summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig3
-rw-r--r--arch/x86/boot/Makefile3
-rw-r--r--arch/x86/include/asm/msr-index.h5
-rw-r--r--arch/x86/include/asm/unistd.h1
-rw-r--r--arch/x86/include/asm/vgtod.h4
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/perf_event.h2
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c61
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c2
-rw-r--r--arch/x86/kernel/cpu/perf_event_knc.c248
-rw-r--r--arch/x86/kernel/cpu/perfctr-watchdog.c4
-rw-r--r--arch/x86/kernel/entry_32.S48
-rw-r--r--arch/x86/kernel/entry_64.S24
-rw-r--r--arch/x86/kernel/kgdb.c2
-rw-r--r--arch/x86/kernel/setup.c3
-rw-r--r--arch/x86/kernel/vsyscall_64.c49
-rw-r--r--arch/x86/um/Kconfig3
-rw-r--r--arch/x86/vdso/vclock_gettime.c22
-rw-r--r--arch/x86/xen/enlighten.c18
-rw-r--r--arch/x86/xen/mmu.c41
20 files changed, 449 insertions, 96 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 42d2c35a5bbd..46c3bff3ced2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -109,6 +109,9 @@ config X86
select HAVE_RCU_USER_QS if X86_64
select HAVE_IRQ_TIME_ACCOUNTING
select GENERIC_KERNEL_THREAD
+ select GENERIC_KERNEL_EXECVE
+ select MODULES_USE_ELF_REL if X86_32
+ select MODULES_USE_ELF_RELA if X86_64
config INSTRUCTION_DECODER
def_bool y
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index ce03476d8c8f..ccce0ed67dde 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -37,7 +37,8 @@ setup-y += video-bios.o
targets += $(setup-y)
hostprogs-y := mkcpustr tools/build
-HOST_EXTRACFLAGS += -I$(srctree)/tools/include $(USERINCLUDE) \
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include \
+ -include include/generated/autoconf.h \
-D__EXPORTED_HEADERS__
$(obj)/cpu.o: $(obj)/cpustr.h
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index fbee9714d9ab..7f0edceb7563 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -121,6 +121,11 @@
#define MSR_P6_EVNTSEL0 0x00000186
#define MSR_P6_EVNTSEL1 0x00000187
+#define MSR_KNC_PERFCTR0 0x00000020
+#define MSR_KNC_PERFCTR1 0x00000021
+#define MSR_KNC_EVNTSEL0 0x00000028
+#define MSR_KNC_EVNTSEL1 0x00000029
+
/* AMD64 MSRs. Not complete. See the architecture manual for a more
complete list. */
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 55d155560fdf..16f3fc6ebf2e 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -51,7 +51,6 @@
# define __ARCH_WANT_SYS_UTIME
# define __ARCH_WANT_SYS_WAITPID
# define __ARCH_WANT_SYS_EXECVE
-# define __ARCH_WANT_KERNEL_EXECVE
/*
* "Conditional" syscalls
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 8b38be2de9e1..46e24d36b7da 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -17,8 +17,8 @@ struct vsyscall_gtod_data {
/* open coded 'struct timespec' */
time_t wall_time_sec;
- u32 wall_time_nsec;
- u32 monotonic_time_nsec;
+ u64 wall_time_snsec;
+ u64 monotonic_time_snsec;
time_t monotonic_time_sec;
struct timezone sys_tz;
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index d30a6a9a0121..a0e067d3d96c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -32,7 +32,7 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o
ifdef CONFIG_PERF_EVENTS
obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o
-obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o
endif
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8b6defe7eefc..271d25700297 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -626,6 +626,8 @@ int p4_pmu_init(void);
int p6_pmu_init(void);
+int knc_pmu_init(void);
+
#else /* CONFIG_CPU_SUP_INTEL */
static inline void reserve_ds_buffers(void)
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index eebd5ffe1bba..6336bcbd0618 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -41,17 +41,22 @@ struct cpu_perf_ibs {
};
struct perf_ibs {
- struct pmu pmu;
- unsigned int msr;
- u64 config_mask;
- u64 cnt_mask;
- u64 enable_mask;
- u64 valid_mask;
- u64 max_period;
- unsigned long offset_mask[1];
- int offset_max;
- struct cpu_perf_ibs __percpu *pcpu;
- u64 (*get_count)(u64 config);
+ struct pmu pmu;
+ unsigned int msr;
+ u64 config_mask;
+ u64 cnt_mask;
+ u64 enable_mask;
+ u64 valid_mask;
+ u64 max_period;
+ unsigned long offset_mask[1];
+ int offset_max;
+ struct cpu_perf_ibs __percpu *pcpu;
+
+ struct attribute **format_attrs;
+ struct attribute_group format_group;
+ const struct attribute_group *attr_groups[2];
+
+ u64 (*get_count)(u64 config);
};
struct perf_ibs_data {
@@ -446,6 +451,19 @@ static void perf_ibs_del(struct perf_event *event, int flags)
static void perf_ibs_read(struct perf_event *event) { }
+PMU_FORMAT_ATTR(rand_en, "config:57");
+PMU_FORMAT_ATTR(cnt_ctl, "config:19");
+
+static struct attribute *ibs_fetch_format_attrs[] = {
+ &format_attr_rand_en.attr,
+ NULL,
+};
+
+static struct attribute *ibs_op_format_attrs[] = {
+ NULL, /* &format_attr_cnt_ctl.attr if IBS_CAPS_OPCNT */
+ NULL,
+};
+
static struct perf_ibs perf_ibs_fetch = {
.pmu = {
.task_ctx_nr = perf_invalid_context,
@@ -465,6 +483,7 @@ static struct perf_ibs perf_ibs_fetch = {
.max_period = IBS_FETCH_MAX_CNT << 4,
.offset_mask = { MSR_AMD64_IBSFETCH_REG_MASK },
.offset_max = MSR_AMD64_IBSFETCH_REG_COUNT,
+ .format_attrs = ibs_fetch_format_attrs,
.get_count = get_ibs_fetch_count,
};
@@ -488,6 +507,7 @@ static struct perf_ibs perf_ibs_op = {
.max_period = IBS_OP_MAX_CNT << 4,
.offset_mask = { MSR_AMD64_IBSOP_REG_MASK },
.offset_max = MSR_AMD64_IBSOP_REG_COUNT,
+ .format_attrs = ibs_op_format_attrs,
.get_count = get_ibs_op_count,
};
@@ -597,6 +617,17 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
perf_ibs->pcpu = pcpu;
+ /* register attributes */
+ if (perf_ibs->format_attrs[0]) {
+ memset(&perf_ibs->format_group, 0, sizeof(perf_ibs->format_group));
+ perf_ibs->format_group.name = "format";
+ perf_ibs->format_group.attrs = perf_ibs->format_attrs;
+
+ memset(&perf_ibs->attr_groups, 0, sizeof(perf_ibs->attr_groups));
+ perf_ibs->attr_groups[0] = &perf_ibs->format_group;
+ perf_ibs->pmu.attr_groups = perf_ibs->attr_groups;
+ }
+
ret = perf_pmu_register(&perf_ibs->pmu, name, -1);
if (ret) {
perf_ibs->pcpu = NULL;
@@ -608,13 +639,19 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
static __init int perf_event_ibs_init(void)
{
+ struct attribute **attr = ibs_op_format_attrs;
+
if (!ibs_caps)
return -ENODEV; /* ibs not supported by the cpu */
perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
- if (ibs_caps & IBS_CAPS_OPCNT)
+
+ if (ibs_caps & IBS_CAPS_OPCNT) {
perf_ibs_op.config_mask |= IBS_OP_CNT_CTL;
+ *attr++ = &format_attr_cnt_ctl.attr;
+ }
perf_ibs_pmu_init(&perf_ibs_op, "ibs_op");
+
register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs");
printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 6bca492b8547..324bb523d9d9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1906,6 +1906,8 @@ __init int intel_pmu_init(void)
switch (boot_cpu_data.x86) {
case 0x6:
return p6_pmu_init();
+ case 0xb:
+ return knc_pmu_init();
case 0xf:
return p4_pmu_init();
}
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
new file mode 100644
index 000000000000..7c46bfdbc373
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -0,0 +1,248 @@
+/* Driver for Intel Xeon Phi "Knights Corner" PMU */
+
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#include "perf_event.h"
+
+static const u64 knc_perfmon_event_map[] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x002a,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x0016,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0028,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x0029,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x0012,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x002b,
+};
+
+static __initconst u64 knc_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) ] = {
+ /* On Xeon Phi event "0" is a valid DATA_READ */
+ /* (L1 Data Cache Reads) Instruction. */
+ /* We code this as ARCH_PERFMON_EVENTSEL_INT as this */
+ /* bit will always be set in x86_pmu_hw_config(). */
+ [ C(RESULT_ACCESS) ] = ARCH_PERFMON_EVENTSEL_INT,
+ /* DATA_READ */
+ [ C(RESULT_MISS) ] = 0x0003, /* DATA_READ_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0001, /* DATA_WRITE */
+ [ C(RESULT_MISS) ] = 0x0004, /* DATA_WRITE_MISS */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0011, /* L1_DATA_PF1 */
+ [ C(RESULT_MISS) ] = 0x001c, /* L1_DATA_PF1_MISS */
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x000c, /* CODE_READ */
+ [ C(RESULT_MISS) ] = 0x000e, /* CODE_CACHE_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0x10cb, /* L2_READ_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x10cc, /* L2_WRITE_HIT */
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x10fc, /* L2_DATA_PF2 */
+ [ C(RESULT_MISS) ] = 0x10fe, /* L2_DATA_PF2_MISS */
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = ARCH_PERFMON_EVENTSEL_INT,
+ /* DATA_READ */
+ /* see note on L1 OP_READ */
+ [ C(RESULT_MISS) ] = 0x0002, /* DATA_PAGE_WALK */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0001, /* DATA_WRITE */
+ [ C(RESULT_MISS) ] = 0x0002, /* DATA_PAGE_WALK */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x000c, /* CODE_READ */
+ [ C(RESULT_MISS) ] = 0x000d, /* CODE_PAGE_WALK */
+ },
+ [ 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) ] = 0x0012, /* BRANCHES */
+ [ C(RESULT_MISS) ] = 0x002b, /* BRANCHES_MISPREDICTED */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
+
+static u64 knc_pmu_event_map(int hw_event)
+{
+ return knc_perfmon_event_map[hw_event];
+}
+
+static struct event_constraint knc_event_constraints[] =
+{
+ INTEL_EVENT_CONSTRAINT(0xc3, 0x1), /* HWP_L2HIT */
+ INTEL_EVENT_CONSTRAINT(0xc4, 0x1), /* HWP_L2MISS */
+ INTEL_EVENT_CONSTRAINT(0xc8, 0x1), /* L2_READ_HIT_E */
+ INTEL_EVENT_CONSTRAINT(0xc9, 0x1), /* L2_READ_HIT_M */
+ INTEL_EVENT_CONSTRAINT(0xca, 0x1), /* L2_READ_HIT_S */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* L2_READ_MISS */
+ INTEL_EVENT_CONSTRAINT(0xcc, 0x1), /* L2_WRITE_HIT */
+ INTEL_EVENT_CONSTRAINT(0xce, 0x1), /* L2_STRONGLY_ORDERED_STREAMING_VSTORES_MISS */
+ INTEL_EVENT_CONSTRAINT(0xcf, 0x1), /* L2_WEAKLY_ORDERED_STREAMING_VSTORE_MISS */
+ INTEL_EVENT_CONSTRAINT(0xd7, 0x1), /* L2_VICTIM_REQ_WITH_DATA */
+ INTEL_EVENT_CONSTRAINT(0xe3, 0x1), /* SNP_HITM_BUNIT */
+ INTEL_EVENT_CONSTRAINT(0xe6, 0x1), /* SNP_HIT_L2 */
+ INTEL_EVENT_CONSTRAINT(0xe7, 0x1), /* SNP_HITM_L2 */
+ INTEL_EVENT_CONSTRAINT(0xf1, 0x1), /* L2_DATA_READ_MISS_CACHE_FILL */
+ INTEL_EVENT_CONSTRAINT(0xf2, 0x1), /* L2_DATA_WRITE_MISS_CACHE_FILL */
+ INTEL_EVENT_CONSTRAINT(0xf6, 0x1), /* L2_DATA_READ_MISS_MEM_FILL */
+ INTEL_EVENT_CONSTRAINT(0xf7, 0x1), /* L2_DATA_WRITE_MISS_MEM_FILL */
+ INTEL_EVENT_CONSTRAINT(0xfc, 0x1), /* L2_DATA_PF2 */
+ INTEL_EVENT_CONSTRAINT(0xfd, 0x1), /* L2_DATA_PF2_DROP */
+ INTEL_EVENT_CONSTRAINT(0xfe, 0x1), /* L2_DATA_PF2_MISS */
+ INTEL_EVENT_CONSTRAINT(0xff, 0x1), /* L2_DATA_HIT_INFLIGHT_PF2 */
+ EVENT_CONSTRAINT_END
+};
+
+#define MSR_KNC_IA32_PERF_GLOBAL_STATUS 0x0000002d
+#define MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL 0x0000002e
+#define MSR_KNC_IA32_PERF_GLOBAL_CTRL 0x0000002f
+
+#define KNC_ENABLE_COUNTER0 0x00000001
+#define KNC_ENABLE_COUNTER1 0x00000002
+
+static void knc_pmu_disable_all(void)
+{
+ u64 val;
+
+ rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+ val &= ~(KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1);
+ wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+}
+
+static void knc_pmu_enable_all(int added)
+{
+ u64 val;
+
+ rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+ val |= (KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1);
+ wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+}
+
+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;
+
+ (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;
+
+ (void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
+}
+
+PMU_FORMAT_ATTR(event, "config:0-7" );
+PMU_FORMAT_ATTR(umask, "config:8-15" );
+PMU_FORMAT_ATTR(edge, "config:18" );
+PMU_FORMAT_ATTR(inv, "config:23" );
+PMU_FORMAT_ATTR(cmask, "config:24-31" );
+
+static struct attribute *intel_knc_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask.attr,
+ NULL,
+};
+
+static __initconst struct x86_pmu knc_pmu = {
+ .name = "knc",
+ .handle_irq = x86_pmu_handle_irq,
+ .disable_all = knc_pmu_disable_all,
+ .enable_all = knc_pmu_enable_all,
+ .enable = knc_pmu_enable_event,
+ .disable = knc_pmu_disable_event,
+ .hw_config = x86_pmu_hw_config,
+ .schedule_events = x86_schedule_events,
+ .eventsel = MSR_KNC_EVNTSEL0,
+ .perfctr = MSR_KNC_PERFCTR0,
+ .event_map = knc_pmu_event_map,
+ .max_events = ARRAY_SIZE(knc_perfmon_event_map),
+ .apic = 1,
+ .max_period = (1ULL << 31) - 1,
+ .version = 0,
+ .num_counters = 2,
+ /* in theory 40 bits, early silicon is buggy though */
+ .cntval_bits = 32,
+ .cntval_mask = (1ULL << 32) - 1,
+ .get_event_constraints = x86_get_event_constraints,
+ .event_constraints = knc_event_constraints,
+ .format_attrs = intel_knc_formats_attr,
+};
+
+__init int knc_pmu_init(void)
+{
+ x86_pmu = knc_pmu;
+
+ memcpy(hw_cache_event_ids, knc_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ return 0;
+}
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 966512b2cacf..2e8caf03f593 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -56,6 +56,8 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
switch (boot_cpu_data.x86) {
case 6:
return msr - MSR_P6_PERFCTR0;
+ case 11:
+ return msr - MSR_KNC_PERFCTR0;
case 15:
return msr - MSR_P4_BPU_PERFCTR0;
}
@@ -82,6 +84,8 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
switch (boot_cpu_data.x86) {
case 6:
return msr - MSR_P6_EVNTSEL0;
+ case 11:
+ return msr - MSR_KNC_EVNTSEL0;
case 15:
return msr - MSR_P4_BSU_ESCR0;
}
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 8f9ed1afde8f..a1193aef6d7d 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -299,12 +299,20 @@ ENTRY(ret_from_fork)
CFI_ENDPROC
END(ret_from_fork)
-ENTRY(ret_from_kernel_execve)
- movl %eax, %esp
- movl $0,PT_EAX(%esp)
+ENTRY(ret_from_kernel_thread)
+ CFI_STARTPROC
+ pushl_cfi %eax
+ call schedule_tail
GET_THREAD_INFO(%ebp)
+ popl_cfi %eax
+ pushl_cfi $0x0202 # Reset kernel eflags
+ popfl_cfi
+ movl PT_EBP(%esp),%eax
+ call *PT_EBX(%esp)
+ movl $0,PT_EAX(%esp)
jmp syscall_exit
-END(ret_from_kernel_execve)
+ CFI_ENDPROC
+ENDPROC(ret_from_kernel_thread)
/*
* Interrupt exit functions should be protected against kprobes
@@ -622,6 +630,10 @@ work_notifysig: # deal with pending signals and
movl %esp, %eax
jne work_notifysig_v86 # returning to kernel-space or
# vm86-space
+1:
+#else
+ movl %esp, %eax
+#endif
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
movb PT_CS(%esp), %bl
@@ -632,24 +644,15 @@ work_notifysig: # deal with pending signals and
call do_notify_resume
jmp resume_userspace
+#ifdef CONFIG_VM86
ALIGN
work_notifysig_v86:
pushl_cfi %ecx # save ti_flags for do_notify_resume
call save_v86_state # %eax contains pt_regs pointer
popl_cfi %ecx
movl %eax, %esp
-#else
- movl %esp, %eax
+ jmp 1b
#endif
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- movb PT_CS(%esp), %bl
- andb $SEGMENT_RPL_MASK, %bl
- cmpb $USER_RPL, %bl
- jb resume_kernel
- xorl %edx, %edx
- call do_notify_resume
- jmp resume_userspace
END(work_pending)
# perform syscall exit tracing
@@ -1020,21 +1023,6 @@ END(spurious_interrupt_bug)
*/
.popsection
-ENTRY(ret_from_kernel_thread)
- CFI_STARTPROC
- pushl_cfi %eax
- call schedule_tail
- GET_THREAD_INFO(%ebp)
- popl_cfi %eax
- pushl_cfi $0x0202 # Reset kernel eflags
- popfl_cfi
- movl PT_EBP(%esp),%eax
- call *PT_EBX(%esp)
- call do_exit
- ud2 # padding for call trace
- CFI_ENDPROC
-ENDPROC(ret_from_kernel_thread)
-
#ifdef CONFIG_XEN
/* Xen doesn't set %esp to be precisely what the normal sysenter
entrypoint expects, so fix it up before using the normal path. */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index cdc790c78f32..0c58952d64e8 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -563,15 +563,13 @@ ENTRY(ret_from_fork)
jmp ret_from_sys_call # go to the SYSRET fastpath
1:
- subq $REST_SKIP, %rsp # move the stack pointer back
+ subq $REST_SKIP, %rsp # leave space for volatiles
CFI_ADJUST_CFA_OFFSET REST_SKIP
movq %rbp, %rdi
call *%rbx
- # exit
- mov %eax, %edi
- call do_exit
- ud2 # padding for call trace
-
+ movl $0, RAX(%rsp)
+ RESTORE_REST
+ jmp int_ret_from_sys_call
CFI_ENDPROC
END(ret_from_fork)
@@ -1326,20 +1324,6 @@ bad_gs:
jmp 2b
.previous
-ENTRY(ret_from_kernel_execve)
- movq %rdi, %rsp
- movl $0, RAX(%rsp)
- // RESTORE_REST
- movq 0*8(%rsp), %r15
- movq 1*8(%rsp), %r14
- movq 2*8(%rsp), %r13
- movq 3*8(%rsp), %r12
- movq 4*8(%rsp), %rbp
- movq 5*8(%rsp), %rbx
- addq $(6*8), %rsp
- jmp int_ret_from_sys_call
-END(ret_from_kernel_execve)
-
/* Call softirq on interrupt stack. Interrupts are off. */
ENTRY(call_softirq)
CFI_STARTPROC
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 3f61904365cf..836f8322960e 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -746,7 +746,9 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
{
int err;
+#ifdef CONFIG_DEBUG_RODATA
char opc[BREAK_INSTR_SIZE];
+#endif /* CONFIG_DEBUG_RODATA */
bpt->type = BP_BREAKPOINT;
err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d609be046b57..a2bb18e02839 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -68,6 +68,7 @@
#include <linux/percpu.h>
#include <linux/crash_dump.h>
#include <linux/tboot.h>
+#include <linux/jiffies.h>
#include <video/edid.h>
@@ -1032,6 +1033,8 @@ void __init setup_arch(char **cmdline_p)
mcheck_init();
arch_init_ideal_nops();
+
+ register_refined_jiffies(CLOCK_TICK_RATE);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 8d141b309046..3a3e8c9e280d 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -28,7 +28,7 @@
#include <linux/jiffies.h>
#include <linux/sysctl.h>
#include <linux/topology.h>
-#include <linux/clocksource.h>
+#include <linux/timekeeper_internal.h>
#include <linux/getcpu.h>
#include <linux/cpu.h>
#include <linux/smp.h>
@@ -82,32 +82,41 @@ void update_vsyscall_tz(void)
vsyscall_gtod_data.sys_tz = sys_tz;
}
-void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
- struct clocksource *clock, u32 mult)
+void update_vsyscall(struct timekeeper *tk)
{
- struct timespec monotonic;
+ struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
- write_seqcount_begin(&vsyscall_gtod_data.seq);
+ write_seqcount_begin(&vdata->seq);
/* copy vsyscall data */
- vsyscall_gtod_data.clock.vclock_mode = clock->archdata.vclock_mode;
- vsyscall_gtod_data.clock.cycle_last = clock->cycle_last;
- vsyscall_gtod_data.clock.mask = clock->mask;
- vsyscall_gtod_data.clock.mult = mult;
- vsyscall_gtod_data.clock.shift = clock->shift;
-
- vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
- vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
+ vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode;
+ vdata->clock.cycle_last = tk->clock->cycle_last;
+ vdata->clock.mask = tk->clock->mask;
+ vdata->clock.mult = tk->mult;
+ vdata->clock.shift = tk->shift;
+
+ vdata->wall_time_sec = tk->xtime_sec;
+ vdata->wall_time_snsec = tk->xtime_nsec;
+
+ vdata->monotonic_time_sec = tk->xtime_sec
+ + tk->wall_to_monotonic.tv_sec;
+ vdata->monotonic_time_snsec = tk->xtime_nsec
+ + (tk->wall_to_monotonic.tv_nsec
+ << tk->shift);
+ while (vdata->monotonic_time_snsec >=
+ (((u64)NSEC_PER_SEC) << tk->shift)) {
+ vdata->monotonic_time_snsec -=
+ ((u64)NSEC_PER_SEC) << tk->shift;
+ vdata->monotonic_time_sec++;
+ }
- monotonic = timespec_add(*wall_time, *wtm);
- vsyscall_gtod_data.monotonic_time_sec = monotonic.tv_sec;
- vsyscall_gtod_data.monotonic_time_nsec = monotonic.tv_nsec;
+ vdata->wall_time_coarse.tv_sec = tk->xtime_sec;
+ vdata->wall_time_coarse.tv_nsec = (long)(tk->xtime_nsec >> tk->shift);
- vsyscall_gtod_data.wall_time_coarse = __current_kernel_time();
- vsyscall_gtod_data.monotonic_time_coarse =
- timespec_add(vsyscall_gtod_data.wall_time_coarse, *wtm);
+ vdata->monotonic_time_coarse = timespec_add(vdata->wall_time_coarse,
+ tk->wall_to_monotonic);
- write_seqcount_end(&vsyscall_gtod_data.seq);
+ write_seqcount_end(&vdata->seq);
}
static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 30c4eec033af..07611759ce35 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -14,6 +14,7 @@ config UML_X86
def_bool y
select GENERIC_FIND_FIRST_BIT
select GENERIC_KERNEL_THREAD
+ select GENERIC_KERNEL_EXECVE
config 64BIT
bool "64-bit kernel" if SUBARCH = "x86"
@@ -23,9 +24,11 @@ config X86_32
def_bool !64BIT
select HAVE_AOUT
select ARCH_WANT_IPC_PARSE_VERSION
+ select MODULES_USE_ELF_REL
config X86_64
def_bool 64BIT
+ select MODULES_USE_ELF_RELA
config RWSEM_XCHGADD_ALGORITHM
def_bool X86_XADD && 64BIT
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 885eff49d6ab..4df6c373421a 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -80,7 +80,7 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
}
-notrace static inline long vgetns(void)
+notrace static inline u64 vgetsns(void)
{
long v;
cycles_t cycles;
@@ -91,21 +91,24 @@ notrace static inline long vgetns(void)
else
return 0;
v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask;
- return (v * gtod->clock.mult) >> gtod->clock.shift;
+ return v * gtod->clock.mult;
}
/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
notrace static int __always_inline do_realtime(struct timespec *ts)
{
- unsigned long seq, ns;
+ unsigned long seq;
+ u64 ns;
int mode;
+ ts->tv_nsec = 0;
do {
seq = read_seqcount_begin(&gtod->seq);
mode = gtod->clock.vclock_mode;
ts->tv_sec = gtod->wall_time_sec;
- ts->tv_nsec = gtod->wall_time_nsec;
- ns = vgetns();
+ ns = gtod->wall_time_snsec;
+ ns += vgetsns();
+ ns >>= gtod->clock.shift;
} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
timespec_add_ns(ts, ns);
@@ -114,15 +117,18 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
notrace static int do_monotonic(struct timespec *ts)
{
- unsigned long seq, ns;
+ unsigned long seq;
+ u64 ns;
int mode;
+ ts->tv_nsec = 0;
do {
seq = read_seqcount_begin(&gtod->seq);
mode = gtod->clock.vclock_mode;
ts->tv_sec = gtod->monotonic_time_sec;
- ts->tv_nsec = gtod->monotonic_time_nsec;
- ns = vgetns();
+ ns = gtod->monotonic_time_snsec;
+ ns += vgetsns();
+ ns >>= gtod->clock.shift;
} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
timespec_add_ns(ts, ns);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bf788d34530d..e3497f240eab 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -987,7 +987,16 @@ static void xen_write_cr4(unsigned long cr4)
native_write_cr4(cr4);
}
-
+#ifdef CONFIG_X86_64
+static inline unsigned long xen_read_cr8(void)
+{
+ return 0;
+}
+static inline void xen_write_cr8(unsigned long val)
+{
+ BUG_ON(val);
+}
+#endif
static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
{
int ret;
@@ -1156,6 +1165,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
.read_cr4_safe = native_read_cr4_safe,
.write_cr4 = xen_write_cr4,
+#ifdef CONFIG_X86_64
+ .read_cr8 = xen_read_cr8,
+ .write_cr8 = xen_write_cr8,
+#endif
+
.wbinvd = native_wbinvd,
.read_msr = native_read_msr_safe,
@@ -1164,6 +1178,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
.read_tsc = native_read_tsc,
.read_pmc = native_read_pmc,
+ .read_tscp = native_read_tscp,
+
.iret = xen_iret,
.irq_enable_sysexit = xen_sysexit,
#ifdef CONFIG_X86_64
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index fd28d86fe3d2..6226c99729b9 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -47,6 +47,7 @@
#include <linux/gfp.h>
#include <linux/memblock.h>
#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
#include <trace/events/xen.h>
@@ -2381,6 +2382,43 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
#ifdef CONFIG_XEN_PVHVM
+#ifdef CONFIG_PROC_VMCORE
+/*
+ * This function is used in two contexts:
+ * - the kdump kernel has to check whether a pfn of the crashed kernel
+ * was a ballooned page. vmcore is using this function to decide
+ * whether to access a pfn of the crashed kernel.
+ * - the kexec kernel has to check whether a pfn was ballooned by the
+ * previous kernel. If the pfn is ballooned, handle it properly.
+ * Returns 0 if the pfn is not backed by a RAM page, the caller may
+ * handle the pfn special in this case.
+ */
+static int xen_oldmem_pfn_is_ram(unsigned long pfn)
+{
+ struct xen_hvm_get_mem_type a = {
+ .domid = DOMID_SELF,
+ .pfn = pfn,
+ };
+ int ram;
+
+ if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a))
+ return -ENXIO;
+
+ switch (a.mem_type) {
+ case HVMMEM_mmio_dm:
+ ram = 0;
+ break;
+ case HVMMEM_ram_rw:
+ case HVMMEM_ram_ro:
+ default:
+ ram = 1;
+ break;
+ }
+
+ return ram;
+}
+#endif
+
static void xen_hvm_exit_mmap(struct mm_struct *mm)
{
struct xen_hvm_pagetable_dying a;
@@ -2411,6 +2449,9 @@ void __init xen_hvm_init_mmu_ops(void)
{
if (is_pagetable_dying_supported())
pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
+#ifdef CONFIG_PROC_VMCORE
+ register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram);
+#endif
}
#endif
generated by cgit (git 2.34.1) at 2025-03-31 04:05:40 +0000