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.c2
-rw-r--r--arch/x86/kernel/alternative.c2
-rw-r--r--arch/x86/kernel/cpu/perf_event.h2
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c12
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c25
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c14
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c3
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c36
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h6
-rw-r--r--arch/x86/kernel/cpuid.c5
-rw-r--r--arch/x86/kernel/devicetree.c51
-rw-r--r--arch/x86/kernel/entry_32.S74
-rw-r--r--arch/x86/kernel/entry_64.S139
-rw-r--r--arch/x86/kernel/ftrace.c73
-rw-r--r--arch/x86/kernel/i8259.c2
-rw-r--r--arch/x86/kernel/irq.c2
-rw-r--r--arch/x86/kernel/kprobes.c67
-rw-r--r--arch/x86/kernel/microcode_amd.c7
-rw-r--r--arch/x86/kernel/microcode_core.c3
-rw-r--r--arch/x86/kernel/msr.c5
-rw-r--r--arch/x86/kernel/perf_regs.c105
-rw-r--r--arch/x86/kernel/ptrace.c5
-rw-r--r--arch/x86/kernel/signal.c4
-rw-r--r--arch/x86/kernel/step.c53
-rw-r--r--arch/x86/kernel/traps.c109
-rw-r--r--arch/x86/kernel/uprobes.c52
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c6
28 files changed, 751 insertions, 115 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8215e5652d9..8d7a619718b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -100,6 +100,8 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
obj-$(CONFIG_OF) += devicetree.o
obj-$(CONFIG_UPROBES) += uprobes.o
+obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index b2297e58c6e..e651f7a589a 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -656,7 +656,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
acpi_register_lapic(physid, ACPI_MADT_ENABLED);
/*
- * If mp_register_lapic successfully generates a new logical cpu
+ * If acpi_register_lapic successfully generates a new logical cpu
* number, then the following will get us exactly what was mapped
*/
cpumask_andnot(new_map, cpu_present_mask, tmp_map);
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index af1f326a31c..357475a87b5 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -152,7 +152,7 @@ static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
#endif
#ifdef P6_NOP1
-static const unsigned char __initconst_or_module p6nops[] =
+static const unsigned char p6nops[] =
{
P6_NOP1,
P6_NOP2,
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6605a81ba33..8b6defe7eef 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -586,6 +586,8 @@ extern struct event_constraint intel_westmere_pebs_event_constraints[];
extern struct event_constraint intel_snb_pebs_event_constraints[];
+extern struct event_constraint intel_ivb_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_enable(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 7bfb5bec863..eebd5ffe1bb 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -209,6 +209,15 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config)
return -EOPNOTSUPP;
}
+static const struct perf_event_attr ibs_notsupp = {
+ .exclude_user = 1,
+ .exclude_kernel = 1,
+ .exclude_hv = 1,
+ .exclude_idle = 1,
+ .exclude_host = 1,
+ .exclude_guest = 1,
+};
+
static int perf_ibs_init(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
@@ -229,6 +238,9 @@ static int perf_ibs_init(struct perf_event *event)
if (event->pmu != &perf_ibs->pmu)
return -ENOENT;
+ if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp))
+ return -EINVAL;
+
if (config & ~perf_ibs->config_mask)
return -EINVAL;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7f2739e03e7..6bca492b854 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2008,6 +2008,7 @@ __init int intel_pmu_init(void)
break;
case 28: /* Atom */
+ case 54: /* Cedariew */
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -2047,7 +2048,6 @@ __init int intel_pmu_init(void)
case 42: /* SandyBridge */
case 45: /* SandyBridge, "Romely-EP" */
x86_add_quirk(intel_sandybridge_quirk);
- case 58: /* IvyBridge */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
@@ -2072,6 +2072,29 @@ __init int intel_pmu_init(void)
pr_cont("SandyBridge events, ");
break;
+ case 58: /* IvyBridge */
+ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
+
+ intel_pmu_lbr_init_snb();
+
+ x86_pmu.event_constraints = intel_snb_event_constraints;
+ x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
+ x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+ x86_pmu.extra_regs = intel_snb_extra_regs;
+ /* all extra regs are per-cpu when HT is on */
+ x86_pmu.er_flags |= ERF_HAS_RSP_1;
+ x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+ /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
+ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+ X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
+
+ pr_cont("IvyBridge events, ");
+ break;
+
default:
switch (x86_pmu.version) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index e38d97bf425..826054a4f2e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -407,6 +407,20 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_ivb_pebs_event_constraints[] = {
+ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+ INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+ INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
+ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *c;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 520b4265fcd..da02e9cc375 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void)
* to have an operational LBR which can freeze
* on PMU interrupt
*/
- if (boot_cpu_data.x86_mask < 10) {
+ if (boot_cpu_data.x86_model == 28
+ && boot_cpu_data.x86_mask < 10) {
pr_cont("LBR disabled due to erratum");
return;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 0a5571080e7..99d96a4978b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -661,6 +661,11 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
}
}
+static struct uncore_event_desc snb_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+ { /* end: all zeroes */ },
+};
+
static struct attribute *snb_uncore_formats_attr[] = {
&format_attr_event.attr,
&format_attr_umask.attr,
@@ -704,6 +709,7 @@ static struct intel_uncore_type snb_uncore_cbox = {
.constraints = snb_uncore_cbox_constraints,
.ops = &snb_uncore_msr_ops,
.format_group = &snb_uncore_format_group,
+ .event_descs = snb_uncore_events,
};
static struct intel_uncore_type *snb_msr_uncores[] = {
@@ -1944,7 +1950,7 @@ struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cp
static struct intel_uncore_box *
uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
{
- static struct intel_uncore_box *box;
+ struct intel_uncore_box *box;
box = *per_cpu_ptr(pmu->box, cpu);
if (box)
@@ -2341,6 +2347,27 @@ int uncore_pmu_event_init(struct perf_event *event)
return ret;
}
+static ssize_t uncore_get_attr_cpumask(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask);
+
+ buf[n++] = '\n';
+ buf[n] = '\0';
+ return n;
+}
+
+static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL);
+
+static struct attribute *uncore_pmu_attrs[] = {
+ &dev_attr_cpumask.attr,
+ NULL,
+};
+
+static struct attribute_group uncore_pmu_attr_group = {
+ .attrs = uncore_pmu_attrs,
+};
+
static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
{
int ret;
@@ -2378,8 +2405,8 @@ static void __init uncore_type_exit(struct intel_uncore_type *type)
free_percpu(type->pmus[i].box);
kfree(type->pmus);
type->pmus = NULL;
- kfree(type->attr_groups[1]);
- type->attr_groups[1] = NULL;
+ kfree(type->events_group);
+ type->events_group = NULL;
}
static void __init uncore_types_exit(struct intel_uncore_type **types)
@@ -2431,9 +2458,10 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
for (j = 0; j < i; j++)
attrs[j] = &type->event_descs[j].attr.attr;
- type->attr_groups[1] = events_group;
+ type->events_group = events_group;
}
+ type->pmu_group = &uncore_pmu_attr_group;
type->pmus = pmus;
return 0;
fail:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 5b81c1856aa..e68a4550e95 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -369,10 +369,12 @@ struct intel_uncore_type {
struct intel_uncore_pmu *pmus;
struct intel_uncore_ops *ops;
struct uncore_event_desc *event_descs;
- const struct attribute_group *attr_groups[3];
+ const struct attribute_group *attr_groups[4];
};
-#define format_group attr_groups[0]
+#define pmu_group attr_groups[0]
+#define format_group attr_groups[1]
+#define events_group attr_groups[2]
struct intel_uncore_ops {
void (*init_box)(struct intel_uncore_box *);
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 39472dd2323..60c78917190 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -199,12 +199,14 @@ static int __init cpuid_init(void)
goto out_chrdev;
}
cpuid_class->devnode = cpuid_devnode;
+ get_online_cpus();
for_each_online_cpu(i) {
err = cpuid_device_create(i);
if (err != 0)
goto out_class;
}
register_hotcpu_notifier(&cpuid_class_cpu_notifier);
+ put_online_cpus();
err = 0;
goto out;
@@ -214,6 +216,7 @@ out_class:
for_each_online_cpu(i) {
cpuid_device_destroy(i);
}
+ put_online_cpus();
class_destroy(cpuid_class);
out_chrdev:
__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
@@ -225,11 +228,13 @@ static void __exit cpuid_exit(void)
{
int cpu = 0;
+ get_online_cpus();
for_each_online_cpu(cpu)
cpuid_device_destroy(cpu);
class_destroy(cpuid_class);
__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
+ put_online_cpus();
}
module_init(cpuid_init);
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 3ae2ced4a87..b1581527a23 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -342,6 +342,47 @@ const struct irq_domain_ops ioapic_irq_domain_ops = {
.xlate = ioapic_xlate,
};
+static void dt_add_ioapic_domain(unsigned int ioapic_num,
+ struct device_node *np)
+{
+ struct irq_domain *id;
+ struct mp_ioapic_gsi *gsi_cfg;
+ int ret;
+ int num;
+
+ gsi_cfg = mp_ioapic_gsi_routing(ioapic_num);
+ num = gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
+
+ id = irq_domain_add_linear(np, num, &ioapic_irq_domain_ops,
+ (void *)ioapic_num);
+ BUG_ON(!id);
+ if (gsi_cfg->gsi_base == 0) {
+ /*
+ * The first NR_IRQS_LEGACY irq descs are allocated in
+ * early_irq_init() and need just a mapping. The
+ * remaining irqs need both. All of them are preallocated
+ * and assigned so we can keep the 1:1 mapping which the ioapic
+ * is having.
+ */
+ ret = irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY);
+ if (ret)
+ pr_err("Error mapping legacy IRQs: %d\n", ret);
+
+ if (num > NR_IRQS_LEGACY) {
+ ret = irq_create_strict_mappings(id, NR_IRQS_LEGACY,
+ NR_IRQS_LEGACY, num - NR_IRQS_LEGACY);
+ if (ret)
+ pr_err("Error creating mapping for the "
+ "remaining IRQs: %d\n", ret);
+ }
+ irq_set_default_host(id);
+ } else {
+ ret = irq_create_strict_mappings(id, gsi_cfg->gsi_base, 0, num);
+ if (ret)
+ pr_err("Error creating IRQ mapping: %d\n", ret);
+ }
+}
+
static void __init ioapic_add_ofnode(struct device_node *np)
{
struct resource r;
@@ -356,15 +397,7 @@ static void __init ioapic_add_ofnode(struct device_node *np)
for (i = 0; i < nr_ioapics; i++) {
if (r.start == mpc_ioapic_addr(i)) {
- struct irq_domain *id;
- struct mp_ioapic_gsi *gsi_cfg;
-
- gsi_cfg = mp_ioapic_gsi_routing(i);
-
- id = irq_domain_add_legacy(np, 32, gsi_cfg->gsi_base, 0,
- &ioapic_irq_domain_ops,
- (void*)i);
- BUG_ON(!id);
+ dt_add_ioapic_domain(i, np);
return;
}
}
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 623f2883747..f438a44bf8f 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1109,17 +1109,21 @@ ENTRY(ftrace_caller)
pushl %eax
pushl %ecx
pushl %edx
- movl 0xc(%esp), %eax
+ pushl $0 /* Pass NULL as regs pointer */
+ movl 4*4(%esp), %eax
movl 0x4(%ebp), %edx
+ leal function_trace_op, %ecx
subl $MCOUNT_INSN_SIZE, %eax
.globl ftrace_call
ftrace_call:
call ftrace_stub
+ addl $4,%esp /* skip NULL pointer */
popl %edx
popl %ecx
popl %eax
+ftrace_ret:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.globl ftrace_graph_call
ftrace_graph_call:
@@ -1131,6 +1135,71 @@ ftrace_stub:
ret
END(ftrace_caller)
+ENTRY(ftrace_regs_caller)
+ pushf /* push flags before compare (in cs location) */
+ cmpl $0, function_trace_stop
+ jne ftrace_restore_flags
+
+ /*
+ * i386 does not save SS and ESP when coming from kernel.
+ * Instead, to get sp, &regs->sp is used (see ptrace.h).
+ * Unfortunately, that means eflags must be at the same location
+ * as the current return ip is. We move the return ip into the
+ * ip location, and move flags into the return ip location.
+ */
+ pushl 4(%esp) /* save return ip into ip slot */
+
+ pushl $0 /* Load 0 into orig_ax */
+ pushl %gs
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+
+ movl 13*4(%esp), %eax /* Get the saved flags */
+ movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
+ /* clobbering return ip */
+ movl $__KERNEL_CS,13*4(%esp)
+
+ movl 12*4(%esp), %eax /* Load ip (1st parameter) */
+ subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
+ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
+ leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+ pushl %esp /* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ addl $4, %esp /* Skip pt_regs */
+ movl 14*4(%esp), %eax /* Move flags back into cs */
+ movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
+ movl 12*4(%esp), %eax /* Get return ip from regs->ip */
+ movl %eax, 14*4(%esp) /* Put return ip back for ret */
+
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+ popl %ds
+ popl %es
+ popl %fs
+ popl %gs
+ addl $8, %esp /* Skip orig_ax and ip */
+ popf /* Pop flags at end (no addl to corrupt flags) */
+ jmp ftrace_ret
+
+ftrace_restore_flags:
+ popf
+ jmp ftrace_stub
#else /* ! CONFIG_DYNAMIC_FTRACE */
ENTRY(mcount)
@@ -1171,9 +1240,6 @@ END(mcount)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
- cmpl $0, function_trace_stop
- jne ftrace_stub
-
pushl %eax
pushl %ecx
pushl %edx
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2c6706167c8..066334be7b7 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -56,6 +56,7 @@
#include <asm/ftrace.h>
#include <asm/percpu.h>
#include <asm/asm.h>
+#include <asm/rcu.h>
#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
@@ -68,25 +69,51 @@
.section .entry.text, "ax"
#ifdef CONFIG_FUNCTION_TRACER
+
+#ifdef CC_USING_FENTRY
+# define function_hook __fentry__
+#else
+# define function_hook mcount
+#endif
+
#ifdef CONFIG_DYNAMIC_FTRACE
-ENTRY(mcount)
+
+ENTRY(function_hook)
retq
-END(mcount)
+END(function_hook)
+
+/* skip is set if stack has been adjusted */
+.macro ftrace_caller_setup skip=0
+ MCOUNT_SAVE_FRAME \skip
+
+ /* Load the ftrace_ops into the 3rd parameter */
+ leaq function_trace_op, %rdx
+
+ /* Load ip into the first parameter */
+ movq RIP(%rsp), %rdi
+ subq $MCOUNT_INSN_SIZE, %rdi
+ /* Load the parent_ip into the second parameter */
+#ifdef CC_USING_FENTRY
+ movq SS+16(%rsp), %rsi
+#else
+ movq 8(%rbp), %rsi
+#endif
+.endm
ENTRY(ftrace_caller)
+ /* Check if tracing was disabled (quick check) */
cmpl $0, function_trace_stop
jne ftrace_stub
- MCOUNT_SAVE_FRAME
-
- movq 0x38(%rsp), %rdi
- movq 8(%rbp), %rsi
- subq $MCOUNT_INSN_SIZE, %rdi
+ ftrace_caller_setup
+ /* regs go into 4th parameter (but make it NULL) */
+ movq $0, %rcx
GLOBAL(ftrace_call)
call ftrace_stub
MCOUNT_RESTORE_FRAME
+ftrace_return:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
GLOBAL(ftrace_graph_call)
@@ -97,8 +124,78 @@ GLOBAL(ftrace_stub)
retq
END(ftrace_caller)
+ENTRY(ftrace_regs_caller)
+ /* Save the current flags before compare (in SS location)*/
+ pushfq
+
+ /* Check if tracing was disabled (quick check) */
+ cmpl $0, function_trace_stop
+ jne ftrace_restore_flags
+
+ /* skip=8 to skip flags saved in SS */
+ ftrace_caller_setup 8
+
+ /* Save the rest of pt_regs */
+ movq %r15, R15(%rsp)
+ movq %r14, R14(%rsp)
+ movq %r13, R13(%rsp)
+ movq %r12, R12(%rsp)
+ movq %r11, R11(%rsp)
+ movq %r10, R10(%rsp)
+ movq %rbp, RBP(%rsp)
+ movq %rbx, RBX(%rsp)
+ /* Copy saved flags */
+ movq SS(%rsp), %rcx
+ movq %rcx, EFLAGS(%rsp)
+ /* Kernel segments */
+ movq $__KERNEL_DS, %rcx
+ movq %rcx, SS(%rsp)
+ movq $__KERNEL_CS, %rcx
+ movq %rcx, CS(%rsp)
+ /* Stack - skipping return address */
+ leaq SS+16(%rsp), %rcx
+ movq %rcx, RSP(%rsp)
+
+ /* regs go into 4th parameter */
+ leaq (%rsp), %rcx
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ /* Copy flags back to SS, to restore them */
+ movq EFLAGS(%rsp), %rax
+ movq %rax, SS(%rsp)
+
+ /* Handlers can change the RIP */
+ movq RIP(%rsp), %rax
+ movq %rax, SS+8(%rsp)
+
+ /* restore the rest of pt_regs */
+ movq R15(%rsp), %r15
+ movq R14(%rsp), %r14
+ movq R13(%rsp), %r13
+ movq R12(%rsp), %r12
+ movq R10(%rsp), %r10
+ movq RBP(%rsp), %rbp
+ movq RBX(%rsp), %rbx
+
+ /* skip=8 to skip flags saved in SS */
+ MCOUNT_RESTORE_FRAME 8
+
+ /* Restore flags */
+ popfq
+
+ jmp ftrace_return
+ftrace_restore_flags:
+ popfq
+ jmp ftrace_stub
+
+END(ftrace_regs_caller)
+
+
#else /* ! CONFIG_DYNAMIC_FTRACE */
-ENTRY(mcount)
+
+ENTRY(function_hook)
cmpl $0, function_trace_stop
jne ftrace_stub
@@ -119,8 +216,12 @@ GLOBAL(ftrace_stub)
trace:
MCOUNT_SAVE_FRAME
- movq 0x38(%rsp), %rdi
+ movq RIP(%rsp), %rdi
+#ifdef CC_USING_FENTRY
+ movq SS+16(%rsp), %rsi
+#else
movq 8(%rbp), %rsi
+#endif
subq $MCOUNT_INSN_SIZE, %rdi
call *ftrace_trace_function
@@ -128,20 +229,22 @@ trace:
MCOUNT_RESTORE_FRAME
jmp ftrace_stub
-END(mcount)
+END(function_hook)
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
- cmpl $0, function_trace_stop
- jne ftrace_stub
-
MCOUNT_SAVE_FRAME
+#ifdef CC_USING_FENTRY
+ leaq SS+16(%rsp), %rdi
+ movq $0, %rdx /* No framepointers needed */
+#else
leaq 8(%rbp), %rdi
- movq 0x38(%rsp), %rsi
movq (%rbp), %rdx
+#endif
+ movq RIP(%rsp), %rsi
subq $MCOUNT_INSN_SIZE, %rsi
call prepare_ftrace_return
@@ -565,7 +668,7 @@ sysret_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
pushq_cfi %rdi
- call schedule
+ SCHEDULE_USER
popq_cfi %rdi
jmp sysret_check
@@ -678,7 +781,7 @@ int_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
pushq_cfi %rdi
- call schedule
+ SCHEDULE_USER
popq_cfi %rdi
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
@@ -974,7 +1077,7 @@ retint_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
pushq_cfi %rdi
- call schedule
+ SCHEDULE_USER
popq_cfi %rdi
GET_THREAD_INFO(%rcx)
DISABLE_INTERRUPTS(CLBR_NONE)
@@ -1449,7 +1552,7 @@ paranoid_userspace:
paranoid_schedule:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_ANY)
- call schedule
+ SCHEDULE_USER
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
jmp paranoid_userspace
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c3a7cb4bf6e..1d414029f1d 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -206,6 +206,21 @@ static int
ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
unsigned const char *new_code);
+/*
+ * Should never be called:
+ * As it is only called by __ftrace_replace_code() which is called by
+ * ftrace_replace_code() that x86 overrides, and by ftrace_update_code()
+ * which is called to turn mcount into nops or nops into function calls
+ * but not to convert a function from not using regs to one that uses
+ * regs, which ftrace_modify_call() is for.
+ */
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ WARN_ON(1);
+ return -EINVAL;
+}
+
int ftrace_update_ftrace_func(ftrace_func_t func)
{
unsigned long ip = (unsigned long)(&ftrace_call);
@@ -220,6 +235,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
ret = ftrace_modify_code(ip, old, new);
+ /* Also update the regs callback function */
+ if (!ret) {
+ ip = (unsigned long)(&ftrace_regs_call);
+ memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
+ new = ftrace_call_replace(ip, (unsigned long)func);
+ ret = ftrace_modify_code(ip, old, new);
+ }
+
atomic_dec(&modifying_ftrace_code);
return ret;
@@ -299,6 +322,32 @@ static int add_brk_on_nop(struct dyn_ftrace *rec)
return add_break(rec->ip, old);
}
+/*
+ * If the record has the FTRACE_FL_REGS set, that means that it
+ * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
+ * is not not set, then it wants to convert to the normal callback.
+ */
+static unsigned long get_ftrace_addr(struct dyn_ftrace *rec)
+{
+ if (rec->flags & FTRACE_FL_REGS)
+ return (unsigned long)FTRACE_REGS_ADDR;
+ else
+ return (unsigned long)FTRACE_ADDR;
+}
+
+/*
+ * The FTRACE_FL_REGS_EN is set when the record already points to
+ * a function that saves all the regs. Basically the '_EN' version
+ * represents the current state of the function.
+ */
+static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec)
+{
+ if (rec->flags & FTRACE_FL_REGS_EN)
+ return (unsigned long)FTRACE_REGS_ADDR;
+ else
+ return (unsigned long)FTRACE_ADDR;
+}
+
static int add_breakpoints(struct dyn_ftrace *rec, int enable)
{
unsigned long ftrace_addr;
@@ -306,7 +355,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
ret = ftrace_test_record(rec, enable);
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
@@ -316,6 +365,10 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
/* converting nop to call */
return add_brk_on_nop(rec);
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
+ ftrace_addr = get_ftrace_old_addr(rec);
+ /* fall through */
case FTRACE_UPDATE_MAKE_NOP:
/* converting a call to a nop */
return add_brk_on_call(rec, ftrace_addr);
@@ -360,13 +413,21 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
* If not, don't touch the breakpoint, we make just create
* a disaster.
*/
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
+ nop = ftrace_call_replace(ip, ftrace_addr);
+
+ if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
+ goto update;
+
+ /* Check both ftrace_addr and ftrace_old_addr */
+ ftrace_addr = get_ftrace_old_addr(rec);
nop = ftrace_call_replace(ip, ftrace_addr);
if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
return -EINVAL;
}
+ update:
return probe_kernel_write((void *)ip, &nop[0], 1);
}
@@ -405,12 +466,14 @@ static int add_update(struct dyn_ftrace *rec, int enable)
ret = ftrace_test_record(rec, enable);
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
return 0;
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
case FTRACE_UPDATE_MAKE_CALL:
/* converting nop to call */
return add_update_call(rec, ftrace_addr);
@@ -455,12 +518,14 @@ static int finish_update(struct dyn_ftrace *rec, int enable)
ret = ftrace_update_record(rec, enable);
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
return 0;
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
case FTRACE_UPDATE_MAKE_CALL:
/* converting nop to call */
return finish_update_call(rec, ftrace_addr);
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 36d1853e91a..9a5c460404d 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -263,7 +263,7 @@ static void i8259A_shutdown(void)
* out of.
*/
outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */
- outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */
+ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */
}
static struct syscore_ops i8259_syscore_ops = {
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 7ad683d7864..d44f7829968 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -270,7 +270,7 @@ void fixup_irqs(void)
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
break_affinity = 1;
- affinity = cpu_all_mask;
+ affinity = cpu_online_mask;
}
chip = irq_data_get_irq_chip(data);
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index e2f751efb7b..57916c0d3cf 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -541,6 +541,23 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb
return 1;
}
+#ifdef KPROBES_CAN_USE_FTRACE
+static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
+{
+ /*
+ * Emulate singlestep (and also recover regs->ip)
+ * as if there is a 5byte nop
+ */
+ regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+ if (unlikely(p->post_handler)) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ p->post_handler(p, regs, 0);
+ }
+ __this_cpu_write(current_kprobe, NULL);
+}
+#endif
+
/*
* Interrupts are disabled on entry as trap3 is an interrupt gate and they
* remain disabled throughout this function.
@@ -599,6 +616,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
} else if (kprobe_running()) {
p = __this_cpu_read(current_kprobe);
if (p->break_handler && p->break_handler(p, regs)) {
+#ifdef KPROBES_CAN_USE_FTRACE
+ if (kprobe_ftrace(p)) {
+ skip_singlestep(p, regs, kcb);
+ return 1;
+ }
+#endif
setup_singlestep(p, regs, kcb, 0);
return 1;
}
@@ -1052,6 +1075,50 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
return 0;
}
+#ifdef KPROBES_CAN_USE_FTRACE
+/* Ftrace callback handler for kprobes */
+void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *ops, struct pt_regs *regs)
+{
+ struct kprobe *p;
+ struct kprobe_ctlblk *kcb;
+ unsigned long flags;
+
+ /* Disable irq for emulating a breakpoint and avoiding preempt */
+ local_irq_save(flags);
+
+ p = get_kprobe((kprobe_opcode_t *)ip);
+ if (unlikely(!p) || kprobe_disabled(p))
+ goto end;
+
+ kcb = get_kprobe_ctlblk();
+ if (kprobe_running()) {
+ kprobes_inc_nmissed_count(p);
+ } else {
+ /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
+ regs->ip = ip + sizeof(kprobe_opcode_t);
+
+ __this_cpu_write(current_kprobe, p);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+ if (!p->pre_handler || !p->pre_handler(p, regs))
+ skip_singlestep(p, regs, kcb);
+ /*
+ * If pre_handler returns !0, it sets regs->ip and
+ * resets current kprobe.
+ */
+ }
+end:
+ local_irq_restore(flags);
+}
+
+int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+ p->ainsn.insn = NULL;
+ p->ainsn.boostable = -1;
+ return 0;
+}
+#endif
+
int __init arch_init_kprobes(void)
{
return arch_init_optprobes();
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 8a2ce8fd41c..82746f942cd 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -143,11 +143,12 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
unsigned int *current_size)
{
struct microcode_header_amd *mc_hdr;
- unsigned int actual_size;
+ unsigned int actual_size, patch_size;
u16 equiv_cpu_id;
/* size of the current patch we're staring at */
- *current_size = *(u32 *)(ucode_ptr + 4) + SECTION_HDR_SIZE;
+ patch_size = *(u32 *)(ucode_ptr + 4);
+ *current_size = patch_size + SECTION_HDR_SIZE;
equiv_cpu_id = find_equiv_id();
if (!equiv_cpu_id)
@@ -174,7 +175,7 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
/*
* now that the header looks sane, verify its size
*/
- actual_size = verify_ucode_size(cpu, *current_size, leftover_size);
+ actual_size = verify_ucode_size(cpu, patch_size, leftover_size);
if (!actual_size)
return 0;
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 4873e62db6a..9e5bcf1e237 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
if (do_microcode_update(buf, len) == 0)
ret = (ssize_t)len;
+ if (ret > 0)
+ perf_check_microcode();
+
mutex_unlock(&microcode_mutex);
put_online_cpus();
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index eb113693f04..a7c5661f849 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -257,12 +257,14 @@ static int __init msr_init(void)
goto out_chrdev;
}
msr_class->devnode = msr_devnode;
+ get_online_cpus();
for_each_online_cpu(i) {
err = msr_device_create(i);
if (err != 0)
goto out_class;
}
register_hotcpu_notifier(&msr_class_cpu_notifier);
+ put_online_cpus();
err = 0;
goto out;
@@ -271,6 +273,7 @@ out_class:
i = 0;
for_each_online_cpu(i)
msr_device_destroy(i);
+ put_online_cpus();
class_destroy(msr_class);
out_chrdev:
__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
@@ -281,11 +284,13 @@ out:
static void __exit msr_exit(void)
{
int cpu = 0;
+ get_online_cpus();
for_each_online_cpu(cpu)
msr_device_destroy(cpu);
class_destroy(msr_class);
__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
unregister_hotcpu_notifier(&msr_class_cpu_notifier);
+ put_online_cpus();
}
module_init(msr_init);
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
new file mode 100644
index 00000000000..e309cc5c276
--- /dev/null
+++ b/arch/x86/kernel/perf_regs.c
@@ -0,0 +1,105 @@
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <linux/stddef.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_X86_32
+#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX
+#else
+#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX
+#endif
+
+#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r)
+
+static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
+ PT_REGS_OFFSET(PERF_REG_X86_AX, ax),
+ PT_REGS_OFFSET(PERF_REG_X86_BX, bx),
+ PT_REGS_OFFSET(PERF_REG_X86_CX, cx),
+ PT_REGS_OFFSET(PERF_REG_X86_DX, dx),
+ PT_REGS_OFFSET(PERF_REG_X86_SI, si),
+ PT_REGS_OFFSET(PERF_REG_X86_DI, di),
+ PT_REGS_OFFSET(PERF_REG_X86_BP, bp),
+ PT_REGS_OFFSET(PERF_REG_X86_SP, sp),
+ PT_REGS_OFFSET(PERF_REG_X86_IP, ip),
+ PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags),
+ PT_REGS_OFFSET(PERF_REG_X86_CS, cs),
+ PT_REGS_OFFSET(PERF_REG_X86_SS, ss),
+#ifdef CONFIG_X86_32
+ PT_REGS_OFFSET(PERF_REG_X86_DS, ds),
+ PT_REGS_OFFSET(PERF_REG_X86_ES, es),
+ PT_REGS_OFFSET(PERF_REG_X86_FS, fs),
+ PT_REGS_OFFSET(PERF_REG_X86_GS, gs),
+#else
+ /*
+ * The pt_regs struct does not store
+ * ds, es, fs, gs in 64 bit mode.
+ */
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+#endif
+#ifdef CONFIG_X86_64
+ PT_REGS_OFFSET(PERF_REG_X86_R8, r8),
+ PT_REGS_OFFSET(PERF_REG_X86_R9, r9),
+ PT_REGS_OFFSET(PERF_REG_X86_R10, r10),
+ PT_REGS_OFFSET(PERF_REG_X86_R11, r11),
+ PT_REGS_OFFSET(PERF_REG_X86_R12, r12),
+ PT_REGS_OFFSET(PERF_REG_X86_R13, r13),
+ PT_REGS_OFFSET(PERF_REG_X86_R14, r14),
+ PT_REGS_OFFSET(PERF_REG_X86_R15, r15),
+#endif
+};
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+ if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
+ return 0;
+
+ return regs_get_register(regs, pt_regs_offset[idx]);
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
+
+#ifdef CONFIG_X86_32
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ return PERF_SAMPLE_REGS_ABI_32;
+}
+#else /* CONFIG_X86_64 */
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+ (1ULL << PERF_REG_X86_ES) | \
+ (1ULL << PERF_REG_X86_FS) | \
+ (1ULL << PERF_REG_X86_GS))
+
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ if (mask & REG_NOSUPPORT)
+ return -EINVAL;
+
+ return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ if (test_tsk_thread_flag(task, TIF_IA32))
+ return PERF_SAMPLE_REGS_ABI_32;
+ else
+ return PERF_SAMPLE_REGS_ABI_64;
+}
+#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index c4c6a5c2bf0..9f94f8ec26e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
#include <linux/signal.h>
#include <linux/perf_event.h>
#include <linux/hw_breakpoint.h>
+#include <linux/rcupdate.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -1463,6 +1464,8 @@ long syscall_trace_enter(struct pt_regs *regs)
{
long ret = 0;
+ rcu_user_exit();
+
/*
* If we stepped into a sysenter/syscall insn, it trapped in
* kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
@@ -1526,4 +1529,6 @@ void syscall_trace_leave(struct pt_regs *regs)
!test_thread_flag(TIF_SYSCALL_EMU);
if (step || test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, step);
+
+ rcu_user_enter();
}
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b280908a376..bca0ab903e5 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -779,6 +779,8 @@ 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();
+
#ifdef CONFIG_X86_MCE
/* notify userspace of pending MCEs */
if (thread_info_flags & _TIF_MCE_NOTIFY)
@@ -804,6 +806,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
#ifdef CONFIG_X86_32
clear_thread_flag(TIF_IRET);
#endif /* CONFIG_X86_32 */
+
+ rcu_user_enter();
}
void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index c346d116148..cd3b2438a98 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -157,6 +157,33 @@ static int enable_single_step(struct task_struct *child)
return 1;
}
+void set_task_blockstep(struct task_struct *task, bool on)
+{
+ unsigned long debugctl;
+
+ /*
+ * Ensure irq/preemption can't change debugctl in between.
+ * Note also that both TIF_BLOCKSTEP and debugctl should
+ * be changed atomically wrt preemption.
+ * FIXME: this means that set/clear TIF_BLOCKSTEP is simply
+ * wrong if task != current, SIGKILL can wakeup the stopped
+ * tracee and set/clear can play with the running task, this
+ * can confuse the next __switch_to_xtra().
+ */
+ local_irq_disable();
+ debugctl = get_debugctlmsr();
+ if (on) {
+ debugctl |= DEBUGCTLMSR_BTF;
+ set_tsk_thread_flag(task, TIF_BLOCKSTEP);
+ } else {
+ debugctl &= ~DEBUGCTLMSR_BTF;
+ clear_tsk_thread_flag(task, TIF_BLOCKSTEP);
+ }
+ if (task == current)
+ update_debugctlmsr(debugctl);
+ local_irq_enable();
+}
+
/*
* Enable single or block step.
*/
@@ -169,19 +196,10 @@ static void enable_step(struct task_struct *child, bool block)
* So no one should try to use debugger block stepping in a program
* that uses user-mode single stepping itself.
*/
- if (enable_single_step(child) && block) {
- unsigned long debugctl = get_debugctlmsr();
-
- debugctl |= DEBUGCTLMSR_BTF;
- update_debugctlmsr(debugctl);
- set_tsk_thread_flag(child, TIF_BLOCKSTEP);
- } else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) {
- unsigned long debugctl = get_debugctlmsr();
-
- debugctl &= ~DEBUGCTLMSR_BTF;
- update_debugctlmsr(debugctl);
- clear_tsk_thread_flag(child, TIF_BLOCKSTEP);
- }
+ if (enable_single_step(child) && block)
+ set_task_blockstep(child, true);
+ else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP))
+ set_task_blockstep(child, false);
}
void user_enable_single_step(struct task_struct *child)
@@ -199,13 +217,8 @@ void user_disable_single_step(struct task_struct *child)
/*
* Make sure block stepping (BTF) is disabled.
*/
- if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) {
- unsigned long debugctl = get_debugctlmsr();
-
- debugctl &= ~DEBUGCTLMSR_BTF;
- update_debugctlmsr(debugctl);
- clear_tsk_thread_flag(child, TIF_BLOCKSTEP);
- }
+ if (test_tsk_thread_flag(child, TIF_BLOCKSTEP))
+ set_task_blockstep(child, false);
/* Always clear TIF_SINGLESTEP... */
clear_tsk_thread_flag(child, TIF_SINGLESTEP);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 6ff771559af..cfbe3fc4158 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -55,6 +55,7 @@
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/mce.h>
+#include <asm/rcu.h>
#include <asm/mach_traps.h>
@@ -178,11 +179,15 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
#define DO_ERROR(trapnr, signr, str, name) \
dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
{ \
- if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
- == NOTIFY_STOP) \
+ exception_enter(regs); \
+ if (notify_die(DIE_TRAP, str, regs, error_code, \
+ trapnr, signr) == NOTIFY_STOP) { \
+ exception_exit(regs); \
return; \
+ } \
conditional_sti(regs); \
do_trap(trapnr, signr, str, regs, error_code, NULL); \
+ exception_exit(regs); \
}
#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
@@ -193,11 +198,15 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
info.si_errno = 0; \
info.si_code = sicode; \
info.si_addr = (void __user *)siaddr; \
- if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
- == NOTIFY_STOP) \
+ exception_enter(regs); \
+ if (notify_die(DIE_TRAP, str, regs, error_code, \
+ trapnr, signr) == NOTIFY_STOP) { \
+ exception_exit(regs); \
return; \
+ } \
conditional_sti(regs); \
do_trap(trapnr, signr, str, regs, error_code, &info); \
+ exception_exit(regs); \
}
DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
@@ -220,12 +229,14 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
/* Runs on IST stack */
dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
{
+ exception_enter(regs);
if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
- X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
- return;
- preempt_conditional_sti(regs);
- do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
- preempt_conditional_cli(regs);
+ X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
+ preempt_conditional_sti(regs);
+ do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
+ preempt_conditional_cli(regs);
+ }
+ exception_exit(regs);
}
dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
@@ -233,6 +244,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
static const char str[] = "double fault";
struct task_struct *tsk = current;
+ exception_enter(regs);
/* Return not checked because double check cannot be ignored */
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -253,16 +265,29 @@ do_general_protection(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk;
+ exception_enter(regs);
conditional_sti(regs);
#ifdef CONFIG_X86_32
- if (regs->flags & X86_VM_MASK)
- goto gp_in_vm86;
+ if (regs->flags & X86_VM_MASK) {
+ local_irq_enable();
+ handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
+ goto exit;
+ }
#endif
tsk = current;
- if (!user_mode(regs))
- goto gp_in_kernel;
+ if (!user_mode(regs)) {
+ if (fixup_exception(regs))
+ goto exit;
+
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_nr = X86_TRAP_GP;
+ if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+ X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
+ die("general protection fault", regs, error_code);
+ goto exit;
+ }
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
@@ -277,25 +302,8 @@ do_general_protection(struct pt_regs *regs, long error_code)
}
force_sig(SIGSEGV, tsk);
- return;
-
-#ifdef CONFIG_X86_32
-gp_in_vm86:
- local_irq_enable();
- handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
- return;
-#endif
-
-gp_in_kernel:
- if (fixup_exception(regs))
- return;
-
- tsk->thread.error_code = error_code;
- tsk->thread.trap_nr = X86_TRAP_GP;
- if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
- X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP)
- return;
- die("general protection fault", regs, error_code);
+exit:
+ exception_exit(regs);
}
/* May run on IST stack. */
@@ -310,15 +318,16 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
ftrace_int3_handler(regs))
return;
#endif
+ exception_enter(regs);
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
SIGTRAP) == NOTIFY_STOP)
- return;
+ goto exit;
#endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
SIGTRAP) == NOTIFY_STOP)
- return;
+ goto exit;
/*
* Let others (NMI) know that the debug stack is in use
@@ -329,6 +338,8 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
preempt_conditional_cli(regs);
debug_stack_usage_dec();
+exit:
+ exception_exit(regs);
}
#ifdef CONFIG_X86_64
@@ -389,6 +400,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
unsigned long dr6;
int si_code;
+ exception_enter(regs);
+
get_debugreg(dr6, 6);
/* Filter out all the reserved bits which are preset to 1 */
@@ -404,7 +417,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
/* Catch kmemcheck conditions first of all! */
if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
- return;
+ goto exit;
/* DR6 may or may not be cleared by the CPU */
set_debugreg(0, 6);
@@ -419,7 +432,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code,
SIGTRAP) == NOTIFY_STOP)
- return;
+ goto exit;
/*
* Let others (NMI) know that the debug stack is in use
@@ -435,7 +448,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
X86_TRAP_DB);
preempt_conditional_cli(regs);
debug_stack_usage_dec();
- return;
+ goto exit;
}
/*
@@ -456,7 +469,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
preempt_conditional_cli(regs);
debug_stack_usage_dec();
- return;
+exit:
+ exception_exit(regs);
}
/*
@@ -553,14 +567,17 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
#ifdef CONFIG_X86_32
ignore_fpu_irq = 1;
#endif
-
+ exception_enter(regs);
math_error(regs, error_code, X86_TRAP_MF);
+ exception_exit(regs);
}
dotraplinkage void
do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
{
+ exception_enter(regs);
math_error(regs, error_code, X86_TRAP_XF);
+ exception_exit(regs);
}
dotraplinkage void
@@ -627,6 +644,7 @@ EXPORT_SYMBOL_GPL(math_state_restore);
dotraplinkage void __kprobes
do_device_not_available(struct pt_regs *regs, long error_code)
{
+ exception_enter(regs);
#ifdef CONFIG_MATH_EMULATION
if (read_cr0() & X86_CR0_EM) {
struct math_emu_info info = { };
@@ -635,6 +653,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
info.regs = regs;
math_emulate(&info);
+ exception_exit(regs);
return;
}
#endif
@@ -642,12 +661,15 @@ do_device_not_available(struct pt_regs *regs, long error_code)
#ifdef CONFIG_X86_32
conditional_sti(regs);
#endif
+ exception_exit(regs);
}
#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
{
siginfo_t info;
+
+ exception_enter(regs);
local_irq_enable();
info.si_signo = SIGILL;
@@ -655,10 +677,11 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
info.si_code = ILL_BADSTK;
info.si_addr = NULL;
if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
- X86_TRAP_IRET, SIGILL) == NOTIFY_STOP)
- return;
- do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
- &info);
+ X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) {
+ do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
+ &info);
+ }
+ exception_exit(regs);
}
#endif
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 36fd42091fa..9538f00827a 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -41,6 +41,9 @@
/* Adjust the return address of a call insn */
#define UPROBE_FIX_CALL 0x2
+/* Instruction will modify TF, don't change it */
+#define UPROBE_FIX_SETF 0x4
+
#define UPROBE_FIX_RIP_AX 0x8000
#define UPROBE_FIX_RIP_CX 0x4000
@@ -239,6 +242,10 @@ static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn)
insn_get_opcode(insn); /* should be a nop */
switch (OPCODE1(insn)) {
+ case 0x9d:
+ /* popf */
+ auprobe->fixups |= UPROBE_FIX_SETF;
+ break;
case 0xc3: /* ret/lret */
case 0xcb:
case 0xc2:
@@ -646,7 +653,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
* Skip these instructions as per the currently known x86 ISA.
* 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 }
*/
-bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
int i;
@@ -673,3 +680,46 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
}
return false;
}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+ bool ret = __skip_sstep(auprobe, regs);
+ if (ret && (regs->flags & X86_EFLAGS_TF))
+ 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;
+ }
+}
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 6020f6f5927..1330dd10295 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -13,9 +13,13 @@
#include <asm/ftrace.h>
#ifdef CONFIG_FUNCTION_TRACER
-/* mcount is defined in assembly */
+/* mcount and __fentry__ are defined in assembly */
+#ifdef CC_USING_FENTRY
+EXPORT_SYMBOL(__fentry__);
+#else
EXPORT_SYMBOL(mcount);
#endif
+#endif
EXPORT_SYMBOL(__get_user_1);
EXPORT_SYMBOL(__get_user_2);