aboutsummaryrefslogtreecommitdiff
path: root/arch/i386/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/i386/kernel')
-rw-r--r--arch/i386/kernel/acpi/boot.c9
-rw-r--r--arch/i386/kernel/cpu/common.c12
-rw-r--r--arch/i386/kernel/efi.c3
-rw-r--r--arch/i386/kernel/i8259.c45
-rw-r--r--arch/i386/kernel/io_apic.c495
-rw-r--r--arch/i386/kernel/irq.c19
-rw-r--r--arch/i386/kernel/kprobes.c41
-rw-r--r--arch/i386/kernel/ldt.c2
-rw-r--r--arch/i386/kernel/process.c6
-rw-r--r--arch/i386/kernel/smpboot.c3
-rw-r--r--arch/i386/kernel/sys_i386.c42
-rw-r--r--arch/i386/kernel/traps.c6
12 files changed, 402 insertions, 281 deletions
diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index 1aaea6ab8c4..92f79cdd9a4 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -62,8 +62,6 @@ static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return
#include <mach_mpparse.h>
#endif /* CONFIG_X86_LOCAL_APIC */
-static inline int gsi_irq_sharing(int gsi) { return gsi; }
-
#endif /* X86 */
#define BAD_MADT_ENTRY(entry, end) ( \
@@ -468,12 +466,7 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
{
-#ifdef CONFIG_X86_IO_APIC
- if (use_pci_vector() && !platform_legacy_irq(gsi))
- *irq = IO_APIC_VECTOR(gsi);
- else
-#endif
- *irq = gsi_irq_sharing(gsi);
+ *irq = gsi;
return 0;
}
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index 2799baaadf4..d9f3e3c31f0 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -184,7 +184,16 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early)
static int __init x86_fxsr_setup(char * s)
{
+ /* Tell all the other CPU's to not use it... */
disable_x86_fxsr = 1;
+
+ /*
+ * ... and clear the bits early in the boot_cpu_data
+ * so that the bootup process doesn't try to do this
+ * either.
+ */
+ clear_bit(X86_FEATURE_FXSR, boot_cpu_data.x86_capability);
+ clear_bit(X86_FEATURE_XMM, boot_cpu_data.x86_capability);
return 1;
}
__setup("nofxsr", x86_fxsr_setup);
@@ -660,8 +669,7 @@ old_gdt:
*/
atomic_inc(&init_mm.mm_count);
current->active_mm = &init_mm;
- if (current->mm)
- BUG();
+ BUG_ON(current->mm);
enter_lazy_tlb(&init_mm, current);
load_esp0(t, thread);
diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c
index f9436989473..8b40648d0ef 100644
--- a/arch/i386/kernel/efi.c
+++ b/arch/i386/kernel/efi.c
@@ -498,8 +498,7 @@ void __init efi_enter_virtual_mode(void)
check_range_for_systab(md);
}
- if (!efi.systab)
- BUG();
+ BUG_ON(!efi.systab);
status = phys_efi_set_virtual_address_map(
memmap.desc_size * memmap.nr_map,
diff --git a/arch/i386/kernel/i8259.c b/arch/i386/kernel/i8259.c
index ea5f4e7958d..d07ed31f11e 100644
--- a/arch/i386/kernel/i8259.c
+++ b/arch/i386/kernel/i8259.c
@@ -34,35 +34,15 @@
* moves to arch independent land
*/
-DEFINE_SPINLOCK(i8259A_lock);
-
-static void end_8259A_irq (unsigned int irq)
-{
- if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS)) &&
- irq_desc[irq].action)
- enable_8259A_irq(irq);
-}
-
-#define shutdown_8259A_irq disable_8259A_irq
-
static int i8259A_auto_eoi;
-
+DEFINE_SPINLOCK(i8259A_lock);
static void mask_and_ack_8259A(unsigned int);
-unsigned int startup_8259A_irq(unsigned int irq)
-{
- enable_8259A_irq(irq);
- return 0; /* never anything pending */
-}
-
-static struct hw_interrupt_type i8259A_irq_type = {
- .typename = "XT-PIC",
- .startup = startup_8259A_irq,
- .shutdown = shutdown_8259A_irq,
- .enable = enable_8259A_irq,
- .disable = disable_8259A_irq,
- .ack = mask_and_ack_8259A,
- .end = end_8259A_irq,
+static struct irq_chip i8259A_chip = {
+ .name = "XT-PIC",
+ .mask = disable_8259A_irq,
+ .unmask = enable_8259A_irq,
+ .mask_ack = mask_and_ack_8259A,
};
/*
@@ -133,7 +113,7 @@ void make_8259A_irq(unsigned int irq)
{
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
- irq_desc[irq].chip = &i8259A_irq_type;
+ set_irq_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
enable_irq(irq);
}
@@ -327,12 +307,12 @@ void init_8259A(int auto_eoi)
outb_p(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */
if (auto_eoi)
/*
- * in AEOI mode we just have to mask the interrupt
+ * In AEOI mode we just have to mask the interrupt
* when acking.
*/
- i8259A_irq_type.ack = disable_8259A_irq;
+ i8259A_chip.mask_ack = disable_8259A_irq;
else
- i8259A_irq_type.ack = mask_and_ack_8259A;
+ i8259A_chip.mask_ack = mask_and_ack_8259A;
udelay(100); /* wait for 8259A to initialize */
@@ -389,12 +369,13 @@ void __init init_ISA_irqs (void)
/*
* 16 old-style INTA-cycle interrupts:
*/
- irq_desc[i].chip = &i8259A_irq_type;
+ set_irq_chip_and_handler(i, &i8259A_chip,
+ handle_level_irq);
} else {
/*
* 'high' PCI IRQs filled in on demand
*/
- irq_desc[i].chip = &no_irq_type;
+ irq_desc[i].chip = &no_irq_chip;
}
}
}
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index fd0df75cfbd..b7287fb499f 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -31,6 +31,9 @@
#include <linux/acpi.h>
#include <linux/module.h>
#include <linux/sysdev.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <linux/htirq.h>
#include <asm/io.h>
#include <asm/smp.h>
@@ -38,6 +41,8 @@
#include <asm/timer.h>
#include <asm/i8259.h>
#include <asm/nmi.h>
+#include <asm/msidef.h>
+#include <asm/hypertransport.h>
#include <mach_apic.h>
#include <mach_apicdef.h>
@@ -86,15 +91,6 @@ static struct irq_pin_list {
int apic, pin, next;
} irq_2_pin[PIN_MAP_SIZE];
-int vector_irq[NR_VECTORS] __read_mostly = { [0 ... NR_VECTORS - 1] = -1};
-#ifdef CONFIG_PCI_MSI
-#define vector_to_irq(vector) \
- (platform_legacy_irq(vector) ? vector : vector_irq[vector])
-#else
-#define vector_to_irq(vector) (vector)
-#endif
-
-
union entry_union {
struct { u32 w1, w2; };
struct IO_APIC_route_entry entry;
@@ -280,7 +276,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
break;
entry = irq_2_pin + entry->next;
}
- set_irq_info(irq, cpumask);
+ set_native_irq_info(irq, cpumask);
spin_unlock_irqrestore(&ioapic_lock, flags);
}
@@ -1181,46 +1177,45 @@ static inline int IO_APIC_irq_trigger(int irq)
/* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */
u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 };
-int assign_irq_vector(int irq)
+static int __assign_irq_vector(int irq)
{
static int current_vector = FIRST_DEVICE_VECTOR, offset = 0;
- unsigned long flags;
int vector;
- BUG_ON(irq != AUTO_ASSIGN && (unsigned)irq >= NR_IRQ_VECTORS);
+ BUG_ON((unsigned)irq >= NR_IRQ_VECTORS);
- spin_lock_irqsave(&vector_lock, flags);
-
- if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0) {
- spin_unlock_irqrestore(&vector_lock, flags);
+ if (IO_APIC_VECTOR(irq) > 0)
return IO_APIC_VECTOR(irq);
- }
-next:
+
current_vector += 8;
if (current_vector == SYSCALL_VECTOR)
- goto next;
+ current_vector += 8;
if (current_vector >= FIRST_SYSTEM_VECTOR) {
offset++;
- if (!(offset%8)) {
- spin_unlock_irqrestore(&vector_lock, flags);
+ if (!(offset % 8))
return -ENOSPC;
- }
current_vector = FIRST_DEVICE_VECTOR + offset;
}
vector = current_vector;
- vector_irq[vector] = irq;
- if (irq != AUTO_ASSIGN)
- IO_APIC_VECTOR(irq) = vector;
+ IO_APIC_VECTOR(irq) = vector;
+
+ return vector;
+}
+
+static int assign_irq_vector(int irq)
+{
+ unsigned long flags;
+ int vector;
+ spin_lock_irqsave(&vector_lock, flags);
+ vector = __assign_irq_vector(irq);
spin_unlock_irqrestore(&vector_lock, flags);
return vector;
}
-
-static struct hw_interrupt_type ioapic_level_type;
-static struct hw_interrupt_type ioapic_edge_type;
+static struct irq_chip ioapic_chip;
#define IOAPIC_AUTO -1
#define IOAPIC_EDGE 0
@@ -1228,16 +1223,14 @@ static struct hw_interrupt_type ioapic_edge_type;
static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
{
- unsigned idx;
-
- idx = use_pci_vector() && !platform_legacy_irq(irq) ? vector : irq;
-
if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
trigger == IOAPIC_LEVEL)
- irq_desc[idx].chip = &ioapic_level_type;
+ set_irq_chip_and_handler(irq, &ioapic_chip,
+ handle_fasteoi_irq);
else
- irq_desc[idx].chip = &ioapic_edge_type;
- set_intr_gate(vector, interrupt[idx]);
+ set_irq_chip_and_handler(irq, &ioapic_chip,
+ handle_edge_irq);
+ set_intr_gate(vector, interrupt[irq]);
}
static void __init setup_IO_APIC_irqs(void)
@@ -1346,7 +1339,8 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
* The timer IRQ doesn't have to know that behind the
* scene we have a 8259A-master in AEOI mode ...
*/
- irq_desc[0].chip = &ioapic_edge_type;
+ irq_desc[0].chip = &ioapic_chip;
+ set_irq_handler(0, handle_edge_irq);
/*
* Add it to the IO-APIC irq-routing table:
@@ -1481,17 +1475,12 @@ void __init print_IO_APIC(void)
);
}
}
- if (use_pci_vector())
- printk(KERN_INFO "Using vector-based indexing\n");
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)
continue;
- if (use_pci_vector() && !platform_legacy_irq(i))
- printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i));
- else
- printk(KERN_DEBUG "IRQ%d ", i);
+ printk(KERN_DEBUG "IRQ%d ", i);
for (;;) {
printk("-> %d:%d", entry->apic, entry->pin);
if (!entry->next)
@@ -1918,6 +1907,8 @@ static int __init timer_irq_works(void)
*/
/*
+ * Startup quirk:
+ *
* 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
@@ -1925,8 +1916,10 @@ static int __init timer_irq_works(void)
*
* This is not complete - we should be able to fake
* an edge even if it isn't on the 8259A...
+ *
+ * (We do this for level-triggered IRQs too - it cannot hurt.)
*/
-static unsigned int startup_edge_ioapic_irq(unsigned int irq)
+static unsigned int startup_ioapic_irq(unsigned int irq)
{
int was_pending = 0;
unsigned long flags;
@@ -1943,47 +1936,18 @@ static unsigned int startup_edge_ioapic_irq(unsigned int irq)
return was_pending;
}
-/*
- * Once we have recorded IRQ_PENDING already, we can mask the
- * interrupt for real. This prevents IRQ storms from unhandled
- * devices.
- */
-static void ack_edge_ioapic_irq(unsigned int irq)
+static void ack_ioapic_irq(unsigned int irq)
{
- move_irq(irq);
- if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED))
- == (IRQ_PENDING | IRQ_DISABLED))
- mask_IO_APIC_irq(irq);
+ move_native_irq(irq);
ack_APIC_irq();
}
-/*
- * Level triggered interrupts can just be masked,
- * and shutting down and starting up the interrupt
- * is the same as enabling and disabling them -- except
- * with a startup need to return a "was pending" value.
- *
- * Level triggered interrupts are special because we
- * do not touch any IO-APIC register while handling
- * them. We ack the APIC in the end-IRQ handler, not
- * in the start-IRQ-handler. Protection against reentrance
- * from the same interrupt is still provided, both by the
- * generic IRQ layer and by the fact that an unacked local
- * APIC does not accept IRQs.
- */
-static unsigned int startup_level_ioapic_irq (unsigned int irq)
-{
- unmask_IO_APIC_irq(irq);
-
- return 0; /* don't check for pending */
-}
-
-static void end_level_ioapic_irq (unsigned int irq)
+static void ack_ioapic_quirk_irq(unsigned int irq)
{
unsigned long v;
int i;
- move_irq(irq);
+ move_native_irq(irq);
/*
* 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
@@ -2018,105 +1982,26 @@ static void end_level_ioapic_irq (unsigned int irq)
}
}
-#ifdef CONFIG_PCI_MSI
-static unsigned int startup_edge_ioapic_vector(unsigned int vector)
-{
- int irq = vector_to_irq(vector);
-
- return startup_edge_ioapic_irq(irq);
-}
-
-static void ack_edge_ioapic_vector(unsigned int vector)
-{
- int irq = vector_to_irq(vector);
-
- move_native_irq(vector);
- ack_edge_ioapic_irq(irq);
-}
-
-static unsigned int startup_level_ioapic_vector (unsigned int vector)
-{
- int irq = vector_to_irq(vector);
-
- return startup_level_ioapic_irq (irq);
-}
-
-static void end_level_ioapic_vector (unsigned int vector)
-{
- int irq = vector_to_irq(vector);
-
- move_native_irq(vector);
- end_level_ioapic_irq(irq);
-}
-
-static void mask_IO_APIC_vector (unsigned int vector)
-{
- int irq = vector_to_irq(vector);
-
- mask_IO_APIC_irq(irq);
-}
-
-static void unmask_IO_APIC_vector (unsigned int vector)
-{
- int irq = vector_to_irq(vector);
-
- unmask_IO_APIC_irq(irq);
-}
-
-#ifdef CONFIG_SMP
-static void set_ioapic_affinity_vector (unsigned int vector,
- cpumask_t cpu_mask)
-{
- int irq = vector_to_irq(vector);
-
- set_native_irq_info(vector, cpu_mask);
- set_ioapic_affinity_irq(irq, cpu_mask);
-}
-#endif
-#endif
-
-static int ioapic_retrigger(unsigned int irq)
+static int ioapic_retrigger_irq(unsigned int irq)
{
send_IPI_self(IO_APIC_VECTOR(irq));
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.
- */
-static struct hw_interrupt_type ioapic_edge_type __read_mostly = {
- .typename = "IO-APIC-edge",
- .startup = startup_edge_ioapic,
- .shutdown = shutdown_edge_ioapic,
- .enable = enable_edge_ioapic,
- .disable = disable_edge_ioapic,
- .ack = ack_edge_ioapic,
- .end = end_edge_ioapic,
+static struct irq_chip ioapic_chip __read_mostly = {
+ .name = "IO-APIC",
+ .startup = startup_ioapic_irq,
+ .mask = mask_IO_APIC_irq,
+ .unmask = unmask_IO_APIC_irq,
+ .ack = ack_ioapic_irq,
+ .eoi = ack_ioapic_quirk_irq,
#ifdef CONFIG_SMP
- .set_affinity = set_ioapic_affinity,
+ .set_affinity = set_ioapic_affinity_irq,
#endif
- .retrigger = ioapic_retrigger,
+ .retrigger = ioapic_retrigger_irq,
};
-static struct hw_interrupt_type ioapic_level_type __read_mostly = {
- .typename = "IO-APIC-level",
- .startup = startup_level_ioapic,
- .shutdown = shutdown_level_ioapic,
- .enable = enable_level_ioapic,
- .disable = disable_level_ioapic,
- .ack = mask_and_ack_level_ioapic,
- .end = end_level_ioapic,
-#ifdef CONFIG_SMP
- .set_affinity = set_ioapic_affinity,
-#endif
- .retrigger = ioapic_retrigger,
-};
static inline void init_IO_APIC_traps(void)
{
@@ -2135,11 +2020,6 @@ static inline void init_IO_APIC_traps(void)
*/
for (irq = 0; irq < NR_IRQS ; irq++) {
int tmp = irq;
- if (use_pci_vector()) {
- if (!platform_legacy_irq(tmp))
- if ((tmp = vector_to_irq(tmp)) == -1)
- continue;
- }
if (IO_APIC_IRQ(tmp) && !IO_APIC_VECTOR(tmp)) {
/*
* Hmm.. We don't have an entry for this,
@@ -2150,20 +2030,21 @@ static inline void init_IO_APIC_traps(void)
make_8259A_irq(irq);
else
/* Strange. Oh, well.. */
- irq_desc[irq].chip = &no_irq_type;
+ irq_desc[irq].chip = &no_irq_chip;
}
}
}
-static void enable_lapic_irq (unsigned int irq)
-{
- unsigned long v;
+/*
+ * The local APIC irq-chip implementation:
+ */
- v = apic_read(APIC_LVT0);
- apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED);
+static void ack_apic(unsigned int irq)
+{
+ ack_APIC_irq();
}
-static void disable_lapic_irq (unsigned int irq)
+static void mask_lapic_irq (unsigned int irq)
{
unsigned long v;
@@ -2171,21 +2052,19 @@ static void disable_lapic_irq (unsigned int irq)
apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
}
-static void ack_lapic_irq (unsigned int irq)
+static void unmask_lapic_irq (unsigned int irq)
{
- ack_APIC_irq();
-}
+ unsigned long v;
-static void end_lapic_irq (unsigned int i) { /* nothing */ }
+ v = apic_read(APIC_LVT0);
+ apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED);
+}
-static struct hw_interrupt_type lapic_irq_type __read_mostly = {
- .typename = "local-APIC-edge",
- .startup = NULL, /* startup_irq() not used for IRQ0 */
- .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */
- .enable = enable_lapic_irq,
- .disable = disable_lapic_irq,
- .ack = ack_lapic_irq,
- .end = end_lapic_irq
+static struct irq_chip lapic_chip __read_mostly = {
+ .name = "local-APIC-edge",
+ .mask = mask_lapic_irq,
+ .unmask = unmask_lapic_irq,
+ .eoi = ack_apic,
};
static void setup_nmi (void)
@@ -2356,7 +2235,7 @@ static inline void check_timer(void)
printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
disable_8259A_irq(0);
- irq_desc[0].chip = &lapic_irq_type;
+ set_irq_chip_and_handler(0, &lapic_chip, handle_fasteoi_irq);
apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */
enable_8259A_irq(0);
@@ -2531,6 +2410,238 @@ static int __init ioapic_init_sysfs(void)
device_initcall(ioapic_init_sysfs);
+/*
+ * Dynamic irq allocate and deallocation
+ */
+int create_irq(void)
+{
+ /* Allocate an unused irq */
+ int irq, new, vector;
+ unsigned long flags;
+
+ irq = -ENOSPC;
+ spin_lock_irqsave(&vector_lock, flags);
+ for (new = (NR_IRQS - 1); new >= 0; new--) {
+ if (platform_legacy_irq(new))
+ continue;
+ if (irq_vector[new] != 0)
+ continue;
+ vector = __assign_irq_vector(new);
+ if (likely(vector > 0))
+ irq = new;
+ break;
+ }
+ spin_unlock_irqrestore(&vector_lock, flags);
+
+ if (irq >= 0) {
+ set_intr_gate(vector, interrupt[irq]);
+ dynamic_irq_init(irq);
+ }
+ return irq;
+}
+
+void destroy_irq(unsigned int irq)
+{
+ unsigned long flags;
+
+ dynamic_irq_cleanup(irq);
+
+ spin_lock_irqsave(&vector_lock, flags);
+ irq_vector[irq] = 0;
+ spin_unlock_irqrestore(&vector_lock, flags);
+}
+
+/*
+ * MSI mesage composition
+ */
+#ifdef CONFIG_PCI_MSI
+static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
+{
+ int vector;
+ unsigned dest;
+
+ vector = assign_irq_vector(irq);
+ if (vector >= 0) {
+ dest = cpu_mask_to_apicid(TARGET_CPUS);
+
+ msg->address_hi = MSI_ADDR_BASE_HI;
+ msg->address_lo =
+ MSI_ADDR_BASE_LO |
+ ((INT_DEST_MODE == 0) ?
+ MSI_ADDR_DEST_MODE_PHYSICAL:
+ MSI_ADDR_DEST_MODE_LOGICAL) |
+ ((INT_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 |
+ ((INT_DELIVERY_MODE != dest_LowestPrio) ?
+ MSI_DATA_DELIVERY_FIXED:
+ MSI_DATA_DELIVERY_LOWPRI) |
+ MSI_DATA_VECTOR(vector);
+ }
+ return vector;
+}
+
+#ifdef CONFIG_SMP
+static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+{
+ struct msi_msg msg;
+ unsigned int dest;
+ cpumask_t tmp;
+ int vector;
+
+ cpus_and(tmp, mask, cpu_online_map);
+ if (cpus_empty(tmp))
+ tmp = TARGET_CPUS;
+
+ vector = assign_irq_vector(irq);
+ if (vector < 0)
+ return;
+
+ dest = cpu_mask_to_apicid(mask);
+
+ read_msi_msg(irq, &msg);
+
+ msg.data &= ~MSI_DATA_VECTOR_MASK;
+ msg.data |= MSI_DATA_VECTOR(vector);
+ msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+ msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+ write_msi_msg(irq, &msg);
+ set_native_irq_info(irq, mask);
+}
+#endif /* CONFIG_SMP */
+
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip msi_chip = {
+ .name = "PCI-MSI",
+ .unmask = unmask_msi_irq,
+ .mask = mask_msi_irq,
+ .ack = ack_ioapic_irq,
+#ifdef CONFIG_SMP
+ .set_affinity = set_msi_irq_affinity,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+
+int arch_setup_msi_irq(unsigned int irq, struct pci_dev *dev)
+{
+ struct msi_msg msg;
+ int ret;
+ ret = msi_compose_msg(dev, irq, &msg);
+ if (ret < 0)
+ return ret;
+
+ write_msi_msg(irq, &msg);
+
+ set_irq_chip_and_handler(irq, &msi_chip, handle_edge_irq);
+
+ return 0;
+}
+
+void arch_teardown_msi_irq(unsigned int irq)
+{
+ return;
+}
+
+#endif /* CONFIG_PCI_MSI */
+
+/*
+ * Hypertransport interrupt support
+ */
+#ifdef CONFIG_HT_IRQ
+
+#ifdef CONFIG_SMP
+
+static void target_ht_irq(unsigned int irq, unsigned int dest)
+{
+ u32 low, high;
+ low = read_ht_irq_low(irq);
+ high = read_ht_irq_high(irq);
+
+ low &= ~(HT_IRQ_LOW_DEST_ID_MASK);
+ high &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+
+ low |= HT_IRQ_LOW_DEST_ID(dest);
+ high |= HT_IRQ_HIGH_DEST_ID(dest);
+
+ write_ht_irq_low(irq, low);
+ write_ht_irq_high(irq, high);
+}
+
+static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
+{
+ unsigned int dest;
+ cpumask_t tmp;
+
+ cpus_and(tmp, mask, cpu_online_map);
+ if (cpus_empty(tmp))
+ tmp = TARGET_CPUS;
+
+ cpus_and(mask, tmp, CPU_MASK_ALL);
+
+ dest = cpu_mask_to_apicid(mask);
+
+ target_ht_irq(irq, dest);
+ set_native_irq_info(irq, mask);
+}
+#endif
+
+static struct hw_interrupt_type ht_irq_chip = {
+ .name = "PCI-HT",
+ .mask = mask_ht_irq,
+ .unmask = unmask_ht_irq,
+ .ack = ack_ioapic_irq,
+#ifdef CONFIG_SMP
+ .set_affinity = set_ht_irq_affinity,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+
+int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
+{
+ int vector;
+
+ vector = assign_irq_vector(irq);
+ if (vector >= 0) {
+ u32 low, high;
+ unsigned dest;
+ cpumask_t tmp;
+
+ cpus_clear(tmp);
+ cpu_set(vector >> 8, tmp);
+ dest = cpu_mask_to_apicid(tmp);
+
+ high = HT_IRQ_HIGH_DEST_ID(dest);
+
+ low = HT_IRQ_LOW_BASE |
+ HT_IRQ_LOW_DEST_ID(dest) |
+ HT_IRQ_LOW_VECTOR(vector) |
+ ((INT_DEST_MODE == 0) ?
+ HT_IRQ_LOW_DM_PHYSICAL :
+ HT_IRQ_LOW_DM_LOGICAL) |
+ HT_IRQ_LOW_RQEOI_EDGE |
+ ((INT_DELIVERY_MODE != dest_LowestPrio) ?
+ HT_IRQ_LOW_MT_FIXED :
+ HT_IRQ_LOW_MT_ARBITRATED) |
+ HT_IRQ_LOW_IRQ_MASKED;
+
+ write_ht_irq_low(irq, low);
+ write_ht_irq_high(irq, high);
+
+ set_irq_chip_and_handler(irq, &ht_irq_chip, handle_edge_irq);
+ }
+ return vector;
+}
+#endif /* CONFIG_HT_IRQ */
+
/* --------------------------------------------------------------------------
ACPI-based IOAPIC Configuration
-------------------------------------------------------------------------- */
@@ -2684,7 +2795,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a
ioapic_write_entry(ioapic, pin, entry);
spin_lock_irqsave(&ioapic_lock, flags);
- set_native_irq_info(use_pci_vector() ? entry.vector : irq, TARGET_CPUS);
+ set_native_irq_info(irq, TARGET_CPUS);
spin_unlock_irqrestore(&ioapic_lock, flags);
return 0;
diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
index 5fe547cd8f9..3dd2e180151 100644
--- a/arch/i386/kernel/irq.c
+++ b/arch/i386/kernel/irq.c
@@ -55,6 +55,7 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs)
{
/* high bit used in ret_from_ code */
int irq = ~regs->orig_eax;
+ struct irq_desc *desc = irq_desc + irq;
#ifdef CONFIG_4KSTACKS
union irq_ctx *curctx, *irqctx;
u32 *isp;
@@ -94,7 +95,7 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs)
* current stack (which is the irq stack already after all)
*/
if (curctx != irqctx) {
- int arg1, arg2, ebx;
+ int arg1, arg2, arg3, ebx;
/* build the stack frame on the IRQ stack */
isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
@@ -110,16 +111,17 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs)
(curctx->tinfo.preempt_count & SOFTIRQ_MASK);
asm volatile(
- " xchgl %%ebx,%%esp \n"
- " call __do_IRQ \n"
+ " xchgl %%ebx,%%esp \n"
+ " call *%%edi \n"
" movl %%ebx,%%esp \n"
- : "=a" (arg1), "=d" (arg2), "=b" (ebx)
- : "0" (irq), "1" (regs), "2" (isp)
- : "memory", "cc", "ecx"
+ : "=a" (arg1), "=d" (arg2), "=c" (arg3), "=b" (ebx)
+ : "0" (irq), "1" (desc), "2" (regs), "3" (isp),
+ "D" (desc->handle_irq)
+ : "memory", "cc"
);
} else
#endif
- __do_IRQ(irq, regs);
+ desc->handle_irq(irq, desc, regs);
irq_exit();
@@ -253,7 +255,8 @@ int show_interrupts(struct seq_file *p, void *v)
for_each_online_cpu(j)
seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
#endif
- seq_printf(p, " %14s", irq_desc[i].chip->typename);
+ seq_printf(p, " %8s", irq_desc[i].chip->name);
+ seq_printf(p, "-%s", handle_irq_name(irq_desc[i].handle_irq));
seq_printf(p, " %s", action->name);
for (action=action->next; action; action = action->next)
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index afe6505ca0b..d98e44b16fe 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -230,20 +230,20 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
struct pt_regs *regs)
{
unsigned long *sara = (unsigned long *)&regs->esp;
- struct kretprobe_instance *ri;
- if ((ri = get_free_rp_inst(rp)) != NULL) {
- ri->rp = rp;
- ri->task = current;
+ struct kretprobe_instance *ri;
+
+ if ((ri = get_free_rp_inst(rp)) != NULL) {
+ ri->rp = rp;
+ ri->task = current;
ri->ret_addr = (kprobe_opcode_t *) *sara;
/* Replace the return addr with trampoline addr */
*sara = (unsigned long) &kretprobe_trampoline;
-
- add_rp_inst(ri);
- } else {
- rp->nmissed++;
- }
+ add_rp_inst(ri);
+ } else {
+ rp->nmissed++;
+ }
}
/*
@@ -359,7 +359,7 @@ no_kprobe:
void __kprobes kretprobe_trampoline_holder(void)
{
asm volatile ( ".global kretprobe_trampoline\n"
- "kretprobe_trampoline: \n"
+ "kretprobe_trampoline: \n"
" pushf\n"
/* skip cs, eip, orig_eax, es, ds */
" subl $20, %esp\n"
@@ -395,14 +395,15 @@ no_kprobe:
*/
fastcall void *__kprobes trampoline_handler(struct pt_regs *regs)
{
- struct kretprobe_instance *ri = NULL;
- struct hlist_head *head;
- struct hlist_node *node, *tmp;
+ struct kretprobe_instance *ri = NULL;
+ struct hlist_head *head, empty_rp;
+ struct hlist_node *node, *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
+ INIT_HLIST_HEAD(&empty_rp);
spin_lock_irqsave(&kretprobe_lock, flags);
- head = kretprobe_inst_table_head(current);
+ head = kretprobe_inst_table_head(current);
/*
* It is possible to have multiple instances associated with a given
@@ -413,14 +414,14 @@ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs)
* We can handle this because:
* - instances are always inserted at the head of the list
* - when multiple return probes are registered for the same
- * function, the first instance's ret_addr will point to the
+ * function, the first instance's ret_addr will point to the
* real return address, and all the rest will point to
* kretprobe_trampoline
*/
hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
- if (ri->task != current)
+ if (ri->task != current)
/* another task is sharing our hash bucket */
- continue;
+ continue;
if (ri->rp && ri->rp->handler){
__get_cpu_var(current_kprobe) = &ri->rp->kp;
@@ -429,7 +430,7 @@ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs)
}
orig_ret_address = (unsigned long)ri->ret_addr;
- recycle_rp_inst(ri);
+ recycle_rp_inst(ri, &empty_rp);
if (orig_ret_address != trampoline_address)
/*
@@ -444,6 +445,10 @@ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs)
spin_unlock_irqrestore(&kretprobe_lock, flags);
+ hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
+ hlist_del(&ri->hlist);
+ kfree(ri);
+ }
return (void*)orig_ret_address;
}
diff --git a/arch/i386/kernel/ldt.c b/arch/i386/kernel/ldt.c
index 983f95707e1..445211eb2d5 100644
--- a/arch/i386/kernel/ldt.c
+++ b/arch/i386/kernel/ldt.c
@@ -1,5 +1,5 @@
/*
- * linux/kernel/ldt.c
+ * linux/arch/i386/kernel/ldt.c
*
* Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
* Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 96cd0232e1e..dad02a960e0 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -297,9 +297,9 @@ void show_regs(struct pt_regs * regs)
if (user_mode_vm(regs))
printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
printk(" EFLAGS: %08lx %s (%s %.*s)\n",
- regs->eflags, print_tainted(), system_utsname.release,
- (int)strcspn(system_utsname.version, " "),
- system_utsname.version);
+ regs->eflags, print_tainted(), init_utsname()->release,
+ (int)strcspn(init_utsname()->version, " "),
+ init_utsname()->version);
printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
regs->eax,regs->ebx,regs->ecx,regs->edx);
printk("ESI: %08lx EDI: %08lx EBP: %08lx",
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 0831f709f77..4bb8b77cd65 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -612,6 +612,7 @@ extern struct {
/* which logical CPUs are on which nodes */
cpumask_t node_2_cpu_mask[MAX_NUMNODES] __read_mostly =
{ [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE };
+EXPORT_SYMBOL(node_2_cpu_mask);
/* which node each logical CPU is on */
int cpu_2_node[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
EXPORT_SYMBOL(cpu_2_node);
@@ -647,7 +648,7 @@ static void map_cpu_to_logical_apicid(void)
{
int cpu = smp_processor_id();
int apicid = logical_smp_processor_id();
- int node = apicid_to_node(hard_smp_processor_id());
+ int node = apicid_to_node(apicid);
if (!node_online(node))
node = first_online_node;
diff --git a/arch/i386/kernel/sys_i386.c b/arch/i386/kernel/sys_i386.c
index 8fdb1fb17a5..4048397f174 100644
--- a/arch/i386/kernel/sys_i386.c
+++ b/arch/i386/kernel/sys_i386.c
@@ -21,6 +21,7 @@
#include <linux/utsname.h>
#include <asm/uaccess.h>
+#include <asm/unistd.h>
#include <asm/ipc.h>
/*
@@ -210,7 +211,7 @@ asmlinkage int sys_uname(struct old_utsname __user * name)
if (!name)
return -EFAULT;
down_read(&uts_sem);
- err=copy_to_user(name, &system_utsname, sizeof (*name));
+ err = copy_to_user(name, utsname(), sizeof (*name));
up_read(&uts_sem);
return err?-EFAULT:0;
}
@@ -226,16 +227,21 @@ asmlinkage int sys_olduname(struct oldold_utsname __user * name)
down_read(&uts_sem);
- error = __copy_to_user(&name->sysname,&system_utsname.sysname,__OLD_UTS_LEN);
- error |= __put_user(0,name->sysname+__OLD_UTS_LEN);
- error |= __copy_to_user(&name->nodename,&system_utsname.nodename,__OLD_UTS_LEN);
- error |= __put_user(0,name->nodename+__OLD_UTS_LEN);
- error |= __copy_to_user(&name->release,&system_utsname.release,__OLD_UTS_LEN);
- error |= __put_user(0,name->release+__OLD_UTS_LEN);
- error |= __copy_to_user(&name->version,&system_utsname.version,__OLD_UTS_LEN);
- error |= __put_user(0,name->version+__OLD_UTS_LEN);
- error |= __copy_to_user(&name->machine,&system_utsname.machine,__OLD_UTS_LEN);
- error |= __put_user(0,name->machine+__OLD_UTS_LEN);
+ error = __copy_to_user(&name->sysname, &utsname()->sysname,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->sysname + __OLD_UTS_LEN);
+ error |= __copy_to_user(&name->nodename, &utsname()->nodename,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->nodename + __OLD_UTS_LEN);
+ error |= __copy_to_user(&name->release, &utsname()->release,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->release + __OLD_UTS_LEN);
+ error |= __copy_to_user(&name->version, &utsname()->version,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->version + __OLD_UTS_LEN);
+ error |= __copy_to_user(&name->machine, &utsname()->machine,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->machine + __OLD_UTS_LEN);
up_read(&uts_sem);
@@ -243,3 +249,17 @@ asmlinkage int sys_olduname(struct oldold_utsname __user * name)
return error;
}
+
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+ long __res;
+ asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx"
+ : "=a" (__res)
+ : "0" (__NR_execve),"ri" (filename),"c" (argv), "d" (envp) : "memory");
+ return __res;
+}
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 6820b8d643c..00489b706d2 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -357,9 +357,9 @@ void show_registers(struct pt_regs *regs)
KERN_EMERG "EIP: %04x:[<%08lx>] %s VLI\n"
KERN_EMERG "EFLAGS: %08lx (%s %.*s)\n",
smp_processor_id(), 0xffff & regs->xcs, regs->eip,
- print_tainted(), regs->eflags, system_utsname.release,
- (int)strcspn(system_utsname.version, " "),
- system_utsname.version);
+ print_tainted(), regs->eflags, init_utsname()->release,
+ (int)strcspn(init_utsname()->version, " "),
+ init_utsname()->version);
print_symbol(KERN_EMERG "EIP is at %s\n", regs->eip);
printk(KERN_EMERG "eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n",
regs->eax, regs->ebx, regs->ecx, regs->edx);