diff options
Diffstat (limited to 'arch/x86/kernel/apic/io_apic.c')
| -rw-r--r-- | arch/x86/kernel/apic/io_apic.c | 1280 |
1 files changed, 518 insertions, 762 deletions
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index fb072754bc1..81e08eff05e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -37,9 +37,6 @@ #include <linux/kthread.h> #include <linux/jiffies.h> /* time_after() */ #include <linux/slab.h> -#ifdef CONFIG_ACPI -#include <acpi/acpi_bus.h> -#endif #include <linux/bootmem.h> #include <linux/dmar.h> #include <linux/hpet.h> @@ -64,6 +61,7 @@ #include <asm/apic.h> #define __apicdebuginit(type) static type __init + #define for_each_irq_pin(entry, head) \ for (entry = head; entry; entry = entry->next) @@ -123,7 +121,7 @@ int mp_irq_entries; /* GSI interrupts */ static int nr_irqs_gsi = NR_IRQS_LEGACY; -#if defined (CONFIG_MCA) || defined (CONFIG_EISA) +#ifdef CONFIG_EISA int mp_bus_id_to_type[MAX_MP_BUSSES]; #endif @@ -208,20 +206,17 @@ int __init arch_early_irq_init(void) count = ARRAY_SIZE(irq_cfgx); node = cpu_to_node(0); - /* Make sure the legacy interrupts are marked in the bitmap */ - irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs); - for (i = 0; i < count; i++) { irq_set_chip_data(i, &cfg[i]); zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node); zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node); /* * For legacy IRQ's, start with assigning irq0 to irq15 to - * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0. + * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's. */ if (i < legacy_pic->nr_legacy_irqs) { cfg[i].vector = IRQ0_VECTOR + i; - cpumask_set_cpu(0, cfg[i].domain); + cpumask_setall(cfg[i].domain); } } @@ -283,17 +278,6 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) return cfg; } -static int alloc_irq_from(unsigned int from, int node) -{ - return irq_alloc_desc_from(from, node); -} - -static void free_irq_at(unsigned int at, struct irq_cfg *cfg) -{ - free_irq_cfg(at, cfg); - irq_free_desc(at); -} - struct io_apic { unsigned int index; unsigned int unused[3]; @@ -308,22 +292,23 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) + (mpc_ioapic_addr(idx) & ~PAGE_MASK); } -static inline void io_apic_eoi(unsigned int apic, unsigned int vector) +void io_apic_eoi(unsigned int apic, unsigned int vector) { struct io_apic __iomem *io_apic = io_apic_base(apic); writel(vector, &io_apic->eoi); } -static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) +unsigned int native_io_apic_read(unsigned int apic, unsigned int reg) { struct io_apic __iomem *io_apic = io_apic_base(apic); writel(reg, &io_apic->index); return readl(&io_apic->data); } -static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) +void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) { struct io_apic __iomem *io_apic = io_apic_base(apic); + writel(reg, &io_apic->index); writel(value, &io_apic->data); } @@ -334,7 +319,7 @@ static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned i * * Older SiS APIC requires we rewrite the index register */ -static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) +void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) { struct io_apic __iomem *io_apic = io_apic_base(apic); @@ -343,29 +328,6 @@ static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned writel(value, &io_apic->data); } -static bool io_apic_level_ack_pending(struct irq_cfg *cfg) -{ - struct irq_pin_list *entry; - unsigned long flags; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, cfg->irq_2_pin) { - unsigned int reg; - int pin; - - 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) { - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return true; - } - } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - - return false; -} - union entry_union { struct { u32 w1, w2; }; struct IO_APIC_route_entry entry; @@ -377,6 +339,7 @@ static struct IO_APIC_route_entry __ioapic_read_entry(int apic, int pin) eu.w1 = io_apic_read(apic, 0x10 + 2 * pin); eu.w2 = io_apic_read(apic, 0x11 + 2 * pin); + return eu.entry; } @@ -384,9 +347,11 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) { union entry_union eu; unsigned long flags; + raw_spin_lock_irqsave(&ioapic_lock, flags); eu.entry = __ioapic_read_entry(apic, pin); raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return eu.entry; } @@ -396,8 +361,7 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) * the interrupt, and we need to make sure the entry is fully populated * before that happens. */ -static void -__ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) +static void __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) { union entry_union eu = {{0, 0}}; @@ -409,6 +373,7 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) { unsigned long flags; + raw_spin_lock_irqsave(&ioapic_lock, flags); __ioapic_write_entry(apic, pin, e); raw_spin_unlock_irqrestore(&ioapic_lock, flags); @@ -435,8 +400,7 @@ static void ioapic_mask_entry(int apic, int pin) * shared ISA-space IRQs, so we have to support them. We are super * fast in the common case, and fast for shared ISA-space IRQs. */ -static int -__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) +static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) { struct irq_pin_list **last, *entry; @@ -450,8 +414,8 @@ __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) entry = alloc_irq_pin_list(node); if (!entry) { - printk(KERN_ERR "can not alloc irq_pin_list (%d,%d,%d)\n", - node, apic, pin); + pr_err("can not alloc irq_pin_list (%d,%d,%d)\n", + node, apic, pin); return -ENOMEM; } entry->apic = apic; @@ -521,6 +485,7 @@ static void io_apic_sync(struct irq_pin_list *entry) * a dummy read from the IO-APIC */ struct io_apic __iomem *io_apic; + io_apic = io_apic_base(entry->apic); readl(&io_apic->data); } @@ -574,19 +539,10 @@ static void unmask_ioapic_irq(struct irq_data *data) * Otherwise, we simulate the EOI message manually by changing the trigger * mode to edge and then back to level, with RTE being masked during this. */ -static void __eoi_ioapic_pin(int apic, int pin, int vector, struct irq_cfg *cfg) +void native_eoi_ioapic_pin(int apic, int pin, int vector) { if (mpc_ioapic_ver(apic) >= 0x20) { - /* - * Intr-remapping uses pin number as the virtual vector - * in the RTE. Actual vector is programmed in - * intr-remapping table entry. Hence for the io-apic - * EOI we use the pin number. - */ - if (cfg && irq_remapped(cfg)) - io_apic_eoi(apic, pin); - else - io_apic_eoi(apic, vector); + io_apic_eoi(apic, vector); } else { struct IO_APIC_route_entry entry, entry1; @@ -607,14 +563,15 @@ static void __eoi_ioapic_pin(int apic, int pin, int vector, struct irq_cfg *cfg) } } -static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) { struct irq_pin_list *entry; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); for_each_irq_pin(entry, cfg->irq_2_pin) - __eoi_ioapic_pin(entry->apic, entry->pin, cfg->vector, cfg); + x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin, + cfg->vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -651,7 +608,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) } raw_spin_lock_irqsave(&ioapic_lock, flags); - __eoi_ioapic_pin(apic, pin, entry.vector, NULL); + x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -662,7 +619,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) ioapic_mask_entry(apic, pin); entry = ioapic_read_entry(apic, pin); if (entry.irr) - printk(KERN_ERR "Unable to reset IRR for apic: %d, pin :%d\n", + pr_err("Unable to reset IRR for apic: %d, pin :%d\n", mpc_ioapic_id(apic), pin); } @@ -836,7 +793,7 @@ static int __init find_isa_irq_apic(int irq, int type) return -1; } -#if defined(CONFIG_EISA) || defined(CONFIG_MCA) +#ifdef CONFIG_EISA /* * EISA Edge/Level control register, ELCR */ @@ -873,12 +830,6 @@ static int EISA_ELCR(unsigned int irq) #define default_PCI_trigger(idx) (1) #define default_PCI_polarity(idx) (1) -/* MCA interrupts are always polarity zero level triggered, - * when listed as conforming in the MP table. */ - -#define default_MCA_trigger(idx) (1) -#define default_MCA_polarity(idx) default_ISA_polarity(idx) - static int irq_polarity(int idx) { int bus = mp_irqs[idx].srcbus; @@ -902,7 +853,7 @@ static int irq_polarity(int idx) } case 2: /* reserved */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); polarity = 1; break; } @@ -913,7 +864,7 @@ static int irq_polarity(int idx) } default: /* invalid */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); polarity = 1; break; } @@ -936,7 +887,7 @@ static int irq_trigger(int idx) trigger = default_ISA_trigger(idx); else trigger = default_PCI_trigger(idx); -#if defined(CONFIG_EISA) || defined(CONFIG_MCA) +#ifdef CONFIG_EISA switch (mp_bus_id_to_type[bus]) { case MP_BUS_ISA: /* ISA pin */ { @@ -953,14 +904,9 @@ static int irq_trigger(int idx) /* set before the switch */ break; } - case MP_BUS_MCA: /* MCA pin */ - { - trigger = default_MCA_trigger(idx); - break; - } default: { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); trigger = 1; break; } @@ -974,7 +920,7 @@ static int irq_trigger(int idx) } case 2: /* reserved */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); trigger = 1; break; } @@ -985,7 +931,7 @@ static int irq_trigger(int idx) } default: /* invalid */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); trigger = 0; break; } @@ -1003,7 +949,7 @@ static int pin_2_irq(int idx, int apic, int pin) * Debugging check, we are in big trouble if this message pops up! */ if (mp_irqs[idx].dstirq != pin) - printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); + pr_err("broken BIOS or MPTABLE parser, ayiee!!\n"); if (test_bit(bus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; @@ -1124,8 +1070,7 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) * 0x80, because int 0x80 is hm, kind of importantish. ;) */ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; - static int current_offset = VECTOR_OFFSET_START % 8; - unsigned int old_vector; + static int current_offset = VECTOR_OFFSET_START % 16; int cpu, err; cpumask_var_t tmp_mask; @@ -1135,48 +1080,61 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC)) return -ENOMEM; - old_vector = cfg->vector; - if (old_vector) { - cpumask_and(tmp_mask, mask, cpu_online_mask); - cpumask_and(tmp_mask, cfg->domain, tmp_mask); - if (!cpumask_empty(tmp_mask)) { - free_cpumask_var(tmp_mask); - return 0; - } - } - /* Only try and allocate irqs on cpus that are present */ err = -ENOSPC; - for_each_cpu_and(cpu, mask, cpu_online_mask) { - int new_cpu; - int vector, offset; + cpumask_clear(cfg->old_domain); + cpu = cpumask_first_and(mask, cpu_online_mask); + while (cpu < nr_cpu_ids) { + int new_cpu, vector, offset; - apic->vector_allocation_domain(cpu, tmp_mask); + apic->vector_allocation_domain(cpu, tmp_mask, mask); + + if (cpumask_subset(tmp_mask, cfg->domain)) { + err = 0; + if (cpumask_equal(tmp_mask, cfg->domain)) + break; + /* + * New cpumask using the vector is a proper subset of + * the current in use mask. So cleanup the vector + * allocation for the members that are not used anymore. + */ + cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); + cpumask_and(cfg->domain, cfg->domain, tmp_mask); + break; + } vector = current_vector; offset = current_offset; next: - vector += 8; + vector += 16; if (vector >= first_system_vector) { - /* If out of vectors on large boxen, must share them. */ - offset = (offset + 1) % 8; + offset = (offset + 1) % 16; vector = FIRST_EXTERNAL_VECTOR + offset; } - if (unlikely(current_vector == vector)) + + if (unlikely(current_vector == vector)) { + cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask); + cpumask_andnot(tmp_mask, mask, cfg->old_domain); + cpu = cpumask_first_and(tmp_mask, cpu_online_mask); continue; + } if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) - if (per_cpu(vector_irq, new_cpu)[vector] != -1) + for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) { + if (per_cpu(vector_irq, new_cpu)[vector] > VECTOR_UNDEFINED) goto next; + } /* Found one! */ current_vector = vector; current_offset = offset; - if (old_vector) { - cfg->move_in_progress = 1; + if (cfg->vector) { cpumask_copy(cfg->old_domain, cfg->domain); + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); } for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) per_cpu(vector_irq, new_cpu)[vector] = irq; @@ -1208,7 +1166,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) vector = cfg->vector; for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) - per_cpu(vector_irq, cpu)[vector] = -1; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; cfg->vector = 0; cpumask_clear(cfg->domain); @@ -1216,11 +1174,10 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) if (likely(!cfg->move_in_progress)) return; for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; - vector++) { + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { if (per_cpu(vector_irq, cpu)[vector] != irq) continue; - per_cpu(vector_irq, cpu)[vector] = -1; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; break; } } @@ -1244,12 +1201,6 @@ void __setup_vector_irq(int cpu) cfg = irq_get_chip_data(irq); if (!cfg) continue; - /* - * If it is a legacy IRQ handled by the legacy PIC, this cpu - * will be part of the irq_cfg's domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq)) - cpumask_set_cpu(cpu, cfg->domain); if (!cpumask_test_cpu(cpu, cfg->domain)) continue; @@ -1259,12 +1210,12 @@ void __setup_vector_irq(int cpu) /* Mark the free vectors */ for (vector = 0; vector < NR_VECTORS; ++vector) { irq = per_cpu(vector_irq, cpu)[vector]; - if (irq < 0) + if (irq <= VECTOR_UNDEFINED) continue; cfg = irq_cfg(irq); if (!cpumask_test_cpu(cpu, cfg->domain)) - per_cpu(vector_irq, cpu)[vector] = -1; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; } raw_spin_unlock(&vector_lock); } @@ -1311,89 +1262,18 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, fasteoi = false; } - if (irq_remapped(cfg)) { - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - irq_remap_modify_chip_defaults(chip); + if (setup_remapped_irq(irq, cfg, chip)) fasteoi = trigger != 0; - } hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; irq_set_chip_and_handler_name(irq, chip, hdl, fasteoi ? "fasteoi" : "edge"); } - -static int setup_ir_ioapic_entry(int irq, - struct IR_IO_APIC_route_entry *entry, +int native_setup_ioapic_entry(int irq, struct 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); - memset(entry, 0, sizeof(*entry)); entry->delivery_mode = apic->irq_delivery_mode; @@ -1422,18 +1302,18 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (!IO_APIC_IRQ(irq)) return; - /* - * For legacy irqs, cfg->domain starts with cpu 0 for legacy - * controllers like 8259. Now that IO-APIC can handle this irq, update - * the cfg->domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && cpumask_test_cpu(0, cfg->domain)) - apic->vector_allocation_domain(0, cfg->domain); if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); + if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(), + &dest)) { + pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n", + mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); + __clear_irq_vector(irq, cfg); + + return; + } apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " @@ -1441,7 +1321,7 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin, cfg->vector, irq, attr->trigger, attr->polarity, dest); - if (setup_ioapic_entry(irq, &entry, dest, cfg->vector, attr)) { + if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) { pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); __clear_irq_vector(irq, cfg); @@ -1545,12 +1425,10 @@ void setup_IO_APIC_irq_extra(u32 gsi) * Set up the timer pin, possibly with the 8259A-master behind. */ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, - unsigned int pin, int vector) + unsigned int pin, int vector) { struct IO_APIC_route_entry entry; - - if (intr_remapping_enabled) - return; + unsigned int dest; memset(&entry, 0, sizeof(entry)); @@ -1558,9 +1436,13 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, * We use logical delivery to get the timer IRQ * to the first CPU. */ + if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(), + apic->target_cpus(), &dest))) + dest = BAD_APICID; + entry.dest_mode = apic->irq_dest_mode; entry.mask = 0; /* don't mask IRQ for edge */ - entry.dest = apic->cpu_mask_to_apicid(apic->target_cpus()); + entry.dest = dest; entry.delivery_mode = apic->irq_delivery_mode; entry.polarity = 0; entry.trigger = 0; @@ -1579,9 +1461,68 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, ioapic_write_entry(ioapic_idx, pin, entry); } -__apicdebuginit(void) print_IO_APIC(int ioapic_idx) +void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries) +{ + int i; + + pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n"); + + for (i = 0; i <= nr_entries; i++) { + struct IO_APIC_route_entry entry; + + entry = ioapic_read_entry(apic, i); + + pr_debug(" %02x %02X ", i, entry.dest); + pr_cont("%1d %1d %1d %1d %1d " + "%1d %1d %02X\n", + entry.mask, + entry.trigger, + entry.irr, + entry.polarity, + entry.delivery_status, + entry.dest_mode, + entry.delivery_mode, + entry.vector); + } +} + +void intel_ir_io_apic_print_entries(unsigned int apic, + unsigned int nr_entries) { int i; + + pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n"); + + for (i = 0; i <= nr_entries; i++) { + struct IR_IO_APIC_route_entry *ir_entry; + struct IO_APIC_route_entry entry; + + entry = ioapic_read_entry(apic, i); + + ir_entry = (struct IR_IO_APIC_route_entry *)&entry; + + pr_debug(" %02x %04X ", i, ir_entry->index); + pr_cont("%1d %1d %1d %1d %1d " + "%1d %1d %X %02X\n", + ir_entry->format, + ir_entry->mask, + ir_entry->trigger, + ir_entry->irr, + ir_entry->polarity, + ir_entry->delivery_status, + ir_entry->index2, + ir_entry->zero, + ir_entry->vector); + } +} + +void ioapic_zap_locks(void) +{ + raw_spin_lock_init(&ioapic_lock); +} + +__apicdebuginit(void) print_IO_APIC(int ioapic_idx) +{ union IO_APIC_reg_00 reg_00; union IO_APIC_reg_01 reg_01; union IO_APIC_reg_02 reg_02; @@ -1597,7 +1538,6 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) reg_03.raw = io_apic_read(ioapic_idx, 3); raw_spin_unlock_irqrestore(&ioapic_lock, flags); - printk("\n"); printk(KERN_DEBUG "IO APIC #%d......\n", mpc_ioapic_id(ioapic_idx)); printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); @@ -1635,58 +1575,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) printk(KERN_DEBUG ".... IRQ redirection table:\n"); - if (intr_remapping_enabled) { - printk(KERN_DEBUG " NR Indx Fmt Mask Trig IRR" - " Pol Stat Indx2 Zero Vect:\n"); - } else { - printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol" - " Stat Dmod Deli Vect:\n"); - } - - for (i = 0; i <= reg_01.bits.entries; i++) { - if (intr_remapping_enabled) { - struct IO_APIC_route_entry entry; - struct IR_IO_APIC_route_entry *ir_entry; - - entry = ioapic_read_entry(ioapic_idx, i); - ir_entry = (struct IR_IO_APIC_route_entry *) &entry; - printk(KERN_DEBUG " %02x %04X ", - i, - ir_entry->index - ); - printk("%1d %1d %1d %1d %1d " - "%1d %1d %X %02X\n", - ir_entry->format, - ir_entry->mask, - ir_entry->trigger, - ir_entry->irr, - ir_entry->polarity, - ir_entry->delivery_status, - ir_entry->index2, - ir_entry->zero, - ir_entry->vector - ); - } else { - struct IO_APIC_route_entry entry; - - entry = ioapic_read_entry(ioapic_idx, i); - printk(KERN_DEBUG " %02x %02X ", - i, - entry.dest - ); - printk("%1d %1d %1d %1d %1d " - "%1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector - ); - } - } + x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries); } __apicdebuginit(void) print_IO_APICs(void) @@ -1727,8 +1616,8 @@ __apicdebuginit(void) print_IO_APICs(void) continue; printk(KERN_DEBUG "IRQ%d ", irq); for_each_irq_pin(entry, cfg->irq_2_pin) - printk("-> %d:%d", entry->apic, entry->pin); - printk("\n"); + pr_cont("-> %d:%d", entry->apic, entry->pin); + pr_cont("\n"); } printk(KERN_INFO ".................................... done.\n"); @@ -1741,9 +1630,9 @@ __apicdebuginit(void) print_APIC_field(int base) printk(KERN_DEBUG); for (i = 0; i < 8; i++) - printk(KERN_CONT "%08x", apic_read(base + i*0x10)); + pr_cont("%08x", apic_read(base + i*0x10)); - printk(KERN_CONT "\n"); + pr_cont("\n"); } __apicdebuginit(void) print_local_APIC(void *dummy) @@ -1845,7 +1734,7 @@ __apicdebuginit(void) print_local_APIC(void *dummy) printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v); } } - printk("\n"); + pr_cont("\n"); } __apicdebuginit(void) print_local_APICs(int maxcpu) @@ -1988,30 +1877,14 @@ void __init enable_IO_APIC(void) clear_IO_APIC(); } -/* - * Not an __init, needed by the reboot code - */ -void disable_IO_APIC(void) +void native_disable_io_apic(void) { /* - * Clear the IO-APIC before rebooting: - */ - clear_IO_APIC(); - - if (!legacy_pic->nr_legacy_irqs) - return; - - /* * If the i8259 is routed through an IOAPIC * Put that IOAPIC in virtual wire mode * so legacy interrupts can be delivered. - * - * With interrupt-remapping, for now we will use virtual wire A mode, - * as virtual wire B is little complex (need to configure both - * 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) { struct IO_APIC_route_entry entry; memset(&entry, 0, sizeof(entry)); @@ -2031,12 +1904,25 @@ void disable_IO_APIC(void) ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } + if (cpu_has_apic || apic_from_smp_config()) + disconnect_bsp_APIC(ioapic_i8259.pin != -1); + +} + +/* + * Not an __init, needed by the reboot code + */ +void disable_IO_APIC(void) +{ /* - * Use virtual wire A mode when interrupt remapping is enabled. + * Clear the IO-APIC before rebooting: */ - if (cpu_has_apic || apic_from_smp_config()) - disconnect_bsp_APIC(!intr_remapping_enabled && - ioapic_i8259.pin != -1); + clear_IO_APIC(); + + if (!legacy_pic->nr_legacy_irqs) + return; + + x86_io_apic_ops.disable(); } #ifdef CONFIG_X86_32 @@ -2141,7 +2027,7 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) reg_00.raw = io_apic_read(ioapic_idx, 0); raw_spin_unlock_irqrestore(&ioapic_lock, flags); if (reg_00.bits.ID != mpc_ioapic_id(ioapic_idx)) - printk("could not set ID!\n"); + pr_cont("could not set ID!\n"); else apic_printk(APIC_VERBOSE, " ok.\n"); } @@ -2252,9 +2138,11 @@ static int ioapic_retrigger_irq(struct irq_data *data) { struct irq_cfg *cfg = data->chip_data; unsigned long flags; + int cpu; raw_spin_lock_irqsave(&vector_lock, flags); - apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector); + cpu = cpumask_first_and(cfg->domain, cpu_online_mask); + apic->send_IPI_mask(cpumask_of(cpu), cfg->vector); raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; @@ -2286,137 +2174,7 @@ void send_cleanup_vector(struct irq_cfg *cfg) cfg->move_in_progress = 0; } -static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) -{ - int apic, pin; - struct irq_pin_list *entry; - u8 vector = cfg->vector; - - for_each_irq_pin(entry, cfg->irq_2_pin) { - unsigned int reg; - - apic = entry->apic; - pin = entry->pin; - /* - * With interrupt-remapping, destination information comes - * from interrupt-remapping table entry. - */ - if (!irq_remapped(cfg)) - io_apic_write(apic, 0x11 + pin*2, dest); - reg = io_apic_read(apic, 0x10 + pin*2); - reg &= ~IO_APIC_REDIR_VECTOR_MASK; - reg |= vector; - io_apic_modify(apic, 0x10 + pin*2, reg); - } -} - -/* - * Either sets data->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and - * leaves data->affinity untouched. - */ -int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id) -{ - struct irq_cfg *cfg = data->chip_data; - - if (!cpumask_intersects(mask, cpu_online_mask)) - return -1; - - if (assign_irq_vector(data->irq, data->chip_data, mask)) - return -1; - - cpumask_copy(data->affinity, mask); - - *dest_id = apic->cpu_mask_to_apicid_and(mask, cfg->domain); - return 0; -} - -static int -ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) -{ - unsigned int dest, irq = data->irq; - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - ret = __ioapic_set_affinity(data, mask, &dest); - if (!ret) { - /* Only the high 8 bits are valid. */ - dest = SET_APIC_LOGICAL_ID(dest); - __target_IO_APIC_irq(irq, dest, data->chip_data); - } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - 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) +asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) { unsigned vector, me; @@ -2426,13 +2184,13 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - unsigned int irq; + int irq; unsigned int irr; struct irq_desc *desc; struct irq_cfg *cfg; irq = __this_cpu_read(vector_irq[vector]); - if (irq == -1) + if (irq <= VECTOR_UNDEFINED) continue; desc = irq_to_desc(irq); @@ -2440,6 +2198,9 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) continue; cfg = irq_cfg(irq); + if (!cfg) + continue; + raw_spin_lock(&desc->lock); /* @@ -2503,6 +2264,84 @@ void irq_force_complete_move(int irq) static inline void irq_complete_move(struct irq_cfg *cfg) { } #endif +static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) +{ + int apic, pin; + struct irq_pin_list *entry; + u8 vector = cfg->vector; + + for_each_irq_pin(entry, cfg->irq_2_pin) { + unsigned int reg; + + apic = entry->apic; + pin = entry->pin; + + io_apic_write(apic, 0x11 + pin*2, dest); + reg = io_apic_read(apic, 0x10 + pin*2); + reg &= ~IO_APIC_REDIR_VECTOR_MASK; + reg |= vector; + io_apic_modify(apic, 0x10 + pin*2, reg); + } +} + +/* + * Either sets data->affinity to a valid value, and returns + * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and + * leaves data->affinity untouched. + */ +int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, + unsigned int *dest_id) +{ + struct irq_cfg *cfg = data->chip_data; + unsigned int irq = data->irq; + int err; + + if (!config_enabled(CONFIG_SMP)) + return -EPERM; + + if (!cpumask_intersects(mask, cpu_online_mask)) + return -EINVAL; + + err = assign_irq_vector(irq, cfg, mask); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); + if (err) { + if (assign_irq_vector(irq, cfg, data->affinity)) + pr_err("Failed to recover vector for irq %d\n", irq); + return err; + } + + cpumask_copy(data->affinity, mask); + + return 0; +} + + +int native_ioapic_set_affinity(struct irq_data *data, + const struct cpumask *mask, + bool force) +{ + unsigned int dest, irq = data->irq; + unsigned long flags; + int ret; + + if (!config_enabled(CONFIG_SMP)) + return -EPERM; + + raw_spin_lock_irqsave(&ioapic_lock, flags); + ret = __ioapic_set_affinity(data, mask, &dest); + if (!ret) { + /* Only the high 8 bits are valid. */ + dest = SET_APIC_LOGICAL_ID(dest); + __target_IO_APIC_irq(irq, dest, data->chip_data); + ret = IRQ_SET_MASK_OK_NOCOPY; + } + raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return ret; +} + static void ack_apic_edge(struct irq_data *data) { irq_complete_move(data->chip_data); @@ -2512,21 +2351,96 @@ static void ack_apic_edge(struct irq_data *data) atomic_t irq_mis_count; -static void ack_apic_level(struct irq_data *data) +#ifdef CONFIG_GENERIC_PENDING_IRQ +static bool io_apic_level_ack_pending(struct irq_cfg *cfg) { - struct irq_cfg *cfg = data->chip_data; - int i, do_unmask_irq = 0, irq = data->irq; - unsigned long v; + struct irq_pin_list *entry; + unsigned long flags; - irq_complete_move(cfg); -#ifdef CONFIG_GENERIC_PENDING_IRQ + raw_spin_lock_irqsave(&ioapic_lock, flags); + for_each_irq_pin(entry, cfg->irq_2_pin) { + unsigned int reg; + int pin; + + 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) { + raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return true; + } + } + raw_spin_unlock_irqrestore(&ioapic_lock, flags); + + return false; +} + +static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +{ /* If we are moving the irq we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data))) { - do_unmask_irq = 1; mask_ioapic(cfg); + return true; } + return false; +} + +static inline void ioapic_irqd_unmask(struct irq_data *data, + struct irq_cfg *cfg, bool masked) +{ + if (unlikely(masked)) { + /* Only migrate the irq if the ack has been received. + * + * On rare occasions the broadcast level triggered ack gets + * delayed going to ioapics, and if we reprogram the + * vector while Remote IRR is still set the irq will never + * fire again. + * + * To prevent this scenario we read the Remote IRR bit + * of the ioapic. This has two effects. + * - On any sane system the read of the ioapic will + * flush writes (and acks) going to the ioapic from + * this cpu. + * - We get to see if the ACK has actually been delivered. + * + * Based on failed experiments of reprogramming the + * ioapic entry from outside of irq context starting + * with masking the ioapic entry and then polling until + * Remote IRR was clear before reprogramming the + * ioapic I don't trust the Remote IRR bit to be + * completey accurate. + * + * However there appears to be no other way to plug + * this race, so if the Remote IRR bit is not + * accurate and is causing problems then it is a hardware bug + * and you can go talk to the chipset vendor about it. + */ + if (!io_apic_level_ack_pending(cfg)) + irq_move_masked_irq(data); + unmask_ioapic(cfg); + } +} +#else +static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +{ + return false; +} +static inline void ioapic_irqd_unmask(struct irq_data *data, + struct irq_cfg *cfg, bool masked) +{ +} #endif +static void ack_apic_level(struct irq_data *data) +{ + struct irq_cfg *cfg = data->chip_data; + int i, irq = data->irq; + unsigned long v; + bool masked; + + irq_complete_move(cfg); + masked = ioapic_irqd_mask(data, cfg); + /* * It appears there is an erratum which affects at least version 0x11 * of I/O APIC (that's the 82093AA and cores integrated into various @@ -2581,69 +2495,9 @@ static void ack_apic_level(struct irq_data *data) eoi_ioapic_irq(irq, cfg); } - /* Now we can move and renable the irq */ - if (unlikely(do_unmask_irq)) { - /* Only migrate the irq if the ack has been received. - * - * On rare occasions the broadcast level triggered ack gets - * delayed going to ioapics, and if we reprogram the - * vector while Remote IRR is still set the irq will never - * fire again. - * - * To prevent this scenario we read the Remote IRR bit - * of the ioapic. This has two effects. - * - On any sane system the read of the ioapic will - * flush writes (and acks) going to the ioapic from - * this cpu. - * - We get to see if the ACK has actually been delivered. - * - * Based on failed experiments of reprogramming the - * ioapic entry from outside of irq context starting - * with masking the ioapic entry and then polling until - * Remote IRR was clear before reprogramming the - * ioapic I don't trust the Remote IRR bit to be - * completey accurate. - * - * However there appears to be no other way to plug - * this race, so if the Remote IRR bit is not - * accurate and is causing problems then it is a hardware bug - * and you can go talk to the chipset vendor about it. - */ - if (!io_apic_level_ack_pending(cfg)) - irq_move_masked_irq(data); - unmask_ioapic(cfg); - } -} - -#ifdef CONFIG_IRQ_REMAP -static void ir_ack_apic_edge(struct irq_data *data) -{ - ack_APIC_irq(); -} - -static void ir_ack_apic_level(struct irq_data *data) -{ - ack_APIC_irq(); - eoi_ioapic_irq(data->irq, data->chip_data); + ioapic_irqd_unmask(data, cfg, masked); } -static void ir_print_prefix(struct irq_data *data, struct seq_file *p) -{ - seq_printf(p, " IR-%s", data->chip->name); -} - -static void irq_remap_modify_chip_defaults(struct irq_chip *chip) -{ - chip->irq_print_chip = ir_print_prefix; - chip->irq_ack = ir_ack_apic_edge; - chip->irq_eoi = ir_ack_apic_level; - -#ifdef CONFIG_SMP - chip->irq_set_affinity = ir_ioapic_set_affinity; -#endif -} -#endif /* CONFIG_IRQ_REMAP */ - static struct irq_chip ioapic_chip __read_mostly = { .name = "IO-APIC", .irq_startup = startup_ioapic_irq, @@ -2651,9 +2505,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_unmask = unmask_ioapic_irq, .irq_ack = ack_apic_edge, .irq_eoi = ack_apic_level, -#ifdef CONFIG_SMP - .irq_set_affinity = ioapic_set_affinity, -#endif + .irq_set_affinity = native_ioapic_set_affinity, .irq_retrigger = ioapic_retrigger_irq, }; @@ -2852,8 +2704,7 @@ static inline void __init check_timer(void) * 8259A. */ if (pin1 == -1) { - if (intr_remapping_enabled) - panic("BIOS bug: timer not connected to IO-APIC"); + panic_if_irq_remap("BIOS bug: timer not connected to IO-APIC"); pin1 = pin2; apic1 = apic2; no_pin1 = 1; @@ -2885,8 +2736,7 @@ static inline void __init check_timer(void) clear_IO_APIC_pin(0, pin1); goto out; } - if (intr_remapping_enabled) - panic("timer doesn't work through Interrupt-remapped IO-APIC"); + panic_if_irq_remap("timer doesn't work through Interrupt-remapped IO-APIC"); local_irq_disable(); clear_IO_APIC_pin(apic1, pin1); if (!no_pin1) @@ -3051,74 +2901,74 @@ static int __init ioapic_init_ops(void) device_initcall(ioapic_init_ops); /* - * Dynamic irq allocate and deallocation + * Dynamic irq allocate and deallocation. Should be replaced by irq domains! */ -unsigned int create_irq_nr(unsigned int from, int node) +int arch_setup_hwirq(unsigned int irq, int node) { struct irq_cfg *cfg; unsigned long flags; - unsigned int ret = 0; - int irq; - - if (from < nr_irqs_gsi) - from = nr_irqs_gsi; + int ret; - irq = alloc_irq_from(from, node); - if (irq < 0) - return 0; cfg = alloc_irq_cfg(irq, node); - if (!cfg) { - free_irq_at(irq, NULL); - return 0; - } + if (!cfg) + return -ENOMEM; raw_spin_lock_irqsave(&vector_lock, flags); - if (!__assign_irq_vector(irq, cfg, apic->target_cpus())) - ret = irq; + ret = __assign_irq_vector(irq, cfg, apic->target_cpus()); raw_spin_unlock_irqrestore(&vector_lock, flags); - if (ret) { + if (!ret) irq_set_chip_data(irq, cfg); - irq_clear_status_flags(irq, IRQ_NOREQUEST); - } else { - free_irq_at(irq, cfg); - } + else + free_irq_cfg(irq, cfg); return ret; } -int create_irq(void) -{ - int node = cpu_to_node(0); - unsigned int irq_want; - int irq; - - irq_want = nr_irqs_gsi; - irq = create_irq_nr(irq_want, node); - - if (irq == 0) - irq = -1; - - return irq; -} - -void destroy_irq(unsigned int irq) +void arch_teardown_hwirq(unsigned int irq) { struct irq_cfg *cfg = irq_get_chip_data(irq); unsigned long flags; - 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); - free_irq_at(irq, cfg); + free_irq_cfg(irq, cfg); } /* * MSI message composition */ +void native_compose_msi_msg(struct pci_dev *pdev, + unsigned int irq, unsigned int dest, + struct msi_msg *msg, u8 hpet_id) +{ + struct irq_cfg *cfg = irq_cfg(irq); + + msg->address_hi = MSI_ADDR_BASE_HI; + + if (x2apic_enabled()) + msg->address_hi |= MSI_ADDR_EXT_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); +} + #ifdef CONFIG_PCI_MSI static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg, u8 hpet_id) @@ -3135,70 +2985,27 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, if (err) return err; - 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); + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; - modify_irte(irq, &irte); + x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id); - 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->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; + return 0; } -#ifdef CONFIG_SMP static int msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { struct irq_cfg *cfg = data->chip_data; struct msi_msg msg; unsigned int dest; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; __get_cached_msi_msg(data->msi_desc, &msg); @@ -3209,9 +3016,8 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) __write_msi_msg(data->msi_desc, &msg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ /* * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, @@ -3222,56 +3028,32 @@ static struct irq_chip msi_chip = { .irq_unmask = unmask_msi_irq, .irq_mask = mask_msi_irq, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = msi_set_affinity, -#endif .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) +int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, + unsigned int irq_base, unsigned int irq_offset) { struct irq_chip *chip = &msi_chip; struct msi_msg msg; + unsigned int irq = irq_base + irq_offset; int ret; ret = msi_compose_msg(dev, irq, &msg, -1); if (ret < 0) return ret; - irq_set_msi_desc(irq, msidesc); - write_msi_msg(irq, &msg); + irq_set_msi_desc_off(irq_base, irq_offset, msidesc); - if (irq_remapped(irq_get_chip_data(irq))) { - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - irq_remap_modify_chip_defaults(chip); - } + /* + * MSI-X message is written per-IRQ, the offset is always 0. + * MSI message denotes a contiguous group of IRQs, written for 0th IRQ. + */ + if (!irq_offset) + write_msi_msg(irq, &msg); + + setup_remapped_irq(irq, irq_get_chip_data(irq), chip); irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); @@ -3282,69 +3064,37 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) 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; + unsigned int irq; + int node, ret; - /* x86 doesn't support multiple MSI yet */ + /* Multiple MSI vectors only supported with interrupt remapping */ if (type == PCI_CAP_ID_MSI && nvec > 1) return 1; node = dev_to_node(&dev->dev); - irq_want = nr_irqs_gsi; - sub_handle = 0; - list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = create_irq_nr(irq_want, node); - if (irq == 0) - return -1; - irq_want = irq + 1; - 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); + list_for_each_entry(msidesc, &dev->msi_list, list) { + irq = irq_alloc_hwirq(node); + if (!irq) + return -ENOSPC; + + ret = setup_msi_irq(dev, msidesc, irq, 0); + if (ret < 0) { + irq_free_hwirq(irq); + return ret; } -no_ir: - ret = setup_msi_irq(dev, msidesc, irq); - if (ret < 0) - goto error; - sub_handle++; + } return 0; - -error: - destroy_irq(irq); - return ret; } void native_teardown_msi_irq(unsigned int irq) { - destroy_irq(irq); + irq_free_hwirq(irq); } #ifdef CONFIG_DMAR_TABLE -#ifdef CONFIG_SMP static int dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) @@ -3352,9 +3102,11 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_cfg *cfg = data->chip_data; unsigned int dest, irq = data->irq; struct msi_msg msg; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; dmar_msi_read(irq, &msg); @@ -3366,19 +3118,15 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, dmar_msi_write(irq, &msg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ - static struct irq_chip dmar_msi_type = { .name = "DMAR_MSI", .irq_unmask = dmar_msi_unmask, .irq_mask = dmar_msi_mask, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = dmar_msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3399,16 +3147,17 @@ int arch_setup_dmar_msi(unsigned int irq) #ifdef CONFIG_HPET_TIMER -#ifdef CONFIG_SMP static int hpet_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { struct irq_cfg *cfg = data->chip_data; struct msi_msg msg; unsigned int dest; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; hpet_msi_read(data->handler_data, &msg); @@ -3419,48 +3168,31 @@ static int hpet_msi_set_affinity(struct irq_data *data, hpet_msi_write(data->handler_data, &msg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ - static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .irq_unmask = hpet_msi_unmask, .irq_mask = hpet_msi_mask, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = hpet_msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; -int arch_setup_hpet_msi(unsigned int irq, unsigned int id) +int default_setup_hpet_msi(unsigned int irq, unsigned int id) { struct irq_chip *chip = &hpet_msi_type; 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) - return -1; - } - ret = msi_compose_msg(NULL, irq, &msg, id); if (ret < 0) return ret; hpet_msi_write(irq_get_handler_data(irq), &msg); irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - if (irq_remapped(irq_get_chip_data(irq))) - irq_remap_modify_chip_defaults(chip); + setup_remapped_irq(irq, irq_get_chip_data(irq), chip); irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); return 0; @@ -3473,8 +3205,6 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id) */ #ifdef CONFIG_HT_IRQ -#ifdef CONFIG_SMP - static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector) { struct ht_irq_msg msg; @@ -3494,30 +3224,30 @@ ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { struct irq_cfg *cfg = data->chip_data; unsigned int dest; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; target_ht_irq(data->irq, dest, cfg->vector); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif - static struct irq_chip ht_irq_chip = { .name = "PCI-HT", .irq_mask = mask_ht_irq, .irq_unmask = unmask_ht_irq, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = ht_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) { struct irq_cfg *cfg; + struct ht_irq_msg msg; + unsigned dest; int err; if (disable_apic) @@ -3525,36 +3255,37 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) cfg = irq_cfg(irq); err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (!err) { - struct ht_irq_msg msg; - unsigned dest; + if (err) + return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus()); + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; - msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); + msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); + + msg.address_lo = + HT_IRQ_LOW_BASE | + HT_IRQ_LOW_DEST_ID(dest) | + HT_IRQ_LOW_VECTOR(cfg->vector) | + ((apic->irq_dest_mode == 0) ? + HT_IRQ_LOW_DM_PHYSICAL : + HT_IRQ_LOW_DM_LOGICAL) | + HT_IRQ_LOW_RQEOI_EDGE | + ((apic->irq_delivery_mode != dest_LowestPrio) ? + HT_IRQ_LOW_MT_FIXED : + HT_IRQ_LOW_MT_ARBITRATED) | + HT_IRQ_LOW_IRQ_MASKED; - msg.address_lo = - HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(dest) | - HT_IRQ_LOW_VECTOR(cfg->vector) | - ((apic->irq_dest_mode == 0) ? - HT_IRQ_LOW_DM_PHYSICAL : - HT_IRQ_LOW_DM_LOGICAL) | - HT_IRQ_LOW_RQEOI_EDGE | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - HT_IRQ_LOW_MT_FIXED : - HT_IRQ_LOW_MT_ARBITRATED) | - HT_IRQ_LOW_IRQ_MASKED; + write_ht_irq_msg(irq, &msg); - write_ht_irq_msg(irq, &msg); + irq_set_chip_and_handler_name(irq, &ht_irq_chip, + handle_edge_irq, "edge"); - irq_set_chip_and_handler_name(irq, &ht_irq_chip, - handle_edge_irq, "edge"); + dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); - dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); - } - return err; + return 0; } #endif /* CONFIG_HT_IRQ */ @@ -3577,12 +3308,15 @@ int io_apic_setup_irq_pin_once(unsigned int irq, int node, { unsigned int ioapic_idx = attr->ioapic, pin = attr->ioapic_pin; int ret; + struct IO_APIC_route_entry orig_entry; /* Avoid redundant programming */ if (test_bit(pin, ioapics[ioapic_idx].pin_programmed)) { - pr_debug("Pin %d-%d already programmed\n", - mpc_ioapic_id(ioapic_idx), pin); - return 0; + pr_debug("Pin %d-%d already programmed\n", mpc_ioapic_id(ioapic_idx), pin); + orig_entry = ioapic_read_entry(attr->ioapic, pin); + if (attr->trigger == orig_entry.trigger && attr->polarity == orig_entry.polarity) + return 0; + return -EBUSY; } ret = io_apic_setup_irq_pin(irq, node, attr); if (!ret) @@ -3617,9 +3351,9 @@ static void __init probe_nr_irqs_gsi(void) printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi); } -int get_nr_irqs_gsi(void) +unsigned int arch_dynirq_lower_bound(unsigned int from) { - return nr_irqs_gsi; + return from < nr_irqs_gsi ? nr_irqs_gsi : from; } int __init arch_probe_nr_irqs(void) @@ -3722,7 +3456,8 @@ static int __init io_apic_get_unique_id(int ioapic, int apic_id) /* Sanity check */ if (reg_00.bits.ID != apic_id) { - printk("IOAPIC[%d]: Unable to change apic_id!\n", ioapic); + pr_err("IOAPIC[%d]: Unable to change apic_id!\n", + ioapic); return -1; } } @@ -3828,10 +3563,7 @@ void __init setup_ioapic_dest(void) else mask = apic->target_cpus(); - if (intr_remapping_enabled) - ir_ioapic_set_affinity(idata, mask, false); - else - ioapic_set_affinity(idata, mask, false); + x86_io_apic_ops.set_affinity(idata, mask, false); } } @@ -3871,7 +3603,7 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics) return res; } -void __init ioapic_and_gsi_init(void) +void __init native_io_apic_init_mappings(void) { unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; struct resource *ioapic_res; @@ -3967,15 +3699,33 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi) static __init int bad_ioapic(unsigned long address) { if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_WARNING "WARNING: Max # of I/O APICs (%d) exceeded " - "(found %d), skipping\n", MAX_IO_APICS, nr_ioapics); + pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n", + MAX_IO_APICS, nr_ioapics); return 1; } if (!address) { - printk(KERN_WARNING "WARNING: Bogus (zero) I/O APIC address" - " found in table, skipping!\n"); + pr_warn("WARNING: Bogus (zero) I/O APIC address found in table, skipping!\n"); + return 1; + } + return 0; +} + +static __init int bad_ioapic_register(int idx) +{ + union IO_APIC_reg_00 reg_00; + union IO_APIC_reg_01 reg_01; + union IO_APIC_reg_02 reg_02; + + reg_00.raw = io_apic_read(idx, 0); + reg_01.raw = io_apic_read(idx, 1); + reg_02.raw = io_apic_read(idx, 2); + + if (reg_00.raw == -1 && reg_01.raw == -1 && reg_02.raw == -1) { + pr_warn("I/O APIC 0x%x registers return all ones, skipping!\n", + mpc_ioapic_addr(idx)); return 1; } + return 0; } @@ -3995,6 +3745,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) ioapics[idx].mp_config.apicaddr = address; set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); + + if (bad_ioapic_register(idx)) { + clear_fixmap(FIX_IO_APIC_BASE_0 + idx); + return; + } + ioapics[idx].mp_config.apicid = io_apic_unique_id(id); ioapics[idx].mp_config.apicver = io_apic_get_version(idx); @@ -4015,10 +3771,10 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) if (gsi_cfg->gsi_end >= gsi_top) gsi_top = gsi_cfg->gsi_end + 1; - printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " - "GSI %d-%d\n", idx, mpc_ioapic_id(idx), - mpc_ioapic_ver(idx), mpc_ioapic_addr(idx), - gsi_cfg->gsi_base, gsi_cfg->gsi_end); + pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n", + idx, mpc_ioapic_id(idx), + mpc_ioapic_ver(idx), mpc_ioapic_addr(idx), + gsi_cfg->gsi_base, gsi_cfg->gsi_end); nr_ioapics++; } |