summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile1
-rw-r--r--arch/x86/kernel/acpi/boot.c11
-rw-r--r--arch/x86/kernel/alternative.c52
-rw-r--r--arch/x86/kernel/apic/Makefile5
-rw-r--r--arch/x86/kernel/apic/apic.c40
-rw-r--r--arch/x86/kernel/apic/hw_nmi.c41
-rw-r--r--arch/x86/kernel/apic/io_apic.c53
-rw-r--r--arch/x86/kernel/apic/nmi.c567
-rw-r--r--arch/x86/kernel/apic/probe_64.c7
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c76
-rw-r--r--arch/x86/kernel/cpu/common.c1
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c135
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c40
-rw-r--r--arch/x86/kernel/cpu/perf_event.c80
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c16
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c26
-rw-r--r--arch/x86/kernel/cpu/perfctr-watchdog.c644
-rw-r--r--arch/x86/kernel/cpuid.c1
-rw-r--r--arch/x86/kernel/dumpstack.c12
-rw-r--r--arch/x86/kernel/dumpstack_32.c25
-rw-r--r--arch/x86/kernel/dumpstack_64.c24
-rw-r--r--arch/x86/kernel/entry_32.S2
-rw-r--r--arch/x86/kernel/entry_64.S2
-rw-r--r--arch/x86/kernel/ftrace.c3
-rw-r--r--arch/x86/kernel/head_32.S91
-rw-r--r--arch/x86/kernel/hpet.c26
-rw-r--r--arch/x86/kernel/hw_breakpoint.c4
-rw-r--r--arch/x86/kernel/kgdb.c12
-rw-r--r--arch/x86/kernel/kprobes.c113
-rw-r--r--arch/x86/kernel/microcode_amd.c34
-rw-r--r--arch/x86/kernel/microcode_intel.c16
-rw-r--r--arch/x86/kernel/mmconf-fam10h_64.c64
-rw-r--r--arch/x86/kernel/msr.c1
-rw-r--r--arch/x86/kernel/process.c10
-rw-r--r--arch/x86/kernel/process_32.c2
-rw-r--r--arch/x86/kernel/process_64.c2
-rw-r--r--arch/x86/kernel/pvclock.c5
-rw-r--r--arch/x86/kernel/resource.c48
-rw-r--r--arch/x86/kernel/setup.c18
-rw-r--r--arch/x86/kernel/smpboot.c36
-rw-r--r--arch/x86/kernel/stacktrace.c8
-rw-r--r--arch/x86/kernel/time.c18
-rw-r--r--arch/x86/kernel/trampoline_64.S2
-rw-r--r--arch/x86/kernel/traps.c35
-rw-r--r--arch/x86/kernel/tsc.c96
-rw-r--r--arch/x86/kernel/verify_cpu.S (renamed from arch/x86/kernel/verify_cpu_64.S)49
-rw-r--r--arch/x86/kernel/vmlinux.lds.S8
-rw-r--r--arch/x86/kernel/xsave.c3
48 files changed, 872 insertions, 1693 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f60153d..34244b2 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -45,6 +45,7 @@ obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
obj-y += tsc.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
+obj-y += resource.o
obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o
obj-y += process.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 1a5b9a8..ec881c6 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -198,6 +198,11 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled)
{
unsigned int ver = 0;
+ if (id >= (MAX_LOCAL_APIC-1)) {
+ printk(KERN_INFO PREFIX "skipped apicid that is too big\n");
+ return;
+ }
+
if (!enabled) {
++disabled_cpus;
return;
@@ -898,13 +903,13 @@ static int __init acpi_parse_madt_lapic_entries(void)
register_lapic_address(acpi_lapic_addr);
count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
- acpi_parse_sapic, MAX_APICS);
+ acpi_parse_sapic, MAX_LOCAL_APIC);
if (!count) {
x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
- acpi_parse_x2apic, MAX_APICS);
+ acpi_parse_x2apic, MAX_LOCAL_APIC);
count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
- acpi_parse_lapic, MAX_APICS);
+ acpi_parse_lapic, MAX_LOCAL_APIC);
}
if (!count && !x2count) {
printk(KERN_ERR PREFIX "No LAPIC entries present\n");
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 5079f24..1236085 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -353,6 +353,7 @@ void __init_or_module alternatives_smp_module_del(struct module *mod)
mutex_unlock(&smp_alt);
}
+bool skip_smp_alternatives;
void alternatives_smp_switch(int smp)
{
struct smp_alt_module *mod;
@@ -368,7 +369,7 @@ void alternatives_smp_switch(int smp)
printk("lockdep: fixing up alternatives.\n");
#endif
- if (noreplace_smp || smp_alt_once)
+ if (noreplace_smp || smp_alt_once || skip_smp_alternatives)
return;
BUG_ON(!smp && (num_online_cpus() > 1));
@@ -591,17 +592,21 @@ static atomic_t stop_machine_first;
static int wrote_text;
struct text_poke_params {
- void *addr;
- const void *opcode;
- size_t len;
+ struct text_poke_param *params;
+ int nparams;
};
static int __kprobes stop_machine_text_poke(void *data)
{
struct text_poke_params *tpp = data;
+ struct text_poke_param *p;
+ int i;
if (atomic_dec_and_test(&stop_machine_first)) {
- text_poke(tpp->addr, tpp->opcode, tpp->len);
+ for (i = 0; i < tpp->nparams; i++) {
+ p = &tpp->params[i];
+ text_poke(p->addr, p->opcode, p->len);
+ }
smp_wmb(); /* Make sure other cpus see that this has run */
wrote_text = 1;
} else {
@@ -610,8 +615,12 @@ static int __kprobes stop_machine_text_poke(void *data)
smp_mb(); /* Load wrote_text before following execution */
}
- flush_icache_range((unsigned long)tpp->addr,
- (unsigned long)tpp->addr + tpp->len);
+ for (i = 0; i < tpp->nparams; i++) {
+ p = &tpp->params[i];
+ flush_icache_range((unsigned long)p->addr,
+ (unsigned long)p->addr + p->len);
+ }
+
return 0;
}
@@ -631,10 +640,13 @@ static int __kprobes stop_machine_text_poke(void *data)
void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
{
struct text_poke_params tpp;
+ struct text_poke_param p;
- tpp.addr = addr;
- tpp.opcode = opcode;
- tpp.len = len;
+ p.addr = addr;
+ p.opcode = opcode;
+ p.len = len;
+ tpp.params = &p;
+ tpp.nparams = 1;
atomic_set(&stop_machine_first, 1);
wrote_text = 0;
/* Use __stop_machine() because the caller already got online_cpus. */
@@ -642,6 +654,26 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
return addr;
}
+/**
+ * text_poke_smp_batch - Update instructions on a live kernel on SMP
+ * @params: an array of text_poke parameters
+ * @n: the number of elements in params.
+ *
+ * Modify multi-byte instruction by using stop_machine() on SMP. Since the
+ * stop_machine() is heavy task, it is better to aggregate text_poke requests
+ * and do it once if possible.
+ *
+ * Note: Must be called under get_online_cpus() and text_mutex.
+ */
+void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
+{
+ struct text_poke_params tpp = {.params = params, .nparams = n};
+
+ atomic_set(&stop_machine_first, 1);
+ wrote_text = 0;
+ stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+}
+
#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 910f20b4..3966b56 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -3,10 +3,7 @@
#
obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o
-ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y)
-obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o
-endif
-obj-$(CONFIG_HARDLOCKUP_DETECTOR) += hw_nmi.o
+obj-y += hw_nmi.o
obj-$(CONFIG_X86_IO_APIC) += io_apic.o
obj-$(CONFIG_SMP) += ipi.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index c0f6426..ce65d44 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -31,7 +31,6 @@
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/dmi.h>
-#include <linux/nmi.h>
#include <linux/smp.h>
#include <linux/mm.h>
@@ -432,17 +431,18 @@ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
reserved = reserve_eilvt_offset(offset, new);
if (reserved != new) {
- pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but "
- "vector 0x%x was already reserved by another core, "
- "APIC%lX=0x%x\n",
- smp_processor_id(), new, reserved, reg, old);
+ pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+ "vector 0x%x, but the register is already in use for "
+ "vector 0x%x on another cpu\n",
+ smp_processor_id(), reg, offset, new, reserved);
return -EINVAL;
}
if (!eilvt_entry_is_changeable(old, new)) {
- pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but "
- "register already in use, APIC%lX=0x%x\n",
- smp_processor_id(), new, reg, old);
+ pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+ "vector 0x%x, but the register is already in use for "
+ "vector 0x%x on this cpu\n",
+ smp_processor_id(), reg, offset, new, old);
return -EBUSY;
}
@@ -799,11 +799,7 @@ void __init setup_boot_APIC_clock(void)
* PIT/HPET going. Otherwise register lapic as a dummy
* device.
*/
- if (nmi_watchdog != NMI_IO_APIC)
- lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
- else
- pr_warning("APIC timer registered as dummy,"
- " due to nmi_watchdog=%d!\n", nmi_watchdog);
+ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
/* Setup the lapic or request the broadcast */
setup_APIC_timer();
@@ -1384,8 +1380,15 @@ void __cpuinit end_local_APIC_setup(void)
}
#endif
- setup_apic_nmi_watchdog(NULL);
apic_pm_activate();
+
+ /*
+ * Now that local APIC setup is completed for BP, configure the fault
+ * handling for interrupt remapping.
+ */
+ if (!smp_processor_id() && intr_remapping_enabled)
+ enable_drhd_fault_handling();
+
}
#ifdef CONFIG_X86_X2APIC
@@ -1694,7 +1697,7 @@ void __init register_lapic_address(unsigned long address)
* This initializes the IO-APIC and APIC hardware if this is
* a UP kernel.
*/
-int apic_version[MAX_APICS];
+int apic_version[MAX_LOCAL_APIC];
int __init APIC_init_uniprocessor(void)
{
@@ -1759,17 +1762,10 @@ int __init APIC_init_uniprocessor(void)
setup_IO_APIC();
else {
nr_ioapics = 0;
- localise_nmi_watchdog();
}
-#else
- localise_nmi_watchdog();
#endif
x86_init.timers.setup_percpu_clockev();
-#ifdef CONFIG_X86_64
- check_nmi_watchdog();
-#endif
-
return 0;
}
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index cefd694..72ec29e 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -17,19 +17,31 @@
#include <linux/nmi.h>
#include <linux/module.h>
-/* For reliability, we're prepared to waste bits here. */
-static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
u64 hw_nmi_get_sample_period(void)
{
return (u64)(cpu_khz) * 1000 * 60;
}
+#endif
+
+#ifdef arch_trigger_all_cpu_backtrace
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+
+/* "in progress" flag of arch_trigger_all_cpu_backtrace */
+static unsigned long backtrace_flag;
-#ifdef ARCH_HAS_NMI_WATCHDOG
void arch_trigger_all_cpu_backtrace(void)
{
int i;
+ if (test_and_set_bit(0, &backtrace_flag))
+ /*
+ * If there is already a trigger_all_cpu_backtrace() in progress
+ * (backtrace_flag == 1), don't output double cpu dump infos.
+ */
+ return;
+
cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
printk(KERN_INFO "sending NMI to all CPUs:\n");
@@ -41,6 +53,9 @@ void arch_trigger_all_cpu_backtrace(void)
break;
mdelay(1);
}
+
+ clear_bit(0, &backtrace_flag);
+ smp_mb__after_clear_bit();
}
static int __kprobes
@@ -49,7 +64,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
{
struct die_args *args = __args;
struct pt_regs *regs;
- int cpu = smp_processor_id();
+ int cpu;
switch (cmd) {
case DIE_NMI:
@@ -61,6 +76,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
}
regs = args->regs;
+ cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
@@ -90,18 +106,3 @@ static int __init register_trigger_all_cpu_backtrace(void)
}
early_initcall(register_trigger_all_cpu_backtrace);
#endif
-
-/* STUB calls to mimic old nmi_watchdog behaviour */
-#if defined(CONFIG_X86_LOCAL_APIC)
-unsigned int nmi_watchdog = NMI_NONE;
-EXPORT_SYMBOL(nmi_watchdog);
-void acpi_nmi_enable(void) { return; }
-void acpi_nmi_disable(void) { return; }
-#endif
-atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */
-EXPORT_SYMBOL(nmi_active);
-int unknown_nmi_panic;
-void cpu_nmi_set_wd_enabled(void) { return; }
-void stop_apic_nmi_watchdog(void *unused) { return; }
-void setup_apic_nmi_watchdog(void *unused) { return; }
-int __init check_nmi_watchdog(void) { return 0; }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index bb61a55..52735a7 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -54,7 +54,6 @@
#include <asm/dma.h>
#include <asm/timer.h>
#include <asm/i8259.h>
-#include <asm/nmi.h>
#include <asm/msidef.h>
#include <asm/hypertransport.h>
#include <asm/setup.h>
@@ -2458,13 +2457,12 @@ static void ack_apic_level(struct irq_data *data)
{
struct irq_cfg *cfg = data->chip_data;
int i, do_unmask_irq = 0, irq = data->irq;
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long v;
irq_complete_move(cfg);
#ifdef CONFIG_GENERIC_PENDING_IRQ
/* If we are moving the irq we need to mask it */
- if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
+ if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
do_unmask_irq = 1;
mask_ioapic(cfg);
}
@@ -2671,24 +2669,6 @@ static void lapic_register_intr(int irq)
"edge");
}
-static void __init setup_nmi(void)
-{
- /*
- * Dirty trick to enable the NMI watchdog ...
- * We put the 8259A master into AEOI mode and
- * unmask on all local APICs LVT0 as NMI.
- *
- * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
- * is from Maciej W. Rozycki - so we do not have to EOI from
- * the NMI handler or the timer interrupt.
- */
- apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
-
- enable_NMI_through_LVT0();
-
- apic_printk(APIC_VERBOSE, " done.\n");
-}
-
/*
* This looks a bit hackish but it's about the only one way of sending
* a few INTA cycles to 8259As and any associated glue logic. ICR does
@@ -2794,15 +2774,6 @@ static inline void __init check_timer(void)
*/
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
legacy_pic->init(1);
-#ifdef CONFIG_X86_32
- {
- unsigned int ver;
-
- ver = apic_read(APIC_LVR);
- ver = GET_APIC_VERSION(ver);
- timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
- }
-#endif
pin1 = find_isa_irq_pin(0, mp_INT);
apic1 = find_isa_irq_apic(0, mp_INT);
@@ -2850,10 +2821,6 @@ static inline void __init check_timer(void)
unmask_ioapic(cfg);
}
if (timer_irq_works()) {
- if (nmi_watchdog == NMI_IO_APIC) {
- setup_nmi();
- legacy_pic->unmask(0);
- }
if (disable_timer_pin_1 > 0)
clear_IO_APIC_pin(0, pin1);
goto out;
@@ -2879,11 +2846,6 @@ static inline void __init check_timer(void)
if (timer_irq_works()) {
apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
timer_through_8259 = 1;
- if (nmi_watchdog == NMI_IO_APIC) {
- legacy_pic->mask(0);
- setup_nmi();
- legacy_pic->unmask(0);
- }
goto out;
}
/*
@@ -2895,15 +2857,6 @@ static inline void __init check_timer(void)
apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
}
- if (nmi_watchdog == NMI_IO_APIC) {
- apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work "
- "through the IO-APIC - disabling NMI Watchdog!\n");
- nmi_watchdog = NMI_NONE;
- }
-#ifdef CONFIG_X86_32
- timer_ack = 0;
-#endif
-
apic_printk(APIC_QUIET, KERN_INFO
"...trying to set up timer as Virtual Wire IRQ...\n");
@@ -3441,6 +3394,7 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
msg.data |= MSI_DATA_VECTOR(cfg->vector);
msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+ msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
dmar_msi_write(irq, &msg);
@@ -4133,7 +4087,8 @@ void __init pre_init_apic_IRQ0(void)
printk(KERN_INFO "Early APIC setup for system timer0\n");
#ifndef CONFIG_SMP
- phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
+ physid_set_mask_of_physid(boot_cpu_physical_apicid,
+ &phys_cpu_present_map);
#endif
/* Make sure the irq descriptor is set up */
cfg = alloc_irq_and_cfg_at(0, 0);
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
deleted file mode 100644
index c90041c..0000000
--- a/arch/x86/kernel/apic/nmi.c
+++ /dev/null
@@ -1,567 +0,0 @@
-/*
- * NMI watchdog support on APIC systems
- *
- * Started by Ingo Molnar <mingo@redhat.com>
- *
- * Fixes:
- * Mikael Pettersson : AMD K7 support for local APIC NMI watchdog.
- * Mikael Pettersson : Power Management for local APIC NMI watchdog.
- * Mikael Pettersson : Pentium 4 support for local APIC NMI watchdog.
- * Pavel Machek and
- * Mikael Pettersson : PM converted to driver model. Disable/enable API.
- */
-
-#include <asm/apic.h>
-
-#include <linux/nmi.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/sysdev.h>
-#include <linux/sysctl.h>
-#include <linux/percpu.h>
-#include <linux/kprobes.h>
-#include <linux/cpumask.h>
-#include <linux/kernel_stat.h>
-#include <linux/kdebug.h>
-#include <linux/smp.h>
-
-#include <asm/i8259.h>
-#include <asm/io_apic.h>
-#include <asm/proto.h>
-#include <asm/timer.h>
-
-#include <asm/mce.h>
-
-#include <asm/mach_traps.h>
-
-int unknown_nmi_panic;
-int nmi_watchdog_enabled;
-
-/* For reliability, we're prepared to waste bits here. */
-static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-
-/* nmi_active:
- * >0: the lapic NMI watchdog is active, but can be disabled
- * <0: the lapic NMI watchdog has not been set up, and cannot
- * be enabled
- * 0: the lapic NMI watchdog is disabled, but can be enabled
- */
-atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */
-EXPORT_SYMBOL(nmi_active);
-
-unsigned int nmi_watchdog = NMI_NONE;
-EXPORT_SYMBOL(nmi_watchdog);
-
-static int panic_on_timeout;
-
-static unsigned int nmi_hz = HZ;
-static DEFINE_PER_CPU(short, wd_enabled);
-static int endflag __initdata;
-
-static inline unsigned int get_nmi_count(int cpu)
-{
- return per_cpu(irq_stat, cpu).__nmi_count;
-}
-
-static inline int mce_in_progress(void)
-{
-#if defined(CONFIG_X86_MCE)
- return atomic_read(&mce_entry) > 0;
-#endif
- return 0;
-}
-
-/*
- * Take the local apic timer and PIT/HPET into account. We don't
- * know which one is active, when we have highres/dyntick on
- */
-static inline unsigned int get_timer_irqs(int cpu)
-{
- return per_cpu(irq_stat, cpu).apic_timer_irqs +
- per_cpu(irq_stat, cpu).irq0_irqs;
-}
-
-#ifdef CONFIG_SMP
-/*
- * The performance counters used by NMI_LOCAL_APIC don't trigger when
- * the CPU is idle. To make sure the NMI watchdog really ticks on all
- * CPUs during the test make them busy.
- */
-static __init void nmi_cpu_busy(void *data)
-{
- local_irq_enable_in_hardirq();
- /*
- * Intentionally don't use cpu_relax here. This is
- * to make sure that the performance counter really ticks,
- * even if there is a simulator or similar that catches the
- * pause instruction. On a real HT machine this is fine because
- * all other CPUs are busy with "useless" delay loops and don't
- * care if they get somewhat less cycles.
- */
- while (endflag == 0)
- mb();
-}
-#endif
-
-static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count)
-{
- printk(KERN_CONT "\n");
-
- printk(KERN_WARNING
- "WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n",
- cpu, prev_nmi_count[cpu], get_nmi_count(cpu));
-
- printk(KERN_WARNING
- "Please report this to bugzilla.kernel.org,\n");
- printk(KERN_WARNING
- "and attach the output of the 'dmesg' command.\n");
-
- per_cpu(wd_enabled, cpu) = 0;
- atomic_dec(&nmi_active);
-}
-
-static void __acpi_nmi_disable(void *__unused)
-{
- apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
-}
-
-int __init check_nmi_watchdog(void)
-{
- unsigned int *prev_nmi_count;
- int cpu;
-
- if (!nmi_watchdog_active() || !atomic_read(&nmi_active))
- return 0;
-
- prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL);
- if (!prev_nmi_count)
- goto error;
-
- printk(KERN_INFO "Testing NMI watchdog ... ");
-
-#ifdef CONFIG_SMP
- if (nmi_watchdog == NMI_LOCAL_APIC)
- smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
-#endif
-
- for_each_possible_cpu(cpu)
- prev_nmi_count[cpu] = get_nmi_count(cpu);
- local_irq_enable();
- mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */
-
- for_each_online_cpu(cpu) {
- if (!per_cpu(wd_enabled, cpu))
- continue;
- if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5)
- report_broken_nmi(cpu, prev_nmi_count);
- }
- endflag = 1;
- if (!atomic_read(&nmi_active)) {
- kfree(prev_nmi_count);
- atomic_set(&nmi_active, -1);
- goto error;
- }
- printk("OK.\n");
-
- /*
- * now that we know it works we can reduce NMI frequency to
- * something more reasonable; makes a difference in some configs
- */
- if (nmi_watchdog == NMI_LOCAL_APIC)
- nmi_hz = lapic_adjust_nmi_hz(1);
-
- kfree(prev_nmi_count);
- return 0;
-error:
- if (nmi_watchdog == NMI_IO_APIC) {
- if (!timer_through_8259)
- legacy_pic->mask(0);
- on_each_cpu(__acpi_nmi_disable, NULL, 1);
- }
-
-#ifdef CONFIG_X86_32
- timer_ack = 0;
-#endif
- return -1;
-}
-
-static int __init setup_nmi_watchdog(char *str)
-{
- unsigned int nmi;
-
- if (!strncmp(str, "panic", 5)) {
- panic_on_timeout = 1;
- str = strchr(str, ',');
- if (!str)
- return 1;
- ++str;
- }
-
- if (!strncmp(str, "lapic", 5))
- nmi_watchdog = NMI_LOCAL_APIC;
- else if (!strncmp(str, "ioapic", 6))
- nmi_watchdog = NMI_IO_APIC;
- else {
- get_option(&str, &nmi);
- if (nmi >= NMI_INVALID)
- return 0;
- nmi_watchdog = nmi;
- }
-
- return 1;
-}
-__setup("nmi_watchdog=", setup_nmi_watchdog);
-
-/*
- * Suspend/resume support
- */
-#ifdef CONFIG_PM
-
-static int nmi_pm_active; /* nmi_active before suspend */
-
-static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
-{
- /* only CPU0 goes here, other CPUs should be offline */
- nmi_pm_active = atomic_read(&nmi_active);
- stop_apic_nmi_watchdog(NULL);
- BUG_ON(atomic_read(&nmi_active) != 0);
- return 0;
-}
-
-static int lapic_nmi_resume(struct sys_device *dev)
-{
- /* only CPU0 goes here, other CPUs should be offline */
- if (nmi_pm_active > 0) {
- setup_apic_nmi_watchdog(NULL);
- touch_nmi_watchdog();
- }
- return 0;
-}
-
-static struct sysdev_class nmi_sysclass = {
- .name = "lapic_nmi",
- .resume = lapic_nmi_resume,
- .suspend = lapic_nmi_suspend,
-};
-
-static struct sys_device device_lapic_nmi = {
- .id = 0,
- .cls = &nmi_sysclass,
-};
-
-static int __init init_lapic_nmi_sysfs(void)
-{
- int error;
-
- /*
- * should really be a BUG_ON but b/c this is an
- * init call, it just doesn't work. -dcz
- */
- if (nmi_watchdog != NMI_LOCAL_APIC)
- return 0;
-
- if (atomic_read(&nmi_active) < 0)
- return 0;
-
- error = sysdev_class_register(&nmi_sysclass);
- if (!error)
- error = sysdev_register(&device_lapic_nmi);
- return error;
-}
-
-/* must come after the local APIC's device_initcall() */
-late_initcall(init_lapic_nmi_sysfs);
-
-#endif /* CONFIG_PM */
-
-static void __acpi_nmi_enable(void *__unused)
-{
- apic_write(APIC_LVT0, APIC_DM_NMI);
-}
-
-/*
- * Enable timer based NMIs on all CPUs:
- */
-void acpi_nmi_enable(void)
-{
- if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
- on_each_cpu(__acpi_nmi_enable, NULL, 1);
-}
-
-/*
- * Disable timer based NMIs on all CPUs:
- */
-void acpi_nmi_disable(void)
-{
- if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
- on_each_cpu(__acpi_nmi_disable, NULL, 1);
-}
-
-/*
- * This function is called as soon the LAPIC NMI watchdog driver has everything
- * in place and it's ready to check if the NMIs belong to the NMI watchdog
- */
-void cpu_nmi_set_wd_enabled(void)
-{
- __get_cpu_var(wd_enabled) = 1;
-}
-
-void setup_apic_nmi_watchdog(void *unused)
-{
- if (__get_cpu_var(wd_enabled))
- return;
-
- /* cheap hack to support suspend/resume */
- /* if cpu0 is not active neither should the other cpus */
- if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0)
- return;
-
- switch (nmi_watchdog) {
- case NMI_LOCAL_APIC:
- if (lapic_watchdog_init(nmi_hz) < 0) {
- __get_cpu_var(wd_enabled) = 0;
- return;
- }
- /* FALL THROUGH */
- case NMI_IO_APIC:
- __get_cpu_var(wd_enabled) = 1;
- atomic_inc(&nmi_active);
- }
-}
-
-void stop_apic_nmi_watchdog(void *unused)
-{
- /* only support LOCAL and IO APICs for now */
- if (!nmi_watchdog_active())
- return;
- if (__get_cpu_var(wd_enabled) == 0)
- return;
- if (nmi_watchdog == NMI_LOCAL_APIC)
- lapic_watchdog_stop();
- else
- __acpi_nmi_disable(NULL);
- __get_cpu_var(wd_enabled) = 0;
- atomic_dec(&nmi_active);
-}
-
-/*
- * the best way to detect whether a CPU has a 'hard lockup' problem
- * is to check it's local APIC timer IRQ counts. If they are not
- * changing then that CPU has some problem.
- *
- * as these watchdog NMI IRQs are generated on every CPU, we only
- * have to check the current processor.
- *
- * since NMIs don't listen to _any_ locks, we have to be extremely
- * careful not to rely on unsafe variables. The printk might lock
- * up though, so we have to break up any console locks first ...
- * [when there will be more tty-related locks, break them up here too!]
- */
-
-static DEFINE_PER_CPU(unsigned, last_irq_sum);
-static DEFINE_PER_CPU(long, alert_counter);
-static DEFINE_PER_CPU(int, nmi_touch);
-
-void touch_nmi_watchdog(void)
-{
- if (nmi_watchdog_active()) {
- unsigned cpu;
-
- /*
- * Tell other CPUs to reset their alert counters. We cannot
- * do it ourselves because the alert count increase is not
- * atomic.
- */
- for_each_present_cpu(cpu) {
- if (per_cpu(nmi_touch, cpu) != 1)
- per_cpu(nmi_touch, cpu) = 1;
- }
- }
-
- /*
- * Tickle the softlockup detector too:
- */
- touch_softlockup_watchdog();
-}
-EXPORT_SYMBOL(touch_nmi_watchdog);
-
-notrace __kprobes int
-nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
-{
- /*
- * Since current_thread_info()-> is always on the stack, and we
- * always switch the stack NMI-atomically, it's safe to use
- * smp_processor_id().
- */
- unsigned int sum;
- int touched = 0;
- int cpu = smp_processor_id();
- int rc = 0;
-
- sum = get_timer_irqs(cpu);
-
- if (__get_cpu_var(nmi_touch)) {
- __get_cpu_var(nmi_touch) = 0;
- touched = 1;
- }
-
- /* We can be called before check_nmi_watchdog, hence NULL check. */
- if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
- static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */
-
- raw_spin_lock(&lock);
- printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
- show_regs(regs);
- dump_stack();
- raw_spin_unlock(&lock);
- cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
-
- rc = 1;
- }
-
- /* Could check oops_in_progress here too, but it's safer not to */
- if (mce_in_progress())
- touched = 1;
-
- /* if the none of the timers isn't firing, this cpu isn't doing much */
- if (!touched && __get_cpu_var(last_irq_sum) == sum) {
- /*
- * Ayiee, looks like this CPU is stuck ...
- * wait a few IRQs (5 seconds) before doing the oops ...
- */
- __this_cpu_inc(alert_counter);
- if (__this_cpu_read(alert_counter) == 5 * nmi_hz)
- /*
- * die_nmi will return ONLY if NOTIFY_STOP happens..
- */
- die_nmi("BUG: NMI Watchdog detected LOCKUP",
- regs, panic_on_timeout);
- } else {
- __get_cpu_var(last_irq_sum) = sum;
- __this_cpu_write(alert_counter, 0);
- }
-
- /* see if the nmi watchdog went off */
- if (!__get_cpu_var(wd_enabled))
- return rc;
- switch (nmi_watchdog) {
- case NMI_LOCAL_APIC:
- rc |= lapic_wd_event(nmi_hz);
- break;
- case NMI_IO_APIC:
- /*
- * don't know how to accurately check for this.
- * just assume it was a watchdog timer interrupt
- * This matches the old behaviour.
- */
- rc = 1;
- break;
- }
- return rc;
-}
-
-#ifdef CONFIG_SYSCTL
-
-static void enable_ioapic_nmi_watchdog_single(void *unused)
-{
- __get_cpu_var(wd_enabled) = 1;
- atomic_inc(&nmi_active);
- __acpi_nmi_enable(NULL);
-}
-
-static void enable_ioapic_nmi_watchdog(void)
-{
- on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1);
- touch_nmi_watchdog();
-}
-
-static void disable_ioapic_nmi_watchdog(void)
-{
- on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
-}
-
-static int __init setup_unknown_nmi_panic(char *str)
-{
- unknown_nmi_panic = 1;
- return 1;
-}
-__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
-
-static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
-{
- unsigned char reason = get_nmi_reason();
- char buf[64];
-
- sprintf(buf, "NMI received for unknown reason %02x\n", reason);
- die_nmi(buf, regs, 1); /* Always panic here */
- return 0;
-}
-
-/*
- * proc handler for /proc/sys/kernel/nmi
- */
-int proc_nmi_enabled(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
-{
- int old_state;
-
- nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
- old_state = nmi_watchdog_enabled;
- proc_dointvec(table, write, buffer, length, ppos);
- if (!!old_state == !!nmi_watchdog_enabled)
- return 0;
-
- if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) {
- printk(KERN_WARNING
- "NMI watchdog is permanently disabled\n");
- return -EIO;
- }
-
- if (nmi_watchdog == NMI_LOCAL_APIC) {
- if (nmi_watchdog_enabled)
- enable_lapic_nmi_watchdog();
- else
- disable_lapic_nmi_watchdog();
- } else if (nmi_watchdog == NMI_IO_APIC) {
- if (nmi_watchdog_enabled)
- enable_ioapic_nmi_watchdog();
- else
- disable_ioapic_nmi_watchdog();
- } else {
- printk(KERN_WARNING
- "NMI watchdog doesn't know what hardware to touch\n");
- return -EIO;
- }
- return 0;
-}
-
-#endif /* CONFIG_SYSCTL */
-
-int do_nmi_callback(struct pt_regs *regs, int cpu)
-{
-#ifdef CONFIG_SYSCTL
- if (unknown_nmi_panic)
- return unknown_nmi_panic_callback(regs, cpu);
-#endif
- return 0;
-}
-
-void arch_trigger_all_cpu_backtrace(void)
-{
- int i;
-
- cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
-
- printk(KERN_INFO "sending NMI to all CPUs:\n");
- apic->send_IPI_all(NMI_VECTOR);
-
- /* Wait for up to 10 seconds for all CPUs to do the backtrace */
- for (i = 0; i < 10 * 1000; i++) {
- if (cpumask_empty(to_cpumask(backtrace_mask)))
- break;
- mdelay(1);
- }
-}
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index f9e4e6a..d8c4a6f 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -79,13 +79,6 @@ void __init default_setup_apic_routing(void)
/* need to update phys_pkg_id */
apic->phys_pkg_id = apicid_phys_pkg_id;
}
-
- /*
- * Now that apic routing model is selected, configure the
- * fault handling for intr remapping.
- */
- if (intr_remapping_enabled)
- enable_drhd_fault_handling();
}
/* Same for both flat and physical. */
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 194539a..2a3f2a7 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -44,8 +44,20 @@ static u64 gru_start_paddr, gru_end_paddr;
static union uvh_apicid uvh_apicid;
int uv_min_hub_revision_id;
EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
+unsigned int uv_apicid_hibits;
+EXPORT_SYMBOL_GPL(uv_apicid_hibits);
static DEFINE_SPINLOCK(uv_nmi_lock);
+static unsigned long __init uv_early_read_mmr(unsigned long addr)
+{
+ unsigned long val, *mmr;
+
+ mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr));
+ val = *mmr;
+ early_iounmap(mmr, sizeof(*mmr));
+ return val;
+}
+
static inline bool is_GRU_range(u64 start, u64 end)
{
return start >= gru_start_paddr && end <= gru_end_paddr;
@@ -56,28 +68,24 @@ static bool uv_is_untracked_pat_range(u64 start, u64 end)
return is_ISA_range(start, end) || is_GRU_range(start, end);
}
-static int early_get_nodeid(void)
+static int __init early_get_pnodeid(void)
{
union uvh_node_id_u node_id;
- unsigned long *mmr;
-
- mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr));
- node_id.v = *mmr;
- early_iounmap(mmr, sizeof(*mmr));
+ union uvh_rh_gam_config_mmr_u m_n_config;
+ int pnode;
/* Currently, all blades have same revision number */
+ node_id.v = uv_early_read_mmr(UVH_NODE_ID);
+ m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR);
uv_min_hub_revision_id = node_id.s.revision;
- return node_id.s.node_id;
+ pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
+ return pnode;
}
static void __init early_get_apic_pnode_shift(void)
{
- unsigned long *mmr;
-
- mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_APICID, sizeof(*mmr));
- uvh_apicid.v = *mmr;
- early_iounmap(mmr, sizeof(*mmr));
+ uvh_apicid.v = uv_early_read_mmr(UVH_APICID);
if (!uvh_apicid.v)
/*
* Old bios, use default value
@@ -85,12 +93,25 @@ static void __init early_get_apic_pnode_shift(void)
uvh_apicid.s.pnode_shift = UV_APIC_PNODE_SHIFT;
}
+/*
+ * Add an extra bit as dictated by bios to the destination apicid of
+ * interrupts potentially passing through the UV HUB. This prevents
+ * a deadlock between interrupts and IO port operations.
+ */
+static void __init uv_set_apicid_hibit(void)
+{
+ union uvh_lb_target_physical_apic_id_mask_u apicid_mask;
+
+ apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK);
+ uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK;
+}
+
static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
- int nodeid;
+ int pnodeid;
if (!strcmp(oem_id, "SGI")) {
- nodeid = early_get_nodeid();
+ pnodeid = early_get_pnodeid();
early_get_apic_pnode_shift();
x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range;
x86_platform.nmi_init = uv_nmi_init;
@@ -100,8 +121,9 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
uv_system_type = UV_X2APIC;
else if (!strcmp(oem_table_id, "UVH")) {
__get_cpu_var(x2apic_extra_bits) =
- nodeid << (uvh_apicid.s.pnode_shift - 1);
+ pnodeid << uvh_apicid.s.pnode_shift;
uv_system_type = UV_NON_UNIQUE_APIC;
+ uv_set_apicid_hibit();
return 1;
}
}
@@ -155,6 +177,7 @@ static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_ri
int pnode;
pnode = uv_apicid_to_pnode(phys_apicid);
+ phys_apicid |= uv_apicid_hibits;
val = (1UL << UVH_IPI_INT_SEND_SHFT) |
(phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
@@ -236,7 +259,7 @@ static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask)
int cpu = cpumask_first(cpumask);
if ((unsigned)cpu < nr_cpu_ids)
- return per_cpu(x86_cpu_to_apicid, cpu);
+ return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits;
else
return BAD_APICID;
}
@@ -255,7 +278,7 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
}
- return per_cpu(x86_cpu_to_apicid, cpu);
+ return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits;
}
static unsigned int x2apic_get_apic_id(unsigned long x)
@@ -661,27 +684,32 @@ void uv_nmi_init(void)
void __init uv_system_init(void)
{
union uvh_rh_gam_config_mmr_u m_n_config;
+ union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
union uvh_node_id_u node_id;
unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
- int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
+ int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val, n_io;
int gnode_extra, max_pnode = 0;
unsigned long mmr_base, present, paddr;
- unsigned short pnode_mask;
+ unsigned short pnode_mask, pnode_io_mask;
map_low_mmrs();
m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
m_val = m_n_config.s.m_skt;
n_val = m_n_config.s.n_skt;
+ mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
+ n_io = mmioh.s.n_io;
mmr_base =
uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
~UV_MMR_ENABLE;
pnode_mask = (1 << n_val) - 1;
+ pnode_io_mask = (1 << n_io) - 1;
+
node_id.v = uv_read_local_mmr(UVH_NODE_ID);
gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
gnode_upper = ((unsigned long)gnode_extra << m_val);
- printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n",
- n_val, m_val, gnode_upper, gnode_extra);
+ printk(KERN_INFO "UV: N %d, M %d, N_IO: %d, gnode_upper 0x%lx, gnode_extra 0x%x, pnode_mask 0x%x, pnode_io_mask 0x%x\n",
+ n_val, m_val, n_io, gnode_upper, gnode_extra, pnode_mask, pnode_io_mask);
printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
@@ -714,7 +742,7 @@ void __init uv_system_init(void)
for (j = 0; j < 64; j++) {
if (!test_bit(j, &present))
continue;
- pnode = (i * 64 + j);
+ pnode = (i * 64 + j) & pnode_mask;
uv_blade_info[blade].pnode = pnode;
uv_blade_info[blade].nr_possible_cpus = 0;
uv_blade_info[blade].nr_online_cpus = 0;
@@ -735,6 +763,7 @@ void __init uv_system_init(void)
/*
* apic_pnode_shift must be set before calling uv_apicid_to_pnode();
*/
+ uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
pnode = uv_apicid_to_pnode(apicid);
blade = boot_pnode_to_blade(pnode);
@@ -751,7 +780,6 @@ void __init uv_system_init(void)
uv_cpu_hub_info(cpu)->numa_blade_id = blade;
uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
uv_cpu_hub_info(cpu)->pnode = pnode;
- uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1;
uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
@@ -775,7 +803,7 @@ void __init uv_system_init(void)
map_gru_high(max_pnode);
map_mmr_high(max_pnode);
- map_mmioh_high(max_pnode);
+ map_mmioh_high(max_pnode & pnode_io_mask);
uv_cpu_init();
uv_scir_register_cpu_notifier();
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4b68bda..1d59834 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -894,7 +894,6 @@ void __init identify_boot_cpu(void)
#else
vgetcpu_set_mode();
#endif
- init_hw_perf_events();
}
void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 80c4823..5bf2fac 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -31,8 +31,6 @@
#include <asm/mce.h>
#include <asm/msr.h>
-#define PFX "mce_threshold: "
-#define VERSION "version 1.1.1"
#define NR_BANKS 6
#define NR_BLOCKS 9
#define THRESHOLD_MAX 0xFFF
@@ -59,12 +57,6 @@ struct threshold_block {
struct list_head miscj;
};
-/* defaults used early on boot */
-static struct threshold_block threshold_defaults = {
- .interrupt_enable = 0,
- .threshold_limit = THRESHOLD_MAX,
-};
-
struct threshold_bank {
struct kobject *kobj;
struct threshold_block *blocks;
@@ -89,50 +81,101 @@ static void amd_threshold_interrupt(void);
struct thresh_restart {
struct threshold_block *b;
int reset;
+ int set_lvt_off;
+ int lvt_off;
u16 old_limit;
};
+static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
+{
+ int msr = (hi & MASK_LVTOFF_HI) >> 20;
+
+ if (apic < 0) {
+ pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt "
+ "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu,
+ b->bank, b->block, b->address, hi, lo);
+ return 0;
+ }
+
+ if (apic != msr) {
+ pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
+ "for bank %d, block %d (MSR%08X=0x%x%08x)\n",
+ b->cpu, apic, b->bank, b->block, b->address, hi, lo);
+ return 0;
+ }
+
+ return 1;
+};
+
/* must be called with correct cpu affinity */
/* Called via smp_call_function_single() */
static void threshold_restart_bank(void *_tr)
{
struct thresh_restart *tr = _tr;
- u32 mci_misc_hi, mci_misc_lo;
+ u32 hi, lo;
- rdmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+ rdmsr(tr->b->address, lo, hi);
- if (tr->b->threshold_limit < (mci_misc_hi & THRESHOLD_MAX))
+ if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
tr->reset = 1; /* limit cannot be lower than err count */
if (tr->reset) { /* reset err count and overflow bit */
- mci_misc_hi =
- (mci_misc_hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
+ hi =
+ (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
(THRESHOLD_MAX - tr->b->threshold_limit);
} else if (tr->old_limit) { /* change limit w/o reset */
- int new_count = (mci_misc_hi & THRESHOLD_MAX) +
+ int new_count = (hi & THRESHOLD_MAX) +
(tr->old_limit - tr->b->threshold_limit);
- mci_misc_hi = (mci_misc_hi & ~MASK_ERR_COUNT_HI) |
+ hi = (hi & ~MASK_ERR_COUNT_HI) |
(new_count & THRESHOLD_MAX);
}
+ if (tr->set_lvt_off) {
+ if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) {
+ /* set new lvt offset */
+ hi &= ~MASK_LVTOFF_HI;
+ hi |= tr->lvt_off << 20;
+ }
+ }
+
tr->b->interrupt_enable ?
- (mci_misc_hi = (mci_misc_hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
- (mci_misc_hi &= ~MASK_INT_TYPE_HI);
+ (hi = (hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
+ (hi &= ~MASK_INT_TYPE_HI);
- mci_misc_hi |= MASK_COUNT_EN_HI;
- wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+ hi |= MASK_COUNT_EN_HI;
+ wrmsr(tr->b->address, lo, hi);
+}
+
+static void mce_threshold_block_init(struct threshold_block *b, int offset)
+{
+ struct thresh_restart tr = {
+ .b = b,
+ .set_lvt_off = 1,
+ .lvt_off = offset,
+ };
+
+ b->threshold_limit = THRESHOLD_MAX;
+ threshold_restart_bank(&tr);
+};
+
+static int setup_APIC_mce(int reserved, int new)
+{
+ if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
+ APIC_EILVT_MSG_FIX, 0))
+ return new;
+
+ return reserved;
}
/* cpu init entry point, called from mce.c with preempt off */
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
+ struct threshold_block b;
unsigned int cpu = smp_processor_id();
u32 low = 0, high = 0, address = 0;
unsigned int bank, block;
- struct thresh_restart tr;
- int lvt_off = -1;
- u8 offset;
+ int offset = -1;
for (bank = 0; bank < NR_BANKS; ++bank) {
for (block = 0; block < NR_BLOCKS; ++block) {
@@ -163,39 +206,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
if (shared_bank[bank] && c->cpu_core_id)
break;
#endif
- offset = (high & MASK_LVTOFF_HI) >> 20;
- if (lvt_off < 0) {
- if (setup_APIC_eilvt(offset,
- THRESHOLD_APIC_VECTOR,
- APIC_EILVT_MSG_FIX, 0)) {
- pr_err(FW_BUG "cpu %d, failed to "
- "setup threshold interrupt "
- "for bank %d, block %d "
- "(MSR%08X=0x%x%08x)",
- smp_processor_id(), bank, block,
- address, high, low);
- continue;
- }
- lvt_off = offset;
- } else if (lvt_off != offset) {
- pr_err(FW_BUG "cpu %d, invalid threshold "
- "interrupt offset %d for bank %d,"
- "block %d (MSR%08X=0x%x%08x)",
- smp_processor_id(), lvt_off, bank,
- block, address, high, low);
- continue;
- }
-
- high &= ~MASK_LVTOFF_HI;
- high |= lvt_off << 20;
- wrmsr(address, low, high);
+ offset = setup_APIC_mce(offset,
+ (high & MASK_LVTOFF_HI) >> 20);
- threshold_defaults.address = address;
- tr.b = &threshold_defaults;
- tr.reset = 0;
- tr.old_limit = 0;
- threshold_restart_bank(&tr);
+ memset(&b, 0, sizeof(b));
+ b.cpu = cpu;
+ b.bank = bank;
+ b.block = block;
+ b.address = address;
+ mce_threshold_block_init(&b, offset);
mce_threshold_vector = amd_threshold_interrupt;
}
}
@@ -298,9 +318,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size)
b->interrupt_enable = !!new;
+ memset(&tr, 0, sizeof(tr));
tr.b = b;
- tr.reset = 0;
- tr.old_limit = 0;
smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
@@ -321,10 +340,10 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size)
if (new < 1)
new = 1;
+ memset(&tr, 0, sizeof(tr));
tr.old_limit = b->threshold_limit;
b->threshold_limit = new;
tr.b = b;
- tr.reset = 0;
smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
@@ -603,9 +622,9 @@ static __cpuinit int threshold_create_device(unsigned int cpu)
continue;
err = threshold_create_bank(cpu, bank);
if (err)
- goto out;
+ return err;
}
-out:
+
return err;
}
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 4b68326..e12246f 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -53,8 +53,13 @@ struct thermal_state {
struct _thermal_state core_power_limit;
struct _thermal_state package_throttle;
struct _thermal_state package_power_limit;
+ struct _thermal_state core_thresh0;
+ struct _thermal_state core_thresh1;
};
+/* Callback to handle core threshold interrupts */
+int (*platform_thermal_notify)(__u64 msr_val);
+
static DEFINE_PER_CPU(struct thermal_state, thermal_state);
static atomic_t therm_throt_en = ATOMIC_INIT(0);
@@ -200,6 +205,22 @@ static int therm_throt_process(bool new_event, int event, int level)
return 0;
}
+static int thresh_event_valid(int event)
+{
+ struct _thermal_state *state;
+ unsigned int this_cpu = smp_processor_id();
+ struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
+ u64 now = get_jiffies_64();
+
+ state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1;
+
+ if (time_before64(now, state->next_check))
+ return 0;
+
+ state->next_check = now + CHECK_INTERVAL;
+ return 1;
+}
+
#ifdef CONFIG_SYSFS
/* Add/Remove thermal_throttle interface for CPU device: */
static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
@@ -313,6 +334,22 @@ device_initcall(thermal_throttle_init_device);
#define PACKAGE_THROTTLED ((__u64)2 << 62)
#define PACKAGE_POWER_LIMIT ((__u64)3 << 62)
+static void notify_thresholds(__u64 msr_val)
+{
+ /* check whether the interrupt handler is defined;
+ * otherwise simply return
+ */
+ if (!platform_thermal_notify)
+ return;
+
+ /* lower threshold reached */
+ if ((msr_val & THERM_LOG_THRESHOLD0) && thresh_event_valid(0))
+ platform_thermal_notify(msr_val);
+ /* higher threshold reached */
+ if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1))
+ platform_thermal_notify(msr_val);
+}
+
/* Thermal transition interrupt handler */
static void intel_thermal_interrupt(void)
{
@@ -321,6 +358,9 @@ static void intel_thermal_interrupt(void)
rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
+ /* Check for violation of core thermal thresholds*/
+ notify_thresholds(msr_val);
+
if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
THERMAL_THROTTLING_EVENT,
CORE_LEVEL) != 0)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index ed63101..0a360d1 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -330,9 +330,6 @@ static bool reserve_pmc_hardware(void)
{
int i;
- if (nmi_watchdog == NMI_LOCAL_APIC)
- disable_lapic_nmi_watchdog();
-
for (i = 0; i < x86_pmu.num_counters; i++) {
if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
goto perfctr_fail;
@@ -355,9 +352,6 @@ perfctr_fail:
for (i--; i >= 0; i--)
release_perfctr_nmi(x86_pmu.perfctr + i);
- if (nmi_watchdog == NMI_LOCAL_APIC)
- enable_lapic_nmi_watchdog();
-
return false;
}
@@ -369,9 +363,6 @@ static void release_pmc_hardware(void)
release_perfctr_nmi(x86_pmu.perfctr + i);
release_evntsel_nmi(x86_pmu.eventsel + i);
}
-
- if (nmi_watchdog == NMI_LOCAL_APIC)
- enable_lapic_nmi_watchdog();
}
#else
@@ -381,6 +372,58 @@ static void release_pmc_hardware(void) {}
#endif
+static bool check_hw_exists(void)
+{
+ u64 val, val_new = 0;
+ int i, reg, ret = 0;
+
+ /*
+ * Check to see if the BIOS enabled any of the counters, if so
+ * complain and bail.
+ */
+ for (i = 0; i < x86_pmu.num_counters; i++) {
+ reg = x86_pmu.eventsel + i;
+ ret = rdmsrl_safe(reg, &val);
+ if (ret)
+ goto msr_fail;
+ if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
+ goto bios_fail;
+ }
+
+ if (x86_pmu.num_counters_fixed) {
+ reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
+ ret = rdmsrl_safe(reg, &val);
+ if (ret)
+ goto msr_fail;
+ for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
+ if (val & (0x03 << i*4))
+ goto bios_fail;
+ }
+ }
+
+ /*
+ * Now write a value and read it back to see if it matches,
+ * this is needed to detect certain hardware emulators (qemu/kvm)
+ * that don't trap on the MSR access and always return 0s.
+ */
+ val = 0xabcdUL;
+ ret = checking_wrmsrl(x86_pmu.perfctr, val);
+ ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
+ if (ret || val != val_new)
+ goto msr_fail;
+
+ return true;
+
+bios_fail:
+ printk(KERN_CONT "Broken BIOS detected, using software events only.\n");
+ printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
+ return false;
+
+msr_fail:
+ printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
+ return false;
+}
+
static void reserve_ds_buffers(void);
static void release_ds_buffers(void);
@@ -437,7 +480,7 @@ static int x86_setup_perfctr(struct perf_event *event)
struct hw_perf_event *hwc = &event->hw;
u64 config;
- if (!hwc->sample_period) {
+ if (!is_sampling_event(event)) {
hwc->sample_period = x86_pmu.max_period;
hwc->last_period = hwc->sample_period;
local64_set(&hwc->period_left, hwc->sample_period);
@@ -1348,7 +1391,7 @@ static void __init pmu_check_apic(void)
pr_info("no hardware sampling interrupt available.\n");
}
-void __init init_hw_perf_events(void)
+int __init init_hw_perf_events(void)
{
struct event_constraint *c;
int err;
@@ -1363,15 +1406,19 @@ void __init init_hw_perf_events(void)
err = amd_pmu_init();
break;
default:
- return;
+ return 0;
}
if (err != 0) {
pr_cont("no PMU driver, software events only.\n");
- return;
+ return 0;
}
pmu_check_apic();
+ /* sanity check that the hardware exists or is emulated */
+ if (!check_hw_exists())
+ return 0;
+
pr_cont("%s PMU driver.\n", x86_pmu.name);
if (x86_pmu.quirks)
@@ -1418,9 +1465,12 @@ void __init init_hw_perf_events(void)
pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed);
pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl);
- perf_pmu_register(&pmu);
+ perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
perf_cpu_notifier(x86_pmu_notifier);
+
+ return 0;
}
+early_initcall(init_hw_perf_events);
static inline void x86_pmu_read(struct perf_event *event)
{
@@ -1666,7 +1716,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_store(entry, regs->ip);
- dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
+ dump_trace(NULL, regs, NULL, &backtrace_ops, entry);
}
#ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index e421b8c..67e2202 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -1,7 +1,5 @@
#ifdef CONFIG_CPU_SUP_AMD
-static DEFINE_RAW_SPINLOCK(amd_nb_lock);
-
static __initconst const u64 amd_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -275,7 +273,7 @@ done:
return &emptyconstraint;
}
-static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
+static struct amd_nb *amd_alloc_nb(int cpu)
{
struct amd_nb *nb;
int i;
@@ -285,7 +283,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
if (!nb)
return NULL;
- nb->nb_id = nb_id;
+ nb->nb_id = -1;
/*
* initialize all possible NB constraints
@@ -306,7 +304,7 @@ static int amd_pmu_cpu_prepare(int cpu)
if (boot_cpu_data.x86_max_cores < 2)
return NOTIFY_OK;
- cpuc->amd_nb = amd_alloc_nb(cpu, -1);
+ cpuc->amd_nb = amd_alloc_nb(cpu);
if (!cpuc->amd_nb)
return NOTIFY_BAD;
@@ -325,8 +323,6 @@ static void amd_pmu_cpu_starting(int cpu)
nb_id = amd_get_nb_id(cpu);
WARN_ON_ONCE(nb_id == BAD_APICID);
- raw_spin_lock(&amd_nb_lock);
-
for_each_online_cpu(i) {
nb = per_cpu(cpu_hw_events, i).amd_nb;
if (WARN_ON_ONCE(!nb))
@@ -341,8 +337,6 @@ static void amd_pmu_cpu_starting(int cpu)
cpuc->amd_nb->nb_id = nb_id;
cpuc->amd_nb->refcnt++;
-
- raw_spin_unlock(&amd_nb_lock);
}
static void amd_pmu_cpu_dead(int cpu)
@@ -354,8 +348,6 @@ static void amd_pmu_cpu_dead(int cpu)
cpuhw = &per_cpu(cpu_hw_events, cpu);
- raw_spin_lock(&amd_nb_lock);
-
if (cpuhw->amd_nb) {
struct amd_nb *nb = cpuhw->amd_nb;
@@ -364,8 +356,6 @@ static void amd_pmu_cpu_dead(int cpu)
cpuhw->amd_nb = NULL;
}
-
- raw_spin_unlock(&amd_nb_lock);
}
static __initconst const struct x86_pmu amd_pmu = {
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index c8f5c08..24e390e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -816,6 +816,32 @@ static int intel_pmu_hw_config(struct perf_event *event)
if (ret)
return ret;
+ if (event->attr.precise_ip &&
+ (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+ /*
+ * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+ * (0x003c) so that we can use it with PEBS.
+ *
+ * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+ * PEBS capable. However we can use INST_RETIRED.ANY_P
+ * (0x00c0), which is a PEBS capable event, to get the same
+ * count.
+ *
+ * INST_RETIRED.ANY_P counts the number of cycles that retires
+ * CNTMASK instructions. By setting CNTMASK to a value (16)
+ * larger than the maximum number of instructions that can be
+ * retired per cycle (4) and then inverting the condition, we
+ * count all cycles that retire 16 or less instructions, which
+ * is every cycle.
+ *
+ * Thereby we gain a PEBS capable cycle counter.
+ */
+ u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */
+
+ alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+ event->hw.config = alt_config;
+ }
+
if (event->attr.type != PERF_TYPE_RAW)
return 0;
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index d9f4ff8..d5a2366 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -16,32 +16,12 @@
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/smp.h>
-#include <linux/nmi.h>
+#include <asm/nmi.h>
#include <linux/kprobes.h>
#include <asm/apic.h>
#include <asm/perf_event.h>
-struct nmi_watchdog_ctlblk {
- unsigned int cccr_msr;
- unsigned int perfctr_msr; /* the MSR to reset in NMI handler */
- unsigned int evntsel_msr; /* the MSR to select the events to handle */
-};
-
-/* Interface defining a CPU specific perfctr watchdog */
-struct wd_ops {
- int (*reserve)(void);
- void (*unreserve)(void);
- int (*setup)(unsigned nmi_hz);
- void (*rearm)(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz);
- void (*stop)(void);
- unsigned perfctr;
- unsigned evntsel;
- u64 checkbit;
-};
-
-static const struct wd_ops *wd_ops;
-
/*
* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
* offset from MSR_P4_BSU_ESCR0.
@@ -60,8 +40,6 @@ static const struct wd_ops *wd_ops;
static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS);
static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS);
-static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
-
/* converts an msr to an appropriate reservation bit */
static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
{
@@ -172,623 +150,3 @@ void release_evntsel_nmi(unsigned int msr)
clear_bit(counter, evntsel_nmi_owner);
}
EXPORT_SYMBOL(release_evntsel_nmi);
-
-void disable_lapic_nmi_watchdog(void)
-{
- BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
- if (atomic_read(&nmi_active) <= 0)
- return;
-
- on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
-
- if (wd_ops)
- wd_ops->unreserve();
-
- BUG_ON(atomic_read(&nmi_active) != 0);
-}
-
-void enable_lapic_nmi_watchdog(void)
-{
- BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
- /* are we already enabled */
- if (atomic_read(&nmi_active) != 0)
- return;
-
- /* are we lapic aware */
- if (!wd_ops)
- return;
- if (!wd_ops->reserve()) {
- printk(KERN_ERR "NMI watchdog: cannot reserve perfctrs\n");
- return;
- }
-
- on_each_cpu(setup_apic_nmi_watchdog, NULL, 1);
- touch_nmi_watchdog();
-}
-
-/*
- * Activate the NMI watchdog via the local APIC.
- */
-
-static unsigned int adjust_for_32bit_ctr(unsigned int hz)
-{
- u64 counter_val;
- unsigned int retval = hz;
-
- /*
- * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter
- * are writable, with higher bits sign extending from bit 31.
- * So, we can only program the counter with 31 bit values and
- * 32nd bit should be 1, for 33.. to be 1.
- * Find the appropriate nmi_hz
- */
- counter_val = (u64)cpu_khz * 1000;
- do_div(counter_val, retval);
- if (counter_val > 0x7fffffffULL) {
- u64 count = (u64)cpu_khz * 1000;
- do_div(count, 0x7fffffffUL);
- retval = count + 1;
- }
- return retval;
-}
-
-static void write_watchdog_counter(unsigned int perfctr_msr,
- const char *descr, unsigned nmi_hz)
-{
- u64 count = (u64)cpu_khz * 1000;
-
- do_div(count, nmi_hz);
- if (descr)
- pr_debug("setting %s to -0x%08Lx\n", descr, count);
- wrmsrl(perfctr_msr, 0 - count);
-}
-
-static void write_watchdog_counter32(unsigned int perfctr_msr,
- const char *descr, unsigned nmi_hz)
-{
- u64 count = (u64)cpu_khz * 1000;
-
- do_div(count, nmi_hz);
- if (descr)
- pr_debug("setting %s to -0x%08Lx\n", descr, count);
- wrmsr(perfctr_msr, (u32)(-count), 0);
-}
-
-/*
- * AMD K7/K8/Family10h/Family11h support.
- * AMD keeps this interface nicely stable so there is not much variety
- */
-#define K7_EVNTSEL_ENABLE (1 << 22)
-#define K7_EVNTSEL_INT (1 << 20)
-#define K7_EVNTSEL_OS (1 << 17)
-#define K7_EVNTSEL_USR (1 << 16)
-#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76
-#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING
-
-static int setup_k7_watchdog(unsigned nmi_hz)
-{
- unsigned int perfctr_msr, evntsel_msr;
- unsigned int evntsel;
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- perfctr_msr = wd_ops->perfctr;
- evntsel_msr = wd_ops->evntsel;
-
- wrmsrl(perfctr_msr, 0UL);
-
- evntsel = K7_EVNTSEL_INT
- | K7_EVNTSEL_OS
- | K7_EVNTSEL_USR
- | K7_NMI_EVENT;
-
- /* setup the timer */
- wrmsr(evntsel_msr, evntsel, 0);
- write_watchdog_counter(perfctr_msr, "K7_PERFCTR0", nmi_hz);
-
- /* initialize the wd struct before enabling */
- wd->perfctr_msr = perfctr_msr;
- wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = 0; /* unused */
-
- /* ok, everything is initialized, announce that we're set */
- cpu_nmi_set_wd_enabled();
-
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- evntsel |= K7_EVNTSEL_ENABLE;
- wrmsr(evntsel_msr, evntsel, 0);
-
- return 1;
-}
-
-static void single_msr_stop_watchdog(void)
-{
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- wrmsr(wd->evntsel_msr, 0, 0);
-}
-
-static int single_msr_reserve(void)
-{
- if (!reserve_perfctr_nmi(wd_ops->perfctr))
- return 0;
-
- if (!reserve_evntsel_nmi(wd_ops->evntsel)) {
- release_perfctr_nmi(wd_ops->perfctr);
- return 0;
- }
- return 1;
-}
-
-static void single_msr_unreserve(void)
-{
- release_evntsel_nmi(wd_ops->evntsel);
- release_perfctr_nmi(wd_ops->perfctr);
-}
-
-static void __kprobes
-single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
-{
- /* start the cycle over again */
- write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
-}
-
-static const struct wd_ops k7_wd_ops = {
- .reserve = single_msr_reserve,
- .unreserve = single_msr_unreserve,
- .setup = setup_k7_watchdog,
- .rearm = single_msr_rearm,
- .stop = single_msr_stop_watchdog,
- .perfctr = MSR_K7_PERFCTR0,
- .evntsel = MSR_K7_EVNTSEL0,
- .checkbit = 1ULL << 47,
-};
-
-/*
- * Intel Model 6 (PPro+,P2,P3,P-M,Core1)
- */
-#define P6_EVNTSEL0_ENABLE (1 << 22)
-#define P6_EVNTSEL_INT (1 << 20)
-#define P6_EVNTSEL_OS (1 << 17)
-#define P6_EVNTSEL_USR (1 << 16)
-#define P6_EVENT_CPU_CLOCKS_NOT_HALTED 0x79
-#define P6_NMI_EVENT P6_EVENT_CPU_CLOCKS_NOT_HALTED
-
-static int setup_p6_watchdog(unsigned nmi_hz)
-{
- unsigned int perfctr_msr, evntsel_msr;
- unsigned int evntsel;
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- perfctr_msr = wd_ops->perfctr;
- evntsel_msr = wd_ops->evntsel;
-
- /* KVM doesn't implement this MSR */
- if (wrmsr_safe(perfctr_msr, 0, 0) < 0)
- return 0;
-
- evntsel = P6_EVNTSEL_INT
- | P6_EVNTSEL_OS
- | P6_EVNTSEL_USR
- | P6_NMI_EVENT;
-
- /* setup the timer */
- wrmsr(evntsel_msr, evntsel, 0);
- nmi_hz = adjust_for_32bit_ctr(nmi_hz);
- write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0", nmi_hz);
-
- /* initialize the wd struct before enabling */
- wd->perfctr_msr = perfctr_msr;
- wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = 0; /* unused */
-
- /* ok, everything is initialized, announce that we're set */
- cpu_nmi_set_wd_enabled();
-
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- evntsel |= P6_EVNTSEL0_ENABLE;
- wrmsr(evntsel_msr, evntsel, 0);
-
- return 1;
-}
-
-static void __kprobes p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
-{
- /*
- * P6 based Pentium M need to re-unmask
- * the apic vector but it doesn't hurt
- * other P6 variant.
- * ArchPerfom/Core Duo also needs this
- */
- apic_write(APIC_LVTPC, APIC_DM_NMI);
-
- /* P6/ARCH_PERFMON has 32 bit counter write */
- write_watchdog_counter32(wd->perfctr_msr, NULL, nmi_hz);
-}
-
-static const struct wd_ops p6_wd_ops = {
- .reserve = single_msr_reserve,
- .unreserve = single_msr_unreserve,
- .setup = setup_p6_watchdog,
- .rearm = p6_rearm,
- .stop = single_msr_stop_watchdog,
- .perfctr = MSR_P6_PERFCTR0,
- .evntsel = MSR_P6_EVNTSEL0,
- .checkbit = 1ULL << 39,
-};
-
-/*
- * Intel P4 performance counters.
- * By far the most complicated of all.
- */
-#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1 << 7)
-#define P4_ESCR_EVENT_SELECT(N) ((N) << 25)
-#define P4_ESCR_OS (1 << 3)
-#define P4_ESCR_USR (1 << 2)
-#define P4_CCCR_OVF_PMI0 (1 << 26)
-#define P4_CCCR_OVF_PMI1 (1 << 27)
-#define P4_CCCR_THRESHOLD(N) ((N) << 20)
-#define P4_CCCR_COMPLEMENT (1 << 19)
-#define P4_CCCR_COMPARE (1 << 18)
-#define P4_CCCR_REQUIRED (3 << 16)
-#define P4_CCCR_ESCR_SELECT(N) ((N) << 13)
-#define P4_CCCR_ENABLE (1 << 12)
-#define P4_CCCR_OVF (1 << 31)
-
-#define P4_CONTROLS 18
-static unsigned int p4_controls[18] = {
- MSR_P4_BPU_CCCR0,
- MSR_P4_BPU_CCCR1,
- MSR_P4_BPU_CCCR2,
- MSR_P4_BPU_CCCR3,
- MSR_P4_MS_CCCR0,
- MSR_P4_MS_CCCR1,
- MSR_P4_MS_CCCR2,
- MSR_P4_MS_CCCR3,
- MSR_P4_FLAME_CCCR0,
- MSR_P4_FLAME_CCCR1,
- MSR_P4_FLAME_CCCR2,
- MSR_P4_FLAME_CCCR3,
- MSR_P4_IQ_CCCR0,
- MSR_P4_IQ_CCCR1,
- MSR_P4_IQ_CCCR2,
- MSR_P4_IQ_CCCR3,
- MSR_P4_IQ_CCCR4,
- MSR_P4_IQ_CCCR5,
-};
-/*
- * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
- * CRU_ESCR0 (with any non-null event selector) through a complemented
- * max threshold. [IA32-Vol3, Section 14.9.9]
- */
-static int setup_p4_watchdog(unsigned nmi_hz)
-{
- unsigned int perfctr_msr, evntsel_msr, cccr_msr;
- unsigned int evntsel, cccr_val;
- unsigned int misc_enable, dummy;
- unsigned int ht_num;
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy);
- if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL))
- return 0;
-
-#ifdef CONFIG_SMP
- /* detect which hyperthread we are on */
- if (smp_num_siblings == 2) {
- unsigned int ebx, apicid;
-
- ebx = cpuid_ebx(1);
- apicid = (ebx >> 24) & 0xff;
- ht_num = apicid & 1;
- } else
-#endif
- ht_num = 0;
-
- /*
- * performance counters are shared resources
- * assign each hyperthread its own set
- * (re-use the ESCR0 register, seems safe
- * and keeps the cccr_val the same)
- */
- if (!ht_num) {
- /* logical cpu 0 */
- perfctr_msr = MSR_P4_IQ_PERFCTR0;
- evntsel_msr = MSR_P4_CRU_ESCR0;
- cccr_msr = MSR_P4_IQ_CCCR0;
- cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
-
- /*
- * If we're on the kdump kernel or other situation, we may
- * still have other performance counter registers set to
- * interrupt and they'll keep interrupting forever because
- * of the P4_CCCR_OVF quirk. So we need to ACK all the
- * pending interrupts and disable all the registers here,
- * before reenabling the NMI delivery. Refer to p4_rearm()
- * about the P4_CCCR_OVF quirk.
- */
- if (reset_devices) {
- unsigned int low, high;
- int i;
-
- for (i = 0; i < P4_CONTROLS; i++) {
- rdmsr(p4_controls[i], low, high);
- low &= ~(P4_CCCR_ENABLE | P4_CCCR_OVF);
- wrmsr(p4_controls[i], low, high);
- }
- }
- } else {
- /* logical cpu 1 */
- perfctr_msr = MSR_P4_IQ_PERFCTR1;
- evntsel_msr = MSR_P4_CRU_ESCR0;
- cccr_msr = MSR_P4_IQ_CCCR1;
-
- /* Pentium 4 D processors don't support P4_CCCR_OVF_PMI1 */
- if (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask == 4)
- cccr_val = P4_CCCR_OVF_PMI0;
- else
- cccr_val = P4_CCCR_OVF_PMI1;
- cccr_val |= P4_CCCR_ESCR_SELECT(4);
- }
-
- evntsel = P4_ESCR_EVENT_SELECT(0x3F)
- | P4_ESCR_OS
- | P4_ESCR_USR;
-
- cccr_val |= P4_CCCR_THRESHOLD(15)
- | P4_CCCR_COMPLEMENT
- | P4_CCCR_COMPARE
- | P4_CCCR_REQUIRED;
-
- wrmsr(evntsel_msr, evntsel, 0);
- wrmsr(cccr_msr, cccr_val, 0);
- write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz);
-
- wd->perfctr_msr = perfctr_msr;
- wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = cccr_msr;
-
- /* ok, everything is initialized, announce that we're set */
- cpu_nmi_set_wd_enabled();
-
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- cccr_val |= P4_CCCR_ENABLE;
- wrmsr(cccr_msr, cccr_val, 0);
- return 1;
-}
-
-static void stop_p4_watchdog(void)
-{
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
- wrmsr(wd->cccr_msr, 0, 0);
- wrmsr(wd->evntsel_msr, 0, 0);
-}
-
-static int p4_reserve(void)
-{
- if (!reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR0))
- return 0;
-#ifdef CONFIG_SMP
- if (smp_num_siblings > 1 && !reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR1))
- goto fail1;
-#endif
- if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0))
- goto fail2;
- /* RED-PEN why is ESCR1 not reserved here? */
- return 1;
- fail2:
-#ifdef CONFIG_SMP
- if (smp_num_siblings > 1)
- release_perfctr_nmi(MSR_P4_IQ_PERFCTR1);
- fail1:
-#endif
- release_perfctr_nmi(MSR_P4_IQ_PERFCTR0);
- return 0;
-}
-
-static void p4_unreserve(void)
-{
-#ifdef CONFIG_SMP
- if (smp_num_siblings > 1)
- release_perfctr_nmi(MSR_P4_IQ_PERFCTR1);
-#endif
- release_evntsel_nmi(MSR_P4_CRU_ESCR0);
- release_perfctr_nmi(MSR_P4_IQ_PERFCTR0);
-}
-
-static void __kprobes p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
-{
- unsigned dummy;
- /*
- * P4 quirks:
- * - An overflown perfctr will assert its interrupt
- * until the OVF flag in its CCCR is cleared.
- * - LVTPC is masked on interrupt and must be
- * unmasked by the LVTPC handler.
- */
- rdmsrl(wd->cccr_msr, dummy);
- dummy &= ~P4_CCCR_OVF;
- wrmsrl(wd->cccr_msr, dummy);
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- /* start the cycle over again */
- write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
-}
-
-static const struct wd_ops p4_wd_ops = {
- .reserve = p4_reserve,
- .unreserve = p4_unreserve,
- .setup = setup_p4_watchdog,
- .rearm = p4_rearm,
- .stop = stop_p4_watchdog,
- /* RED-PEN this is wrong for the other sibling */
- .perfctr = MSR_P4_BPU_PERFCTR0,
- .evntsel = MSR_P4_BSU_ESCR0,
- .checkbit = 1ULL << 39,
-};
-
-/*
- * Watchdog using the Intel architected PerfMon.
- * Used for Core2 and hopefully all future Intel CPUs.
- */
-#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
-#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
-
-static struct wd_ops intel_arch_wd_ops;
-
-static int setup_intel_arch_watchdog(unsigned nmi_hz)
-{
- unsigned int ebx;
- union cpuid10_eax eax;
- unsigned int unused;
- unsigned int perfctr_msr, evntsel_msr;
- unsigned int evntsel;
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- /*
- * Check whether the Architectural PerfMon supports
- * Unhalted Core Cycles Event or not.
- * NOTE: Corresponding bit = 0 in ebx indicates event present.
- */
- cpuid(10, &(eax.full), &ebx, &unused, &unused);
- if ((eax.split.mask_length <
- (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
- (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
- return 0;
-
- perfctr_msr = wd_ops->perfctr;
- evntsel_msr = wd_ops->evntsel;
-
- wrmsrl(perfctr_msr, 0UL);
-
- evntsel = ARCH_PERFMON_EVENTSEL_INT
- | ARCH_PERFMON_EVENTSEL_OS
- | ARCH_PERFMON_EVENTSEL_USR
- | ARCH_PERFMON_NMI_EVENT_SEL
- | ARCH_PERFMON_NMI_EVENT_UMASK;
-
- /* setup the timer */
- wrmsr(evntsel_msr, evntsel, 0);
- nmi_hz = adjust_for_32bit_ctr(nmi_hz);
- write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz);
-
- wd->perfctr_msr = perfctr_msr;
- wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = 0; /* unused */
-
- /* ok, everything is initialized, announce that we're set */
- cpu_nmi_set_wd_enabled();
-
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- evntsel |= ARCH_PERFMON_EVENTSEL_ENABLE;
- wrmsr(evntsel_msr, evntsel, 0);
- intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
- return 1;
-}
-
-static struct wd_ops intel_arch_wd_ops __read_mostly = {
- .reserve = single_msr_reserve,
- .unreserve = single_msr_unreserve,
- .setup = setup_intel_arch_watchdog,
- .rearm = p6_rearm,
- .stop = single_msr_stop_watchdog,
- .perfctr = MSR_ARCH_PERFMON_PERFCTR1,
- .evntsel = MSR_ARCH_PERFMON_EVENTSEL1,
-};
-
-static void probe_nmi_watchdog(void)
-{
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
- if (boot_cpu_data.x86 == 6 ||
- (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15))
- wd_ops = &k7_wd_ops;
- return;
- case X86_VENDOR_INTEL:
- /* Work around where perfctr1 doesn't have a working enable
- * bit as described in the following errata:
- * AE49 Core Duo and Intel Core Solo 65 nm
- * AN49 Intel Pentium Dual-Core
- * AF49 Dual-Core Intel Xeon Processor LV
- */
- if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) ||
- ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 15 &&
- boot_cpu_data.x86_mask == 4))) {
- intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0;
- intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0;
- }
- if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
- wd_ops = &intel_arch_wd_ops;
- break;
- }
- switch (boot_cpu_data.x86) {
- case 6:
- if (boot_cpu_data.x86_model > 13)
- return;
-
- wd_ops = &p6_wd_ops;
- break;
- case 15:
- wd_ops = &p4_wd_ops;
- break;
- default:
- return;
- }
- break;
- }
-}
-
-/* Interface to nmi.c */
-
-int lapic_watchdog_init(unsigned nmi_hz)
-{
- if (!wd_ops) {
- probe_nmi_watchdog();
- if (!wd_ops) {
- printk(KERN_INFO "NMI watchdog: CPU not supported\n");
- return -1;
- }
-
- if (!wd_ops->reserve()) {
- printk(KERN_ERR
- "NMI watchdog: cannot reserve perfctrs\n");
- return -1;
- }
- }
-
- if (!(wd_ops->setup(nmi_hz))) {
- printk(KERN_ERR "Cannot setup NMI watchdog on CPU %d\n",
- raw_smp_processor_id());
- return -1;
- }
-
- return 0;
-}
-
-void lapic_watchdog_stop(void)
-{
- if (wd_ops)
- wd_ops->stop();
-}
-
-unsigned lapic_adjust_nmi_hz(unsigned hz)
-{
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
- if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
- wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1)
- hz = adjust_for_32bit_ctr(hz);
- return hz;
-}
-
-int __kprobes lapic_wd_event(unsigned nmi_hz)
-{
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
- u64 ctr;
-
- rdmsrl(wd->perfctr_msr, ctr);
- if (ctr & wd_ops->checkbit) /* perfctr still running? */
- return 0;
-
- wd_ops->rearm(wd, nmi_hz);
- return 1;
-}
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 1b7b31a..212a6a4 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -33,7 +33,6 @@
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/smp.h>
-#include <linux/smp_lock.h>
#include <linux/major.h>
#include <linux/fs.h>
#include <linux/device.h>
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 6e8752c..8474c99 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = {
void
show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp, char *log_lvl)
+ unsigned long *stack, char *log_lvl)
{
printk("%sCall Trace:\n", log_lvl);
- dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
+ dump_trace(task, regs, stack, &print_trace_ops, log_lvl);
}
void show_trace(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp)
+ unsigned long *stack)
{
- show_trace_log_lvl(task, regs, stack, bp, "");
+ show_trace_log_lvl(task, regs, stack, "");
}
void show_stack(struct task_struct *task, unsigned long *sp)
{
- show_stack_log_lvl(task, NULL, sp, 0, "");
+ show_stack_log_lvl(task, NULL, sp, "");
}
/*
@@ -210,7 +210,7 @@ void dump_stack(void)
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
- show_trace(NULL, NULL, &stack, bp);
+ show_trace(NULL, NULL, &stack);
}
EXPORT_SYMBOL(dump_stack);
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 1bc7f75..74cc1ed 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -17,11 +17,12 @@
#include <asm/stacktrace.h>
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp,
+void dump_trace(struct task_struct *task,
+ struct pt_regs *regs, unsigned long *stack,
const struct stacktrace_ops *ops, void *data)
{
int graph = 0;
+ unsigned long bp;
if (!task)
task = current;
@@ -34,18 +35,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
stack = (unsigned long *)task->thread.sp;
}
-#ifdef CONFIG_FRAME_POINTER
- if (!bp) {
- if (task == current) {
- /* Grab bp right from our regs */
- get_bp(bp);
- } else {
- /* bp is the last reg pushed by switch_to */
- bp = *(unsigned long *) task->thread.sp;
- }
- }
-#endif
-
+ bp = stack_frame(task, regs);
for (;;) {
struct thread_info *context;
@@ -65,7 +55,7 @@ EXPORT_SYMBOL(dump_trace);
void
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *sp, unsigned long bp, char *log_lvl)
+ unsigned long *sp, char *log_lvl)
{
unsigned long *stack;
int i;
@@ -87,7 +77,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
touch_nmi_watchdog();
}
printk(KERN_CONT "\n");
- show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+ show_trace_log_lvl(task, regs, sp, log_lvl);
}
@@ -112,8 +102,7 @@ void show_registers(struct pt_regs *regs)
u8 *ip;
printk(KERN_EMERG "Stack:\n");
- show_stack_log_lvl(NULL, regs, &regs->sp,
- 0, KERN_EMERG);
+ show_stack_log_lvl(NULL, regs, &regs->sp, KERN_EMERG);
printk(KERN_EMERG "Code: ");
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6a34048..6410133 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
* severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
*/
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp,
+void dump_trace(struct task_struct *task,
+ struct pt_regs *regs, unsigned long *stack,
const struct stacktrace_ops *ops, void *data)
{
const unsigned cpu = get_cpu();
@@ -149,6 +149,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
unsigned used = 0;
struct thread_info *tinfo;
int graph = 0;
+ unsigned long bp;
if (!task)
task = current;
@@ -160,18 +161,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
stack = (unsigned long *)task->thread.sp;
}
-#ifdef CONFIG_FRAME_POINTER
- if (!bp) {
- if (task == current) {
- /* Grab bp right from our regs */
- get_bp(bp);
- } else {
- /* bp is the last reg pushed by switch_to */
- bp = *(unsigned long *) task->thread.sp;
- }
- }
-#endif
-
+ bp = stack_frame(task, regs);
/*
* Print function call entries in all stacks, starting at the
* current stack address. If the stacks consist of nested
@@ -235,7 +225,7 @@ EXPORT_SYMBOL(dump_trace);
void
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *sp, unsigned long bp, char *log_lvl)
+ unsigned long *sp, char *log_lvl)
{
unsigned long *irq_stack_end;
unsigned long *irq_stack;
@@ -279,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
preempt_enable();
printk(KERN_CONT "\n");
- show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+ show_trace_log_lvl(task, regs, sp, log_lvl);
}
void show_registers(struct pt_regs *regs)
@@ -308,7 +298,7 @@ void show_registers(struct pt_regs *regs)
printk(KERN_EMERG "Stack:\n");
show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
- regs->bp, KERN_EMERG);
+ KERN_EMERG);
printk(KERN_EMERG "Code: ");
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 59e175e..591e601 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -395,7 +395,7 @@ sysenter_past_esp:
* A tiny bit of offset fixup is necessary - 4*4 means the 4 words
* pushed above; +8 corresponds to copy_thread's esp0 setting.
*/
- pushl_cfi (TI_sysenter_return-THREAD_SIZE_asm+8+4*4)(%esp)
+ pushl_cfi ((TI_sysenter_return)-THREAD_SIZE_asm+8+4*4)(%esp)
CFI_REL_OFFSET eip, 0
pushl_cfi %eax
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index fe2690d..e3ba417 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -295,6 +295,7 @@ ENDPROC(native_usergs_sysret64)
.endm
/* save partial stack frame */
+ .pushsection .kprobes.text, "ax"
ENTRY(save_args)
XCPT_FRAME
cld
@@ -334,6 +335,7 @@ ENTRY(save_args)
ret
CFI_ENDPROC
END(save_args)
+ .popsection
ENTRY(save_rest)
PARTIAL_FRAME 1 REST_SKIP+8
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 3afb33f..2984486 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -19,6 +19,7 @@
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/list.h>
+#include <linux/module.h>
#include <trace/syscall.h>
@@ -49,6 +50,7 @@ static DEFINE_PER_CPU(int, save_modifying_code);
int ftrace_arch_code_modify_prepare(void)
{
set_kernel_text_rw();
+ set_all_modules_text_rw();
modifying_code = 1;
return 0;
}
@@ -56,6 +58,7 @@ int ftrace_arch_code_modify_prepare(void)
int ftrace_arch_code_modify_post_process(void)
{
modifying_code = 0;
+ set_all_modules_text_ro();
set_kernel_text_ro();
return 0;
}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index bcece91..9f54b20 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -60,16 +60,18 @@
#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
#endif
+/* Number of possible pages in the lowmem region */
+LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
+
/* Enough space to fit pagetables for the low memory linear map */
-MAPPING_BEYOND_END = \
- PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT
+MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
/*
* Worst-case size of the kernel mapping we need to make:
- * the worst-case size of the kernel itself, plus the extra we need
- * to map for the linear map.
+ * a relocatable kernel can live anywhere in lowmem, so we need to be able
+ * to map all of lowmem.
*/
-KERNEL_PAGES = (KERNEL_IMAGE_SIZE + MAPPING_BEYOND_END)>>PAGE_SHIFT
+KERNEL_PAGES = LOWMEM_PAGES
INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm
RESERVE_BRK(pagetables, INIT_MAP_SIZE)
@@ -137,39 +139,6 @@ ENTRY(startup_32)
movl %eax, pa(olpc_ofw_pgd)
#endif
-#ifdef CONFIG_PARAVIRT
- /* This is can only trip for a broken bootloader... */
- cmpw $0x207, pa(boot_params + BP_version)
- jb default_entry
-
- /* Paravirt-compatible boot parameters. Look to see what architecture
- we're booting under. */
- movl pa(boot_params + BP_hardware_subarch), %eax
- cmpl $num_subarch_entries, %eax
- jae bad_subarch
-
- movl pa(subarch_entries)(,%eax,4), %eax
- subl $__PAGE_OFFSET, %eax
- jmp *%eax
-
-bad_subarch:
-WEAK(lguest_entry)
-WEAK(xen_entry)
- /* Unknown implementation; there's really
- nothing we can do at this point. */
- ud2a
-
- __INITDATA
-
-subarch_entries:
- .long default_entry /* normal x86/PC */
- .long lguest_entry /* lguest hypervisor */
- .long xen_entry /* Xen hypervisor */
- .long default_entry /* Moorestown MID */
-num_subarch_entries = (. - subarch_entries) / 4
-.previous
-#endif /* CONFIG_PARAVIRT */
-
/*
* Initialize page tables. This creates a PDE and a set of page
* tables, which are located immediately beyond __brk_base. The variable
@@ -179,7 +148,6 @@ num_subarch_entries = (. - subarch_entries) / 4
*
* Note that the stack is not yet set up!
*/
-default_entry:
#ifdef CONFIG_X86_PAE
/*
@@ -259,7 +227,42 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
movl %eax,pa(initial_page_table+0xffc)
#endif
- jmp 3f
+
+#ifdef CONFIG_PARAVIRT
+ /* This is can only trip for a broken bootloader... */
+ cmpw $0x207, pa(boot_params + BP_version)
+ jb default_entry
+
+ /* Paravirt-compatible boot parameters. Look to see what architecture
+ we're booting under. */
+ movl pa(boot_params + BP_hardware_subarch), %eax
+ cmpl $num_subarch_entries, %eax
+ jae bad_subarch
+
+ movl pa(subarch_entries)(,%eax,4), %eax
+ subl $__PAGE_OFFSET, %eax
+ jmp *%eax
+
+bad_subarch:
+WEAK(lguest_entry)
+WEAK(xen_entry)
+ /* Unknown implementation; there's really
+ nothing we can do at this point. */
+ ud2a
+
+ __INITDATA
+
+subarch_entries:
+ .long default_entry /* normal x86/PC */
+ .long lguest_entry /* lguest hypervisor */
+ .long xen_entry /* Xen hypervisor */
+ .long default_entry /* Moorestown MID */
+num_subarch_entries = (. - subarch_entries) / 4
+.previous
+#else
+ jmp default_entry
+#endif /* CONFIG_PARAVIRT */
+
/*
* Non-boot CPU entry point; entered from trampoline.S
* We can't lgdt here, because lgdt itself uses a data segment, but
@@ -280,7 +283,7 @@ ENTRY(startup_32_smp)
movl %eax,%fs
movl %eax,%gs
#endif /* CONFIG_SMP */
-3:
+default_entry:
/*
* New page tables may be in 4Mbyte page mode and may
@@ -314,6 +317,10 @@ ENTRY(startup_32_smp)
subl $0x80000001, %eax
cmpl $(0x8000ffff-0x80000001), %eax
ja 6f
+
+ /* Clear bogus XD_DISABLE bits */
+ call verify_cpu
+
mov $0x80000001, %eax
cpuid
/* Execute Disable bit supported? */
@@ -609,6 +616,8 @@ ignore_int:
#endif
iret
+#include "verify_cpu.S"
+
__REFDATA
.align 4
ENTRY(initial_code)
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ae03cab..4ff5968 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -27,6 +27,9 @@
#define HPET_DEV_FSB_CAP 0x1000
#define HPET_DEV_PERI_CAP 0x2000
+#define HPET_MIN_CYCLES 128
+#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+
#define EVT_TO_HPET_DEV(evt) container_of(evt, struct hpet_dev, evt)
/*
@@ -299,8 +302,9 @@ static void hpet_legacy_clockevent_register(void)
/* Calculate the min / max delta */
hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
&hpet_clockevent);
- /* 5 usec minimum reprogramming delta. */
- hpet_clockevent.min_delta_ns = 5000;
+ /* Setup minimum reprogramming delta. */
+ hpet_clockevent.min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA,
+ &hpet_clockevent);
/*
* Start hpet with the boot cpu mask and make it
@@ -393,22 +397,24 @@ static int hpet_next_event(unsigned long delta,
* the wraparound into account) nor a simple count down event
* mode. Further the write to the comparator register is
* delayed internally up to two HPET clock cycles in certain
- * chipsets (ATI, ICH9,10). We worked around that by reading
- * back the compare register, but that required another
- * workaround for ICH9,10 chips where the first readout after
- * write can return the old stale value. We already have a
- * minimum delta of 5us enforced, but a NMI or SMI hitting
+ * chipsets (ATI, ICH9,10). Some newer AMD chipsets have even
+ * longer delays. We worked around that by reading back the
+ * compare register, but that required another workaround for
+ * ICH9,10 chips where the first readout after write can
+ * return the old stale value. We already had a minimum
+ * programming delta of 5us enforced, but a NMI or SMI hitting
* between the counter readout and the comparator write can
* move us behind that point easily. Now instead of reading
* the compare register back several times, we make the ETIME
* decision based on the following: Return ETIME if the
- * counter value after the write is less than 8 HPET cycles
+ * counter value after the write is less than HPET_MIN_CYCLES
* away from the event or if the counter is already ahead of
- * the event.
+ * the event. The minimum programming delta for the generic
+ * clockevents code is set to 1.5 * HPET_MIN_CYCLES.
*/
res = (s32)(cnt - hpet_readl(HPET_COUNTER));
- return res < 8 ? -ETIME : 0;
+ return res < HPET_MIN_CYCLES ? -ETIME : 0;
}
static void hpet_legacy_set_mode(enum clock_event_mode mode,
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index ff15c9d..42c5942 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -433,6 +433,10 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
dr6_p = (unsigned long *)ERR_PTR(args->err);
dr6 = *dr6_p;
+ /* If it's a single step, TRAP bits are random */
+ if (dr6 & DR_STEP)
+ return NOTIFY_DONE;
+
/* Do an early return if no trap bits are set in DR6 */
if ((dr6 & DR_TRAP_BITS) == 0)
return NOTIFY_DONE;
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index ec592ca..cd21b65 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -315,14 +315,18 @@ static void kgdb_remove_all_hw_break(void)
if (!breakinfo[i].enabled)
continue;
bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
- if (bp->attr.disabled == 1)
+ if (!bp->attr.disabled) {
+ arch_uninstall_hw_breakpoint(bp);
+ bp->attr.disabled = 1;
continue;
+ }
if (dbg_is_early)
early_dr7 &= ~encode_dr7(i, breakinfo[i].len,
breakinfo[i].type);
- else
- arch_uninstall_hw_breakpoint(bp);
- bp->attr.disabled = 1;
+ else if (hw_break_release_slot(i))
+ printk(KERN_ERR "KGDB: hw bpt remove failed %lx\n",
+ breakinfo[i].addr);
+ breakinfo[i].enabled = 0;
}
}
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 1cbd54c..5940282b 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -1184,6 +1184,10 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ /* This is possible if op is under delayed unoptimizing */
+ if (kprobe_disabled(&op->kp))
+ return;
+
preempt_disable();
if (kprobe_running()) {
kprobes_inc_nmissed_count(&op->kp);
@@ -1401,10 +1405,16 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
return 0;
}
-/* Replace a breakpoint (int3) with a relative jump. */
-int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
+#define MAX_OPTIMIZE_PROBES 256
+static struct text_poke_param *jump_poke_params;
+static struct jump_poke_buffer {
+ u8 buf[RELATIVEJUMP_SIZE];
+} *jump_poke_bufs;
+
+static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
+ u8 *insn_buf,
+ struct optimized_kprobe *op)
{
- unsigned char jmp_code[RELATIVEJUMP_SIZE];
s32 rel = (s32)((long)op->optinsn.insn -
((long)op->kp.addr + RELATIVEJUMP_SIZE));
@@ -1412,16 +1422,79 @@ int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
RELATIVE_ADDR_SIZE);
- jmp_code[0] = RELATIVEJUMP_OPCODE;
- *(s32 *)(&jmp_code[1]) = rel;
+ insn_buf[0] = RELATIVEJUMP_OPCODE;
+ *(s32 *)(&insn_buf[1]) = rel;
+
+ tprm->addr = op->kp.addr;
+ tprm->opcode = insn_buf;
+ tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Replace breakpoints (int3) with relative jumps.
+ * Caller must call with locking kprobe_mutex and text_mutex.
+ */
+void __kprobes arch_optimize_kprobes(struct list_head *oplist)
+{
+ struct optimized_kprobe *op, *tmp;
+ int c = 0;
+
+ list_for_each_entry_safe(op, tmp, oplist, list) {
+ WARN_ON(kprobe_disabled(&op->kp));
+ /* Setup param */
+ setup_optimize_kprobe(&jump_poke_params[c],
+ jump_poke_bufs[c].buf, op);
+ list_del_init(&op->list);
+ if (++c >= MAX_OPTIMIZE_PROBES)
+ break;
+ }
/*
* text_poke_smp doesn't support NMI/MCE code modifying.
* However, since kprobes itself also doesn't support NMI/MCE
* code probing, it's not a problem.
*/
- text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE);
- return 0;
+ text_poke_smp_batch(jump_poke_params, c);
+}
+
+static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
+ u8 *insn_buf,
+ struct optimized_kprobe *op)
+{
+ /* Set int3 to first byte for kprobes */
+ insn_buf[0] = BREAKPOINT_INSTRUCTION;
+ memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+
+ tprm->addr = op->kp.addr;
+ tprm->opcode = insn_buf;
+ tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Recover original instructions and breakpoints from relative jumps.
+ * Caller must call with locking kprobe_mutex.
+ */
+extern void arch_unoptimize_kprobes(struct list_head *oplist,
+ struct list_head *done_list)
+{
+ struct optimized_kprobe *op, *tmp;
+ int c = 0;
+
+ list_for_each_entry_safe(op, tmp, oplist, list) {
+ /* Setup param */
+ setup_unoptimize_kprobe(&jump_poke_params[c],
+ jump_poke_bufs[c].buf, op);
+ list_move(&op->list, done_list);
+ if (++c >= MAX_OPTIMIZE_PROBES)
+ break;
+ }
+
+ /*
+ * text_poke_smp doesn't support NMI/MCE code modifying.
+ * However, since kprobes itself also doesn't support NMI/MCE
+ * code probing, it's not a problem.
+ */
+ text_poke_smp_batch(jump_poke_params, c);
}
/* Replace a relative jump with a breakpoint (int3). */
@@ -1453,11 +1526,35 @@ static int __kprobes setup_detour_execution(struct kprobe *p,
}
return 0;
}
+
+static int __kprobes init_poke_params(void)
+{
+ /* Allocate code buffer and parameter array */
+ jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
+ MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+ if (!jump_poke_bufs)
+ return -ENOMEM;
+
+ jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
+ MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+ if (!jump_poke_params) {
+ kfree(jump_poke_bufs);
+ jump_poke_bufs = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+#else /* !CONFIG_OPTPROBES */
+static int __kprobes init_poke_params(void)
+{
+ return 0;
+}
#endif
int __init arch_init_kprobes(void)
{
- return 0;
+ return init_poke_params();
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index ce0cb47..0fe6d1a 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -155,12 +155,6 @@ static int apply_microcode_amd(int cpu)
return 0;
}
-static int get_ucode_data(void *to, const u8 *from, size_t n)
-{
- memcpy(to, from, n);
- return 0;
-}
-
static void *
get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
{
@@ -168,8 +162,7 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
void *mc;
- if (get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR))
- return NULL;
+ get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR);
if (section_hdr[0] != UCODE_UCODE_TYPE) {
pr_err("error: invalid type field in container file section header\n");
@@ -183,16 +176,13 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
return NULL;
}
- mc = vmalloc(UCODE_MAX_SIZE);
- if (mc) {
- memset(mc, 0, UCODE_MAX_SIZE);
- if (get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR,
- total_size)) {
- vfree(mc);
- mc = NULL;
- } else
- *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
- }
+ mc = vzalloc(UCODE_MAX_SIZE);
+ if (!mc)
+ return NULL;
+
+ get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size);
+ *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
+
return mc;
}
@@ -202,8 +192,7 @@ static int install_equiv_cpu_table(const u8 *buf)
unsigned int *buf_pos = (unsigned int *)container_hdr;
unsigned long size;
- if (get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE))
- return 0;
+ get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE);
size = buf_pos[2];
@@ -219,10 +208,7 @@ static int install_equiv_cpu_table(const u8 *buf)
}
buf += UCODE_CONTAINER_HEADER_SIZE;
- if (get_ucode_data(equiv_cpu_table, buf, size)) {
- vfree(equiv_cpu_table);
- return 0;
- }
+ get_ucode_data(equiv_cpu_table, buf, size);
return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */
}
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index dcb65cc..1a1b606 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -364,8 +364,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
/* For performance reasons, reuse mc area when possible */
if (!mc || mc_size > curr_mc_size) {
- if (mc)
- vfree(mc);
+ vfree(mc);
mc = vmalloc(mc_size);
if (!mc)
break;
@@ -374,13 +373,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
if (get_ucode_data(mc, ucode_ptr, mc_size) ||
microcode_sanity_check(mc) < 0) {
- vfree(mc);
break;
}
if (get_matching_microcode(&uci->cpu_sig, mc, new_rev)) {
- if (new_mc)
- vfree(new_mc);
+ vfree(new_mc);
new_rev = mc_header.rev;
new_mc = mc;
mc = NULL; /* trigger new vmalloc */
@@ -390,12 +387,10 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
leftover -= mc_size;
}
- if (mc)
- vfree(mc);
+ vfree(mc);
if (leftover) {
- if (new_mc)
- vfree(new_mc);
+ vfree(new_mc);
state = UCODE_ERROR;
goto out;
}
@@ -405,8 +400,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
goto out;
}
- if (uci->mc)
- vfree(uci->mc);
+ vfree(uci->mc);
uci->mc = (struct microcode_intel *)new_mc;
pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index 6da143c..ac861b8 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -25,7 +25,6 @@ struct pci_hostbridge_probe {
};
static u64 __cpuinitdata fam10h_pci_mmconf_base;
-static int __cpuinitdata fam10h_pci_mmconf_base_status;
static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = {
{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 },
@@ -44,10 +43,12 @@ static int __cpuinit cmp_range(const void *x1, const void *x2)
return start1 - start2;
}
-/*[47:0] */
-/* need to avoid (0xfd<<32) and (0xfe<<32), ht used space */
+#define MMCONF_UNIT (1ULL << FAM10H_MMIO_CONF_BASE_SHIFT)
+#define MMCONF_MASK (~(MMCONF_UNIT - 1))
+#define MMCONF_SIZE (MMCONF_UNIT << 8)
+/* need to avoid (0xfd<<32), (0xfe<<32), and (0xff<<32), ht used space */
#define FAM10H_PCI_MMCONF_BASE (0xfcULL<<32)
-#define BASE_VALID(b) ((b != (0xfdULL << 32)) && (b != (0xfeULL << 32)))
+#define BASE_VALID(b) ((b) + MMCONF_SIZE <= (0xfdULL<<32) || (b) >= (1ULL<<40))
static void __cpuinit get_fam10h_pci_mmconf_base(void)
{
int i;
@@ -64,12 +65,11 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
struct range range[8];
/* only try to get setting from BSP */
- /* -1 or 1 */
- if (fam10h_pci_mmconf_base_status)
+ if (fam10h_pci_mmconf_base)
return;
if (!early_pci_allowed())
- goto fail;
+ return;
found = 0;
for (i = 0; i < ARRAY_SIZE(pci_probes); i++) {
@@ -91,7 +91,7 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
}
if (!found)
- goto fail;
+ return;
/* SYS_CFG */
address = MSR_K8_SYSCFG;
@@ -99,16 +99,16 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
/* TOP_MEM2 is not enabled? */
if (!(val & (1<<21))) {
- tom2 = 0;
+ tom2 = 1ULL << 32;
} else {
/* TOP_MEM2 */
address = MSR_K8_TOP_MEM2;
rdmsrl(address, val);
- tom2 = val & (0xffffULL<<32);
+ tom2 = max(val & 0xffffff800000ULL, 1ULL << 32);
}
if (base <= tom2)
- base = tom2 + (1ULL<<32);
+ base = (tom2 + 2 * MMCONF_UNIT - 1) & MMCONF_MASK;
/*
* need to check if the range is in the high mmio range that is
@@ -123,11 +123,11 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
if (!(reg & 3))
continue;
- start = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/
+ start = (u64)(reg & 0xffffff00) << 8; /* 39:16 on 31:8*/
reg = read_pci_config(bus, slot, 1, 0x84 + (i << 3));
- end = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/
+ end = ((u64)(reg & 0xffffff00) << 8) | 0xffff; /* 39:16 on 31:8*/
- if (!end)
+ if (end < tom2)
continue;
range[hi_mmio_num].start = start;
@@ -143,32 +143,27 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
if (range[hi_mmio_num - 1].end < base)
goto out;
- if (range[0].start > base)
+ if (range[0].start > base + MMCONF_SIZE)
goto out;
/* need to find one window */
- base = range[0].start - (1ULL << 32);
+ base = (range[0].start & MMCONF_MASK) - MMCONF_UNIT;
if ((base > tom2) && BASE_VALID(base))
goto out;
- base = range[hi_mmio_num - 1].end + (1ULL << 32);
- if ((base > tom2) && BASE_VALID(base))
+ base = (range[hi_mmio_num - 1].end + MMCONF_UNIT) & MMCONF_MASK;
+ if (BASE_VALID(base))
goto out;
/* need to find window between ranges */
- if (hi_mmio_num > 1)
- for (i = 0; i < hi_mmio_num - 1; i++) {
- if (range[i + 1].start > (range[i].end + (1ULL << 32))) {
- base = range[i].end + (1ULL << 32);
- if ((base > tom2) && BASE_VALID(base))
- goto out;
- }
+ for (i = 1; i < hi_mmio_num; i++) {
+ base = (range[i - 1].end + MMCONF_UNIT) & MMCONF_MASK;
+ val = range[i].start & MMCONF_MASK;
+ if (val >= base + MMCONF_SIZE && BASE_VALID(base))
+ goto out;
}
-
-fail:
- fam10h_pci_mmconf_base_status = -1;
return;
+
out:
fam10h_pci_mmconf_base = base;
- fam10h_pci_mmconf_base_status = 1;
}
void __cpuinit fam10h_check_enable_mmcfg(void)
@@ -190,11 +185,10 @@ void __cpuinit fam10h_check_enable_mmcfg(void)
/* only trust the one handle 256 buses, if acpi=off */
if (!acpi_pci_disabled || busnbits >= 8) {
- u64 base;
- base = val & (0xffffULL << 32);
- if (fam10h_pci_mmconf_base_status <= 0) {
+ u64 base = val & MMCONF_MASK;
+
+ if (!fam10h_pci_mmconf_base) {
fam10h_pci_mmconf_base = base;
- fam10h_pci_mmconf_base_status = 1;
return;
} else if (fam10h_pci_mmconf_base == base)
return;
@@ -206,8 +200,10 @@ void __cpuinit fam10h_check_enable_mmcfg(void)
* with 256 buses
*/
get_fam10h_pci_mmconf_base();
- if (fam10h_pci_mmconf_base_status <= 0)
+ if (!fam10h_pci_mmconf_base) {
+ pci_probe &= ~PCI_CHECK_ENABLE_AMD_MMCONF;
return;
+ }
printk(KERN_INFO "Enable MMCONFIG on AMD Family 10h\n");
val &= ~((FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT) |
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 7bf2dc4..12fcbe2 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -30,7 +30,6 @@
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/smp.h>
-#include <linux/smp_lock.h>
#include <linux/major.h>
#include <linux/fs.h>
#include <linux/device.h>
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 57d1868..c852041 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -91,8 +91,7 @@ void exit_thread(void)
void show_regs(struct pt_regs *regs)
{
show_registers(regs);
- show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs),
- regs->bp);
+ show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs));
}
void show_regs_common(void)
@@ -374,6 +373,7 @@ void default_idle(void)
{
if (hlt_use_halt()) {
trace_power_start(POWER_CSTATE, 1, smp_processor_id());
+ trace_cpu_idle(1, smp_processor_id());
current_thread_info()->status &= ~TS_POLLING;
/*
* TS_POLLING-cleared state must be visible before we
@@ -444,6 +444,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
{
trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id());
+ trace_cpu_idle((ax>>4)+1, smp_processor_id());
if (!need_resched()) {
if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
clflush((void *)&current_thread_info()->flags);
@@ -460,6 +461,7 @@ static void mwait_idle(void)
{
if (!need_resched()) {
trace_power_start(POWER_CSTATE, 1, smp_processor_id());
+ trace_cpu_idle(1, smp_processor_id());
if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
clflush((void *)&current_thread_info()->flags);
@@ -481,10 +483,12 @@ static void mwait_idle(void)
static void poll_idle(void)
{
trace_power_start(POWER_CSTATE, 0, smp_processor_id());
+ trace_cpu_idle(0, smp_processor_id());
local_irq_enable();
while (!need_resched())
cpu_relax();
- trace_power_end(0);
+ trace_power_end(smp_processor_id());
+ trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
}
/*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 96586c3..4b9befa 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -113,8 +113,8 @@ void cpu_idle(void)
stop_critical_timings();
pm_idle();
start_critical_timings();
-
trace_power_end(smp_processor_id());
+ trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
}
tick_nohz_restart_sched_tick();
preempt_enable_no_resched();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b3d7a3a..4c818a7 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -142,6 +142,8 @@ void cpu_idle(void)
start_critical_timings();
trace_power_end(smp_processor_id());
+ trace_cpu_idle(PWR_EVENT_EXIT,
+ smp_processor_id());
/* In many cases the interrupt that ended idle
has already called exit_idle. But some idle
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 008b91e..42eb330 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -83,6 +83,11 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src)
static atomic64_t last_value = ATOMIC64_INIT(0);
+void pvclock_resume(void)
+{
+ atomic64_set(&last_value, 0);
+}
+
cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
{
struct pvclock_shadow_time shadow;
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
new file mode 100644
index 0000000..2a26819
--- /dev/null
+++ b/arch/x86/kernel/resource.c
@@ -0,0 +1,48 @@
+#include <linux/ioport.h>
+#include <asm/e820.h>
+
+static void resource_clip(struct resource *res, resource_size_t start,
+ resource_size_t end)
+{
+ resource_size_t low = 0, high = 0;
+
+ if (res->end < start || res->start > end)
+ return; /* no conflict */
+
+ if (res->start < start)
+ low = start - res->start;
+
+ if (res->end > end)
+ high = res->end - end;
+
+ /* Keep the area above or below the conflict, whichever is larger */
+ if (low > high)
+ res->end = start - 1;
+ else
+ res->start = end + 1;
+}
+
+static void remove_e820_regions(struct resource *avail)
+{
+ int i;
+ struct e820entry *entry;
+
+ for (i = 0; i < e820.nr_map; i++) {
+ entry = &e820.map[i];
+
+ resource_clip(avail, entry->addr,
+ entry->addr + entry->size - 1);
+ }
+}
+
+void arch_remove_reservations(struct resource *avail)
+{
+ /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+ if (avail->flags & IORESOURCE_MEM) {
+ if (avail->start < BIOS_END)
+ avail->start = BIOS_END;
+ resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
+
+ remove_e820_regions(avail);
+ }
+}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0afb8c7..d3cfe26c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -501,7 +501,18 @@ static inline unsigned long long get_total_mem(void)
return total << PAGE_SHIFT;
}
-#define DEFAULT_BZIMAGE_ADDR_MAX 0x37FFFFFF
+/*
+ * Keep the crash kernel below this limit. On 32 bits earlier kernels
+ * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this
+ * limit once kexec-tools are fixed.
+ */
+#ifdef CONFIG_X86_32
+# define CRASH_KERNEL_ADDR_MAX (512 << 20)
+#else
+# define CRASH_KERNEL_ADDR_MAX (896 << 20)
+#endif
+
static void __init reserve_crashkernel(void)
{
unsigned long long total_mem;
@@ -520,10 +531,10 @@ static void __init reserve_crashkernel(void)
const unsigned long long alignment = 16<<20; /* 16M */
/*
- * kexec want bzImage is below DEFAULT_BZIMAGE_ADDR_MAX
+ * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
*/
crash_base = memblock_find_in_range(alignment,
- DEFAULT_BZIMAGE_ADDR_MAX, crash_size, alignment);
+ CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
if (crash_base == MEMBLOCK_ERROR) {
pr_info("crashkernel reservation failed - No suitable area found.\n");
@@ -769,7 +780,6 @@ void __init setup_arch(char **cmdline_p)
x86_init.oem.arch_setup();
- resource_alloc_from_bottom = 0;
iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
setup_memory_map();
parse_setup_data();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 083e99d..ee886fe 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -281,6 +281,13 @@ static void __cpuinit smp_callin(void)
*/
smp_store_cpu_info(cpuid);
+ /*
+ * This must be done before setting cpu_online_mask
+ * or calling notify_cpu_starting.
+ */
+ set_cpu_sibling_map(raw_smp_processor_id());
+ wmb();
+
notify_cpu_starting(cpuid);
/*
@@ -316,16 +323,6 @@ notrace static void __cpuinit start_secondary(void *unused)
*/
check_tsc_sync_target();
- if (nmi_watchdog == NMI_IO_APIC) {
- legacy_pic->mask(0);
- enable_NMI_through_LVT0();
- legacy_pic->unmask(0);
- }
-
- /* This must be done before setting cpu_online_mask */
- set_cpu_sibling_map(raw_smp_processor_id());
- wmb();
-
/*
* We need to hold call_lock, so there is no inconsistency
* between the time smp_call_function() determines number of
@@ -1061,8 +1058,6 @@ static int __init smp_sanity_check(unsigned max_cpus)
printk(KERN_INFO "SMP mode deactivated.\n");
smpboot_clear_io_apic();
- localise_nmi_watchdog();
-
connect_bsp_APIC();
setup_local_APIC();
end_local_APIC_setup();
@@ -1166,6 +1161,20 @@ out:
preempt_enable();
}
+void arch_disable_nonboot_cpus_begin(void)
+{
+ /*
+ * Avoid the smp alternatives switch during the disable_nonboot_cpus().
+ * In the suspend path, we will be back in the SMP mode shortly anyways.
+ */
+ skip_smp_alternatives = true;
+}
+
+void arch_disable_nonboot_cpus_end(void)
+{
+ skip_smp_alternatives = false;
+}
+
void arch_enable_nonboot_cpus_begin(void)
{
set_mtrr_aps_delayed_init();
@@ -1196,7 +1205,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
#ifdef CONFIG_X86_IO_APIC
setup_ioapic_dest();
#endif
- check_nmi_watchdog();
mtrr_aps_init();
}
@@ -1341,8 +1349,6 @@ int native_cpu_disable(void)
if (cpu == 0)
return -EBUSY;
- if (nmi_watchdog == NMI_LOCAL_APIC)
- stop_apic_nmi_watchdog(NULL);
clear_local_APIC();
cpu_disable_common();
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index b53c525..938c8e1 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -73,22 +73,22 @@ static const struct stacktrace_ops save_stack_ops_nosched = {
*/
void save_stack_trace(struct stack_trace *trace)
{
- dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace);
+ dump_trace(current, NULL, NULL, &save_stack_ops, trace);
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace);
-void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp)
+void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs)
{
- dump_trace(current, NULL, NULL, bp, &save_stack_ops, trace);
+ dump_trace(current, regs, NULL, &save_stack_ops, trace);
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
- dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace);
+ dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace);
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index fb5cc5e1..25a28a2 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -22,10 +22,6 @@
#include <asm/hpet.h>
#include <asm/time.h>
-#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC)
-int timer_ack;
-#endif
-
#ifdef CONFIG_X86_64
volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
#endif
@@ -63,20 +59,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
/* Keep nmi watchdog up to date */
inc_irq_stat(irq0_irqs);
- /* Optimized out for !IO_APIC and x86_64 */
- if (timer_ack) {
- /*
- * Subtle, when I/O APICs are used we have to ack timer IRQ
- * manually to deassert NMI lines for the watchdog if run
- * on an 82489DX-based system.
- */
- raw_spin_lock(&i8259A_lock);
- outb(0x0c, PIC_MASTER_OCW3);
- /* Ack the IRQ; AEOI will end it automatically. */
- inb(PIC_MASTER_POLL);
- raw_spin_unlock(&i8259A_lock);
- }
-
global_clock_event->event_handler(global_clock_event);
/* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 3af2dff..075d130 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -127,7 +127,7 @@ startup_64:
no_longmode:
hlt
jmp no_longmode
-#include "verify_cpu_64.S"
+#include "verify_cpu.S"
# Careful these need to be in the same 64K segment as the above;
tidt:
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index cb838ca..c76aaca 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -83,6 +83,8 @@ EXPORT_SYMBOL_GPL(used_vectors);
static int ignore_nmis;
+int unknown_nmi_panic;
+
static inline void conditional_sti(struct pt_regs *regs)
{
if (regs->flags & X86_EFLAGS_IF)
@@ -300,6 +302,13 @@ gp_in_kernel:
die("general protection fault", regs, error_code);
}
+static int __init setup_unknown_nmi_panic(char *str)
+{
+ unknown_nmi_panic = 1;
+ return 1;
+}
+__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
+
static notrace __kprobes void
mem_parity_error(unsigned char reason, struct pt_regs *regs)
{
@@ -342,9 +351,11 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
reason = (reason & 0xf) | 8;
outb(reason, 0x61);
- i = 2000;
- while (--i)
- udelay(1000);
+ i = 20000;
+ while (--i) {
+ touch_nmi_watchdog();
+ udelay(100);
+ }
reason &= ~8;
outb(reason, 0x61);
@@ -371,7 +382,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
reason, smp_processor_id());
printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
- if (panic_on_unrecovered_nmi)
+ if (unknown_nmi_panic || panic_on_unrecovered_nmi)
panic("NMI: Not continuing");
printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
@@ -397,20 +408,8 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
== NOTIFY_STOP)
return;
-
-#ifndef CONFIG_LOCKUP_DETECTOR
- /*
- * Ok, so this is none of the documented NMI sources,
- * so it must be the NMI watchdog.
- */
- if (nmi_watchdog_tick(regs, reason))
- return;
- if (!do_nmi_callback(regs, cpu))
-#endif /* !CONFIG_LOCKUP_DETECTOR */
- unknown_nmi_error(reason, regs);
-#else
- unknown_nmi_error(reason, regs);
#endif
+ unknown_nmi_error(reason, regs);
return;
}
@@ -446,14 +445,12 @@ do_nmi(struct pt_regs *regs, long error_code)
void stop_nmi(void)
{
- acpi_nmi_disable();
ignore_nmis++;
}
void restart_nmi(void)
{
ignore_nmis--;
- acpi_nmi_enable();
}
/* May run on IST stack. */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 0c40d8b..356a0d4 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -872,6 +872,9 @@ __cpuinit int unsynchronized_tsc(void)
if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
return 0;
+
+ if (tsc_clocksource_reliable)
+ return 0;
/*
* Intel systems are normally all synchronized.
* Exceptions must mark TSC as unstable:
@@ -879,14 +882,92 @@ __cpuinit int unsynchronized_tsc(void)
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
/* assume multi socket systems are not synchronized: */
if (num_possible_cpus() > 1)
- tsc_unstable = 1;
+ return 1;
}
- return tsc_unstable;
+ return 0;
+}
+
+
+static void tsc_refine_calibration_work(struct work_struct *work);
+static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
+/**
+ * tsc_refine_calibration_work - Further refine tsc freq calibration
+ * @work - ignored.
+ *
+ * This functions uses delayed work over a period of a
+ * second to further refine the TSC freq value. Since this is
+ * timer based, instead of loop based, we don't block the boot
+ * process while this longer calibration is done.
+ *
+ * If there are any calibration anomolies (too many SMIs, etc),
+ * or the refined calibration is off by 1% of the fast early
+ * calibration, we throw out the new calibration and use the
+ * early calibration.
+ */
+static void tsc_refine_calibration_work(struct work_struct *work)
+{
+ static u64 tsc_start = -1, ref_start;
+ static int hpet;
+ u64 tsc_stop, ref_stop, delta;
+ unsigned long freq;
+
+ /* Don't bother refining TSC on unstable systems */
+ if (check_tsc_unstable())
+ goto out;
+
+ /*
+ * Since the work is started early in boot, we may be
+ * delayed the first time we expire. So set the workqueue
+ * again once we know timers are working.
+ */
+ if (tsc_start == -1) {
+ /*
+ * Only set hpet once, to avoid mixing hardware
+ * if the hpet becomes enabled later.
+ */
+ hpet = is_hpet_enabled();
+ schedule_delayed_work(&tsc_irqwork, HZ);
+ tsc_start = tsc_read_refs(&ref_start, hpet);
+ return;
+ }
+
+ tsc_stop = tsc_read_refs(&ref_stop, hpet);
+
+ /* hpet or pmtimer available ? */
+ if (!hpet && !ref_start && !ref_stop)
+ goto out;
+
+ /* Check, whether the sampling was disturbed by an SMI */
+ if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
+ goto out;
+
+ delta = tsc_stop - tsc_start;
+ delta *= 1000000LL;
+ if (hpet)
+ freq = calc_hpet_ref(delta, ref_start, ref_stop);
+ else
+ freq = calc_pmtimer_ref(delta, ref_start, ref_stop);
+
+ /* Make sure we're within 1% */
+ if (abs(tsc_khz - freq) > tsc_khz/100)
+ goto out;
+
+ tsc_khz = freq;
+ printk(KERN_INFO "Refined TSC clocksource calibration: "
+ "%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000,
+ (unsigned long)tsc_khz % 1000);
+
+out:
+ clocksource_register_khz(&clocksource_tsc, tsc_khz);
}
-static void __init init_tsc_clocksource(void)
+
+static int __init init_tsc_clocksource(void)
{
+ if (!cpu_has_tsc || tsc_disabled > 0)
+ return 0;
+
if (tsc_clocksource_reliable)
clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
/* lower the rating if we already know its unstable: */
@@ -894,8 +975,14 @@ static void __init init_tsc_clocksource(void)
clocksource_tsc.rating = 0;
clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
}
- clocksource_register_khz(&clocksource_tsc, tsc_khz);
+ schedule_delayed_work(&tsc_irqwork, 0);
+ return 0;
}
+/*
+ * We use device_initcall here, to ensure we run after the hpet
+ * is fully initialized, which may occur at fs_initcall time.
+ */
+device_initcall(init_tsc_clocksource);
void __init tsc_init(void)
{
@@ -949,6 +1036,5 @@ void __init tsc_init(void)
mark_tsc_unstable("TSCs unsynchronized");
check_system_tsc_reliable();
- init_tsc_clocksource();
}
diff --git a/arch/x86/kernel/verify_cpu_64.S b/arch/x86/kernel/verify_cpu.S
index 56a8c2a..0edefc1 100644
--- a/arch/x86/kernel/verify_cpu_64.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -7,6 +7,7 @@
* Copyright (c) 2007 Andi Kleen (ak@suse.de)
* Copyright (c) 2007 Eric Biederman (ebiederm@xmission.com)
* Copyright (c) 2007 Vivek Goyal (vgoyal@in.ibm.com)
+ * Copyright (c) 2010 Kees Cook (kees.cook@canonical.com)
*
* This source code is licensed under the GNU General Public License,
* Version 2. See the file COPYING for more details.
@@ -14,18 +15,17 @@
* This is a common code for verification whether CPU supports
* long mode and SSE or not. It is not called directly instead this
* file is included at various places and compiled in that context.
- * Following are the current usage.
+ * This file is expected to run in 32bit code. Currently:
*
- * This file is included by both 16bit and 32bit code.
+ * arch/x86/boot/compressed/head_64.S: Boot cpu verification
+ * arch/x86/kernel/trampoline_64.S: secondary processor verfication
+ * arch/x86/kernel/head_32.S: processor startup
*
- * arch/x86_64/boot/setup.S : Boot cpu verification (16bit)
- * arch/x86_64/boot/compressed/head.S: Boot cpu verification (32bit)
- * arch/x86_64/kernel/trampoline.S: secondary processor verfication (16bit)
- * arch/x86_64/kernel/acpi/wakeup.S:Verfication at resume (16bit)
- *
- * verify_cpu, returns the status of cpu check in register %eax.
+ * verify_cpu, returns the status of longmode and SSE in register %eax.
* 0: Success 1: Failure
*
+ * On Intel, the XD_DISABLE flag will be cleared as a side-effect.
+ *
* The caller needs to check for the error code and take the action
* appropriately. Either display a message or halt.
*/
@@ -62,8 +62,41 @@ verify_cpu:
cmpl $0x444d4163,%ecx
jnz verify_cpu_noamd
mov $1,%di # cpu is from AMD
+ jmp verify_cpu_check
verify_cpu_noamd:
+ cmpl $0x756e6547,%ebx # GenuineIntel?
+ jnz verify_cpu_check
+ cmpl $0x49656e69,%edx
+ jnz verify_cpu_check
+ cmpl $0x6c65746e,%ecx
+ jnz verify_cpu_check
+
+ # only call IA32_MISC_ENABLE when:
+ # family > 6 || (family == 6 && model >= 0xd)
+ movl $0x1, %eax # check CPU family and model
+ cpuid
+ movl %eax, %ecx
+
+ andl $0x0ff00f00, %eax # mask family and extended family
+ shrl $8, %eax
+ cmpl $6, %eax
+ ja verify_cpu_clear_xd # family > 6, ok
+ jb verify_cpu_check # family < 6, skip
+
+ andl $0x000f00f0, %ecx # mask model and extended model
+ shrl $4, %ecx
+ cmpl $0xd, %ecx
+ jb verify_cpu_check # family == 6, model < 0xd, skip
+
+verify_cpu_clear_xd:
+ movl $MSR_IA32_MISC_ENABLE, %ecx
+ rdmsr
+ btrl $2, %edx # clear MSR_IA32_MISC_ENABLE_XD_DISABLE
+ jnc verify_cpu_check # only write MSR if bit was changed
+ wrmsr
+
+verify_cpu_check:
movl $0x1,%eax # Does the cpu have what it takes
cpuid
andl $REQUIRED_MASK0,%edx
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index e03530a..bf47007 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -69,7 +69,7 @@ jiffies_64 = jiffies;
PHDRS {
text PT_LOAD FLAGS(5); /* R_E */
- data PT_LOAD FLAGS(7); /* RWE */
+ data PT_LOAD FLAGS(6); /* RW_ */
#ifdef CONFIG_X86_64
user PT_LOAD FLAGS(5); /* R_E */
#ifdef CONFIG_SMP
@@ -116,6 +116,10 @@ SECTIONS
EXCEPTION_TABLE(16) :text = 0x9090
+#if defined(CONFIG_DEBUG_RODATA)
+ /* .text should occupy whole number of pages */
+ . = ALIGN(PAGE_SIZE);
+#endif
X64_ALIGN_DEBUG_RODATA_BEGIN
RO_DATA(PAGE_SIZE)
X64_ALIGN_DEBUG_RODATA_END
@@ -335,7 +339,7 @@ SECTIONS
__bss_start = .;
*(.bss..page_aligned)
*(.bss)
- . = ALIGN(4);
+ . = ALIGN(PAGE_SIZE);
__bss_stop = .;
}
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 9c253bd..5471285 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -394,7 +394,8 @@ static void __init setup_xstate_init(void)
* Setup init_xstate_buf to represent the init state of
* all the features managed by the xsave
*/
- init_xstate_buf = alloc_bootmem(xstate_size);
+ init_xstate_buf = alloc_bootmem_align(xstate_size,
+ __alignof__(struct xsave_struct));
init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;
clts();