summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/acpi/boot.c2
-rw-r--r--arch/x86/kernel/apic/apic.c30
-rw-r--r--arch/x86/kernel/apic/io_apic.c297
-rw-r--r--arch/x86/kernel/apm_32.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c18
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c14
-rw-r--r--arch/x86/kernel/init_task.c42
-rw-r--r--arch/x86/kernel/irq_32.c8
-rw-r--r--arch/x86/kernel/kvm.c9
-rw-r--r--arch/x86/kernel/microcode_intel.c14
-rw-r--r--arch/x86/kernel/nmi.c83
-rw-r--r--arch/x86/kernel/process.c34
-rw-r--r--arch/x86/kernel/process_64.c1
-rw-r--r--arch/x86/kernel/setup_percpu.c14
-rw-r--r--arch/x86/kernel/smpboot.c83
16 files changed, 183 insertions, 470 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 532d2e090e6f..56ebd1f98447 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -2,7 +2,7 @@
# Makefile for the linux kernel.
#
-extra-y := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinux.lds
+extra-y := head_$(BITS).o head$(BITS).o head.o vmlinux.lds
CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a415b1f44365..7c439fe4941b 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -593,7 +593,7 @@ void __init acpi_set_irq_model_ioapic(void)
#ifdef CONFIG_ACPI_HOTPLUG_CPU
#include <acpi/processor.h>
-static void __cpuinitdata acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static void __cpuinit acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
{
#ifdef CONFIG_ACPI_NUMA
int nid;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index edc24480469f..3722179a49db 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -35,6 +35,7 @@
#include <linux/smp.h>
#include <linux/mm.h>
+#include <asm/irq_remapping.h>
#include <asm/perf_event.h>
#include <asm/x86_init.h>
#include <asm/pgalloc.h>
@@ -1441,8 +1442,8 @@ void __init bsp_end_local_APIC_setup(void)
* Now that local APIC setup is completed for BP, configure the fault
* handling for interrupt remapping.
*/
- if (intr_remapping_enabled)
- enable_drhd_fault_handling();
+ if (irq_remapping_enabled)
+ irq_remap_enable_fault_handling();
}
@@ -1517,7 +1518,7 @@ void enable_x2apic(void)
int __init enable_IR(void)
{
#ifdef CONFIG_IRQ_REMAP
- if (!intr_remapping_supported()) {
+ if (!irq_remapping_supported()) {
pr_debug("intr-remapping not supported\n");
return -1;
}
@@ -1528,7 +1529,7 @@ int __init enable_IR(void)
return -1;
}
- return enable_intr_remapping();
+ return irq_remapping_enable();
#endif
return -1;
}
@@ -1537,10 +1538,13 @@ void __init enable_IR_x2apic(void)
{
unsigned long flags;
int ret, x2apic_enabled = 0;
- int dmar_table_init_ret;
+ int hardware_init_ret;
- dmar_table_init_ret = dmar_table_init();
- if (dmar_table_init_ret && !x2apic_supported())
+ /* Make sure irq_remap_ops are initialized */
+ setup_irq_remapping_ops();
+
+ hardware_init_ret = irq_remapping_prepare();
+ if (hardware_init_ret && !x2apic_supported())
return;
ret = save_ioapic_entries();
@@ -1556,7 +1560,7 @@ void __init enable_IR_x2apic(void)
if (x2apic_preenabled && nox2apic)
disable_x2apic();
- if (dmar_table_init_ret)
+ if (hardware_init_ret)
ret = -1;
else
ret = enable_IR();
@@ -2176,8 +2180,8 @@ static int lapic_suspend(void)
local_irq_save(flags);
disable_local_APIC();
- if (intr_remapping_enabled)
- disable_intr_remapping();
+ if (irq_remapping_enabled)
+ irq_remapping_disable();
local_irq_restore(flags);
return 0;
@@ -2193,7 +2197,7 @@ static void lapic_resume(void)
return;
local_irq_save(flags);
- if (intr_remapping_enabled) {
+ if (irq_remapping_enabled) {
/*
* IO-APIC and PIC have their own resume routines.
* We just mask them here to make sure the interrupt
@@ -2245,8 +2249,8 @@ static void lapic_resume(void)
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
- if (intr_remapping_enabled)
- reenable_intr_remapping(x2apic_mode);
+ if (irq_remapping_enabled)
+ irq_remapping_reenable(x2apic_mode);
local_irq_restore(flags);
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e88300d8e80a..ef0648cd7084 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -86,6 +86,22 @@ void __init set_io_apic_ops(const struct io_apic_ops *ops)
io_apic_ops = *ops;
}
+#ifdef CONFIG_IRQ_REMAP
+static void irq_remap_modify_chip_defaults(struct irq_chip *chip);
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+ return cfg->irq_2_iommu.iommu != NULL;
+}
+#else
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+ return false;
+}
+static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+{
+}
+#endif
+
/*
* Is the SiS APIC rmw bug present ?
* -1 = don't know, 0 = no, 1 = yes
@@ -1361,77 +1377,13 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
fasteoi ? "fasteoi" : "edge");
}
-
-static int setup_ir_ioapic_entry(int irq,
- struct IR_IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
-{
- int index;
- struct irte irte;
- int ioapic_id = mpc_ioapic_id(attr->ioapic);
- struct intel_iommu *iommu = map_ioapic_to_ir(ioapic_id);
-
- if (!iommu) {
- pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
- return -ENODEV;
- }
-
- index = alloc_irte(iommu, irq, 1);
- if (index < 0) {
- pr_warn("Failed to allocate IRTE for ioapic %d\n", ioapic_id);
- return -ENOMEM;
- }
-
- prepare_irte(&irte, vector, destination);
-
- /* Set source-id of interrupt request */
- set_ioapic_sid(&irte, ioapic_id);
-
- modify_irte(irq, &irte);
-
- apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: "
- "Set IRTE entry (P:%d FPD:%d Dst_Mode:%d "
- "Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X "
- "Avail:%X Vector:%02X Dest:%08X "
- "SID:%04X SQ:%X SVT:%X)\n",
- attr->ioapic, irte.present, irte.fpd, irte.dst_mode,
- irte.redir_hint, irte.trigger_mode, irte.dlvry_mode,
- irte.avail, irte.vector, irte.dest_id,
- irte.sid, irte.sq, irte.svt);
-
- memset(entry, 0, sizeof(*entry));
-
- entry->index2 = (index >> 15) & 0x1;
- entry->zero = 0;
- entry->format = 1;
- entry->index = (index & 0x7fff);
- /*
- * IO-APIC RTE will be configured with virtual vector.
- * irq handler will do the explicit EOI to the io-apic.
- */
- entry->vector = attr->ioapic_pin;
- entry->mask = 0; /* enable IRQ */
- entry->trigger = attr->trigger;
- entry->polarity = attr->polarity;
-
- /* Mask level triggered irqs.
- * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
- */
- if (attr->trigger)
- entry->mask = 1;
-
- return 0;
-}
-
static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
unsigned int destination, int vector,
struct io_apic_irq_attr *attr)
{
- if (intr_remapping_enabled)
- return setup_ir_ioapic_entry(irq,
- (struct IR_IO_APIC_route_entry *)entry,
- destination, vector, attr);
+ if (irq_remapping_enabled)
+ return setup_ioapic_remapped_entry(irq, entry, destination,
+ vector, attr);
memset(entry, 0, sizeof(*entry));
@@ -1588,7 +1540,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx,
{
struct IO_APIC_route_entry entry;
- if (intr_remapping_enabled)
+ if (irq_remapping_enabled)
return;
memset(&entry, 0, sizeof(entry));
@@ -1674,7 +1626,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
printk(KERN_DEBUG ".... IRQ redirection table:\n");
- if (intr_remapping_enabled) {
+ if (irq_remapping_enabled) {
printk(KERN_DEBUG " NR Indx Fmt Mask Trig IRR"
" Pol Stat Indx2 Zero Vect:\n");
} else {
@@ -1683,7 +1635,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
}
for (i = 0; i <= reg_01.bits.entries; i++) {
- if (intr_remapping_enabled) {
+ if (irq_remapping_enabled) {
struct IO_APIC_route_entry entry;
struct IR_IO_APIC_route_entry *ir_entry;
@@ -2050,7 +2002,7 @@ void disable_IO_APIC(void)
* IOAPIC RTE as well as interrupt-remapping table entry).
* As this gets called during crash dump, keep this simple for now.
*/
- if (ioapic_i8259.pin != -1 && !intr_remapping_enabled) {
+ if (ioapic_i8259.pin != -1 && !irq_remapping_enabled) {
struct IO_APIC_route_entry entry;
memset(&entry, 0, sizeof(entry));
@@ -2074,7 +2026,7 @@ void disable_IO_APIC(void)
* Use virtual wire A mode when interrupt remapping is enabled.
*/
if (cpu_has_apic || apic_from_smp_config())
- disconnect_bsp_APIC(!intr_remapping_enabled &&
+ disconnect_bsp_APIC(!irq_remapping_enabled &&
ioapic_i8259.pin != -1);
}
@@ -2390,71 +2342,6 @@ ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
return ret;
}
-#ifdef CONFIG_IRQ_REMAP
-
-/*
- * Migrate the IO-APIC irq in the presence of intr-remapping.
- *
- * For both level and edge triggered, irq migration is a simple atomic
- * update(of vector and cpu destination) of IRTE and flush the hardware cache.
- *
- * For level triggered, we eliminate the io-apic RTE modification (with the
- * updated vector information), by using a virtual vector (io-apic pin number).
- * Real vector that is used for interrupting cpu will be coming from
- * the interrupt-remapping table entry.
- *
- * As the migration is a simple atomic update of IRTE, the same mechanism
- * is used to migrate MSI irq's in the presence of interrupt-remapping.
- */
-static int
-ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
-{
- struct irq_cfg *cfg = data->chip_data;
- unsigned int dest, irq = data->irq;
- struct irte irte;
-
- if (!cpumask_intersects(mask, cpu_online_mask))
- return -EINVAL;
-
- if (get_irte(irq, &irte))
- return -EBUSY;
-
- if (assign_irq_vector(irq, cfg, mask))
- return -EBUSY;
-
- dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
-
- irte.vector = cfg->vector;
- irte.dest_id = IRTE_DEST(dest);
-
- /*
- * Atomically updates the IRTE with the new destination, vector
- * and flushes the interrupt entry cache.
- */
- modify_irte(irq, &irte);
-
- /*
- * After this point, all the interrupts will start arriving
- * at the new destination. So, time to cleanup the previous
- * vector allocation.
- */
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
-
- cpumask_copy(data->affinity, mask);
- return 0;
-}
-
-#else
-static inline int
-ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
-{
- return 0;
-}
-#endif
-
asmlinkage void smp_irq_move_cleanup_interrupt(void)
{
unsigned vector, me;
@@ -2699,7 +2586,7 @@ static void irq_remap_modify_chip_defaults(struct irq_chip *chip)
chip->irq_eoi = ir_ack_apic_level;
#ifdef CONFIG_SMP
- chip->irq_set_affinity = ir_ioapic_set_affinity;
+ chip->irq_set_affinity = set_remapped_irq_affinity;
#endif
}
#endif /* CONFIG_IRQ_REMAP */
@@ -2912,7 +2799,7 @@ static inline void __init check_timer(void)
* 8259A.
*/
if (pin1 == -1) {
- if (intr_remapping_enabled)
+ if (irq_remapping_enabled)
panic("BIOS bug: timer not connected to IO-APIC");
pin1 = pin2;
apic1 = apic2;
@@ -2945,7 +2832,7 @@ static inline void __init check_timer(void)
clear_IO_APIC_pin(0, pin1);
goto out;
}
- if (intr_remapping_enabled)
+ if (irq_remapping_enabled)
panic("timer doesn't work through Interrupt-remapped IO-APIC");
local_irq_disable();
clear_IO_APIC_pin(apic1, pin1);
@@ -3169,7 +3056,7 @@ void destroy_irq(unsigned int irq)
irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
if (irq_remapped(cfg))
- free_irte(irq);
+ free_remapped_irq(irq);
raw_spin_lock_irqsave(&vector_lock, flags);
__clear_irq_vector(irq, cfg);
raw_spin_unlock_irqrestore(&vector_lock, flags);
@@ -3198,54 +3085,34 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
if (irq_remapped(cfg)) {
- struct irte irte;
- int ir_index;
- u16 sub_handle;
-
- ir_index = map_irq_to_irte_handle(irq, &sub_handle);
- BUG_ON(ir_index == -1);
-
- prepare_irte(&irte, cfg->vector, dest);
-
- /* Set source-id of interrupt request */
- if (pdev)
- set_msi_sid(&irte, pdev);
- else
- set_hpet_sid(&irte, hpet_id);
-
- modify_irte(irq, &irte);
+ compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id);
+ return err;
+ }
+ if (x2apic_enabled())
+ msg->address_hi = MSI_ADDR_BASE_HI |
+ MSI_ADDR_EXT_DEST_ID(dest);
+ else
msg->address_hi = MSI_ADDR_BASE_HI;
- msg->data = sub_handle;
- msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
- MSI_ADDR_IR_SHV |
- MSI_ADDR_IR_INDEX1(ir_index) |
- MSI_ADDR_IR_INDEX2(ir_index);
- } else {
- if (x2apic_enabled())
- msg->address_hi = MSI_ADDR_BASE_HI |
- MSI_ADDR_EXT_DEST_ID(dest);
- else
- msg->address_hi = MSI_ADDR_BASE_HI;
- msg->address_lo =
- MSI_ADDR_BASE_LO |
- ((apic->irq_dest_mode == 0) ?
- MSI_ADDR_DEST_MODE_PHYSICAL:
- MSI_ADDR_DEST_MODE_LOGICAL) |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_ADDR_REDIRECTION_CPU:
- MSI_ADDR_REDIRECTION_LOWPRI) |
- MSI_ADDR_DEST_ID(dest);
+ msg->address_lo =
+ MSI_ADDR_BASE_LO |
+ ((apic->irq_dest_mode == 0) ?
+ MSI_ADDR_DEST_MODE_PHYSICAL:
+ MSI_ADDR_DEST_MODE_LOGICAL) |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ MSI_ADDR_REDIRECTION_CPU:
+ MSI_ADDR_REDIRECTION_LOWPRI) |
+ MSI_ADDR_DEST_ID(dest);
+
+ msg->data =
+ MSI_DATA_TRIGGER_EDGE |
+ MSI_DATA_LEVEL_ASSERT |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ MSI_DATA_DELIVERY_FIXED:
+ MSI_DATA_DELIVERY_LOWPRI) |
+ MSI_DATA_VECTOR(cfg->vector);
- msg->data =
- MSI_DATA_TRIGGER_EDGE |
- MSI_DATA_LEVEL_ASSERT |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_DATA_DELIVERY_FIXED:
- MSI_DATA_DELIVERY_LOWPRI) |
- MSI_DATA_VECTOR(cfg->vector);
- }
return err;
}
@@ -3288,33 +3155,6 @@ static struct irq_chip msi_chip = {
.irq_retrigger = ioapic_retrigger_irq,
};
-/*
- * Map the PCI dev to the corresponding remapping hardware unit
- * and allocate 'nvec' consecutive interrupt-remapping table entries
- * in it.
- */
-static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
-{
- struct intel_iommu *iommu;
- int index;
-
- iommu = map_dev_to_ir(dev);
- if (!iommu) {
- printk(KERN_ERR
- "Unable to map PCI %s to iommu\n", pci_name(dev));
- return -ENOENT;
- }
-
- index = alloc_irte(iommu, irq, nvec);
- if (index < 0) {
- printk(KERN_ERR
- "Unable to allocate %d IRTE for PCI %s\n", nvec,
- pci_name(dev));
- return -ENOSPC;
- }
- return index;
-}
-
static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
{
struct irq_chip *chip = &msi_chip;
@@ -3345,7 +3185,6 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
int node, ret, sub_handle, index = 0;
unsigned int irq, irq_want;
struct msi_desc *msidesc;
- struct intel_iommu *iommu = NULL;
/* x86 doesn't support multiple MSI yet */
if (type == PCI_CAP_ID_MSI && nvec > 1)
@@ -3359,7 +3198,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
if (irq == 0)
return -1;
irq_want = irq + 1;
- if (!intr_remapping_enabled)
+ if (!irq_remapping_enabled)
goto no_ir;
if (!sub_handle) {
@@ -3367,23 +3206,16 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
* allocate the consecutive block of IRTE's
* for 'nvec'
*/
- index = msi_alloc_irte(dev, irq, nvec);
+ index = msi_alloc_remapped_irq(dev, irq, nvec);
if (index < 0) {
ret = index;
goto error;
}
} else {
- iommu = map_dev_to_ir(dev);
- if (!iommu) {
- ret = -ENOENT;
+ ret = msi_setup_remapped_irq(dev, irq, index,
+ sub_handle);
+ if (ret < 0)
goto error;
- }
- /*
- * setup the mapping between the irq and the IRTE
- * base index, the sub_handle pointing to the
- * appropriate interrupt remap table entry.
- */
- set_irte_irq(irq, iommu, index, sub_handle);
}
no_ir:
ret = setup_msi_irq(dev, msidesc, irq);
@@ -3501,15 +3333,8 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
struct msi_msg msg;
int ret;
- if (intr_remapping_enabled) {
- struct intel_iommu *iommu = map_hpet_to_ir(id);
- int index;
-
- if (!iommu)
- return -1;
-
- index = alloc_irte(iommu, irq, 1);
- if (index < 0)
+ if (irq_remapping_enabled) {
+ if (!setup_hpet_msi_remapped(irq, id))
return -1;
}
@@ -3888,8 +3713,8 @@ void __init setup_ioapic_dest(void)
else
mask = apic->target_cpus();
- if (intr_remapping_enabled)
- ir_ioapic_set_affinity(idata, mask, false);
+ if (irq_remapping_enabled)
+ set_remapped_irq_affinity(idata, mask, false);
else
ioapic_set_affinity(idata, mask, false);
}
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 459e78cbf61e..07b0c0db466c 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -2401,7 +2401,7 @@ static void __exit apm_exit(void)
* (pm_idle), Wait for all processors to update cached/local
* copies of pm_idle before proceeding.
*/
- cpu_idle_wait();
+ kick_all_cpus_sync();
}
if (((apm_info.bios.flags & APM_BIOS_DISENGAGED) == 0)
&& (apm_info.connection_version > 0x0100)) {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1c67ca100e4c..146bb6218eec 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -580,6 +580,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
}
}
+ /* re-enable TopologyExtensions if switched off by BIOS */
+ if ((c->x86 == 0x15) &&
+ (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+ !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+ u64 val;
+
+ if (!rdmsrl_amd_safe(0xc0011005, &val)) {
+ val |= 1ULL << 54;
+ wrmsrl_amd_safe(0xc0011005, val);
+ rdmsrl(0xc0011005, val);
+ if (val & (1ULL << 54)) {
+ set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+ printk(KERN_INFO FW_INFO "CPU: Re-enabling "
+ "disabled Topology Extensions Support\n");
+ }
+ }
+ }
+
cpu_detect_cache_sizes(c);
/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d086a09c087d..11c9166c3337 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -945,9 +945,10 @@ struct mce_info {
atomic_t inuse;
struct task_struct *t;
__u64 paddr;
+ int restartable;
} mce_info[MCE_INFO_MAX];
-static void mce_save_info(__u64 addr)
+static void mce_save_info(__u64 addr, int c)
{
struct mce_info *mi;
@@ -955,6 +956,7 @@ static void mce_save_info(__u64 addr)
if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
mi->t = current;
mi->paddr = addr;
+ mi->restartable = c;
return;
}
}
@@ -1130,7 +1132,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
mce_panic("Fatal machine check on current CPU", &m, msg);
if (worst == MCE_AR_SEVERITY) {
/* schedule action before return to userland */
- mce_save_info(m.addr);
+ mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV);
set_thread_flag(TIF_MCE_NOTIFY);
} else if (kill_it) {
force_sig(SIGBUS, current);
@@ -1179,7 +1181,13 @@ void mce_notify_process(void)
pr_err("Uncorrected hardware memory error in user-access at %llx",
mi->paddr);
- if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) {
+ /*
+ * We must call memory_failure() here even if the current process is
+ * doomed. We still need to mark the page as poisoned and alert any
+ * other users of the page.
+ */
+ if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 ||
+ mi->restartable == 0) {
pr_err("Memory error not recovered");
force_sig(SIGBUS, current);
}
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
deleted file mode 100644
index 43e9ccf44947..000000000000
--- a/arch/x86/kernel/init_task.c
+++ /dev/null
@@ -1,42 +0,0 @@
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/init_task.h>
-#include <linux/fs.h>
-#include <linux/mqueue.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-
-static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
-static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
-
-/*
- * Initial thread structure.
- *
- * We need to make sure that this is THREAD_SIZE aligned due to the
- * way process stacks are handled. This is done by having a special
- * "init_task" linker map entry..
- */
-union thread_union init_thread_union __init_task_data =
- { INIT_THREAD_INFO(init_task) };
-
-/*
- * Initial task structure.
- *
- * All other task structs will be allocated on slabs in fork.c
- */
-struct task_struct init_task = INIT_TASK(init_task);
-EXPORT_SYMBOL(init_task);
-
-/*
- * per-CPU TSS segments. Threads are completely 'soft' on Linux,
- * no more per-task TSS's. The TSS size is kept cacheline-aligned
- * so they are allowed to end up in the .data..cacheline_aligned
- * section. Since TSS's are completely CPU-local, we want them
- * on exact cacheline boundaries, to eliminate cacheline ping-pong.
- */
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
-
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 58b7f27cb3e9..344faf8d0d62 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -127,8 +127,8 @@ void __cpuinit irq_ctx_init(int cpu)
return;
irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
- THREAD_FLAGS,
- THREAD_ORDER));
+ THREADINFO_GFP,
+ THREAD_SIZE_ORDER));
memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
irqctx->tinfo.cpu = cpu;
irqctx->tinfo.preempt_count = HARDIRQ_OFFSET;
@@ -137,8 +137,8 @@ void __cpuinit irq_ctx_init(int cpu)
per_cpu(hardirq_ctx, cpu) = irqctx;
irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
- THREAD_FLAGS,
- THREAD_ORDER));
+ THREADINFO_GFP,
+ THREAD_SIZE_ORDER));
memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
irqctx->tinfo.cpu = cpu;
irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b8ba6e4a27e4..e554e5ad2fe8 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -79,7 +79,6 @@ struct kvm_task_sleep_node {
u32 token;
int cpu;
bool halted;
- struct mm_struct *mm;
};
static struct kvm_task_sleep_head {
@@ -126,9 +125,7 @@ void kvm_async_pf_task_wait(u32 token)
n.token = token;
n.cpu = smp_processor_id();
- n.mm = current->active_mm;
n.halted = idle || preempt_count() > 1;
- atomic_inc(&n.mm->mm_count);
init_waitqueue_head(&n.wq);
hlist_add_head(&n.link, &b->list);
spin_unlock(&b->lock);
@@ -161,9 +158,6 @@ EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
static void apf_task_wake_one(struct kvm_task_sleep_node *n)
{
hlist_del_init(&n->link);
- if (!n->mm)
- return;
- mmdrop(n->mm);
if (n->halted)
smp_send_reschedule(n->cpu);
else if (waitqueue_active(&n->wq))
@@ -207,7 +201,7 @@ again:
* async PF was not yet handled.
* Add dummy entry for the token.
*/
- n = kmalloc(sizeof(*n), GFP_ATOMIC);
+ n = kzalloc(sizeof(*n), GFP_ATOMIC);
if (!n) {
/*
* Allocation failed! Busy wait while other cpu
@@ -219,7 +213,6 @@ again:
}
n->token = token;
n->cpu = smp_processor_id();
- n->mm = NULL;
init_waitqueue_head(&n->wq);
hlist_add_head(&n->link, &b->list);
} else
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 3ca42d0e43a2..0327e2b3c408 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -147,12 +147,6 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
memset(csig, 0, sizeof(*csig));
- if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
- cpu_has(c, X86_FEATURE_IA64)) {
- pr_err("CPU%d not a capable Intel processor\n", cpu_num);
- return -1;
- }
-
csig->sig = cpuid_eax(0x00000001);
if ((c->x86_model >= 5) || (c->x86 > 6)) {
@@ -463,6 +457,14 @@ static struct microcode_ops microcode_intel_ops = {
struct microcode_ops * __init init_intel_microcode(void)
{
+ struct cpuinfo_x86 *c = &cpu_data(0);
+
+ if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
+ cpu_has(c, X86_FEATURE_IA64)) {
+ pr_err("Intel CPU family 0x%x not supported\n", c->x86);
+ return NULL;
+ }
+
return &microcode_intel_ops;
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 47acaf319165..585be4bd71a5 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -31,14 +31,6 @@
#include <asm/nmi.h>
#include <asm/x86_init.h>
-#define NMI_MAX_NAMELEN 16
-struct nmiaction {
- struct list_head list;
- nmi_handler_t handler;
- unsigned int flags;
- char *name;
-};
-
struct nmi_desc {
spinlock_t lock;
struct list_head head;
@@ -54,6 +46,14 @@ static struct nmi_desc nmi_desc[NMI_MAX] =
.lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock),
.head = LIST_HEAD_INIT(nmi_desc[1].head),
},
+ {
+ .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock),
+ .head = LIST_HEAD_INIT(nmi_desc[2].head),
+ },
+ {
+ .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock),
+ .head = LIST_HEAD_INIT(nmi_desc[3].head),
+ },
};
@@ -107,11 +107,14 @@ static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs,
return handled;
}
-static int __setup_nmi(unsigned int type, struct nmiaction *action)
+int __register_nmi_handler(unsigned int type, struct nmiaction *action)
{
struct nmi_desc *desc = nmi_to_desc(type);
unsigned long flags;
+ if (!action->handler)
+ return -EINVAL;
+
spin_lock_irqsave(&desc->lock, flags);
/*
@@ -120,6 +123,8 @@ static int __setup_nmi(unsigned int type, struct nmiaction *action)
* to manage expectations
*/
WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
+ WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
+ WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));
/*
* some handlers need to be executed first otherwise a fake
@@ -133,8 +138,9 @@ static int __setup_nmi(unsigned int type, struct nmiaction *action)
spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
+EXPORT_SYMBOL(__register_nmi_handler);
-static struct nmiaction *__free_nmi(unsigned int type, const char *name)
+void unregister_nmi_handler(unsigned int type, const char *name)
{
struct nmi_desc *desc = nmi_to_desc(type);
struct nmiaction *n;
@@ -157,61 +163,16 @@ static struct nmiaction *__free_nmi(unsigned int type, const char *name)
spin_unlock_irqrestore(&desc->lock, flags);
synchronize_rcu();
- return (n);
}
-
-int register_nmi_handler(unsigned int type, nmi_handler_t handler,
- unsigned long nmiflags, const char *devname)
-{
- struct nmiaction *action;
- int retval = -ENOMEM;
-
- if (!handler)
- return -EINVAL;
-
- action = kzalloc(sizeof(struct nmiaction), GFP_KERNEL);
- if (!action)
- goto fail_action;
-
- action->handler = handler;
- action->flags = nmiflags;
- action->name = kstrndup(devname, NMI_MAX_NAMELEN, GFP_KERNEL);
- if (!action->name)
- goto fail_action_name;
-
- retval = __setup_nmi(type, action);
-
- if (retval)
- goto fail_setup_nmi;
-
- return retval;
-
-fail_setup_nmi:
- kfree(action->name);
-fail_action_name:
- kfree(action);
-fail_action:
-
- return retval;
-}
-EXPORT_SYMBOL_GPL(register_nmi_handler);
-
-void unregister_nmi_handler(unsigned int type, const char *name)
-{
- struct nmiaction *a;
-
- a = __free_nmi(type, name);
- if (a) {
- kfree(a->name);
- kfree(a);
- }
-}
-
EXPORT_SYMBOL_GPL(unregister_nmi_handler);
static notrace __kprobes void
pci_serr_error(unsigned char reason, struct pt_regs *regs)
{
+ /* check to see if anyone registered against these types of errors */
+ if (nmi_handle(NMI_SERR, regs, false))
+ return;
+
pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
reason, smp_processor_id());
@@ -241,6 +202,10 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
{
unsigned long i;
+ /* check to see if anyone registered against these types of errors */
+ if (nmi_handle(NMI_IO_CHECK, regs, false))
+ return;
+
pr_emerg(
"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
reason, smp_processor_id());
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 1d92a5ab6e8b..e8173154800d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -27,6 +27,15 @@
#include <asm/debugreg.h>
#include <asm/nmi.h>
+/*
+ * per-CPU TSS segments. Threads are completely 'soft' on Linux,
+ * no more per-task TSS's. The TSS size is kept cacheline-aligned
+ * so they are allowed to end up in the .data..cacheline_aligned
+ * section. Since TSS's are completely CPU-local, we want them
+ * on exact cacheline boundaries, to eliminate cacheline ping-pong.
+ */
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
+
#ifdef CONFIG_X86_64
static DEFINE_PER_CPU(unsigned char, is_idle);
static ATOMIC_NOTIFIER_HEAD(idle_notifier);
@@ -67,10 +76,9 @@ void free_thread_xstate(struct task_struct *tsk)
fpu_free(&tsk->thread.fpu);
}
-void free_thread_info(struct thread_info *ti)
+void arch_release_task_struct(struct task_struct *tsk)
{
- free_thread_xstate(ti->task);
- free_pages((unsigned long)ti, THREAD_ORDER);
+ free_thread_xstate(tsk);
}
void arch_task_cache_init(void)
@@ -516,26 +524,6 @@ void stop_this_cpu(void *dummy)
}
}
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
- smp_mb();
- /* kick all the CPUs so that they exit out of pm_idle */
- smp_call_function(do_nothing, NULL, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
/* Default MONITOR/MWAIT with no hints, used for default C1 state */
static void mwait_idle(void)
{
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 733ca39f367e..43d8b48b23e6 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -423,6 +423,7 @@ void set_personality_ia32(bool x32)
current_thread_info()->status |= TS_COMPAT;
}
}
+EXPORT_SYMBOL_GPL(set_personality_ia32);
unsigned long get_wchan(struct task_struct *p)
{
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 71f4727da373..5a98aa272184 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void)
#endif
rc = -EINVAL;
if (pcpu_chosen_fc != PCPU_FC_PAGE) {
- const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
const size_t dyn_size = PERCPU_MODULE_RESERVE +
PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+ size_t atom_size;
+ /*
+ * On 64bit, use PMD_SIZE for atom_size so that embedded
+ * percpu areas are aligned to PMD. This, in the future,
+ * can also allow using PMD mappings in vmalloc area. Use
+ * PAGE_SIZE on 32bit as vmalloc space is highly contended
+ * and large vmalloc area allocs can easily fail.
+ */
+#ifdef CONFIG_X86_64
+ atom_size = PMD_SIZE;
+#else
+ atom_size = PAGE_SIZE;
+#endif
rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
dyn_size, atom_size,
pcpu_cpu_distance,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6e1e406038c2..3acaf51dfddb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -76,20 +76,8 @@
/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
-/* Store all idle threads, this can be reused instead of creating
-* a new thread. Also avoids complicated thread destroy functionality
-* for idle threads.
-*/
#ifdef CONFIG_HOTPLUG_CPU
/*
- * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
- * removed after init for !CONFIG_HOTPLUG_CPU.
- */
-static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
-#define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x))
-#define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p))
-
-/*
* We need this for trampoline_base protection from concurrent accesses when
* off- and onlining cores wildly.
*/
@@ -97,20 +85,16 @@ static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex);
void cpu_hotplug_driver_lock(void)
{
- mutex_lock(&x86_cpu_hotplug_driver_mutex);
+ mutex_lock(&x86_cpu_hotplug_driver_mutex);
}
void cpu_hotplug_driver_unlock(void)
{
- mutex_unlock(&x86_cpu_hotplug_driver_mutex);
+ mutex_unlock(&x86_cpu_hotplug_driver_mutex);
}
ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; }
ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; }
-#else
-static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
-#define get_idle_for_cpu(x) (idle_thread_array[(x)])
-#define set_idle_for_cpu(x, p) (idle_thread_array[(x)] = (p))
#endif
/* Number of siblings per CPU package */
@@ -618,22 +602,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
return (send_status | accept_status);
}
-struct create_idle {
- struct work_struct work;
- struct task_struct *idle;
- struct completion done;
- int cpu;
-};
-
-static void __cpuinit do_fork_idle(struct work_struct *work)
-{
- struct create_idle *c_idle =
- container_of(work, struct create_idle, work);
-
- c_idle->idle = fork_idle(c_idle->cpu);
- complete(&c_idle->done);
-}
-
/* reduce the number of lines printed when booting a large cpu count system */
static void __cpuinit announce_cpu(int cpu, int apicid)
{
@@ -660,58 +628,31 @@ static void __cpuinit announce_cpu(int cpu, int apicid)
* Returns zero if CPU booted OK, else error code from
* ->wakeup_secondary_cpu.
*/
-static int __cpuinit do_boot_cpu(int apicid, int cpu)
+static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
{
unsigned long boot_error = 0;
unsigned long start_ip;
int timeout;
- struct create_idle c_idle = {
- .cpu = cpu,
- .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
- };
-
- INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);
alternatives_smp_switch(1);
- c_idle.idle = get_idle_for_cpu(cpu);
-
- /*
- * We can't use kernel_thread since we must avoid to
- * reschedule the child.
- */
- if (c_idle.idle) {
- c_idle.idle->thread.sp = (unsigned long) (((struct pt_regs *)
- (THREAD_SIZE + task_stack_page(c_idle.idle))) - 1);
- init_idle(c_idle.idle, cpu);
- goto do_rest;
- }
+ idle->thread.sp = (unsigned long) (((struct pt_regs *)
+ (THREAD_SIZE + task_stack_page(idle))) - 1);
+ per_cpu(current_task, cpu) = idle;
- schedule_work(&c_idle.work);
- wait_for_completion(&c_idle.done);
-
- if (IS_ERR(c_idle.idle)) {
- printk("failed fork for CPU %d\n", cpu);
- destroy_work_on_stack(&c_idle.work);
- return PTR_ERR(c_idle.idle);
- }
-
- set_idle_for_cpu(cpu, c_idle.idle);
-do_rest:
- per_cpu(current_task, cpu) = c_idle.idle;
#ifdef CONFIG_X86_32
/* Stack for startup_32 can be just as for start_secondary onwards */
irq_ctx_init(cpu);
#else
- clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
+ clear_tsk_thread_flag(idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
per_cpu(kernel_stack, cpu) =
- (unsigned long)task_stack_page(c_idle.idle) -
+ (unsigned long)task_stack_page(idle) -
KERNEL_STACK_OFFSET + THREAD_SIZE;
#endif
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
- stack_start = c_idle.idle->thread.sp;
+ stack_start = idle->thread.sp;
/* start_ip had better be page-aligned! */
start_ip = trampoline_address();
@@ -813,12 +754,10 @@ do_rest:
*/
smpboot_restore_warm_reset_vector();
}
-
- destroy_work_on_stack(&c_idle.work);
return boot_error;
}
-int __cpuinit native_cpu_up(unsigned int cpu)
+int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
int apicid = apic->cpu_present_to_apicid(cpu);
unsigned long flags;
@@ -851,7 +790,7 @@ int __cpuinit native_cpu_up(unsigned int cpu)
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
- err = do_boot_cpu(apicid, cpu);
+ err = do_boot_cpu(apicid, cpu, tidle);
if (err) {
pr_debug("do_boot_cpu failed %d\n", err);
return -EIO;
generated by cgit v1.2.3 (git 2.0.4) at 2024-10-07 16:35:56 +0000