summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/cstate.c15
-rw-r--r--arch/x86/kernel/apic/apic.c90
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c4
-rw-r--r--arch/x86/kernel/apic/io_apic.c50
-rw-r--r--arch/x86/kernel/apic/vector.c4
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c12
-rw-r--r--arch/x86/kernel/cpu/bugs.c11
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c3
-rw-r--r--arch/x86/kernel/cpu/common.c58
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c9
-rw-r--r--arch/x86/kernel/cpu/intel.c27
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c15
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c8
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c15
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c35
-rw-r--r--arch/x86/kernel/cpu/scattered.c4
-rw-r--r--arch/x86/kernel/cpu/umwait.c200
-rw-r--r--arch/x86/kernel/cpu/vmware.c2
-rw-r--r--arch/x86/kernel/cpu/zhaoxin.c167
-rw-r--r--arch/x86/kernel/fpu/core.c52
-rw-r--r--arch/x86/kernel/fpu/init.c19
-rw-r--r--arch/x86/kernel/fpu/xstate.c11
-rw-r--r--arch/x86/kernel/ftrace.c10
-rw-r--r--arch/x86/kernel/head64.c20
-rw-r--r--arch/x86/kernel/i8253.c25
-rw-r--r--arch/x86/kernel/idt.c3
-rw-r--r--arch/x86/kernel/irq.c2
-rw-r--r--arch/x86/kernel/jailhouse.c2
-rw-r--r--arch/x86/kernel/perf_regs.c7
-rw-r--r--arch/x86/kernel/ptrace.c17
-rw-r--r--arch/x86/kernel/pvclock.c1
-rw-r--r--arch/x86/kernel/smp.c2
-rw-r--r--arch/x86/kernel/time.c7
-rw-r--r--arch/x86/kernel/tsc.c57
-rw-r--r--arch/x86/kernel/tsc_msr.c4
-rw-r--r--arch/x86/kernel/unwind_orc.c26
38 files changed, 789 insertions, 209 deletions
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index a5e5484988fd..caf2edccbad2 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -64,6 +64,21 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
c->x86_stepping >= 0x0e))
flags->bm_check = 1;
}
+
+ if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+ /*
+ * All Zhaoxin CPUs that support C3 share cache.
+ * And caches should not be flushed by software while
+ * entering C3 type state.
+ */
+ flags->bm_check = 1;
+ /*
+ * On all recent Zhaoxin platforms, ARB_DISABLE is a nop.
+ * So, set bm_control to zero to indicate that ARB_DISABLE
+ * is not required while entering C3 type state.
+ */
+ flags->bm_control = 0;
+ }
}
EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 177aa8ef2afa..1bd91cb7b320 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -195,7 +195,7 @@ static struct resource lapic_resource = {
.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
};
-unsigned int lapic_timer_frequency = 0;
+unsigned int lapic_timer_period = 0;
static void apic_pm_activate(void);
@@ -501,7 +501,7 @@ lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot)
if (evt->features & CLOCK_EVT_FEAT_DUMMY)
return 0;
- __setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1);
+ __setup_APIC_LVTT(lapic_timer_period, oneshot, 1);
return 0;
}
@@ -805,11 +805,11 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
static int __init lapic_init_clockevent(void)
{
- if (!lapic_timer_frequency)
+ if (!lapic_timer_period)
return -1;
/* Calculate the scaled math multiplication factor */
- lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+ lapic_clockevent.mult = div_sc(lapic_timer_period/APIC_DIVISOR,
TICK_NSEC, lapic_clockevent.shift);
lapic_clockevent.max_delta_ns =
clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
@@ -821,6 +821,33 @@ static int __init lapic_init_clockevent(void)
return 0;
}
+bool __init apic_needs_pit(void)
+{
+ /*
+ * If the frequencies are not known, PIT is required for both TSC
+ * and apic timer calibration.
+ */
+ if (!tsc_khz || !cpu_khz)
+ return true;
+
+ /* Is there an APIC at all? */
+ if (!boot_cpu_has(X86_FEATURE_APIC))
+ return true;
+
+ /* Deadline timer is based on TSC so no further PIT action required */
+ if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+ return false;
+
+ /* APIC timer disabled? */
+ if (disable_apic_timer)
+ return true;
+ /*
+ * The APIC timer frequency is known already, no PIT calibration
+ * required. If unknown, let the PIT be initialized.
+ */
+ return lapic_timer_period == 0;
+}
+
static int __init calibrate_APIC_clock(void)
{
struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
@@ -839,7 +866,7 @@ static int __init calibrate_APIC_clock(void)
*/
if (!lapic_init_clockevent()) {
apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
- lapic_timer_frequency);
+ lapic_timer_period);
/*
* Direct calibration methods must have an always running
* local APIC timer, no need for broadcast timer.
@@ -884,13 +911,13 @@ static int __init calibrate_APIC_clock(void)
pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
&delta, &deltatsc);
- lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+ lapic_timer_period = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
lapic_init_clockevent();
apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
- lapic_timer_frequency);
+ lapic_timer_period);
if (boot_cpu_has(X86_FEATURE_TSC)) {
apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
@@ -901,13 +928,13 @@ static int __init calibrate_APIC_clock(void)
apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
"%u.%04u MHz.\n",
- lapic_timer_frequency / (1000000 / HZ),
- lapic_timer_frequency % (1000000 / HZ));
+ lapic_timer_period / (1000000 / HZ),
+ lapic_timer_period % (1000000 / HZ));
/*
* Do a sanity check on the APIC calibration result
*/
- if (lapic_timer_frequency < (1000000 / HZ)) {
+ if (lapic_timer_period < (1000000 / HZ)) {
local_irq_enable();
pr_warning("APIC frequency too slow, disabling apic timer\n");
return -1;
@@ -1351,6 +1378,8 @@ void __init init_bsp_APIC(void)
apic_write(APIC_LVT1, value);
}
+static void __init apic_bsp_setup(bool upmode);
+
/* Init the interrupt delivery mode for the BSP */
void __init apic_intr_mode_init(void)
{
@@ -1464,7 +1493,8 @@ static void apic_pending_intr_clear(void)
if (queued) {
if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) {
ntsc = rdtsc();
- max_loops = (cpu_khz << 10) - (ntsc - tsc);
+ max_loops = (long long)cpu_khz << 10;
+ max_loops -= ntsc - tsc;
} else {
max_loops--;
}
@@ -2040,21 +2070,32 @@ __visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs)
entering_irq();
trace_spurious_apic_entry(vector);
+ inc_irq_stat(irq_spurious_count);
+
+ /*
+ * If this is a spurious interrupt then do not acknowledge
+ */
+ if (vector == SPURIOUS_APIC_VECTOR) {
+ /* See SDM vol 3 */
+ pr_info("Spurious APIC interrupt (vector 0xFF) on CPU#%d, should never happen.\n",
+ smp_processor_id());
+ goto out;
+ }
+
/*
- * Check if this really is a spurious interrupt and ACK it
- * if it is a vectored one. Just in case...
- * Spurious interrupts should not be ACKed.
+ * If it is a vectored one, verify it's set in the ISR. If set,
+ * acknowledge it.
*/
v = apic_read(APIC_ISR + ((vector & ~0x1f) >> 1));
- if (v & (1 << (vector & 0x1f)))
+ if (v & (1 << (vector & 0x1f))) {
+ pr_info("Spurious interrupt (vector 0x%02x) on CPU#%d. Acked\n",
+ vector, smp_processor_id());
ack_APIC_irq();
-
- inc_irq_stat(irq_spurious_count);
-
- /* see sw-dev-man vol 3, chapter 7.4.13.5 */
- pr_info("spurious APIC interrupt through vector %02x on CPU#%d, "
- "should never happen.\n", vector, smp_processor_id());
-
+ } else {
+ pr_info("Spurious interrupt (vector 0x%02x) on CPU#%d. Not pending!\n",
+ vector, smp_processor_id());
+ }
+out:
trace_spurious_apic_exit(vector);
exiting_irq();
}
@@ -2415,11 +2456,8 @@ static void __init apic_bsp_up_setup(void)
/**
* apic_bsp_setup - Setup function for local apic and io-apic
* @upmode: Force UP mode (for APIC_init_uniprocessor)
- *
- * Returns:
- * apic_id of BSP APIC
*/
-void __init apic_bsp_setup(bool upmode)
+static void __init apic_bsp_setup(bool upmode)
{
connect_bsp_APIC();
if (upmode)
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index bf083c3f1d73..bbdca603f94a 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -78,7 +78,7 @@ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector)
int cpu = smp_processor_id();
if (cpu < BITS_PER_LONG)
- clear_bit(cpu, &mask);
+ __clear_bit(cpu, &mask);
_flat_send_IPI_mask(mask, vector);
}
@@ -92,7 +92,7 @@ static void flat_send_IPI_allbutself(int vector)
unsigned long mask = cpumask_bits(cpu_online_mask)[0];
if (cpu < BITS_PER_LONG)
- clear_bit(cpu, &mask);
+ __clear_bit(cpu, &mask);
_flat_send_IPI_mask(mask, vector);
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 53aa234a6803..c7bb6c69f21c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -58,6 +58,7 @@
#include <asm/acpi.h>
#include <asm/dma.h>
#include <asm/timer.h>
+#include <asm/time.h>
#include <asm/i8259.h>
#include <asm/setup.h>
#include <asm/irq_remapping.h>
@@ -1893,6 +1894,50 @@ static int ioapic_set_affinity(struct irq_data *irq_data,
return ret;
}
+/*
+ * Interrupt shutdown masks the ioapic pin, but the interrupt might already
+ * be in flight, but not yet serviced by the target CPU. That means
+ * __synchronize_hardirq() would return and claim that everything is calmed
+ * down. So free_irq() would proceed and deactivate the interrupt and free
+ * resources.
+ *
+ * Once the target CPU comes around to service it it will find a cleared
+ * vector and complain. While the spurious interrupt is harmless, the full
+ * release of resources might prevent the interrupt from being acknowledged
+ * which keeps the hardware in a weird state.
+ *
+ * Verify that the corresponding Remote-IRR bits are clear.
+ */
+static int ioapic_irq_get_chip_state(struct irq_data *irqd,
+ enum irqchip_irq_state which,
+ bool *state)
+{
+ struct mp_chip_data *mcd = irqd->chip_data;
+ struct IO_APIC_route_entry rentry;
+ struct irq_pin_list *p;
+
+ if (which != IRQCHIP_STATE_ACTIVE)
+ return -EINVAL;
+
+ *state = false;
+ raw_spin_lock(&ioapic_lock);
+ for_each_irq_pin(p, mcd->irq_2_pin) {
+ rentry = __ioapic_read_entry(p->apic, p->pin);
+ /*
+ * The remote IRR is only valid in level trigger mode. It's
+ * meaning is undefined for edge triggered interrupts and
+ * irrelevant because the IO-APIC treats them as fire and
+ * forget.
+ */
+ if (rentry.irr && rentry.trigger) {
+ *state = true;
+ break;
+ }
+ }
+ raw_spin_unlock(&ioapic_lock);
+ return 0;
+}
+
static struct irq_chip ioapic_chip __read_mostly = {
.name = "IO-APIC",
.irq_startup = startup_ioapic_irq,
@@ -1902,6 +1947,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_eoi = ioapic_ack_level,
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_get_irqchip_state = ioapic_irq_get_chip_state,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
@@ -1914,6 +1960,7 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
.irq_eoi = ioapic_ir_ack_level,
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_get_irqchip_state = ioapic_irq_get_chip_state,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
@@ -2083,6 +2130,9 @@ static inline void __init check_timer(void)
unsigned long flags;
int no_pin1 = 0;
+ if (!global_clock_event)
+ return;
+
local_irq_save(flags);
/*
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index e7cb78aed644..fdacb864c3dd 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -340,7 +340,7 @@ static void clear_irq_vector(struct irq_data *irqd)
trace_vector_clear(irqd->irq, vector, apicd->cpu, apicd->prev_vector,
apicd->prev_cpu);
- per_cpu(vector_irq, apicd->cpu)[vector] = VECTOR_UNUSED;
+ per_cpu(vector_irq, apicd->cpu)[vector] = VECTOR_SHUTDOWN;
irq_matrix_free(vector_matrix, apicd->cpu, vector, managed);
apicd->vector = 0;
@@ -349,7 +349,7 @@ static void clear_irq_vector(struct irq_data *irqd)
if (!vector)
return;
- per_cpu(vector_irq, apicd->prev_cpu)[vector] = VECTOR_UNUSED;
+ per_cpu(vector_irq, apicd->prev_cpu)[vector] = VECTOR_SHUTDOWN;
irq_matrix_free(vector_matrix, apicd->prev_cpu, vector, managed);
apicd->prev_vector = 0;
apicd->move_in_progress = 0;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 7685444a106b..609e499387a1 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -50,7 +50,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
cpumask_copy(tmpmsk, mask);
/* If IPI should not be sent to self, clear current CPU */
if (apic_dest != APIC_DEST_ALLINC)
- cpumask_clear_cpu(smp_processor_id(), tmpmsk);
+ __cpumask_clear_cpu(smp_processor_id(), tmpmsk);
/* Collapse cpus in a cluster so a single IPI per cluster is sent */
for_each_cpu(cpu, tmpmsk) {
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 5102bf7c8192..4b4eb06e117c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -24,6 +24,7 @@ obj-y += match.o
obj-y += bugs.o
obj-y += aperfmperf.o
obj-y += cpuid-deps.o
+obj-y += umwait.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
@@ -38,6 +39,7 @@ obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o
obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o
obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o
obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o
+obj-$(CONFIG_CPU_SUP_ZHAOXIN) += zhaoxin.o
obj-$(CONFIG_X86_MCE) += mce/
obj-$(CONFIG_MTRR) += mtrr/
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index e71a6ff8a67e..e2f319dc992d 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -13,6 +13,7 @@
#include <linux/percpu.h>
#include <linux/cpufreq.h>
#include <linux/smp.h>
+#include <linux/sched/isolation.h>
#include "cpu.h"
@@ -85,6 +86,9 @@ unsigned int aperfmperf_get_khz(int cpu)
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
+ if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+ return 0;
+
aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
return per_cpu(samples.khz, cpu);
}
@@ -101,9 +105,12 @@ void arch_freq_prepare_all(void)
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return;
- for_each_online_cpu(cpu)
+ for_each_online_cpu(cpu) {
+ if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+ continue;
if (!aperfmperf_snapshot_cpu(cpu, now, false))
wait = true;
+ }
if (wait)
msleep(APERFMPERF_REFRESH_DELAY_MS);
@@ -117,6 +124,9 @@ unsigned int arch_freq_get_on_cpu(int cpu)
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
+ if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+ return 0;
+
if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
return per_cpu(samples.khz, cpu);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 03b4cc0ec3a7..66ca906aa790 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -836,6 +836,16 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
}
/*
+ * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper
+ * bit in the mask to allow guests to use the mitigation even in the
+ * case where the host does not enable it.
+ */
+ if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+ static_cpu_has(X86_FEATURE_AMD_SSBD)) {
+ x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
+ }
+
+ /*
* We have three CPU feature flags that are in play here:
* - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
* - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
@@ -852,7 +862,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
x86_amd_ssb_disable();
} else {
x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
- x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
}
}
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 395d46f78582..c7503be92f35 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -658,8 +658,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
if (c->x86 < 0x17) {
/* LLC is at the node level. */
per_cpu(cpu_llc_id, cpu) = node_id;
- } else if (c->x86 == 0x17 &&
- c->x86_model >= 0 && c->x86_model <= 0x1F) {
+ } else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
/*
* LLC is at the core complex level.
* Core complex ID is ApicId[3] for these processors.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2c57fffebf9b..dad20bc891d5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -801,6 +801,30 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
}
}
+static void init_cqm(struct cpuinfo_x86 *c)
+{
+ if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+ c->x86_cache_max_rmid = -1;
+ c->x86_cache_occ_scale = -1;
+ return;
+ }
+
+ /* will be overridden if occupancy monitoring exists */
+ c->x86_cache_max_rmid = cpuid_ebx(0xf);
+
+ if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+ cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+ cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+ u32 eax, ebx, ecx, edx;
+
+ /* QoS sub-leaf, EAX=0Fh, ECX=1 */
+ cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+
+ c->x86_cache_max_rmid = ecx;
+ c->x86_cache_occ_scale = ebx;
+ }
+}
+
void get_cpu_cap(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
@@ -823,6 +847,12 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[CPUID_7_0_EBX] = ebx;
c->x86_capability[CPUID_7_ECX] = ecx;
c->x86_capability[CPUID_7_EDX] = edx;
+
+ /* Check valid sub-leaf index before accessing it */
+ if (eax >= 1) {
+ cpuid_count(0x00000007, 1, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[CPUID_7_1_EAX] = eax;
+ }
}
/* Extended state features: level 0x0000000d */
@@ -832,33 +862,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[CPUID_D_1_EAX] = eax;
}
- /* Additional Intel-defined flags: level 0x0000000F */
- if (c->cpuid_level >= 0x0000000F) {
-
- /* QoS sub-leaf, EAX=0Fh, ECX=0 */
- cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_0_EDX] = edx;
-
- if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
- /* will be overridden if occupancy monitoring exists */
- c->x86_cache_max_rmid = ebx;
-
- /* QoS sub-leaf, EAX=0Fh, ECX=1 */
- cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_1_EDX] = edx;
-
- if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
- ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
- (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
- c->x86_cache_max_rmid = ecx;
- c->x86_cache_occ_scale = ebx;
- }
- } else {
- c->x86_cache_max_rmid = -1;
- c->x86_cache_occ_scale = -1;
- }
- }
-
/* AMD-defined flags: level 0x80000001 */
eax = cpuid_eax(0x80000000);
c->extended_cpuid_level = eax;
@@ -889,6 +892,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
init_scattered_cpuid_features(c);
init_speculation_control(c);
+ init_cqm(c);
/*
* Clear/Set all flags overridden by options, after probe.
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 2c0bd38a44ab..b5353244749b 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -20,6 +20,7 @@ struct cpuid_dep {
* but it's difficult to tell that to the init reference checker.
*/
static const struct cpuid_dep cpuid_deps[] = {
+ { X86_FEATURE_FXSR, X86_FEATURE_FPU },
{ X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE },
{ X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE },
{ X86_FEATURE_XSAVES, X86_FEATURE_XSAVE },
@@ -27,7 +28,11 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_PKU, X86_FEATURE_XSAVE },
{ X86_FEATURE_MPX, X86_FEATURE_XSAVE },
{ X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE },
+ { X86_FEATURE_CMOV, X86_FEATURE_FXSR },
+ { X86_FEATURE_MMX, X86_FEATURE_FXSR },
+ { X86_FEATURE_MMXEXT, X86_FEATURE_MMX },
{ X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR },
+ { X86_FEATURE_XSAVE, X86_FEATURE_FXSR },
{ X86_FEATURE_XMM, X86_FEATURE_FXSR },
{ X86_FEATURE_XMM2, X86_FEATURE_XMM },
{ X86_FEATURE_XMM3, X86_FEATURE_XMM2 },
@@ -59,6 +64,10 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
{}
};
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index f17c1a714779..8d6d92ebeb54 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -66,6 +66,32 @@ void check_mpx_erratum(struct cpuinfo_x86 *c)
}
}
+/*
+ * Processors which have self-snooping capability can handle conflicting
+ * memory type across CPUs by snooping its own cache. However, there exists
+ * CPU models in which having conflicting memory types still leads to
+ * unpredictable behavior, machine check errors, or hangs. Clear this
+ * feature to prevent its use on machines with known erratas.
+ */
+static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c)
+{
+ switch (c->x86_model) {
+ case INTEL_FAM6_CORE_YONAH:
+ case INTEL_FAM6_CORE2_MEROM:
+ case INTEL_FAM6_CORE2_MEROM_L:
+ case INTEL_FAM6_CORE2_PENRYN:
+ case INTEL_FAM6_CORE2_DUNNINGTON:
+ case INTEL_FAM6_NEHALEM:
+ case INTEL_FAM6_NEHALEM_G:
+ case INTEL_FAM6_NEHALEM_EP:
+ case INTEL_FAM6_NEHALEM_EX:
+ case INTEL_FAM6_WESTMERE:
+ case INTEL_FAM6_WESTMERE_EP:
+ case INTEL_FAM6_SANDYBRIDGE:
+ setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP);
+ }
+}
+
static bool ring3mwait_disabled __read_mostly;
static int __init ring3mwait_disable(char *__unused)
@@ -304,6 +330,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
}
check_mpx_erratum(c);
+ check_memory_type_self_snoop_errata(c);
/*
* Get the number of SMT siblings early from the extended topology
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index a813987b5552..cb0fdcaf1415 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -789,13 +789,16 @@ static struct syscore_ops mc_syscore_ops = {
.resume = mc_bp_resume,
};
-static int mc_cpu_online(unsigned int cpu)
+static int mc_cpu_starting(unsigned int cpu)
{
- struct device *dev;
-
- dev = get_cpu_device(cpu);
microcode_update_cpu(cpu);
pr_debug("CPU%d added\n", cpu);
+ return 0;
+}
+
+static int mc_cpu_online(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
if (sysfs_create_group(&dev->kobj, &mc_attr_group))
pr_err("Failed to create group for CPU%d\n", cpu);
@@ -872,7 +875,9 @@ int __init microcode_init(void)
goto out_ucode_group;
register_syscore_ops(&mc_syscore_ops);
- cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:online",
+ cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting",
+ mc_cpu_starting, NULL);
+ cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
mc_cpu_online, mc_cpu_down_prep);
pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 7df29f08871b..062f77279ce3 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -17,6 +17,7 @@
#include <linux/irq.h>
#include <linux/kexec.h>
#include <linux/i8253.h>
+#include <linux/random.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
#include <asm/hyperv-tlfs.h>
@@ -80,6 +81,7 @@ __visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs)
inc_irq_stat(hyperv_stimer0_count);
if (hv_stimer0_handler)
hv_stimer0_handler();
+ add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0);
ack_APIC_irq();
exiting_irq();
@@ -89,7 +91,7 @@ __visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs)
int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void))
{
*vector = HYPERV_STIMER0_VECTOR;
- *irq = 0; /* Unused on x86/x64 */
+ *irq = -1; /* Unused on x86/x64 */
hv_stimer0_handler = handler;
return 0;
}
@@ -266,9 +268,9 @@ static void __init ms_hyperv_init_platform(void)
rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
- lapic_timer_frequency = hv_lapic_frequency;
+ lapic_timer_period = hv_lapic_frequency;
pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n",
- lapic_timer_frequency);
+ lapic_timer_period);
}
register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9356c1c9024d..aa5c064a6a22 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -743,7 +743,15 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
cr0 = read_cr0() | X86_CR0_CD;
write_cr0(cr0);
- wbinvd();
+
+ /*
+ * Cache flushing is the most time-consuming step when programming
+ * the MTRRs. Fortunately, as per the Intel Software Development
+ * Manual, we can skip it if the processor supports cache self-
+ * snooping.
+ */
+ if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+ wbinvd();
/* Save value of CR4 and clear Page Global Enable (bit 7) */
if (boot_cpu_has(X86_FEATURE_PGE)) {
@@ -760,7 +768,10 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
/* Disable MTRRs, and set the default type to uncached */
mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
- wbinvd();
+
+ /* Again, only flush caches if we have to. */
+ if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+ wbinvd();
}
static void post_set(void) __releases(set_atomicity_lock)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 2131b8bbaad7..2f4824793798 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -796,8 +796,12 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
- u32 sw_shareable = 0, hw_shareable = 0;
- u32 exclusive = 0, pseudo_locked = 0;
+ /*
+ * Use unsigned long even though only 32 bits are used to ensure
+ * test_bit() is used safely.
+ */
+ unsigned long sw_shareable = 0, hw_shareable = 0;
+ unsigned long exclusive = 0, pseudo_locked = 0;
struct rdt_domain *dom;
int i, hwb, swb, excl, psl;
enum rdtgrp_mode mode;
@@ -842,10 +846,10 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
}
for (i = r->cache.cbm_len - 1; i >= 0; i--) {
pseudo_locked = dom->plr ? dom->plr->cbm : 0;
- hwb = test_bit(i, (unsigned long *)&hw_shareable);
- swb = test_bit(i, (unsigned long *)&sw_shareable);
- excl = test_bit(i, (unsigned long *)&exclusive);
- psl = test_bit(i, (unsigned long *)&pseudo_locked);
+ hwb = test_bit(i, &hw_shareable);
+ swb = test_bit(i, &sw_shareable);
+ excl = test_bit(i, &exclusive);
+ psl = test_bit(i, &pseudo_locked);
if (hwb && swb)
seq_putc(seq, 'X');
else if (hwb && !swb)
@@ -2486,26 +2490,19 @@ out_destroy:
*/
static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
{
- /*
- * Convert the u32 _val to an unsigned long required by all the bit
- * operations within this function. No more than 32 bits of this
- * converted value can be accessed because all bit operations are
- * additionally provided with cbm_len that is initialized during
- * hardware enumeration using five bits from the EAX register and
- * thus never can exceed 32 bits.
- */
- unsigned long *val = (unsigned long *)_val;
+ unsigned long val = *_val;
unsigned int cbm_len = r->cache.cbm_len;
unsigned long first_bit, zero_bit;
- if (*val == 0)
+ if (val == 0)
return;
- first_bit = find_first_bit(val, cbm_len);
- zero_bit = find_next_zero_bit(val, cbm_len, first_bit);
+ first_bit = find_first_bit(&val, cbm_len);
+ zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
/* Clear any remaining bits to ensure contiguous region */
- bitmap_clear(val, zero_bit, cbm_len - zero_bit);
+ bitmap_clear(&val, zero_bit, cbm_len - zero_bit);
+ *_val = (u32)val;
}
/*
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 94aa1c72ca98..adf9b71386ef 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -26,6 +26,10 @@ struct cpuid_bit {
static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
+ { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 },
+ { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 },
+ { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 },
+ { X86_FEATURE_CQM_MBM_LOCAL, CPUID_EDX, 2, 0x0000000f, 1 },
{ X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 },
{ X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 },
{ X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 },
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
new file mode 100644
index 000000000000..6a204e7336c1
--- /dev/null
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/syscore_ops.h>
+#include <linux/suspend.h>
+#include <linux/cpu.h>
+
+#include <asm/msr.h>
+
+#define UMWAIT_C02_ENABLE 0
+
+#define UMWAIT_CTRL_VAL(max_time, c02_disable) \
+ (((max_time) & MSR_IA32_UMWAIT_CONTROL_TIME_MASK) | \
+ ((c02_disable) & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE))
+
+/*
+ * Cache IA32_UMWAIT_CONTROL MSR. This is a systemwide control. By default,
+ * umwait max time is 100000 in TSC-quanta and C0.2 is enabled
+ */
+static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
+
+/*
+ * Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR in
+ * the sysfs write functions.
+ */
+static DEFINE_MUTEX(umwait_lock);
+
+static void umwait_update_control_msr(void * unused)
+{
+ lockdep_assert_irqs_disabled();
+ wrmsr(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached), 0);
+}
+
+/*
+ * The CPU hotplug callback sets the control MSR to the global control
+ * value.
+ *
+ * Disable interrupts so the read of umwait_control_cached and the WRMSR
+ * are protected against a concurrent sysfs write. Otherwise the sysfs
+ * write could update the cached value after it had been read on this CPU
+ * and issue the IPI before the old value had been written. The IPI would
+ * interrupt, write the new value and after return from IPI the previous
+ * value would be written by this CPU.
+ *
+ * With interrupts disabled the upcoming CPU either sees the new control
+ * value or the IPI is updating this CPU to the new control value after
+ * interrupts have been reenabled.
+ */
+static int umwait_cpu_online(unsigned int cpu)
+{
+ local_irq_disable();
+ umwait_update_control_msr(NULL);
+ local_irq_enable();
+ return 0;
+}
+
+/*
+ * On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which
+ * is the only active CPU at this time. The MSR is set up on the APs via the
+ * CPU hotplug callback.
+ *
+ * This function is invoked on resume from suspend and hibernation. On
+ * resume from suspend the restore should be not required, but we neither
+ * trust the firmware nor does it matter if the same value is written
+ * again.
+ */
+static void umwait_syscore_resume(void)
+{
+ umwait_update_control_msr(NULL);
+}
+
+static struct syscore_ops umwait_syscore_ops = {
+ .resume = umwait_syscore_resume,
+};
+
+/* sysfs interface */
+
+/*
+ * When bit 0 in IA32_UMWAIT_CONTROL MSR is 1, C0.2 is disabled.
+ * Otherwise, C0.2 is enabled.
+ */
+static inline bool umwait_ctrl_c02_enabled(u32 ctrl)
+{
+ return !(ctrl & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE);
+}
+
+static inline u32 umwait_ctrl_max_time(u32 ctrl)
+{
+ return ctrl & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+}
+
+static inline void umwait_update_control(u32 maxtime, bool c02_enable)
+{
+ u32 ctrl = maxtime & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+
+ if (!c02_enable)
+ ctrl |= MSR_IA32_UMWAIT_CONTROL_C02_DISABLE;
+
+ WRITE_ONCE(umwait_control_cached, ctrl);
+ /* Propagate to all CPUs */
+ on_each_cpu(umwait_update_control_msr, NULL, 1);
+}
+
+static ssize_t
+enable_c02_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ u32 ctrl = READ_ONCE(umwait_control_cached);
+
+ return sprintf(buf, "%d\n", umwait_ctrl_c02_enabled(ctrl));
+}
+
+static ssize_t enable_c02_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ bool c02_enable;
+ u32 ctrl;
+ int ret;
+
+ ret = kstrtobool(buf, &c02_enable);
+ if (ret)
+ return ret;
+
+ mutex_lock(&umwait_lock);
+
+ ctrl = READ_ONCE(umwait_control_cached);
+ if (c02_enable != umwait_ctrl_c02_enabled(ctrl))
+ umwait_update_control(ctrl, c02_enable);
+
+ mutex_unlock(&umwait_lock);
+
+ return count;
+}
+static DEVICE_ATTR_RW(enable_c02);
+
+static ssize_t
+max_time_show(struct device *kobj, struct device_attribute *attr, char *buf)
+{
+ u32 ctrl = READ_ONCE(umwait_control_cached);
+
+ return sprintf(buf, "%u\n", umwait_ctrl_max_time(ctrl));
+}
+
+static ssize_t max_time_store(struct device *kobj,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ u32 max_time, ctrl;
+ int ret;
+
+ ret = kstrtou32(buf, 0, &max_time);
+ if (ret)
+ return ret;
+
+ /* bits[1:0] must be zero */
+ if (max_time & ~MSR_IA32_UMWAIT_CONTROL_TIME_MASK)
+ return -EINVAL;
+
+ mutex_lock(&umwait_lock);
+
+ ctrl = READ_ONCE(umwait_control_cached);
+ if (max_time != umwait_ctrl_max_time(ctrl))
+ umwait_update_control(max_time, umwait_ctrl_c02_enabled(ctrl));
+
+ mutex_unlock(&umwait_lock);
+
+ return count;
+}
+static DEVICE_ATTR_RW(max_time);
+
+static struct attribute *umwait_attrs[] = {
+ &dev_attr_enable_c02.attr,
+ &dev_attr_max_time.attr,
+ NULL
+};
+
+static struct attribute_group umwait_attr_group = {
+ .attrs = umwait_attrs,
+ .name = "umwait_control",
+};
+
+static int __init umwait_init(void)
+{
+ struct device *dev;
+ int ret;
+
+ if (!boot_cpu_has(X86_FEATURE_WAITPKG))
+ return -ENODEV;
+
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
+ umwait_cpu_online, NULL);
+
+ register_syscore_ops(&umwait_syscore_ops);
+
+ /*
+ * Add umwait control interface. Ignore failure, so at least the
+ * default values are set up in case the machine manages to boot.
+ */
+ dev = cpu_subsys.dev_root;
+ return sysfs_create_group(&dev->kobj, &umwait_attr_group);
+}
+device_initcall(umwait_init);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 0eda91f8eeac..3c648476d4fb 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -157,7 +157,7 @@ static void __init vmware_platform_setup(void)
#ifdef CONFIG_X86_LOCAL_APIC
/* Skip lapic calibration since we know the bus frequency. */
- lapic_timer_frequency = ecx / HZ;
+ lapic_timer_period = ecx / HZ;
pr_info("Host bus clock speed read from hypervisor : %u Hz\n",
ecx);
#endif
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
new file mode 100644
index 000000000000..8e6f2f4b4afe
--- /dev/null
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+
+#include <asm/cpufeature.h>
+
+#include "cpu.h"
+
+#define MSR_ZHAOXIN_FCR57 0x00001257
+
+#define ACE_PRESENT (1 << 6)
+#define ACE_ENABLED (1 << 7)
+#define ACE_FCR (1 << 7) /* MSR_ZHAOXIN_FCR */
+
+#define RNG_PRESENT (1 << 2)
+#define RNG_ENABLED (1 << 3)
+#define RNG_ENABLE (1 << 8) /* MSR_ZHAOXIN_RNG */
+
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020
+
+static void init_zhaoxin_cap(struct cpuinfo_x86 *c)
+{
+ u32 lo, hi;
+
+ /* Test for Extended Feature Flags presence */
+ if (cpuid_eax(0xC0000000) >= 0xC0000001) {
+ u32 tmp = cpuid_edx(0xC0000001);
+
+ /* Enable ACE unit, if present and disabled */
+ if ((tmp & (ACE_PRESENT | ACE_ENABLED)) == ACE_PRESENT) {
+ rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ /* Enable ACE unit */
+ lo |= ACE_FCR;
+ wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ pr_info("CPU: Enabled ACE h/w crypto\n");
+ }
+
+ /* Enable RNG unit, if present and disabled */
+ if ((tmp & (RNG_PRESENT | RNG_ENABLED)) == RNG_PRESENT) {
+ rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ /* Enable RNG unit */
+ lo |= RNG_ENABLE;
+ wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ pr_info("CPU: Enabled h/w RNG\n");
+ }
+
+ /*
+ * Store Extended Feature Flags as word 5 of the CPU
+ * capability bit array
+ */
+ c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001);
+ }
+
+ if (c->x86 >= 0x6)
+ set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+ cpu_detect_cache_sizes(c);
+}
+
+static void early_init_zhaoxin(struct cpuinfo_x86 *c)
+{
+ if (c->x86 >= 0x6)
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+#ifdef CONFIG_X86_64
+ set_cpu_cap(c, X86_FEATURE_SYSENTER32);
+#endif
+ if (c->x86_power & (1 << 8)) {
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+ set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+ }
+
+ if (c->cpuid_level >= 0x00000001) {
+ u32 eax, ebx, ecx, edx;
+
+ cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
+ /*
+ * If HTT (EDX[28]) is set EBX[16:23] contain the number of
+ * apicids which are reserved per package. Store the resulting
+ * shift value for the package management code.
+ */
+ if (edx & (1U << 28))
+ c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
+ }
+
+}
+
+static void zhaoxin_detect_vmx_virtcap(struct cpuinfo_x86 *c)
+{
+ u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+ msr_ctl = vmx_msr_high | vmx_msr_low;
+
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+ set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+ set_cpu_cap(c, X86_FEATURE_VNMI);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+ vmx_msr_low, vmx_msr_high);
+ msr_ctl2 = vmx_msr_high | vmx_msr_low;
+ if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+ (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+ set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+ set_cpu_cap(c, X86_FEATURE_EPT);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+ set_cpu_cap(c, X86_FEATURE_VPID);
+ }
+}
+
+static void init_zhaoxin(struct cpuinfo_x86 *c)
+{
+ early_init_zhaoxin(c);
+ init_intel_cacheinfo(c);
+ detect_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+ detect_ht(c);
+#endif
+
+ if (c->cpuid_level > 9) {
+ unsigned int eax = cpuid_eax(10);
+
+ /*
+ * Check for version and the number of counters
+ * Version(eax[7:0]) can't be 0;
+ * Counters(eax[15:8]) should be greater than 1;
+ */
+ if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1))
+ set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+ }
+
+ if (c->x86 >= 0x6)
+ init_zhaoxin_cap(c);
+#ifdef CONFIG_X86_64
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+#endif
+
+ if (cpu_has(c, X86_FEATURE_VMX))
+ zhaoxin_detect_vmx_virtcap(c);
+}
+
+#ifdef CONFIG_X86_32
+static unsigned int
+zhaoxin_size_cache(struct cpuinfo_x86 *c, unsigned int size)
+{
+ return size;
+}
+#endif
+
+static const struct cpu_dev zhaoxin_cpu_dev = {
+ .c_vendor = "zhaoxin",
+ .c_ident = { " Shanghai " },
+ .c_early_init = early_init_zhaoxin,
+ .c_init = init_zhaoxin,
+#ifdef CONFIG_X86_32
+ .legacy_cache_size = zhaoxin_size_cache,
+#endif
+ .c_x86_vendor = X86_VENDOR_ZHAOXIN,
+};
+
+cpu_dev_register(zhaoxin_cpu_dev);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 649fbc3fcf9f..12c70840980e 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -43,18 +43,6 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu);
*/
DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
-static void kernel_fpu_disable(void)
-{
- WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
- this_cpu_write(in_kernel_fpu, true);
-}
-
-static void kernel_fpu_enable(void)
-{
- WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
- this_cpu_write(in_kernel_fpu, false);
-}
-
static bool kernel_fpu_disabled(void)
{
return this_cpu_read(in_kernel_fpu);
@@ -94,42 +82,33 @@ bool irq_fpu_usable(void)
}
EXPORT_SYMBOL(irq_fpu_usable);
-static void __kernel_fpu_begin(void)
+void kernel_fpu_begin(void)
{
- struct fpu *fpu = &current->thread.fpu;
+ preempt_disable();
WARN_ON_FPU(!irq_fpu_usable());
+ WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
- kernel_fpu_disable();
+ this_cpu_write(in_kernel_fpu, true);
- if (!(current->flags & PF_KTHREAD)) {
- if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
- set_thread_flag(TIF_NEED_FPU_LOAD);
- /*
- * Ignore return value -- we don't care if reg state
- * is clobbered.
- */
- copy_fpregs_to_fpstate(fpu);
- }
+ if (!(current->flags & PF_KTHREAD) &&
+ !test_thread_flag(TIF_NEED_FPU_LOAD)) {
+ set_thread_flag(TIF_NEED_FPU_LOAD);
+ /*
+ * Ignore return value -- we don't care if reg state
+ * is clobbered.
+ */
+ copy_fpregs_to_fpstate(&current->thread.fpu);
}
__cpu_invalidate_fpregs_state();
}
-
-static void __kernel_fpu_end(void)
-{
- kernel_fpu_enable();
-}
-
-void kernel_fpu_begin(void)
-{
- preempt_disable();
- __kernel_fpu_begin();
-}
EXPORT_SYMBOL_GPL(kernel_fpu_begin);
void kernel_fpu_end(void)
{
- __kernel_fpu_end();
+ WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+
+ this_cpu_write(in_kernel_fpu, false);
preempt_enable();
}
EXPORT_SYMBOL_GPL(kernel_fpu_end);
@@ -155,7 +134,6 @@ void fpu__save(struct fpu *fpu)
trace_x86_fpu_after_save(fpu);
fpregs_unlock();
}
-EXPORT_SYMBOL_GPL(fpu__save);
/*
* Legacy x87 fpstate state init:
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index ef0030e3fe6b..6ce7e0a23268 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -204,12 +204,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
*/
if (!boot_cpu_has(X86_FEATURE_FPU)) {
- /*
- * Disable xsave as we do not support it if i387
- * emulation is enabled.
- */
- setup_clear_cpu_cap(X86_FEATURE_XSAVE);
- setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
fpu_kernel_xstate_size = sizeof(struct swregs_state);
} else {
if (boot_cpu_has(X86_FEATURE_FXSR))
@@ -252,17 +246,20 @@ static void __init fpu__init_parse_early_param(void)
char *argptr = arg;
int bit;
+#ifdef CONFIG_X86_32
if (cmdline_find_option_bool(boot_command_line, "no387"))
+#ifdef CONFIG_MATH_EMULATION
setup_clear_cpu_cap(X86_FEATURE_FPU);
+#else
+ pr_err("Option 'no387' required CONFIG_MATH_EMULATION enabled.\n");
+#endif
- if (cmdline_find_option_bool(boot_command_line, "nofxsr")) {
+ if (cmdline_find_option_bool(boot_command_line, "nofxsr"))
setup_clear_cpu_cap(X86_FEATURE_FXSR);
- setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
- setup_clear_cpu_cap(X86_FEATURE_XMM);
- }
+#endif
if (cmdline_find_option_bool(boot_command_line, "noxsave"))
- fpu__xstate_clear_all_cpu_caps();
+ setup_clear_cpu_cap(X86_FEATURE_XSAVE);
if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 3c36dd1784db..7b4c52aa929f 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -68,15 +68,6 @@ static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
unsigned int fpu_user_xstate_size;
/*
- * Clear all of the X86_FEATURE_* bits that are unavailable
- * when the CPU has no XSAVE support.
- */
-void fpu__xstate_clear_all_cpu_caps(void)
-{
- setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-}
-
-/*
* Return whether the system supports a given xfeature.
*
* Also return the name of the (most advanced) feature that the caller requested:
@@ -709,7 +700,7 @@ static void fpu__init_disable_system_xstate(void)
{
xfeatures_mask = 0;
cr4_clear_bits(X86_CR4_OSXSAVE);
- fpu__xstate_clear_all_cpu_caps();
+ setup_clear_cpu_cap(X86_FEATURE_XSAVE);
}
/*
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 0927bb158ffc..76228525acd0 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -22,6 +22,7 @@
#include <linux/init.h>
#include <linux/list.h>
#include <linux/module.h>
+#include <linux/memory.h>
#include <trace/syscall.h>
@@ -34,16 +35,25 @@
#ifdef CONFIG_DYNAMIC_FTRACE
int ftrace_arch_code_modify_prepare(void)
+ __acquires(&text_mutex)
{
+ /*
+ * Need to grab text_mutex to prevent a race from module loading
+ * and live kernel patching from changing the text permissions while
+ * ftrace has it set to "read/write".
+ */
+ mutex_lock(&text_mutex);
set_kernel_text_rw();
set_all_modules_text_rw();
return 0;
}
int ftrace_arch_code_modify_post_process(void)
+ __releases(&text_mutex)
{
set_all_modules_text_ro();
set_kernel_text_ro();
+ mutex_unlock(&text_mutex);
return 0;
}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 16b1cbd3a61e..29ffa495bd1c 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -184,24 +184,25 @@ unsigned long __head __startup_64(unsigned long physaddr,
pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
if (la57) {
- p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
+ p4d = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++],
+ physaddr);
i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
- i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D;
- p4d[i + 0] = (pgdval_t)pud + pgtable_flags;
- p4d[i + 1] = (pgdval_t)pud + pgtable_flags;
+ i = physaddr >> P4D_SHIFT;
+ p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
+ p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
} else {
i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
}
- i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD;
- pud[i + 0] = (pudval_t)pmd + pgtable_flags;
- pud[i + 1] = (pudval_t)pmd + pgtable_flags;
+ i = physaddr >> PUD_SHIFT;
+ pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
+ pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
/* Filter out unsupported __PAGE_KERNEL_* bits: */
@@ -211,8 +212,9 @@ unsigned long __head __startup_64(unsigned long physaddr,
pmd_entry += physaddr;
for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) {
- int idx = i + (physaddr >> PMD_SHIFT) % PTRS_PER_PMD;
- pmd[idx] = pmd_entry + i * PMD_SIZE;
+ int idx = i + (physaddr >> PMD_SHIFT);
+
+ pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE;
}
/*
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 0d307a657abb..2b7999a1a50a 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -8,6 +8,7 @@
#include <linux/timex.h>
#include <linux/i8253.h>
+#include <asm/apic.h>
#include <asm/hpet.h>
#include <asm/time.h>
#include <asm/smp.h>
@@ -18,10 +19,32 @@
*/
struct clock_event_device *global_clock_event;
-void __init setup_pit_timer(void)
+/*
+ * Modern chipsets can disable the PIT clock which makes it unusable. It
+ * would be possible to enable the clock but the registers are chipset
+ * specific and not discoverable. Avoid the whack a mole game.
+ *
+ * These platforms have discoverable TSC/CPU frequencies but this also
+ * requires to know the local APIC timer frequency as it normally is
+ * calibrated against the PIT interrupt.
+ */
+static bool __init use_pit(void)
+{
+ if (!IS_ENABLED(CONFIG_X86_TSC) || !boot_cpu_has(X86_FEATURE_TSC))
+ return true;
+
+ /* This also returns true when APIC is disabled */
+ return apic_needs_pit();
+}
+
+bool __init pit_timer_init(void)
{
+ if (!use_pit())
+ return false;
+
clockevent_i8253_init(true);
global_clock_event = &i8253_clockevent;
+ return true;
}
#ifndef CONFIG_X86_64
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index d2482bbbe3d0..87ef69a72c52 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -319,7 +319,8 @@ void __init idt_setup_apic_and_irq_gates(void)
#ifdef CONFIG_X86_LOCAL_APIC
for_each_clear_bit_from(i, system_vectors, NR_VECTORS) {
set_bit(i, system_vectors);
- set_intr_gate(i, spurious_interrupt);
+ entry = spurious_entries_start + 8 * (i - FIRST_SYSTEM_VECTOR);
+ set_intr_gate(i, entry);
}
#endif
}
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 9b68b5b00ac9..cc496eb7a8d2 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -247,7 +247,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
if (!handle_irq(desc, regs)) {
ack_APIC_irq();
- if (desc != VECTOR_RETRIGGERED) {
+ if (desc != VECTOR_RETRIGGERED && desc != VECTOR_SHUTDOWN) {
pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n",
__func__, smp_processor_id(),
vector);
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 1b2ee55a2dfb..ba95bc70460d 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -45,7 +45,7 @@ static void jailhouse_get_wallclock(struct timespec64 *now)
static void __init jailhouse_timer_init(void)
{
- lapic_timer_frequency = setup_data.apic_khz * (1000 / HZ);
+ lapic_timer_period = setup_data.apic_khz * (1000 / HZ);
}
static unsigned long jailhouse_get_tsc(void)
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 07c30ee17425..bb7e1132290b 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -74,6 +74,9 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
return regs_get_register(regs, pt_regs_offset[idx]);
}
+#define PERF_REG_X86_RESERVED (((1ULL << PERF_REG_X86_XMM0) - 1) & \
+ ~((1ULL << PERF_REG_X86_MAX) - 1))
+
#ifdef CONFIG_X86_32
#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
(1ULL << PERF_REG_X86_R9) | \
@@ -86,7 +89,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
int perf_reg_validate(u64 mask)
{
- if (!mask || (mask & REG_NOSUPPORT))
+ if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED)))
return -EINVAL;
return 0;
@@ -112,7 +115,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
int perf_reg_validate(u64 mask)
{
- if (!mask || (mask & REG_NOSUPPORT))
+ if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED)))
return -EINVAL;
return 0;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index a166c960bc9e..53f34121fdca 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -397,22 +397,12 @@ static int putreg(struct task_struct *child,
case offsetof(struct user_regs_struct,fs_base):
if (value >= TASK_SIZE_MAX)
return -EIO;
- /*
- * When changing the FS base, use do_arch_prctl_64()
- * to set the index to zero and to set the base
- * as requested.
- */
- if (child->thread.fsbase != value)
- return do_arch_prctl_64(child, ARCH_SET_FS, value);
+ x86_fsbase_write_task(child, value);
return 0;
case offsetof(struct user_regs_struct,gs_base):
- /*
- * Exactly the same here as the %fs handling above.
- */
if (value >= TASK_SIZE_MAX)
return -EIO;
- if (child->thread.gsbase != value)
- return do_arch_prctl_64(child, ARCH_SET_GS, value);
+ x86_gsbase_write_task(child, value);
return 0;
#endif
}
@@ -747,9 +737,6 @@ static int ioperm_get(struct task_struct *target,
void ptrace_disable(struct task_struct *child)
{
user_disable_single_step(child);
-#ifdef TIF_SYSCALL_EMU
- clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
-#endif
}
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 0ff3e294d0e5..10125358b9c4 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -3,6 +3,7 @@
*/
+#include <linux/clocksource.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 4693e2f3a03e..96421f97e75c 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -144,7 +144,7 @@ void native_send_call_func_ipi(const struct cpumask *mask)
}
cpumask_copy(allbutself, cpu_online_mask);
- cpumask_clear_cpu(smp_processor_id(), allbutself);
+ __cpumask_clear_cpu(smp_processor_id(), allbutself);
if (cpumask_equal(mask, allbutself) &&
cpumask_equal(cpu_online_mask, cpu_callout_mask))
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 0e14f6c0d35e..07c0e960b3f3 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -82,8 +82,11 @@ static void __init setup_default_timer_irq(void)
/* Default timer init function */
void __init hpet_time_init(void)
{
- if (!hpet_enable())
- setup_pit_timer();
+ if (!hpet_enable()) {
+ if (!pit_timer_init())
+ return;
+ }
+
setup_default_timer_irq();
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 0b29e58f288e..59b57605e66c 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -632,31 +632,38 @@ unsigned long native_calibrate_tsc(void)
crystal_khz = ecx_hz / 1000;
- if (crystal_khz == 0) {
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
- crystal_khz = 24000; /* 24.0 MHz */
- break;
- case INTEL_FAM6_ATOM_GOLDMONT_X:
- crystal_khz = 25000; /* 25.0 MHz */
- break;
- case INTEL_FAM6_ATOM_GOLDMONT:
- crystal_khz = 19200; /* 19.2 MHz */
- break;
- }
- }
+ /*
+ * Denverton SoCs don't report crystal clock, and also don't support
+ * CPUID.0x16 for the calculation below, so hardcode the 25MHz crystal
+ * clock.
+ */
+ if (crystal_khz == 0 &&
+ boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_X)
+ crystal_khz = 25000;
- if (crystal_khz == 0)
- return 0;
/*
- * TSC frequency determined by CPUID is a "hardware reported"
+ * TSC frequency reported directly by CPUID is a "hardware reported"
* frequency and is the most accurate one so far we have. This
* is considered a known frequency.
*/
- setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+ if (crystal_khz != 0)
+ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+
+ /*
+ * Some Intel SoCs like Skylake and Kabylake don't report the crystal
+ * clock, but we can easily calculate it to a high degree of accuracy
+ * by considering the crystal ratio and the CPU speed.
+ */
+ if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= 0x16) {
+ unsigned int eax_base_mhz, ebx, ecx, edx;
+
+ cpuid(0x16, &eax_base_mhz, &ebx, &ecx, &edx);
+ crystal_khz = eax_base_mhz * 1000 *
+ eax_denominator / ebx_numerator;
+ }
+
+ if (crystal_khz == 0)
+ return 0;
/*
* For Atom SoCs TSC is the only reliable clocksource.
@@ -665,6 +672,16 @@ unsigned long native_calibrate_tsc(void)
if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT)
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * The local APIC appears to be fed by the core crystal clock
+ * (which sounds entirely sensible). We can set the global
+ * lapic_timer_period here to avoid having to calibrate the APIC
+ * timer later.
+ */
+ lapic_timer_period = crystal_khz * 1000 / HZ;
+#endif
+
return crystal_khz * ebx_numerator / eax_denominator;
}
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 3d0e9aeea7c8..067858fe4db8 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -71,7 +71,7 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
/*
* MSR-based CPU/TSC frequency discovery for certain CPUs.
*
- * Set global "lapic_timer_frequency" to bus_clock_cycles/jiffy
+ * Set global "lapic_timer_period" to bus_clock_cycles/jiffy
* Return processor base frequency in KHz, or 0 on failure.
*/
unsigned long cpu_khz_from_msr(void)
@@ -104,7 +104,7 @@ unsigned long cpu_khz_from_msr(void)
res = freq * ratio;
#ifdef CONFIG_X86_LOCAL_APIC
- lapic_timer_frequency = (freq * 1000) / HZ;
+ lapic_timer_period = (freq * 1000) / HZ;
#endif
/*
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 33b66b5c5aec..72b997eaa1fc 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -82,9 +82,9 @@ static struct orc_entry *orc_find(unsigned long ip);
* But they are copies of the ftrace entries that are static and
* defined in ftrace_*.S, which do have orc entries.
*
- * If the undwinder comes across a ftrace trampoline, then find the
+ * If the unwinder comes across a ftrace trampoline, then find the
* ftrace function that was used to create it, and use that ftrace
- * function's orc entrie, as the placement of the return code in
+ * function's orc entry, as the placement of the return code in
* the stack will be identical.
*/
static struct orc_entry *orc_ftrace_find(unsigned long ip)
@@ -128,6 +128,16 @@ static struct orc_entry null_orc_entry = {
.type = ORC_TYPE_CALL
};
+/* Fake frame pointer entry -- used as a fallback for generated code */
+static struct orc_entry orc_fp_entry = {
+ .type = ORC_TYPE_CALL,
+ .sp_reg = ORC_REG_BP,
+ .sp_offset = 16,
+ .bp_reg = ORC_REG_PREV_SP,
+ .bp_offset = -16,
+ .end = 0,
+};
+
static struct orc_entry *orc_find(unsigned long ip)
{
static struct orc_entry *orc;
@@ -392,8 +402,16 @@ bool unwind_next_frame(struct unwind_state *state)
* calls and calls to noreturn functions.
*/
orc = orc_find(state->signal ? state->ip : state->ip - 1);
- if (!orc)
- goto err;
+ if (!orc) {
+ /*
+ * As a fallback, try to assume this code uses a frame pointer.
+ * This is useful for generated code, like BPF, which ORC
+ * doesn't know about. This is just a guess, so the rest of
+ * the unwind is no longer considered reliable.
+ */
+ orc = &orc_fp_entry;
+ state->error = true;
+ }
/* End-of-stack check for kernel threads: */
if (orc->sp_reg == ORC_REG_UNDEFINED) {
OpenPOWER on IntegriCloud