summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/acpi/boot.c6
-rw-r--r--arch/x86/kernel/acpi/sleep.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c3
-rw-r--r--arch/x86/kernel/cpu/amd.c14
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c31
-rw-r--r--arch/x86/kernel/cpu/perf_event.c131
-rw-r--r--arch/x86/kernel/cpu/perf_event.h5
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c9
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c9
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c45
-rw-r--r--arch/x86/kernel/cpu/perf_event_knc.c93
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c129
-rw-r--r--arch/x86/kernel/e820.c3
-rw-r--r--arch/x86/kernel/entry_64.S16
-rw-r--r--arch/x86/kernel/head_32.S9
-rw-r--r--arch/x86/kernel/microcode_amd.c8
-rw-r--r--arch/x86/kernel/ptrace.c42
-rw-r--r--arch/x86/kernel/rtc.c6
-rw-r--r--arch/x86/kernel/setup.c27
-rw-r--r--arch/x86/kernel/signal.c5
-rw-r--r--arch/x86/kernel/smpboot.c5
-rw-r--r--arch/x86/kernel/sys_x86_64.c151
-rw-r--r--arch/x86/kernel/trace_clock.c21
-rw-r--r--arch/x86/kernel/traps.c2
-rw-r--r--arch/x86/kernel/tsc.c6
-rw-r--r--arch/x86/kernel/uprobes.c54
28 files changed, 588 insertions, 248 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 91ce48f05f9..34e923a5376 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -9,7 +9,6 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
ifdef CONFIG_FUNCTION_TRACER
# Do not profile debug and lowlevel utilities
CFLAGS_REMOVE_tsc.o = -pg
-CFLAGS_REMOVE_rtc.o = -pg
CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
CFLAGS_REMOVE_pvclock.o = -pg
CFLAGS_REMOVE_kvmclock.o = -pg
@@ -62,6 +61,7 @@ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
+obj-$(CONFIG_X86_TSC) += trace_clock.o
obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o
obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index e651f7a589a..e48cafcf92a 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -574,6 +574,12 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
return irq;
}
+EXPORT_SYMBOL_GPL(acpi_register_gsi);
+
+void acpi_unregister_gsi(u32 gsi)
+{
+}
+EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
void __init acpi_set_irq_model_pic(void)
{
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 11676cf65ae..d5e0d717005 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -101,6 +101,8 @@ static int __init acpi_sleep_setup(char *str)
#endif
if (strncmp(str, "nonvs", 5) == 0)
acpi_nvs_nosave();
+ if (strncmp(str, "nonvs_s3", 8) == 0)
+ acpi_nvs_nosave_s3();
if (strncmp(str, "old_ordering", 12) == 0)
acpi_old_suspend_ordering();
str = strchr(str, ',');
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c265593ec2c..1817fa91102 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2257,6 +2257,9 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
continue;
cfg = irq_cfg(irq);
+ if (!cfg)
+ continue;
+
raw_spin_lock(&desc->lock);
/*
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f7e98a2c0d1..1b7d1656a04 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -631,6 +631,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
}
}
+ /*
+ * The way access filter has a performance penalty on some workloads.
+ * Disable it on the affected CPUs.
+ */
+ if ((c->x86 == 0x15) &&
+ (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+ u64 val;
+
+ if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+ val |= 0x1E;
+ wrmsrl_safe(0xc0011021, val);
+ }
+ }
+
cpu_detect_cache_sizes(c);
/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 698b6ec12e0..1ac581f38df 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -6,7 +6,7 @@
*
* Written by Jacob Shin - AMD, Inc.
*
- * Support: borislav.petkov@amd.com
+ * Maintained by: Borislav Petkov <bp@alien8.de>
*
* April 2006
* - added support for AMD Family 0x10 processors
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 5f88abf07e9..4f9a3cbfc4a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -285,34 +285,39 @@ void cmci_clear(void)
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
+static long cmci_rediscover_work_func(void *arg)
+{
+ int banks;
+
+ /* Recheck banks in case CPUs don't all have the same */
+ if (cmci_supported(&banks))
+ cmci_discover(banks);
+
+ return 0;
+}
+
/*
* After a CPU went down cycle through all the others and rediscover
* Must run in process context.
*/
void cmci_rediscover(int dying)
{
- int banks;
- int cpu;
- cpumask_var_t old;
+ int cpu, banks;
if (!cmci_supported(&banks))
return;
- if (!alloc_cpumask_var(&old, GFP_KERNEL))
- return;
- cpumask_copy(old, &current->cpus_allowed);
for_each_online_cpu(cpu) {
if (cpu == dying)
continue;
- if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
+
+ if (cpu == smp_processor_id()) {
+ cmci_rediscover_work_func(NULL);
continue;
- /* Recheck banks in case CPUs don't all have the same */
- if (cmci_supported(&banks))
- cmci_discover(banks);
- }
+ }
- set_cpus_allowed_ptr(current, old);
- free_cpumask_var(old);
+ work_on_cpu(cpu, cmci_rediscover_work_func, NULL);
+ }
}
/*
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3373f84d139..4428fd178bc 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -208,12 +208,14 @@ static bool check_hw_exists(void)
}
/*
- * 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.
+ * Read the current value, change it 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;
reg = x86_pmu_event_addr(0);
+ if (rdmsrl_safe(reg, &val))
+ goto msr_fail;
+ val ^= 0xffffUL;
ret = wrmsrl_safe(reg, val);
ret |= rdmsrl_safe(reg, &val_new);
if (ret || val != val_new)
@@ -1314,6 +1316,121 @@ static struct attribute_group x86_pmu_format_group = {
.attrs = NULL,
};
+struct perf_pmu_events_attr {
+ struct device_attribute attr;
+ u64 id;
+};
+
+/*
+ * Remove all undefined events (x86_pmu.event_map(id) == 0)
+ * out of events_attr attributes.
+ */
+static void __init filter_events(struct attribute **attrs)
+{
+ int i, j;
+
+ for (i = 0; attrs[i]; i++) {
+ if (x86_pmu.event_map(i))
+ continue;
+
+ for (j = i; attrs[j]; j++)
+ attrs[j] = attrs[j + 1];
+
+ /* Check the shifted attr. */
+ i--;
+ }
+}
+
+static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+ char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr = \
+ container_of(attr, struct perf_pmu_events_attr, attr);
+
+ u64 config = x86_pmu.event_map(pmu_attr->id);
+ return x86_pmu.events_sysfs_show(page, config);
+}
+
+#define EVENT_VAR(_id) event_attr_##_id
+#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
+
+#define EVENT_ATTR(_name, _id) \
+static struct perf_pmu_events_attr EVENT_VAR(_id) = { \
+ .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \
+ .id = PERF_COUNT_HW_##_id, \
+};
+
+EVENT_ATTR(cpu-cycles, CPU_CYCLES );
+EVENT_ATTR(instructions, INSTRUCTIONS );
+EVENT_ATTR(cache-references, CACHE_REFERENCES );
+EVENT_ATTR(cache-misses, CACHE_MISSES );
+EVENT_ATTR(branch-instructions, BRANCH_INSTRUCTIONS );
+EVENT_ATTR(branch-misses, BRANCH_MISSES );
+EVENT_ATTR(bus-cycles, BUS_CYCLES );
+EVENT_ATTR(stalled-cycles-frontend, STALLED_CYCLES_FRONTEND );
+EVENT_ATTR(stalled-cycles-backend, STALLED_CYCLES_BACKEND );
+EVENT_ATTR(ref-cycles, REF_CPU_CYCLES );
+
+static struct attribute *empty_attrs;
+
+static struct attribute *events_attr[] = {
+ EVENT_PTR(CPU_CYCLES),
+ EVENT_PTR(INSTRUCTIONS),
+ EVENT_PTR(CACHE_REFERENCES),
+ EVENT_PTR(CACHE_MISSES),
+ EVENT_PTR(BRANCH_INSTRUCTIONS),
+ EVENT_PTR(BRANCH_MISSES),
+ EVENT_PTR(BUS_CYCLES),
+ EVENT_PTR(STALLED_CYCLES_FRONTEND),
+ EVENT_PTR(STALLED_CYCLES_BACKEND),
+ EVENT_PTR(REF_CPU_CYCLES),
+ NULL,
+};
+
+static struct attribute_group x86_pmu_events_group = {
+ .name = "events",
+ .attrs = events_attr,
+};
+
+ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event)
+{
+ u64 umask = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
+ u64 cmask = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24;
+ bool edge = (config & ARCH_PERFMON_EVENTSEL_EDGE);
+ bool pc = (config & ARCH_PERFMON_EVENTSEL_PIN_CONTROL);
+ bool any = (config & ARCH_PERFMON_EVENTSEL_ANY);
+ bool inv = (config & ARCH_PERFMON_EVENTSEL_INV);
+ ssize_t ret;
+
+ /*
+ * We have whole page size to spend and just little data
+ * to write, so we can safely use sprintf.
+ */
+ ret = sprintf(page, "event=0x%02llx", event);
+
+ if (umask)
+ ret += sprintf(page + ret, ",umask=0x%02llx", umask);
+
+ if (edge)
+ ret += sprintf(page + ret, ",edge");
+
+ if (pc)
+ ret += sprintf(page + ret, ",pc");
+
+ if (any)
+ ret += sprintf(page + ret, ",any");
+
+ if (inv)
+ ret += sprintf(page + ret, ",inv");
+
+ if (cmask)
+ ret += sprintf(page + ret, ",cmask=0x%02llx", cmask);
+
+ ret += sprintf(page + ret, "\n");
+
+ return ret;
+}
+
static int __init init_hw_perf_events(void)
{
struct x86_pmu_quirk *quirk;
@@ -1360,6 +1477,11 @@ static int __init init_hw_perf_events(void)
x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
+ if (!x86_pmu.events_sysfs_show)
+ x86_pmu_events_group.attrs = &empty_attrs;
+ else
+ filter_events(x86_pmu_events_group.attrs);
+
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
pr_info("... generic registers: %d\n", x86_pmu.num_counters);
@@ -1649,6 +1771,7 @@ static struct attribute_group x86_pmu_attr_group = {
static const struct attribute_group *x86_pmu_attr_groups[] = {
&x86_pmu_attr_group,
&x86_pmu_format_group,
+ &x86_pmu_events_group,
NULL,
};
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 271d2570029..115c1ea9774 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -354,6 +354,8 @@ struct x86_pmu {
int attr_rdpmc;
struct attribute **format_attrs;
+ ssize_t (*events_sysfs_show)(char *page, u64 config);
+
/*
* CPU Hotplug hooks
*/
@@ -536,6 +538,9 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
regs->ip = ip;
}
+ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
+ssize_t intel_event_sysfs_show(char *page, u64 config);
+
#ifdef CONFIG_CPU_SUP_AMD
int amd_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 4528ae7b6ec..c93bc4e813a 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -568,6 +568,14 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev
}
}
+static ssize_t amd_event_sysfs_show(char *page, u64 config)
+{
+ u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) |
+ (config & AMD64_EVENTSEL_EVENT) >> 24;
+
+ return x86_event_sysfs_show(page, config, event);
+}
+
static __initconst const struct x86_pmu amd_pmu = {
.name = "AMD",
.handle_irq = x86_pmu_handle_irq,
@@ -591,6 +599,7 @@ static __initconst const struct x86_pmu amd_pmu = {
.put_event_constraints = amd_put_event_constraints,
.format_attrs = amd_format_attr,
+ .events_sysfs_show = amd_event_sysfs_show,
.cpu_prepare = amd_pmu_cpu_prepare,
.cpu_starting = amd_pmu_cpu_starting,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 324bb523d9d..93b9e1181f8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1603,6 +1603,13 @@ static struct attribute *intel_arch_formats_attr[] = {
NULL,
};
+ssize_t intel_event_sysfs_show(char *page, u64 config)
+{
+ u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT);
+
+ return x86_event_sysfs_show(page, config, event);
+}
+
static __initconst const struct x86_pmu core_pmu = {
.name = "core",
.handle_irq = x86_pmu_handle_irq,
@@ -1628,6 +1635,7 @@ static __initconst const struct x86_pmu core_pmu = {
.event_constraints = intel_core_event_constraints,
.guest_get_msrs = core_guest_get_msrs,
.format_attrs = intel_arch_formats_attr,
+ .events_sysfs_show = intel_event_sysfs_show,
};
struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1766,6 +1774,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.pebs_aliases = intel_pebs_aliases_core2,
.format_attrs = intel_arch3_formats_attr,
+ .events_sysfs_show = intel_event_sysfs_show,
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 5df8d32ba91..3cf3d97cce3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -118,22 +118,24 @@ static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
int box_ctl = uncore_pci_box_ctl(box);
- u32 config;
+ u32 config = 0;
- pci_read_config_dword(pdev, box_ctl, &config);
- config |= SNBEP_PMON_BOX_CTL_FRZ;
- pci_write_config_dword(pdev, box_ctl, config);
+ if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ pci_write_config_dword(pdev, box_ctl, config);
+ }
}
static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
int box_ctl = uncore_pci_box_ctl(box);
- u32 config;
+ u32 config = 0;
- pci_read_config_dword(pdev, box_ctl, &config);
- config &= ~SNBEP_PMON_BOX_CTL_FRZ;
- pci_write_config_dword(pdev, box_ctl, config);
+ if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ pci_write_config_dword(pdev, box_ctl, config);
+ }
}
static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
@@ -156,7 +158,7 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe
{
struct pci_dev *pdev = box->pci_dev;
struct hw_perf_event *hwc = &event->hw;
- u64 count;
+ u64 count = 0;
pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
@@ -603,11 +605,12 @@ static struct pci_driver snbep_uncore_pci_driver = {
/*
* build pci bus to socket mapping
*/
-static void snbep_pci2phy_map_init(void)
+static int snbep_pci2phy_map_init(void)
{
struct pci_dev *ubox_dev = NULL;
int i, bus, nodeid;
- u32 config;
+ int err = 0;
+ u32 config = 0;
while (1) {
/* find the UBOX device */
@@ -618,10 +621,14 @@ static void snbep_pci2phy_map_init(void)
break;
bus = ubox_dev->bus->number;
/* get the Node ID of the local register */
- pci_read_config_dword(ubox_dev, 0x40, &config);
+ err = pci_read_config_dword(ubox_dev, 0x40, &config);
+ if (err)
+ break;
nodeid = config;
/* get the Node ID mapping */
- pci_read_config_dword(ubox_dev, 0x54, &config);
+ err = pci_read_config_dword(ubox_dev, 0x54, &config);
+ if (err)
+ break;
/*
* every three bits in the Node ID mapping register maps
* to a particular node.
@@ -633,7 +640,11 @@ static void snbep_pci2phy_map_init(void)
}
}
};
- return;
+
+ if (ubox_dev)
+ pci_dev_put(ubox_dev);
+
+ return err ? pcibios_err_to_errno(err) : 0;
}
/* end of Sandy Bridge-EP uncore support */
@@ -1547,7 +1558,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- int port;
/* adjust the main event selector and extra register index */
if (reg1->idx % 2) {
@@ -1559,7 +1569,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
}
/* adjust extra register config */
- port = reg1->idx / 6 + box->pmu->pmu_idx * 4;
switch (reg1->idx % 6) {
case 2:
/* shift the 8~15 bits to the 0~7 bits */
@@ -2578,9 +2587,11 @@ static int __init uncore_pci_init(void)
switch (boot_cpu_data.x86_model) {
case 45: /* Sandy Bridge-EP */
+ ret = snbep_pci2phy_map_init();
+ if (ret)
+ return ret;
pci_uncores = snbep_pci_uncores;
uncore_pci_driver = &snbep_uncore_pci_driver;
- snbep_pci2phy_map_init();
break;
default:
return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 7c46bfdbc37..4b7731bf23a 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -3,6 +3,8 @@
#include <linux/perf_event.h>
#include <linux/types.h>
+#include <asm/hardirq.h>
+
#include "perf_event.h"
static const u64 knc_perfmon_event_map[] =
@@ -173,30 +175,100 @@ static void knc_pmu_enable_all(int added)
static inline void
knc_pmu_disable_event(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
u64 val;
val = hwc->config;
- if (cpuc->enabled)
- val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+ val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
}
static void knc_pmu_enable_event(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
u64 val;
val = hwc->config;
- if (cpuc->enabled)
- val |= ARCH_PERFMON_EVENTSEL_ENABLE;
+ val |= ARCH_PERFMON_EVENTSEL_ENABLE;
(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
}
+static inline u64 knc_pmu_get_status(void)
+{
+ u64 status;
+
+ rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_STATUS, status);
+
+ return status;
+}
+
+static inline void knc_pmu_ack_status(u64 ack)
+{
+ wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL, ack);
+}
+
+static int knc_pmu_handle_irq(struct pt_regs *regs)
+{
+ struct perf_sample_data data;
+ struct cpu_hw_events *cpuc;
+ int handled = 0;
+ int bit, loops;
+ u64 status;
+
+ cpuc = &__get_cpu_var(cpu_hw_events);
+
+ knc_pmu_disable_all();
+
+ status = knc_pmu_get_status();
+ if (!status) {
+ knc_pmu_enable_all(0);
+ return handled;
+ }
+
+ loops = 0;
+again:
+ knc_pmu_ack_status(status);
+ if (++loops > 100) {
+ WARN_ONCE(1, "perf: irq loop stuck!\n");
+ perf_event_print_debug();
+ goto done;
+ }
+
+ inc_irq_stat(apic_perf_irqs);
+
+ for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
+ struct perf_event *event = cpuc->events[bit];
+
+ handled++;
+
+ if (!test_bit(bit, cpuc->active_mask))
+ continue;
+
+ if (!intel_pmu_save_and_restart(event))
+ continue;
+
+ perf_sample_data_init(&data, 0, event->hw.last_period);
+
+ if (perf_event_overflow(event, &data, regs))
+ x86_pmu_stop(event, 0);
+ }
+
+ /*
+ * Repeat if there is more work to be done:
+ */
+ status = knc_pmu_get_status();
+ if (status)
+ goto again;
+
+done:
+ knc_pmu_enable_all(0);
+
+ return handled;
+}
+
+
PMU_FORMAT_ATTR(event, "config:0-7" );
PMU_FORMAT_ATTR(umask, "config:8-15" );
PMU_FORMAT_ATTR(edge, "config:18" );
@@ -214,7 +286,7 @@ static struct attribute *intel_knc_formats_attr[] = {
static __initconst struct x86_pmu knc_pmu = {
.name = "knc",
- .handle_irq = x86_pmu_handle_irq,
+ .handle_irq = knc_pmu_handle_irq,
.disable_all = knc_pmu_disable_all,
.enable_all = knc_pmu_enable_all,
.enable = knc_pmu_enable_event,
@@ -226,12 +298,11 @@ static __initconst struct x86_pmu knc_pmu = {
.event_map = knc_pmu_event_map,
.max_events = ARRAY_SIZE(knc_perfmon_event_map),
.apic = 1,
- .max_period = (1ULL << 31) - 1,
+ .max_period = (1ULL << 39) - 1,
.version = 0,
.num_counters = 2,
- /* in theory 40 bits, early silicon is buggy though */
- .cntval_bits = 32,
- .cntval_mask = (1ULL << 32) - 1,
+ .cntval_bits = 40,
+ .cntval_mask = (1ULL << 40) - 1,
.get_event_constraints = x86_get_event_constraints,
.event_constraints = knc_event_constraints,
.format_attrs = intel_knc_formats_attr,
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index e4dd0f7a045..f2af39f5dc3 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -8,13 +8,106 @@
*/
static const u64 p6_perfmon_event_map[] =
{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x0079,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x012e,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
- [PERF_COUNT_HW_BUS_CYCLES] = 0x0062,
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0079, /* CPU_CLK_UNHALTED */
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, /* INST_RETIRED */
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e, /* L2_RQSTS:M:E:S:I */
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x012e, /* L2_RQSTS:I */
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, /* BR_INST_RETIRED */
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, /* BR_MISS_PRED_RETIRED */
+ [PERF_COUNT_HW_BUS_CYCLES] = 0x0062, /* BUS_DRDY_CLOCKS */
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a2, /* RESOURCE_STALLS */
+
+};
+
+static __initconst u64 p6_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0043, /* DATA_MEM_REFS */
+ [ C(RESULT_MISS) ] = 0x0045, /* DCU_LINES_IN */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0x0f29, /* L2_LD:M:E:S:I */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0080, /* IFU_IFETCH */
+ [ C(RESULT_MISS) ] = 0x0f28, /* L2_IFETCH:M:E:S:I */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0x0025, /* L2_M_LINES_INM */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0043, /* DATA_MEM_REFS */
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0080, /* IFU_IFETCH */
+ [ C(RESULT_MISS) ] = 0x0085, /* ITLB_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED */
+ [ C(RESULT_MISS) ] = 0x00c5, /* BR_MISS_PRED_RETIRED */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
};
static u64 p6_pmu_event_map(int hw_event)
@@ -34,7 +127,7 @@ static struct event_constraint p6_event_constraints[] =
{
INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */
INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
- INTEL_EVENT_CONSTRAINT(0x11, 0x1), /* FP_ASSIST */
+ INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
@@ -64,25 +157,25 @@ static void p6_pmu_enable_all(int added)
static inline void
p6_pmu_disable_event(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
u64 val = P6_NOP_EVENT;
- if (cpuc->enabled)
- val |= ARCH_PERFMON_EVENTSEL_ENABLE;
-
(void)wrmsrl_safe(hwc->config_base, val);
}
static void p6_pmu_enable_event(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
u64 val;
val = hwc->config;
- if (cpuc->enabled)
- val |= ARCH_PERFMON_EVENTSEL_ENABLE;
+
+ /*
+ * p6 only has a global event enable, set on PerfEvtSel0
+ * We "disable" events by programming P6_NOP_EVENT
+ * and we rely on p6_pmu_enable_all() being called
+ * to actually enable the events.
+ */
(void)wrmsrl_safe(hwc->config_base, val);
}
@@ -134,6 +227,8 @@ static __initconst const struct x86_pmu p6_pmu = {
.event_constraints = p6_event_constraints,
.format_attrs = intel_p6_formats_attr,
+ .events_sysfs_show = intel_event_sysfs_show,
+
};
__init int p6_pmu_init(void)
@@ -158,5 +253,9 @@ __init int p6_pmu_init(void)
x86_pmu = p6_pmu;
+ memcpy(hw_cache_event_ids, p6_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+
return 0;
}
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index ed858e9e9a7..df06ade26be 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1077,6 +1077,9 @@ void __init memblock_x86_fill(void)
memblock_add(ei->addr, ei->size);
}
+ /* throw away partial pages */
+ memblock_trim_memory(PAGE_SIZE);
+
memblock_dump_all();
}
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 811795db4fc..31b46128a63 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -56,7 +56,7 @@
#include <asm/ftrace.h>
#include <asm/percpu.h>
#include <asm/asm.h>
-#include <asm/rcu.h>
+#include <asm/context_tracking.h>
#include <asm/smap.h>
#include <linux/err.h>
@@ -995,8 +995,8 @@ END(interrupt)
*/
.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
- ASM_CLAC
XCPT_FRAME
+ ASM_CLAC
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
/* 0(%rsp): old_rsp-ARGOFFSET */
@@ -1135,8 +1135,8 @@ END(common_interrupt)
*/
.macro apicinterrupt num sym do_sym
ENTRY(\sym)
- ASM_CLAC
INTR_FRAME
+ ASM_CLAC
pushq_cfi $~(\num)
.Lcommon_\sym:
interrupt \do_sym
@@ -1190,8 +1190,8 @@ apicinterrupt IRQ_WORK_VECTOR \
*/
.macro zeroentry sym do_sym
ENTRY(\sym)
- ASM_CLAC
INTR_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
subq $ORIG_RAX-R15, %rsp
@@ -1208,8 +1208,8 @@ END(\sym)
.macro paranoidzeroentry sym do_sym
ENTRY(\sym)
- ASM_CLAC
INTR_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
subq $ORIG_RAX-R15, %rsp
@@ -1227,8 +1227,8 @@ END(\sym)
#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8)
.macro paranoidzeroentry_ist sym do_sym ist
ENTRY(\sym)
- ASM_CLAC
INTR_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
subq $ORIG_RAX-R15, %rsp
@@ -1247,8 +1247,8 @@ END(\sym)
.macro errorentry sym do_sym
ENTRY(\sym)
- ASM_CLAC
XCPT_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
subq $ORIG_RAX-R15, %rsp
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
@@ -1266,8 +1266,8 @@ END(\sym)
/* error code is on the stack already */
.macro paranoiderrorentry sym do_sym
ENTRY(\sym)
- ASM_CLAC
XCPT_FRAME
+ ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
subq $ORIG_RAX-R15, %rsp
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 957a47aec64..4dac2f68ed4 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -292,8 +292,8 @@ default_entry:
* be using the global pages.
*
* NOTE! If we are on a 486 we may have no cr4 at all!
- * Specifically, cr4 exists if and only if CPUID exists,
- * which in turn exists if and only if EFLAGS.ID exists.
+ * Specifically, cr4 exists if and only if CPUID exists
+ * and has flags other than the FPU flag set.
*/
movl $X86_EFLAGS_ID,%ecx
pushl %ecx
@@ -308,6 +308,11 @@ default_entry:
testl %ecx,%eax
jz 6f # No ID flag = no CPUID = no CR4
+ movl $1,%eax
+ cpuid
+ andl $~1,%edx # Ignore CPUID.FPU
+ jz 6f # No flags or only CPUID.FPU = no CR4
+
movl pa(mmu_cr4_features),%eax
movl %eax,%cr4
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7720ff5a9ee..efdec7cd8e0 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -8,8 +8,8 @@
* Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
*
* Maintainers:
- * Andreas Herrmann <andreas.herrmann3@amd.com>
- * Borislav Petkov <borislav.petkov@amd.com>
+ * Andreas Herrmann <herrmann.der.user@googlemail.com>
+ * Borislav Petkov <bp@alien8.de>
*
* This driver allows to upgrade microcode on F10h AMD
* CPUs and later.
@@ -190,6 +190,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
#define F1XH_MPB_MAX_SIZE 2048
#define F14H_MPB_MAX_SIZE 1824
#define F15H_MPB_MAX_SIZE 4096
+#define F16H_MPB_MAX_SIZE 3458
switch (c->x86) {
case 0x14:
@@ -198,6 +199,9 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
case 0x15:
max_size = F15H_MPB_MAX_SIZE;
break;
+ case 0x16:
+ max_size = F16H_MPB_MAX_SIZE;
+ break;
default:
max_size = F1XH_MPB_MAX_SIZE;
break;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index b00b33a1839..b629bbe0d9b 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -22,6 +22,8 @@
#include <linux/perf_event.h>
#include <linux/hw_breakpoint.h>
#include <linux/rcupdate.h>
+#include <linux/module.h>
+#include <linux/context_tracking.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -166,6 +168,35 @@ static inline bool invalid_selector(u16 value)
#define FLAG_MASK FLAG_MASK_32
+/*
+ * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
+ * when it traps. The previous stack will be directly underneath the saved
+ * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
+ *
+ * Now, if the stack is empty, '&regs->sp' is out of range. In this
+ * case we try to take the previous stack. To always return a non-null
+ * stack pointer we fall back to regs as stack if no previous stack
+ * exists.
+ *
+ * This is valid only for kernel mode traps.
+ */
+unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+ unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
+ unsigned long sp = (unsigned long)&regs->sp;
+ struct thread_info *tinfo;
+
+ if (context == (sp & ~(THREAD_SIZE - 1)))
+ return sp;
+
+ tinfo = (struct thread_info *)context;
+ if (tinfo->previous_esp)
+ return tinfo->previous_esp;
+
+ return (unsigned long)regs;
+}
+EXPORT_SYMBOL_GPL(kernel_stack_pointer);
+
static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
{
BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
@@ -1461,7 +1492,7 @@ long syscall_trace_enter(struct pt_regs *regs)
{
long ret = 0;
- rcu_user_exit();
+ user_exit();
/*
* If we stepped into a sysenter/syscall insn, it trapped in
@@ -1511,6 +1542,13 @@ void syscall_trace_leave(struct pt_regs *regs)
{
bool step;
+ /*
+ * We may come here right after calling schedule_user()
+ * or do_notify_resume(), in which case we can be in RCU
+ * user mode.
+ */
+ user_exit();
+
audit_syscall_exit(regs);
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
@@ -1527,5 +1565,5 @@ void syscall_trace_leave(struct pt_regs *regs)
if (step || test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, step);
- rcu_user_enter();
+ user_enter();
}
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 4929c1be0ac..801602b5d74 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -195,12 +195,6 @@ void read_persistent_clock(struct timespec *ts)
ts->tv_nsec = 0;
}
-unsigned long long native_read_tsc(void)
-{
- return __native_read_tsc();
-}
-EXPORT_SYMBOL(native_read_tsc);
-
static struct resource rtc_resources[] = {
[0] = {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 468e98dfd44..ca45696f30f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -921,18 +921,19 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_X86_64
if (max_pfn > max_low_pfn) {
int i;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
+ unsigned long start, end;
+ unsigned long start_pfn, end_pfn;
- if (ei->addr + ei->size <= 1UL << 32)
- continue;
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
+ NULL) {
- if (ei->type == E820_RESERVED)
+ end = PFN_PHYS(end_pfn);
+ if (end <= (1UL<<32))
continue;
+ start = PFN_PHYS(start_pfn);
max_pfn_mapped = init_memory_mapping(
- ei->addr < 1UL << 32 ? 1UL << 32 : ei->addr,
- ei->addr + ei->size);
+ max((1UL<<32), start), end);
}
/* can we preseve max_low_pfn ?*/
@@ -1048,6 +1049,18 @@ void __init setup_arch(char **cmdline_p)
arch_init_ideal_nops();
register_refined_jiffies(CLOCK_TICK_RATE);
+
+#ifdef CONFIG_EFI
+ /* Once setup is done above, disable efi_enabled on mismatched
+ * firmware/kernel archtectures since there is no support for
+ * runtime services.
+ */
+ if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) {
+ pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+ efi_unmap_memmap();
+ efi_enabled = 0;
+ }
+#endif
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 70b27ee6118..fbbb604313a 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -22,6 +22,7 @@
#include <linux/uaccess.h>
#include <linux/user-return-notifier.h>
#include <linux/uprobes.h>
+#include <linux/context_tracking.h>
#include <asm/processor.h>
#include <asm/ucontext.h>
@@ -816,7 +817,7 @@ static void do_signal(struct pt_regs *regs)
void
do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
{
- rcu_user_exit();
+ user_exit();
#ifdef CONFIG_X86_MCE
/* notify userspace of pending MCEs */
@@ -838,7 +839,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
fire_user_return_notifiers();
- rcu_user_enter();
+ user_enter();
}
void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c80a33bc528..f3e2ec878b8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,6 +68,8 @@
#include <asm/mwait.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
@@ -818,6 +820,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
+ /* the FPU context is blank, nobody can own it */
+ __cpu_disable_lazy_restore(cpu);
+
err = do_boot_cpu(apicid, cpu, tidle);
if (err) {
pr_debug("do_boot_cpu failed %d\n", err);
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index b4d3c3927dd..97ef74b88e0 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -21,37 +21,23 @@
/*
* Align a virtual address to avoid aliasing in the I$ on AMD F15h.
- *
- * @flags denotes the allocation direction - bottomup or topdown -
- * or vDSO; see call sites below.
*/
-unsigned long align_addr(unsigned long addr, struct file *filp,
- enum align_flags flags)
+static unsigned long get_align_mask(void)
{
- unsigned long tmp_addr;
-
/* handle 32- and 64-bit case with a single conditional */
if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32())))
- return addr;
+ return 0;
if (!(current->flags & PF_RANDOMIZE))
- return addr;
-
- if (!((flags & ALIGN_VDSO) || filp))
- return addr;
-
- tmp_addr = addr;
-
- /*
- * We need an address which is <= than the original
- * one only when in topdown direction.
- */
- if (!(flags & ALIGN_TOPDOWN))
- tmp_addr += va_align.mask;
+ return 0;
- tmp_addr &= ~va_align.mask;
+ return va_align.mask;
+}
- return tmp_addr;
+unsigned long align_vdso_addr(unsigned long addr)
+{
+ unsigned long align_mask = get_align_mask();
+ return (addr + align_mask) & ~align_mask;
}
static int __init control_va_addr_alignment(char *str)
@@ -126,7 +112,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- unsigned long start_addr;
+ struct vm_unmapped_area_info info;
unsigned long begin, end;
if (flags & MAP_FIXED)
@@ -144,50 +130,16 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
(!vma || addr + len <= vma->vm_start))
return addr;
}
- if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32))
- && len <= mm->cached_hole_size) {
- mm->cached_hole_size = 0;
- mm->free_area_cache = begin;
- }
- addr = mm->free_area_cache;
- if (addr < begin)
- addr = begin;
- start_addr = addr;
-
-full_search:
-
- addr = align_addr(addr, filp, 0);
-
- for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
- /* At this point: (!vma || addr < vma->vm_end). */
- if (end - len < addr) {
- /*
- * Start a new search - just in case we missed
- * some holes.
- */
- if (start_addr != begin) {
- start_addr = addr = begin;
- mm->cached_hole_size = 0;
- goto full_search;
- }
- return -ENOMEM;
- }
- if (!vma || addr + len <= vma->vm_start) {
- /*
- * Remember the place where we stopped the search:
- */
- mm->free_area_cache = addr + len;
- return addr;
- }
- if (addr + mm->cached_hole_size < vma->vm_start)
- mm->cached_hole_size = vma->vm_start - addr;
- addr = vma->vm_end;
- addr = align_addr(addr, filp, 0);
- }
+ info.flags = 0;
+ info.length = len;
+ info.low_limit = begin;
+ info.high_limit = end;
+ info.align_mask = filp ? get_align_mask() : 0;
+ info.align_offset = pgoff << PAGE_SHIFT;
+ return vm_unmapped_area(&info);
}
-
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
const unsigned long len, const unsigned long pgoff,
@@ -195,7 +147,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
- unsigned long addr = addr0, start_addr;
+ unsigned long addr = addr0;
+ struct vm_unmapped_area_info info;
/* requested length too big for entire address space */
if (len > TASK_SIZE)
@@ -217,51 +170,16 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
return addr;
}
- /* check if free_area_cache is useful for us */
- if (len <= mm->cached_hole_size) {
- mm->cached_hole_size = 0;
- mm->free_area_cache = mm->mmap_base;
- }
-
-try_again:
- /* either no address requested or can't fit in requested address hole */
- start_addr = addr = mm->free_area_cache;
-
- if (addr < len)
- goto fail;
-
- addr -= len;
- do {
- addr = align_addr(addr, filp, ALIGN_TOPDOWN);
-
- /*
- * Lookup failure means no vma is above this address,
- * else if new region fits below vma->vm_start,
- * return with success:
- */
- vma = find_vma(mm, addr);
- if (!vma || addr+len <= vma->vm_start)
- /* remember the address as a hint for next time */
- return mm->free_area_cache = addr;
-
- /* remember the largest hole we saw so far */
- if (addr + mm->cached_hole_size < vma->vm_start)
- mm->cached_hole_size = vma->vm_start - addr;
-
- /* try just below the current vma->vm_start */
- addr = vma->vm_start-len;
- } while (len < vma->vm_start);
-
-fail:
- /*
- * if hint left us with no space for the requested
- * mapping then try again:
- */
- if (start_addr != mm->mmap_base) {
- mm->free_area_cache = mm->mmap_base;
- mm->cached_hole_size = 0;
- goto try_again;
- }
+ info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+ info.length = len;
+ info.low_limit = PAGE_SIZE;
+ info.high_limit = mm->mmap_base;
+ info.align_mask = filp ? get_align_mask() : 0;
+ info.align_offset = pgoff << PAGE_SHIFT;
+ addr = vm_unmapped_area(&info);
+ if (!(addr & ~PAGE_MASK))
+ return addr;
+ VM_BUG_ON(addr != -ENOMEM);
bottomup:
/*
@@ -270,14 +188,5 @@ bottomup:
* can happen with large stack limits and large mmap()
* allocations.
*/
- mm->cached_hole_size = ~0UL;
- mm->free_area_cache = TASK_UNMAPPED_BASE;
- addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
- /*
- * Restore the topdown base:
- */
- mm->free_area_cache = mm->mmap_base;
- mm->cached_hole_size = ~0UL;
-
- return addr;
+ return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
}
diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c
new file mode 100644
index 00000000000..25b993729f9
--- /dev/null
+++ b/arch/x86/kernel/trace_clock.c
@@ -0,0 +1,21 @@
+/*
+ * X86 trace clocks
+ */
+#include <asm/trace_clock.h>
+#include <asm/barrier.h>
+#include <asm/msr.h>
+
+/*
+ * trace_clock_x86_tsc(): A clock that is just the cycle counter.
+ *
+ * Unlike the other clocks, this is not in nanoseconds.
+ */
+u64 notrace trace_clock_x86_tsc(void)
+{
+ u64 ret;
+
+ rdtsc_barrier();
+ rdtscll(ret);
+
+ return ret;
+}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8276dc6794c..eb8586693e0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -55,7 +55,7 @@
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/mce.h>
-#include <asm/rcu.h>
+#include <asm/context_tracking.h>
#include <asm/mach_traps.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cfa5d4f7ca5..06ccb5073a3 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -77,6 +77,12 @@ unsigned long long
sched_clock(void) __attribute__((alias("native_sched_clock")));
#endif
+unsigned long long native_read_tsc(void)
+{
+ return __native_read_tsc();
+}
+EXPORT_SYMBOL(native_read_tsc);
+
int check_tsc_unstable(void)
{
return tsc_unstable;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index aafa5557b39..c71025b6746 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -478,6 +478,11 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
regs->ip = current->utask->xol_vaddr;
pre_xol_rip_insn(auprobe, regs, autask);
+ autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF);
+ regs->flags |= X86_EFLAGS_TF;
+ if (test_tsk_thread_flag(current, TIF_BLOCKSTEP))
+ set_task_blockstep(current, false);
+
return 0;
}
@@ -603,6 +608,16 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
if (auprobe->fixups & UPROBE_FIX_CALL)
result = adjust_ret_addr(regs->sp, correction);
+ /*
+ * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP
+ * so we can get an extra SIGTRAP if we do not clear TF. We need
+ * to examine the opcode to make it right.
+ */
+ if (utask->autask.saved_tf)
+ send_sig(SIGTRAP, current, 0);
+ else if (!(auprobe->fixups & UPROBE_FIX_SETF))
+ regs->flags &= ~X86_EFLAGS_TF;
+
return result;
}
@@ -647,6 +662,10 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
current->thread.trap_nr = utask->autask.saved_trap_nr;
handle_riprel_post_xol(auprobe, regs, NULL);
instruction_pointer_set(regs, utask->vaddr);
+
+ /* clear TF if it was set by us in arch_uprobe_pre_xol() */
+ if (!utask->autask.saved_tf)
+ regs->flags &= ~X86_EFLAGS_TF;
}
/*
@@ -676,38 +695,3 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
send_sig(SIGTRAP, current, 0);
return ret;
}
-
-void arch_uprobe_enable_step(struct arch_uprobe *auprobe)
-{
- struct task_struct *task = current;
- struct arch_uprobe_task *autask = &task->utask->autask;
- struct pt_regs *regs = task_pt_regs(task);
-
- autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF);
-
- regs->flags |= X86_EFLAGS_TF;
- if (test_tsk_thread_flag(task, TIF_BLOCKSTEP))
- set_task_blockstep(task, false);
-}
-
-void arch_uprobe_disable_step(struct arch_uprobe *auprobe)
-{
- struct task_struct *task = current;
- struct arch_uprobe_task *autask = &task->utask->autask;
- bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED);
- struct pt_regs *regs = task_pt_regs(task);
- /*
- * The state of TIF_BLOCKSTEP was not saved so we can get an extra
- * SIGTRAP if we do not clear TF. We need to examine the opcode to
- * make it right.
- */
- if (unlikely(trapped)) {
- if (!autask->saved_tf)
- regs->flags &= ~X86_EFLAGS_TF;
- } else {
- if (autask->saved_tf)
- send_sig(SIGTRAP, task, 0);
- else if (!(auprobe->fixups & UPROBE_FIX_SETF))
- regs->flags &= ~X86_EFLAGS_TF;
- }
-}