summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/wakeup_64.S10
-rw-r--r--arch/x86/kernel/alternative.c6
-rw-r--r--arch/x86/kernel/amd_nb.c3
-rw-r--r--arch/x86/kernel/apic/apic.c212
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c66
-rw-r--r--arch/x86/kernel/apic/apic_noop.c18
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c8
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c33
-rw-r--r--arch/x86/kernel/apic/io_apic.c8
-rw-r--r--arch/x86/kernel/apic/ipi.c174
-rw-r--r--arch/x86/kernel/apic/local.h68
-rw-r--r--arch/x86/kernel/apic/probe_32.c41
-rw-r--r--arch/x86/kernel/apic/probe_64.c21
-rw-r--r--arch/x86/kernel/apic/vector.c11
-rw-r--r--arch/x86/kernel/apic/x2apic.h9
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c20
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c23
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c30
-rw-r--r--arch/x86/kernel/asm-offsets_64.c21
-rw-r--r--arch/x86/kernel/cpu/amd.c26
-rw-r--r--arch/x86/kernel/cpu/bugs.c20
-rw-r--r--arch/x86/kernel/cpu/common.c16
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c97
-rw-r--r--arch/x86/kernel/cpu/hygon.c21
-rw-r--r--arch/x86/kernel/cpu/intel.c31
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c2
-rw-r--r--arch/x86/kernel/cpu/mce/severity.c4
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c10
-rw-r--r--arch/x86/kernel/cpu/vmware.c94
-rw-r--r--arch/x86/kernel/crash.c2
-rw-r--r--arch/x86/kernel/dumpstack.c7
-rw-r--r--arch/x86/kernel/irq.c10
-rw-r--r--arch/x86/kernel/irq_32.c7
-rw-r--r--arch/x86/kernel/irq_64.c9
-rw-r--r--arch/x86/kernel/kgdb.c2
-rw-r--r--arch/x86/kernel/kprobes/core.c2
-rw-r--r--arch/x86/kernel/kprobes/opt.c2
-rw-r--r--arch/x86/kernel/kvm.c51
-rw-r--r--arch/x86/kernel/machine_kexec_32.c4
-rw-r--r--arch/x86/kernel/nmi.c3
-rw-r--r--arch/x86/kernel/paravirt.c4
-rw-r--r--arch/x86/kernel/pci-dma.c20
-rw-r--r--arch/x86/kernel/process.c2
-rw-r--r--arch/x86/kernel/quirks.c4
-rw-r--r--arch/x86/kernel/reboot.c7
-rw-r--r--arch/x86/kernel/smp.c88
-rw-r--r--arch/x86/kernel/smpboot.c12
-rw-r--r--arch/x86/kernel/tsc.c2
-rw-r--r--arch/x86/kernel/tsc_msr.c5
-rw-r--r--arch/x86/kernel/umip.c65
-rw-r--r--arch/x86/kernel/uprobes.c17
51 files changed, 769 insertions, 659 deletions
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index b0715c3ac18d..7f9ade13bbcf 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -18,8 +18,13 @@ ENTRY(wakeup_long64)
movq saved_magic, %rax
movq $0x123456789abcdef0, %rdx
cmpq %rdx, %rax
- jne bogus_64_magic
+ je 2f
+ /* stop here on a saved_magic mismatch */
+ movq $0xbad6d61676963, %rcx
+1:
+ jmp 1b
+2:
movw $__KERNEL_DS, %ax
movw %ax, %ss
movw %ax, %ds
@@ -37,9 +42,6 @@ ENTRY(wakeup_long64)
jmp *%rax
ENDPROC(wakeup_long64)
-bogus_64_magic:
- jmp bogus_64_magic
-
ENTRY(do_suspend_lowlevel)
FRAME_BEGIN
subq $8, %rsp
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ccd32013c47a..9d3a971ea364 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -713,7 +713,7 @@ void __init alternative_instructions(void)
* Don't stop machine check exceptions while patching.
* MCEs only happen when something got corrupted and in this
* case we must do something about the corruption.
- * Ignoring it is worse than a unlikely patching race.
+ * Ignoring it is worse than an unlikely patching race.
* Also machine checks tend to be broadcast and if one CPU
* goes into machine check the others follow quickly, so we don't
* expect a machine check to cause undue problems during to code
@@ -753,8 +753,8 @@ void __init alternative_instructions(void)
* When you use this code to patch more than one byte of an instruction
* you need to make sure that other CPUs cannot execute this code in parallel.
* Also no thread must be currently preempted in the middle of these
- * instructions. And on the local CPU you need to be protected again NMI or MCE
- * handlers seeing an inconsistent instruction while you patch.
+ * instructions. And on the local CPU you need to be protected against NMI or
+ * MCE handlers seeing an inconsistent instruction while you patch.
*/
void __init_or_module text_poke_early(void *addr, const void *opcode,
size_t len)
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index d63e63b7d1d9..251c795b4eb3 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -21,6 +21,7 @@
#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464
#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
+#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444
/* Protect the PCI config register pairs used for SMN and DF indirect access. */
static DEFINE_MUTEX(smn_mutex);
@@ -50,6 +51,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
{}
};
EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
@@ -63,6 +65,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
{}
};
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index aa5495d0f478..9e2dd2b296cd 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -65,10 +65,10 @@ unsigned int num_processors;
unsigned disabled_cpus;
/* Processor that is doing the boot up */
-unsigned int boot_cpu_physical_apicid = -1U;
+unsigned int boot_cpu_physical_apicid __ro_after_init = -1U;
EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
-u8 boot_cpu_apic_version;
+u8 boot_cpu_apic_version __ro_after_init;
/*
* The highest APIC ID seen during enumeration.
@@ -85,13 +85,13 @@ physid_mask_t phys_cpu_present_map;
* disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to
* avoid undefined behaviour caused by sending INIT from AP to BSP.
*/
-static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID;
+static unsigned int disabled_cpu_apicid __ro_after_init = BAD_APICID;
/*
* This variable controls which CPUs receive external NMIs. By default,
* external NMIs are delivered only to the BSP.
*/
-static int apic_extnmi = APIC_EXTNMI_BSP;
+static int apic_extnmi __ro_after_init = APIC_EXTNMI_BSP;
/*
* Map cpu index to physical APIC ID
@@ -114,7 +114,7 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid);
DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID);
/* Local APIC was disabled by the BIOS and enabled by the kernel */
-static int enabled_via_apicbase;
+static int enabled_via_apicbase __ro_after_init;
/*
* Handle interrupt mode configuration register (IMCR).
@@ -172,23 +172,23 @@ static __init int setup_apicpmtimer(char *s)
__setup("apicpmtimer", setup_apicpmtimer);
#endif
-unsigned long mp_lapic_addr;
-int disable_apic;
+unsigned long mp_lapic_addr __ro_after_init;
+int disable_apic __ro_after_init;
/* Disable local APIC timer from the kernel commandline or via dmi quirk */
static int disable_apic_timer __initdata;
/* Local APIC timer works in C2 */
-int local_apic_timer_c2_ok;
+int local_apic_timer_c2_ok __ro_after_init;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
/*
* Debug level, exported for io_apic.c
*/
-int apic_verbosity;
+int apic_verbosity __ro_after_init;
-int pic_mode;
+int pic_mode __ro_after_init;
/* Have we found an MP table */
-int smp_found_config;
+int smp_found_config __ro_after_init;
static struct resource lapic_resource = {
.name = "Local APIC",
@@ -199,7 +199,7 @@ unsigned int lapic_timer_period = 0;
static void apic_pm_activate(void);
-static unsigned long apic_phys;
+static unsigned long apic_phys __ro_after_init;
/*
* Get the LAPIC version
@@ -590,21 +590,21 @@ static u32 skx_deadline_rev(void)
static const struct x86_cpu_id deadline_match[] = {
DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev),
DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020),
- DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev),
+ DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_D, bdx_deadline_rev),
DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_GT3E, 0x17),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL, 0x22),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_L, 0x20),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_G, 0x17),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_CORE, 0x25),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_GT3E, 0x17),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL, 0x25),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_G, 0x17),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_MOBILE, 0xb2),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_DESKTOP, 0xb2),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_L, 0xb2),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE, 0xb2),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_MOBILE, 0x52),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_DESKTOP, 0x52),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_L, 0x52),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE, 0x52),
{},
};
@@ -834,6 +834,10 @@ bool __init apic_needs_pit(void)
if (!boot_cpu_has(X86_FEATURE_APIC))
return true;
+ /* Virt guests may lack ARAT, but still have DEADLINE */
+ if (!boot_cpu_has(X86_FEATURE_ARAT))
+ 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;
@@ -1220,25 +1224,38 @@ void clear_local_APIC(void)
}
/**
- * disable_local_APIC - clear and disable the local APIC
+ * apic_soft_disable - Clears and software disables the local APIC on hotplug
+ *
+ * Contrary to disable_local_APIC() this does not touch the enable bit in
+ * MSR_IA32_APICBASE. Clearing that bit on systems based on the 3 wire APIC
+ * bus would require a hardware reset as the APIC would lose track of bus
+ * arbitration. On systems with FSB delivery APICBASE could be disabled,
+ * but it has to be guaranteed that no interrupt is sent to the APIC while
+ * in that state and it's not clear from the SDM whether it still responds
+ * to INIT/SIPI messages. Stay on the safe side and use software disable.
*/
-void disable_local_APIC(void)
+void apic_soft_disable(void)
{
- unsigned int value;
-
- /* APIC hasn't been mapped yet */
- if (!x2apic_mode && !apic_phys)
- return;
+ u32 value;
clear_local_APIC();
- /*
- * Disable APIC (implies clearing of registers
- * for 82489DX!).
- */
+ /* Soft disable APIC (implies clearing of registers for 82489DX!). */
value = apic_read(APIC_SPIV);
value &= ~APIC_SPIV_APIC_ENABLED;
apic_write(APIC_SPIV, value);
+}
+
+/**
+ * disable_local_APIC - clear and disable the local APIC
+ */
+void disable_local_APIC(void)
+{
+ /* APIC hasn't been mapped yet */
+ if (!x2apic_mode && !apic_phys)
+ return;
+
+ apic_soft_disable();
#ifdef CONFIG_X86_32
/*
@@ -1303,7 +1320,7 @@ void __init sync_Arb_IDs(void)
APIC_INT_LEVELTRIG | APIC_DM_INIT);
}
-enum apic_intr_mode_id apic_intr_mode;
+enum apic_intr_mode_id apic_intr_mode __ro_after_init;
static int __init apic_intr_mode_select(void)
{
@@ -1491,54 +1508,72 @@ static void lapic_setup_esr(void)
oldvalue, value);
}
-static void apic_pending_intr_clear(void)
+#define APIC_IR_REGS APIC_ISR_NR
+#define APIC_IR_BITS (APIC_IR_REGS * 32)
+#define APIC_IR_MAPSIZE (APIC_IR_BITS / BITS_PER_LONG)
+
+union apic_ir {
+ unsigned long map[APIC_IR_MAPSIZE];
+ u32 regs[APIC_IR_REGS];
+};
+
+static bool apic_check_and_ack(union apic_ir *irr, union apic_ir *isr)
{
- long long max_loops = cpu_khz ? cpu_khz : 1000000;
- unsigned long long tsc = 0, ntsc;
- unsigned int queued;
- unsigned long value;
- int i, j, acked = 0;
+ int i, bit;
+
+ /* Read the IRRs */
+ for (i = 0; i < APIC_IR_REGS; i++)
+ irr->regs[i] = apic_read(APIC_IRR + i * 0x10);
+
+ /* Read the ISRs */
+ for (i = 0; i < APIC_IR_REGS; i++)
+ isr->regs[i] = apic_read(APIC_ISR + i * 0x10);
- if (boot_cpu_has(X86_FEATURE_TSC))
- tsc = rdtsc();
/*
- * After a crash, we no longer service the interrupts and a pending
- * interrupt from previous kernel might still have ISR bit set.
- *
- * Most probably by now CPU has serviced that pending interrupt and
- * it might not have done the ack_APIC_irq() because it thought,
- * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it
- * does not clear the ISR bit and cpu thinks it has already serivced
- * the interrupt. Hence a vector might get locked. It was noticed
- * for timer irq (vector 0x31). Issue an extra EOI to clear ISR.
+ * If the ISR map is not empty. ACK the APIC and run another round
+ * to verify whether a pending IRR has been unblocked and turned
+ * into a ISR.
*/
- do {
- queued = 0;
- for (i = APIC_ISR_NR - 1; i >= 0; i--)
- queued |= apic_read(APIC_IRR + i*0x10);
-
- for (i = APIC_ISR_NR - 1; i >= 0; i--) {
- value = apic_read(APIC_ISR + i*0x10);
- for_each_set_bit(j, &value, 32) {
- ack_APIC_irq();
- acked++;
- }
- }
- if (acked > 256) {
- pr_err("LAPIC pending interrupts after %d EOI\n", acked);
- break;
- }
- if (queued) {
- if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) {
- ntsc = rdtsc();
- max_loops = (long long)cpu_khz << 10;
- max_loops -= ntsc - tsc;
- } else {
- max_loops--;
- }
- }
- } while (queued && max_loops > 0);
- WARN_ON(max_loops <= 0);
+ if (!bitmap_empty(isr->map, APIC_IR_BITS)) {
+ /*
+ * There can be multiple ISR bits set when a high priority
+ * interrupt preempted a lower priority one. Issue an ACK
+ * per set bit.
+ */
+ for_each_set_bit(bit, isr->map, APIC_IR_BITS)
+ ack_APIC_irq();
+ return true;
+ }
+
+ return !bitmap_empty(irr->map, APIC_IR_BITS);
+}
+
+/*
+ * After a crash, we no longer service the interrupts and a pending
+ * interrupt from previous kernel might still have ISR bit set.
+ *
+ * Most probably by now the CPU has serviced that pending interrupt and it
+ * might not have done the ack_APIC_irq() because it thought, interrupt
+ * came from i8259 as ExtInt. LAPIC did not get EOI so it does not clear
+ * the ISR bit and cpu thinks it has already serivced the interrupt. Hence
+ * a vector might get locked. It was noticed for timer irq (vector
+ * 0x31). Issue an extra EOI to clear ISR.
+ *
+ * If there are pending IRR bits they turn into ISR bits after a higher
+ * priority ISR bit has been acked.
+ */
+static void apic_pending_intr_clear(void)
+{
+ union apic_ir irr, isr;
+ unsigned int i;
+
+ /* 512 loops are way oversized and give the APIC a chance to obey. */
+ for (i = 0; i < 512; i++) {
+ if (!apic_check_and_ack(&irr, &isr))
+ return;
+ }
+ /* Dump the IRR/ISR content if that failed */
+ pr_warn("APIC: Stale IRR: %256pb ISR: %256pb\n", irr.map, isr.map);
}
/**
@@ -1555,12 +1590,19 @@ static void setup_local_APIC(void)
int logical_apicid, ldr_apicid;
#endif
-
if (disable_apic) {
disable_ioapic_support();
return;
}
+ /*
+ * If this comes from kexec/kcrash the APIC might be enabled in
+ * SPIV. Soft disable it before doing further initialization.
+ */
+ value = apic_read(APIC_SPIV);
+ value &= ~APIC_SPIV_APIC_ENABLED;
+ apic_write(APIC_SPIV, value);
+
#ifdef CONFIG_X86_32
/* Pound the ESR really hard over the head with a big hammer - mbligh */
if (lapic_is_integrated() && apic->disable_esr) {
@@ -1570,8 +1612,6 @@ static void setup_local_APIC(void)
apic_write(APIC_ESR, 0);
}
#endif
- perf_events_lapic_init();
-
/*
* Double-check whether this APIC is really registered.
* This is meaningless in clustered apic mode, so we skip it.
@@ -1599,13 +1639,17 @@ static void setup_local_APIC(void)
#endif
/*
- * Set Task Priority to 'accept all'. We never change this
- * later on.
+ * Set Task Priority to 'accept all except vectors 0-31'. An APIC
+ * vector in the 16-31 range could be delivered if TPR == 0, but we
+ * would think it's an exception and terrible things will happen. We
+ * never change this later on.
*/
value = apic_read(APIC_TASKPRI);
value &= ~APIC_TPRI_MASK;
+ value |= 0x10;
apic_write(APIC_TASKPRI, value);
+ /* Clear eventually stale ISR/IRR bits */
apic_pending_intr_clear();
/*
@@ -1652,6 +1696,8 @@ static void setup_local_APIC(void)
value |= SPURIOUS_APIC_VECTOR;
apic_write(APIC_SPIV, value);
+ perf_events_lapic_init();
+
/*
* Set up LVT0, LVT1:
*
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index bbdca603f94a..7862b152a052 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -8,21 +8,14 @@
* Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
* James Cleverdon.
*/
-#include <linux/acpi.h>
-#include <linux/errno.h>
-#include <linux/threads.h>
#include <linux/cpumask.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/ctype.h>
-#include <linux/hardirq.h>
#include <linux/export.h>
+#include <linux/acpi.h>
-#include <asm/smp.h>
-#include <asm/ipi.h>
-#include <asm/apic.h>
-#include <asm/apic_flat_64.h>
#include <asm/jailhouse_para.h>
+#include <asm/apic.h>
+
+#include "local.h"
static struct apic apic_physflat;
static struct apic apic_flat;
@@ -83,35 +76,6 @@ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector)
_flat_send_IPI_mask(mask, vector);
}
-static void flat_send_IPI_allbutself(int vector)
-{
- int cpu = smp_processor_id();
-
- if (IS_ENABLED(CONFIG_HOTPLUG_CPU) || vector == NMI_VECTOR) {
- if (!cpumask_equal(cpu_online_mask, cpumask_of(cpu))) {
- unsigned long mask = cpumask_bits(cpu_online_mask)[0];
-
- if (cpu < BITS_PER_LONG)
- __clear_bit(cpu, &mask);
-
- _flat_send_IPI_mask(mask, vector);
- }
- } else if (num_online_cpus() > 1) {
- __default_send_IPI_shortcut(APIC_DEST_ALLBUT,
- vector, apic->dest_logical);
- }
-}
-
-static void flat_send_IPI_all(int vector)
-{
- if (vector == NMI_VECTOR) {
- flat_send_IPI_mask(cpu_online_mask, vector);
- } else {
- __default_send_IPI_shortcut(APIC_DEST_ALLINC,
- vector, apic->dest_logical);
- }
-}
-
static unsigned int flat_get_apic_id(unsigned long x)
{
return (x >> 24) & 0xFF;
@@ -173,9 +137,9 @@ static struct apic apic_flat __ro_after_init = {
.send_IPI = default_send_IPI_single,
.send_IPI_mask = flat_send_IPI_mask,
.send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself,
- .send_IPI_allbutself = flat_send_IPI_allbutself,
- .send_IPI_all = flat_send_IPI_all,
- .send_IPI_self = apic_send_IPI_self,
+ .send_IPI_allbutself = default_send_IPI_allbutself,
+ .send_IPI_all = default_send_IPI_all,
+ .send_IPI_self = default_send_IPI_self,
.inquire_remote_apic = default_inquire_remote_apic,
@@ -225,16 +189,6 @@ static void physflat_init_apic_ldr(void)
*/
}
-static void physflat_send_IPI_allbutself(int vector)
-{
- default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
-}
-
-static void physflat_send_IPI_all(int vector)
-{
- default_send_IPI_mask_sequence_phys(cpu_online_mask, vector);
-}
-
static int physflat_probe(void)
{
if (apic == &apic_physflat || num_possible_cpus() > 8 ||
@@ -276,9 +230,9 @@ static struct apic apic_physflat __ro_after_init = {
.send_IPI = default_send_IPI_single_phys,
.send_IPI_mask = default_send_IPI_mask_sequence_phys,
.send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_phys,
- .send_IPI_allbutself = physflat_send_IPI_allbutself,
- .send_IPI_all = physflat_send_IPI_all,
- .send_IPI_self = apic_send_IPI_self,
+ .send_IPI_allbutself = default_send_IPI_allbutself,
+ .send_IPI_all = default_send_IPI_all,
+ .send_IPI_self = default_send_IPI_self,
.inquire_remote_apic = default_inquire_remote_apic,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 5078b5ce63a7..98c9bb75d185 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -9,25 +9,9 @@
* to not uglify the caller's code and allow to call (some) apic routines
* like self-ipi, etc...
*/
-
-#include <linux/threads.h>
#include <linux/cpumask.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/ctype.h>
-#include <linux/errno.h>
-#include <asm/fixmap.h>
-#include <asm/mpspec.h>
-#include <asm/apicdef.h>
-#include <asm/apic.h>
-#include <asm/setup.h>
-#include <linux/smp.h>
-#include <asm/ipi.h>
-
-#include <linux/interrupt.h>
-#include <asm/acpi.h>
-#include <asm/e820/api.h>
+#include <asm/apic.h>
static void noop_init_apic_ldr(void) { }
static void noop_send_IPI(int cpu, int vector) { }
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index a5464b8b6c46..cdf45b4700f2 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -10,15 +10,15 @@
* Send feedback to <support@numascale.com>
*
*/
-
+#include <linux/types.h>
#include <linux/init.h>
#include <asm/numachip/numachip.h>
#include <asm/numachip/numachip_csr.h>
-#include <asm/ipi.h>
-#include <asm/apic_flat_64.h>
+
#include <asm/pgtable.h>
-#include <asm/pci_x86.h>
+
+#include "local.h"
u8 numachip_system __read_mostly;
static const struct apic apic_numachip1;
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index afee386ff711..38b5b51d42f6 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -4,18 +4,13 @@
*
* Drives the local APIC in "clustered mode".
*/
-#include <linux/threads.h>
#include <linux/cpumask.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
#include <linux/dmi.h>
#include <linux/smp.h>
-#include <asm/apicdef.h>
-#include <asm/fixmap.h>
-#include <asm/mpspec.h>
#include <asm/apic.h>
-#include <asm/ipi.h>
+
+#include "local.h"
static unsigned bigsmp_get_apic_id(unsigned long x)
{
@@ -38,32 +33,12 @@ static int bigsmp_early_logical_apicid(int cpu)
return early_per_cpu(x86_cpu_to_apicid, cpu);
}
-static inline unsigned long calculate_ldr(int cpu)
-{
- unsigned long val, id;
-
- val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
- id = per_cpu(x86_bios_cpu_apicid, cpu);
- val |= SET_APIC_LOGICAL_ID(id);
-
- return val;
-}
-
/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116). So here it goes...
+ * bigsmp enables physical destination mode
+ * and doesn't use LDR and DFR
*/
static void bigsmp_init_apic_ldr(void)
{
- unsigned long val;
- int cpu = smp_processor_id();
-
- apic_write(APIC_DFR, APIC_DFR_FLAT);
- val = calculate_ldr(cpu);
- apic_write(APIC_LDR, val);
}
static void bigsmp_setup_apic_routing(void)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c7bb6c69f21c..d6af97fd170a 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2438,7 +2438,13 @@ unsigned int arch_dynirq_lower_bound(unsigned int from)
* dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use
* gsi_top if ioapic_dynirq_base hasn't been initialized yet.
*/
- return ioapic_initialized ? ioapic_dynirq_base : gsi_top;
+ if (!ioapic_initialized)
+ return gsi_top;
+ /*
+ * For DT enabled machines ioapic_dynirq_base is irrelevant and not
+ * updated. So simply return @from if ioapic_dynirq_base == 0.
+ */
+ return ioapic_dynirq_base ? : from;
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 82f9244fe61f..6ca0f91372fd 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -1,24 +1,113 @@
// SPDX-License-Identifier: GPL-2.0
+
#include <linux/cpumask.h>
-#include <linux/interrupt.h>
-
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/spinlock.h>
-#include <linux/kernel_stat.h>
-#include <linux/mc146818rtc.h>
-#include <linux/cache.h>
-#include <linux/cpu.h>
-
-#include <asm/smp.h>
-#include <asm/mtrr.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
-#include <asm/apic.h>
-#include <asm/proto.h>
-#include <asm/ipi.h>
-
-void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
+#include <linux/smp.h>
+
+#include "local.h"
+
+DEFINE_STATIC_KEY_FALSE(apic_use_ipi_shorthand);
+
+#ifdef CONFIG_SMP
+static int apic_ipi_shorthand_off __ro_after_init;
+
+static __init int apic_ipi_shorthand(char *str)
+{
+ get_option(&str, &apic_ipi_shorthand_off);
+ return 1;
+}
+__setup("no_ipi_broadcast=", apic_ipi_shorthand);
+
+static int __init print_ipi_mode(void)
+{
+ pr_info("IPI shorthand broadcast: %s\n",
+ apic_ipi_shorthand_off ? "disabled" : "enabled");
+ return 0;
+}
+late_initcall(print_ipi_mode);
+
+void apic_smt_update(void)
+{
+ /*
+ * Do not switch to broadcast mode if:
+ * - Disabled on the command line
+ * - Only a single CPU is online
+ * - Not all present CPUs have been at least booted once
+ *
+ * The latter is important as the local APIC might be in some
+ * random state and a broadcast might cause havoc. That's
+ * especially true for NMI broadcasting.
+ */
+ if (apic_ipi_shorthand_off || num_online_cpus() == 1 ||
+ !cpumask_equal(cpu_present_mask, &cpus_booted_once_mask)) {
+ static_branch_disable(&apic_use_ipi_shorthand);
+ } else {
+ static_branch_enable(&apic_use_ipi_shorthand);
+ }
+}
+
+void apic_send_IPI_allbutself(unsigned int vector)
+{
+ if (num_online_cpus() < 2)
+ return;
+
+ if (static_branch_likely(&apic_use_ipi_shorthand))
+ apic->send_IPI_allbutself(vector);
+ else
+ apic->send_IPI_mask_allbutself(cpu_online_mask, vector);
+}
+
+/*
+ * Send a 'reschedule' IPI to another CPU. It goes straight through and
+ * wastes no time serializing anything. Worst case is that we lose a
+ * reschedule ...
+ */
+void native_smp_send_reschedule(int cpu)
+{
+ if (unlikely(cpu_is_offline(cpu))) {
+ WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu);
+ return;
+ }
+ apic->send_IPI(cpu, RESCHEDULE_VECTOR);
+}
+
+void native_send_call_func_single_ipi(int cpu)
+{
+ apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR);
+}
+
+void native_send_call_func_ipi(const struct cpumask *mask)
+{
+ if (static_branch_likely(&apic_use_ipi_shorthand)) {
+ unsigned int cpu = smp_processor_id();
+
+ if (!cpumask_or_equal(mask, cpumask_of(cpu), cpu_online_mask))
+ goto sendmask;
+
+ if (cpumask_test_cpu(cpu, mask))
+ apic->send_IPI_all(CALL_FUNCTION_VECTOR);
+ else if (num_online_cpus() > 1)
+ apic->send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+ return;
+ }
+
+sendmask:
+ apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
+}
+
+#endif /* CONFIG_SMP */
+
+static inline int __prepare_ICR2(unsigned int mask)
+{
+ return SET_APIC_DEST_FIELD(mask);
+}
+
+static inline void __xapic_wait_icr_idle(void)
+{
+ while (native_apic_mem_read(APIC_ICR) & APIC_ICR_BUSY)
+ cpu_relax();
+}
+
+void __default_send_IPI_shortcut(unsigned int shortcut, int vector)
{
/*
* Subtle. In the case of the 'never do double writes' workaround
@@ -32,12 +121,16 @@ void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int
/*
* Wait for idle.
*/
- __xapic_wait_icr_idle();
+ if (unlikely(vector == NMI_VECTOR))
+ safe_apic_wait_icr_idle();
+ else
+ __xapic_wait_icr_idle();
/*
- * No need to touch the target chip field
+ * No need to touch the target chip field. Also the destination
+ * mode is ignored when a shorthand is used.
*/
- cfg = __prepare_ICR(shortcut, vector, dest);
+ cfg = __prepare_ICR(shortcut, vector, 0);
/*
* Send the IPI. The write to APIC_ICR fires this off.
@@ -133,6 +226,21 @@ void default_send_IPI_single(int cpu, int vector)
apic->send_IPI_mask(cpumask_of(cpu), vector);
}
+void default_send_IPI_allbutself(int vector)
+{
+ __default_send_IPI_shortcut(APIC_DEST_ALLBUT, vector);
+}
+
+void default_send_IPI_all(int vector)
+{
+ __default_send_IPI_shortcut(APIC_DEST_ALLINC, vector);
+}
+
+void default_send_IPI_self(int vector)
+{
+ __default_send_IPI_shortcut(APIC_DEST_SELF, vector);
+}
+
#ifdef CONFIG_X86_32
void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
@@ -192,28 +300,6 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
local_irq_restore(flags);
}
-void default_send_IPI_allbutself(int vector)
-{
- /*
- * if there are no other CPUs in the system then we get an APIC send
- * error if we try to broadcast, thus avoid sending IPIs in this case.
- */
- if (!(num_online_cpus() > 1))
- return;
-
- __default_local_send_IPI_allbutself(vector);
-}
-
-void default_send_IPI_all(int vector)
-{
- __default_local_send_IPI_all(vector);
-}
-
-void default_send_IPI_self(int vector)
-{
- __default_send_IPI_shortcut(APIC_DEST_SELF, vector, apic->dest_logical);
-}
-
/* must come after the send_IPI functions above for inlining */
static int convert_apicid_to_cpu(int apic_id)
{
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
new file mode 100644
index 000000000000..04797f05ce94
--- /dev/null
+++ b/arch/x86/kernel/apic/local.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Historical copyright notices:
+ *
+ * Copyright 2004 James Cleverdon, IBM.
+ * (c) 1995 Alan Cox, Building #3 <alan@redhat.com>
+ * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com>
+ * (c) 2002,2003 Andi Kleen, SuSE Labs.
+ */
+
+#include <linux/jump_label.h>
+
+#include <asm/apic.h>
+
+/* APIC flat 64 */
+void flat_init_apic_ldr(void);
+
+/* X2APIC */
+int x2apic_apic_id_valid(u32 apicid);
+int x2apic_apic_id_registered(void);
+void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest);
+unsigned int x2apic_get_apic_id(unsigned long id);
+u32 x2apic_set_apic_id(unsigned int id);
+int x2apic_phys_pkg_id(int initial_apicid, int index_msb);
+void x2apic_send_IPI_self(int vector);
+void __x2apic_send_IPI_shorthand(int vector, u32 which);
+
+/* IPI */
+
+DECLARE_STATIC_KEY_FALSE(apic_use_ipi_shorthand);
+
+static inline unsigned int __prepare_ICR(unsigned int shortcut, int vector,
+ unsigned int dest)
+{
+ unsigned int icr = shortcut | dest;
+
+ switch (vector) {
+ default:
+ icr |= APIC_DM_FIXED | vector;
+ break;
+ case NMI_VECTOR:
+ icr |= APIC_DM_NMI;
+ break;
+ }
+ return icr;
+}
+
+void __default_send_IPI_shortcut(unsigned int shortcut, int vector);
+
+/*
+ * This is used to send an IPI with no shorthand notation (the destination is
+ * specified in bits 56 to 63 of the ICR).
+ */
+void __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest);
+
+void default_send_IPI_single(int cpu, int vector);
+void default_send_IPI_single_phys(int cpu, int vector);
+void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector);
+void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, int vector);
+void default_send_IPI_allbutself(int vector);
+void default_send_IPI_all(int vector);
+void default_send_IPI_self(int vector);
+
+#ifdef CONFIG_X86_32
+void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector);
+void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector);
+void default_send_IPI_mask_logical(const struct cpumask *mask, int vector);
+#endif
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index ee2d91e382f1..67b33d67002f 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -6,51 +6,14 @@
*
* Generic x86 APIC driver probe layer.
*/
-#include <linux/threads.h>
-#include <linux/cpumask.h>
#include <linux/export.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/ctype.h>
-#include <linux/init.h>
#include <linux/errno.h>
-#include <asm/fixmap.h>
-#include <asm/mpspec.h>
-#include <asm/apicdef.h>
-#include <asm/apic.h>
-#include <asm/setup.h>
-
#include <linux/smp.h>
-#include <asm/ipi.h>
-#include <linux/interrupt.h>
+#include <asm/apic.h>
#include <asm/acpi.h>
-#include <asm/e820/api.h>
-#ifdef CONFIG_HOTPLUG_CPU
-#define DEFAULT_SEND_IPI (1)
-#else
-#define DEFAULT_SEND_IPI (0)
-#endif
-
-int no_broadcast = DEFAULT_SEND_IPI;
-
-static __init int no_ipi_broadcast(char *str)
-{
- get_option(&str, &no_broadcast);
- pr_info("Using %s mode\n",
- no_broadcast ? "No IPI Broadcast" : "IPI Broadcast");
- return 1;
-}
-__setup("no_ipi_broadcast=", no_ipi_broadcast);
-
-static int __init print_ipi_mode(void)
-{
- pr_info("Using IPI %s mode\n",
- no_broadcast ? "No-Shortcut" : "Shortcut");
- return 0;
-}
-late_initcall(print_ipi_mode);
+#include "local.h"
static int default_x86_32_early_logical_apicid(int cpu)
{
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index e6560a02eb46..29f0e0984557 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -8,19 +8,9 @@
* Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
* James Cleverdon.
*/
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/string.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/ctype.h>
-#include <linux/hardirq.h>
-#include <linux/dmar.h>
-
-#include <asm/smp.h>
#include <asm/apic.h>
-#include <asm/ipi.h>
-#include <asm/setup.h>
+
+#include "local.h"
/*
* Check the APIC IDs in bios_cpu_apicid and choose the APIC mode.
@@ -46,13 +36,6 @@ void __init default_setup_apic_routing(void)
x86_platform.apic_post_init();
}
-/* Same for both flat and physical. */
-
-void apic_send_IPI_self(int vector)
-{
- __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
-}
-
int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
struct apic **drv;
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index fdacb864c3dd..2c5676b0a6e7 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -398,6 +398,17 @@ static int activate_reserved(struct irq_data *irqd)
if (!irqd_can_reserve(irqd))
apicd->can_reserve = false;
}
+
+ /*
+ * Check to ensure that the effective affinity mask is a subset
+ * the user supplied affinity mask, and warn the user if it is not
+ */
+ if (!cpumask_subset(irq_data_get_effective_affinity_mask(irqd),
+ irq_data_get_affinity_mask(irqd))) {
+ pr_warn("irq %u: Affinity broken due to vector space exhaustion.\n",
+ irqd->irq);
+ }
+
return ret;
}
diff --git a/arch/x86/kernel/apic/x2apic.h b/arch/x86/kernel/apic/x2apic.h
deleted file mode 100644
index a49b3604027f..000000000000
--- a/arch/x86/kernel/apic/x2apic.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* Common bits for X2APIC cluster/physical modes. */
-
-int x2apic_apic_id_valid(u32 apicid);
-int x2apic_apic_id_registered(void);
-void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest);
-unsigned int x2apic_get_apic_id(unsigned long id);
-u32 x2apic_set_apic_id(unsigned int id);
-int x2apic_phys_pkg_id(int initial_apicid, int index_msb);
-void x2apic_send_IPI_self(int vector);
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 609e499387a1..45e92cba92f5 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -1,15 +1,13 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/threads.h>
+
+#include <linux/cpuhotplug.h>
#include <linux/cpumask.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/ctype.h>
-#include <linux/dmar.h>
-#include <linux/irq.h>
-#include <linux/cpu.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <asm/apic.h>
-#include <asm/smp.h>
-#include "x2apic.h"
+#include "local.h"
struct cluster_mask {
unsigned int clusterid;
@@ -84,12 +82,12 @@ x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
static void x2apic_send_IPI_allbutself(int vector)
{
- __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLBUT);
+ __x2apic_send_IPI_shorthand(vector, APIC_DEST_ALLBUT);
}
static void x2apic_send_IPI_all(int vector)
{
- __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC);
+ __x2apic_send_IPI_shorthand(vector, APIC_DEST_ALLINC);
}
static u32 x2apic_calc_apicid(unsigned int cpu)
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index b5cf9e7b3830..bc9693841353 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -1,14 +1,9 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/threads.h>
+
#include <linux/cpumask.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/ctype.h>
-#include <linux/dmar.h>
+#include <linux/acpi.h>
-#include <asm/smp.h>
-#include <asm/ipi.h>
-#include "x2apic.h"
+#include "local.h"
int x2apic_phys;
@@ -80,12 +75,12 @@ static void
static void x2apic_send_IPI_allbutself(int vector)
{
- __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLBUT);
+ __x2apic_send_IPI_shorthand(vector, APIC_DEST_ALLBUT);
}
static void x2apic_send_IPI_all(int vector)
{
- __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC);
+ __x2apic_send_IPI_shorthand(vector, APIC_DEST_ALLINC);
}
static void init_x2apic_ldr(void)
@@ -117,6 +112,14 @@ void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest)
native_x2apic_icr_write(cfg, apicid);
}
+void __x2apic_send_IPI_shorthand(int vector, u32 which)
+{
+ unsigned long cfg = __prepare_ICR(which, vector, 0);
+
+ x2apic_wrmsr_fence();
+ native_x2apic_icr_write(cfg, 0);
+}
+
unsigned int x2apic_get_apic_id(unsigned long id)
{
return id;
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1e225528f0d7..e6230af19864 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -7,42 +7,22 @@
*
* Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved.
*/
+#include <linux/crash_dump.h>
+#include <linux/cpuhotplug.h>
#include <linux/cpumask.h>
-#include <linux/hardirq.h>
#include <linux/proc_fs.h>
-#include <linux/threads.h>
-#include <linux/kernel.h>
+#include <linux/memory.h>
#include <linux/export.h>
-#include <linux/string.h>
-#include <linux/ctype.h>
-#include <linux/sched.h>
-#include <linux/timer.h>
-#include <linux/slab.h>
-#include <linux/cpu.h>
-#include <linux/init.h>
-#include <linux/io.h>
#include <linux/pci.h>
-#include <linux/kdebug.h>
-#include <linux/delay.h>
-#include <linux/crash_dump.h>
-#include <linux/reboot.h>
-#include <linux/memory.h>
-#include <linux/numa.h>
+#include <asm/e820/api.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
-#include <asm/current.h>
-#include <asm/pgtable.h>
#include <asm/uv/bios.h>
#include <asm/uv/uv.h>
#include <asm/apic.h>
-#include <asm/e820/api.h>
-#include <asm/ipi.h>
-#include <asm/smp.h>
-#include <asm/x86_init.h>
-#include <asm/nmi.h>
-DEFINE_PER_CPU(int, x2apic_extra_bits);
+static DEFINE_PER_CPU(int, x2apic_extra_bits);
static enum uv_system_type uv_system_type;
static bool uv_hubless_system;
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index d3d075226c0a..24d2fde30d00 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -6,13 +6,28 @@
#include <asm/ia32.h>
#define __SYSCALL_64(nr, sym, qual) [nr] = 1,
+#define __SYSCALL_X32(nr, sym, qual)
static char syscalls_64[] = {
#include <asm/syscalls_64.h>
};
+#undef __SYSCALL_64
+#undef __SYSCALL_X32
+
+#ifdef CONFIG_X86_X32_ABI
+#define __SYSCALL_64(nr, sym, qual)
+#define __SYSCALL_X32(nr, sym, qual) [nr] = 1,
+static char syscalls_x32[] = {
+#include <asm/syscalls_64.h>
+};
+#undef __SYSCALL_64
+#undef __SYSCALL_X32
+#endif
+
#define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
static char syscalls_ia32[] = {
#include <asm/syscalls_32.h>
};
+#undef __SYSCALL_I386
#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
#include <asm/kvm_para.h>
@@ -62,7 +77,6 @@ int main(void)
ENTRY(cr2);
ENTRY(cr3);
ENTRY(cr4);
- ENTRY(cr8);
ENTRY(gdt_desc);
BLANK();
#undef ENTRY
@@ -80,6 +94,11 @@ int main(void)
DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
DEFINE(NR_syscalls, sizeof(syscalls_64));
+#ifdef CONFIG_X86_X32_ABI
+ DEFINE(__NR_syscall_x32_max, sizeof(syscalls_x32) - 1);
+ DEFINE(X32_NR_syscalls, sizeof(syscalls_x32));
+#endif
+
DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1);
DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32));
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 68c363c341bf..90f75e515876 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -8,6 +8,7 @@
#include <linux/sched.h>
#include <linux/sched/clock.h>
#include <linux/random.h>
+#include <linux/topology.h>
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/cacheinfo.h>
@@ -889,6 +890,10 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
{
set_cpu_cap(c, X86_FEATURE_ZEN);
+#ifdef CONFIG_NUMA
+ node_reclaim_distance = 32;
+#endif
+
/*
* Fix erratum 1076: CPB feature bit not being set in CPUID.
* Always set it, except when running under a hypervisor.
@@ -945,12 +950,8 @@ static void init_amd(struct cpuinfo_x86 *c)
init_amd_cacheinfo(c);
if (cpu_has(c, X86_FEATURE_XMM2)) {
- unsigned long long val;
- int ret;
-
/*
- * A serializing LFENCE has less overhead than MFENCE, so
- * use it for execution serialization. On families which
+ * Use LFENCE for execution serialization. On families which
* don't have that MSR, LFENCE is already serializing.
* msr_set_bit() uses the safe accessors, too, even if the MSR
* is not present.
@@ -958,19 +959,8 @@ static void init_amd(struct cpuinfo_x86 *c)
msr_set_bit(MSR_F10H_DECFG,
MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
- /*
- * Verify that the MSR write was successful (could be running
- * under a hypervisor) and only then assume that LFENCE is
- * serializing.
- */
- ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
- if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
- /* A serializing LFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
- } else {
- /* MFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
- }
+ /* A serializing LFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
}
/*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c6fa3ef10b4e..91c2561b905f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -787,7 +787,7 @@ static void update_mds_branch_idle(void)
#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
-void arch_smt_update(void)
+void cpu_bugs_smt_update(void)
{
/* Enhanced IBRS implies STIBP. No update required. */
if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@@ -1184,15 +1184,15 @@ static void override_cache_bits(struct cpuinfo_x86 *c)
case INTEL_FAM6_WESTMERE:
case INTEL_FAM6_SANDYBRIDGE:
case INTEL_FAM6_IVYBRIDGE:
- case INTEL_FAM6_HASWELL_CORE:
- case INTEL_FAM6_HASWELL_ULT:
- case INTEL_FAM6_HASWELL_GT3E:
- case INTEL_FAM6_BROADWELL_CORE:
- case INTEL_FAM6_BROADWELL_GT3E:
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
+ case INTEL_FAM6_HASWELL:
+ case INTEL_FAM6_HASWELL_L:
+ case INTEL_FAM6_HASWELL_G:
+ case INTEL_FAM6_BROADWELL:
+ case INTEL_FAM6_BROADWELL_G:
+ case INTEL_FAM6_SKYLAKE_L:
+ case INTEL_FAM6_SKYLAKE:
+ case INTEL_FAM6_KABYLAKE_L:
+ case INTEL_FAM6_KABYLAKE:
if (c->x86_cache_bits < 44)
c->x86_cache_bits = 44;
break;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f125bf7ecb6f..9ae7d1bcd4f4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1050,7 +1050,7 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION),
VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
- VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
@@ -1059,9 +1059,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL_INTEL(CORE_YONAH, NO_SSB),
VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS),
VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS),
- VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS),
VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS),
/*
@@ -1957,3 +1958,14 @@ void microcode_check(void)
pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
}
+
+/*
+ * Invoked from core CPU hotplug code after hotplug operations
+ */
+void arch_smt_update(void)
+{
+ /* Handle the speculative execution misfeatures */
+ cpu_bugs_smt_update();
+ /* Check whether IPI broadcasting can be enabled */
+ apic_smt_update();
+}
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index b5353244749b..3cbe24ca80ab 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -20,54 +20,55 @@ 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 },
- { X86_FEATURE_AVX, X86_FEATURE_XSAVE },
- { 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 },
- { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 },
- { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 },
- { X86_FEATURE_XMM3, X86_FEATURE_XMM2 },
- { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 },
- { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, },
- { X86_FEATURE_F16C, X86_FEATURE_XMM2, },
- { X86_FEATURE_AES, X86_FEATURE_XMM2 },
- { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 },
- { X86_FEATURE_FMA, X86_FEATURE_AVX },
- { X86_FEATURE_AVX2, X86_FEATURE_AVX, },
- { X86_FEATURE_AVX512F, X86_FEATURE_AVX, },
- { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL },
- { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL },
- { X86_FEATURE_VAES, X86_FEATURE_AVX512VL },
- { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL },
- { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL },
- { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL },
- { 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 },
+ { X86_FEATURE_FXSR, X86_FEATURE_FPU },
+ { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE },
+ { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE },
+ { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE },
+ { X86_FEATURE_AVX, X86_FEATURE_XSAVE },
+ { 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 },
+ { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 },
+ { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 },
+ { X86_FEATURE_XMM3, X86_FEATURE_XMM2 },
+ { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 },
+ { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, },
+ { X86_FEATURE_F16C, X86_FEATURE_XMM2, },
+ { X86_FEATURE_AES, X86_FEATURE_XMM2 },
+ { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 },
+ { X86_FEATURE_FMA, X86_FEATURE_AVX },
+ { X86_FEATURE_AVX2, X86_FEATURE_AVX, },
+ { X86_FEATURE_AVX512F, X86_FEATURE_AVX, },
+ { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_VAES, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_VP2INTERSECT, X86_FEATURE_AVX512VL },
+ { 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/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 415621ddb8a2..4e28c1fc8749 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -330,12 +330,8 @@ static void init_hygon(struct cpuinfo_x86 *c)
init_hygon_cacheinfo(c);
if (cpu_has(c, X86_FEATURE_XMM2)) {
- unsigned long long val;
- int ret;
-
/*
- * A serializing LFENCE has less overhead than MFENCE, so
- * use it for execution serialization. On families which
+ * Use LFENCE for execution serialization. On families which
* don't have that MSR, LFENCE is already serializing.
* msr_set_bit() uses the safe accessors, too, even if the MSR
* is not present.
@@ -343,19 +339,8 @@ static void init_hygon(struct cpuinfo_x86 *c)
msr_set_bit(MSR_F10H_DECFG,
MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
- /*
- * Verify that the MSR write was successful (could be running
- * under a hypervisor) and only then assume that LFENCE is
- * serializing.
- */
- ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
- if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
- /* A serializing LFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
- } else {
- /* MFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
- }
+ /* A serializing LFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
}
/*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 8d6d92ebeb54..c2fdc00df163 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -142,21 +142,21 @@ struct sku_microcode {
u32 microcode;
};
static const struct sku_microcode spectre_bad_microcodes[] = {
- { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x80 },
- { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x80 },
- { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x80 },
- { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x80 },
- { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 },
+ { INTEL_FAM6_KABYLAKE, 0x0B, 0x80 },
+ { INTEL_FAM6_KABYLAKE, 0x0A, 0x80 },
+ { INTEL_FAM6_KABYLAKE, 0x09, 0x80 },
+ { INTEL_FAM6_KABYLAKE_L, 0x0A, 0x80 },
+ { INTEL_FAM6_KABYLAKE_L, 0x09, 0x80 },
{ INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e },
{ INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c },
- { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 },
- { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b },
- { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 },
- { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 },
+ { INTEL_FAM6_BROADWELL, 0x04, 0x28 },
+ { INTEL_FAM6_BROADWELL_G, 0x01, 0x1b },
+ { INTEL_FAM6_BROADWELL_D, 0x02, 0x14 },
+ { INTEL_FAM6_BROADWELL_D, 0x03, 0x07000011 },
{ INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 },
- { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 },
- { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 },
- { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 },
+ { INTEL_FAM6_HASWELL_L, 0x01, 0x21 },
+ { INTEL_FAM6_HASWELL_G, 0x01, 0x18 },
+ { INTEL_FAM6_HASWELL, 0x03, 0x23 },
{ INTEL_FAM6_HASWELL_X, 0x02, 0x3b },
{ INTEL_FAM6_HASWELL_X, 0x04, 0x10 },
{ INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a },
@@ -265,9 +265,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
if (c->x86 == 6) {
switch (c->x86_model) {
- case 0x27: /* Penwell */
- case 0x35: /* Cloverview */
- case 0x4a: /* Merrifield */
+ case INTEL_FAM6_ATOM_SALTWELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL_TABLET:
+ case INTEL_FAM6_ATOM_SILVERMONT_MID:
+ case INTEL_FAM6_ATOM_AIRMONT_NP:
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
break;
default:
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index e43eb6732630..88cd9598fa57 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -479,7 +479,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
switch (c->x86_model) {
case INTEL_FAM6_IVYBRIDGE_X:
case INTEL_FAM6_HASWELL_X:
- case INTEL_FAM6_BROADWELL_XEON_D:
+ case INTEL_FAM6_BROADWELL_D:
case INTEL_FAM6_BROADWELL_X:
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_XEON_PHI_KNL:
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 210f1f5db5f7..87bcdc6dc2f0 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -107,11 +107,11 @@ static struct severity {
*/
MCESEV(
AO, "Action optional: memory scrubbing error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB)
+ SER, MASK(MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB)
),
MCESEV(
AO, "Action optional: last level cache writeback error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
+ SER, MASK(MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
),
/* ignore OVER for UCNA */
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 062f77279ce3..267daad8c036 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -29,6 +29,7 @@
#include <asm/timer.h>
#include <asm/reboot.h>
#include <asm/nmi.h>
+#include <clocksource/hyperv_timer.h>
struct ms_hyperv_info ms_hyperv;
EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -338,6 +339,15 @@ static void __init ms_hyperv_init_platform(void)
x2apic_phys = 1;
# endif
+ /* Register Hyper-V specific clocksource */
+ hv_init_clocksource();
+#endif
+}
+
+void hv_setup_sched_clock(void *sched_clock)
+{
+#ifdef CONFIG_PARAVIRT
+ pv_ops.time.sched_clock = sched_clock;
#endif
}
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 3c648476d4fb..9735139cfdf8 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -30,34 +30,69 @@
#include <asm/hypervisor.h>
#include <asm/timer.h>
#include <asm/apic.h>
+#include <asm/vmware.h>
#undef pr_fmt
#define pr_fmt(fmt) "vmware: " fmt
-#define CPUID_VMWARE_INFO_LEAF 0x40000000
+#define CPUID_VMWARE_INFO_LEAF 0x40000000
+#define CPUID_VMWARE_FEATURES_LEAF 0x40000010
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1)
+
#define VMWARE_HYPERVISOR_MAGIC 0x564D5868
-#define VMWARE_HYPERVISOR_PORT 0x5658
-#define VMWARE_PORT_CMD_GETVERSION 10
-#define VMWARE_PORT_CMD_GETHZ 45
-#define VMWARE_PORT_CMD_GETVCPU_INFO 68
-#define VMWARE_PORT_CMD_LEGACY_X2APIC 3
-#define VMWARE_PORT_CMD_VCPU_RESERVED 31
+#define VMWARE_CMD_GETVERSION 10
+#define VMWARE_CMD_GETHZ 45
+#define VMWARE_CMD_GETVCPU_INFO 68
+#define VMWARE_CMD_LEGACY_X2APIC 3
+#define VMWARE_CMD_VCPU_RESERVED 31
#define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \
__asm__("inl (%%dx)" : \
- "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
- "0"(VMWARE_HYPERVISOR_MAGIC), \
- "1"(VMWARE_PORT_CMD_##cmd), \
- "2"(VMWARE_HYPERVISOR_PORT), "3"(UINT_MAX) : \
- "memory");
+ "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
+ "a"(VMWARE_HYPERVISOR_MAGIC), \
+ "c"(VMWARE_CMD_##cmd), \
+ "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) : \
+ "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+ __asm__("vmcall" : \
+ "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
+ "a"(VMWARE_HYPERVISOR_MAGIC), \
+ "c"(VMWARE_CMD_##cmd), \
+ "d"(0), "b"(UINT_MAX) : \
+ "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx) \
+ __asm__("vmmcall" : \
+ "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
+ "a"(VMWARE_HYPERVISOR_MAGIC), \
+ "c"(VMWARE_CMD_##cmd), \
+ "d"(0), "b"(UINT_MAX) : \
+ "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do { \
+ switch (vmware_hypercall_mode) { \
+ case CPUID_VMWARE_FEATURES_ECX_VMCALL: \
+ VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+ break; \
+ case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+ VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx); \
+ break; \
+ default: \
+ VMWARE_PORT(cmd, eax, ebx, ecx, edx); \
+ break; \
+ } \
+ } while (0)
static unsigned long vmware_tsc_khz __ro_after_init;
+static u8 vmware_hypercall_mode __ro_after_init;
static inline int __vmware_platform(void)
{
uint32_t eax, ebx, ecx, edx;
- VMWARE_PORT(GETVERSION, eax, ebx, ecx, edx);
+ VMWARE_CMD(GETVERSION, eax, ebx, ecx, edx);
return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC;
}
@@ -129,6 +164,10 @@ static void __init vmware_set_capabilities(void)
{
setup_force_cpu_cap(X86_FEATURE_CONSTANT_TSC);
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+ if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMCALL)
+ setup_force_cpu_cap(X86_FEATURE_VMCALL);
+ else if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMMCALL)
+ setup_force_cpu_cap(X86_FEATURE_VMW_VMMCALL);
}
static void __init vmware_platform_setup(void)
@@ -136,7 +175,7 @@ static void __init vmware_platform_setup(void)
uint32_t eax, ebx, ecx, edx;
uint64_t lpj, tsc_khz;
- VMWARE_PORT(GETHZ, eax, ebx, ecx, edx);
+ VMWARE_CMD(GETHZ, eax, ebx, ecx, edx);
if (ebx != UINT_MAX) {
lpj = tsc_khz = eax | (((uint64_t)ebx) << 32);
@@ -174,10 +213,21 @@ static void __init vmware_platform_setup(void)
vmware_set_capabilities();
}
+static u8 vmware_select_hypercall(void)
+{
+ int eax, ebx, ecx, edx;
+
+ cpuid(CPUID_VMWARE_FEATURES_LEAF, &eax, &ebx, &ecx, &edx);
+ return (ecx & (CPUID_VMWARE_FEATURES_ECX_VMMCALL |
+ CPUID_VMWARE_FEATURES_ECX_VMCALL));
+}
+
/*
* While checking the dmi string information, just checking the product
* serial key should be enough, as this will always have a VMware
* specific string when running under VMware hypervisor.
+ * If !boot_cpu_has(X86_FEATURE_HYPERVISOR), vmware_hypercall_mode
+ * intentionally defaults to 0.
*/
static uint32_t __init vmware_platform(void)
{
@@ -187,8 +237,16 @@ static uint32_t __init vmware_platform(void)
cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &hyper_vendor_id[0],
&hyper_vendor_id[1], &hyper_vendor_id[2]);
- if (!memcmp(hyper_vendor_id, "VMwareVMware", 12))
+ if (!memcmp(hyper_vendor_id, "VMwareVMware", 12)) {
+ if (eax >= CPUID_VMWARE_FEATURES_LEAF)
+ vmware_hypercall_mode =
+ vmware_select_hypercall();
+
+ pr_info("hypercall mode: 0x%02x\n",
+ (unsigned int) vmware_hypercall_mode);
+
return CPUID_VMWARE_INFO_LEAF;
+ }
} else if (dmi_available && dmi_name_in_serial("VMware") &&
__vmware_platform())
return 1;
@@ -200,9 +258,9 @@ static uint32_t __init vmware_platform(void)
static bool __init vmware_legacy_x2apic_available(void)
{
uint32_t eax, ebx, ecx, edx;
- VMWARE_PORT(GETVCPU_INFO, eax, ebx, ecx, edx);
- return (eax & (1 << VMWARE_PORT_CMD_VCPU_RESERVED)) == 0 &&
- (eax & (1 << VMWARE_PORT_CMD_LEGACY_X2APIC)) != 0;
+ VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx);
+ return (eax & (1 << VMWARE_CMD_VCPU_RESERVED)) == 0 &&
+ (eax & (1 << VMWARE_CMD_LEGACY_X2APIC)) != 0;
}
const __initconst struct hypervisor_x86 x86_hyper_vmware = {
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 2bf70a2fed90..eb651fbde92a 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -225,8 +225,6 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem)
if (crashk_low_res.end) {
ret = crash_exclude_mem_range(cmem, crashk_low_res.start,
crashk_low_res.end);
- if (ret)
- return ret;
}
return ret;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2b5886401e5f..e07424e19274 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -367,13 +367,18 @@ NOKPROBE_SYMBOL(oops_end);
int __die(const char *str, struct pt_regs *regs, long err)
{
+ const char *pr = "";
+
/* Save the regs of the first oops for the executive summary later. */
if (!die_counter)
exec_summary_regs = *regs;
+ if (IS_ENABLED(CONFIG_PREEMPTION))
+ pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
+
printk(KERN_DEFAULT
"%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
- IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
+ pr,
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "",
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 4215653f8a8e..21efee32e2b1 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -243,11 +243,15 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
desc = __this_cpu_read(vector_irq[vector]);
-
- if (!handle_irq(desc, regs)) {
+ if (likely(!IS_ERR_OR_NULL(desc))) {
+ if (IS_ENABLED(CONFIG_X86_32))
+ handle_irq(desc, regs);
+ else
+ generic_handle_irq_desc(desc);
+ } else {
ack_APIC_irq();
- if (desc != VECTOR_RETRIGGERED && desc != VECTOR_SHUTDOWN) {
+ if (desc == VECTOR_UNUSED) {
pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n",
__func__, smp_processor_id(),
vector);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index fc34816c6f04..a759ca97cd01 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -148,18 +148,13 @@ void do_softirq_own_stack(void)
call_on_stack(__do_softirq, isp);
}
-bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
+void handle_irq(struct irq_desc *desc, struct pt_regs *regs)
{
int overflow = check_stack_overflow();
- if (IS_ERR_OR_NULL(desc))
- return false;
-
if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) {
if (unlikely(overflow))
print_stack_overflow();
generic_handle_irq_desc(desc);
}
-
- return true;
}
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 6bf6517a05bb..12df3a4abfdd 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -26,15 +26,6 @@
DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
DECLARE_INIT_PER_CPU(irq_stack_backing_store);
-bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
-{
- if (IS_ERR_OR_NULL(desc))
- return false;
-
- generic_handle_irq_desc(desc);
- return true;
-}
-
#ifdef CONFIG_VMAP_STACK
/*
* VMAP the backing store with guard pages
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 23297ea64f5f..c44fe7d8d9a4 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -416,7 +416,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs)
*/
void kgdb_roundup_cpus(void)
{
- apic->send_IPI_allbutself(APIC_DM_NMI);
+ apic_send_IPI_allbutself(NMI_VECTOR);
}
#endif
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0e0b08008b5a..43fc13c831af 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -580,7 +580,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
if (setup_detour_execution(p, regs, reenter))
return;
-#if !defined(CONFIG_PREEMPT)
+#if !defined(CONFIG_PREEMPTION)
if (p->ainsn.boostable && !p->post_handler) {
/* Boost up -- we can execute copied instructions directly */
if (!reenter)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 9d4aedece363..b348dd506d58 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -403,7 +403,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
(u8 *)op->kp.addr + op->optinsn.size);
len += RELATIVEJUMP_SIZE;
- /* We have to use text_poke for instuction buffer because it is RO */
+ /* We have to use text_poke() for instruction buffer because it is RO */
text_poke(slot, buf, len);
ret = 0;
out:
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4ab377c9fffe..e820568ed4d5 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -311,7 +311,7 @@ static void kvm_guest_cpu_init(void)
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
pa |= KVM_ASYNC_PF_SEND_ALWAYS;
#endif
pa |= KVM_ASYNC_PF_ENABLED;
@@ -502,16 +502,6 @@ static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
__send_ipi_mask(local_mask, vector);
}
-static void kvm_send_ipi_allbutself(int vector)
-{
- kvm_send_ipi_mask_allbutself(cpu_online_mask, vector);
-}
-
-static void kvm_send_ipi_all(int vector)
-{
- __send_ipi_mask(cpu_online_mask, vector);
-}
-
/*
* Set the IPI entry points
*/
@@ -519,8 +509,6 @@ static void kvm_setup_pv_ipi(void)
{
apic->send_IPI_mask = kvm_send_ipi_mask;
apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself;
- apic->send_IPI_allbutself = kvm_send_ipi_allbutself;
- apic->send_IPI_all = kvm_send_ipi_all;
pr_info("KVM setup pv IPIs\n");
}
@@ -705,6 +693,7 @@ unsigned int kvm_arch_para_hints(void)
{
return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES);
}
+EXPORT_SYMBOL_GPL(kvm_arch_para_hints);
static uint32_t __init kvm_detect(void)
{
@@ -867,3 +856,39 @@ void __init kvm_spinlock_init(void)
}
#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+
+static void kvm_disable_host_haltpoll(void *i)
+{
+ wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+}
+
+static void kvm_enable_host_haltpoll(void *i)
+{
+ wrmsrl(MSR_KVM_POLL_CONTROL, 1);
+}
+
+void arch_haltpoll_enable(unsigned int cpu)
+{
+ if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) {
+ pr_err_once("kvm: host does not support poll control\n");
+ pr_err_once("kvm: host upgrade recommended\n");
+ return;
+ }
+
+ /* Enable guest halt poll disables host halt poll */
+ smp_call_function_single(cpu, kvm_disable_host_haltpoll, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(arch_haltpoll_enable);
+
+void arch_haltpoll_disable(unsigned int cpu)
+{
+ if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+ return;
+
+ /* Enable guest halt poll disables host halt poll */
+ smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
+#endif
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 77854b192fef..7b45e8daad22 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -148,7 +148,7 @@ int machine_kexec_prepare(struct kimage *image)
{
int error;
- set_pages_x(image->control_code_page, 1);
+ set_memory_x((unsigned long)page_address(image->control_code_page), 1);
error = machine_kexec_alloc_page_tables(image);
if (error)
return error;
@@ -162,7 +162,7 @@ int machine_kexec_prepare(struct kimage *image)
*/
void machine_kexec_cleanup(struct kimage *image)
{
- set_pages_nx(image->control_code_page, 1);
+ set_memory_nx((unsigned long)page_address(image->control_code_page), 1);
machine_kexec_free_page_tables(image);
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 4df7705022b9..e676a9916c49 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -512,6 +512,9 @@ NOKPROBE_SYMBOL(is_debug_stack);
dotraplinkage notrace void
do_nmi(struct pt_regs *regs, long error_code)
{
+ if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id()))
+ return;
+
if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
this_cpu_write(nmi_state, NMI_LATCHED);
return;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 0aa6256eedd8..59d3d2763a9e 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -311,10 +311,6 @@ struct paravirt_patch_template pv_ops = {
.cpu.read_cr0 = native_read_cr0,
.cpu.write_cr0 = native_write_cr0,
.cpu.write_cr4 = native_write_cr4,
-#ifdef CONFIG_X86_64
- .cpu.read_cr8 = native_read_cr8,
- .cpu.write_cr8 = native_write_cr8,
-#endif
.cpu.wbinvd = native_wbinvd,
.cpu.read_msr = native_read_msr,
.cpu.write_msr = native_write_msr,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index f62b498b18fb..fa4352dce491 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/dma-direct.h>
#include <linux/dma-debug.h>
+#include <linux/iommu.h>
#include <linux/dmar.h>
#include <linux/export.h>
#include <linux/memblock.h>
@@ -34,21 +35,6 @@ int no_iommu __read_mostly;
/* Set this to 1 if there is a HW IOMMU in the system */
int iommu_detected __read_mostly = 0;
-/*
- * This variable becomes 1 if iommu=pt is passed on the kernel command line.
- * If this variable is 1, IOMMU implementations do no DMA translation for
- * devices and allow every device to access to whole physical memory. This is
- * useful if a user wants to use an IOMMU only for KVM device assignment to
- * guests and not for driver dma translation.
- * It is also possible to disable by default in kernel config, and enable with
- * iommu=nopt at boot time.
- */
-#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH
-int iommu_pass_through __read_mostly = 1;
-#else
-int iommu_pass_through __read_mostly;
-#endif
-
extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
void __init pci_iommu_alloc(void)
@@ -120,9 +106,9 @@ static __init int iommu_setup(char *p)
swiotlb = 1;
#endif
if (!strncmp(p, "pt", 2))
- iommu_pass_through = 1;
+ iommu_set_default_passthrough(true);
if (!strncmp(p, "nopt", 4))
- iommu_pass_through = 0;
+ iommu_set_default_translated(true);
gart_parse_options(p);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 75fea0d48c0e..5e94c4354d4e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -580,7 +580,7 @@ void __cpuidle default_idle(void)
safe_halt();
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
}
-#ifdef CONFIG_APM_MODULE
+#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
EXPORT_SYMBOL(default_idle);
#endif
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 8451f38ad399..1daf8f2aa21f 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -90,8 +90,6 @@ static void ich_force_hpet_resume(void)
BUG();
else
printk(KERN_DEBUG "Force enabled HPET at resume\n");
-
- return;
}
static void ich_force_enable_hpet(struct pci_dev *dev)
@@ -448,7 +446,6 @@ static void nvidia_force_enable_hpet(struct pci_dev *dev)
dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n",
force_hpet_address);
cached_dev = dev;
- return;
}
/* ISA Bridges */
@@ -513,7 +510,6 @@ static void e6xx_force_enable_hpet(struct pci_dev *dev)
force_hpet_resume_type = NONE_FORCE_HPET_RESUME;
dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at "
"0x%lx\n", force_hpet_address);
- return;
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU,
e6xx_force_enable_hpet);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 09d6bded3c1e..0cc7c0b106bb 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -828,11 +828,6 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
return NMI_HANDLED;
}
-static void smp_send_nmi_allbutself(void)
-{
- apic->send_IPI_allbutself(NMI_VECTOR);
-}
-
/*
* Halt all other CPUs, calling the specified function on each of them
*
@@ -861,7 +856,7 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
*/
wmb();
- smp_send_nmi_allbutself();
+ apic_send_IPI_allbutself(NMI_VECTOR);
/* Kick CPUs looping in NMI context. */
WRITE_ONCE(crash_ipi_issued, 1);
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 96421f97e75c..b8d4e9c3c070 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -115,46 +115,6 @@
static atomic_t stopping_cpu = ATOMIC_INIT(-1);
static bool smp_no_nmi_ipi = false;
-/*
- * this function sends a 'reschedule' IPI to another CPU.
- * it goes straight through and wastes no time serializing
- * anything. Worst case is that we lose a reschedule ...
- */
-static void native_smp_send_reschedule(int cpu)
-{
- if (unlikely(cpu_is_offline(cpu))) {
- WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu);
- return;
- }
- apic->send_IPI(cpu, RESCHEDULE_VECTOR);
-}
-
-void native_send_call_func_single_ipi(int cpu)
-{
- apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR);
-}
-
-void native_send_call_func_ipi(const struct cpumask *mask)
-{
- cpumask_var_t allbutself;
-
- if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) {
- apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
- return;
- }
-
- cpumask_copy(allbutself, cpu_online_mask);
- __cpumask_clear_cpu(smp_processor_id(), allbutself);
-
- if (cpumask_equal(mask, allbutself) &&
- cpumask_equal(cpu_online_mask, cpu_callout_mask))
- apic->send_IPI_allbutself(CALL_FUNCTION_VECTOR);
- else
- apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
-
- free_cpumask_var(allbutself);
-}
-
static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
{
/* We are registered on stopping cpu too, avoid spurious NMI */
@@ -179,6 +139,12 @@ asmlinkage __visible void smp_reboot_interrupt(void)
irq_exit();
}
+static int register_stop_handler(void)
+{
+ return register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
+ NMI_FLAG_FIRST, "smp_stop");
+}
+
static void native_stop_other_cpus(int wait)
{
unsigned long flags;
@@ -209,42 +175,44 @@ static void native_stop_other_cpus(int wait)
/* sync above data before sending IRQ */
wmb();
- apic->send_IPI_allbutself(REBOOT_VECTOR);
+ apic_send_IPI_allbutself(REBOOT_VECTOR);
/*
- * Don't wait longer than a second if the caller
- * didn't ask us to wait.
+ * Don't wait longer than a second for IPI completion. The
+ * wait request is not checked here because that would
+ * prevent an NMI shutdown attempt in case that not all
+ * CPUs reach shutdown state.
*/
timeout = USEC_PER_SEC;
- while (num_online_cpus() > 1 && (wait || timeout--))
+ while (num_online_cpus() > 1 && timeout--)
udelay(1);
}
-
- /* if the REBOOT_VECTOR didn't work, try with the NMI */
- if ((num_online_cpus() > 1) && (!smp_no_nmi_ipi)) {
- if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
- NMI_FLAG_FIRST, "smp_stop"))
- /* Note: we ignore failures here */
- /* Hope the REBOOT_IRQ is good enough */
- goto finish;
- /* sync above data before sending IRQ */
- wmb();
-
- pr_emerg("Shutting down cpus with NMI\n");
+ /* if the REBOOT_VECTOR didn't work, try with the NMI */
+ if (num_online_cpus() > 1) {
+ /*
+ * If NMI IPI is enabled, try to register the stop handler
+ * and send the IPI. In any case try to wait for the other
+ * CPUs to stop.
+ */
+ if (!smp_no_nmi_ipi && !register_stop_handler()) {
+ /* Sync above data before sending IRQ */
+ wmb();
- apic->send_IPI_allbutself(NMI_VECTOR);
+ pr_emerg("Shutting down cpus with NMI\n");
+ apic_send_IPI_allbutself(NMI_VECTOR);
+ }
/*
- * Don't wait longer than a 10 ms if the caller
- * didn't ask us to wait.
+ * Don't wait longer than 10 ms if the caller didn't
+ * reqeust it. If wait is true, the machine hangs here if
+ * one or more CPUs do not reach shutdown state.
*/
timeout = USEC_PER_MSEC * 10;
while (num_online_cpus() > 1 && (wait || timeout--))
udelay(1);
}
-finish:
local_irq_save(flags);
disable_local_APIC();
mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fdbd47ceb84d..69881b2d446c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1023,8 +1023,6 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
int *cpu0_nmi_registered)
{
- volatile u32 *trampoline_status =
- (volatile u32 *) __va(real_mode_header->trampoline_status);
/* start_ip had better be page-aligned! */
unsigned long start_ip = real_mode_header->trampoline_start;
@@ -1116,9 +1114,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
}
}
- /* mark "stuck" area as not stuck */
- *trampoline_status = 0;
-
if (x86_platform.legacy.warm_reset) {
/*
* Cleanup possible dangling ends...
@@ -1596,7 +1591,12 @@ int native_cpu_disable(void)
if (ret)
return ret;
- clear_local_APIC();
+ /*
+ * Disable the local APIC. Otherwise IPI broadcasts will reach
+ * it. It still responds normally to INIT, NMI, SMI, and SIPI
+ * messages.
+ */
+ apic_soft_disable();
cpu_disable_common();
return 0;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 57d87f79558f..c59454c382fd 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -638,7 +638,7 @@ unsigned long native_calibrate_tsc(void)
* clock.
*/
if (crystal_khz == 0 &&
- boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_X)
+ boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_D)
crystal_khz = 25000;
/*
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 067858fe4db8..e0cbe4f2af49 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -58,6 +58,10 @@ static const struct freq_desc freq_desc_ann = {
1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 }
};
+static const struct freq_desc freq_desc_lgm = {
+ 1, { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 }
+};
+
static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
INTEL_CPU_FAM6(ATOM_SALTWELL_MID, freq_desc_pnw),
INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET, freq_desc_clv),
@@ -65,6 +69,7 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, freq_desc_tng),
INTEL_CPU_FAM6(ATOM_AIRMONT, freq_desc_cht),
INTEL_CPU_FAM6(ATOM_AIRMONT_MID, freq_desc_ann),
+ INTEL_CPU_FAM6(ATOM_AIRMONT_NP, freq_desc_lgm),
{}
};
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 5b345add550f..548fefed71ee 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -19,7 +19,7 @@
/** DOC: Emulation for User-Mode Instruction Prevention (UMIP)
*
* The feature User-Mode Instruction Prevention present in recent Intel
- * processor prevents a group of instructions (sgdt, sidt, sldt, smsw, and str)
+ * processor prevents a group of instructions (SGDT, SIDT, SLDT, SMSW and STR)
* from being executed with CPL > 0. Otherwise, a general protection fault is
* issued.
*
@@ -36,8 +36,8 @@
* DOSEMU2) rely on this subset of instructions to function.
*
* The instructions protected by UMIP can be split in two groups. Those which
- * return a kernel memory address (sgdt and sidt) and those which return a
- * value (sldt, str and smsw).
+ * return a kernel memory address (SGDT and SIDT) and those which return a
+ * value (SLDT, STR and SMSW).
*
* For the instructions that return a kernel memory address, applications
* such as WineHQ rely on the result being located in the kernel memory space,
@@ -45,15 +45,13 @@
* value that, lies close to the top of the kernel memory. The limit for the GDT
* and the IDT are set to zero.
*
- * Given that sldt and str are not commonly used in programs that run on WineHQ
+ * Given that SLDT and STR are not commonly used in programs that run on WineHQ
* or DOSEMU2, they are not emulated.
*
* The instruction smsw is emulated to return the value that the register CR0
* has at boot time as set in the head_32.
*
- * Also, emulation is provided only for 32-bit processes; 64-bit processes
- * that attempt to use the instructions that UMIP protects will receive the
- * SIGSEGV signal issued as a consequence of the general protection fault.
+ * Emulation is provided for both 32-bit and 64-bit processes.
*
* Care is taken to appropriately emulate the results when segmentation is
* used. That is, rather than relying on USER_DS and USER_CS, the function
@@ -63,17 +61,18 @@
* application uses a local descriptor table.
*/
-#define UMIP_DUMMY_GDT_BASE 0xfffe0000
-#define UMIP_DUMMY_IDT_BASE 0xffff0000
+#define UMIP_DUMMY_GDT_BASE 0xfffffffffffe0000ULL
+#define UMIP_DUMMY_IDT_BASE 0xffffffffffff0000ULL
/*
* The SGDT and SIDT instructions store the contents of the global descriptor
* table and interrupt table registers, respectively. The destination is a
* memory operand of X+2 bytes. X bytes are used to store the base address of
- * the table and 2 bytes are used to store the limit. In 32-bit processes, the
- * only processes for which emulation is provided, X has a value of 4.
+ * the table and 2 bytes are used to store the limit. In 32-bit processes X
+ * has a value of 4, in 64-bit processes X has a value of 8.
*/
-#define UMIP_GDT_IDT_BASE_SIZE 4
+#define UMIP_GDT_IDT_BASE_SIZE_64BIT 8
+#define UMIP_GDT_IDT_BASE_SIZE_32BIT 4
#define UMIP_GDT_IDT_LIMIT_SIZE 2
#define UMIP_INST_SGDT 0 /* 0F 01 /0 */
@@ -189,6 +188,7 @@ static int identify_insn(struct insn *insn)
* @umip_inst: A constant indicating the instruction to emulate
* @data: Buffer into which the dummy result is stored
* @data_size: Size of the emulated result
+ * @x86_64: true if process is 64-bit, false otherwise
*
* Emulate an instruction protected by UMIP and provide a dummy result. The
* result of the emulation is saved in @data. The size of the results depends
@@ -202,11 +202,8 @@ static int identify_insn(struct insn *insn)
* 0 on success, -EINVAL on error while emulating.
*/
static int emulate_umip_insn(struct insn *insn, int umip_inst,
- unsigned char *data, int *data_size)
+ unsigned char *data, int *data_size, bool x86_64)
{
- unsigned long dummy_base_addr, dummy_value;
- unsigned short dummy_limit = 0;
-
if (!data || !data_size || !insn)
return -EINVAL;
/*
@@ -219,6 +216,9 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
* is always returned irrespective of the operand size.
*/
if (umip_inst == UMIP_INST_SGDT || umip_inst == UMIP_INST_SIDT) {
+ u64 dummy_base_addr;
+ u16 dummy_limit = 0;
+
/* SGDT and SIDT do not use registers operands. */
if (X86_MODRM_MOD(insn->modrm.value) == 3)
return -EINVAL;
@@ -228,13 +228,24 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
else
dummy_base_addr = UMIP_DUMMY_IDT_BASE;
- *data_size = UMIP_GDT_IDT_LIMIT_SIZE + UMIP_GDT_IDT_BASE_SIZE;
+ /*
+ * 64-bit processes use the entire dummy base address.
+ * 32-bit processes use the lower 32 bits of the base address.
+ * dummy_base_addr is always 64 bits, but we memcpy the correct
+ * number of bytes from it to the destination.
+ */
+ if (x86_64)
+ *data_size = UMIP_GDT_IDT_BASE_SIZE_64BIT;
+ else
+ *data_size = UMIP_GDT_IDT_BASE_SIZE_32BIT;
+
+ memcpy(data + 2, &dummy_base_addr, *data_size);
- memcpy(data + 2, &dummy_base_addr, UMIP_GDT_IDT_BASE_SIZE);
+ *data_size += UMIP_GDT_IDT_LIMIT_SIZE;
memcpy(data, &dummy_limit, UMIP_GDT_IDT_LIMIT_SIZE);
} else if (umip_inst == UMIP_INST_SMSW) {
- dummy_value = CR0_STATE;
+ unsigned long dummy_value = CR0_STATE;
/*
* Even though the CR0 register has 4 bytes, the number
@@ -290,11 +301,10 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
* fixup_umip_exception() - Fixup a general protection fault caused by UMIP
* @regs: Registers as saved when entering the #GP handler
*
- * The instructions sgdt, sidt, str, smsw, sldt cause a general protection
- * fault if executed with CPL > 0 (i.e., from user space). If the offending
- * user-space process is not in long mode, this function fixes the exception
- * up and provides dummy results for sgdt, sidt and smsw; str and sldt are not
- * fixed up. Also long mode user-space processes are not fixed up.
+ * The instructions SGDT, SIDT, STR, SMSW and SLDT cause a general protection
+ * fault if executed with CPL > 0 (i.e., from user space). This function fixes
+ * the exception up and provides dummy results for SGDT, SIDT and SMSW; STR
+ * and SLDT are not fixed up.
*
* If operands are memory addresses, results are copied to user-space memory as
* indicated by the instruction pointed by eIP using the registers indicated in
@@ -373,13 +383,14 @@ bool fixup_umip_exception(struct pt_regs *regs)
umip_pr_warning(regs, "%s instruction cannot be used by applications.\n",
umip_insns[umip_inst]);
- /* Do not emulate SLDT, STR or user long mode processes. */
- if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT || user_64bit_mode(regs))
+ /* Do not emulate (spoof) SLDT or STR. */
+ if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT)
return false;
umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n");
- if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size))
+ if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size,
+ user_64bit_mode(regs)))
return false;
/*
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index d8359ebeea70..8cd745ef8c7b 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -508,9 +508,12 @@ struct uprobe_xol_ops {
void (*abort)(struct arch_uprobe *, struct pt_regs *);
};
-static inline int sizeof_long(void)
+static inline int sizeof_long(struct pt_regs *regs)
{
- return in_ia32_syscall() ? 4 : 8;
+ /*
+ * Check registers for mode as in_xxx_syscall() does not apply here.
+ */
+ return user_64bit_mode(regs) ? 8 : 4;
}
static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
@@ -521,9 +524,9 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
static int emulate_push_stack(struct pt_regs *regs, unsigned long val)
{
- unsigned long new_sp = regs->sp - sizeof_long();
+ unsigned long new_sp = regs->sp - sizeof_long(regs);
- if (copy_to_user((void __user *)new_sp, &val, sizeof_long()))
+ if (copy_to_user((void __user *)new_sp, &val, sizeof_long(regs)))
return -EFAULT;
regs->sp = new_sp;
@@ -556,7 +559,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs
long correction = utask->vaddr - utask->xol_vaddr;
regs->ip += correction;
} else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) {
- regs->sp += sizeof_long(); /* Pop incorrect return address */
+ regs->sp += sizeof_long(regs); /* Pop incorrect return address */
if (emulate_push_stack(regs, utask->vaddr + auprobe->defparam.ilen))
return -ERESTART;
}
@@ -675,7 +678,7 @@ static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
* "call" insn was executed out-of-line. Just restore ->sp and restart.
* We could also restore ->ip and try to call branch_emulate_op() again.
*/
- regs->sp += sizeof_long();
+ regs->sp += sizeof_long(regs);
return -ERESTART;
}
@@ -1056,7 +1059,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
unsigned long
arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
{
- int rasize = sizeof_long(), nleft;
+ int rasize = sizeof_long(regs), nleft;
unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */
if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize))