#include <linux/sched.h>
#include <linux/pci.h>
#include <linux/mc146818rtc.h>
+#include <linux/compiler.h>
#include <linux/acpi.h>
+#include <linux/module.h>
#include <linux/sysdev.h>
#include <linux/msi.h>
#include <linux/htirq.h>
-#include <linux/dmar.h>
-#include <linux/jiffies.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/jiffies.h> /* time_after() */
#ifdef CONFIG_ACPI
#include <acpi/acpi_bus.h>
#endif
#include <linux/bootmem.h>
+#include <linux/dmar.h>
#include <asm/idle.h>
#include <asm/io.h>
#include <asm/proto.h>
#include <asm/acpi.h>
#include <asm/dma.h>
+#include <asm/timer.h>
#include <asm/i8259.h>
#include <asm/nmi.h>
#include <asm/msidef.h>
#include <asm/hypertransport.h>
+#include <asm/setup.h>
+#include <asm/irq_remapping.h>
#include <mach_ipi.h>
#include <mach_apic.h>
+#include <mach_apicdef.h>
+
+#define __apicdebuginit(type) static type __init
+
+/*
+ * Is the SiS APIC rmw bug present ?
+ * -1 = don't know, 0 = no, 1 = yes
+ */
+int sis_apic_bug = -1;
+
+static DEFINE_SPINLOCK(ioapic_lock);
+static DEFINE_SPINLOCK(vector_lock);
+
+int first_free_entry;
+/*
+ * Rough estimation of how many shared IRQs there are, can
+ * be changed anytime.
+ */
+int pin_map_size;
+
+/*
+ * # of IRQ routing registers
+ */
+int nr_ioapic_registers[MAX_IO_APICS];
+
+/* I/O APIC entries */
+struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+int nr_ioapics;
+
+/* MP IRQ source entries */
+struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+/* # of MP IRQ source entries */
+int mp_irq_entries;
+
+DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
+
+int skip_ioapic_setup;
+
+static int __init parse_noapic(char *str)
+{
+ disable_ioapic_setup();
+ return 0;
+}
+early_param("noapic", parse_noapic);
+
+
+struct irq_cfg;
+struct irq_pin_list;
struct irq_cfg {
+ unsigned int irq;
+ struct irq_cfg *next;
+ struct irq_pin_list *irq_2_pin;
cpumask_t domain;
cpumask_t old_domain;
unsigned move_cleanup_count;
};
/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
-static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
- [0] = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR, },
- [1] = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR, },
- [2] = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR, },
- [3] = { .domain = CPU_MASK_ALL, .vector = IRQ3_VECTOR, },
- [4] = { .domain = CPU_MASK_ALL, .vector = IRQ4_VECTOR, },
- [5] = { .domain = CPU_MASK_ALL, .vector = IRQ5_VECTOR, },
- [6] = { .domain = CPU_MASK_ALL, .vector = IRQ6_VECTOR, },
- [7] = { .domain = CPU_MASK_ALL, .vector = IRQ7_VECTOR, },
- [8] = { .domain = CPU_MASK_ALL, .vector = IRQ8_VECTOR, },
- [9] = { .domain = CPU_MASK_ALL, .vector = IRQ9_VECTOR, },
- [10] = { .domain = CPU_MASK_ALL, .vector = IRQ10_VECTOR, },
- [11] = { .domain = CPU_MASK_ALL, .vector = IRQ11_VECTOR, },
- [12] = { .domain = CPU_MASK_ALL, .vector = IRQ12_VECTOR, },
- [13] = { .domain = CPU_MASK_ALL, .vector = IRQ13_VECTOR, },
- [14] = { .domain = CPU_MASK_ALL, .vector = IRQ14_VECTOR, },
- [15] = { .domain = CPU_MASK_ALL, .vector = IRQ15_VECTOR, },
+static struct irq_cfg irq_cfg_legacy[] __initdata = {
+ [0] = { .irq = 0, .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR, },
+ [1] = { .irq = 1, .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR, },
+ [2] = { .irq = 2, .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR, },
+ [3] = { .irq = 3, .domain = CPU_MASK_ALL, .vector = IRQ3_VECTOR, },
+ [4] = { .irq = 4, .domain = CPU_MASK_ALL, .vector = IRQ4_VECTOR, },
+ [5] = { .irq = 5, .domain = CPU_MASK_ALL, .vector = IRQ5_VECTOR, },
+ [6] = { .irq = 6, .domain = CPU_MASK_ALL, .vector = IRQ6_VECTOR, },
+ [7] = { .irq = 7, .domain = CPU_MASK_ALL, .vector = IRQ7_VECTOR, },
+ [8] = { .irq = 8, .domain = CPU_MASK_ALL, .vector = IRQ8_VECTOR, },
+ [9] = { .irq = 9, .domain = CPU_MASK_ALL, .vector = IRQ9_VECTOR, },
+ [10] = { .irq = 10, .domain = CPU_MASK_ALL, .vector = IRQ10_VECTOR, },
+ [11] = { .irq = 11, .domain = CPU_MASK_ALL, .vector = IRQ11_VECTOR, },
+ [12] = { .irq = 12, .domain = CPU_MASK_ALL, .vector = IRQ12_VECTOR, },
+ [13] = { .irq = 13, .domain = CPU_MASK_ALL, .vector = IRQ13_VECTOR, },
+ [14] = { .irq = 14, .domain = CPU_MASK_ALL, .vector = IRQ14_VECTOR, },
+ [15] = { .irq = 15, .domain = CPU_MASK_ALL, .vector = IRQ15_VECTOR, },
};
-static int assign_irq_vector(int irq, cpumask_t mask);
+static struct irq_cfg irq_cfg_init = { .irq = -1U, };
+/* need to be biger than size of irq_cfg_legacy */
+static int nr_irq_cfg = 32;
-int first_system_vector = 0xfe;
+static int __init parse_nr_irq_cfg(char *arg)
+{
+ if (arg) {
+ nr_irq_cfg = simple_strtoul(arg, NULL, 0);
+ if (nr_irq_cfg < 32)
+ nr_irq_cfg = 32;
+ }
+ return 0;
+}
-char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
+early_param("nr_irq_cfg", parse_nr_irq_cfg);
-#define __apicdebuginit __init
+static void init_one_irq_cfg(struct irq_cfg *cfg)
+{
+ memcpy(cfg, &irq_cfg_init, sizeof(struct irq_cfg));
+}
-int sis_apic_bug; /* not actually supported, dummy for compile */
+static struct irq_cfg *irq_cfgx;
+static struct irq_cfg *irq_cfgx_free;
+static void __init init_work(void *data)
+{
+ struct dyn_array *da = data;
+ struct irq_cfg *cfg;
+ int legacy_count;
+ int i;
-static int no_timer_check;
+ cfg = *da->name;
-static int disable_timer_pin_1 __initdata;
+ memcpy(cfg, irq_cfg_legacy, sizeof(irq_cfg_legacy));
-int timer_through_8259 __initdata;
+ legacy_count = sizeof(irq_cfg_legacy)/sizeof(irq_cfg_legacy[0]);
+ for (i = legacy_count; i < *da->nr; i++)
+ init_one_irq_cfg(&cfg[i]);
-/* Where if anywhere is the i8259 connect in external int mode */
-static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
+ for (i = 1; i < *da->nr; i++)
+ cfg[i-1].next = &cfg[i];
-static DEFINE_SPINLOCK(ioapic_lock);
-static DEFINE_SPINLOCK(vector_lock);
+ irq_cfgx_free = &irq_cfgx[legacy_count];
+ irq_cfgx[legacy_count - 1].next = NULL;
+}
-/*
- * # of IRQ routing registers
- */
-int nr_ioapic_registers[MAX_IO_APICS];
+#define for_each_irq_cfg(cfg) \
+ for (cfg = irq_cfgx; cfg; cfg = cfg->next)
-/* I/O APIC entries */
-struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
-int nr_ioapics;
+DEFINE_DYN_ARRAY(irq_cfgx, sizeof(struct irq_cfg), nr_irq_cfg, PAGE_SIZE, init_work);
-/* MP IRQ source entries */
-struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+static struct irq_cfg *irq_cfg(unsigned int irq)
+{
+ struct irq_cfg *cfg;
-/* # of MP IRQ source entries */
-int mp_irq_entries;
+ cfg = irq_cfgx;
+ while (cfg) {
+ if (cfg->irq == irq)
+ return cfg;
-DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
+ cfg = cfg->next;
+ }
-/*
- * Rough estimation of how many shared IRQs there are, can
- * be changed anytime.
- */
-#define MAX_PLUS_SHARED_IRQS NR_IRQS
-#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
+ return NULL;
+}
+
+static struct irq_cfg *irq_cfg_alloc(unsigned int irq)
+{
+ struct irq_cfg *cfg, *cfg_pri;
+ int i;
+ int count = 0;
+
+ cfg_pri = cfg = irq_cfgx;
+ while (cfg) {
+ if (cfg->irq == irq)
+ return cfg;
+
+ cfg_pri = cfg;
+ cfg = cfg->next;
+ count++;
+ }
+
+ if (!irq_cfgx_free) {
+ unsigned long phys;
+ unsigned long total_bytes;
+ /*
+ * we run out of pre-allocate ones, allocate more
+ */
+ printk(KERN_DEBUG "try to get more irq_cfg %d\n", nr_irq_cfg);
+
+ total_bytes = sizeof(struct irq_cfg) * nr_irq_cfg;
+ if (after_bootmem)
+ cfg = kzalloc(total_bytes, GFP_ATOMIC);
+ else
+ cfg = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
+
+ if (!cfg)
+ panic("please boot with nr_irq_cfg= %d\n", count * 2);
+
+ phys = __pa(cfg);
+ printk(KERN_DEBUG "irq_irq ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
+
+ for (i = 0; i < nr_irq_cfg; i++)
+ init_one_irq_cfg(&cfg[i]);
+
+ for (i = 1; i < nr_irq_cfg; i++)
+ cfg[i-1].next = &cfg[i];
+
+ irq_cfgx_free = cfg;
+ }
+
+ cfg = irq_cfgx_free;
+ irq_cfgx_free = irq_cfgx_free->next;
+ cfg->next = NULL;
+ if (cfg_pri)
+ cfg_pri->next = cfg;
+ else
+ irq_cfgx = cfg;
+ cfg->irq = irq;
+ printk(KERN_DEBUG "found new irq_cfg for irq %d\n", cfg->irq);
+#ifdef CONFIG_HAVE_SPARSE_IRQ_DEBUG
+ {
+ /* dump the results */
+ struct irq_cfg *cfg;
+ unsigned long phys;
+ unsigned long bytes = sizeof(struct irq_cfg);
+
+ printk(KERN_DEBUG "=========================== %d\n", irq);
+ printk(KERN_DEBUG "irq_cfg dump after get that for %d\n", irq);
+ for_each_irq_cfg(cfg) {
+ phys = __pa(cfg);
+ printk(KERN_DEBUG "irq_cfg %d ==> [%#lx - %#lx]\n", cfg->irq, phys, phys + bytes);
+ }
+ printk(KERN_DEBUG "===========================\n");
+ }
+#endif
+ return cfg;
+}
/*
* This is performance-critical, we want to do it O(1)
* between pins and IRQs.
*/
-static struct irq_pin_list {
- short apic, pin, next;
-} irq_2_pin[PIN_MAP_SIZE];
+struct irq_pin_list {
+ int apic, pin;
+ struct irq_pin_list *next;
+};
+
+static struct irq_pin_list *irq_2_pin_head;
+/* fill one page ? */
+static int nr_irq_2_pin = 0x100;
+static struct irq_pin_list *irq_2_pin_ptr;
+static void __init irq_2_pin_init_work(void *data)
+{
+ struct dyn_array *da = data;
+ struct irq_pin_list *pin;
+ int i;
+
+ pin = *da->name;
+
+ for (i = 1; i < *da->nr; i++)
+ pin[i-1].next = &pin[i];
+
+ irq_2_pin_ptr = &pin[0];
+}
+DEFINE_DYN_ARRAY(irq_2_pin_head, sizeof(struct irq_pin_list), nr_irq_2_pin, PAGE_SIZE, irq_2_pin_init_work);
+
+static struct irq_pin_list *get_one_free_irq_2_pin(void)
+{
+ struct irq_pin_list *pin;
+ int i;
+
+ pin = irq_2_pin_ptr;
+
+ if (pin) {
+ irq_2_pin_ptr = pin->next;
+ pin->next = NULL;
+ return pin;
+ }
+
+ /*
+ * we run out of pre-allocate ones, allocate more
+ */
+ printk(KERN_DEBUG "try to get more irq_2_pin %d\n", nr_irq_2_pin);
+
+ if (after_bootmem)
+ pin = kzalloc(sizeof(struct irq_pin_list)*nr_irq_2_pin,
+ GFP_ATOMIC);
+ else
+ pin = __alloc_bootmem_nopanic(sizeof(struct irq_pin_list) *
+ nr_irq_2_pin, PAGE_SIZE, 0);
+
+ if (!pin)
+ panic("can not get more irq_2_pin\n");
+
+ for (i = 1; i < nr_irq_2_pin; i++)
+ pin[i-1].next = &pin[i];
+
+ irq_2_pin_ptr = pin->next;
+ pin->next = NULL;
+
+ return pin;
+}
struct io_apic {
unsigned int index;
* Re-write a value: to be used for read-modify-write
* cycles where the read already set up the index register.
*/
-static inline void io_apic_modify(unsigned int apic, unsigned int value)
+static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
+ if (sis_apic_bug)
+ writel(reg, &io_apic->index);
writel(value, &io_apic->data);
}
{
struct irq_pin_list *entry;
unsigned long flags;
+ struct irq_cfg *cfg = irq_cfg(irq);
spin_lock_irqsave(&ioapic_lock, flags);
- entry = irq_2_pin + irq;
+ entry = cfg->irq_2_pin;
for (;;) {
unsigned int reg;
int pin;
- pin = entry->pin;
- if (pin == -1)
+ if (!entry)
break;
+ pin = entry->pin;
reg = io_apic_read(entry->apic, 0x10 + pin*2);
/* Is the remote IRR bit set? */
if (reg & IO_APIC_REDIR_REMOTE_IRR) {
}
if (!entry->next)
break;
- entry = irq_2_pin + entry->next;
+ entry = entry->next;
}
spin_unlock_irqrestore(&ioapic_lock, flags);
return false;
}
-/*
- * Synchronize the IO-APIC and the CPU by doing
- * a dummy read from the IO-APIC
- */
-static inline void io_apic_sync(unsigned int apic)
-{
- struct io_apic __iomem *io_apic = io_apic_base(apic);
- readl(&io_apic->data);
-}
-
-#define __DO_ACTION(R, ACTION, FINAL) \
- \
-{ \
- int pin; \
- struct irq_pin_list *entry = irq_2_pin + irq; \
- \
- BUG_ON(irq >= NR_IRQS); \
- for (;;) { \
- unsigned int reg; \
- pin = entry->pin; \
- if (pin == -1) \
- break; \
- reg = io_apic_read(entry->apic, 0x10 + R + pin*2); \
- reg ACTION; \
- io_apic_modify(entry->apic, reg); \
- FINAL; \
- if (!entry->next) \
- break; \
- entry = irq_2_pin + entry->next; \
- } \
-}
-
union entry_union {
struct { u32 w1, w2; };
struct IO_APIC_route_entry entry;
static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
{
int apic, pin;
- struct irq_pin_list *entry = irq_2_pin + irq;
+ struct irq_cfg *cfg;
+ struct irq_pin_list *entry;
- BUG_ON(irq >= NR_IRQS);
+ cfg = irq_cfg(irq);
+ entry = cfg->irq_2_pin;
for (;;) {
unsigned int reg;
+
+ if (!entry)
+ break;
+
apic = entry->apic;
pin = entry->pin;
- if (pin == -1)
- break;
+#ifdef CONFIG_INTR_REMAP
+ /*
+ * With interrupt-remapping, destination information comes
+ * from interrupt-remapping table entry.
+ */
+ if (!irq_remapped(irq))
+ io_apic_write(apic, 0x11 + pin*2, dest);
+#else
io_apic_write(apic, 0x11 + pin*2, dest);
+#endif
reg = io_apic_read(apic, 0x10 + pin*2);
reg &= ~IO_APIC_REDIR_VECTOR_MASK;
reg |= vector;
- io_apic_modify(apic, reg);
+ io_apic_modify(apic, 0x10 + pin*2, reg);
if (!entry->next)
break;
- entry = irq_2_pin + entry->next;
+ entry = entry->next;
}
}
+static int assign_irq_vector(int irq, cpumask_t mask);
+
static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
{
- struct irq_cfg *cfg = irq_cfg + irq;
+ struct irq_cfg *cfg = irq_cfg(irq);
unsigned long flags;
unsigned int dest;
cpumask_t tmp;
+ struct irq_desc *desc;
cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
*/
dest = SET_APIC_LOGICAL_ID(dest);
+ desc = irq_to_desc(irq);
spin_lock_irqsave(&ioapic_lock, flags);
__target_IO_APIC_irq(irq, dest, cfg->vector);
- irq_desc[irq].affinity = mask;
+ desc->affinity = mask;
spin_unlock_irqrestore(&ioapic_lock, flags);
}
#endif
*/
static void add_pin_to_irq(unsigned int irq, int apic, int pin)
{
- static int first_free_entry = NR_IRQS;
- struct irq_pin_list *entry = irq_2_pin + irq;
+ struct irq_cfg *cfg;
+ struct irq_pin_list *entry;
+
+ /* first time to refer irq_cfg, so with new */
+ cfg = irq_cfg_alloc(irq);
+ entry = cfg->irq_2_pin;
+ if (!entry) {
+ entry = get_one_free_irq_2_pin();
+ cfg->irq_2_pin = entry;
+ entry->apic = apic;
+ entry->pin = pin;
+ printk(KERN_DEBUG " 0 add_pin_to_irq: irq %d --> apic %d pin %d\n", irq, apic, pin);
+ return;
+ }
- BUG_ON(irq >= NR_IRQS);
- while (entry->next)
- entry = irq_2_pin + entry->next;
+ while (entry->next) {
+ /* not again, please */
+ if (entry->apic == apic && entry->pin == pin)
+ return;
- if (entry->pin != -1) {
- entry->next = first_free_entry;
- entry = irq_2_pin + entry->next;
- if (++first_free_entry >= PIN_MAP_SIZE)
- panic("io_apic.c: ran out of irq_2_pin entries!");
+ entry = entry->next;
}
+
+ entry->next = get_one_free_irq_2_pin();
+ entry = entry->next;
entry->apic = apic;
entry->pin = pin;
+ printk(KERN_DEBUG " x add_pin_to_irq: irq %d --> apic %d pin %d\n", irq, apic, pin);
}
/*
int oldapic, int oldpin,
int newapic, int newpin)
{
- struct irq_pin_list *entry = irq_2_pin + irq;
+ struct irq_cfg *cfg = irq_cfg(irq);
+ struct irq_pin_list *entry = cfg->irq_2_pin;
+ int replaced = 0;
- while (1) {
+ while (entry) {
if (entry->apic == oldapic && entry->pin == oldpin) {
entry->apic = newapic;
entry->pin = newpin;
- }
- if (!entry->next)
+ replaced = 1;
+ /* every one is different, right? */
break;
- entry = irq_2_pin + entry->next;
+ }
+ entry = entry->next;
}
+
+ /* why? call replace before add? */
+ if (!replaced)
+ add_pin_to_irq(irq, newapic, newpin);
+}
+
+/*
+ * Synchronize the IO-APIC and the CPU by doing
+ * a dummy read from the IO-APIC
+ */
+static inline void io_apic_sync(unsigned int apic)
+{
+ struct io_apic __iomem *io_apic = io_apic_base(apic);
+ readl(&io_apic->data);
}
+#define __DO_ACTION(R, ACTION, FINAL) \
+ \
+{ \
+ int pin; \
+ struct irq_cfg *cfg; \
+ struct irq_pin_list *entry; \
+ \
+ cfg = irq_cfg(irq); \
+ entry = cfg->irq_2_pin; \
+ for (;;) { \
+ unsigned int reg; \
+ if (!entry) \
+ break; \
+ pin = entry->pin; \
+ reg = io_apic_read(entry->apic, 0x10 + R + pin*2); \
+ reg ACTION; \
+ io_apic_modify(entry->apic, 0x10 + R + pin*2, reg); \
+ FINAL; \
+ if (!entry->next) \
+ break; \
+ entry = entry->next; \
+ } \
+}
#define DO_ACTION(name,R,ACTION, FINAL) \
\
clear_IO_APIC_pin(apic, pin);
}
-int skip_ioapic_setup;
-int ioapic_force;
+#ifdef CONFIG_INTR_REMAP
+/* I/O APIC RTE contents at the OS boot up */
+static struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS];
-static int __init parse_noapic(char *str)
+/*
+ * Saves and masks all the unmasked IO-APIC RTE's
+ */
+int save_mask_IO_APIC_setup(void)
{
- disable_ioapic_setup();
+ union IO_APIC_reg_01 reg_01;
+ unsigned long flags;
+ int apic, pin;
+
+ /*
+ * The number of IO-APIC IRQ registers (== #pins):
+ */
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(apic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ nr_ioapic_registers[apic] = reg_01.bits.entries+1;
+ }
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ early_ioapic_entries[apic] =
+ kzalloc(sizeof(struct IO_APIC_route_entry) *
+ nr_ioapic_registers[apic], GFP_KERNEL);
+ if (!early_ioapic_entries[apic])
+ return -ENOMEM;
+ }
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+ struct IO_APIC_route_entry entry;
+
+ entry = early_ioapic_entries[apic][pin] =
+ ioapic_read_entry(apic, pin);
+ if (!entry.mask) {
+ entry.mask = 1;
+ ioapic_write_entry(apic, pin, entry);
+ }
+ }
return 0;
}
-early_param("noapic", parse_noapic);
-/* Actually the next is obsolete, but keep it for paranoid reasons -AK */
-static int __init disable_timer_pin_setup(char *arg)
+void restore_IO_APIC_setup(void)
{
- disable_timer_pin_1 = 1;
- return 1;
+ int apic, pin;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+ ioapic_write_entry(apic, pin,
+ early_ioapic_entries[apic][pin]);
}
-__setup("disable_timer_pin_1", disable_timer_pin_setup);
+void reinit_intr_remapped_IO_APIC(int intr_remapping)
+{
+ /*
+ * for now plain restore of previous settings.
+ * TBD: In the case of OS enabling interrupt-remapping,
+ * IO-APIC RTE's need to be setup to point to interrupt-remapping
+ * table entries. for now, do a plain restore, and wait for
+ * the setup_IO_APIC_irqs() to do proper initialization.
+ */
+ restore_IO_APIC_setup();
+}
+#endif
/*
* Find the IRQ entry number of a certain pin.
best_guess = irq;
}
}
- BUG_ON(best_guess >= NR_IRQS);
return best_guess;
}
irq += nr_ioapic_registers[i++];
irq += pin;
}
- BUG_ON(irq >= NR_IRQS);
return irq;
}
int cpu;
struct irq_cfg *cfg;
- BUG_ON((unsigned)irq >= NR_IRQS);
- cfg = &irq_cfg[irq];
+ cfg = irq_cfg(irq);
/* Only try and allocate irqs on cpus that are present */
cpus_and(mask, mask, cpu_online_map);
cpumask_t mask;
int cpu, vector;
- BUG_ON((unsigned)irq >= NR_IRQS);
- cfg = &irq_cfg[irq];
+ cfg = irq_cfg(irq);
BUG_ON(!cfg->vector);
vector = cfg->vector;
/* Initialize vector_irq on a new cpu */
/* This function must be called with vector_lock held */
int irq, vector;
+ struct irq_cfg *cfg;
/* Mark the inuse vectors */
- for (irq = 0; irq < NR_IRQS; ++irq) {
- if (!cpu_isset(cpu, irq_cfg[irq].domain))
+ for_each_irq_cfg(cfg) {
+ if (!cpu_isset(cpu, cfg->domain))
continue;
- vector = irq_cfg[irq].vector;
+ vector = cfg->vector;
+ irq = cfg->irq;
per_cpu(vector_irq, cpu)[vector] = irq;
}
/* Mark the free vectors */
irq = per_cpu(vector_irq, cpu)[vector];
if (irq < 0)
continue;
- if (!cpu_isset(cpu, irq_cfg[irq].domain))
+
+ cfg = irq_cfg(irq);
+ if (!cpu_isset(cpu, cfg->domain))
per_cpu(vector_irq, cpu)[vector] = -1;
}
}
static struct irq_chip ioapic_chip;
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip;
+#endif
static void ioapic_register_intr(int irq, unsigned long trigger)
{
- if (trigger) {
- irq_desc[irq].status |= IRQ_LEVEL;
+ struct irq_desc *desc;
+
+ /* first time to use this irq_desc */
+ if (irq < 16)
+ desc = irq_to_desc(irq);
+ else
+ desc = irq_to_desc_alloc(irq);
+
+ if (trigger)
+ desc->status |= IRQ_LEVEL;
+ else
+ desc->status &= ~IRQ_LEVEL;
+
+#ifdef CONFIG_INTR_REMAP
+ if (irq_remapped(irq)) {
+ desc->status |= IRQ_MOVE_PCNTXT;
+ if (trigger)
+ set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+ handle_fasteoi_irq,
+ "fasteoi");
+ else
+ set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+ handle_edge_irq, "edge");
+ return;
+ }
+#endif
+ if (trigger)
set_irq_chip_and_handler_name(irq, &ioapic_chip,
- handle_fasteoi_irq, "fasteoi");
- } else {
- irq_desc[irq].status &= ~IRQ_LEVEL;
+ handle_fasteoi_irq,
+ "fasteoi");
+ else
set_irq_chip_and_handler_name(irq, &ioapic_chip,
handle_edge_irq, "edge");
+}
+
+static int setup_ioapic_entry(int apic, int irq,
+ struct IO_APIC_route_entry *entry,
+ unsigned int destination, int trigger,
+ int polarity, int vector)
+{
+ /*
+ * add it to the IO-APIC irq-routing table:
+ */
+ memset(entry,0,sizeof(*entry));
+
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled) {
+ struct intel_iommu *iommu = map_ioapic_to_ir(apic);
+ struct irte irte;
+ struct IR_IO_APIC_route_entry *ir_entry =
+ (struct IR_IO_APIC_route_entry *) entry;
+ int index;
+
+ if (!iommu)
+ panic("No mapping iommu for ioapic %d\n", apic);
+
+ index = alloc_irte(iommu, irq, 1);
+ if (index < 0)
+ panic("Failed to allocate IRTE for ioapic %d\n", apic);
+
+ memset(&irte, 0, sizeof(irte));
+
+ irte.present = 1;
+ irte.dst_mode = INT_DEST_MODE;
+ irte.trigger_mode = trigger;
+ irte.dlvry_mode = INT_DELIVERY_MODE;
+ irte.vector = vector;
+ irte.dest_id = IRTE_DEST(destination);
+
+ modify_irte(irq, &irte);
+
+ ir_entry->index2 = (index >> 15) & 0x1;
+ ir_entry->zero = 0;
+ ir_entry->format = 1;
+ ir_entry->index = (index & 0x7fff);
+ } else
+#endif
+ {
+ entry->delivery_mode = INT_DELIVERY_MODE;
+ entry->dest_mode = INT_DEST_MODE;
+ entry->dest = destination;
}
+
+ entry->mask = 0; /* enable IRQ */
+ entry->trigger = trigger;
+ entry->polarity = polarity;
+ entry->vector = vector;
+
+ /* Mask level triggered irqs.
+ * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
+ */
+ if (trigger)
+ entry->mask = 1;
+ return 0;
}
static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
int trigger, int polarity)
{
- struct irq_cfg *cfg = irq_cfg + irq;
+ struct irq_cfg *cfg;
struct IO_APIC_route_entry entry;
cpumask_t mask;
if (!IO_APIC_IRQ(irq))
return;
+ cfg = irq_cfg(irq);
+
mask = TARGET_CPUS;
if (assign_irq_vector(irq, mask))
return;
apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
irq, trigger, polarity);
- /*
- * add it to the IO-APIC irq-routing table:
- */
- memset(&entry,0,sizeof(entry));
-
- entry.delivery_mode = INT_DELIVERY_MODE;
- entry.dest_mode = INT_DEST_MODE;
- entry.dest = cpu_mask_to_apicid(mask);
- entry.mask = 0; /* enable IRQ */
- entry.trigger = trigger;
- entry.polarity = polarity;
- entry.vector = cfg->vector;
- /* Mask level triggered irqs.
- * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
- */
- if (trigger)
- entry.mask = 1;
+ if (setup_ioapic_entry(mp_ioapics[apic].mp_apicid, irq, &entry,
+ cpu_mask_to_apicid(mask), trigger, polarity,
+ cfg->vector)) {
+ printk("Failed to setup ioapic entry for ioapic %d, pin %d\n",
+ mp_ioapics[apic].mp_apicid, pin);
+ __clear_irq_vector(irq);
+ return;
+ }
ioapic_register_intr(irq, trigger);
if (irq < 16)
{
struct IO_APIC_route_entry entry;
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled)
+ return;
+#endif
+
memset(&entry, 0, sizeof(entry));
/*
ioapic_write_entry(apic, pin, entry);
}
-void __apicdebuginit print_IO_APIC(void)
+
+__apicdebuginit(void) print_IO_APIC(void)
{
int apic, i;
union IO_APIC_reg_00 reg_00;
union IO_APIC_reg_01 reg_01;
union IO_APIC_reg_02 reg_02;
unsigned long flags;
+ struct irq_cfg *cfg;
if (apic_verbosity == APIC_QUIET)
return;
printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
+ printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type);
+ printk(KERN_DEBUG "....... : LTS : %X\n", reg_00.bits.LTS);
printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)®_01);
printk(KERN_DEBUG "....... : max redirection entries: %04X\n", reg_01.bits.entries);
}
}
printk(KERN_DEBUG "IRQ to pin mappings:\n");
- for (i = 0; i < NR_IRQS; i++) {
- struct irq_pin_list *entry = irq_2_pin + i;
- if (entry->pin < 0)
+ for_each_irq_cfg(cfg) {
+ struct irq_pin_list *entry = cfg->irq_2_pin;
+ if (!entry)
continue;
- printk(KERN_DEBUG "IRQ%d ", i);
+ printk(KERN_DEBUG "IRQ%d ", cfg->irq);
for (;;) {
printk("-> %d:%d", entry->apic, entry->pin);
if (!entry->next)
break;
- entry = irq_2_pin + entry->next;
+ entry = entry->next;
}
printk("\n");
}
return;
}
-#if 0
-
-static __apicdebuginit void print_APIC_bitfield (int base)
+__apicdebuginit(void) print_APIC_bitfield(int base)
{
unsigned int v;
int i, j;
}
}
-void __apicdebuginit print_local_APIC(void * dummy)
+__apicdebuginit(void) print_local_APIC(void *dummy)
{
unsigned int v, ver, maxlvt;
+ unsigned long icr;
if (apic_verbosity == APIC_QUIET)
return;
printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
smp_processor_id(), hard_smp_processor_id());
v = apic_read(APIC_ID);
- printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
+ printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, read_apic_id());
v = apic_read(APIC_LVR);
printk(KERN_INFO "... APIC VERSION: %08x\n", v);
ver = GET_APIC_VERSION(v);
v = apic_read(APIC_ESR);
printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
- v = apic_read(APIC_ICR);
- printk(KERN_DEBUG "... APIC ICR: %08x\n", v);
- v = apic_read(APIC_ICR2);
- printk(KERN_DEBUG "... APIC ICR2: %08x\n", v);
+ icr = apic_icr_read();
+ printk(KERN_DEBUG "... APIC ICR: %08x\n", (u32)icr);
+ printk(KERN_DEBUG "... APIC ICR2: %08x\n", (u32)(icr >> 32));
v = apic_read(APIC_LVTT);
printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
printk("\n");
}
-void print_all_local_APICs (void)
+__apicdebuginit(void) print_all_local_APICs(void)
{
on_each_cpu(print_local_APIC, NULL, 1);
}
-void __apicdebuginit print_PIC(void)
+__apicdebuginit(void) print_PIC(void)
{
unsigned int v;
unsigned long flags;
printk(KERN_DEBUG "... PIC ELCR: %04x\n", v);
}
-#endif /* 0 */
+__apicdebuginit(int) print_all_ICs(void)
+{
+ print_PIC();
+ print_all_local_APICs();
+ print_IO_APIC();
+
+ return 0;
+}
+
+fs_initcall(print_all_ICs);
+
+
+/* Where if anywhere is the i8259 connect in external int mode */
+static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
void __init enable_IO_APIC(void)
{
union IO_APIC_reg_01 reg_01;
int i8259_apic, i8259_pin;
- int i, apic;
+ int apic;
unsigned long flags;
- for (i = 0; i < PIN_MAP_SIZE; i++) {
- irq_2_pin[i].pin = -1;
- irq_2_pin[i].next = 0;
- }
-
/*
* The number of IO-APIC IRQ registers (== #pins):
*/
entry.dest_mode = 0; /* Physical */
entry.delivery_mode = dest_ExtINT; /* ExtInt */
entry.vector = 0;
- entry.dest = GET_APIC_ID(read_apic_id());
+ entry.dest = read_apic_id();
/*
* Add it to the IO-APIC irq-routing table:
disconnect_bsp_APIC(ioapic_i8259.pin != -1);
}
+int no_timer_check __initdata;
+
+static int __init notimercheck(char *s)
+{
+ no_timer_check = 1;
+ return 1;
+}
+__setup("no_timer_check", notimercheck);
+
/*
* There is a nasty bug in some older SMP boards, their mptable lies
* about the timer IRQ. We do the following to work around the situation:
unsigned long t1 = jiffies;
unsigned long flags;
+ if (no_timer_check)
+ return 1;
+
local_save_flags(flags);
local_irq_enable();
/* Let ten ticks pass... */
return 0;
}
-/*
- * In the SMP+IOAPIC case it might happen that there are an unspecified
- * number of pending IRQ events unhandled. These cases are very rare,
- * so we 'resend' these IRQs via IPIs, to the same CPU. It's much
- * better to do it this way as thus we do not have to be aware of
- * 'pending' interrupts in the IRQ path, except at this point.
- */
-/*
- * Edge triggered needs to resend any interrupt
- * that was delayed but this is now handled in the device
- * independent code.
- */
+/*
+ * In the SMP+IOAPIC case it might happen that there are an unspecified
+ * number of pending IRQ events unhandled. These cases are very rare,
+ * so we 'resend' these IRQs via IPIs, to the same CPU. It's much
+ * better to do it this way as thus we do not have to be aware of
+ * 'pending' interrupts in the IRQ path, except at this point.
+ */
+/*
+ * Edge triggered needs to resend any interrupt
+ * that was delayed but this is now handled in the device
+ * independent code.
+ */
+
+/*
+ * Starting up a edge-triggered IO-APIC interrupt is
+ * nasty - we need to make sure that we get the edge.
+ * If it is already asserted for some reason, we need
+ * return 1 to indicate that is was pending.
+ *
+ * This is not complete - we should be able to fake
+ * an edge even if it isn't on the 8259A...
+ */
+
+static unsigned int startup_ioapic_irq(unsigned int irq)
+{
+ int was_pending = 0;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ if (irq < 16) {
+ disable_8259A_irq(irq);
+ if (i8259A_irq_pending(irq))
+ was_pending = 1;
+ }
+ __unmask_IO_APIC_irq(irq);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return was_pending;
+}
+
+static int ioapic_retrigger_irq(unsigned int irq)
+{
+ struct irq_cfg *cfg = irq_cfg(irq);
+ unsigned long flags;
+
+ spin_lock_irqsave(&vector_lock, flags);
+ send_IPI_mask(cpumask_of_cpu(first_cpu(cfg->domain)), cfg->vector);
+ spin_unlock_irqrestore(&vector_lock, flags);
+
+ return 1;
+}
+
+/*
+ * Level and edge triggered IO-APIC interrupts need different handling,
+ * so we use two separate IRQ descriptors. Edge triggered IRQs can be
+ * handled with the level-triggered descriptor, but that one has slightly
+ * more overhead. Level-triggered interrupts cannot be handled with the
+ * edge-triggered handler, without risking IRQ storms and other ugly
+ * races.
+ */
+
+#ifdef CONFIG_SMP
+
+#ifdef CONFIG_INTR_REMAP
+static void ir_irq_migration(struct work_struct *work);
+
+static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration);
+
+/*
+ * Migrate the IO-APIC irq in the presence of intr-remapping.
+ *
+ * For 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 need to modify the io-apic RTE aswell with the update
+ * vector information, along with modifying IRTE with vector and destination.
+ * So irq migration for level triggered is little bit more complex compared to
+ * edge triggered migration. But the good news is, we use the same algorithm
+ * for level triggered migration as we have today, only difference being,
+ * we now initiate the irq migration from process context instead of the
+ * interrupt context.
+ *
+ * In future, when we do a directed EOI (combined with cpu EOI broadcast
+ * suppression) to the IO-APIC, level triggered irq migration will also be
+ * as simple as edge triggered migration and we can do the irq migration
+ * with a simple atomic update to IO-APIC RTE.
+ */
+static void migrate_ioapic_irq(int irq, cpumask_t mask)
+{
+ struct irq_cfg *cfg;
+ struct irq_desc *desc;
+ cpumask_t tmp, cleanup_mask;
+ struct irte irte;
+ int modify_ioapic_rte;
+ unsigned int dest;
+ unsigned long flags;
+
+ cpus_and(tmp, mask, cpu_online_map);
+ if (cpus_empty(tmp))
+ return;
+
+ if (get_irte(irq, &irte))
+ return;
+
+ if (assign_irq_vector(irq, mask))
+ return;
+
+ cfg = irq_cfg(irq);
+ cpus_and(tmp, cfg->domain, mask);
+ dest = cpu_mask_to_apicid(tmp);
+
+ desc = irq_to_desc(irq);
+ modify_ioapic_rte = desc->status & IRQ_LEVEL;
+ if (modify_ioapic_rte) {
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __target_IO_APIC_irq(irq, dest, cfg->vector);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ }
+
+ irte.vector = cfg->vector;
+ irte.dest_id = IRTE_DEST(dest);
+
+ /*
+ * Modified the IRTE and flushes the Interrupt entry cache.
+ */
+ modify_irte(irq, &irte);
-/*
- * Starting up a edge-triggered IO-APIC interrupt is
- * nasty - we need to make sure that we get the edge.
- * If it is already asserted for some reason, we need
- * return 1 to indicate that is was pending.
- *
- * This is not complete - we should be able to fake
- * an edge even if it isn't on the 8259A...
- */
+ if (cfg->move_in_progress) {
+ cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+ cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+ send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+ cfg->move_in_progress = 0;
+ }
-static unsigned int startup_ioapic_irq(unsigned int irq)
+ desc->affinity = mask;
+}
+
+static int migrate_irq_remapped_level(int irq)
{
- int was_pending = 0;
- unsigned long flags;
+ int ret = -1;
+ struct irq_desc *desc = irq_to_desc(irq);
- spin_lock_irqsave(&ioapic_lock, flags);
- if (irq < 16) {
- disable_8259A_irq(irq);
- if (i8259A_irq_pending(irq))
- was_pending = 1;
+ mask_IO_APIC_irq(irq);
+
+ if (io_apic_level_ack_pending(irq)) {
+ /*
+ * Interrupt in progress. Migrating irq now will change the
+ * vector information in the IO-APIC RTE and that will confuse
+ * the EOI broadcast performed by cpu.
+ * So, delay the irq migration to the next instance.
+ */
+ schedule_delayed_work(&ir_migration_work, 1);
+ goto unmask;
}
- __unmask_IO_APIC_irq(irq);
- spin_unlock_irqrestore(&ioapic_lock, flags);
- return was_pending;
+ /* everthing is clear. we have right of way */
+ migrate_ioapic_irq(irq, desc->pending_mask);
+
+ ret = 0;
+ desc->status &= ~IRQ_MOVE_PENDING;
+ cpus_clear(desc->pending_mask);
+
+unmask:
+ unmask_IO_APIC_irq(irq);
+ return ret;
}
-static int ioapic_retrigger_irq(unsigned int irq)
+static void ir_irq_migration(struct work_struct *work)
{
- struct irq_cfg *cfg = &irq_cfg[irq];
- unsigned long flags;
+ unsigned int irq;
+ struct irq_desc *desc;
- spin_lock_irqsave(&vector_lock, flags);
- send_IPI_mask(cpumask_of_cpu(first_cpu(cfg->domain)), cfg->vector);
- spin_unlock_irqrestore(&vector_lock, flags);
+ for_each_irq_desc(irq, desc) {
+ if (desc->status & IRQ_MOVE_PENDING) {
+ unsigned long flags;
- return 1;
+ spin_lock_irqsave(&desc->lock, flags);
+ if (!desc->chip->set_affinity ||
+ !(desc->status & IRQ_MOVE_PENDING)) {
+ desc->status &= ~IRQ_MOVE_PENDING;
+ spin_unlock_irqrestore(&desc->lock, flags);
+ continue;
+ }
+
+ desc->chip->set_affinity(irq, desc->pending_mask);
+ spin_unlock_irqrestore(&desc->lock, flags);
+ }
+ }
}
/*
- * Level and edge triggered IO-APIC interrupts need different handling,
- * so we use two separate IRQ descriptors. Edge triggered IRQs can be
- * handled with the level-triggered descriptor, but that one has slightly
- * more overhead. Level-triggered interrupts cannot be handled with the
- * edge-triggered handler, without risking IRQ storms and other ugly
- * races.
+ * Migrates the IRQ destination in the process context.
*/
+static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ if (desc->status & IRQ_LEVEL) {
+ desc->status |= IRQ_MOVE_PENDING;
+ desc->pending_mask = mask;
+ migrate_irq_remapped_level(irq);
+ return;
+ }
+
+ migrate_ioapic_irq(irq, mask);
+}
+#endif
-#ifdef CONFIG_SMP
asmlinkage void smp_irq_move_cleanup_interrupt(void)
{
unsigned vector, me;
struct irq_desc *desc;
struct irq_cfg *cfg;
irq = __get_cpu_var(vector_irq)[vector];
- if (irq >= NR_IRQS)
+
+ desc = irq_to_desc(irq);
+ if (!desc)
continue;
- desc = irq_desc + irq;
- cfg = irq_cfg + irq;
+ cfg = irq_cfg(irq);
spin_lock(&desc->lock);
if (!cfg->move_cleanup_count)
goto unlock;
static void irq_complete_move(unsigned int irq)
{
- struct irq_cfg *cfg = irq_cfg + irq;
+ struct irq_cfg *cfg = irq_cfg(irq);
unsigned vector, me;
if (likely(!cfg->move_in_progress))
#else
static inline void irq_complete_move(unsigned int irq) {}
#endif
+#ifdef CONFIG_INTR_REMAP
+static void ack_x2apic_level(unsigned int irq)
+{
+ ack_x2APIC_irq();
+}
+
+static void ack_x2apic_edge(unsigned int irq)
+{
+ ack_x2APIC_irq();
+}
+#endif
static void ack_apic_edge(unsigned int irq)
{
irq_complete_move(irq);
#ifdef CONFIG_GENERIC_PENDING_IRQ
/* If we are moving the irq we need to mask it */
- if (unlikely(irq_desc[irq].status & IRQ_MOVE_PENDING)) {
+ if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
do_unmask_irq = 1;
mask_IO_APIC_irq(irq);
}
.retrigger = ioapic_retrigger_irq,
};
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip __read_mostly = {
+ .name = "IR-IO-APIC",
+ .startup = startup_ioapic_irq,
+ .mask = mask_IO_APIC_irq,
+ .unmask = unmask_IO_APIC_irq,
+ .ack = ack_x2apic_edge,
+ .eoi = ack_x2apic_level,
+#ifdef CONFIG_SMP
+ .set_affinity = set_ir_ioapic_affinity_irq,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+#endif
+
static inline void init_IO_APIC_traps(void)
{
int irq;
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
/*
* NOTE! The local APIC isn't very good at handling
* Also, we've got to be careful not to trash gate
* 0x80, because int 0x80 is hm, kind of importantish. ;)
*/
- for (irq = 0; irq < NR_IRQS ; irq++) {
- if (IO_APIC_IRQ(irq) && !irq_cfg[irq].vector) {
+ for_each_irq_cfg(cfg) {
+ irq = cfg->irq;
+ if (IO_APIC_IRQ(irq) && !cfg->vector) {
/*
* Hmm.. We don't have an entry for this,
* so default to an old-fashioned 8259
*/
if (irq < 16)
make_8259A_irq(irq);
- else
+ else {
+ desc = irq_to_desc(irq);
/* Strange. Oh, well.. */
- irq_desc[irq].chip = &no_irq_chip;
+ desc->chip = &no_irq_chip;
+ }
}
}
}
static void lapic_register_intr(int irq)
{
- irq_desc[irq].status &= ~IRQ_LEVEL;
+ struct irq_desc *desc;
+
+ desc = irq_to_desc(irq);
+ desc->status &= ~IRQ_LEVEL;
set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
"edge");
}
ioapic_write_entry(apic, pin, entry0);
}
+static int disable_timer_pin_1 __initdata;
+/* Actually the next is obsolete, but keep it for paranoid reasons -AK */
+static int __init disable_timer_pin_setup(char *arg)
+{
+ disable_timer_pin_1 = 1;
+ return 0;
+}
+early_param("disable_timer_pin_1", disable_timer_pin_setup);
+
+int timer_through_8259 __initdata;
+
/*
* This code may look a bit paranoid, but it's supposed to cooperate with
* a wide range of boards and BIOS bugs. Fortunately only the timer IRQ
*/
static inline void __init check_timer(void)
{
- struct irq_cfg *cfg = irq_cfg + 0;
+ struct irq_cfg *cfg = irq_cfg(0);
int apic1, pin1, apic2, pin2;
unsigned long flags;
int no_pin1 = 0;
* 8259A.
*/
if (pin1 == -1) {
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled)
+ panic("BIOS bug: timer not connected to IO-APIC");
+#endif
pin1 = pin2;
apic1 = apic2;
no_pin1 = 1;
setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
}
unmask_IO_APIC_irq(0);
- if (!no_timer_check && timer_irq_works()) {
+ if (timer_irq_works()) {
if (nmi_watchdog == NMI_IO_APIC) {
setup_nmi();
enable_8259A_irq(0);
clear_IO_APIC_pin(0, pin1);
goto out;
}
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled)
+ panic("timer doesn't work through Interrupt-remapped IO-APIC");
+#endif
clear_IO_APIC_pin(apic1, pin1);
if (!no_pin1)
apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: "
local_irq_restore(flags);
}
-static int __init notimercheck(char *s)
-{
- no_timer_check = 1;
- return 1;
-}
-__setup("no_timer_check", notimercheck);
-
/*
* Traditionally ISA IRQ2 is the cascade IRQ, and is not available
* to devices. However there may be an I/O APIC pin available for
setup_IO_APIC_irqs();
init_IO_APIC_traps();
check_timer();
- if (!acpi_ioapic)
- print_IO_APIC();
}
+/*
+ * Called after all the initialization is done. If we didnt find any
+ * APIC bugs then we can allow the modify fast path
+ */
+
+static int __init io_apic_bug_finalize(void)
+{
+ if (sis_apic_bug == -1)
+ sis_apic_bug = 0;
+ return 0;
+}
+
+late_initcall(io_apic_bug_finalize);
+
struct sysfs_ioapic_data {
struct sys_device dev;
struct IO_APIC_route_entry entry[0];
/*
* Dynamic irq allocate and deallocation
*/
-int create_irq(void)
+unsigned int create_irq_nr(unsigned int irq_want)
{
/* Allocate an unused irq */
- int irq;
- int new;
+ unsigned int irq;
+ unsigned int new;
unsigned long flags;
+ struct irq_cfg *cfg_new;
- irq = -ENOSPC;
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+ irq_want = nr_irqs - 1;
+#endif
+
+ irq = 0;
spin_lock_irqsave(&vector_lock, flags);
- for (new = (NR_IRQS - 1); new >= 0; new--) {
+ for (new = irq_want; new > 0; new--) {
if (platform_legacy_irq(new))
continue;
- if (irq_cfg[new].vector != 0)
+ cfg_new = irq_cfg(new);
+ if (cfg_new && cfg_new->vector != 0)
continue;
+ /* check if need to create one */
+ if (!cfg_new)
+ cfg_new = irq_cfg_alloc(new);
if (__assign_irq_vector(new, TARGET_CPUS) == 0)
irq = new;
break;
}
spin_unlock_irqrestore(&vector_lock, flags);
- if (irq >= 0) {
+ if (irq > 0) {
dynamic_irq_init(irq);
}
return irq;
}
+int create_irq(void)
+{
+ int irq;
+
+ irq = create_irq_nr(nr_irqs - 1);
+
+ if (irq == 0)
+ irq = -1;
+
+ return irq;
+}
+
void destroy_irq(unsigned int irq)
{
unsigned long flags;
dynamic_irq_cleanup(irq);
+#ifdef CONFIG_INTR_REMAP
+ free_irte(irq);
+#endif
spin_lock_irqsave(&vector_lock, flags);
__clear_irq_vector(irq);
spin_unlock_irqrestore(&vector_lock, flags);
#ifdef CONFIG_PCI_MSI
static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
{
- struct irq_cfg *cfg = irq_cfg + irq;
+ struct irq_cfg *cfg;
int err;
unsigned dest;
cpumask_t tmp;
tmp = TARGET_CPUS;
err = assign_irq_vector(irq, tmp);
- if (!err) {
- cpus_and(tmp, cfg->domain, tmp);
- dest = cpu_mask_to_apicid(tmp);
+ if (err)
+ return err;
+ cfg = irq_cfg(irq);
+ cpus_and(tmp, cfg->domain, tmp);
+ dest = cpu_mask_to_apicid(tmp);
+
+#ifdef CONFIG_INTR_REMAP
+ if (irq_remapped(irq)) {
+ struct irte irte;
+ int ir_index;
+ u16 sub_handle;
+
+ ir_index = map_irq_to_irte_handle(irq, &sub_handle);
+ BUG_ON(ir_index == -1);
+
+ memset (&irte, 0, sizeof(irte));
+
+ irte.present = 1;
+ irte.dst_mode = INT_DEST_MODE;
+ irte.trigger_mode = 0; /* edge */
+ irte.dlvry_mode = INT_DELIVERY_MODE;
+ irte.vector = cfg->vector;
+ irte.dest_id = IRTE_DEST(dest);
+
+ modify_irte(irq, &irte);
+
+ 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
+#endif
+ {
msg->address_hi = MSI_ADDR_BASE_HI;
msg->address_lo =
MSI_ADDR_BASE_LO |
#ifdef CONFIG_SMP
static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
{
- struct irq_cfg *cfg = irq_cfg + irq;
+ struct irq_cfg *cfg;
struct msi_msg msg;
unsigned int dest;
cpumask_t tmp;
+ struct irq_desc *desc;
cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
if (assign_irq_vector(irq, mask))
return;
+ cfg = irq_cfg(irq);
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);
msg.address_lo |= MSI_ADDR_DEST_ID(dest);
write_msi_msg(irq, &msg);
- irq_desc[irq].affinity = mask;
+ desc = irq_to_desc(irq);
+ desc->affinity = mask;
+}
+
+#ifdef CONFIG_INTR_REMAP
+/*
+ * Migrate the MSI irq to another cpumask. This migration is
+ * done in the process context using interrupt-remapping hardware.
+ */
+static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+{
+ struct irq_cfg *cfg;
+ unsigned int dest;
+ cpumask_t tmp, cleanup_mask;
+ struct irte irte;
+ struct irq_desc *desc;
+
+ cpus_and(tmp, mask, cpu_online_map);
+ if (cpus_empty(tmp))
+ return;
+
+ if (get_irte(irq, &irte))
+ return;
+
+ if (assign_irq_vector(irq, mask))
+ return;
+
+ cfg = irq_cfg(irq);
+ cpus_and(tmp, cfg->domain, mask);
+ dest = cpu_mask_to_apicid(tmp);
+
+ irte.vector = cfg->vector;
+ irte.dest_id = IRTE_DEST(dest);
+
+ /*
+ * atomically update the IRTE with the new destination and vector.
+ */
+ 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) {
+ cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+ cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+ send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+ cfg->move_in_progress = 0;
+ }
+
+ desc = irq_to_desc(irq);
+ desc->affinity = mask;
}
+#endif
#endif /* CONFIG_SMP */
/*
.retrigger = ioapic_retrigger_irq,
};
-int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip msi_ir_chip = {
+ .name = "IR-PCI-MSI",
+ .unmask = unmask_msi_irq,
+ .mask = mask_msi_irq,
+ .ack = ack_x2apic_edge,
+#ifdef CONFIG_SMP
+ .set_affinity = ir_set_msi_irq_affinity,
+#endif
+ .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;
+}
+#endif
+
+static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
{
+ int ret;
struct msi_msg msg;
- int irq, ret;
- irq = create_irq();
- if (irq < 0)
- return irq;
ret = msi_compose_msg(dev, irq, &msg);
+ if (ret < 0)
+ return ret;
+
+ set_irq_msi(irq, desc);
+ write_msi_msg(irq, &msg);
+
+#ifdef CONFIG_INTR_REMAP
+ if (irq_remapped(irq)) {
+ struct irq_desc *desc = irq_to_desc(irq);
+ /*
+ * irq migration in process context
+ */
+ desc->status |= IRQ_MOVE_PCNTXT;
+ set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
+ } else
+#endif
+ set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+
+ return 0;
+}
+
+static unsigned int build_irq_for_pci_dev(struct pci_dev *dev)
+{
+ unsigned int irq;
+
+ irq = dev->bus->number;
+ irq <<= 8;
+ irq |= dev->devfn;
+ irq <<= 12;
+
+ return irq;
+}
+
+int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+{
+ unsigned int irq;
+ int ret;
+ unsigned int irq_want;
+
+ irq_want = build_irq_for_pci_dev(dev) + 0x100;
+
+ irq = create_irq_nr(irq_want);
+ if (irq == 0)
+ return -1;
+
+#ifdef CONFIG_INTR_REMAP
+ if (!intr_remapping_enabled)
+ goto no_ir;
+
+ ret = msi_alloc_irte(dev, irq, 1);
+ if (ret < 0)
+ goto error;
+no_ir:
+#endif
+ ret = setup_msi_irq(dev, desc, irq);
if (ret < 0) {
destroy_irq(irq);
return ret;
}
+ return 0;
- set_irq_msi(irq, desc);
- write_msi_msg(irq, &msg);
+#ifdef CONFIG_INTR_REMAP
+error:
+ destroy_irq(irq);
+ return ret;
+#endif
+}
- set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ unsigned int irq;
+ int ret, sub_handle;
+ struct msi_desc *desc;
+ unsigned int irq_want;
+
+#ifdef CONFIG_INTR_REMAP
+ struct intel_iommu *iommu = 0;
+ int index = 0;
+#endif
+ irq_want = build_irq_for_pci_dev(dev) + 0x100;
+ sub_handle = 0;
+ list_for_each_entry(desc, &dev->msi_list, list) {
+ irq = create_irq_nr(irq_want--);
+ if (irq == 0)
+ return -1;
+#ifdef CONFIG_INTR_REMAP
+ if (!intr_remapping_enabled)
+ goto no_ir;
+
+ if (!sub_handle) {
+ /*
+ * allocate the consecutive block of IRTE's
+ * for 'nvec'
+ */
+ index = msi_alloc_irte(dev, irq, nvec);
+ if (index < 0) {
+ ret = index;
+ goto error;
+ }
+ } else {
+ iommu = map_dev_to_ir(dev);
+ if (!iommu) {
+ ret = -ENOENT;
+ 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:
+#endif
+ ret = setup_msi_irq(dev, desc, irq);
+ if (ret < 0)
+ goto error;
+ sub_handle++;
+ }
return 0;
+
+error:
+ destroy_irq(irq);
+ return ret;
}
void arch_teardown_msi_irq(unsigned int irq)
#ifdef CONFIG_SMP
static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
{
- struct irq_cfg *cfg = irq_cfg + irq;
+ struct irq_cfg *cfg;
struct msi_msg msg;
unsigned int dest;
cpumask_t tmp;
+ struct irq_desc *desc;
cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
if (assign_irq_vector(irq, mask))
return;
+ cfg = irq_cfg(irq);
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);
msg.address_lo |= MSI_ADDR_DEST_ID(dest);
dmar_msi_write(irq, &msg);
- irq_desc[irq].affinity = mask;
+ desc = irq_to_desc(irq);
+ desc->affinity = mask;
}
#endif /* CONFIG_SMP */
static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
{
- struct irq_cfg *cfg = irq_cfg + irq;
+ struct irq_cfg *cfg;
unsigned int dest;
cpumask_t tmp;
+ struct irq_desc *desc;
cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
if (assign_irq_vector(irq, mask))
return;
+ cfg = irq_cfg(irq);
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);
target_ht_irq(irq, dest, cfg->vector);
- irq_desc[irq].affinity = mask;
+ desc = irq_to_desc(irq);
+ desc->affinity = mask;
}
#endif
int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
{
- struct irq_cfg *cfg = irq_cfg + irq;
+ struct irq_cfg *cfg;
int err;
cpumask_t tmp;
struct ht_irq_msg msg;
unsigned dest;
+ cfg = irq_cfg(irq);
cpus_and(tmp, cfg->domain, tmp);
dest = cpu_mask_to_apicid(tmp);
void __init setup_ioapic_dest(void)
{
int pin, ioapic, irq, irq_entry;
+ struct irq_cfg *cfg;
if (skip_ioapic_setup == 1)
return;
* when you have too many devices, because at that time only boot
* cpu is online.
*/
- if (!irq_cfg[irq].vector)
+ cfg = irq_cfg(irq);
+ if (!cfg->vector)
setup_IO_APIC_irq(ioapic, pin, irq,
irq_trigger(irq_entry),
irq_polarity(irq_entry));
+#ifdef CONFIG_INTR_REMAP
+ else if (intr_remapping_enabled)
+ set_ir_ioapic_affinity_irq(irq, TARGET_CPUS);
+#endif
else
set_ioapic_affinity_irq(irq, TARGET_CPUS);
}