summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-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.c10
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c48
-rw-r--r--arch/x86/kernel/cpu/perf_event_knc.c93
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c127
-rw-r--r--arch/x86/kernel/e820.c3
-rw-r--r--arch/x86/kernel/entry_32.S8
-rw-r--r--arch/x86/kernel/entry_64.S16
-rw-r--r--arch/x86/kernel/head_32.S9
-rw-r--r--arch/x86/kernel/kvm.c3
-rw-r--r--arch/x86/kernel/microcode_amd.c8
-rw-r--r--arch/x86/kernel/ptrace.c37
-rw-r--r--arch/x86/kernel/setup.c27
-rw-r--r--arch/x86/kernel/signal.c4
-rw-r--r--arch/x86/kernel/smpboot.c5
-rw-r--r--arch/x86/kernel/uprobes.c16
19 files changed, 364 insertions, 100 deletions
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c265593ec2cd..1817fa911024 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 f7e98a2c0d12..1b7d1656a042 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 698b6ec12e0f..1ac581f38dfa 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 5f88abf07e9c..4f9a3cbfc4a3 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 3373f84d1397..4a3374e61a93 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)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 99d96a4978b5..3cf3d97cce3a 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;
@@ -2926,6 +2937,9 @@ static int __init intel_uncore_init(void)
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return -ENODEV;
+ if (cpu_has_hypervisor)
+ return -ENODEV;
+
ret = uncore_pci_init();
if (ret)
goto fail;
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 7c46bfdbc373..4b7731bf23a8 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 e4dd0f7a0453..7d0270bd793e 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);
}
@@ -158,5 +251,9 @@ __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 ed858e9e9a74..df06ade26bef 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_32.S b/arch/x86/kernel/entry_32.S
index a1193aef6d7d..88b725aa1d52 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1035,7 +1035,7 @@ ENTRY(xen_sysenter_target)
ENTRY(xen_hypervisor_callback)
CFI_STARTPROC
- pushl_cfi $0
+ pushl_cfi $-1 /* orig_ax = -1 => not a system call */
SAVE_ALL
TRACE_IRQS_OFF
@@ -1077,14 +1077,16 @@ ENTRY(xen_failsafe_callback)
2: mov 8(%esp),%es
3: mov 12(%esp),%fs
4: mov 16(%esp),%gs
+ /* EAX == 0 => Category 1 (Bad segment)
+ EAX != 0 => Category 2 (Bad IRET) */
testl %eax,%eax
popl_cfi %eax
lea 16(%esp),%esp
CFI_ADJUST_CFA_OFFSET -16
jz 5f
addl $16,%esp
- jmp iret_exc # EAX != 0 => Category 2 (Bad IRET)
-5: pushl_cfi $0 # EAX == 0 => Category 1 (Bad segment)
+ jmp iret_exc
+5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */
SAVE_ALL
jmp ret_from_exception
CFI_ENDPROC
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 0c58952d64e8..1328fe49a3f1 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -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
@@ -1435,7 +1435,7 @@ ENTRY(xen_failsafe_callback)
CFI_RESTORE r11
addq $0x30,%rsp
CFI_ADJUST_CFA_OFFSET -0x30
- pushq_cfi $0
+ pushq_cfi $-1 /* orig_ax = -1 => not a system call */
SAVE_ALL
jmp error_exit
CFI_ENDPROC
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 957a47aec64e..4dac2f68ed4a 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/kvm.c b/arch/x86/kernel/kvm.c
index b3e5e51bc907..4180a874c764 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -247,7 +247,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
break;
case KVM_PV_REASON_PAGE_NOT_PRESENT:
/* page is swapped out by the host. */
+ rcu_irq_enter();
+ exit_idle();
kvm_async_pf_task_wait((u32)read_cr2());
+ rcu_irq_exit();
break;
case KVM_PV_REASON_PAGE_READY:
rcu_irq_enter();
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7720ff5a9ee2..efdec7cd8e01 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 b00b33a18390..974b67e46dd0 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -22,6 +22,7 @@
#include <linux/perf_event.h>
#include <linux/hw_breakpoint.h>
#include <linux/rcupdate.h>
+#include <linux/module.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -166,6 +167,35 @@ 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);
@@ -1511,6 +1541,13 @@ 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.
+ */
+ rcu_user_exit();
+
audit_syscall_exit(regs);
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 468e98dfd44e..ca45696f30fb 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 29ad351804e9..70b27ee6118e 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -824,10 +824,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
mce_notify_process();
#endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
- if (thread_info_flags & _TIF_UPROBE) {
- clear_thread_flag(TIF_UPROBE);
+ if (thread_info_flags & _TIF_UPROBE)
uprobe_notify_resume(regs);
- }
/* deal with pending signal delivery */
if (thread_info_flags & _TIF_SIGPENDING)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c80a33bc528b..f3e2ec878b8c 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/uprobes.c b/arch/x86/kernel/uprobes.c
index 9538f00827a9..aafa5557b396 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -651,31 +651,19 @@ 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 }
+ * rep=0x66*; nop=0x90
*/
static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
int i;
for (i = 0; i < MAX_UINSN_BYTES; i++) {
- if ((auprobe->insn[i] == 0x66))
+ if (auprobe->insn[i] == 0x66)
continue;
if (auprobe->insn[i] == 0x90)
return true;
- if (i == (MAX_UINSN_BYTES - 1))
- break;
-
- if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x1f))
- return true;
-
- if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x19))
- return true;
-
- if ((auprobe->insn[i] == 0x87) && (auprobe->insn[i+1] == 0xc0))
- return true;
-
break;
}
return false;
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-20 19:34:45 +0300