Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 84132ed..2b0faf8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Local APIC handling, local APIC timers
*
@@ -20,7 +21,7 @@
#include <linux/acpi_pmtmr.h>
#include <linux/clockchips.h>
#include <linux/interrupt.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/ftrace.h>
#include <linux/ioport.h>
#include <linux/export.h>
@@ -44,6 +45,7 @@
#include <asm/mpspec.h>
#include <asm/i8259.h>
#include <asm/proto.h>
+#include <asm/traps.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/desc.h>
@@ -63,10 +65,10 @@
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.
@@ -83,13 +85,13 @@
* 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
@@ -112,7 +114,7 @@
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).
@@ -170,34 +172,34 @@
__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
*/
-unsigned 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",
.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
};
-unsigned int lapic_timer_frequency = 0;
+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
@@ -224,6 +226,11 @@
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
boot_cpu_data.x86 >= 0xf)
return 1;
+
+ /* Hygon systems use modern APIC */
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+ return 1;
+
return lapic_get_version() >= 0x14;
}
@@ -494,7 +501,7 @@
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;
}
@@ -583,21 +590,21 @@
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),
{},
};
@@ -715,7 +722,7 @@
static __initdata unsigned long lapic_cal_j1, lapic_cal_j2;
/*
- * Temporary interrupt handler.
+ * Temporary interrupt handler and polled calibration function.
*/
static void __init lapic_cal_handler(struct clock_event_device *dev)
{
@@ -796,33 +803,79 @@
return 0;
}
+static int __init lapic_init_clockevent(void)
+{
+ if (!lapic_timer_period)
+ return -1;
+
+ /* Calculate the scaled math multiplication factor */
+ 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);
+ lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
+ lapic_clockevent.min_delta_ns =
+ clockevent_delta2ns(0xF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ticks = 0xF;
+
+ 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;
+
+ /* 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;
+
+ /* 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);
- void (*real_handler)(struct clock_event_device *dev);
+ u64 tsc_perj = 0, tsc_start = 0;
+ unsigned long jif_start;
unsigned long deltaj;
long delta, deltatsc;
int pm_referenced = 0;
- /**
- * check if lapic timer has already been calibrated by platform
- * specific routine, such as tsc calibration code. if so, we just fill
+ if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+ return 0;
+
+ /*
+ * Check if lapic timer has already been calibrated by platform
+ * specific routine, such as tsc calibration code. If so just fill
* in the clockevent structure and return.
*/
-
- if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
- return 0;
- } else if (lapic_timer_frequency) {
+ if (!lapic_init_clockevent()) {
apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
- lapic_timer_frequency);
- lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
- TICK_NSEC, lapic_clockevent.shift);
- lapic_clockevent.max_delta_ns =
- clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
- lapic_clockevent.max_delta_ticks = 0x7FFFFF;
- lapic_clockevent.min_delta_ns =
- clockevent_delta2ns(0xF, &lapic_clockevent);
- lapic_clockevent.min_delta_ticks = 0xF;
+ lapic_timer_period);
+ /*
+ * Direct calibration methods must have an always running
+ * local APIC timer, no need for broadcast timer.
+ */
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
return 0;
}
@@ -830,29 +883,65 @@
apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
"calibrating APIC timer ...\n");
+ /*
+ * There are platforms w/o global clockevent devices. Instead of
+ * making the calibration conditional on that, use a polling based
+ * approach everywhere.
+ */
local_irq_disable();
- /* Replace the global interrupt handler */
- real_handler = global_clock_event->event_handler;
- global_clock_event->event_handler = lapic_cal_handler;
-
/*
* Setup the APIC counter to maximum. There is no way the lapic
* can underflow in the 100ms detection time frame
*/
__setup_APIC_LVTT(0xffffffff, 0, 0);
- /* Let the interrupts run */
+ /*
+ * Methods to terminate the calibration loop:
+ * 1) Global clockevent if available (jiffies)
+ * 2) TSC if available and frequency is known
+ */
+ jif_start = READ_ONCE(jiffies);
+
+ if (tsc_khz) {
+ tsc_start = rdtsc();
+ tsc_perj = div_u64((u64)tsc_khz * 1000, HZ);
+ }
+
+ /*
+ * Enable interrupts so the tick can fire, if a global
+ * clockevent device is available
+ */
local_irq_enable();
- while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
- cpu_relax();
+ while (lapic_cal_loops <= LAPIC_CAL_LOOPS) {
+ /* Wait for a tick to elapse */
+ while (1) {
+ if (tsc_khz) {
+ u64 tsc_now = rdtsc();
+ if ((tsc_now - tsc_start) >= tsc_perj) {
+ tsc_start += tsc_perj;
+ break;
+ }
+ } else {
+ unsigned long jif_now = READ_ONCE(jiffies);
+
+ if (time_after(jif_now, jif_start)) {
+ jif_start = jif_now;
+ break;
+ }
+ }
+ cpu_relax();
+ }
+
+ /* Invoke the calibration routine */
+ local_irq_disable();
+ lapic_cal_handler(NULL);
+ local_irq_enable();
+ }
local_irq_disable();
- /* Restore the real event handler */
- global_clock_event->event_handler = real_handler;
-
/* Build delta t1-t2 as apic timer counts down */
delta = lapic_cal_t1 - lapic_cal_t2;
apic_printk(APIC_VERBOSE, "... lapic delta = %ld\n", delta);
@@ -863,22 +952,13 @@
pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
&delta, &deltatsc);
- /* Calculate the scaled math multiplication factor */
- lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
- lapic_clockevent.shift);
- lapic_clockevent.max_delta_ns =
- clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
- lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
- lapic_clockevent.min_delta_ns =
- clockevent_delta2ns(0xF, &lapic_clockevent);
- lapic_clockevent.min_delta_ticks = 0xF;
-
- 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 "
@@ -889,13 +969,13 @@
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;
@@ -904,10 +984,11 @@
levt->features &= ~CLOCK_EVT_FEAT_DUMMY;
/*
- * PM timer calibration failed or not turned on
- * so lets try APIC timer based calibration
+ * PM timer calibration failed or not turned on so lets try APIC
+ * timer based calibration, if a global clockevent device is
+ * available.
*/
- if (!pm_referenced) {
+ if (!pm_referenced && global_clock_event) {
apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
/*
@@ -1143,25 +1224,38 @@
}
/**
+ * 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 apic_soft_disable(void)
+{
+ u32 value;
+
+ clear_local_APIC();
+
+ /* 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)
{
- unsigned int value;
-
/* APIC hasn't been mapped yet */
if (!x2apic_mode && !apic_phys)
return;
- clear_local_APIC();
-
- /*
- * Disable APIC (implies clearing of registers
- * for 82489DX!).
- */
- value = apic_read(APIC_SPIV);
- value &= ~APIC_SPIV_APIC_ENABLED;
- apic_write(APIC_SPIV, value);
+ apic_soft_disable();
#ifdef CONFIG_X86_32
/*
@@ -1226,7 +1320,7 @@
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)
{
@@ -1339,6 +1433,8 @@
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)
{
@@ -1412,53 +1508,72 @@
oldvalue, value);
}
+#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)
+{
+ 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 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.
+ */
+ 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)
{
- 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;
+ union apic_ir irr, isr;
+ unsigned int i;
- 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.
- */
- 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 = (cpu_khz << 10) - (ntsc - tsc);
- } else {
- max_loops--;
- }
- }
- } while (queued && max_loops > 0);
- WARN_ON(max_loops <= 0);
+ /* 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);
}
/**
@@ -1471,16 +1586,20 @@
{
int cpu = smp_processor_id();
unsigned int value;
-#ifdef CONFIG_X86_32
- 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) {
@@ -1490,8 +1609,6 @@
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.
@@ -1506,26 +1623,35 @@
apic->init_apic_ldr();
#ifdef CONFIG_X86_32
- /*
- * APIC LDR is initialized. If logical_apicid mapping was
- * initialized during get_smp_config(), make sure it matches the
- * actual value.
- */
- logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
- ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
- WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid);
- /* always use the value from LDR */
- early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
+ if (apic->dest_logical) {
+ int logical_apicid, ldr_apicid;
+
+ /*
+ * APIC LDR is initialized. If logical_apicid mapping was
+ * initialized during get_smp_config(), make sure it matches
+ * the actual value.
+ */
+ logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+ ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+ if (logical_apicid != BAD_APICID)
+ WARN_ON(logical_apicid != ldr_apicid);
+ /* Always use the value from LDR. */
+ early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
+ }
#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();
/*
@@ -1572,6 +1698,8 @@
value |= SPURIOUS_APIC_VECTOR;
apic_write(APIC_SPIV, value);
+ perf_events_lapic_init();
+
/*
* Set up LVT0, LVT1:
*
@@ -1912,6 +2040,8 @@
(boot_cpu_data.x86 >= 15))
break;
goto no_apic;
+ case X86_VENDOR_HYGON:
+ break;
case X86_VENDOR_INTEL:
if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
(boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)))
@@ -2026,21 +2156,32 @@
entering_irq();
trace_spurious_apic_entry(vector);
- /*
- * 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.
- */
- v = apic_read(APIC_ISR + ((vector & ~0x1f) >> 1));
- if (v & (1 << (vector & 0x1f)))
- 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());
+ /*
+ * 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;
+ }
+ /*
+ * 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))) {
+ pr_info("Spurious interrupt (vector 0x%02x) on CPU#%d. Acked\n",
+ vector, smp_processor_id());
+ ack_APIC_irq();
+ } 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();
}
@@ -2401,11 +2542,8 @@
/**
* 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 e84c9eb..7862b15 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -1,6 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright 2004 James Cleverdon, IBM.
- * Subject to the GNU Public License, v.2
*
* Flat APIC subarch code.
*
@@ -8,21 +8,15 @@
* Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
* James Cleverdon.
*/
-#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 <asm/smp.h>
-#include <asm/apic.h>
-#include <asm/ipi.h>
-#include <asm/jailhouse_para.h>
-
#include <linux/acpi.h>
+#include <asm/jailhouse_para.h>
+#include <asm/apic.h>
+
+#include "local.h"
+
static struct apic apic_physflat;
static struct apic apic_flat;
@@ -77,40 +71,11 @@
int cpu = smp_processor_id();
if (cpu < BITS_PER_LONG)
- clear_bit(cpu, &mask);
+ __clear_bit(cpu, &mask);
_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;
@@ -172,9 +137,9 @@
.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,
@@ -224,16 +189,6 @@
*/
}
-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 ||
@@ -275,9 +230,9 @@
.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 5078b5c..98c9bb7 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>
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 78778b5..cdf45b4 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;
@@ -175,7 +175,7 @@
this_cpu_write(cpu_llc_id, node);
/* Account for nodes per socket in multi-core-module processors */
- if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
+ if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
rdmsrl(MSR_FAM10H_NODE_ID, val);
nodes = ((val >> 3) & 7) + 1;
}
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index afee386..38b5b51 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 @@
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 ff0d14c..d6af97f 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -47,7 +47,7 @@
#include <linux/kthread.h>
#include <linux/jiffies.h> /* time_after() */
#include <linux/slab.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <asm/irqdomain.h>
#include <asm/io.h>
@@ -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>
@@ -812,6 +813,7 @@
return IOAPIC_POL_HIGH;
case MP_IRQPOL_RESERVED:
pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
+ /* fall through */
case MP_IRQPOL_ACTIVE_LOW:
default: /* Pointless default required due to do gcc stupidity */
return IOAPIC_POL_LOW;
@@ -859,6 +861,7 @@
return IOAPIC_EDGE;
case MP_IRQTRIG_RESERVED:
pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
+ /* fall through */
case MP_IRQTRIG_LEVEL:
default: /* Pointless default required due to do gcc stupidity */
return IOAPIC_LEVEL;
@@ -1891,6 +1894,50 @@
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,
@@ -1900,6 +1947,7 @@
.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,
};
@@ -1912,6 +1960,7 @@
.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,
};
@@ -2081,6 +2130,9 @@
unsigned long flags;
int no_pin1 = 0;
+ if (!global_clock_event)
+ return;
+
local_irq_save(flags);
/*
@@ -2386,7 +2438,13 @@
* 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
@@ -2578,7 +2636,9 @@
n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource);
n *= nr_ioapics;
- mem = alloc_bootmem(n);
+ mem = memblock_alloc(n, SMP_CACHE_BYTES);
+ if (!mem)
+ panic("%s: Failed to allocate %lu bytes\n", __func__, n);
res = (void *)mem;
mem += sizeof(struct resource) * nr_ioapics;
@@ -2621,7 +2681,11 @@
#ifdef CONFIG_X86_32
fake_ioapic_page:
#endif
- ioapic_phys = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
+ ioapic_phys = (unsigned long)memblock_alloc(PAGE_SIZE,
+ PAGE_SIZE);
+ if (!ioapic_phys)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+ __func__, PAGE_SIZE, PAGE_SIZE);
ioapic_phys = __pa(ioapic_phys);
}
set_fixmap_nocache(idx, ioapic_phys);
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 82f9244..6ca0f91 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/smp.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 "local.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>
+DEFINE_STATIC_KEY_FALSE(apic_use_ipi_shorthand);
-void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
+#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 @@
/*
* 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 @@
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 @@
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 0000000..04797f0
--- /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/msi.c b/arch/x86/kernel/apic/msi.c
index 72a9440..7f75334 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Support of MSI, HPET and DMAR interrupts.
*
@@ -5,10 +6,6 @@
* Moved from arch/x86/kernel/apic/io_apic.c.
* Jiang Liu <jiang.liu@linux.intel.com>
* Convert to hierarchical irqdomain
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/mm.h>
#include <linux/interrupt.h>
@@ -373,14 +370,14 @@
return d;
}
-int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev,
+int hpet_assign_irq(struct irq_domain *domain, struct hpet_channel *hc,
int dev_num)
{
struct irq_alloc_info info;
init_irq_alloc_info(&info, NULL);
info.type = X86_IRQ_ALLOC_TYPE_HPET;
- info.hpet_data = dev;
+ info.hpet_data = hc;
info.hpet_id = hpet_dev_id(domain);
info.hpet_index = dev_num;
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 02e8acb..67b33d6 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -1,56 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Default generic APIC driver. This handles up to 8 CPUs.
*
* Copyright 2003 Andi Kleen, SuSE Labs.
- * Subject to the GNU Public License, v.2
*
* 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)
{
@@ -184,7 +147,9 @@
def_to_bigsmp = 0;
break;
}
- /* If P4 and above fall through */
+ /* P4 and above */
+ /* fall through */
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
def_to_bigsmp = 1;
}
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index c303054..29f0e09 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -1,6 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright 2004 James Cleverdon, IBM.
- * Subject to the GNU Public License, v.2
*
* Generic APIC sub-arch probe layer.
*
@@ -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 @@
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 7654feb..2c5676b 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Local APIC related interfaces to support IOAPIC, MSI, etc.
*
@@ -5,10 +6,6 @@
* Moved from arch/x86/kernel/apic/io_apic.c.
* Jiang Liu <jiang.liu@linux.intel.com>
* Enable support of hierarchical irqdomains
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/interrupt.h>
#include <linux/irq.h>
@@ -18,6 +15,7 @@
#include <linux/slab.h>
#include <asm/irqdomain.h>
#include <asm/hw_irq.h>
+#include <asm/traps.h>
#include <asm/apic.h>
#include <asm/i8259.h>
#include <asm/desc.h>
@@ -313,14 +311,13 @@
struct apic_chip_data *apicd = apic_chip_data(irqd);
int vector, cpu;
- cpumask_and(vector_searchmask, vector_searchmask, affmsk);
- cpu = cpumask_first(vector_searchmask);
- if (cpu >= nr_cpu_ids)
- return -EINVAL;
+ cpumask_and(vector_searchmask, dest, affmsk);
+
/* set_affinity might call here for nothing */
if (apicd->vector && cpumask_test_cpu(apicd->cpu, vector_searchmask))
return 0;
- vector = irq_matrix_alloc_managed(vector_matrix, cpu);
+ vector = irq_matrix_alloc_managed(vector_matrix, vector_searchmask,
+ &cpu);
trace_vector_alloc_managed(irqd->irq, vector, vector);
if (vector < 0)
return vector;
@@ -343,7 +340,7 @@
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;
@@ -352,7 +349,7 @@
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;
@@ -401,6 +398,17 @@
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 a49b360..0000000
--- 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 7685444..b0889c4 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/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 <asm/smp.h>
-#include "x2apic.h"
+#include <linux/cpuhotplug.h>
+#include <linux/cpumask.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <asm/apic.h>
+
+#include "local.h"
struct cluster_mask {
unsigned int clusterid;
@@ -50,7 +48,7 @@
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) {
@@ -84,12 +82,12 @@
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)
@@ -158,7 +156,8 @@
{
struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu);
- cpumask_clear_cpu(dead_cpu, &cmsk->mask);
+ if (cmsk)
+ cpumask_clear_cpu(dead_cpu, &cmsk->mask);
free_cpumask_var(per_cpu(ipi_mask, dead_cpu));
return 0;
}
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index b5cf9e7..bc96938 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 <asm/smp.h>
-#include <asm/ipi.h>
-#include "x2apic.h"
+#include <linux/cpumask.h>
+#include <linux/acpi.h>
+
+#include "local.h"
int x2apic_phys;
@@ -80,12 +75,12 @@
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 @@
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 391f358..e6230af 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -7,41 +7,22 @@
*
* Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved.
*/
-#include <linux/cpumask.h>
-#include <linux/hardirq.h>
-#include <linux/proc_fs.h>
-#include <linux/threads.h>
-#include <linux/kernel.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/cpuhotplug.h>
+#include <linux/cpumask.h>
+#include <linux/proc_fs.h>
#include <linux/memory.h>
+#include <linux/export.h>
+#include <linux/pci.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;
@@ -1079,7 +1060,7 @@
#endif /* !CONFIG_HOTPLUG_CPU */
/* Direct Legacy VGA I/O traffic to designated IOH */
-int uv_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags)
+static int uv_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags)
{
int domain, bus, rc;
@@ -1148,7 +1129,7 @@
mnp->m_shift = mnp->m_val ? 64 - mnp->m_val : 0;
}
-void __init uv_init_hub_info(struct uv_hub_info_s *hi)
+static void __init uv_init_hub_info(struct uv_hub_info_s *hi)
{
union uvh_node_id_u node_id;
struct mn mn;
@@ -1390,7 +1371,7 @@
}
/* Set socket -> node values: */
- lnid = -1;
+ lnid = NUMA_NO_NODE;
for_each_present_cpu(cpu) {
int nid = cpu_to_node(cpu);
int apicid, sockid;
@@ -1521,7 +1502,7 @@
new_hub->pnode = 0xffff;
new_hub->numa_blade_id = uv_node_to_blade_id(nodeid);
- new_hub->memory_nid = -1;
+ new_hub->memory_nid = NUMA_NO_NODE;
new_hub->nr_possible_cpus = 0;
new_hub->nr_online_cpus = 0;
}
@@ -1538,7 +1519,7 @@
uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid);
uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++;
- if (uv_cpu_hub_info(cpu)->memory_nid == -1)
+ if (uv_cpu_hub_info(cpu)->memory_nid == NUMA_NO_NODE)
uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu);
/* Init memoryless node: */