
- irte.dlvry_mode = INT_DELIVERY_MODE;
+ irte.dlvry_mode = apic->irq_delivery_mode;
irte.vector = vector;
irte.dest_id = IRTE_DEST(destination);
@@ -1528,8 +1521,8 @@ static int setup_ioapic_entry(int apic, int irq,
} else
#endif
{
- entry->delivery_mode = INT_DELIVERY_MODE;
- entry->dest_mode = INT_DEST_MODE;
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
entry->dest = destination;
}
@@ -1546,7 +1539,7 @@ static int setup_ioapic_entry(int apic, int irq,
return 0;
}
-static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, struct irq_desc *desc,
+static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq_desc *desc,
int trigger, int polarity)
{
struct irq_cfg *cfg;
@@ -1558,22 +1551,22 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, struct irq_de
cfg = desc->chip_data;
- if (assign_irq_vector(irq, cfg, TARGET_CPUS))
+ if (assign_irq_vector(irq, cfg, apic->target_cpus()))
return;
- dest = cpu_mask_to_apicid_and(cfg->domain, TARGET_CPUS);
+ dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
apic_printk(APIC_VERBOSE,KERN_DEBUG
"IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
"IRQ %d Mode:%i Active:%i)\n",
- apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
+ apic_id, mp_ioapics[apic_id].apicid, pin, cfg->vector,
irq, trigger, polarity);
- if (setup_ioapic_entry(mp_ioapics[apic].mp_apicid, irq, &entry,
+ if (setup_ioapic_entry(mp_ioapics[apic_id].apicid, irq, &entry,
dest, trigger, polarity, cfg->vector)) {
printk("Failed to setup ioapic entry for ioapic %d, pin %d\n",
- mp_ioapics[apic].mp_apicid, pin);
+ mp_ioapics[apic_id].apicid, pin);
__clear_irq_vector(irq, cfg);
return;
}
@@ -1582,12 +1575,12 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, struct irq_de
if (irq < NR_IRQS_LEGACY)
disable_8259A_irq(irq);
- ioapic_write_entry(apic, pin, entry);
+ ioapic_write_entry(apic_id, pin, entry);
}
static void __init setup_IO_APIC_irqs(void)
{
- int apic, pin, idx, irq;
+ int apic_id, pin, idx, irq;
int notcon = 0;
struct irq_desc *desc;
struct irq_cfg *cfg;
@@ -1595,21 +1588,19 @@ static void __init setup_IO_APIC_irqs(void)
apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
- for (apic = 0; apic < nr_ioapics; apic++) {
- for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+ 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, pin, mp_INT);
+ 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].mp_apicid,
- pin);
+ mp_ioapics[apic_id].apicid, pin);
} else
apic_printk(APIC_VERBOSE, " %d-%d",
- mp_ioapics[apic].mp_apicid,
- pin);
+ mp_ioapics[apic_id].apicid, pin);
continue;
}
if (notcon) {
@@ -1618,20 +1609,25 @@ static void __init setup_IO_APIC_irqs(void)
notcon = 0;
}
- irq = pin_2_irq(idx, apic, pin);
-#ifdef CONFIG_X86_32
- if (multi_timer_check(apic, irq))
+ irq = pin_2_irq(idx, 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;
-#endif
+
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, pin);
+ add_pin_to_irq_cpu(cfg, cpu, apic_id, pin);
- setup_IO_APIC_irq(apic, pin, irq, desc,
+ setup_IO_APIC_irq(apic_id, pin, irq, desc,
irq_trigger(idx), irq_polarity(idx));
}
}
@@ -1644,7 +1640,7 @@ static void __init setup_IO_APIC_irqs(void)
/*
* Set up the timer pin, possibly with the 8259A-master behind.
*/
-static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin,
int vector)
{
struct IO_APIC_route_entry entry;
@@ -1660,10 +1656,10 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
* We use logical delivery to get the timer IRQ
* to the first CPU.
*/
- entry.dest_mode = INT_DEST_MODE;
+ entry.dest_mode = apic->irq_dest_mode;
entry.mask = 1; /* mask IRQ now */
- entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
- entry.delivery_mode = INT_DELIVERY_MODE;
+ entry.dest = apic->cpu_mask_to_apicid(apic->target_cpus());
+ entry.delivery_mode = apic->irq_delivery_mode;
entry.polarity = 0;
entry.trigger = 0;
entry.vector = vector;
@@ -1677,7 +1673,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
/*
* Add it to the IO-APIC irq-routing table:
*/
- ioapic_write_entry(apic, pin, entry);
+ ioapic_write_entry(apic_id, pin, entry);
}
@@ -1699,7 +1695,7 @@ __apicdebuginit(void) print_IO_APIC(void)
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (i = 0; i < nr_ioapics; i++)
printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
- mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]);
+ mp_ioapics[i].apicid, nr_ioapic_registers[i]);
/*
* We are a bit conservative about what we expect. We have to
@@ -1719,7 +1715,7 @@ __apicdebuginit(void) print_IO_APIC(void)
spin_unlock_irqrestore(&ioapic_lock, flags);
printk("\n");
- printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].apicid);
printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type);
@@ -2090,7 +2086,7 @@ static void __init setup_ioapic_ids_from_mpc(void)
{
union IO_APIC_reg_00 reg_00;
physid_mask_t phys_id_present_map;
- int apic;
+ int apic_id;
int i;
unsigned char old_id;
unsigned long flags;
@@ -2109,26 +2105,26 @@ static void __init setup_ioapic_ids_from_mpc(void)
* This is broken; anything with a real cpu count has to
* circumvent this idiocy regardless.
*/
- phys_id_present_map = ioapic_phys_id_map(phys_cpu_present_map);
+ phys_id_present_map = apic->ioapic_phys_id_map(phys_cpu_present_map);
/*
* Set the IOAPIC ID to the value stored in the MPC table.
*/
- for (apic = 0; apic < nr_ioapics; apic++) {
+ for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
/* Read the register 0 value */
spin_lock_irqsave(&ioapic_lock, flags);
- reg_00.raw = io_apic_read(apic, 0);
+ reg_00.raw = io_apic_read(apic_id, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
- old_id = mp_ioapics[apic].mp_apicid;
+ old_id = mp_ioapics[apic_id].apicid;
- if (mp_ioapics[apic].mp_apicid >= get_physical_broadcast()) {
+ if (mp_ioapics[apic_id].apicid >= get_physical_broadcast()) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
- apic, mp_ioapics[apic].mp_apicid);
+ apic_id, mp_ioapics[apic_id].apicid);
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
reg_00.bits.ID);
- mp_ioapics[apic].mp_apicid = reg_00.bits.ID;
+ mp_ioapics[apic_id].apicid = reg_00.bits.ID;
}
/*
@@ -2136,10 +2132,10 @@ static void __init setup_ioapic_ids_from_mpc(void)
* system must have a unique ID or we get lots of nice
* 'stuck on smp_invalidate_needed IPI wait' messages.
*/
- if (check_apicid_used(phys_id_present_map,
- mp_ioapics[apic].mp_apicid)) {
+ if (apic->check_apicid_used(phys_id_present_map,
+ mp_ioapics[apic_id].apicid)) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
- apic, mp_ioapics[apic].mp_apicid);
+ apic_id, mp_ioapics[apic_id].apicid);
for (i = 0; i < get_physical_broadcast(); i++)
if (!physid_isset(i, phys_id_present_map))
break;
@@ -2148,13 +2144,13 @@ static void __init setup_ioapic_ids_from_mpc(void)
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
i);
physid_set(i, phys_id_present_map);
- mp_ioapics[apic].mp_apicid = i;
+ mp_ioapics[apic_id].apicid = i;
} else {
physid_mask_t tmp;
- tmp = apicid_to_cpu_present(mp_ioapics[apic].mp_apicid);
+ tmp = apic->apicid_to_cpu_present(mp_ioapics[apic_id].apicid);
apic_printk(APIC_VERBOSE, "Setting %d in the "
"phys_id_present_map\n",
- mp_ioapics[apic].mp_apicid);
+ mp_ioapics[apic_id].apicid);
physids_or(phys_id_present_map, phys_id_present_map, tmp);
}
@@ -2163,11 +2159,11 @@ static void __init setup_ioapic_ids_from_mpc(void)
* We need to adjust the IRQ routing table
* if the ID changed.
*/
- if (old_id != mp_ioapics[apic].mp_apicid)
+ if (old_id != mp_ioapics[apic_id].apicid)
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mp_dstapic == old_id)
- mp_irqs[i].mp_dstapic
- = mp_ioapics[apic].mp_apicid;
+ if (mp_irqs[i].dstapic == old_id)
+ mp_irqs[i].dstapic
+ = mp_ioapics[apic_id].apicid;
/*
* Read the right value from the MPC table and
@@ -2175,20 +2171,20 @@ static void __init setup_ioapic_ids_from_mpc(void)
*/
apic_printk(APIC_VERBOSE, KERN_INFO
"...changing IO-APIC physical APIC ID to %d ...",
- mp_ioapics[apic].mp_apicid);
+ mp_ioapics[apic_id].apicid);
- reg_00.bits.ID = mp_ioapics[apic].mp_apicid;
+ reg_00.bits.ID = mp_ioapics[apic_id].apicid;
spin_lock_irqsave(&ioapic_lock, flags);
- io_apic_write(apic, 0, reg_00.raw);
+ io_apic_write(apic_id, 0, reg_00.raw);
spin_unlock_irqrestore(&ioapic_lock, flags);
/*
* Sanity check
*/
spin_lock_irqsave(&ioapic_lock, flags);
- reg_00.raw = io_apic_read(apic, 0);
+ reg_00.raw = io_apic_read(apic_id, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
- if (reg_00.bits.ID != mp_ioapics[apic].mp_apicid)
+ if (reg_00.bits.ID != mp_ioapics[apic_id].apicid)
printk("could not set ID!\n");
else
apic_printk(APIC_VERBOSE, " ok.\n");
@@ -2291,7 +2287,7 @@ static int ioapic_retrigger_irq(unsigned int irq)
unsigned long flags;
spin_lock_irqsave(&vector_lock, flags);
- send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector);
+ apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector);
spin_unlock_irqrestore(&vector_lock, flags);
return 1;
@@ -2299,7 +2295,7 @@ static int ioapic_retrigger_irq(unsigned int irq)
#else
static int ioapic_retrigger_irq(unsigned int irq)
{
- send_IPI_self(irq_cfg(irq)->vector);
+ apic->send_IPI_self(irq_cfg(irq)->vector);
return 1;
}
@@ -2363,7 +2359,7 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
set_extra_move_desc(desc, mask);
- dest = cpu_mask_to_apicid_and(cfg->domain, mask);
+ dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
modify_ioapic_rte = desc->status & IRQ_LEVEL;
if (modify_ioapic_rte) {
@@ -2383,7 +2379,7 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
if (cfg->move_in_progress)
send_cleanup_vector(cfg);
- cpumask_copy(&desc->affinity, mask);
+ cpumask_copy(desc->affinity, mask);
}
static int migrate_irq_remapped_level_desc(struct irq_desc *desc)
@@ -2405,11 +2401,11 @@ static int migrate_irq_remapped_level_desc(struct irq_desc *desc)
}
/* everthing is clear. we have right of way */
- migrate_ioapic_irq_desc(desc, &desc->pending_mask);
+ migrate_ioapic_irq_desc(desc, desc->pending_mask);
ret = 0;
desc->status &= ~IRQ_MOVE_PENDING;
- cpumask_clear(&desc->pending_mask);
+ cpumask_clear(desc->pending_mask);
unmask:
unmask_IO_APIC_irq_desc(desc);
@@ -2434,7 +2430,7 @@ static void ir_irq_migration(struct work_struct *work)
continue;
}
- desc->chip->set_affinity(irq, &desc->pending_mask);
+ desc->chip->set_affinity(irq, desc->pending_mask);
spin_unlock_irqrestore(&desc->lock, flags);
}
}
@@ -2448,7 +2444,7 @@ static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
{
if (desc->status & IRQ_LEVEL) {
desc->status |= IRQ_MOVE_PENDING;
- cpumask_copy(&desc->pending_mask, mask);
+ cpumask_copy(desc->pending_mask, mask);
migrate_irq_remapped_level_desc(desc);
return;
}
@@ -2516,7 +2512,7 @@ static void irq_complete_move(struct irq_desc **descp)
/* domain has not changed, but affinity did */
me = smp_processor_id();
- if (cpu_isset(me, desc->affinity)) {
+ if (cpumask_test_cpu(me, desc->affinity)) {
*descp = desc = move_irq_desc(desc, me);
/* get the new one */
cfg = desc->chip_data;
@@ -2879,7 +2875,7 @@ static inline void __init check_timer(void)
* get/set the timer IRQ vector:
*/
disable_8259A_irq(0);
- assign_irq_vector(0, cfg, TARGET_CPUS);
+ assign_irq_vector(0, cfg, apic->target_cpus());
/*
* As IRQ0 is to be enabled in the 8259A, the virtual
@@ -3118,8 +3114,8 @@ static int ioapic_resume(struct sys_device *dev)
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(dev->id, 0);
- if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) {
- reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid;
+ if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].apicid;
io_apic_write(dev->id, 0, reg_00.raw);
}
spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -3184,7 +3180,7 @@ unsigned int create_irq_nr(unsigned int irq_want)
irq = 0;
spin_lock_irqsave(&vector_lock, flags);
- for (new = irq_want; new < NR_IRQS; new++) {
+ for (new = irq_want; new < nr_irqs; new++) {
if (platform_legacy_irq(new))
continue;
@@ -3197,7 +3193,7 @@ unsigned int create_irq_nr(unsigned int irq_want)
if (cfg_new->vector != 0)
continue;
- if (__assign_irq_vector(new, cfg_new, TARGET_CPUS) == 0)
+ if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
irq = new;
break;
}
@@ -3259,12 +3255,15 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
int err;
unsigned dest;
+ if (disable_apic)
+ return -ENXIO;
+
cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, TARGET_CPUS);
+ err = assign_irq_vector(irq, cfg, apic->target_cpus());
if (err)
return err;
- dest = cpu_mask_to_apicid_and(cfg->domain, TARGET_CPUS);
+ dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
#ifdef CONFIG_INTR_REMAP
if (irq_remapped(irq)) {
@@ -3278,9 +3277,9 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
memset (&irte, 0, sizeof(irte));
irte.present = 1;
- irte.dst_mode = INT_DEST_MODE;
+ irte.dst_mode = apic->irq_dest_mode;
irte.trigger_mode = 0; /* edge */
- irte.dlvry_mode = INT_DELIVERY_MODE;
+ irte.dlvry_mode = apic->irq_delivery_mode;
irte.vector = cfg->vector;
irte.dest_id = IRTE_DEST(dest);
@@ -3298,10 +3297,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
msg->address_hi = MSI_ADDR_BASE_HI;
msg->address_lo =
MSI_ADDR_BASE_LO |
- ((INT_DEST_MODE == 0) ?
+ ((apic->irq_dest_mode == 0) ?
MSI_ADDR_DEST_MODE_PHYSICAL:
MSI_ADDR_DEST_MODE_LOGICAL) |
- ((INT_DELIVERY_MODE != dest_LowestPrio) ?
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
MSI_ADDR_REDIRECTION_CPU:
MSI_ADDR_REDIRECTION_LOWPRI) |
MSI_ADDR_DEST_ID(dest);
@@ -3309,7 +3308,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
msg->data =
MSI_DATA_TRIGGER_EDGE |
MSI_DATA_LEVEL_ASSERT |
- ((INT_DELIVERY_MODE != dest_LowestPrio) ?
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
MSI_DATA_DELIVERY_FIXED:
MSI_DATA_DELIVERY_LOWPRI) |
MSI_DATA_VECTOR(cfg->vector);
@@ -3464,40 +3463,6 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
return 0;
}
-int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc)
-{
- unsigned int irq;
- int ret;
- unsigned int irq_want;
-
- irq_want = nr_irqs_gsi;
- irq = create_irq_nr(irq_want);
- if (irq == 0)
- return -1;
-
-#ifdef CONFIG_INTR_REMAP
- if (!intr_remapping_enabled)
- goto no_ir;
-
- ret = msi_alloc_irte(dev, irq, 1);
- if (ret < 0)
- goto error;
-no_ir:
-#endif
- ret = setup_msi_irq(dev, msidesc, irq);
- if (ret < 0) {
- destroy_irq(irq);
- return ret;
- }
- return 0;
-
-#ifdef CONFIG_INTR_REMAP
-error:
- destroy_irq(irq);
- return ret;
-#endif
-}
-
int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
unsigned int irq;
@@ -3727,13 +3692,17 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
struct irq_cfg *cfg;
int err;
+ if (disable_apic)
+ return -ENXIO;
+
cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, TARGET_CPUS);
+ err = assign_irq_vector(irq, cfg, apic->target_cpus());
if (!err) {
struct ht_irq_msg msg;
unsigned dest;
- dest = cpu_mask_to_apicid_and(cfg->domain, TARGET_CPUS);
+ dest = apic->cpu_mask_to_apicid_and(cfg->domain,
+ apic->target_cpus());
msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
@@ -3741,11 +3710,11 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
HT_IRQ_LOW_BASE |
HT_IRQ_LOW_DEST_ID(dest) |
HT_IRQ_LOW_VECTOR(cfg->vector) |
- ((INT_DEST_MODE == 0) ?
+ ((apic->irq_dest_mode == 0) ?
HT_IRQ_LOW_DM_PHYSICAL :
HT_IRQ_LOW_DM_LOGICAL) |
HT_IRQ_LOW_RQEOI_EDGE |
- ((INT_DELIVERY_MODE != dest_LowestPrio) ?
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
HT_IRQ_LOW_MT_FIXED :
HT_IRQ_LOW_MT_ARBITRATED) |
HT_IRQ_LOW_IRQ_MASKED;
@@ -3761,7 +3730,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
}
#endif /* CONFIG_HT_IRQ */
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_UV
/*
* Re-target the irq to the specified CPU and enable the specified MMR located
* on the specified blade to allow the sending of MSIs to the specified CPU.
@@ -3793,12 +3762,12 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
entry->vector = cfg->vector;
- entry->delivery_mode = INT_DELIVERY_MODE;
- entry->dest_mode = INT_DEST_MODE;
+ 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 = cpu_mask_to_apicid(eligible_cpu);
+ 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);
@@ -3851,6 +3820,22 @@ void __init probe_nr_irqs_gsi(void)
nr_irqs_gsi = nr;
}
+#ifdef CONFIG_SPARSE_IRQ
+int __init arch_probe_nr_irqs(void)
+{
+ int nr;
+
+ nr = ((8 * nr_cpu_ids) > (32 * nr_ioapics) ?
+ (NR_VECTORS + (8 * nr_cpu_ids)) :
+ (NR_VECTORS + (32 * nr_ioapics)));
+
+ if (nr < nr_irqs && nr > nr_irqs_gsi)
+ nr_irqs = nr;
+
+ return 0;
+}
+#endif
+
/* --------------------------------------------------------------------------
ACPI-based IOAPIC Configuration
-------------------------------------------------------------------------- */
@@ -3876,7 +3861,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
*/
if (physids_empty(apic_id_map))
- apic_id_map = ioapic_phys_id_map(phys_cpu_present_map);
+ apic_id_map = apic->ioapic_phys_id_map(phys_cpu_present_map);
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(ioapic, 0);
@@ -3892,10 +3877,10 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
* Every APIC in a system must have a unique ID or we get lots of nice
* 'stuck on smp_invalidate_needed IPI wait' messages.
*/
- if (check_apicid_used(apic_id_map, apic_id)) {
+ if (apic->check_apicid_used(apic_id_map, apic_id)) {
for (i = 0; i < get_physical_broadcast(); i++) {
- if (!check_apicid_used(apic_id_map, i))
+ if (!apic->check_apicid_used(apic_id_map, i))
break;
}
@@ -3908,7 +3893,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
apic_id = i;
}
- tmp = apicid_to_cpu_present(apic_id);
+ tmp = apic->apicid_to_cpu_present(apic_id);
physids_or(apic_id_map, apic_id_map, tmp);
if (reg_00.bits.ID != apic_id) {
@@ -3985,8 +3970,8 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
return -1;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mp_irqtype == mp_INT &&
- mp_irqs[i].mp_srcbusirq == bus_irq)
+ if (mp_irqs[i].irqtype == mp_INT &&
+ mp_irqs[i].srcbusirq == bus_irq)
break;
if (i >= mp_irq_entries)
return -1;
@@ -4001,7 +3986,7 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
/*
* This function currently is only a helper for the i386 smp boot process where
* we need to reprogram the ioredtbls to cater for the cpus which have come online
- * so mask in all cases should simply be TARGET_CPUS
+ * so mask in all cases should simply be apic->target_cpus()
*/
#ifdef CONFIG_SMP
void __init setup_ioapic_dest(void)
@@ -4040,9 +4025,9 @@ void __init setup_ioapic_dest(void)
*/
if (desc->status &
(IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
- mask = &desc->affinity;
+ mask = desc->affinity;
else
- mask = TARGET_CPUS;
+ mask = apic->target_cpus();
#ifdef CONFIG_INTR_REMAP
if (intr_remapping_enabled)
@@ -4101,7 +4086,7 @@ void __init ioapic_init_mappings(void)
ioapic_res = ioapic_setup_resources();
for (i = 0; i < nr_ioapics; i++) {
if (smp_found_config) {
- ioapic_phys = mp_ioapics[i].mp_apicaddr;
+ ioapic_phys = mp_ioapics[i].apicaddr;
#ifdef CONFIG_X86_32
if (!ioapic_phys) {
printk(KERN_ERR
diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c
index 285bbf8831fa..dbf5445727a9 100644
--- a/arch/x86/kernel/ipi.c
+++ b/arch/x86/kernel/ipi.c
@@ -17,147 +17,121 @@
#include <asm/mmu_context.h>
#include <asm/apic.h>
#include <asm/proto.h>
+#include <asm/ipi.h>
-#ifdef CONFIG_X86_32
-#include <mach_apic.h>
-#include <mach_ipi.h>
-
-/*
- * the following functions deal with sending IPIs between CPUs.
- *
- * We use 'broadcast', CPU->CPU IPIs and self-IPIs too.
- */
-
-static inline int __prepare_ICR(unsigned int shortcut, int vector)
+void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector)
{
- unsigned int icr = shortcut | APIC_DEST_LOGICAL;
-
- switch (vector) {
- default:
- icr |= APIC_DM_FIXED | vector;
- break;
- case NMI_VECTOR:
- icr |= APIC_DM_NMI;
- break;
+ unsigned long query_cpu;
+ unsigned long flags;
+
+ /*
+ * Hack. The clustered APIC addressing mode doesn't allow us to send
+ * to an arbitrary mask, so I do a unicast to each CPU instead.
+ * - mbligh
+ */
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid,
+ query_cpu), vector, APIC_DEST_PHYSICAL);
}
- return icr;
+ local_irq_restore(flags);
}
-static inline int __prepare_ICR2(unsigned int mask)
+void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
+ int vector)
{
- return SET_APIC_DEST_FIELD(mask);
-}
+ unsigned int this_cpu = smp_processor_id();
+ unsigned int query_cpu;
+ unsigned long flags;
-void __send_IPI_shortcut(unsigned int shortcut, int vector)
-{
- /*
- * Subtle. In the case of the 'never do double writes' workaround
- * we have to lock out interrupts to be safe. As we don't care
- * of the value read we use an atomic rmw access to avoid costly
- * cli/sti. Otherwise we use an even cheaper single atomic write
- * to the APIC.
- */
- unsigned int cfg;
+ /* See Hack comment above */
- /*
- * Wait for idle.
- */
- apic_wait_icr_idle();
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ if (query_cpu == this_cpu)
+ continue;
+ __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid,
+ query_cpu), vector, APIC_DEST_PHYSICAL);
+ }
+ local_irq_restore(flags);
+}
- /*
- * No need to touch the target chip field
- */
- cfg = __prepare_ICR(shortcut, vector);
+void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
+ int vector)
+{
+ unsigned long flags;
+ unsigned int query_cpu;
/*
- * Send the IPI. The write to APIC_ICR fires this off.
+ * Hack. The clustered APIC addressing mode doesn't allow us to send
+ * to an arbitrary mask, so I do a unicasts to each CPU instead. This
+ * should be modified to do 1 message per cluster ID - mbligh
*/
- apic_write(APIC_ICR, cfg);
-}
-void send_IPI_self(int vector)
-{
- __send_IPI_shortcut(APIC_DEST_SELF, vector);
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask)
+ __default_send_IPI_dest_field(
+ apic->cpu_to_logical_apicid(query_cpu), vector,
+ apic->dest_logical);
+ local_irq_restore(flags);
}
-/*
- * This is used to send an IPI with no shorthand notation (the destination is
- * specified in bits 56 to 63 of the ICR).
- */
-static inline void __send_IPI_dest_field(unsigned long mask, int vector)
+void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
+ int vector)
{
- unsigned long cfg;
-
- /*
- * Wait for idle.
- */
- if (unlikely(vector == NMI_VECTOR))
- safe_apic_wait_icr_idle();
- else
- apic_wait_icr_idle();
-
- /*
- * prepare target chip field
- */
- cfg = __prepare_ICR2(mask);
- apic_write(APIC_ICR2, cfg);
+ unsigned long flags;
+ unsigned int query_cpu;
+ unsigned int this_cpu = smp_processor_id();
- /*
- * program the ICR
- */
- cfg = __prepare_ICR(0, vector);
+ /* See Hack comment above */
- /*
- * Send the IPI. The write to APIC_ICR fires this off.
- */
- apic_write(APIC_ICR, cfg);
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ if (query_cpu == this_cpu)
+ continue;
+ __default_send_IPI_dest_field(
+ apic->cpu_to_logical_apicid(query_cpu), vector,
+ apic->dest_logical);
+ }
+ local_irq_restore(flags);
}
+#ifdef CONFIG_X86_32
+
/*
* This is only used on smaller machines.
*/
-void send_IPI_mask_bitmask(const struct cpumask *cpumask, int vector)
+void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
{
unsigned long mask = cpumask_bits(cpumask)[0];
unsigned long flags;
local_irq_save(flags);
WARN_ON(mask & ~cpumask_bits(cpu_online_mask)[0]);
- __send_IPI_dest_field(mask, vector);
+ __default_send_IPI_dest_field(mask, vector, apic->dest_logical);
local_irq_restore(flags);
}
-void send_IPI_mask_sequence(const struct cpumask *mask, int vector)
+void default_send_IPI_allbutself(int vector)
{
- unsigned long flags;
- unsigned int query_cpu;
-
/*
- * Hack. The clustered APIC addressing mode doesn't allow us to send
- * to an arbitrary mask, so I do a unicasts to each CPU instead. This
- * should be modified to do 1 message per cluster ID - mbligh
+ * if there are no other CPUs in the system then we get an APIC send
+ * error if we try to broadcast, thus avoid sending IPIs in this case.
*/
+ if (!(num_online_cpus() > 1))
+ return;
- local_irq_save(flags);
- for_each_cpu(query_cpu, mask)
- __send_IPI_dest_field(cpu_to_logical_apicid(query_cpu), vector);
- local_irq_restore(flags);
+ __default_local_send_IPI_allbutself(vector);
}
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
+void default_send_IPI_all(int vector)
{
- unsigned long flags;
- unsigned int query_cpu;
- unsigned int this_cpu = smp_processor_id();
-
- /* See Hack comment above */
+ __default_local_send_IPI_all(vector);
+}
- local_irq_save(flags);
- for_each_cpu(query_cpu, mask)
- if (query_cpu != this_cpu)
- __send_IPI_dest_field(cpu_to_logical_apicid(query_cpu),
- vector);
- local_irq_restore(flags);
+void default_send_IPI_self(int vector)
+{
+ __default_send_IPI_shortcut(APIC_DEST_SELF, vector, apic->dest_logical);
}
/* must come after the send_IPI functions above for inlining */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 3973e2df7f87..8b30d0c2512c 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -36,11 +36,7 @@ void ack_bad_irq(unsigned int irq)
#endif
}
-#ifdef CONFIG_X86_32
-# define irq_stats(x) (&per_cpu(irq_stat, x))
-#else
-# define irq_stats(x) cpu_pda(x)
-#endif
+#define irq_stats(x) (&per_cpu(irq_stat, x))
/*
* /proc/interrupts printing:
*/
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 74b9ff7341e9..d802c844991e 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -231,7 +231,7 @@ unsigned int do_IRQ(struct pt_regs *regs)
}
#ifdef CONFIG_HOTPLUG_CPU
-#include <mach_apic.h>
+#include <asm/genapic.h>
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
@@ -248,7 +248,7 @@ void fixup_irqs(void)
if (irq == 2)
continue;
- affinity = &desc->affinity;
+ affinity = desc->affinity;
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
printk("Breaking affinity for irq %i\n", irq);
affinity = cpu_all_mask;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 63c88e6ec025..018963aa6ee3 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,6 +18,13 @@
#include <linux/smp.h>
#include <asm/io_apic.h>
#include <asm/idle.h>
+#include <asm/apic.h>
+
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
/*
* Probabilistic stack overflow check:
@@ -100,7 +107,7 @@ void fixup_irqs(void)
/* interrupt's are disabled at this point */
spin_lock(&desc->lock);
- affinity = &desc->affinity;
+ affinity = desc->affinity;
if (!irq_has_action(irq) ||
cpumask_equal(affinity, cpu_online_mask)) {
spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 10a09c2f1828..bf629cadec1a 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -78,6 +78,15 @@ void __init init_ISA_irqs(void)
}
}
+/*
+ * IRQ2 is cascade interrupt to second interrupt controller
+ */
+static struct irqaction irq2 = {
+ .handler = no_action,
+ .mask = CPU_MASK_NONE,
+ .name = "cascade",
+};
+
DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
[0 ... IRQ0_VECTOR - 1] = -1,
[IRQ0_VECTOR] = 0,
@@ -140,8 +149,15 @@ void __init native_init_IRQ(void)
*/
alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
- /* IPI for invalidation */
- alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_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);
@@ -169,6 +185,9 @@ void __init native_init_IRQ(void)
alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
#endif
+ if (!acpi_ioapic)
+ setup_irq(2, &irq2);
+
/* setup after call gates are initialised (usually add in
* the architecture specific gates)
*/
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 10435a120d22..5c4f55483849 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -46,7 +46,7 @@
#include <asm/apicdef.h>
#include <asm/system.h>
-#include <mach_ipi.h>
+#include <asm/genapic.h>
/*
* Put the error code here just in case the user cares:
@@ -347,7 +347,7 @@ void kgdb_post_primary_code(struct pt_regs *regs, int e_vector, int err_code)
*/
void kgdb_roundup_cpus(unsigned long flags)
{
- send_IPI_allbutself(APIC_DM_NMI);
+ apic->send_IPI_allbutself(APIC_DM_NMI);
}
#endif
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index b7f4c929e615..5e9f4fc51385 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -87,9 +87,9 @@
#include <linux/cpu.h>
#include <linux/firmware.h>
#include <linux/platform_device.h>
+#include <linux/uaccess.h>
#include <asm/msr.h>
-#include <asm/uaccess.h>
#include <asm/processor.h>
#include <asm/microcode.h>
@@ -196,7 +196,7 @@ static inline int update_match_cpu(struct cpu_signature *csig, int sig, int pf)
return (!sigmatch(sig, csig->sig, pf, csig->pf)) ? 0 : 1;
}
-static inline int
+static inline int
update_match_revision(struct microcode_header_intel *mc_header, int rev)
{
return (mc_header->rev <= rev) ? 0 : 1;
@@ -442,8 +442,8 @@ static int request_microcode_fw(int cpu, struct device *device)
return ret;
}
- ret = generic_load_microcode(cpu, (void*)firmware->data, firmware->size,
- &get_ucode_fw);
+ ret = generic_load_microcode(cpu, (void *)firmware->data,
+ firmware->size, &get_ucode_fw);
release_firmware(firmware);
@@ -460,7 +460,7 @@ static int request_microcode_user(int cpu, const void __user *buf, size_t size)
/* We should bind the task to the CPU */
BUG_ON(cpu != raw_smp_processor_id());
- return generic_load_microcode(cpu, (void*)buf, size, &get_ucode_user);
+ return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
}
static void microcode_fini_cpu(int cpu)
diff --git a/arch/x86/kernel/module_32.c b/arch/x86/kernel/module_32.c
index 3db0a5442eb1..0edd819050e7 100644
--- a/arch/x86/kernel/module_32.c
+++ b/arch/x86/kernel/module_32.c
@@ -42,7 +42,7 @@ void module_free(struct module *mod, void *module_region)
{
vfree(module_region);
/* FIXME: If module_region == mod->init_region, trim exception
- table entries. */
+ table entries. */
}
/* We don't need anything special. */
@@ -113,13 +113,13 @@ int module_finalize(const Elf_Ehdr *hdr,
*para = NULL;
char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
- for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+ for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
if (!strcmp(".text", secstrings + s->sh_name))
text = s;
if (!strcmp(".altinstructions", secstrings + s->sh_name))
alt = s;
if (!strcmp(".smp_locks", secstrings + s->sh_name))
- locks= s;
+ locks = s;
if (!strcmp(".parainstructions", secstrings + s->sh_name))
para = s;
}
diff --git a/arch/x86/kernel/module_64.c b/arch/x86/kernel/module_64.c
index 6ba87830d4b1..c23880b90b5c 100644
--- a/arch/x86/kernel/module_64.c
+++ b/arch/x86/kernel/module_64.c
@@ -30,14 +30,14 @@
#include <asm/page.h>
#include <asm/pgtable.h>
-#define DEBUGP(fmt...)
+#define DEBUGP(fmt...)
#ifndef CONFIG_UML
void module_free(struct module *mod, void *module_region)
{
vfree(module_region);
/* FIXME: If module_region == mod->init_region, trim exception
- table entries. */
+ table entries. */
}
void *module_alloc(unsigned long size)
@@ -77,7 +77,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;
Elf64_Sym *sym;
void *loc;
- u64 val;
+ u64 val;
DEBUGP("Applying relocate section %u to %u\n", relsec,
sechdrs[relsec].sh_info);
@@ -91,11 +91,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
+ ELF64_R_SYM(rel[i].r_info);
- DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n",
- (int)ELF64_R_TYPE(rel[i].r_info),
- sym->st_value, rel[i].r_addend, (u64)loc);
+ DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n",
+ (int)ELF64_R_TYPE(rel[i].r_info),
+ sym->st_value, rel[i].r_addend, (u64)loc);
- val = sym->st_value + rel[i].r_addend;
+ val = sym->st_value + rel[i].r_addend;
switch (ELF64_R_TYPE(rel[i].r_info)) {
case R_X86_64_NONE:
@@ -113,16 +113,16 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
if ((s64)val != *(s32 *)loc)
goto overflow;
break;
- case R_X86_64_PC32:
+ case R_X86_64_PC32:
val -= (u64)loc;
*(u32 *)loc = val;
#if 0
if ((s64)val != *(s32 *)loc)
- goto overflow;
+ goto overflow;
#endif
break;
default:
- printk(KERN_ERR "module %s: Unknown rela relocation: %Lu\n",
+ printk(KERN_ERR "module %s: Unknown rela relocation: %llu\n",
me->name, ELF64_R_TYPE(rel[i].r_info));
return -ENOEXEC;
}
@@ -130,7 +130,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
return 0;
overflow:
- printk(KERN_ERR "overflow in relocation type %d val %Lx\n",
+ printk(KERN_ERR "overflow in relocation type %d val %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), val);
printk(KERN_ERR "`%s' likely not compiled with -mcmodel=kernel\n",
me->name);
@@ -143,13 +143,13 @@ int apply_relocate(Elf_Shdr *sechdrs,
unsigned int relsec,
struct module *me)
{
- printk("non add relocation not supported\n");
+ printk(KERN_ERR "non add relocation not supported\n");
return -ENOSYS;
-}
+}
int module_finalize(const Elf_Ehdr *hdr,
- const Elf_Shdr *sechdrs,
- struct module *me)
+ const Elf_Shdr *sechdrs,
+ struct module *me)
{
const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
*para = NULL;
@@ -161,7 +161,7 @@ int module_finalize(const Elf_Ehdr *hdr,
if (!strcmp(".altinstructions", secstrings + s->sh_name))
alt = s;
if (!strcmp(".smp_locks", secstrings + s->sh_name))
- locks= s;
+ locks = s;
if (!strcmp(".parainstructions", secstrings + s->sh_name))
para = s;
}
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index a649a4ccad43..66ebb823f390 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -3,7 +3,7 @@
* compliant MP-table parsing routines.
*
* (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk>
- * (c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com>
+ * (c) 1998, 1999, 2000, 2009 Ingo Molnar <mingo@redhat.com>
* (c) 2008 Alexey Starikovskiy <astarikovskiy@suse.de>
*/
@@ -29,12 +29,7 @@
#include <asm/setup.h>
#include <asm/smp.h>
-#include <mach_apic.h>
-#ifdef CONFIG_X86_32
-#include <mach_apicdef.h>
-#include <mach_mpparse.h>
-#endif
-
+#include <asm/genapic.h>
/*
* Checksum an MP configuration block.
*/
@@ -144,11 +139,11 @@ static void __init MP_ioapic_info(struct mpc_ioapic *m)
if (bad_ioapic(m->apicaddr))
return;
- mp_ioapics[nr_ioapics].mp_apicaddr = m->apicaddr;
- mp_ioapics[nr_ioapics].mp_apicid = m->apicid;
- mp_ioapics[nr_ioapics].mp_type = m->type;
- mp_ioapics[nr_ioapics].mp_apicver = m->apicver;
- mp_ioapics[nr_ioapics].mp_flags = m->flags;
+ mp_ioapics[nr_ioapics].apicaddr = m->apicaddr;
+ mp_ioapics[nr_ioapics].apicid = m->apicid;
+ mp_ioapics[nr_ioapics].type = m->type;
+ mp_ioapics[nr_ioapics].apicver = m->apicver;
+ mp_ioapics[nr_ioapics].flags = m->flags;
nr_ioapics++;
}
@@ -160,55 +155,55 @@ static void print_MP_intsrc_info(struct mpc_intsrc *m)
m->srcbusirq, m->dstapic, m->dstirq);
}
-static void __init print_mp_irq_info(struct mp_config_intsrc *mp_irq)
+static void __init print_mp_irq_info(struct mpc_intsrc *mp_irq)
{
apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
" IRQ %02x, APIC ID %x, APIC INT %02x\n",
- mp_irq->mp_irqtype, mp_irq->mp_irqflag & 3,
- (mp_irq->mp_irqflag >> 2) & 3, mp_irq->mp_srcbus,
- mp_irq->mp_srcbusirq, mp_irq->mp_dstapic, mp_irq->mp_dstirq);
+ mp_irq->irqtype, mp_irq->irqflag & 3,
+ (mp_irq->irqflag >> 2) & 3, mp_irq->srcbus,
+ mp_irq->srcbusirq, mp_irq->dstapic, mp_irq->dstirq);
}
static void __init assign_to_mp_irq(struct mpc_intsrc *m,
- struct mp_config_intsrc *mp_irq)
+ struct mpc_intsrc *mp_irq)
{
- mp_irq->mp_dstapic = m->dstapic;
- mp_irq->mp_type = m->type;
- mp_irq->mp_irqtype = m->irqtype;
- mp_irq->mp_irqflag = m->irqflag;
- mp_irq->mp_srcbus = m->srcbus;
- mp_irq->mp_srcbusirq = m->srcbusirq;
- mp_irq->mp_dstirq = m->dstirq;
+ mp_irq->dstapic = m->dstapic;
+ mp_irq->type = m->type;
+ mp_irq->irqtype = m->irqtype;
+ mp_irq->irqflag = m->irqflag;
+ mp_irq->srcbus = m->srcbus;
+ mp_irq->srcbusirq = m->srcbusirq;
+ mp_irq->dstirq = m->dstirq;
}
-static void __init assign_to_mpc_intsrc(struct mp_config_intsrc *mp_irq,
+static void __init assign_to_mpc_intsrc(struct mpc_intsrc *mp_irq,
struct mpc_intsrc *m)
{
- m->dstapic = mp_irq->mp_dstapic;
- m->type = mp_irq->mp_type;
- m->irqtype = mp_irq->mp_irqtype;
- m->irqflag = mp_irq->mp_irqflag;
- m->srcbus = mp_irq->mp_srcbus;
- m->srcbusirq = mp_irq->mp_srcbusirq;
- m->dstirq = mp_irq->mp_dstirq;
+ m->dstapic = mp_irq->dstapic;
+ m->type = mp_irq->type;
+ m->irqtype = mp_irq->irqtype;
+ m->irqflag = mp_irq->irqflag;
+ m->srcbus = mp_irq->srcbus;
+ m->srcbusirq = mp_irq->srcbusirq;
+ m->dstirq = mp_irq->dstirq;
}
-static int __init mp_irq_mpc_intsrc_cmp(struct mp_config_intsrc *mp_irq,
+static int __init mp_irq_mpc_intsrc_cmp(struct mpc_intsrc *mp_irq,
struct mpc_intsrc *m)
{
- if (mp_irq->mp_dstapic != m->dstapic)
+ if (mp_irq->dstapic != m->dstapic)
return 1;
- if (mp_irq->mp_type != m->type)
+ if (mp_irq->type != m->type)
return 2;
- if (mp_irq->mp_irqtype != m->irqtype)
+ if (mp_irq->irqtype != m->irqtype)
return 3;
- if (mp_irq->mp_irqflag != m->irqflag)
+ if (mp_irq->irqflag != m->irqflag)
return 4;
- if (mp_irq->mp_srcbus != m->srcbus)
+ if (mp_irq->srcbus != m->srcbus)
return 5;
- if (mp_irq->mp_srcbusirq != m->srcbusirq)
+ if (mp_irq->srcbusirq != m->srcbusirq)
return 6;
- if (mp_irq->mp_dstirq != m->dstirq)
+ if (mp_irq->dstirq != m->dstirq)
return 7;
return 0;
@@ -292,16 +287,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
return 0;
#ifdef CONFIG_X86_32
- /*
- * need to make sure summit and es7000's mps_oem_check is safe to be
- * called early via genericarch 's mps_oem_check
- */
- if (early) {
-#ifdef CONFIG_X86_NUMAQ
- numaq_mps_oem_check(mpc, oem, str);
-#endif
- } else
- mps_oem_check(mpc, oem, str);
+ generic_mps_oem_check(mpc, oem, str);
#endif
/* save the local APIC address, it might be non-default */
if (!acpi_lapic)
@@ -386,13 +372,13 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
(*x86_quirks->mpc_record)++;
}
-#ifdef CONFIG_X86_GENERICARCH
- generic_bigsmp_probe();
+#ifdef CONFIG_X86_BIGSMP
+ generic_bigsmp_probe();
#endif
-#ifdef CONFIG_X86_32
- setup_apic_routing();
-#endif
+ if (apic->setup_apic_routing)
+ apic->setup_apic_routing();
+
if (!num_processors)
printk(KERN_ERR "MPTABLE: no processors registered!\n");
return num_processors;
@@ -417,7 +403,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
intsrc.type = MP_INTSRC;
intsrc.irqflag = 0; /* conforming */
intsrc.srcbus = 0;
- intsrc.dstapic = mp_ioapics[0].mp_apicid;
+ intsrc.dstapic = mp_ioapics[0].apicid;
intsrc.irqtype = mp_INT;
@@ -570,14 +556,14 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
}
}
-static struct intel_mp_floating *mpf_found;
+static struct mpf_intel *mpf_found;
/*
* Scan the memory blocks for an SMP configuration block.
*/
static void __init __get_smp_config(unsigned int early)
{
- struct intel_mp_floating *mpf = mpf_found;
+ struct mpf_intel *mpf = mpf_found;
if (!mpf)
return;
@@ -598,9 +584,9 @@ static void __init __get_smp_config(unsigned int early)
}
printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
- mpf->mpf_specification);
+ mpf->specification);
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
- if (mpf->mpf_feature2 & (1 << 7)) {
+ if (mpf->feature2 & (1 << 7)) {
printk(KERN_INFO " IMCR and PIC compatibility mode.\n");
pic_mode = 1;
} else {
@@ -611,7 +597,7 @@ static void __init __get_smp_config(unsigned int early)
/*
* Now see if we need to read further.
*/
- if (mpf->mpf_feature1 != 0) {
+ if (mpf->feature1 != 0) {
if (early) {
/*
* local APIC has default address
@@ -621,16 +607,16 @@ static void __init __get_smp_config(unsigned int early)
}
printk(KERN_INFO "Default MP configuration #%d\n",
- mpf->mpf_feature1);
- construct_default_ISA_mptable(mpf->mpf_feature1);
+ mpf->feature1);
+ construct_default_ISA_mptable(mpf->feature1);
- } else if (mpf->mpf_physptr) {
+ } else if (mpf->physptr) {
/*
* Read the physical hardware table. Anything here will
* override the defaults.
*/
- if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr), early)) {
+ if (!smp_read_mpc(phys_to_virt(mpf->physptr), early)) {
#ifdef CONFIG_X86_LOCAL_APIC
smp_found_config = 0;
#endif
@@ -688,19 +674,19 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
unsigned reserve)
{
unsigned int *bp = phys_to_virt(base);
- struct intel_mp_floating *mpf;
+ struct mpf_intel *mpf;
apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n",
bp, length);
BUILD_BUG_ON(sizeof(*mpf) != 16);
while (length > 0) {
- mpf = (struct intel_mp_floating *)bp;
+ mpf = (struct mpf_intel *)bp;
if ((*bp == SMP_MAGIC_IDENT) &&
- (mpf->mpf_length == 1) &&
+ (mpf->length == 1) &&
!mpf_checksum((unsigned char *)bp, 16) &&
- ((mpf->mpf_specification == 1)
- || (mpf->mpf_specification == 4))) {
+ ((mpf->specification == 1)
+ || (mpf->specification == 4))) {
#ifdef CONFIG_X86_LOCAL_APIC
smp_found_config = 1;
#endif
@@ -713,7 +699,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
return 1;
reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE,
BOOTMEM_DEFAULT);
- if (mpf->mpf_physptr) {
+ if (mpf->physptr) {
unsigned long size = PAGE_SIZE;
#ifdef CONFIG_X86_32
/*
@@ -722,14 +708,14 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
* the bottom is mapped now.
* PC-9800's MPC table places on the very last
* of physical memory; so that simply reserving
- * PAGE_SIZE from mpg->mpf_physptr yields BUG()
+ * PAGE_SIZE from mpf->physptr yields BUG()
* in reserve_bootmem.
*/
unsigned long end = max_low_pfn * PAGE_SIZE;
- if (mpf->mpf_physptr + size > end)
- size = end - mpf->mpf_physptr;
+ if (mpf->physptr + size > end)
+ size = end - mpf->physptr;
#endif
- reserve_bootmem_generic(mpf->mpf_physptr, size,
+ reserve_bootmem_generic(mpf->physptr, size,
BOOTMEM_DEFAULT);
}
@@ -809,15 +795,15 @@ static int __init get_MP_intsrc_index(struct mpc_intsrc *m)
/* not legacy */
for (i = 0; i < mp_irq_entries; i++) {
- if (mp_irqs[i].mp_irqtype != mp_INT)
+ if (mp_irqs[i].irqtype != mp_INT)
continue;
- if (mp_irqs[i].mp_irqflag != 0x0f)
+ if (mp_irqs[i].irqflag != 0x0f)
continue;
- if (mp_irqs[i].mp_srcbus != m->srcbus)
+ if (mp_irqs[i].srcbus != m->srcbus)
continue;
- if (mp_irqs[i].mp_srcbusirq != m->srcbusirq)
+ if (mp_irqs[i].srcbusirq != m->srcbusirq)
continue;
if (irq_used[i]) {
/* already claimed */
@@ -922,10 +908,10 @@ static int __init replace_intsrc_all(struct mpc_table *mpc,
if (irq_used[i])
continue;
- if (mp_irqs[i].mp_irqtype != mp_INT)
+ if (mp_irqs[i].irqtype != mp_INT)
continue;
- if (mp_irqs[i].mp_irqflag != 0x0f)
+ if (mp_irqs[i].irqflag != 0x0f)
continue;
if (nr_m_spare > 0) {
@@ -1001,7 +987,7 @@ static int __init update_mp_table(void)
{
char str[16];
char oem[10];
- struct intel_mp_floating *mpf;
+ struct mpf_intel *mpf;
struct mpc_table *mpc, *mpc_new;
if (!enable_update_mptable)
@@ -1014,19 +1000,19 @@ static int __init update_mp_table(void)
/*
* Now see if we need to go further.
*/
- if (mpf->mpf_feature1 != 0)
+ if (mpf->feature1 != 0)
return 0;
- if (!mpf->mpf_physptr)
+ if (!mpf->physptr)
return 0;
- mpc = phys_to_virt(mpf->mpf_physptr);
+ mpc = phys_to_virt(mpf->physptr);
if (!smp_check_mpc(mpc, oem, str))
return 0;
printk(KERN_INFO "mpf: %lx\n", virt_to_phys(mpf));
- printk(KERN_INFO "mpf_physptr: %x\n", mpf->mpf_physptr);
+ printk(KERN_INFO "physptr: %x\n", mpf->physptr);
if (mpc_new_phys && mpc->length > mpc_new_length) {
mpc_new_phys = 0;
@@ -1047,23 +1033,23 @@ static int __init update_mp_table(void)
}
printk(KERN_INFO "use in-positon replacing\n");
} else {
- mpf->mpf_physptr = mpc_new_phys;
+ mpf->physptr = mpc_new_phys;
mpc_new = phys_to_virt(mpc_new_phys);
memcpy(mpc_new, mpc, mpc->length);
mpc = mpc_new;
/* check if we can modify that */
- if (mpc_new_phys - mpf->mpf_physptr) {
- struct intel_mp_floating *mpf_new;
+ if (mpc_new_phys - mpf->physptr) {
+ struct mpf_intel *mpf_new;
/* steal 16 bytes from [0, 1k) */
printk(KERN_INFO "mpf new: %x\n", 0x400 - 16);
mpf_new = phys_to_virt(0x400 - 16);
memcpy(mpf_new, mpf, 16);
mpf = mpf_new;
- mpf->mpf_physptr = mpc_new_phys;
+ mpf->physptr = mpc_new_phys;
}
- mpf->mpf_checksum = 0;
- mpf->mpf_checksum -= mpf_checksum((unsigned char *)mpf, 16);
- printk(KERN_INFO "mpf_physptr new: %x\n", mpf->mpf_physptr);
+ mpf->checksum = 0;
+ mpf->checksum -= mpf_checksum((unsigned char *)mpf, 16);
+ printk(KERN_INFO "physptr new: %x\n", mpf->physptr);
}
/*
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 726266695b2c..3cf3413ec626 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -35,10 +35,10 @@
#include <linux/device.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
+#include <linux/uaccess.h>
#include <asm/processor.h>
#include <asm/msr.h>
-#include <asm/uaccess.h>
#include <asm/system.h>
static struct class *msr_class;
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 7228979f1e7f..bdfad80c3cf1 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -34,7 +34,7 @@
#include <asm/mce.h>
-#include <mach_traps.h>
+#include <asm/mach_traps.h>
int unknown_nmi_panic;
int nmi_watchdog_enabled;
@@ -61,11 +61,7 @@ static int endflag __initdata;
static inline unsigned int get_nmi_count(int cpu)
{
-#ifdef CONFIG_X86_64
- return cpu_pda(cpu)->__nmi_count;
-#else
- return nmi_count(cpu);
-#endif
+ return per_cpu(irq_stat, cpu).__nmi_count;
}
static inline int mce_in_progress(void)
@@ -82,12 +78,8 @@ static inline int mce_in_progress(void)
*/
static inline unsigned int get_timer_irqs(int cpu)
{
-#ifdef CONFIG_X86_64
- return read_pda(apic_timer_irqs) + read_pda(irq0_irqs);
-#else
return per_cpu(irq_stat, cpu).apic_timer_irqs +
per_cpu(irq_stat, cpu).irq0_irqs;
-#endif
}
#ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/numaq_32.c b/arch/x86/kernel/numaq_32.c
index f2191d4f2717..947748e17211 100644
--- a/arch/x86/kernel/numaq_32.c
+++ b/arch/x86/kernel/numaq_32.c
@@ -236,7 +236,7 @@ static int __init numaq_setup_ioapic_ids(void)
static int __init numaq_update_genapic(void)
{
- genapic->wakeup_cpu = wakeup_secondary_cpu_via_nmi;
+ apic->wakeup_cpu = wakeup_secondary_cpu_via_nmi;
return 0;
}
@@ -291,3 +291,279 @@ int __init get_memcfg_numaq(void)
smp_dump_qct();
return 1;
}
+
+/*
+ * APIC driver for the IBM NUMAQ chipset.
+ */
+#define APIC_DEFINITION 1
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <asm/mpspec.h>
+#include <asm/genapic.h>
+#include <asm/fixmap.h>
+#include <asm/apicdef.h>
+#include <asm/ipi.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/numa.h>
+#include <linux/smp.h>
+#include <asm/numaq.h>
+#include <asm/io.h>
+#include <linux/mmzone.h>
+#include <linux/nodemask.h>
+
+#define NUMAQ_APIC_DFR_VALUE (APIC_DFR_CLUSTER)
+
+static inline unsigned int numaq_get_apic_id(unsigned long x)
+{
+ return (x >> 24) & 0x0F;
+}
+
+static inline void numaq_send_IPI_mask(const struct cpumask *mask, int vector)
+{
+ default_send_IPI_mask_sequence_logical(mask, vector);
+}
+
+static inline void numaq_send_IPI_allbutself(int vector)
+{
+ default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector);
+}
+
+static inline void numaq_send_IPI_all(int vector)
+{
+ numaq_send_IPI_mask(cpu_online_mask, vector);
+}
+
+extern void numaq_mps_oem_check(struct mpc_table *, char *, char *);
+
+#define NUMAQ_TRAMPOLINE_PHYS_LOW (0x8)
+#define NUMAQ_TRAMPOLINE_PHYS_HIGH (0xa)
+
+/*
+ * Because we use NMIs rather than the INIT-STARTUP sequence to
+ * bootstrap the CPUs, the APIC may be in a weird state. Kick it:
+ */
+static inline void numaq_smp_callin_clear_local_apic(void)
+{
+ clear_local_APIC();
+}
+
+static inline void
+numaq_store_NMI_vector(unsigned short *high, unsigned short *low)
+{
+ printk("Storing NMI vector\n");
+ *high =
+ *((volatile unsigned short *)phys_to_virt(NUMAQ_TRAMPOLINE_PHYS_HIGH));
+ *low =
+ *((volatile unsigned short *)phys_to_virt(NUMAQ_TRAMPOLINE_PHYS_LOW));
+}
+
+static inline const cpumask_t *numaq_target_cpus(void)
+{
+ return &CPU_MASK_ALL;
+}
+
+static inline unsigned long
+numaq_check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+ return physid_isset(apicid, bitmap);
+}
+
+static inline unsigned long numaq_check_apicid_present(int bit)
+{
+ return physid_isset(bit, phys_cpu_present_map);
+}
+
+#define apicid_cluster(apicid) (apicid & 0xF0)
+
+static inline int numaq_apic_id_registered(void)
+{
+ return 1;
+}
+
+static inline void numaq_init_apic_ldr(void)
+{
+ /* Already done in NUMA-Q firmware */
+}
+
+static inline void numaq_setup_apic_routing(void)
+{
+ printk("Enabling APIC mode: %s. Using %d I/O APICs\n",
+ "NUMA-Q", nr_ioapics);
+}
+
+/*
+ * Skip adding the timer int on secondary nodes, which causes
+ * a small but painful rift in the time-space continuum.
+ */
+static inline int numaq_multi_timer_check(int apic, int irq)
+{
+ return apic != 0 && irq == 0;
+}
+
+static inline physid_mask_t numaq_ioapic_phys_id_map(physid_mask_t phys_map)
+{
+ /* We don't have a good way to do this yet - hack */
+ return physids_promote(0xFUL);
+}
+
+/* Mapping from cpu number to logical apicid */
+extern u8 cpu_2_logical_apicid[];
+
+static inline int numaq_cpu_to_logical_apicid(int cpu)
+{
+ if (cpu >= nr_cpu_ids)
+ return BAD_APICID;
+ return (int)cpu_2_logical_apicid[cpu];
+}
+
+/*
+ * Supporting over 60 cpus on NUMA-Q requires a locality-dependent
+ * cpu to APIC ID relation to properly interact with the intelligent
+ * mode of the cluster controller.
+ */
+static inline int numaq_cpu_present_to_apicid(int mps_cpu)
+{
+ if (mps_cpu < 60)
+ return ((mps_cpu >> 2) << 4) | (1 << (mps_cpu & 0x3));
+ else
+ return BAD_APICID;
+}
+
+static inline int numaq_apicid_to_node(int logical_apicid)
+{
+ return logical_apicid >> 4;
+}
+
+static inline physid_mask_t numaq_apicid_to_cpu_present(int logical_apicid)
+{
+ int node = numaq_apicid_to_node(logical_apicid);
+ int cpu = __ffs(logical_apicid & 0xf);
+
+ return physid_mask_of_physid(cpu + 4*node);
+}
+
+extern void *xquad_portio;
+
+static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+ return 1;
+}
+
+/*
+ * We use physical apicids here, not logical, so just return the default
+ * physical broadcast to stop people from breaking us
+ */
+static inline unsigned int numaq_cpu_mask_to_apicid(const cpumask_t *cpumask)
+{
+ return 0x0F;
+}
+
+static inline unsigned int
+numaq_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
+{
+ return 0x0F;
+}
+
+/* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */
+static inline int numaq_phys_pkg_id(int cpuid_apic, int index_msb)
+{
+ return cpuid_apic >> index_msb;
+}
+static int __numaq_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid)
+{
+ numaq_mps_oem_check(mpc, oem, productid);
+ return found_numaq;
+}
+
+static int probe_numaq(void)
+{
+ /* already know from get_memcfg_numaq() */
+ return found_numaq;
+}
+
+static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask)
+{
+ /* Careful. Some cpus do not strictly honor the set of cpus
+ * specified in the interrupt destination when using lowest
+ * priority interrupt delivery mode.
+ *
+ * In particular there was a hyperthreading cpu observed to
+ * deliver interrupts to the wrong hyperthread when only one
+ * hyperthread was specified in the interrupt desitination.
+ */
+ *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+}
+
+static void numaq_setup_portio_remap(void)
+{
+ int num_quads = num_online_nodes();
+
+ if (num_quads <= 1)
+ return;
+
+ printk("Remapping cross-quad port I/O for %d quads\n", num_quads);
+ xquad_portio = ioremap(XQUAD_PORTIO_BASE, num_quads*XQUAD_PORTIO_QUAD);
+ printk("xquad_portio vaddr 0x%08lx, len %08lx\n",
+ (u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD);
+}
+
+struct genapic apic_numaq = {
+
+ .name = "NUMAQ",
+ .probe = probe_numaq,
+ .acpi_madt_oem_check = NULL,
+ .apic_id_registered = numaq_apic_id_registered,
+
+ .irq_delivery_mode = dest_LowestPrio,
+ /* physical delivery on LOCAL quad: */
+ .irq_dest_mode = 0,
+
+ .target_cpus = numaq_target_cpus,
+ .disable_esr = 1,
+ .dest_logical = APIC_DEST_LOGICAL,
+ .check_apicid_used = numaq_check_apicid_used,
+ .check_apicid_present = numaq_check_apicid_present,
+
+ .vector_allocation_domain = numaq_vector_allocation_domain,
+ .init_apic_ldr = numaq_init_apic_ldr,
+
+ .ioapic_phys_id_map = numaq_ioapic_phys_id_map,
+ .setup_apic_routing = numaq_setup_apic_routing,
+ .multi_timer_check = numaq_multi_timer_check,
+ .apicid_to_node = numaq_apicid_to_node,
+ .cpu_to_logical_apicid = numaq_cpu_to_logical_apicid,
+ .cpu_present_to_apicid = numaq_cpu_present_to_apicid,
+ .apicid_to_cpu_present = numaq_apicid_to_cpu_present,
+ .setup_portio_remap = numaq_setup_portio_remap,
+ .check_phys_apicid_present = numaq_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = numaq_phys_pkg_id,
+ .mps_oem_check = __numaq_mps_oem_check,
+
+ .get_apic_id = numaq_get_apic_id,
+ .set_apic_id = NULL,
+ .apic_id_mask = 0x0F << 24,
+
+ .cpu_mask_to_apicid = numaq_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = numaq_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = numaq_send_IPI_mask,
+ .send_IPI_mask_allbutself = NULL,
+ .send_IPI_allbutself = numaq_send_IPI_allbutself,
+ .send_IPI_all = numaq_send_IPI_all,
+ .send_IPI_self = default_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = NUMAQ_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = NUMAQ_TRAMPOLINE_PHYS_HIGH,
+
+ /* We don't do anything here because we use NMI's to boot instead */
+ .wait_for_init_deassert = NULL,
+
+ .smp_callin_clear_local_apic = numaq_smp_callin_clear_local_apic,
+ .store_NMI_vector = numaq_store_NMI_vector,
+ .inquire_remote_apic = NULL,
+};
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 95777b0faa73..3a7c5a44082e 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -26,13 +26,3 @@ struct pv_lock_ops pv_lock_ops = {
};
EXPORT_SYMBOL(pv_lock_ops);
-void __init paravirt_use_bytelocks(void)
-{
-#ifdef CONFIG_SMP
- pv_lock_ops.spin_is_locked = __byte_spin_is_locked;
- pv_lock_ops.spin_is_contended = __byte_spin_is_contended;
- pv_lock_ops.spin_lock = __byte_spin_lock;
- pv_lock_ops.spin_trylock = __byte_spin_trylock;
- pv_lock_ops.spin_unlock = __byte_spin_unlock;
-#endif
-}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index e4c8fb608873..202514be5923 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -435,7 +435,6 @@ struct pv_mmu_ops pv_mmu_ops = {
#endif /* PAGETABLE_LEVELS >= 3 */
.pte_val = native_pte_val,
- .pte_flags = native_pte_flags,
.pgd_val = native_pgd_val,
.make_pte = native_make_pte,
diff --git a/arch/x86/kernel/probe_32.c b/arch/x86/kernel/probe_32.c
new file mode 100644
index 000000000000..22337b75de62
--- /dev/null
+++ b/arch/x86/kernel/probe_32.c
@@ -0,0 +1,411 @@
+/*
+ * Default generic APIC driver. This handles up to 8 CPUs.
+ *
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic x86 APIC driver probe layer.
+ */
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <asm/fixmap.h>
+#include <asm/mpspec.h>
+#include <asm/apicdef.h>
+#include <asm/genapic.h>
+#include <asm/setup.h>
+
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <asm/mpspec.h>
+#include <asm/genapic.h>
+#include <asm/fixmap.h>
+#include <asm/apicdef.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <asm/genapic.h>
+#include <asm/ipi.h>
+
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <asm/acpi.h>
+#include <asm/arch_hooks.h>
+#include <asm/e820.h>
+#include <asm/setup.h>
+
+#include <asm/genapic.h>
+
+#ifdef CONFIG_HOTPLUG_CPU
+#define DEFAULT_SEND_IPI (1)
+#else
+#define DEFAULT_SEND_IPI (0)
+#endif
+
+int no_broadcast = DEFAULT_SEND_IPI;
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+static void default_vector_allocation_domain(int cpu, struct cpumask *retmask)
+{
+ /*
+ * Careful. Some cpus do not strictly honor the set of cpus
+ * specified in the interrupt destination when using lowest
+ * priority interrupt delivery mode.
+ *
+ * In particular there was a hyperthreading cpu observed to
+ * deliver interrupts to the wrong hyperthread when only one
+ * hyperthread was specified in the interrupt desitination.
+ */
+ *retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } };
+}
+
+/* should be called last. */
+static int probe_default(void)
+{
+ return 1;
+}
+
+struct genapic apic_default = {
+
+ .name = "default",
+ .probe = probe_default,
+ .acpi_madt_oem_check = NULL,
+ .apic_id_registered = default_apic_id_registered,
+
+ .irq_delivery_mode = dest_LowestPrio,
+ /* logical delivery broadcast to all CPUs: */
+ .irq_dest_mode = 1,
+
+ .target_cpus = default_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = APIC_DEST_LOGICAL,
+ .check_apicid_used = default_check_apicid_used,
+ .check_apicid_present = default_check_apicid_present,
+
+ .vector_allocation_domain = default_vector_allocation_domain,
+ .init_apic_ldr = default_init_apic_ldr,
+
+ .ioapic_phys_id_map = default_ioapic_phys_id_map,
+ .setup_apic_routing = default_setup_apic_routing,
+ .multi_timer_check = NULL,
+ .apicid_to_node = default_apicid_to_node,
+ .cpu_to_logical_apicid = default_cpu_to_logical_apicid,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = default_apicid_to_cpu_present,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = default_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = default_get_apic_id,
+ .set_apic_id = NULL,
+ .apic_id_mask = 0x0F << 24,
+
+ .cpu_mask_to_apicid = default_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = default_send_IPI_mask_logical,
+ .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_logical,
+ .send_IPI_allbutself = default_send_IPI_allbutself,
+ .send_IPI_all = default_send_IPI_all,
+ .send_IPI_self = default_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+
+ .wait_for_init_deassert = default_wait_for_init_deassert,
+
+ .smp_callin_clear_local_apic = NULL,
+ .store_NMI_vector = NULL,
+ .inquire_remote_apic = default_inquire_remote_apic,
+};
+
+extern struct genapic apic_numaq;
+extern struct genapic apic_summit;
+extern struct genapic apic_bigsmp;
+extern struct genapic apic_es7000;
+extern struct genapic apic_default;
+
+struct genapic *apic = &apic_default;
+
+static struct genapic *apic_probe[] __initdata = {
+#ifdef CONFIG_X86_NUMAQ
+ &apic_numaq,
+#endif
+#ifdef CONFIG_X86_SUMMIT
+ &apic_summit,
+#endif
+#ifdef CONFIG_X86_BIGSMP
+ &apic_bigsmp,
+#endif
+#ifdef CONFIG_X86_ES7000
+ &apic_es7000,
+#endif
+ &apic_default, /* must be last */
+ NULL,
+};
+
+static int cmdline_apic __initdata;
+static int __init parse_apic(char *arg)
+{
+ int i;
+
+ if (!arg)
+ return -EINVAL;
+
+ for (i = 0; apic_probe[i]; i++) {
+ if (!strcmp(apic_probe[i]->name, arg)) {
+ apic = apic_probe[i];
+ cmdline_apic = 1;
+ return 0;
+ }
+ }
+
+ if (x86_quirks->update_genapic)
+ x86_quirks->update_genapic();
+
+ /* Parsed again by __setup for debug/verbose */
+ return 0;
+}
+early_param("apic", parse_apic);
+
+void __init generic_bigsmp_probe(void)
+{
+#ifdef CONFIG_X86_BIGSMP
+ /*
+ * This routine is used to switch to bigsmp mode when
+ * - There is no apic= option specified by the user
+ * - generic_apic_probe() has chosen apic_default as the sub_arch
+ * - we find more than 8 CPUs in acpi LAPIC listing with xAPIC support
+ */
+
+ if (!cmdline_apic && apic == &apic_default) {
+ if (apic_bigsmp.probe()) {
+ apic = &apic_bigsmp;
+ if (x86_quirks->update_genapic)
+ x86_quirks->update_genapic();
+ printk(KERN_INFO "Overriding APIC driver with %s\n",
+ apic->name);
+ }
+ }
+#endif
+}
+
+void __init generic_apic_probe(void)
+{
+ if (!cmdline_apic) {
+ int i;
+ for (i = 0; apic_probe[i]; i++) {
+ if (apic_probe[i]->probe()) {
+ apic = apic_probe[i];
+ break;
+ }
+ }
+ /* Not visible without early console */
+ if (!apic_probe[i])
+ panic("Didn't find an APIC driver");
+
+ if (x86_quirks->update_genapic)
+ x86_quirks->update_genapic();
+ }
+ printk(KERN_INFO "Using APIC driver %s\n", apic->name);
+}
+
+/* These functions can switch the APIC even after the initial ->probe() */
+
+int __init
+generic_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid)
+{
+ int i;
+
+ for (i = 0; apic_probe[i]; ++i) {
+ if (!apic_probe[i]->mps_oem_check)
+ continue;
+ if (!apic_probe[i]->mps_oem_check(mpc, oem, productid))
+ continue;
+
+ if (!cmdline_apic) {
+ apic = apic_probe[i];
+ if (x86_quirks->update_genapic)
+ x86_quirks->update_genapic();
+ printk(KERN_INFO "Switched to APIC driver `%s'.\n",
+ apic->name);
+ }
+ return 1;
+ }
+ return 0;
+}
+
+int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ int i;
+
+ for (i = 0; apic_probe[i]; ++i) {
+ if (!apic_probe[i]->acpi_madt_oem_check)
+ continue;
+ if (!apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id))
+ continue;
+
+ if (!cmdline_apic) {
+ apic = apic_probe[i];
+ if (x86_quirks->update_genapic)
+ x86_quirks->update_genapic();
+ printk(KERN_INFO "Switched to APIC driver `%s'.\n",
+ apic->name);
+ }
+ return 1;
+ }
+ return 0;
+}
+
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+/**
+ * pre_intr_init_hook - 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 pre_intr_init_hook(void)
+{
+ if (x86_quirks->arch_pre_intr_init) {
+ if (x86_quirks->arch_pre_intr_init())
+ return;
+ }
+ init_ISA_irqs();
+}
+
+/**
+ * intr_init_hook - post gate setup interrupt initialisation
+ *
+ * Description:
+ * Fill in any interrupts that may have been left out by the general
+ * init_IRQ() routine. interrupts having to do with the machine rather
+ * than the devices on the I/O bus (like APIC interrupts in intel MP
+ * systems) are started here.
+ **/
+void __init intr_init_hook(void)
+{
+ if (x86_quirks->arch_intr_init) {
+ if (x86_quirks->arch_intr_init())
+ return;
+ }
+}
+
+/**
+ * pre_setup_arch_hook - hook called prior to any setup_arch() execution
+ *
+ * Description:
+ * generally used to activate any machine specific identification
+ * routines that may be needed before setup_arch() runs. On Voyager
+ * this is used to get the board revision and type.
+ **/
+void __init pre_setup_arch_hook(void)
+{
+}
+
+/**
+ * trap_init_hook - initialise system specific traps
+ *
+ * Description:
+ * Called as the final act of trap_init(). Used in VISWS to initialise
+ * the various board specific APIC traps.
+ **/
+void __init trap_init_hook(void)
+{
+ if (x86_quirks->arch_trap_init) {
+ if (x86_quirks->arch_trap_init())
+ return;
+ }
+}
+
+static struct irqaction irq0 = {
+ .handler = timer_interrupt,
+ .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL,
+ .mask = CPU_MASK_NONE,
+ .name = "timer"
+};
+
+/**
+ * pre_time_init_hook - do any specific initialisations before.
+ *
+ **/
+void __init pre_time_init_hook(void)
+{
+ if (x86_quirks->arch_pre_time_init)
+ x86_quirks->arch_pre_time_init();
+}
+
+/**
+ * time_init_hook - do any specific initialisations for the system timer.
+ *
+ * Description:
+ * Must plug the system timer interrupt source at HZ into the IRQ listed
+ * in irq_vectors.h:TIMER_IRQ
+ **/
+void __init time_init_hook(void)
+{
+ if (x86_quirks->arch_time_init) {
+ /*
+ * A nonzero return code does not mean failure, it means
+ * that the architecture quirk does not want any
+ * generic (timer) setup to be performed after this:
+ */
+ if (x86_quirks->arch_time_init())
+ return;
+ }
+
+ irq0.mask = cpumask_of_cpu(0);
+ setup_irq(0, &irq0);
+}
+
+#ifdef CONFIG_MCA
+/**
+ * mca_nmi_hook - hook into MCA specific NMI chain
+ *
+ * Description:
+ * The MCA (Microchannel Architecture) has an NMI chain for NMI sources
+ * along the MCA bus. Use this to hook into that chain if you will need
+ * it.
+ **/
+void mca_nmi_hook(void)
+{
+ /*
+ * If I recall correctly, there's a whole bunch of other things that
+ * we can do to check for NMI problems, but that's all I know about
+ * at the moment.
+ */
+ pr_warning("NMI generated from unknown source!\n");
+}
+#endif
+
+static __init int no_ipi_broadcast(char *str)
+{
+ get_option(&str, &no_broadcast);
+ pr_info("Using %s mode\n",
+ no_broadcast ? "No IPI Broadcast" : "IPI Broadcast");
+ return 1;
+}
+__setup("no_ipi_broadcast=", no_ipi_broadcast);
+
+static int __init print_ipi_mode(void)
+{
+ pr_info("Using IPI %s mode\n",
+ no_broadcast ? "No-Shortcut" : "Shortcut");
+ return 0;
+}
+
+late_initcall(print_ipi_mode);
+
diff --git a/arch/x86/kernel/probe_roms_32.c b/arch/x86/kernel/probe_roms_32.c
index 675a48c404a5..071e7fea42e5 100644
--- a/arch/x86/kernel/probe_roms_32.c
+++ b/arch/x86/kernel/probe_roms_32.c
@@ -18,7 +18,7 @@
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/io.h>
-#include <setup_arch.h>
+#include <asm/setup_arch.h>
static struct resource system_rom_resource = {
.name = "System ROM",
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e68bb9e30864..89537f678b2d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -344,7 +344,7 @@ static void c1e_idle(void)
void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
if (pm_idle == poll_idle && smp_num_siblings > 1) {
printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
" performance may degrade.\n");
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a546f55c77b4..1a1ae8edc40c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -66,9 +66,6 @@ asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
EXPORT_PER_CPU_SYMBOL(current_task);
-DEFINE_PER_CPU(int, cpu_number);
-EXPORT_PER_CPU_SYMBOL(cpu_number);
-
/*
* Return saved PC of a blocked thread.
*/
@@ -111,7 +108,6 @@ void cpu_idle(void)
play_dead();
local_irq_disable();
- __get_cpu_var(irq_stat).idle_timestamp = jiffies;
/* Don't trace irqs off for idle */
stop_critical_timings();
pm_idle();
@@ -591,7 +587,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
if (prev->gs | next->gs)
loadsegment(gs, next->gs);
- x86_write_percpu(current_task, next_p);
+ percpu_write(current_task, next_p);
return prev_p;
}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 85b4cb5c1980..8eb169e45584 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -16,6 +16,7 @@
#include <stdarg.h>
+#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
@@ -47,7 +48,6 @@
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/mmu_context.h>
-#include <asm/pda.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/proto.h>
@@ -58,6 +58,12 @@
asmlinkage extern void ret_from_fork(void);
+DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+
+DEFINE_PER_CPU(unsigned long, old_rsp);
+static DEFINE_PER_CPU(unsigned char, is_idle);
+
unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
static ATOMIC_NOTIFIER_HEAD(idle_notifier);
@@ -76,13 +82,13 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister);
void enter_idle(void)
{
- write_pda(isidle, 1);
+ percpu_write(is_idle, 1);
atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}
static void __exit_idle(void)
{
- if (test_and_clear_bit_pda(0, isidle) == 0)
+ if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
return;
atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
}
@@ -112,6 +118,17 @@ static inline void play_dead(void)
void cpu_idle(void)
{
current_thread_info()->status |= TS_POLLING;
+
+ /*
+ * If we're the non-boot CPU, nothing set the PDA stack
+ * canary up for us - and if we are the boot CPU we have
+ * a 0 stack canary. This is a good place for updating
+ * it, as we wont ever return from this function (so the
+ * invalid canaries already on the stack wont ever
+ * trigger):
+ */
+ boot_init_stack_canary();
+
/* endless idle loop with no priority at all */
while (1) {
tick_nohz_stop_sched_tick(1);
@@ -397,7 +414,7 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
load_gs_index(0);
regs->ip = new_ip;
regs->sp = new_sp;
- write_pda(oldrsp, new_sp);
+ percpu_write(old_rsp, new_sp);
regs->cs = __USER_CS;
regs->ss = __USER_DS;
regs->flags = 0x200;
@@ -618,21 +635,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
/*
* Switch the PDA and FPU contexts.
*/
- prev->usersp = read_pda(oldrsp);
- write_pda(oldrsp, next->usersp);
- write_pda(pcurrent, next_p);
+ prev->usersp = percpu_read(old_rsp);
+ percpu_write(old_rsp, next->usersp);
+ percpu_write(current_task, next_p);
- write_pda(kernelstack,
+ percpu_write(kernel_stack,
(unsigned long)task_stack_page(next_p) +
- THREAD_SIZE - PDA_STACKOFFSET);
-#ifdef CONFIG_CC_STACKPROTECTOR
- write_pda(stack_canary, next_p->stack_canary);
- /*
- * Build time only check to make sure the stack_canary is at
- * offset 40 in the pda; this is a gcc ABI requirement
- */
- BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40);
-#endif
+ THREAD_SIZE - KERNEL_STACK_OFFSET);
/*
* Now maybe reload the debug registers and handle I/O bitmaps
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 2b46eb41643b..32e8f0af292c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -14,6 +14,7 @@
#include <asm/reboot.h>
#include <asm/pci_x86.h>
#include <asm/virtext.h>
+#include <asm/cpu.h>
#ifdef CONFIG_X86_32
# include <linux/dmi.h>
@@ -23,7 +24,7 @@
# include <asm/iommu.h>
#endif
-#include <mach_ipi.h>
+#include <asm/genapic.h>
/*
* Power off function, if any
@@ -650,7 +651,7 @@ static int crash_nmi_callback(struct notifier_block *self,
static void smp_send_nmi_allbutself(void)
{
- send_IPI_allbutself(NMI_VECTOR);
+ apic->send_IPI_allbutself(NMI_VECTOR);
}
static struct notifier_block crash_nmi_nb = {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c461f6d69074..8d8fa992c9a0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -81,7 +81,7 @@
#include <asm/io_apic.h>
#include <asm/ist.h>
#include <asm/vmi.h>
-#include <setup_arch.h>
+#include <asm/setup_arch.h>
#include <asm/bios_ebda.h>
#include <asm/cacheflush.h>
#include <asm/processor.h>
@@ -89,7 +89,7 @@
#include <asm/system.h>
#include <asm/vsyscall.h>
-#include <asm/smp.h>
+#include <asm/cpu.h>
#include <asm/desc.h>
#include <asm/dma.h>
#include <asm/iommu.h>
@@ -97,7 +97,7 @@
#include <asm/mmu_context.h>
#include <asm/proto.h>
-#include <mach_apic.h>
+#include <asm/genapic.h>
#include <asm/paravirt.h>
#include <asm/hypervisor.h>
@@ -112,6 +112,20 @@
#define ARCH_SETUP
#endif
+unsigned int boot_cpu_id __read_mostly;
+
+#ifdef CONFIG_X86_64
+int default_cpu_present_to_apicid(int mps_cpu)
+{
+ return __default_cpu_present_to_apicid(mps_cpu);
+}
+
+int default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+ return __default_check_phys_apicid_present(boot_cpu_physical_apicid);
+}
+#endif
+
#ifndef CONFIG_DEBUG_BOOT_PARAMS
struct boot_params __initdata boot_params;
#else
@@ -588,10 +602,9 @@ early_param("elfcorehdr", setup_elfcorehdr);
static int __init default_update_genapic(void)
{
-#ifdef CONFIG_X86_SMP
-# if defined(CONFIG_X86_GENERICARCH) || defined(CONFIG_X86_64)
- genapic->wakeup_cpu = wakeup_secondary_cpu_via_init;
-# endif
+#ifdef CONFIG_SMP
+ if (!apic->wakeup_cpu)
+ apic->wakeup_cpu = wakeup_secondary_cpu_via_init;
#endif
return 0;
@@ -892,12 +905,11 @@ void __init setup_arch(char **cmdline_p)
*/
acpi_reserve_bootmem();
#endif
-#ifdef CONFIG_X86_FIND_SMP_CONFIG
/*
* Find and reserve possible boot-time SMP configuration:
*/
find_smp_config();
-#endif
+
reserve_crashkernel();
#ifdef CONFIG_X86_64
@@ -924,7 +936,7 @@ void __init setup_arch(char **cmdline_p)
map_vsyscall();
#endif
-#ifdef CONFIG_X86_GENERICARCH
+#if defined(CONFIG_X86_32_NON_STANDARD) || defined(CONFIG_X86_BIGSMP)
generic_apic_probe();
#endif
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 01161077a49c..0d1e7ac439f4 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -13,145 +13,46 @@
#include <asm/mpspec.h>
#include <asm/apicdef.h>
#include <asm/highmem.h>
+#include <asm/proto.h>
+#include <asm/cpumask.h>
+#include <asm/cpu.h>
-#ifdef CONFIG_X86_LOCAL_APIC
-unsigned int num_processors;
-unsigned disabled_cpus __cpuinitdata;
-/* Processor that is doing the boot up */
-unsigned int boot_cpu_physical_apicid = -1U;
-EXPORT_SYMBOL(boot_cpu_physical_apicid);
-unsigned int max_physical_apicid;
-
-/* Bitmask of physically existing CPUs */
-physid_mask_t phys_cpu_present_map;
-#endif
-
-/* map cpu index to physical APIC ID */
-DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
-DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
-#define X86_64_NUMA 1
-
-/* map cpu index to node index */
-DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
-
-/* which logical CPUs are on which nodes */
-cpumask_t *node_to_cpumask_map;
-EXPORT_SYMBOL(node_to_cpumask_map);
-
-/* setup node_to_cpumask_map */
-static void __init setup_node_to_cpumask_map(void);
-
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
#else
-static inline void setup_node_to_cpumask_map(void) { }
+# define DBG(x...)
#endif
-#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP)
-/*
- * Copy data used in early init routines from the initial arrays to the
- * per cpu data areas. These arrays then become expendable and the
- * *_early_ptr's are zeroed indicating that the static arrays are gone.
- */
-static void __init setup_per_cpu_maps(void)
-{
- int cpu;
+DEFINE_PER_CPU(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
- for_each_possible_cpu(cpu) {
- per_cpu(x86_cpu_to_apicid, cpu) =
- early_per_cpu_map(x86_cpu_to_apicid, cpu);
- per_cpu(x86_bios_cpu_apicid, cpu) =
- early_per_cpu_map(x86_bios_cpu_apicid, cpu);
-#ifdef X86_64_NUMA
- per_cpu(x86_cpu_to_node_map, cpu) =
- early_per_cpu_map(x86_cpu_to_node_map, cpu);
+#ifdef CONFIG_X86_64
+#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
+#else
+#define BOOT_PERCPU_OFFSET 0
#endif
- }
- /* indicate the early static arrays will soon be gone */
- early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
- early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
-#ifdef X86_64_NUMA
- early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
-#endif
-}
+DEFINE_PER_CPU(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+EXPORT_PER_CPU_SYMBOL(this_cpu_off);
-#ifdef CONFIG_X86_32
-/*
- * Great future not-so-futuristic plan: make i386 and x86_64 do it
- * the same way
- */
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
+ [0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
+};
EXPORT_SYMBOL(__per_cpu_offset);
-static inline void setup_cpu_pda_map(void) { }
-
-#elif !defined(CONFIG_SMP)
-static inline void setup_cpu_pda_map(void) { }
-
-#else /* CONFIG_SMP && CONFIG_X86_64 */
-
-/*
- * Allocate cpu_pda pointer table and array via alloc_bootmem.
- */
-static void __init setup_cpu_pda_map(void)
-{
- char *pda;
- struct x8664_pda **new_cpu_pda;
- unsigned long size;
- int cpu;
-
- size = roundup(sizeof(struct x8664_pda), cache_line_size());
-
- /* allocate cpu_pda array and pointer table */
- {
- unsigned long tsize = nr_cpu_ids * sizeof(void *);
- unsigned long asize = size * (nr_cpu_ids - 1);
- tsize = roundup(tsize, cache_line_size());
- new_cpu_pda = alloc_bootmem(tsize + asize);
- pda = (char *)new_cpu_pda + tsize;
- }
-
- /* initialize pointer table to static pda's */
- for_each_possible_cpu(cpu) {
- if (cpu == 0) {
- /* leave boot cpu pda in place */
- new_cpu_pda[0] = cpu_pda(0);
- continue;
- }
- new_cpu_pda[cpu] = (struct x8664_pda *)pda;
- new_cpu_pda[cpu]->in_bootmem = 1;
- pda += size;
- }
-
- /* point to new pointer table */
- _cpu_pda = new_cpu_pda;
-}
-
-#endif /* CONFIG_SMP && CONFIG_X86_64 */
-
-#ifdef CONFIG_X86_64
-
-/* correctly size the local cpu masks */
-static void __init setup_cpu_local_masks(void)
+static inline void setup_percpu_segment(int cpu)
{
- alloc_bootmem_cpumask_var(&cpu_initialized_mask);
- alloc_bootmem_cpumask_var(&cpu_callin_mask);
- alloc_bootmem_cpumask_var(&cpu_callout_mask);
- alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
-}
-
-#else /* CONFIG_X86_32 */
+#ifdef CONFIG_X86_32
+ struct desc_struct gdt;
-static inline void setup_cpu_local_masks(void)
-{
+ pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF,
+ 0x2 | DESCTYPE_S, 0x8);
+ gdt.s = 1;
+ write_gdt_entry(get_cpu_gdt_table(cpu),
+ GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
+#endif
}
-#endif /* CONFIG_X86_32 */
-
/*
* Great future plan:
* Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
@@ -159,18 +60,12 @@ static inline void setup_cpu_local_masks(void)
*/
void __init setup_per_cpu_areas(void)
{
- ssize_t size, old_size;
+ ssize_t size;
char *ptr;
int cpu;
- unsigned long align = 1;
-
- /* Setup cpu_pda map */
- setup_cpu_pda_map();
/* Copy section for each CPU (we discard the original) */
- old_size = PERCPU_ENOUGH_ROOM;
- align = max_t(unsigned long, PAGE_SIZE, align);
- size = roundup(old_size, align);
+ size = roundup(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
@@ -179,30 +74,67 @@ void __init setup_per_cpu_areas(void)
for_each_possible_cpu(cpu) {
#ifndef CONFIG_NEED_MULTIPLE_NODES
- ptr = __alloc_bootmem(size, align,
- __pa(MAX_DMA_ADDRESS));
+ ptr = alloc_bootmem_pages(size);
#else
int node = early_cpu_to_node(cpu);
if (!node_online(node) || !NODE_DATA(node)) {
- ptr = __alloc_bootmem(size, align,
- __pa(MAX_DMA_ADDRESS));
+ ptr = alloc_bootmem_pages(size);
pr_info("cpu %d has no node %d or node-local memory\n",
cpu, node);
pr_debug("per cpu data for cpu%d at %016lx\n",
cpu, __pa(ptr));
} else {
- ptr = __alloc_bootmem_node(NODE_DATA(node), size, align,
- __pa(MAX_DMA_ADDRESS));
+ ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
pr_debug("per cpu data for cpu%d on node%d at %016lx\n",
cpu, node, __pa(ptr));
}
#endif
+
+ memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start);
per_cpu_offset(cpu) = ptr - __per_cpu_start;
- memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+ per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
+ per_cpu(cpu_number, cpu) = cpu;
+ setup_percpu_segment(cpu);
+ /*
+ * Copy data used in early init routines from the
+ * initial arrays to the per cpu data areas. These
+ * arrays then become expendable and the *_early_ptr's
+ * are zeroed indicating that the static arrays are
+ * gone.
+ */
+#ifdef CONFIG_X86_LOCAL_APIC
+ per_cpu(x86_cpu_to_apicid, cpu) =
+ early_per_cpu_map(x86_cpu_to_apicid, cpu);
+ per_cpu(x86_bios_cpu_apicid, cpu) =
+ early_per_cpu_map(x86_bios_cpu_apicid, cpu);
+#endif
+#ifdef CONFIG_X86_64
+ per_cpu(irq_stack_ptr, cpu) =
+ per_cpu(irq_stack_union.irq_stack, cpu) +
+ IRQ_STACK_SIZE - 64;
+#ifdef CONFIG_NUMA
+ per_cpu(x86_cpu_to_node_map, cpu) =
+ early_per_cpu_map(x86_cpu_to_node_map, cpu);
+#endif
+#endif
+ /*
+ * Up to this point, the boot CPU has been using .data.init
+ * area. Reload any changed state for the boot CPU.
+ */
+ if (cpu == boot_cpu_id)
+ switch_to_new_gdt();
+
+ DBG("PERCPU: cpu %4d %p\n", cpu, ptr);
}
- /* Setup percpu data maps */
- setup_per_cpu_maps();
+ /* indicate the early static arrays will soon be gone */
+#ifdef CONFIG_X86_LOCAL_APIC
+ early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
+ early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
+#endif
+#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+ early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
+#endif
/* Setup node to cpumask map */
setup_node_to_cpumask_map();
@@ -210,199 +142,3 @@ void __init setup_per_cpu_areas(void)
/* Setup cpu initialized, callin, callout masks */
setup_cpu_local_masks();
}
-
-#endif
-
-#ifdef X86_64_NUMA
-
-/*
- * Allocate node_to_cpumask_map based on number of available nodes
- * Requires node_possible_map to be valid.
- *
- * Note: node_to_cpumask() is not valid until after this is done.
- */
-static void __init setup_node_to_cpumask_map(void)
-{
- unsigned int node, num = 0;
- cpumask_t *map;
-
- /* setup nr_node_ids if not done yet */
- if (nr_node_ids == MAX_NUMNODES) {
- for_each_node_mask(node, node_possible_map)
- num = node;
- nr_node_ids = num + 1;
- }
-
- /* allocate the map */
- map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
-
- pr_debug("Node to cpumask map at %p for %d nodes\n",
- map, nr_node_ids);
-
- /* node_to_cpumask() will now work */
- node_to_cpumask_map = map;
-}
-
-void __cpuinit numa_set_node(int cpu, int node)
-{
- int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
-
- if (cpu_pda(cpu) && node != NUMA_NO_NODE)
- cpu_pda(cpu)->nodenumber = node;
-
- if (cpu_to_node_map)
- cpu_to_node_map[cpu] = node;
-
- else if (per_cpu_offset(cpu))
- per_cpu(x86_cpu_to_node_map, cpu) = node;
-
- else
- pr_debug("Setting node for non-present cpu %d\n", cpu);
-}
-
-void __cpuinit numa_clear_node(int cpu)
-{
- numa_set_node(cpu, NUMA_NO_NODE);
-}
-
-#ifndef CONFIG_DEBUG_PER_CPU_MAPS
-
-void __cpuinit numa_add_cpu(int cpu)
-{
- cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
-}
-
-void __cpuinit numa_remove_cpu(int cpu)
-{
- cpu_clear(cpu, node_to_cpumask_map[cpu_to_node(cpu)]);
-}
-
-#else /* CONFIG_DEBUG_PER_CPU_MAPS */
-
-/*
- * --------- debug versions of the numa functions ---------
- */
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
-{
- int node = cpu_to_node(cpu);
- cpumask_t *mask;
- char buf[64];
-
- if (node_to_cpumask_map == NULL) {
- printk(KERN_ERR "node_to_cpumask_map NULL\n");
- dump_stack();
- return;
- }
-
- mask = &node_to_cpumask_map[node];
- if (enable)
- cpu_set(cpu, *mask);
- else
- cpu_clear(cpu, *mask);
-
- cpulist_scnprintf(buf, sizeof(buf), mask);
- printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
- enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf);
-}
-
-void __cpuinit numa_add_cpu(int cpu)
-{
- numa_set_cpumask(cpu, 1);
-}
-
-void __cpuinit numa_remove_cpu(int cpu)
-{
- numa_set_cpumask(cpu, 0);
-}
-
-int cpu_to_node(int cpu)
-{
- if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
- printk(KERN_WARNING
- "cpu_to_node(%d): usage too early!\n", cpu);
- dump_stack();
- return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
- }
- return per_cpu(x86_cpu_to_node_map, cpu);
-}
-EXPORT_SYMBOL(cpu_to_node);
-
-/*
- * Same function as cpu_to_node() but used if called before the
- * per_cpu areas are setup.
- */
-int early_cpu_to_node(int cpu)
-{
- if (early_per_cpu_ptr(x86_cpu_to_node_map))
- return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
- if (!per_cpu_offset(cpu)) {
- printk(KERN_WARNING
- "early_cpu_to_node(%d): no per_cpu area!\n", cpu);
- dump_stack();
- return NUMA_NO_NODE;
- }
- return per_cpu(x86_cpu_to_node_map, cpu);
-}
-
-
-/* empty cpumask */
-static const cpumask_t cpu_mask_none;
-
-/*
- * Returns a pointer to the bitmask of CPUs on Node 'node'.
- */
-const cpumask_t *cpumask_of_node(int node)
-{
- if (node_to_cpumask_map == NULL) {
- printk(KERN_WARNING
- "cpumask_of_node(%d): no node_to_cpumask_map!\n",
- node);
- dump_stack();
- return (const cpumask_t *)&cpu_online_map;
- }
- if (node >= nr_node_ids) {
- printk(KERN_WARNING
- "cpumask_of_node(%d): node > nr_node_ids(%d)\n",
- node, nr_node_ids);
- dump_stack();
- return &cpu_mask_none;
- }
- return &node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(cpumask_of_node);
-
-/*
- * Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used. The
- * node_to_cpumask_ptr function should be used whenever possible.
- */
-cpumask_t node_to_cpumask(int node)
-{
- if (node_to_cpumask_map == NULL) {
- printk(KERN_WARNING
- "node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
- dump_stack();
- return cpu_online_map;
- }
- if (node >= nr_node_ids) {
- printk(KERN_WARNING
- "node_to_cpumask(%d): node > nr_node_ids(%d)\n",
- node, nr_node_ids);
- dump_stack();
- return cpu_mask_none;
- }
- return node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(node_to_cpumask);
-
-/*
- * --------- end of debug versions of the numa functions ---------
- */
-
-#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
-
-#endif /* X86_64_NUMA */
-
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index df0587f24c54..7fc78b019815 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -51,24 +51,24 @@
#endif
#define COPY(x) { \
- err |= __get_user(regs->x, &sc->x); \
+ get_user_ex(regs->x, &sc->x); \
}
#define COPY_SEG(seg) { \
unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
+ get_user_ex(tmp, &sc->seg); \
regs->seg = tmp; \
}
#define COPY_SEG_CPL3(seg) { \
unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
+ get_user_ex(tmp, &sc->seg); \
regs->seg = tmp | 3; \
}
#define GET_SEG(seg) { \
unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
+ get_user_ex(tmp, &sc->seg); \
loadsegment(seg, tmp); \
}
@@ -83,45 +83,49 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
/* Always make any pending restarted system calls return -EINTR */
current_thread_info()->restart_block.fn = do_no_restart_syscall;
+ get_user_try {
+
#ifdef CONFIG_X86_32
- GET_SEG(gs);
- COPY_SEG(fs);
- COPY_SEG(es);
- COPY_SEG(ds);
+ GET_SEG(gs);
+ COPY_SEG(fs);
+ COPY_SEG(es);
+ COPY_SEG(ds);
#endif /* CONFIG_X86_32 */
- COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
- COPY(dx); COPY(cx); COPY(ip);
+ COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
+ COPY(dx); COPY(cx); COPY(ip);
#ifdef CONFIG_X86_64
- COPY(r8);
- COPY(r9);
- COPY(r10);
- COPY(r11);
- COPY(r12);
- COPY(r13);
- COPY(r14);
- COPY(r15);
+ COPY(r8);
+ COPY(r9);
+ COPY(r10);
+ COPY(r11);
+ COPY(r12);
+ COPY(r13);
+ COPY(r14);
+ COPY(r15);
#endif /* CONFIG_X86_64 */
#ifdef CONFIG_X86_32
- COPY_SEG_CPL3(cs);
- COPY_SEG_CPL3(ss);
+ COPY_SEG_CPL3(cs);
+ COPY_SEG_CPL3(ss);
#else /* !CONFIG_X86_32 */
- /* Kernel saves and restores only the CS segment register on signals,
- * which is the bare minimum needed to allow mixed 32/64-bit code.
- * App's signal handler can save/restore other segments if needed. */
- COPY_SEG_CPL3(cs);
+ /* Kernel saves and restores only the CS segment register on signals,
+ * which is the bare minimum needed to allow mixed 32/64-bit code.
+ * App's signal handler can save/restore other segments if needed. */
+ COPY_SEG_CPL3(cs);
#endif /* CONFIG_X86_32 */
- err |= __get_user(tmpflags, &sc->flags);
- regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
- regs->orig_ax = -1; /* disable syscall checks */
+ get_user_ex(tmpflags, &sc->flags);
+ regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
+ regs->orig_ax = -1; /* disable syscall checks */
+
+ get_user_ex(buf, &sc->fpstate);
+ err |= restore_i387_xstate(buf);
- err |= __get_user(buf, &sc->fpstate);
- err |= restore_i387_xstate(buf);
+ get_user_ex(*pax, &sc->ax);
+ } get_user_catch(err);
- err |= __get_user(*pax, &sc->ax);
return err;
}
@@ -131,57 +135,60 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
{
int err = 0;
+ put_user_try {
+
#ifdef CONFIG_X86_32
- {
- unsigned int tmp;
+ {
+ unsigned int tmp;
- savesegment(gs, tmp);
- err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
- }
- err |= __put_user(regs->fs, (unsigned int __user *)&sc->fs);
- err |= __put_user(regs->es, (unsigned int __user *)&sc->es);
- err |= __put_user(regs->ds, (unsigned int __user *)&sc->ds);
+ savesegment(gs, tmp);
+ put_user_ex(tmp, (unsigned int __user *)&sc->gs);
+ }
+ put_user_ex(regs->fs, (unsigned int __user *)&sc->fs);
+ put_user_ex(regs->es, (unsigned int __user *)&sc->es);
+ put_user_ex(regs->ds, (unsigned int __user *)&sc->ds);
#endif /* CONFIG_X86_32 */
- err |= __put_user(regs->di, &sc->di);
- err |= __put_user(regs->si, &sc->si);
- err |= __put_user(regs->bp, &sc->bp);
- err |= __put_user(regs->sp, &sc->sp);
- err |= __put_user(regs->bx, &sc->bx);
- err |= __put_user(regs->dx, &sc->dx);
- err |= __put_user(regs->cx, &sc->cx);
- err |= __put_user(regs->ax, &sc->ax);
+ put_user_ex(regs->di, &sc->di);
+ put_user_ex(regs->si, &sc->si);
+ put_user_ex(regs->bp, &sc->bp);
+ put_user_ex(regs->sp, &sc->sp);
+ put_user_ex(regs->bx, &sc->bx);
+ put_user_ex(regs->dx, &sc->dx);
+ put_user_ex(regs->cx, &sc->cx);
+ put_user_ex(regs->ax, &sc->ax);
#ifdef CONFIG_X86_64
- err |= __put_user(regs->r8, &sc->r8);
- err |= __put_user(regs->r9, &sc->r9);
- err |= __put_user(regs->r10, &sc->r10);
- err |= __put_user(regs->r11, &sc->r11);
- err |= __put_user(regs->r12, &sc->r12);
- err |= __put_user(regs->r13, &sc->r13);
- err |= __put_user(regs->r14, &sc->r14);
- err |= __put_user(regs->r15, &sc->r15);
+ put_user_ex(regs->r8, &sc->r8);
+ put_user_ex(regs->r9, &sc->r9);
+ put_user_ex(regs->r10, &sc->r10);
+ put_user_ex(regs->r11, &sc->r11);
+ put_user_ex(regs->r12, &sc->r12);
+ put_user_ex(regs->r13, &sc->r13);
+ put_user_ex(regs->r14, &sc->r14);
+ put_user_ex(regs->r15, &sc->r15);
#endif /* CONFIG_X86_64 */
- err |= __put_user(current->thread.trap_no, &sc->trapno);
- err |= __put_user(current->thread.error_code, &sc->err);
- err |= __put_user(regs->ip, &sc->ip);
+ put_user_ex(current->thread.trap_no, &sc->trapno);
+ put_user_ex(current->thread.error_code, &sc->err);
+ put_user_ex(regs->ip, &sc->ip);
#ifdef CONFIG_X86_32
- err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs);
- err |= __put_user(regs->flags, &sc->flags);
- err |= __put_user(regs->sp, &sc->sp_at_signal);
- err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
+ put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
+ put_user_ex(regs->flags, &sc->flags);
+ put_user_ex(regs->sp, &sc->sp_at_signal);
+ put_user_ex(regs->ss, (unsigned int __user *)&sc->ss);
#else /* !CONFIG_X86_32 */
- err |= __put_user(regs->flags, &sc->flags);
- err |= __put_user(regs->cs, &sc->cs);
- err |= __put_user(0, &sc->gs);
- err |= __put_user(0, &sc->fs);
+ put_user_ex(regs->flags, &sc->flags);
+ put_user_ex(regs->cs, &sc->cs);
+ put_user_ex(0, &sc->gs);
+ put_user_ex(0, &sc->fs);
#endif /* CONFIG_X86_32 */
- err |= __put_user(fpstate, &sc->fpstate);
+ put_user_ex(fpstate, &sc->fpstate);
- /* non-iBCS2 extensions.. */
- err |= __put_user(mask, &sc->oldmask);
- err |= __put_user(current->thread.cr2, &sc->cr2);
+ /* non-iBCS2 extensions.. */
+ put_user_ex(mask, &sc->oldmask);
+ put_user_ex(current->thread.cr2, &sc->cr2);
+ } put_user_catch(err);
return err;
}
@@ -336,43 +343,41 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return -EFAULT;
- err |= __put_user(sig, &frame->sig);
- err |= __put_user(&frame->info, &frame->pinfo);
- err |= __put_user(&frame->uc, &frame->puc);
- err |= copy_siginfo_to_user(&frame->info, info);
- if (err)
- return -EFAULT;
-
- /* Create the ucontext. */
- if (cpu_has_xsave)
- err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
- else
- err |= __put_user(0, &frame->uc.uc_flags);
- err |= __put_user(0, &frame->uc.uc_link);
- err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- err |= __put_user(sas_ss_flags(regs->sp),
- &frame->uc.uc_stack.ss_flags);
- err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
- if (err)
- return -EFAULT;
+ put_user_try {
+ put_user_ex(sig, &frame->sig);
+ put_user_ex(&frame->info, &frame->pinfo);
+ put_user_ex(&frame->uc, &frame->puc);
+ err |= copy_siginfo_to_user(&frame->info, info);
- /* Set up to return from userspace. */
- restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
- if (ka->sa.sa_flags & SA_RESTORER)
- restorer = ka->sa.sa_restorer;
- err |= __put_user(restorer, &frame->pretcode);
+ /* Create the ucontext. */
+ if (cpu_has_xsave)
+ put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ put_user_ex(0, &frame->uc.uc_flags);
+ put_user_ex(0, &frame->uc.uc_link);
+ put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ put_user_ex(sas_ss_flags(regs->sp),
+ &frame->uc.uc_stack.ss_flags);
+ put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+ /* Set up to return from userspace. */
+ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
+ if (ka->sa.sa_flags & SA_RESTORER)
+ restorer = ka->sa.sa_restorer;
+ put_user_ex(restorer, &frame->pretcode);
- /*
- * This is movl $__NR_rt_sigreturn, %ax ; int $0x80
- *
- * WE DO NOT USE IT ANY MORE! It's only left here for historical
- * reasons and because gdb uses it as a signature to notice
- * signal handler stack frames.
- */
- err |= __put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
+ /*
+ * This is movl $__NR_rt_sigreturn, %ax ; int $0x80
+ *
+ * WE DO NOT USE IT ANY MORE! It's only left here for historical
+ * reasons and because gdb uses it as a signature to notice
+ * signal handler stack frames.
+ */
+ put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
+ } put_user_catch(err);
if (err)
return -EFAULT;
@@ -436,28 +441,30 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
return -EFAULT;
}
- /* Create the ucontext. */
- if (cpu_has_xsave)
- err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
- else
- err |= __put_user(0, &frame->uc.uc_flags);
- err |= __put_user(0, &frame->uc.uc_link);
- err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- err |= __put_user(sas_ss_flags(regs->sp),
- &frame->uc.uc_stack.ss_flags);
- err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
- /* Set up to return from userspace. If provided, use a stub
- already in userspace. */
- /* x86-64 should always use SA_RESTORER. */
- if (ka->sa.sa_flags & SA_RESTORER) {
- err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
- } else {
- /* could use a vstub here */
- return -EFAULT;
- }
+ put_user_try {
+ /* Create the ucontext. */
+ if (cpu_has_xsave)
+ put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ put_user_ex(0, &frame->uc.uc_flags);
+ put_user_ex(0, &frame->uc.uc_link);
+ put_user_ex(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ put_user_ex(sas_ss_flags(regs->sp),
+ &frame->uc.uc_stack.ss_flags);
+ put_user_ex(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ /* x86-64 should always use SA_RESTORER. */
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ put_user_ex(ka->sa.sa_restorer, &frame->pretcode);
+ } else {
+ /* could use a vstub here */
+ err |= -EFAULT;
+ }
+ } put_user_catch(err);
if (err)
return -EFAULT;
@@ -509,31 +516,41 @@ sys_sigaction(int sig, const struct old_sigaction __user *act,
struct old_sigaction __user *oact)
{
struct k_sigaction new_ka, old_ka;
- int ret;
+ int ret = 0;
if (act) {
old_sigset_t mask;
- if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
- __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
- __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+ if (!access_ok(VERIFY_READ, act, sizeof(*act)))
return -EFAULT;
- __get_user(new_ka.sa.sa_flags, &act->sa_flags);
- __get_user(mask, &act->sa_mask);
+ get_user_try {
+ get_user_ex(new_ka.sa.sa_handler, &act->sa_handler);
+ get_user_ex(new_ka.sa.sa_flags, &act->sa_flags);
+ get_user_ex(mask, &act->sa_mask);
+ get_user_ex(new_ka.sa.sa_restorer, &act->sa_restorer);
+ } get_user_catch(ret);
+
+ if (ret)
+ return -EFAULT;
siginitset(&new_ka.sa.sa_mask, mask);
}
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
- if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
- __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
- __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+ if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)))
return -EFAULT;
- __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
- __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+ put_user_try {
+ put_user_ex(old_ka.sa.sa_handler, &oact->sa_handler);
+ put_user_ex(old_ka.sa.sa_flags, &oact->sa_flags);
+ put_user_ex(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+ put_user_ex(old_ka.sa.sa_restorer, &oact->sa_restorer);
+ } put_user_catch(ret);
+
+ if (ret)
+ return -EFAULT;
}
return ret;
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index e6faa3316bd2..eaaffae31cc0 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -2,7 +2,7 @@
* Intel SMP support routines.
*
* (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk>
- * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com>
+ * (c) 1998-99, 2000, 2009 Ingo Molnar <mingo@redhat.com>
* (c) 2002,2003 Andi Kleen, SuSE Labs.
*
* i386 and x86_64 integration by Glauber Costa <gcosta@redhat.com>
@@ -26,8 +26,7 @@
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
-#include <mach_ipi.h>
-#include <mach_apic.h>
+#include <asm/genapic.h>
/*
* Some notes on x86 processor bugs affecting SMP operation:
*
@@ -118,12 +117,12 @@ static void native_smp_send_reschedule(int cpu)
WARN_ON(1);
return;
}
- send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR);
+ apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR);
}
void native_send_call_func_single_ipi(int cpu)
{
- send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR);
+ apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR);
}
void native_send_call_func_ipi(const struct cpumask *mask)
@@ -131,7 +130,7 @@ void native_send_call_func_ipi(const struct cpumask *mask)
cpumask_var_t allbutself;
if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) {
- send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
+ apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
return;
}
@@ -140,9 +139,9 @@ void native_send_call_func_ipi(const struct cpumask *mask)
if (cpumask_equal(mask, allbutself) &&
cpumask_equal(cpu_online_mask, cpu_callout_mask))
- send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+ apic->send_IPI_allbutself(CALL_FUNCTION_VECTOR);
else
- send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
+ apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
free_cpumask_var(allbutself);
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index bb1a3b1fc87f..96f7d304f5c9 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -2,7 +2,7 @@
* x86 SMP booting functions
*
* (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk>
- * (c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com>
+ * (c) 1998, 1999, 2000, 2009 Ingo Molnar <mingo@redhat.com>
* Copyright 2001 Andi Kleen, SuSE Labs.
*
* Much of the core SMP work is based on previous work by Thomas Radke, to
@@ -53,7 +53,6 @@
#include <asm/nmi.h>
#include <asm/irq.h>
#include <asm/idle.h>
-#include <asm/smp.h>
#include <asm/trampoline.h>
#include <asm/cpu.h>
#include <asm/numa.h>
@@ -63,11 +62,11 @@
#include <asm/vmi.h>
#include <asm/genapic.h>
#include <asm/setup.h>
+#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
-#include <mach_apic.h>
-#include <mach_wakecpu.h>
-#include <smpboot_hooks.h>
+#include <asm/genapic.h>
+#include <asm/smpboot_hooks.h>
#ifdef CONFIG_X86_32
u8 apicid_2_node[MAX_APICID];
@@ -163,7 +162,7 @@ static void map_cpu_to_logical_apicid(void)
{
int cpu = smp_processor_id();
int apicid = logical_smp_processor_id();
- int node = apicid_to_node(apicid);
+ int node = apic->apicid_to_node(apicid);
if (!node_online(node))
node = first_online_node;
@@ -196,7 +195,8 @@ static void __cpuinit smp_callin(void)
* our local APIC. We have to wait for the IPI or we'll
* lock up on an APIC access.
*/
- wait_for_init_deassert(&init_deasserted);
+ if (apic->wait_for_init_deassert)
+ apic->wait_for_init_deassert(&init_deasserted);
/*
* (This works even if the APIC is not enabled.)
@@ -243,7 +243,8 @@ static void __cpuinit smp_callin(void)
*/
pr_debug("CALLIN, before setup_local_APIC().\n");
- smp_callin_clear_local_apic();
+ if (apic->smp_callin_clear_local_apic)
+ apic->smp_callin_clear_local_apic();
setup_local_APIC();
end_local_APIC_setup();
map_cpu_to_logical_apicid();
@@ -583,7 +584,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
/* Target chip */
/* Boot on the stack */
/* Kick the second */
- apic_icr_write(APIC_DM_NMI | APIC_DEST_LOGICAL, logical_apicid);
+ apic_icr_write(APIC_DM_NMI | apic->dest_logical, logical_apicid);
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
@@ -745,57 +746,11 @@ static void __cpuinit do_fork_idle(struct work_struct *work)
complete(&c_idle->done);
}
-#ifdef CONFIG_X86_64
-
-/* __ref because it's safe to call free_bootmem when after_bootmem == 0. */
-static void __ref free_bootmem_pda(struct x8664_pda *oldpda)
-{
- if (!after_bootmem)
- free_bootmem((unsigned long)oldpda, sizeof(*oldpda));
-}
-
-/*
- * Allocate node local memory for the AP pda.
- *
- * Must be called after the _cpu_pda pointer table is initialized.
- */
-int __cpuinit get_local_pda(int cpu)
-{
- struct x8664_pda *oldpda, *newpda;
- unsigned long size = sizeof(struct x8664_pda);
- int node = cpu_to_node(cpu);
-
- if (cpu_pda(cpu) && !cpu_pda(cpu)->in_bootmem)
- return 0;
-
- oldpda = cpu_pda(cpu);
- newpda = kmalloc_node(size, GFP_ATOMIC, node);
- if (!newpda) {
- printk(KERN_ERR "Could not allocate node local PDA "
- "for CPU %d on node %d\n", cpu, node);
-
- if (oldpda)
- return 0; /* have a usable pda */
- else
- return -1;
- }
-
- if (oldpda) {
- memcpy(newpda, oldpda, size);
- free_bootmem_pda(oldpda);
- }
-
- newpda->in_bootmem = 0;
- cpu_pda(cpu) = newpda;
- return 0;
-}
-#endif /* CONFIG_X86_64 */
-
static int __cpuinit do_boot_cpu(int apicid, int cpu)
/*
* NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
* (ie clustered apic addressing mode), this is a LOGICAL apic ID.
- * Returns zero if CPU booted OK, else error code from wakeup_secondary_cpu.
+ * Returns zero if CPU booted OK, else error code from ->wakeup_cpu.
*/
{
unsigned long boot_error = 0;
@@ -808,16 +763,6 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
};
INIT_WORK(&c_idle.work, do_fork_idle);
-#ifdef CONFIG_X86_64
- /* Allocate node local memory for AP pdas */
- if (cpu > 0) {
- boot_error = get_local_pda(cpu);
- if (boot_error)
- goto restore_state;
- /* if can't get pda memory, can't start cpu */
- }
-#endif
-
alternatives_smp_switch(1);
c_idle.idle = get_idle_for_cpu(cpu);
@@ -847,14 +792,16 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
set_idle_for_cpu(cpu, c_idle.idle);
do_rest:
-#ifdef CONFIG_X86_32
per_cpu(current_task, cpu) = c_idle.idle;
- init_gdt(cpu);
+#ifdef CONFIG_X86_32
/* Stack for startup_32 can be just as for start_secondary onwards */
irq_ctx_init(cpu);
#else
- cpu_pda(cpu)->pcurrent = c_idle.idle;
clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
+ initial_gs = per_cpu_offset(cpu);
+ per_cpu(kernel_stack, cpu) =
+ (unsigned long)task_stack_page(c_idle.idle) -
+ KERNEL_STACK_OFFSET + THREAD_SIZE;
#endif
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
@@ -878,7 +825,8 @@ do_rest:
pr_debug("Setting warm reset code and vector.\n");
- store_NMI_vector(&nmi_high, &nmi_low);
+ if (apic->store_NMI_vector)
+ apic->store_NMI_vector(&nmi_high, &nmi_low);
smpboot_setup_warm_reset_vector(start_ip);
/*
@@ -893,7 +841,7 @@ do_rest:
/*
* Starting actual IPI sequence...
*/
- boot_error = wakeup_secondary_cpu(apicid, start_ip);
+ boot_error = apic->wakeup_cpu(apicid, start_ip);
if (!boot_error) {
/*
@@ -927,13 +875,11 @@ do_rest:
else
/* trampoline code not run */
printk(KERN_ERR "Not responding.\n");
- if (get_uv_system_type() != UV_NON_UNIQUE_APIC)
- inquire_remote_apic(apicid);
+ if (apic->inquire_remote_apic)
+ apic->inquire_remote_apic(apicid);
}
}
-#ifdef CONFIG_X86_64
-restore_state:
-#endif
+
if (boot_error) {
/* Try to put things back the way they were before ... */
numa_remove_cpu(cpu); /* was set by numa_add_cpu */
@@ -961,7 +907,7 @@ restore_state:
int __cpuinit native_cpu_up(unsigned int cpu)
{
- int apicid = cpu_present_to_apicid(cpu);
+ int apicid = apic->cpu_present_to_apicid(cpu);
unsigned long flags;
int err;
@@ -1054,14 +1000,14 @@ static int __init smp_sanity_check(unsigned max_cpus)
{
preempt_disable();
-#if defined(CONFIG_X86_PC) && defined(CONFIG_X86_32)
+#if !defined(CONFIG_X86_BIGSMP) && defined(CONFIG_X86_32)
if (def_to_bigsmp && nr_cpu_ids > 8) {
unsigned int cpu;
unsigned nr;
printk(KERN_WARNING
"More than 8 CPUs detected - skipping them.\n"
- "Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.\n");
+ "Use CONFIG_X86_BIGSMP.\n");
nr = 0;
for_each_present_cpu(cpu) {
@@ -1107,7 +1053,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
* Should not be necessary because the MP table should list the boot
* CPU too, but we do it for the sake of robustness anyway.
*/
- if (!check_phys_apicid_present(boot_cpu_physical_apicid)) {
+ if (!apic->check_phys_apicid_present(boot_cpu_physical_apicid)) {
printk(KERN_NOTICE
"weird, boot CPU (#%d) not listed by the BIOS.\n",
boot_cpu_physical_apicid);
@@ -1125,6 +1071,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
printk(KERN_ERR "... forcing use of dummy APIC emulation."
"(tell your hw vendor)\n");
smpboot_clear_io_apic();
+ arch_disable_smp_support();
return -1;
}
@@ -1183,7 +1130,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
#ifdef CONFIG_X86_64
enable_IR_x2apic();
- setup_apic_routing();
+ default_setup_apic_routing();
#endif
if (smp_sanity_check(max_cpus) < 0) {
@@ -1218,7 +1165,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
map_cpu_to_logical_apicid();
- setup_portio_remap();
+ if (apic->setup_portio_remap)
+ apic->setup_portio_remap();
smpboot_setup_io_apic();
/*
@@ -1240,9 +1188,6 @@ out:
void __init native_smp_prepare_boot_cpu(void)
{
int me = smp_processor_id();
-#ifdef CONFIG_X86_32
- init_gdt(me);
-#endif
switch_to_new_gdt();
/* already set me in cpu_online_mask in boot_cpu_init() */
cpumask_set_cpu(me, cpu_callout_mask);
diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c
deleted file mode 100644
index 397e309839dd..000000000000
--- a/arch/x86/kernel/smpcommon.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * SMP stuff which is common to all sub-architectures.
- */
-#include <linux/module.h>
-#include <asm/smp.h>
-
-#ifdef CONFIG_X86_32
-DEFINE_PER_CPU(unsigned long, this_cpu_off);
-EXPORT_PER_CPU_SYMBOL(this_cpu_off);
-
-/*
- * Initialize the CPU's GDT. This is either the boot CPU doing itself
- * (still using the master per-cpu area), or a CPU doing it for a
- * secondary which will soon come up.
- */
-__cpuinit void init_gdt(int cpu)
-{
- struct desc_struct gdt;
-
- pack_descriptor(&gdt, __per_cpu_offset[cpu], 0xFFFFF,
- 0x2 | DESCTYPE_S, 0x8);
- gdt.s = 1;
-
- write_gdt_entry(get_cpu_gdt_table(cpu),
- GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
-
- per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
- per_cpu(cpu_number, cpu) = cpu;
-}
-#endif
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 10786af95545..f7bddc2e37d1 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -1,7 +1,7 @@
/*
* Stack trace management functions
*
- * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2006-2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*/
#include <linux/sched.h>
#include <linux/stacktrace.h>
diff --git a/arch/x86/kernel/summit_32.c b/arch/x86/kernel/summit_32.c
index 7b987852e876..1e733eff9b33 100644
--- a/arch/x86/kernel/summit_32.c
+++ b/arch/x86/kernel/summit_32.c
@@ -30,8 +30,364 @@
#include <linux/init.h>
#include <asm/io.h>
#include <asm/bios_ebda.h>
-#include <asm/summit/mpparse.h>
+/*
+ * APIC driver for the IBM "Summit" chipset.
+ */
+#define APIC_DEFINITION 1
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <asm/mpspec.h>
+#include <asm/apic.h>
+#include <asm/smp.h>
+#include <asm/genapic.h>
+#include <asm/fixmap.h>
+#include <asm/apicdef.h>
+#include <asm/ipi.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/gfp.h>
+#include <linux/smp.h>
+
+static inline unsigned summit_get_apic_id(unsigned long x)
+{
+ return (x >> 24) & 0xFF;
+}
+
+static inline void summit_send_IPI_mask(const cpumask_t *mask, int vector)
+{
+ default_send_IPI_mask_sequence_logical(mask, vector);
+}
+
+static inline void summit_send_IPI_allbutself(int vector)
+{
+ cpumask_t mask = cpu_online_map;
+ cpu_clear(smp_processor_id(), mask);
+
+ if (!cpus_empty(mask))
+ summit_send_IPI_mask(&mask, vector);
+}
+
+static inline void summit_send_IPI_all(int vector)
+{
+ summit_send_IPI_mask(&cpu_online_map, vector);
+}
+
+#include <asm/tsc.h>
+
+extern int use_cyclone;
+
+#ifdef CONFIG_X86_SUMMIT_NUMA
+extern void setup_summit(void);
+#else
+#define setup_summit() {}
+#endif
+
+static inline int
+summit_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid)
+{
+ if (!strncmp(oem, "IBM ENSW", 8) &&
+ (!strncmp(productid, "VIGIL SMP", 9)
+ || !strncmp(productid, "EXA", 3)
+ || !strncmp(productid, "RUTHLESS SMP", 12))){
+ mark_tsc_unstable("Summit based system");
+ use_cyclone = 1; /*enable cyclone-timer*/
+ setup_summit();
+ return 1;
+ }
+ return 0;
+}
+
+/* Hook from generic ACPI tables.c */
+static inline int summit_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ if (!strncmp(oem_id, "IBM", 3) &&
+ (!strncmp(oem_table_id, "SERVIGIL", 8)
+ || !strncmp(oem_table_id, "EXA", 3))){
+ mark_tsc_unstable("Summit based system");
+ use_cyclone = 1; /*enable cyclone-timer*/
+ setup_summit();
+ return 1;
+ }
+ return 0;
+}
+
+struct rio_table_hdr {
+ unsigned char version; /* Version number of this data structure */
+ /* Version 3 adds chassis_num & WP_index */
+ unsigned char num_scal_dev; /* # of Scalability devices (Twisters for Vigil) */
+ unsigned char num_rio_dev; /* # of RIO I/O devices (Cyclones and Winnipegs) */
+} __attribute__((packed));
+
+struct scal_detail {
+ unsigned char node_id; /* Scalability Node ID */
+ unsigned long CBAR; /* Address of 1MB register space */
+ unsigned char port0node; /* Node ID port connected to: 0xFF=None */
+ unsigned char port0port; /* Port num port connected to: 0,1,2, or 0xFF=None */
+ unsigned char port1node; /* Node ID port connected to: 0xFF = None */
+ unsigned char port1port; /* Port num port connected to: 0,1,2, or 0xFF=None */
+ unsigned char port2node; /* Node ID port connected to: 0xFF = None */
+ unsigned char port2port; /* Port num port connected to: 0,1,2, or 0xFF=None */
+ unsigned char chassis_num; /* 1 based Chassis number (1 = boot node) */
+} __attribute__((packed));
+
+struct rio_detail {
+ unsigned char node_id; /* RIO Node ID */
+ unsigned long BBAR; /* Address of 1MB register space */
+ unsigned char type; /* Type of device */
+ unsigned char owner_id; /* For WPEG: Node ID of Cyclone that owns this WPEG*/
+ /* For CYC: Node ID of Twister that owns this CYC */
+ unsigned char port0node; /* Node ID port connected to: 0xFF=None */
+ unsigned char port0port; /* Port num port connected to: 0,1,2, or 0xFF=None */
+ unsigned char port1node; /* Node ID port connected to: 0xFF=None */
+ unsigned char port1port; /* Port num port connected to: 0,1,2, or 0xFF=None */
+ unsigned char first_slot; /* For WPEG: Lowest slot number below this WPEG */
+ /* For CYC: 0 */
+ unsigned char status; /* For WPEG: Bit 0 = 1 : the XAPIC is used */
+ /* = 0 : the XAPIC is not used, ie:*/
+ /* ints fwded to another XAPIC */
+ /* Bits1:7 Reserved */
+ /* For CYC: Bits0:7 Reserved */
+ unsigned char WP_index; /* For WPEG: WPEG instance index - lower ones have */
+ /* lower slot numbers/PCI bus numbers */
+ /* For CYC: No meaning */
+ unsigned char chassis_num; /* 1 based Chassis number */
+ /* For LookOut WPEGs this field indicates the */
+ /* Expansion Chassis #, enumerated from Boot */
+ /* Node WPEG external port, then Boot Node CYC */
+ /* external port, then Next Vigil chassis WPEG */
+ /* external port, etc. */
+ /* Shared Lookouts have only 1 chassis number (the */
+ /* first one assigned) */
+} __attribute__((packed));
+
+
+typedef enum {
+ CompatTwister = 0, /* Compatibility Twister */
+ AltTwister = 1, /* Alternate Twister of internal 8-way */
+ CompatCyclone = 2, /* Compatibility Cyclone */
+ AltCyclone = 3, /* Alternate Cyclone of internal 8-way */
+ CompatWPEG = 4, /* Compatibility WPEG */
+ AltWPEG = 5, /* Second Planar WPEG */
+ LookOutAWPEG = 6, /* LookOut WPEG */
+ LookOutBWPEG = 7, /* LookOut WPEG */
+} node_type;
+
+static inline int is_WPEG(struct rio_detail *rio){
+ return (rio->type == CompatWPEG || rio->type == AltWPEG ||
+ 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 inline const cpumask_t *summit_target_cpus(void)
+{
+ /* CPU_MASK_ALL (0xff) has undefined behaviour with
+ * dest_LowestPrio mode logical clustered apic interrupt routing
+ * Just start on cpu 0. IRQ balancing will spread load
+ */
+ return &cpumask_of_cpu(0);
+}
+
+static inline unsigned long
+summit_check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+ return 0;
+}
+
+/* we don't use the phys_cpu_present_map to indicate apicid presence */
+static inline unsigned long summit_check_apicid_present(int bit)
+{
+ return 1;
+}
+
+#define apicid_cluster(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK)
+
+extern u8 cpu_2_logical_apicid[];
+
+static inline void summit_init_apic_ldr(void)
+{
+ unsigned long val, id;
+ int count = 0;
+ u8 my_id = (u8)hard_smp_processor_id();
+ u8 my_cluster = (u8)apicid_cluster(my_id);
+#ifdef CONFIG_SMP
+ u8 lid;
+ int i;
+
+ /* Create logical APIC IDs by counting CPUs already in cluster. */
+ for (count = 0, i = nr_cpu_ids; --i >= 0; ) {
+ lid = cpu_2_logical_apicid[i];
+ if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster)
+ ++count;
+ }
+#endif
+ /* We only have a 4 wide bitmap in cluster mode. If a deranged
+ * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
+ BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
+ id = my_cluster | (1UL << count);
+ apic_write(APIC_DFR, SUMMIT_APIC_DFR_VALUE);
+ val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+ val |= SET_APIC_LOGICAL_ID(id);
+ apic_write(APIC_LDR, val);
+}
+
+static inline int summit_apic_id_registered(void)
+{
+ return 1;
+}
+
+static inline void summit_setup_apic_routing(void)
+{
+ printk("Enabling APIC mode: Summit. Using %d I/O APICs\n",
+ nr_ioapics);
+}
+
+static inline int summit_apicid_to_node(int logical_apicid)
+{
+#ifdef CONFIG_SMP
+ return apicid_2_node[hard_smp_processor_id()];
+#else
+ return 0;
+#endif
+}
+
+/* Mapping from cpu number to logical apicid */
+static inline int summit_cpu_to_logical_apicid(int cpu)
+{
+#ifdef CONFIG_SMP
+ if (cpu >= nr_cpu_ids)
+ return BAD_APICID;
+ return (int)cpu_2_logical_apicid[cpu];
+#else
+ return logical_smp_processor_id();
+#endif
+}
+
+static inline int summit_cpu_present_to_apicid(int mps_cpu)
+{
+ if (mps_cpu < nr_cpu_ids)
+ return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
+ else
+ return BAD_APICID;
+}
+
+static inline physid_mask_t
+summit_ioapic_phys_id_map(physid_mask_t phys_id_map)
+{
+ /* For clustered we don't have a good way to do this yet - hack */
+ return physids_promote(0x0F);
+}
+
+static inline physid_mask_t summit_apicid_to_cpu_present(int apicid)
+{
+ return physid_mask_of_physid(0);
+}
+
+static inline void summit_setup_portio_remap(void)
+{
+}
+
+static inline int summit_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+ return 1;
+}
+
+static inline unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask)
+{
+ int cpus_found = 0;
+ int num_bits_set;
+ int apicid;
+ int cpu;
+
+ num_bits_set = cpus_weight(*cpumask);
+ /* Return id to all */
+ if (num_bits_set >= nr_cpu_ids)
+ return 0xFF;
+ /*
+ * The cpus in the mask must all be on the apic cluster. If are not
+ * on the same apicid cluster return default value of target_cpus():
+ */
+ cpu = first_cpu(*cpumask);
+ apicid = summit_cpu_to_logical_apicid(cpu);
+
+ while (cpus_found < num_bits_set) {
+ if (cpu_isset(cpu, *cpumask)) {
+ int new_apicid = summit_cpu_to_logical_apicid(cpu);
+
+ if (apicid_cluster(apicid) !=
+ apicid_cluster(new_apicid)) {
+ printk ("%s: Not a valid mask!\n", __func__);
+
+ return 0xFF;
+ }
+ apicid = apicid | new_apicid;
+ cpus_found++;
+ }
+ cpu++;
+ }
+ return apicid;
+}
+
+static inline unsigned int
+summit_cpu_mask_to_apicid_and(const struct cpumask *inmask,
+ const struct cpumask *andmask)
+{
+ int apicid = summit_cpu_to_logical_apicid(0);
+ cpumask_var_t cpumask;
+
+ if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
+ return apicid;
+
+ cpumask_and(cpumask, inmask, andmask);
+ cpumask_and(cpumask, cpumask, cpu_online_mask);
+ apicid = summit_cpu_mask_to_apicid(cpumask);
+
+ free_cpumask_var(cpumask);
+
+ return apicid;
+}
+
+/*
+ * cpuid returns the value latched in the HW at reset, not the APIC ID
+ * register's value. For any box whose BIOS changes APIC IDs, like
+ * clustered APIC systems, we must use hard_smp_processor_id.
+ *
+ * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID.
+ */
+static inline int summit_phys_pkg_id(int cpuid_apic, int index_msb)
+{
+ return hard_smp_processor_id() >> index_msb;
+}
+
+static int probe_summit(void)
+{
+ /* probed later in mptable/ACPI hooks */
+ return 0;
+}
+
+static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask)
+{
+ /* Careful. Some cpus do not strictly honor the set of cpus
+ * specified in the interrupt destination when using lowest
+ * priority interrupt delivery mode.
+ *
+ * In particular there was a hyperthreading cpu observed to
+ * deliver interrupts to the wrong hyperthread when only one
+ * hyperthread was specified in the interrupt desitination.
+ */
+ *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+}
+
+#ifdef CONFIG_X86_SUMMIT_NUMA
static struct rio_table_hdr *rio_table_hdr __initdata;
static struct scal_detail *scal_devs[MAX_NUMNODES] __initdata;
static struct rio_detail *rio_devs[MAX_NUMNODES*4] __initdata;
@@ -186,3 +542,61 @@ void __init setup_summit(void)
next_wpeg = 0;
} while (next_wpeg != 0);
}
+#endif
+
+struct genapic apic_summit = {
+
+ .name = "summit",
+ .probe = probe_summit,
+ .acpi_madt_oem_check = summit_acpi_madt_oem_check,
+ .apic_id_registered = summit_apic_id_registered,
+
+ .irq_delivery_mode = dest_LowestPrio,
+ /* logical delivery broadcast to all CPUs: */
+ .irq_dest_mode = 1,
+
+ .target_cpus = summit_target_cpus,
+ .disable_esr = 1,
+ .dest_logical = APIC_DEST_LOGICAL,
+ .check_apicid_used = summit_check_apicid_used,
+ .check_apicid_present = summit_check_apicid_present,
+
+ .vector_allocation_domain = summit_vector_allocation_domain,
+ .init_apic_ldr = summit_init_apic_ldr,
+
+ .ioapic_phys_id_map = summit_ioapic_phys_id_map,
+ .setup_apic_routing = summit_setup_apic_routing,
+ .multi_timer_check = NULL,
+ .apicid_to_node = summit_apicid_to_node,
+ .cpu_to_logical_apicid = summit_cpu_to_logical_apicid,
+ .cpu_present_to_apicid = summit_cpu_present_to_apicid,
+ .apicid_to_cpu_present = summit_apicid_to_cpu_present,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = summit_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = summit_phys_pkg_id,
+ .mps_oem_check = summit_mps_oem_check,
+
+ .get_apic_id = summit_get_apic_id,
+ .set_apic_id = NULL,
+ .apic_id_mask = 0xFF << 24,
+
+ .cpu_mask_to_apicid = summit_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = summit_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = summit_send_IPI_mask,
+ .send_IPI_mask_allbutself = NULL,
+ .send_IPI_allbutself = summit_send_IPI_allbutself,
+ .send_IPI_all = summit_send_IPI_all,
+ .send_IPI_self = default_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+
+ .wait_for_init_deassert = default_wait_for_init_deassert,
+
+ .smp_callin_clear_local_apic = NULL,
+ .store_NMI_vector = NULL,
+ .inquire_remote_apic = default_inquire_remote_apic,
+};
diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c
index 3985cac0ed47..764c74e871f2 100644
--- a/arch/x86/kernel/time_32.c
+++ b/arch/x86/kernel/time_32.c
@@ -38,7 +38,7 @@
#include <asm/time.h>
#include <asm/timer.h>
-#include "do_timer.h"
+#include <asm/do_timer.h>
int timer_ack;
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
deleted file mode 100644
index ce5054642247..000000000000
--- a/arch/x86/kernel/tlb_32.c
+++ /dev/null
@@ -1,256 +0,0 @@
-#include <linux/spinlock.h>
-#include <linux/cpu.h>
-#include <linux/interrupt.h>
-
-#include <asm/tlbflush.h>
-
-DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate)
- ____cacheline_aligned = { &init_mm, 0, };
-
-/* must come after the send_IPI functions above for inlining */
-#include <mach_ipi.h>
-
-/*
- * Smarter SMP flushing macros.
- * c/o Linus Torvalds.
- *
- * These mean you can really definitely utterly forget about
- * writing to user space from interrupts. (Its not allowed anyway).
- *
- * Optimizations Manfred Spraul <manfred@colorfullife.com>
- */
-
-static cpumask_t flush_cpumask;
-static struct mm_struct *flush_mm;
-static unsigned long flush_va;
-static DEFINE_SPINLOCK(tlbstate_lock);
-
-/*
- * We cannot call mmdrop() because we are in interrupt context,
- * instead update mm->cpu_vm_mask.
- *
- * We need to reload %cr3 since the page tables may be going
- * away from under us..
- */
-void leave_mm(int cpu)
-{
- BUG_ON(x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK);
- cpu_clear(cpu, x86_read_percpu(cpu_tlbstate.active_mm)->cpu_vm_mask);
- load_cr3(swapper_pg_dir);
-}
-EXPORT_SYMBOL_GPL(leave_mm);
-
-/*
- *
- * The flush IPI assumes that a thread switch happens in this order:
- * [cpu0: the cpu that switches]
- * 1) switch_mm() either 1a) or 1b)
- * 1a) thread switch to a different mm
- * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
- * Stop ipi delivery for the old mm. This is not synchronized with
- * the other cpus, but smp_invalidate_interrupt ignore flush ipis
- * for the wrong mm, and in the worst case we perform a superfluous
- * tlb flush.
- * 1a2) set cpu_tlbstate to TLBSTATE_OK
- * Now the smp_invalidate_interrupt won't call leave_mm if cpu0
- * was in lazy tlb mode.
- * 1a3) update cpu_tlbstate[].active_mm
- * Now cpu0 accepts tlb flushes for the new mm.
- * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
- * Now the other cpus will send tlb flush ipis.
- * 1a4) change cr3.
- * 1b) thread switch without mm change
- * cpu_tlbstate[].active_mm is correct, cpu0 already handles
- * flush ipis.
- * 1b1) set cpu_tlbstate to TLBSTATE_OK
- * 1b2) test_and_set the cpu bit in cpu_vm_mask.
- * Atomically set the bit [other cpus will start sending flush ipis],
- * and test the bit.
- * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
- * 2) switch %%esp, ie current
- *
- * The interrupt must handle 2 special cases:
- * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
- * - the cpu performs speculative tlb reads, i.e. even if the cpu only
- * runs in kernel space, the cpu could load tlb entries for user space
- * pages.
- *
- * The good news is that cpu_tlbstate is local to each cpu, no
- * write/read ordering problems.
- */
-
-/*
- * TLB flush IPI:
- *
- * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
- * 2) Leave the mm if we are in the lazy tlb mode.
- */
-
-void smp_invalidate_interrupt(struct pt_regs *regs)
-{
- unsigned long cpu;
-
- cpu = get_cpu();
-
- if (!cpu_isset(cpu, flush_cpumask))
- goto out;
- /*
- * This was a BUG() but until someone can quote me the
- * line from the intel manual that guarantees an IPI to
- * multiple CPUs is retried _only_ on the erroring CPUs
- * its staying as a return
- *
- * BUG();
- */
-
- if (flush_mm == x86_read_percpu(cpu_tlbstate.active_mm)) {
- if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK) {
- if (flush_va == TLB_FLUSH_ALL)
- local_flush_tlb();
- else
- __flush_tlb_one(flush_va);
- } else
- leave_mm(cpu);
- }
- ack_APIC_irq();
- smp_mb__before_clear_bit();
- cpu_clear(cpu, flush_cpumask);
- smp_mb__after_clear_bit();
-out:
- put_cpu_no_resched();
- inc_irq_stat(irq_tlb_count);
-}
-
-void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
- unsigned long va)
-{
- cpumask_t cpumask = *cpumaskp;
-
- /*
- * A couple of (to be removed) sanity checks:
- *
- * - current CPU must not be in mask
- * - mask must exist :)
- */
- BUG_ON(cpus_empty(cpumask));
- BUG_ON(cpu_isset(smp_processor_id(), cpumask));
- BUG_ON(!mm);
-
-#ifdef CONFIG_HOTPLUG_CPU
- /* If a CPU which we ran on has gone down, OK. */
- cpus_and(cpumask, cpumask, cpu_online_map);
- if (unlikely(cpus_empty(cpumask)))
- return;
-#endif
-
- /*
- * i'm not happy about this global shared spinlock in the
- * MM hot path, but we'll see how contended it is.
- * AK: x86-64 has a faster method that could be ported.
- */
- spin_lock(&tlbstate_lock);
-
- flush_mm = mm;
- flush_va = va;
- cpus_or(flush_cpumask, cpumask, flush_cpumask);
-
- /*
- * Make the above memory operations globally visible before
- * sending the IPI.
- */
- smp_mb();
- /*
- * We have to send the IPI only to
- * CPUs affected.
- */
- send_IPI_mask(&cpumask, INVALIDATE_TLB_VECTOR);
-
- while (!cpus_empty(flush_cpumask))
- /* nothing. lockup detection does not belong here */
- cpu_relax();
-
- flush_mm = NULL;
- flush_va = 0;
- spin_unlock(&tlbstate_lock);
-}
-
-void flush_tlb_current_task(void)
-{
- struct mm_struct *mm = current->mm;
- cpumask_t cpu_mask;
-
- preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
-
- local_flush_tlb();
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
- preempt_enable();
-}
-
-void flush_tlb_mm(struct mm_struct *mm)
-{
- cpumask_t cpu_mask;
-
- preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
-
- if (current->active_mm == mm) {
- if (current->mm)
- local_flush_tlb();
- else
- leave_mm(smp_processor_id());
- }
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
-
- preempt_enable();
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
-{
- struct mm_struct *mm = vma->vm_mm;
- cpumask_t cpu_mask;
-
- preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
-
- if (current->active_mm == mm) {
- if (current->mm)
- __flush_tlb_one(va);
- else
- leave_mm(smp_processor_id());
- }
-
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, va);
-
- preempt_enable();
-}
-EXPORT_SYMBOL(flush_tlb_page);
-
-static void do_flush_tlb_all(void *info)
-{
- unsigned long cpu = smp_processor_id();
-
- __flush_tlb_all();
- if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_LAZY)
- leave_mm(cpu);
-}
-
-void flush_tlb_all(void)
-{
- on_each_cpu(do_flush_tlb_all, NULL, 1);
-}
-
-void reset_lazy_tlbstate(void)
-{
- int cpu = raw_smp_processor_id();
-
- per_cpu(cpu_tlbstate, cpu).state = 0;
- per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
-}
-
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c
deleted file mode 100644
index f8be6f1d2e48..000000000000
--- a/arch/x86/kernel/tlb_64.c
+++ /dev/null
@@ -1,284 +0,0 @@
-#include <linux/init.h>
-
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/kernel_stat.h>
-#include <linux/mc146818rtc.h>
-#include <linux/interrupt.h>
-
-#include <asm/mtrr.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
-#include <asm/proto.h>
-#include <asm/apicdef.h>
-#include <asm/idle.h>
-#include <asm/uv/uv_hub.h>
-#include <asm/uv/uv_bau.h>
-
-#include <mach_ipi.h>
-/*
- * Smarter SMP flushing macros.
- * c/o Linus Torvalds.
- *
- * These mean you can really definitely utterly forget about
- * writing to user space from interrupts. (Its not allowed anyway).
- *
- * Optimizations Manfred Spraul <manfred@colorfullife.com>
- *
- * More scalable flush, from Andi Kleen
- *
- * To avoid global state use 8 different call vectors.
- * Each CPU uses a specific vector to trigger flushes on other
- * CPUs. Depending on the received vector the target CPUs look into
- * the right per cpu variable for the flush data.
- *
- * With more than 8 CPUs they are hashed to the 8 available
- * vectors. The limited global vector space forces us to this right now.
- * In future when interrupts are split into per CPU domains this could be
- * fixed, at the cost of triggering multiple IPIs in some cases.
- */
-
-union smp_flush_state {
- struct {
- cpumask_t flush_cpumask;
- struct mm_struct *flush_mm;
- unsigned long flush_va;
- spinlock_t tlbstate_lock;
- };
- char pad[SMP_CACHE_BYTES];
-} ____cacheline_aligned;
-
-/* State is put into the per CPU data section, but padded
- to a full cache line because other CPUs can access it and we don't
- want false sharing in the per cpu data segment. */
-static DEFINE_PER_CPU(union smp_flush_state, flush_state);
-
-/*
- * We cannot call mmdrop() because we are in interrupt context,
- * instead update mm->cpu_vm_mask.
- */
-void leave_mm(int cpu)
-{
- if (read_pda(mmu_state) == TLBSTATE_OK)
- BUG();
- cpu_clear(cpu, read_pda(active_mm)->cpu_vm_mask);
- load_cr3(swapper_pg_dir);
-}
-EXPORT_SYMBOL_GPL(leave_mm);
-
-/*
- *
- * The flush IPI assumes that a thread switch happens in this order:
- * [cpu0: the cpu that switches]
- * 1) switch_mm() either 1a) or 1b)
- * 1a) thread switch to a different mm
- * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
- * Stop ipi delivery for the old mm. This is not synchronized with
- * the other cpus, but smp_invalidate_interrupt ignore flush ipis
- * for the wrong mm, and in the worst case we perform a superfluous
- * tlb flush.
- * 1a2) set cpu mmu_state to TLBSTATE_OK
- * Now the smp_invalidate_interrupt won't call leave_mm if cpu0
- * was in lazy tlb mode.
- * 1a3) update cpu active_mm
- * Now cpu0 accepts tlb flushes for the new mm.
- * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
- * Now the other cpus will send tlb flush ipis.
- * 1a4) change cr3.
- * 1b) thread switch without mm change
- * cpu active_mm is correct, cpu0 already handles
- * flush ipis.
- * 1b1) set cpu mmu_state to TLBSTATE_OK
- * 1b2) test_and_set the cpu bit in cpu_vm_mask.
- * Atomically set the bit [other cpus will start sending flush ipis],
- * and test the bit.
- * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
- * 2) switch %%esp, ie current
- *
- * The interrupt must handle 2 special cases:
- * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
- * - the cpu performs speculative tlb reads, i.e. even if the cpu only
- * runs in kernel space, the cpu could load tlb entries for user space
- * pages.
- *
- * The good news is that cpu mmu_state is local to each cpu, no
- * write/read ordering problems.
- */
-
-/*
- * TLB flush IPI:
- *
- * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
- * 2) Leave the mm if we are in the lazy tlb mode.
- *
- * Interrupts are disabled.
- */
-
-asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
-{
- int cpu;
- int sender;
- union smp_flush_state *f;
-
- cpu = smp_processor_id();
- /*
- * orig_rax contains the negated interrupt vector.
- * Use that to determine where the sender put the data.
- */
- sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START;
- f = &per_cpu(flush_state, sender);
-
- if (!cpu_isset(cpu, f->flush_cpumask))
- goto out;
- /*
- * This was a BUG() but until someone can quote me the
- * line from the intel manual that guarantees an IPI to
- * multiple CPUs is retried _only_ on the erroring CPUs
- * its staying as a return
- *
- * BUG();
- */
-
- if (f->flush_mm == read_pda(active_mm)) {
- if (read_pda(mmu_state) == TLBSTATE_OK) {
- if (f->flush_va == TLB_FLUSH_ALL)
- local_flush_tlb();
- else
- __flush_tlb_one(f->flush_va);
- } else
- leave_mm(cpu);
- }
-out:
- ack_APIC_irq();
- cpu_clear(cpu, f->flush_cpumask);
- inc_irq_stat(irq_tlb_count);
-}
-
-void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
- unsigned long va)
-{
- int sender;
- union smp_flush_state *f;
- cpumask_t cpumask = *cpumaskp;
-
- if (is_uv_system() && uv_flush_tlb_others(&cpumask, mm, va))
- return;
-
- /* Caller has disabled preemption */
- sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
- f = &per_cpu(flush_state, sender);
-
- /*
- * Could avoid this lock when
- * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
- * probably not worth checking this for a cache-hot lock.
- */
- spin_lock(&f->tlbstate_lock);
-
- f->flush_mm = mm;
- f->flush_va = va;
- cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask);
-
- /*
- * Make the above memory operations globally visible before
- * sending the IPI.
- */
- smp_mb();
- /*
- * We have to send the IPI only to
- * CPUs affected.
- */
- send_IPI_mask(&cpumask, INVALIDATE_TLB_VECTOR_START + sender);
-
- while (!cpus_empty(f->flush_cpumask))
- cpu_relax();
-
- f->flush_mm = NULL;
- f->flush_va = 0;
- spin_unlock(&f->tlbstate_lock);
-}
-
-static int __cpuinit init_smp_flush(void)
-{
- int i;
-
- for_each_possible_cpu(i)
- spin_lock_init(&per_cpu(flush_state, i).tlbstate_lock);
-
- return 0;
-}
-core_initcall(init_smp_flush);
-
-void flush_tlb_current_task(void)
-{
- struct mm_struct *mm = current->mm;
- cpumask_t cpu_mask;
-
- preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
-
- local_flush_tlb();
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
- preempt_enable();
-}
-
-void flush_tlb_mm(struct mm_struct *mm)
-{
- cpumask_t cpu_mask;
-
- preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
-
- if (current->active_mm == mm) {
- if (current->mm)
- local_flush_tlb();
- else
- leave_mm(smp_processor_id());
- }
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
-
- preempt_enable();
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
-{
- struct mm_struct *mm = vma->vm_mm;
- cpumask_t cpu_mask;
-
- preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
-
- if (current->active_mm == mm) {
- if (current->mm)
- __flush_tlb_one(va);
- else
- leave_mm(smp_processor_id());
- }
-
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, va);
-
- preempt_enable();
-}
-
-static void do_flush_tlb_all(void *info)
-{
- unsigned long cpu = smp_processor_id();
-
- __flush_tlb_all();
- if (read_pda(mmu_state) == TLBSTATE_LAZY)
- leave_mm(cpu);
-}
-
-void flush_tlb_all(void)
-{
- on_each_cpu(do_flush_tlb_all, NULL, 1);
-}
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 6812b829ed83..755ede02b13f 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <asm/mmu_context.h>
+#include <asm/uv/uv.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
#include <asm/uv/uv_bau.h>
@@ -19,7 +20,7 @@
#include <asm/tsc.h>
#include <asm/irq_vectors.h>
-#include <mach_apic.h>
+#include <asm/genapic.h>
static struct bau_control **uv_bau_table_bases __read_mostly;
static int uv_bau_retry_limit __read_mostly;
@@ -210,14 +211,15 @@ static int uv_wait_completion(struct bau_desc *bau_desc,
*
* Send a broadcast and wait for a broadcast message to complete.
*
- * The cpumaskp mask contains the cpus the broadcast was sent to.
+ * The flush_mask contains the cpus the broadcast was sent to.
*
- * Returns 1 if all remote flushing was done. The mask is zeroed.
- * Returns 0 if some remote flushing remains to be done. The mask is left
- * unchanged.
+ * Returns NULL if all remote flushing was done. The mask is zeroed.
+ * Returns @flush_mask if some remote flushing remains to be done. The
+ * mask will have some bits still set.
*/
-int uv_flush_send_and_wait(int cpu, int this_blade, struct bau_desc *bau_desc,
- cpumask_t *cpumaskp)
+const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
+ struct bau_desc *bau_desc,
+ struct cpumask *flush_mask)
{
int completion_status = 0;
int right_shift;
@@ -264,59 +266,69 @@ int uv_flush_send_and_wait(int cpu, int this_blade, struct bau_desc *bau_desc,
* Success, so clear the remote cpu's from the mask so we don't
* use the IPI method of shootdown on them.
*/
- for_each_cpu_mask(bit, *cpumaskp) {
+ for_each_cpu(bit, flush_mask) {
blade = uv_cpu_to_blade_id(bit);
if (blade == this_blade)
continue;
- cpu_clear(bit, *cpumaskp);
+ cpumask_clear_cpu(bit, flush_mask);
}
- if (!cpus_empty(*cpumaskp))
- return 0;
- return 1;
+ if (!cpumask_empty(flush_mask))
+ return flush_mask;
+ return NULL;
}
/**
* uv_flush_tlb_others - globally purge translation cache of a virtual
* address or all TLB's
- * @cpumaskp: mask of all cpu's in which the address is to be removed
+ * @cpumask: mask of all cpu's in which the address is to be removed
* @mm: mm_struct containing virtual address range
* @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu)
+ * @cpu: the current cpu
*
* This is the entry point for initiating any UV global TLB shootdown.
*
* Purges the translation caches of all specified processors of the given
* virtual address, or purges all TLB's on specified processors.
*
- * The caller has derived the cpumaskp from the mm_struct and has subtracted
- * the local cpu from the mask. This function is called only if there
- * are bits set in the mask. (e.g. flush_tlb_page())
+ * The caller has derived the cpumask from the mm_struct. This function
+ * is called only if there are bits set in the mask. (e.g. flush_tlb_page())
*
- * The cpumaskp is converted into a nodemask of the nodes containing
+ * The cpumask is converted into a nodemask of the nodes containing
* the cpus.
*
- * Returns 1 if all remote flushing was done.
- * Returns 0 if some remote flushing remains to be done.
+ * Note that this function should be called with preemption disabled.
+ *
+ * Returns NULL if all remote flushing was done.
+ * Returns pointer to cpumask if some remote flushing remains to be
+ * done. The returned pointer is valid till preemption is re-enabled.
*/
-int uv_flush_tlb_others(cpumask_t *cpumaskp, struct mm_struct *mm,
- unsigned long va)
+const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
+ struct mm_struct *mm,
+ unsigned long va, unsigned int cpu)
{
+ static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
+ struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask);
int i;
int bit;
int blade;
- int cpu;
+ int uv_cpu;
int this_blade;
int locals = 0;
struct bau_desc *bau_desc;
- cpu = uv_blade_processor_id();
+ WARN_ON(!in_atomic());
+
+ cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu));
+
+ uv_cpu = uv_blade_processor_id();
this_blade = uv_numa_blade_id();
bau_desc = __get_cpu_var(bau_control).descriptor_base;
- bau_desc += UV_ITEMS_PER_DESCRIPTOR * cpu;
+ bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu;
bau_nodes_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
i = 0;
- for_each_cpu_mask(bit, *cpumaskp) {
+ for_each_cpu(bit, flush_mask) {
blade = uv_cpu_to_blade_id(bit);
BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1));
if (blade == this_blade) {
@@ -331,17 +343,17 @@ int uv_flush_tlb_others(cpumask_t *cpumaskp, struct mm_struct *mm,
* no off_node flushing; return status for local node
*/
if (locals)
- return 0;
+ return flush_mask;
else
- return 1;
+ return NULL;
}
__get_cpu_var(ptcstats).requestor++;
__get_cpu_var(ptcstats).ntargeted += i;
bau_desc->payload.address = va;
- bau_desc->payload.sending_cpu = smp_processor_id();
+ bau_desc->payload.sending_cpu = cpu;
- return uv_flush_send_and_wait(cpu, this_blade, bau_desc, cpumaskp);
+ return uv_flush_send_and_wait(uv_cpu, this_blade, bau_desc, flush_mask);
}
/*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 98c2d055284b..214bc327a0c3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -54,12 +54,11 @@
#include <asm/desc.h>
#include <asm/i387.h>
-#include <mach_traps.h>
+#include <asm/mach_traps.h>
#ifdef CONFIG_X86_64
#include <asm/pgalloc.h>
#include <asm/proto.h>
-#include <asm/pda.h>
#else
#include <asm/processor-flags.h>
#include <asm/arch_hooks.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 599e58168631..83d53ce5d4c4 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -773,7 +773,7 @@ __cpuinit int unsynchronized_tsc(void)
if (!cpu_has_tsc || tsc_unstable)
return 1;
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
if (apic_is_clustered_box())
return 1;
#endif
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index d801d06af068..4fd646e6dd43 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -32,9 +32,9 @@
#include <asm/e820.h>
#include <asm/io.h>
-#include <mach_ipi.h>
+#include <asm/genapic.h>
-#include "mach_apic.h"
+#include <asm/genapic.h>
#include <linux/kernel_stat.h>
@@ -200,7 +200,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
return;
}
- apic_cpus = apicid_to_cpu_present(m->apicid);
+ apic_cpus = apic->apicid_to_cpu_present(m->apicid);
physids_or(phys_cpu_present_map, phys_cpu_present_map, apic_cpus);
/*
* Validate version
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index c4c1f9e09402..a4791ef412d1 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -256,7 +256,7 @@ void __devinit vmi_time_bsp_init(void)
*/
clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
local_irq_disable();
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
/*
* XXX handle_percpu_irq only defined for SMP; we need to switch over
* to using it, since this is a local interrupt, which each CPU must
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index 82c67559dde7..3eba7f7bac05 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -178,14 +178,7 @@ SECTIONS
__initramfs_end = .;
}
#endif
- . = ALIGN(PAGE_SIZE);
- .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
- __per_cpu_start = .;
- *(.data.percpu.page_aligned)
- *(.data.percpu)
- *(.data.percpu.shared_aligned)
- __per_cpu_end = .;
- }
+ PERCPU(PAGE_SIZE)
. = ALIGN(PAGE_SIZE);
/* freed after init ends here */
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 1a614c0e6bef..c9740996430a 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -5,6 +5,7 @@
#define LOAD_OFFSET __START_KERNEL_map
#include <asm-generic/vmlinux.lds.h>
+#include <asm/asm-offsets.h>
#include <asm/page.h>
#undef i386 /* in case the preprocessor is a 32bit one */
@@ -13,12 +14,14 @@ OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
OUTPUT_ARCH(i386:x86-64)
ENTRY(phys_startup_64)
jiffies_64 = jiffies;
-_proxy_pda = 1;
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
note PT_NOTE FLAGS(0); /* ___ */
}
SECTIONS
@@ -208,14 +211,28 @@ SECTIONS
__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
+ * switch it back to data.init. 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 = .;
. = ALIGN(PAGE_SIZE);
__nosave_begin = .;
- .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) { *(.data.nosave) }
+ .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+ *(.data.nosave)
+ } :data.init /* switch back to data.init, see PERCPU_VADDR() above */
. = ALIGN(PAGE_SIZE);
__nosave_end = .;
@@ -244,3 +261,8 @@ SECTIONS
*/
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
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 695e426aa354..3909e3ba5ce3 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -58,5 +58,3 @@ EXPORT_SYMBOL(__memcpy);
EXPORT_SYMBOL(empty_zero_page);
EXPORT_SYMBOL(init_level4_pgt);
EXPORT_SYMBOL(load_gs_index);
-
-EXPORT_SYMBOL(_proxy_pda);