summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/apic/apic.c111
-rw-r--r--arch/x86/kernel/apic/io_apic.c16
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h59
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c20
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c78
-rw-r--r--arch/x86/kernel/cpuid.c34
-rw-r--r--arch/x86/kernel/crash.c3
-rw-r--r--arch/x86/kernel/devicetree.c2
-rw-r--r--arch/x86/kernel/dumpstack.c49
-rw-r--r--arch/x86/kernel/dumpstack_32.c42
-rw-r--r--arch/x86/kernel/dumpstack_64.c42
-rw-r--r--arch/x86/kernel/idt.c3
-rw-r--r--arch/x86/kernel/irqinit.c9
-rw-r--r--arch/x86/kernel/kvm.c4
-rw-r--r--arch/x86/kernel/machine_kexec_32.c8
-rw-r--r--arch/x86/kernel/machine_kexec_64.c8
-rw-r--r--arch/x86/kernel/reboot.c3
-rw-r--r--arch/x86/kernel/rtc.c6
-rw-r--r--arch/x86/kernel/vmlinux.lds.S7
-rw-r--r--arch/x86/kernel/x86_init.c6
21 files changed, 293 insertions, 219 deletions
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b203af0855b5..2aabd4cb0e3f 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1408,22 +1408,69 @@ static void lapic_setup_esr(void)
oldvalue, value);
}
+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;
+
+ 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);
+}
+
/**
* setup_local_APIC - setup the local APIC
*
* Used to setup local APIC while initializing BSP or bringing up APs.
* Always called with preemption disabled.
*/
-void setup_local_APIC(void)
+static void setup_local_APIC(void)
{
int cpu = smp_processor_id();
- unsigned int value, queued;
- int i, j, acked = 0;
- unsigned long long tsc = 0, ntsc;
- long long max_loops = cpu_khz ? cpu_khz : 1000000;
+ unsigned int value;
+#ifdef CONFIG_X86_32
+ int logical_apicid, ldr_apicid;
+#endif
- if (boot_cpu_has(X86_FEATURE_TSC))
- tsc = rdtsc();
if (disable_apic) {
disable_ioapic_support();
@@ -1460,11 +1507,11 @@ void setup_local_APIC(void)
* initialized during get_smp_config(), make sure it matches the
* actual value.
*/
- i = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
- WARN_ON(i != BAD_APICID && i != logical_smp_processor_id());
+ 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) =
- logical_smp_processor_id();
+ early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
#endif
/*
@@ -1475,45 +1522,7 @@ void setup_local_APIC(void)
value &= ~APIC_TPRI_MASK;
apic_write(APIC_TASKPRI, value);
- /*
- * 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 (j = 31; j >= 0; j--) {
- if (value & (1<<j)) {
- ack_APIC_irq();
- acked++;
- }
- }
- }
- if (acked > 256) {
- printk(KERN_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);
+ apic_pending_intr_clear();
/*
* Now that we are all set up, enable the APIC
@@ -1570,7 +1579,7 @@ void setup_local_APIC(void)
* TODO: set up through-local-APIC from through-I/O-APIC? --macro
*/
value = apic_read(APIC_LVT0) & APIC_LVT_MASKED;
- if (!cpu && (pic_mode || !value)) {
+ if (!cpu && (pic_mode || !value || skip_ioapic_setup)) {
value = APIC_DM_EXTINT;
apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n", cpu);
} else {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 7c5538769f7e..7553819c74c3 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -587,7 +587,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
mpc_ioapic_id(apic), pin);
}
-static void clear_IO_APIC (void)
+void clear_IO_APIC (void)
{
int apic, pin;
@@ -1410,7 +1410,7 @@ void __init enable_IO_APIC(void)
clear_IO_APIC();
}
-void native_disable_io_apic(void)
+void native_restore_boot_irq_mode(void)
{
/*
* If the i8259 is routed through an IOAPIC
@@ -1438,20 +1438,12 @@ void native_disable_io_apic(void)
disconnect_bsp_APIC(ioapic_i8259.pin != -1);
}
-/*
- * Not an __init, needed by the reboot code
- */
-void disable_IO_APIC(void)
+void restore_boot_irq_mode(void)
{
- /*
- * Clear the IO-APIC before rebooting:
- */
- clear_IO_APIC();
-
if (!nr_legacy_irqs())
return;
- x86_io_apic_ops.disable();
+ x86_apic_ops.restore();
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index f8d9d69994e6..e2829bf40e4a 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -14,7 +14,7 @@ int x2apic_phys;
static struct apic apic_x2apic_phys;
-static int set_x2apic_phys_mode(char *arg)
+static int __init set_x2apic_phys_mode(char *arg)
{
x2apic_phys = 1;
return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index e956eb267061..374d1aa66952 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -113,8 +113,6 @@ static inline void mce_register_injector_chain(struct notifier_block *nb) { }
static inline void mce_unregister_injector_chain(struct notifier_block *nb) { }
#endif
-extern struct mca_config mca_cfg;
-
#ifndef CONFIG_X86_64
/*
* On 32-bit systems it would be difficult to safely unmap a poison page
@@ -130,4 +128,61 @@ static inline void mce_unmap_kpfn(unsigned long pfn) {}
#define mce_unmap_kpfn mce_unmap_kpfn
#endif
+struct mca_config {
+ bool dont_log_ce;
+ bool cmci_disabled;
+ bool ignore_ce;
+
+ __u64 lmce_disabled : 1,
+ disabled : 1,
+ ser : 1,
+ recovery : 1,
+ bios_cmci_threshold : 1,
+ __reserved : 59;
+
+ u8 banks;
+ s8 bootlog;
+ int tolerant;
+ int monarch_timeout;
+ int panic_timeout;
+ u32 rip_msr;
+};
+
+extern struct mca_config mca_cfg;
+
+struct mce_vendor_flags {
+ /*
+ * Indicates that overflow conditions are not fatal, when set.
+ */
+ __u64 overflow_recov : 1,
+
+ /*
+ * (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and
+ * Recovery. It indicates support for data poisoning in HW and deferred
+ * error interrupts.
+ */
+ succor : 1,
+
+ /*
+ * (AMD) SMCA: This bit indicates support for Scalable MCA which expands
+ * the register space for each MCA bank and also increases number of
+ * banks. Also, to accommodate the new banks and registers, the MCA
+ * register space is moved to a new MSR range.
+ */
+ smca : 1,
+
+ __reserved_0 : 61;
+};
+
+extern struct mce_vendor_flags mce_flags;
+
+struct mca_msr_regs {
+ u32 (*ctl) (int bank);
+ u32 (*status) (int bank);
+ u32 (*addr) (int bank);
+ u32 (*misc) (int bank);
+};
+
+extern struct mca_msr_regs msr_ops;
+
#endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 6d43f18e39ea..42cf2880d0ed 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -273,7 +273,9 @@ static void __print_mce(struct mce *m)
static void print_mce(struct mce *m)
{
__print_mce(m);
- pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
+
+ if (m->cpuvendor != X86_VENDOR_AMD)
+ pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}
#define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -1504,7 +1506,7 @@ static int __mcheck_cpu_cap_init(void)
mca_cfg.rip_msr = MSR_IA32_MCG_EIP;
if (cap & MCG_SER_P)
- mca_cfg.ser = true;
+ mca_cfg.ser = 1;
return 0;
}
@@ -1812,12 +1814,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
return;
if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
- mca_cfg.disabled = true;
+ mca_cfg.disabled = 1;
return;
}
if (mce_gen_pool_init()) {
- mca_cfg.disabled = true;
+ mca_cfg.disabled = 1;
pr_emerg("Couldn't allocate MCE records pool!\n");
return;
}
@@ -1895,11 +1897,11 @@ static int __init mcheck_enable(char *str)
if (*str == '=')
str++;
if (!strcmp(str, "off"))
- cfg->disabled = true;
+ cfg->disabled = 1;
else if (!strcmp(str, "no_cmci"))
cfg->cmci_disabled = true;
else if (!strcmp(str, "no_lmce"))
- cfg->lmce_disabled = true;
+ cfg->lmce_disabled = 1;
else if (!strcmp(str, "dont_log_ce"))
cfg->dont_log_ce = true;
else if (!strcmp(str, "ignore_ce"))
@@ -1907,9 +1909,9 @@ static int __init mcheck_enable(char *str)
else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
cfg->bootlog = (str[0] == 'b');
else if (!strcmp(str, "bios_cmci_threshold"))
- cfg->bios_cmci_threshold = true;
+ cfg->bios_cmci_threshold = 1;
else if (!strcmp(str, "recovery"))
- cfg->recovery = true;
+ cfg->recovery = 1;
else if (isdigit(str[0])) {
if (get_option(&str, &cfg->tolerant) == 2)
get_option(&str, &(cfg->monarch_timeout));
@@ -2397,7 +2399,7 @@ device_initcall_sync(mcheck_init_device);
*/
static int __init mcheck_disable(char *str)
{
- mca_cfg.disabled = true;
+ mca_cfg.disabled = 1;
return 1;
}
__setup("nomce", mcheck_disable);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 0f32ad242324..f7666eef4a87 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -82,6 +82,7 @@ static struct smca_bank_name smca_names[] = {
[SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" },
[SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" },
[SMCA_DE] = { "decode_unit", "Decode Unit" },
+ [SMCA_RESERVED] = { "reserved", "Reserved" },
[SMCA_EX] = { "execution_unit", "Execution Unit" },
[SMCA_FP] = { "floating_point", "Floating Point Unit" },
[SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" },
@@ -110,14 +111,14 @@ const char *smca_get_long_name(enum smca_bank_types t)
}
EXPORT_SYMBOL_GPL(smca_get_long_name);
-static enum smca_bank_types smca_get_bank_type(struct mce *m)
+static enum smca_bank_types smca_get_bank_type(unsigned int bank)
{
struct smca_bank *b;
- if (m->bank >= N_SMCA_BANK_TYPES)
+ if (bank >= MAX_NR_BANKS)
return N_SMCA_BANK_TYPES;
- b = &smca_banks[m->bank];
+ b = &smca_banks[bank];
if (!b->hwid)
return N_SMCA_BANK_TYPES;
@@ -127,6 +128,9 @@ static enum smca_bank_types smca_get_bank_type(struct mce *m)
static struct smca_hwid smca_hwid_mcatypes[] = {
/* { bank_type, hwid_mcatype, xec_bitmap } */
+ /* Reserved type */
+ { SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0), 0x0 },
+
/* ZN Core (HWID=0xB0) MCA types */
{ SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF },
{ SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF },
@@ -427,35 +431,58 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
wrmsr(MSR_CU_DEF_ERR, low, high);
}
+static u32 smca_get_block_address(unsigned int cpu, unsigned int bank,
+ unsigned int block)
+{
+ u32 low, high;
+ u32 addr = 0;
+
+ if (smca_get_bank_type(bank) == SMCA_RESERVED)
+ return addr;
+
+ if (!block)
+ return MSR_AMD64_SMCA_MCx_MISC(bank);
+
+ /*
+ * For SMCA enabled processors, BLKPTR field of the first MISC register
+ * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
+ */
+ if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+ return addr;
+
+ if (!(low & MCI_CONFIG_MCAX))
+ return addr;
+
+ if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
+ (low & MASK_BLKPTR_LO))
+ return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+
+ return addr;
+}
+
static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high,
unsigned int bank, unsigned int block)
{
u32 addr = 0, offset = 0;
- if (mce_flags.smca) {
- if (!block) {
- addr = MSR_AMD64_SMCA_MCx_MISC(bank);
- } else {
- /*
- * For SMCA enabled processors, BLKPTR field of the
- * first MISC register (MCx_MISC0) indicates presence of
- * additional MISC register set (MISC1-4).
- */
- u32 low, high;
+ if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
+ return addr;
- if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
- return addr;
+ /* Get address from already initialized block. */
+ if (per_cpu(threshold_banks, cpu)) {
+ struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank];
- if (!(low & MCI_CONFIG_MCAX))
- return addr;
+ if (bankp && bankp->blocks) {
+ struct threshold_block *blockp = &bankp->blocks[block];
- if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
- (low & MASK_BLKPTR_LO))
- addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+ if (blockp)
+ return blockp->address;
}
- return addr;
}
+ if (mce_flags.smca)
+ return smca_get_block_address(cpu, bank, block);
+
/* Fall back to method we used for older processors: */
switch (block) {
case 0:
@@ -760,7 +787,7 @@ bool amd_mce_is_memory_error(struct mce *m)
u8 xec = (m->status >> 16) & 0x1f;
if (mce_flags.smca)
- return smca_get_bank_type(m) == SMCA_UMC && xec == 0x0;
+ return smca_get_bank_type(m->bank) == SMCA_UMC && xec == 0x0;
return m->bank == 4 && xec == 0x8;
}
@@ -1063,7 +1090,7 @@ static struct kobj_type threshold_ktype = {
static const char *get_name(unsigned int bank, struct threshold_block *b)
{
- unsigned int bank_type;
+ enum smca_bank_types bank_type;
if (!mce_flags.smca) {
if (b && bank == 4)
@@ -1072,11 +1099,10 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
return th_names[bank];
}
- if (!smca_banks[bank].hwid)
+ bank_type = smca_get_bank_type(bank);
+ if (bank_type >= N_SMCA_BANK_TYPES)
return NULL;
- bank_type = smca_banks[bank].hwid->bank_type;
-
if (b && bank_type == SMCA_UMC) {
if (b->block < ARRAY_SIZE(smca_umc_block_names))
return smca_umc_block_names[b->block];
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 0931a105ffe1..1d300f96df4b 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -40,6 +40,7 @@
#include <linux/notifier.h>
#include <linux/uaccess.h>
#include <linux/gfp.h>
+#include <linux/completion.h>
#include <asm/processor.h>
#include <asm/msr.h>
@@ -47,19 +48,27 @@
static struct class *cpuid_class;
static enum cpuhp_state cpuhp_cpuid_state;
+struct cpuid_regs_done {
+ struct cpuid_regs regs;
+ struct completion done;
+};
+
static void cpuid_smp_cpuid(void *cmd_block)
{
- struct cpuid_regs *cmd = (struct cpuid_regs *)cmd_block;
+ struct cpuid_regs_done *cmd = cmd_block;
+
+ cpuid_count(cmd->regs.eax, cmd->regs.ecx,
+ &cmd->regs.eax, &cmd->regs.ebx,
+ &cmd->regs.ecx, &cmd->regs.edx);
- cpuid_count(cmd->eax, cmd->ecx,
- &cmd->eax, &cmd->ebx, &cmd->ecx, &cmd->edx);
+ complete(&cmd->done);
}
static ssize_t cpuid_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
char __user *tmp = buf;
- struct cpuid_regs cmd;
+ struct cpuid_regs_done cmd;
int cpu = iminor(file_inode(file));
u64 pos = *ppos;
ssize_t bytes = 0;
@@ -68,19 +77,28 @@ static ssize_t cpuid_read(struct file *file, char __user *buf,
if (count % 16)
return -EINVAL; /* Invalid chunk size */
+ init_completion(&cmd.done);
for (; count; count -= 16) {
- cmd.eax = pos;
- cmd.ecx = pos >> 32;
- err = smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1);
+ call_single_data_t csd = {
+ .func = cpuid_smp_cpuid,
+ .info = &cmd,
+ };
+
+ cmd.regs.eax = pos;
+ cmd.regs.ecx = pos >> 32;
+
+ err = smp_call_function_single_async(cpu, &csd);
if (err)
break;
- if (copy_to_user(tmp, &cmd, 16)) {
+ wait_for_completion(&cmd.done);
+ if (copy_to_user(tmp, &cmd.regs, 16)) {
err = -EFAULT;
break;
}
tmp += 16;
bytes += 16;
*ppos = ++pos;
+ reinit_completion(&cmd.done);
}
return bytes ? bytes : err;
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 10e74d4778a1..1f6680427ff0 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -199,9 +199,10 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
#ifdef CONFIG_X86_IO_APIC
/* Prevent crash_kexec() from deadlocking on ioapic_lock. */
ioapic_zap_locks();
- disable_IO_APIC();
+ clear_IO_APIC();
#endif
lapic_shutdown();
+ restore_boot_irq_mode();
#ifdef CONFIG_HPET_TIMER
hpet_disable();
#endif
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 25de5f6ca997..45416826f6ee 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -259,7 +259,7 @@ static void __init dtb_apic_setup(void)
dtb_ioapic_setup();
}
-#ifdef CONFIG_OF_FLATTREE
+#ifdef CONFIG_OF_EARLY_FLATTREE
static void __init x86_flattree_get_config(void)
{
u32 size, map_len;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index a2d8a3908670..18fa9d74c182 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -24,7 +24,7 @@
int panic_on_unrecovered_nmi;
int panic_on_io_nmi;
-unsigned int code_bytes = 64;
+static unsigned int code_bytes = 64;
static int die_counter;
bool in_task_stack(unsigned long *stack, struct task_struct *task,
@@ -375,3 +375,50 @@ static int __init code_bytes_setup(char *s)
return 1;
}
__setup("code_bytes=", code_bytes_setup);
+
+void show_regs(struct pt_regs *regs)
+{
+ bool all = true;
+ int i;
+
+ show_regs_print_info(KERN_DEFAULT);
+
+ if (IS_ENABLED(CONFIG_X86_32))
+ all = !user_mode(regs);
+
+ __show_regs(regs, all);
+
+ /*
+ * When in-kernel, we also print out the stack and code at the
+ * time of the fault..
+ */
+ if (!user_mode(regs)) {
+ unsigned int code_prologue = code_bytes * 43 / 64;
+ unsigned int code_len = code_bytes;
+ unsigned char c;
+ u8 *ip;
+
+ show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT);
+
+ printk(KERN_DEFAULT "Code: ");
+
+ ip = (u8 *)regs->ip - code_prologue;
+ if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
+ /* try starting at IP */
+ ip = (u8 *)regs->ip;
+ code_len = code_len - code_prologue + 1;
+ }
+ for (i = 0; i < code_len; i++, ip++) {
+ if (ip < (u8 *)PAGE_OFFSET ||
+ probe_kernel_address(ip, c)) {
+ pr_cont(" Bad RIP value.");
+ break;
+ }
+ if (ip == (u8 *)regs->ip)
+ pr_cont("<%02x> ", c);
+ else
+ pr_cont("%02x ", c);
+ }
+ }
+ pr_cont("\n");
+}
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 04170f63e3a1..cd53f3030e40 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -127,45 +127,3 @@ unknown:
info->type = STACK_TYPE_UNKNOWN;
return -EINVAL;
}
-
-void show_regs(struct pt_regs *regs)
-{
- int i;
-
- show_regs_print_info(KERN_EMERG);
- __show_regs(regs, !user_mode(regs));
-
- /*
- * When in-kernel, we also print out the stack and code at the
- * time of the fault..
- */
- if (!user_mode(regs)) {
- unsigned int code_prologue = code_bytes * 43 / 64;
- unsigned int code_len = code_bytes;
- unsigned char c;
- u8 *ip;
-
- show_trace_log_lvl(current, regs, NULL, KERN_EMERG);
-
- pr_emerg("Code:");
-
- ip = (u8 *)regs->ip - code_prologue;
- if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
- /* try starting at IP */
- ip = (u8 *)regs->ip;
- code_len = code_len - code_prologue + 1;
- }
- for (i = 0; i < code_len; i++, ip++) {
- if (ip < (u8 *)PAGE_OFFSET ||
- probe_kernel_address(ip, c)) {
- pr_cont(" Bad EIP value.");
- break;
- }
- if (ip == (u8 *)regs->ip)
- pr_cont(" <%02x>", c);
- else
- pr_cont(" %02x", c);
- }
- }
- pr_cont("\n");
-}
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 563e28d14f2c..5cdb9e84da57 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -149,45 +149,3 @@ unknown:
info->type = STACK_TYPE_UNKNOWN;
return -EINVAL;
}
-
-void show_regs(struct pt_regs *regs)
-{
- int i;
-
- show_regs_print_info(KERN_DEFAULT);
- __show_regs(regs, 1);
-
- /*
- * When in-kernel, we also print out the stack and code at the
- * time of the fault..
- */
- if (!user_mode(regs)) {
- unsigned int code_prologue = code_bytes * 43 / 64;
- unsigned int code_len = code_bytes;
- unsigned char c;
- u8 *ip;
-
- show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT);
-
- printk(KERN_DEFAULT "Code: ");
-
- ip = (u8 *)regs->ip - code_prologue;
- if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
- /* try starting at IP */
- ip = (u8 *)regs->ip;
- code_len = code_len - code_prologue + 1;
- }
- for (i = 0; i < code_len; i++, ip++) {
- if (ip < (u8 *)PAGE_OFFSET ||
- probe_kernel_address(ip, c)) {
- pr_cont(" Bad RIP value.");
- break;
- }
- if (ip == (u8 *)regs->ip)
- pr_cont("<%02x> ", c);
- else
- pr_cont("%02x ", c);
- }
- }
- pr_cont("\n");
-}
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 50bee5fe1140..2c3a1b4294eb 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -140,6 +140,9 @@ static const __initconst struct idt_data apic_idts[] = {
# ifdef CONFIG_IRQ_WORK
INTG(IRQ_WORK_VECTOR, irq_work_interrupt),
# endif
+#ifdef CONFIG_X86_UV
+ INTG(UV_BAU_MESSAGE, uv_bau_message_intr1),
+#endif
INTG(SPURIOUS_APIC_VECTOR, spurious_interrupt),
INTG(ERROR_APIC_VECTOR, error_interrupt),
#endif
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index a539410c4ea9..772196c1b8c4 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -61,9 +61,14 @@ void __init init_ISA_irqs(void)
struct irq_chip *chip = legacy_pic->chip;
int i;
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+ /*
+ * Try to set up the through-local-APIC virtual wire mode earlier.
+ *
+ * On some 32-bit UP machines, whose APIC has been disabled by BIOS
+ * and then got re-enabled by "lapic", it hangs at boot time without this.
+ */
init_bsp_APIC();
-#endif
+
legacy_pic->init(0);
for (i = 0; i < nr_legacy_irqs(); i++)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index bc1a27280c4b..fae86e36e399 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -546,7 +546,7 @@ static void __init kvm_guest_init(void)
}
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
+ kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -635,7 +635,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
int cpu;
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+ kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
for_each_possible_cpu(cpu) {
zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
GFP_KERNEL, cpu_to_node(cpu));
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index edfede768688..60cdec6628b0 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -195,11 +195,11 @@ void machine_kexec(struct kimage *image)
/*
* We need to put APICs in legacy mode so that we can
* get timer interrupts in second kernel. kexec/kdump
- * paths already have calls to disable_IO_APIC() in
- * one form or other. kexec jump path also need
- * one.
+ * paths already have calls to restore_boot_irq_mode()
+ * in one form or other. kexec jump path also need one.
*/
- disable_IO_APIC();
+ clear_IO_APIC();
+ restore_boot_irq_mode();
#endif
}
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 02f913cb27b5..93bd4fb603d1 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -293,11 +293,11 @@ void machine_kexec(struct kimage *image)
/*
* We need to put APICs in legacy mode so that we can
* get timer interrupts in second kernel. kexec/kdump
- * paths already have calls to disable_IO_APIC() in
- * one form or other. kexec jump path also need
- * one.
+ * paths already have calls to restore_boot_irq_mode()
+ * in one form or other. kexec jump path also need one.
*/
- disable_IO_APIC();
+ clear_IO_APIC();
+ restore_boot_irq_mode();
#endif
}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 2126b9d27c34..725624b6c0c0 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -666,7 +666,7 @@ void native_machine_shutdown(void)
* Even without the erratum, it still makes sense to quiet IO APIC
* before disabling Local APIC.
*/
- disable_IO_APIC();
+ clear_IO_APIC();
#endif
#ifdef CONFIG_SMP
@@ -680,6 +680,7 @@ void native_machine_shutdown(void)
#endif
lapic_shutdown();
+ restore_boot_irq_mode();
#ifdef CONFIG_HPET_TIMER
hpet_disable();
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 69ac9cb9cac6..f7b82ed7b5b5 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -41,11 +41,11 @@ EXPORT_SYMBOL(rtc_lock);
*/
int mach_set_rtc_mmss(const struct timespec *now)
{
- unsigned long nowtime = now->tv_sec;
+ unsigned long long nowtime = now->tv_sec;
struct rtc_time tm;
int retval = 0;
- rtc_time_to_tm(nowtime, &tm);
+ rtc_time64_to_tm(nowtime, &tm);
if (!rtc_valid_tm(&tm)) {
retval = mc146818_set_time(&tm);
if (retval)
@@ -53,7 +53,7 @@ int mach_set_rtc_mmss(const struct timespec *now)
__func__, retval);
} else {
printk(KERN_ERR
- "%s: Invalid RTC value: write of %lx to RTC failed\n",
+ "%s: Invalid RTC value: write of %llx to RTC failed\n",
__func__, nowtime);
retval = -EINVAL;
}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index b854ebf5851b..795f3a80e576 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -102,7 +102,6 @@ SECTIONS
_stext = .;
/* bootstrapping code */
HEAD_TEXT
- . = ALIGN(8);
TEXT_TEXT
SCHED_TEXT
CPUIDLE_TEXT
@@ -200,7 +199,7 @@ SECTIONS
. = __vvar_beginning_hack + PAGE_SIZE;
} :data
- . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
+ . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
/* Init code and data - will be freed after init */
. = ALIGN(PAGE_SIZE);
@@ -368,8 +367,8 @@ SECTIONS
. = ALIGN(PAGE_SIZE); /* keep VO_INIT_SIZE page aligned */
_end = .;
- STABS_DEBUG
- DWARF_DEBUG
+ STABS_DEBUG
+ DWARF_DEBUG
/* Sections to be discarded */
DISCARDS
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index ac67ccffeef0..ebda84a91510 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -153,7 +153,7 @@ void arch_restore_msi_irqs(struct pci_dev *dev)
}
#endif
-struct x86_io_apic_ops x86_io_apic_ops __ro_after_init = {
- .read = native_io_apic_read,
- .disable = native_disable_io_apic,
+struct x86_apic_ops x86_apic_ops __ro_after_init = {
+ .io_apic_read = native_io_apic_read,
+ .restore = native_restore_boot_irq_mode,
};