* domain gets 1024 event channels, but NR_IRQ is not that large, we
* must dynamically map irqs<->event channels. The event channels
* interface with the rest of the kernel by defining a xen interrupt
- * chip. When an event is recieved, it is mapped to an irq and sent
+ * chip. When an event is received, it is mapped to an irq and sent
* through the normal interrupt processing path.
*
* There are four kinds of events which can be mapped to an event
*/
static DEFINE_SPINLOCK(irq_mapping_update_lock);
+static LIST_HEAD(xen_irq_list_head);
+
/* IRQ <-> VIRQ mapping. */
static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
*/
struct irq_info
{
+ struct list_head list;
enum xen_irq_type type; /* type */
+ unsigned irq;
unsigned short evtchn; /* event channel */
unsigned short cpu; /* cpu bound */
unsigned short gsi;
unsigned char vector;
unsigned char flags;
+ uint16_t domid;
} pirq;
} u;
};
#define PIRQ_NEEDS_EOI (1 << 0)
#define PIRQ_SHAREABLE (1 << 1)
-static struct irq_info *irq_info;
-static int *pirq_to_irq;
-
static int *evtchn_to_irq;
-struct cpu_evtchn_s {
- unsigned long bits[NR_EVENT_CHANNELS/BITS_PER_LONG];
-};
-static __initdata struct cpu_evtchn_s init_evtchn_mask = {
- .bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
-};
-static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
-
-static inline unsigned long *cpu_evtchn_mask(int cpu)
-{
- return cpu_evtchn_mask_p[cpu].bits;
-}
+static DEFINE_PER_CPU(unsigned long [NR_EVENT_CHANNELS/BITS_PER_LONG],
+ cpu_evtchn_mask);
/* Xen will never allocate port zero for any purpose. */
#define VALID_EVTCHN(chn) ((chn) != 0)
static struct irq_chip xen_dynamic_chip;
static struct irq_chip xen_percpu_chip;
static struct irq_chip xen_pirq_chip;
+static void enable_dynirq(struct irq_data *data);
+static void disable_dynirq(struct irq_data *data);
+
+/* Get info for IRQ */
+static struct irq_info *info_for_irq(unsigned irq)
+{
+ return irq_get_handler_data(irq);
+}
-/* Constructor for packed IRQ information. */
-static struct irq_info mk_unbound_info(void)
+/* Constructors for packed IRQ information. */
+static void xen_irq_info_common_init(struct irq_info *info,
+ unsigned irq,
+ enum xen_irq_type type,
+ unsigned short evtchn,
+ unsigned short cpu)
{
- return (struct irq_info) { .type = IRQT_UNBOUND };
+
+ BUG_ON(info->type != IRQT_UNBOUND && info->type != type);
+
+ info->type = type;
+ info->irq = irq;
+ info->evtchn = evtchn;
+ info->cpu = cpu;
+
+ evtchn_to_irq[evtchn] = irq;
}
-static struct irq_info mk_evtchn_info(unsigned short evtchn)
+static void xen_irq_info_evtchn_init(unsigned irq,
+ unsigned short evtchn)
{
- return (struct irq_info) { .type = IRQT_EVTCHN, .evtchn = evtchn,
- .cpu = 0 };
+ struct irq_info *info = info_for_irq(irq);
+
+ xen_irq_info_common_init(info, irq, IRQT_EVTCHN, evtchn, 0);
}
-static struct irq_info mk_ipi_info(unsigned short evtchn, enum ipi_vector ipi)
+static void xen_irq_info_ipi_init(unsigned cpu,
+ unsigned irq,
+ unsigned short evtchn,
+ enum ipi_vector ipi)
{
- return (struct irq_info) { .type = IRQT_IPI, .evtchn = evtchn,
- .cpu = 0, .u.ipi = ipi };
+ struct irq_info *info = info_for_irq(irq);
+
+ xen_irq_info_common_init(info, irq, IRQT_IPI, evtchn, 0);
+
+ info->u.ipi = ipi;
+
+ per_cpu(ipi_to_irq, cpu)[ipi] = irq;
}
-static struct irq_info mk_virq_info(unsigned short evtchn, unsigned short virq)
+static void xen_irq_info_virq_init(unsigned cpu,
+ unsigned irq,
+ unsigned short evtchn,
+ unsigned short virq)
{
- return (struct irq_info) { .type = IRQT_VIRQ, .evtchn = evtchn,
- .cpu = 0, .u.virq = virq };
+ struct irq_info *info = info_for_irq(irq);
+
+ xen_irq_info_common_init(info, irq, IRQT_VIRQ, evtchn, 0);
+
+ info->u.virq = virq;
+
+ per_cpu(virq_to_irq, cpu)[virq] = irq;
}
-static struct irq_info mk_pirq_info(unsigned short evtchn, unsigned short pirq,
- unsigned short gsi, unsigned short vector)
+static void xen_irq_info_pirq_init(unsigned irq,
+ unsigned short evtchn,
+ unsigned short pirq,
+ unsigned short gsi,
+ unsigned short vector,
+ uint16_t domid,
+ unsigned char flags)
{
- return (struct irq_info) { .type = IRQT_PIRQ, .evtchn = evtchn,
- .cpu = 0,
- .u.pirq = { .pirq = pirq, .gsi = gsi, .vector = vector } };
+ struct irq_info *info = info_for_irq(irq);
+
+ xen_irq_info_common_init(info, irq, IRQT_PIRQ, evtchn, 0);
+
+ info->u.pirq.pirq = pirq;
+ info->u.pirq.gsi = gsi;
+ info->u.pirq.vector = vector;
+ info->u.pirq.domid = domid;
+ info->u.pirq.flags = flags;
}
/*
* Accessors for packed IRQ information.
*/
-static struct irq_info *info_for_irq(unsigned irq)
-{
- return &irq_info[irq];
-}
-
static unsigned int evtchn_from_irq(unsigned irq)
{
if (unlikely(WARN(irq < 0 || irq >= nr_irqs, "Invalid irq %d!\n", irq)))
return info->u.pirq.pirq;
}
-static unsigned gsi_from_irq(unsigned irq)
-{
- struct irq_info *info = info_for_irq(irq);
-
- BUG_ON(info == NULL);
- BUG_ON(info->type != IRQT_PIRQ);
-
- return info->u.pirq.gsi;
-}
-
-static unsigned vector_from_irq(unsigned irq)
-{
- struct irq_info *info = info_for_irq(irq);
-
- BUG_ON(info == NULL);
- BUG_ON(info->type != IRQT_PIRQ);
-
- return info->u.pirq.vector;
-}
-
static enum xen_irq_type type_from_irq(unsigned irq)
{
return info_for_irq(irq)->type;
unsigned int idx)
{
return (sh->evtchn_pending[idx] &
- cpu_evtchn_mask(cpu)[idx] &
+ per_cpu(cpu_evtchn_mask, cpu)[idx] &
~sh->evtchn_mask[idx]);
}
BUG_ON(irq == -1);
#ifdef CONFIG_SMP
- cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu));
+ cpumask_copy(irq_to_desc(irq)->irq_data.affinity, cpumask_of(cpu));
#endif
- clear_bit(chn, cpu_evtchn_mask(cpu_from_irq(irq)));
- set_bit(chn, cpu_evtchn_mask(cpu));
+ clear_bit(chn, per_cpu(cpu_evtchn_mask, cpu_from_irq(irq)));
+ set_bit(chn, per_cpu(cpu_evtchn_mask, cpu));
- irq_info[irq].cpu = cpu;
+ info_for_irq(irq)->cpu = cpu;
}
static void init_evtchn_cpu_bindings(void)
{
int i;
#ifdef CONFIG_SMP
- struct irq_desc *desc;
+ struct irq_info *info;
/* By default all event channels notify CPU#0. */
- for_each_irq_desc(i, desc) {
- cpumask_copy(desc->affinity, cpumask_of(0));
+ list_for_each_entry(info, &xen_irq_list_head, list) {
+ struct irq_desc *desc = irq_to_desc(info->irq);
+ cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
}
#endif
for_each_possible_cpu(i)
- memset(cpu_evtchn_mask(i),
- (i == 0) ? ~0 : 0, sizeof(struct cpu_evtchn_s));
-
+ memset(per_cpu(cpu_evtchn_mask, i),
+ (i == 0) ? ~0 : 0, sizeof(*per_cpu(cpu_evtchn_mask, i)));
}
static inline void clear_evtchn(int port)
put_cpu();
}
-static int get_nr_hw_irqs(void)
+static void xen_irq_init(unsigned irq)
{
- int ret = 1;
+ struct irq_info *info;
+ struct irq_desc *desc = irq_to_desc(irq);
-#ifdef CONFIG_X86_IO_APIC
- ret = get_nr_irqs_gsi();
+#ifdef CONFIG_SMP
+ /* By default all event channels notify CPU#0. */
+ cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
#endif
- return ret;
-}
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (info == NULL)
+ panic("Unable to allocate metadata for IRQ%d\n", irq);
-static int find_unbound_pirq(int type)
-{
- int rc, i;
- struct physdev_get_free_pirq op_get_free_pirq;
- op_get_free_pirq.type = type;
+ info->type = IRQT_UNBOUND;
- rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
- if (!rc)
- return op_get_free_pirq.pirq;
+ irq_set_handler_data(irq, info);
- for (i = 0; i < nr_irqs; i++) {
- if (pirq_to_irq[i] < 0)
- return i;
- }
- return -1;
+ list_add_tail(&info->list, &xen_irq_list_head);
}
-static int find_unbound_irq(void)
+static int __must_check xen_allocate_irq_dynamic(void)
{
- struct irq_data *data;
- int irq, res;
- int bottom = get_nr_hw_irqs();
- int top = nr_irqs-1;
-
- if (bottom == nr_irqs)
- goto no_irqs;
+ int first = 0;
+ int irq;
- /* This loop starts from the top of IRQ space and goes down.
- * We need this b/c if we have a PCI device in a Xen PV guest
- * we do not have an IO-APIC (though the backend might have them)
- * mapped in. To not have a collision of physical IRQs with the Xen
- * event channels start at the top of the IRQ space for virtual IRQs.
+#ifdef CONFIG_X86_IO_APIC
+ /*
+ * For an HVM guest or domain 0 which see "real" (emulated or
+ * actual respectively) GSIs we allocate dynamic IRQs
+ * e.g. those corresponding to event channels or MSIs
+ * etc. from the range above those "real" GSIs to avoid
+ * collisions.
*/
- for (irq = top; irq > bottom; irq--) {
- data = irq_get_irq_data(irq);
- /* only 15->0 have init'd desc; handle irq > 16 */
- if (!data)
- break;
- if (data->chip == &no_irq_chip)
- break;
- if (data->chip != &xen_dynamic_chip)
- continue;
- if (irq_info[irq].type == IRQT_UNBOUND)
- return irq;
- }
-
- if (irq == bottom)
- goto no_irqs;
+ if (xen_initial_domain() || xen_hvm_domain())
+ first = get_nr_irqs_gsi();
+#endif
- res = irq_alloc_desc_at(irq, -1);
+ irq = irq_alloc_desc_from(first, -1);
- if (WARN_ON(res != irq))
- return -1;
+ xen_irq_init(irq);
return irq;
-
-no_irqs:
- panic("No available IRQ to bind to: increase nr_irqs!\n");
}
-static bool identity_mapped_irq(unsigned irq)
+static int __must_check xen_allocate_irq_gsi(unsigned gsi)
{
- /* identity map all the hardware irqs */
- return irq < get_nr_hw_irqs();
+ int irq;
+
+ /*
+ * A PV guest has no concept of a GSI (since it has no ACPI
+ * nor access to/knowledge of the physical APICs). Therefore
+ * all IRQs are dynamically allocated from the entire IRQ
+ * space.
+ */
+ if (xen_pv_domain() && !xen_initial_domain())
+ return xen_allocate_irq_dynamic();
+
+ /* Legacy IRQ descriptors are already allocated by the arch. */
+ if (gsi < NR_IRQS_LEGACY)
+ irq = gsi;
+ else
+ irq = irq_alloc_desc_at(gsi, -1);
+
+ xen_irq_init(irq);
+
+ return irq;
}
-static void pirq_unmask_notify(int irq)
+static void xen_free_irq(unsigned irq)
{
- struct physdev_eoi eoi = { .irq = pirq_from_irq(irq) };
+ struct irq_info *info = irq_get_handler_data(irq);
- if (unlikely(pirq_needs_eoi(irq))) {
- int rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
- WARN_ON(rc);
- }
+ list_del(&info->list);
+
+ irq_set_handler_data(irq, NULL);
+
+ kfree(info);
+
+ /* Legacy IRQ descriptors are managed by the arch. */
+ if (irq < NR_IRQS_LEGACY)
+ return;
+
+ irq_free_desc(irq);
}
static void pirq_query_unmask(int irq)
return desc && desc->action == NULL;
}
-static unsigned int startup_pirq(unsigned int irq)
+static void eoi_pirq(struct irq_data *data)
+{
+ int evtchn = evtchn_from_irq(data->irq);
+ struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
+ int rc = 0;
+
+ irq_move_irq(data);
+
+ if (VALID_EVTCHN(evtchn))
+ clear_evtchn(evtchn);
+
+ if (pirq_needs_eoi(data->irq)) {
+ rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
+ WARN_ON(rc);
+ }
+}
+
+static void mask_ack_pirq(struct irq_data *data)
+{
+ disable_dynirq(data);
+ eoi_pirq(data);
+}
+
+static unsigned int __startup_pirq(unsigned int irq)
{
struct evtchn_bind_pirq bind_pirq;
struct irq_info *info = info_for_irq(irq);
out:
unmask_evtchn(evtchn);
- pirq_unmask_notify(irq);
+ eoi_pirq(irq_get_irq_data(irq));
return 0;
}
-static void shutdown_pirq(unsigned int irq)
+static unsigned int startup_pirq(struct irq_data *data)
+{
+ return __startup_pirq(data->irq);
+}
+
+static void shutdown_pirq(struct irq_data *data)
{
struct evtchn_close close;
+ unsigned int irq = data->irq;
struct irq_info *info = info_for_irq(irq);
int evtchn = evtchn_from_irq(irq);
info->evtchn = 0;
}
-static void enable_pirq(unsigned int irq)
+static void enable_pirq(struct irq_data *data)
{
- startup_pirq(irq);
+ startup_pirq(data);
}
-static void disable_pirq(unsigned int irq)
+static void disable_pirq(struct irq_data *data)
{
-}
-
-static void ack_pirq(unsigned int irq)
-{
- int evtchn = evtchn_from_irq(irq);
-
- move_native_irq(irq);
-
- if (VALID_EVTCHN(evtchn)) {
- mask_evtchn(evtchn);
- clear_evtchn(evtchn);
- }
-}
-
-static void end_pirq(unsigned int irq)
-{
- int evtchn = evtchn_from_irq(irq);
- struct irq_desc *desc = irq_to_desc(irq);
-
- if (WARN_ON(!desc))
- return;
-
- if ((desc->status & (IRQ_DISABLED|IRQ_PENDING)) ==
- (IRQ_DISABLED|IRQ_PENDING)) {
- shutdown_pirq(irq);
- } else if (VALID_EVTCHN(evtchn)) {
- unmask_evtchn(evtchn);
- pirq_unmask_notify(irq);
- }
+ disable_dynirq(data);
}
static int find_irq_by_gsi(unsigned gsi)
{
- int irq;
-
- for (irq = 0; irq < nr_irqs; irq++) {
- struct irq_info *info = info_for_irq(irq);
+ struct irq_info *info;
- if (info == NULL || info->type != IRQT_PIRQ)
+ list_for_each_entry(info, &xen_irq_list_head, list) {
+ if (info->type != IRQT_PIRQ)
continue;
- if (gsi_from_irq(irq) == gsi)
- return irq;
+ if (info->u.pirq.gsi == gsi)
+ return info->irq;
}
return -1;
}
-int xen_allocate_pirq(unsigned gsi, int shareable, char *name)
+int xen_allocate_pirq_gsi(unsigned gsi)
{
- return xen_map_pirq_gsi(gsi, gsi, shareable, name);
+ return gsi;
}
-/* xen_map_pirq_gsi might allocate irqs from the top down, as a
- * consequence don't assume that the irq number returned has a low value
- * or can be used as a pirq number unless you know otherwise.
- *
- * One notable exception is when xen_map_pirq_gsi is called passing an
- * hardware gsi as argument, in that case the irq number returned
- * matches the gsi number passed as second argument.
+/*
+ * Do not make any assumptions regarding the relationship between the
+ * IRQ number returned here and the Xen pirq argument.
*
* Note: We don't assign an event channel until the irq actually started
* up. Return an existing irq if we've already got one for the gsi.
*/
-int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name)
+int xen_bind_pirq_gsi_to_irq(unsigned gsi,
+ unsigned pirq, int shareable, char *name)
{
- int irq = 0;
+ int irq = -1;
struct physdev_irq irq_op;
spin_lock(&irq_mapping_update_lock);
- if ((pirq > nr_irqs) || (gsi > nr_irqs)) {
- printk(KERN_WARNING "xen_map_pirq_gsi: %s %s is incorrect!\n",
- pirq > nr_irqs ? "pirq" :"",
- gsi > nr_irqs ? "gsi" : "");
- goto out;
- }
-
irq = find_irq_by_gsi(gsi);
if (irq != -1) {
printk(KERN_INFO "xen_map_pirq_gsi: returning irq %d for gsi %u\n",
goto out; /* XXX need refcount? */
}
- /* If we are a PV guest, we don't have GSIs (no ACPI passed). Therefore
- * we are using the !xen_initial_domain() to drop in the function.*/
- if (identity_mapped_irq(gsi) || (!xen_initial_domain() &&
- xen_pv_domain())) {
- irq = gsi;
- irq_alloc_desc_at(irq, -1);
- } else
- irq = find_unbound_irq();
-
- set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
- handle_level_irq, name);
+ irq = xen_allocate_irq_gsi(gsi);
+ if (irq < 0)
+ goto out;
irq_op.irq = irq;
irq_op.vector = 0;
* this in the priv domain. */
if (xen_initial_domain() &&
HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
- irq_free_desc(irq);
+ xen_free_irq(irq);
irq = -ENOSPC;
goto out;
}
- irq_info[irq] = mk_pirq_info(0, pirq, gsi, irq_op.vector);
- irq_info[irq].u.pirq.flags |= shareable ? PIRQ_SHAREABLE : 0;
- pirq_to_irq[pirq] = irq;
+ xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, DOMID_SELF,
+ shareable ? PIRQ_SHAREABLE : 0);
+
+ pirq_query_unmask(irq);
+ /* We try to use the handler with the appropriate semantic for the
+ * type of interrupt: if the interrupt doesn't need an eoi
+ * (pirq_needs_eoi returns false), we treat it like an edge
+ * triggered interrupt so we use handle_edge_irq.
+ * As a matter of fact this only happens when the corresponding
+ * physical interrupt is edge triggered or an msi.
+ *
+ * On the other hand if the interrupt needs an eoi (pirq_needs_eoi
+ * returns true) we treat it like a level triggered interrupt so we
+ * use handle_fasteoi_irq like the native code does for this kind of
+ * interrupts.
+ * Depending on the Xen version, pirq_needs_eoi might return true
+ * not only for level triggered interrupts but for edge triggered
+ * interrupts too. In any case Xen always honors the eoi mechanism,
+ * not injecting any more pirqs of the same kind if the first one
+ * hasn't received an eoi yet. Therefore using the fasteoi handler
+ * is the right choice either way.
+ */
+ if (pirq_needs_eoi(irq))
+ irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+ handle_fasteoi_irq, name);
+ else
+ irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+ handle_edge_irq, name);
out:
spin_unlock(&irq_mapping_update_lock);
}
#ifdef CONFIG_PCI_MSI
-#include <linux/msi.h>
-#include "../pci/msi.h"
-
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc)
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
{
- spin_lock(&irq_mapping_update_lock);
-
- if (alloc & XEN_ALLOC_IRQ) {
- *irq = find_unbound_irq();
- if (*irq == -1)
- goto out;
- }
-
- if (alloc & XEN_ALLOC_PIRQ) {
- *pirq = find_unbound_pirq(MAP_PIRQ_TYPE_MSI);
- if (*pirq == -1)
- goto out;
- }
+ int rc;
+ struct physdev_get_free_pirq op_get_free_pirq;
- set_irq_chip_and_handler_name(*irq, &xen_pirq_chip,
- handle_level_irq, name);
+ op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI;
+ rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
- irq_info[*irq] = mk_pirq_info(0, *pirq, 0, 0);
- pirq_to_irq[*pirq] = *irq;
+ WARN_ONCE(rc == -ENOSYS,
+ "hypervisor does not support the PHYSDEVOP_get_free_pirq interface\n");
-out:
- spin_unlock(&irq_mapping_update_lock);
+ return rc ? -1 : op_get_free_pirq.pirq;
}
-int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type)
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+ int pirq, int vector, const char *name,
+ domid_t domid)
{
- int irq = -1;
- struct physdev_map_pirq map_irq;
- int rc;
- int pos;
- u32 table_offset, bir;
-
- memset(&map_irq, 0, sizeof(map_irq));
- map_irq.domid = DOMID_SELF;
- map_irq.type = MAP_PIRQ_TYPE_MSI;
- map_irq.index = -1;
- map_irq.pirq = -1;
- map_irq.bus = dev->bus->number;
- map_irq.devfn = dev->devfn;
-
- if (type == PCI_CAP_ID_MSIX) {
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-
- pci_read_config_dword(dev, msix_table_offset_reg(pos),
- &table_offset);
- bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
-
- map_irq.table_base = pci_resource_start(dev, bir);
- map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
- }
+ int irq, ret;
spin_lock(&irq_mapping_update_lock);
- irq = find_unbound_irq();
-
+ irq = xen_allocate_irq_dynamic();
if (irq == -1)
goto out;
- rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
- if (rc) {
- printk(KERN_WARNING "xen map irq failed %d\n", rc);
-
- irq_free_desc(irq);
-
- irq = -1;
- goto out;
- }
- irq_info[irq] = mk_pirq_info(0, map_irq.pirq, 0, map_irq.index);
-
- set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
- handle_level_irq,
- (type == PCI_CAP_ID_MSIX) ? "msi-x":"msi");
+ irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
+ name);
+ xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, domid, 0);
+ ret = irq_set_msi_desc(irq, msidesc);
+ if (ret < 0)
+ goto error_irq;
out:
spin_unlock(&irq_mapping_update_lock);
return irq;
+error_irq:
+ spin_unlock(&irq_mapping_update_lock);
+ xen_free_irq(irq);
+ return -1;
}
#endif
if (xen_initial_domain()) {
unmap_irq.pirq = info->u.pirq.pirq;
- unmap_irq.domid = DOMID_SELF;
+ unmap_irq.domid = info->u.pirq.domid;
rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);
- if (rc) {
+ /* If another domain quits without making the pci_disable_msix
+ * call, the Xen hypervisor takes care of freeing the PIRQs
+ * (free_domain_pirqs).
+ */
+ if ((rc == -ESRCH && info->u.pirq.domid != DOMID_SELF))
+ printk(KERN_INFO "domain %d does not have %d anymore\n",
+ info->u.pirq.domid, info->u.pirq.pirq);
+ else if (rc) {
printk(KERN_WARNING "unmap irq failed %d\n", rc);
goto out;
}
- pirq_to_irq[info->u.pirq.pirq] = -1;
}
- irq_info[irq] = mk_unbound_info();
- irq_free_desc(irq);
+ xen_free_irq(irq);
out:
spin_unlock(&irq_mapping_update_lock);
return rc;
}
-int xen_vector_from_irq(unsigned irq)
+int xen_irq_from_pirq(unsigned pirq)
{
- return vector_from_irq(irq);
-}
+ int irq;
-int xen_gsi_from_irq(unsigned irq)
-{
- return gsi_from_irq(irq);
+ struct irq_info *info;
+
+ spin_lock(&irq_mapping_update_lock);
+
+ list_for_each_entry(info, &xen_irq_list_head, list) {
+ if (info == NULL || info->type != IRQT_PIRQ)
+ continue;
+ irq = info->irq;
+ if (info->u.pirq.pirq == pirq)
+ goto out;
+ }
+ irq = -1;
+out:
+ spin_unlock(&irq_mapping_update_lock);
+
+ return irq;
}
-int xen_irq_from_pirq(unsigned pirq)
+
+int xen_pirq_from_irq(unsigned irq)
{
- return pirq_to_irq[pirq];
+ return pirq_from_irq(irq);
}
-
+EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
int bind_evtchn_to_irq(unsigned int evtchn)
{
int irq;
irq = evtchn_to_irq[evtchn];
if (irq == -1) {
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_dynamic();
+ if (irq == -1)
+ goto out;
- set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
- handle_fasteoi_irq, "event");
+ irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
+ handle_edge_irq, "event");
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_evtchn_info(evtchn);
+ xen_irq_info_evtchn_init(irq, evtchn);
}
+out:
spin_unlock(&irq_mapping_update_lock);
return irq;
irq = per_cpu(ipi_to_irq, cpu)[ipi];
if (irq == -1) {
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_dynamic();
if (irq < 0)
goto out;
- set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
+ irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
handle_percpu_irq, "ipi");
bind_ipi.vcpu = cpu;
BUG();
evtchn = bind_ipi.port;
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_ipi_info(evtchn, ipi);
- per_cpu(ipi_to_irq, cpu)[ipi] = irq;
+ xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
bind_evtchn_to_cpu(evtchn, cpu);
}
return irq;
}
+static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+ unsigned int remote_port)
+{
+ struct evtchn_bind_interdomain bind_interdomain;
+ int err;
+
+ bind_interdomain.remote_dom = remote_domain;
+ bind_interdomain.remote_port = remote_port;
+
+ err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+ &bind_interdomain);
+
+ return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
+}
+
int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
{
irq = per_cpu(virq_to_irq, cpu)[virq];
if (irq == -1) {
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_dynamic();
+ if (irq == -1)
+ goto out;
- set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
+ irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
handle_percpu_irq, "virq");
bind_virq.virq = virq;
BUG();
evtchn = bind_virq.port;
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_virq_info(evtchn, virq);
-
- per_cpu(virq_to_irq, cpu)[virq] = irq;
+ xen_irq_info_virq_init(cpu, irq, evtchn, virq);
bind_evtchn_to_cpu(evtchn, cpu);
}
+out:
spin_unlock(&irq_mapping_update_lock);
return irq;
evtchn_to_irq[evtchn] = -1;
}
- if (irq_info[irq].type != IRQT_UNBOUND) {
- irq_info[irq] = mk_unbound_info();
+ BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
- irq_free_desc(irq);
- }
+ xen_free_irq(irq);
spin_unlock(&irq_mapping_update_lock);
}
unsigned long irqflags,
const char *devname, void *dev_id)
{
- unsigned int irq;
- int retval;
+ int irq, retval;
irq = bind_evtchn_to_irq(evtchn);
+ if (irq < 0)
+ return irq;
retval = request_irq(irq, handler, irqflags, devname, dev_id);
if (retval != 0) {
unbind_from_irq(irq);
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);
+int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
+ unsigned int remote_port,
+ irq_handler_t handler,
+ unsigned long irqflags,
+ const char *devname,
+ void *dev_id)
+{
+ int irq, retval;
+
+ irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port);
+ if (irq < 0)
+ return irq;
+
+ retval = request_irq(irq, handler, irqflags, devname, dev_id);
+ if (retval != 0) {
+ unbind_from_irq(irq);
+ return retval;
+ }
+
+ return irq;
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler);
+
int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
irq_handler_t handler,
unsigned long irqflags, const char *devname, void *dev_id)
{
- unsigned int irq;
- int retval;
+ int irq, retval;
irq = bind_virq_to_irq(virq, cpu);
+ if (irq < 0)
+ return irq;
retval = request_irq(irq, handler, irqflags, devname, dev_id);
if (retval != 0) {
unbind_from_irq(irq);
if (irq < 0)
return irq;
- irqflags |= IRQF_NO_SUSPEND;
+ irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME;
retval = request_irq(irq, handler, irqflags, devname, dev_id);
if (retval != 0) {
unbind_from_irq(irq);
{
struct shared_info *sh = HYPERVISOR_shared_info;
int cpu = smp_processor_id();
- unsigned long *cpu_evtchn = cpu_evtchn_mask(cpu);
+ unsigned long *cpu_evtchn = per_cpu(cpu_evtchn_mask, cpu);
int i;
unsigned long flags;
static DEFINE_SPINLOCK(debug_lock);
}
static DEFINE_PER_CPU(unsigned, xed_nesting_count);
+static DEFINE_PER_CPU(unsigned int, current_word_idx);
+static DEFINE_PER_CPU(unsigned int, current_bit_idx);
+
+/*
+ * Mask out the i least significant bits of w
+ */
+#define MASK_LSBS(w, i) (w & ((~0UL) << i))
/*
* Search the CPUs pending events bitmasks. For each one found, map
*/
static void __xen_evtchn_do_upcall(void)
{
+ int start_word_idx, start_bit_idx;
+ int word_idx, bit_idx;
+ int i;
int cpu = get_cpu();
struct shared_info *s = HYPERVISOR_shared_info;
struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
wmb();
#endif
pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);
- while (pending_words != 0) {
+
+ start_word_idx = __this_cpu_read(current_word_idx);
+ start_bit_idx = __this_cpu_read(current_bit_idx);
+
+ word_idx = start_word_idx;
+
+ for (i = 0; pending_words != 0; i++) {
unsigned long pending_bits;
- int word_idx = __ffs(pending_words);
- pending_words &= ~(1UL << word_idx);
+ unsigned long words;
+
+ words = MASK_LSBS(pending_words, word_idx);
+
+ /*
+ * If we masked out all events, wrap to beginning.
+ */
+ if (words == 0) {
+ word_idx = 0;
+ bit_idx = 0;
+ continue;
+ }
+ word_idx = __ffs(words);
+
+ pending_bits = active_evtchns(cpu, s, word_idx);
+ bit_idx = 0; /* usually scan entire word from start */
+ if (word_idx == start_word_idx) {
+ /* We scan the starting word in two parts */
+ if (i == 0)
+ /* 1st time: start in the middle */
+ bit_idx = start_bit_idx;
+ else
+ /* 2nd time: mask bits done already */
+ bit_idx &= (1UL << start_bit_idx) - 1;
+ }
- while ((pending_bits = active_evtchns(cpu, s, word_idx)) != 0) {
- int bit_idx = __ffs(pending_bits);
- int port = (word_idx * BITS_PER_LONG) + bit_idx;
- int irq = evtchn_to_irq[port];
+ do {
+ unsigned long bits;
+ int port, irq;
struct irq_desc *desc;
- mask_evtchn(port);
- clear_evtchn(port);
+ bits = MASK_LSBS(pending_bits, bit_idx);
+
+ /* If we masked out all events, move on. */
+ if (bits == 0)
+ break;
+
+ bit_idx = __ffs(bits);
+
+ /* Process port. */
+ port = (word_idx * BITS_PER_LONG) + bit_idx;
+ irq = evtchn_to_irq[port];
if (irq != -1) {
desc = irq_to_desc(irq);
if (desc)
generic_handle_irq_desc(irq, desc);
}
- }
+
+ bit_idx = (bit_idx + 1) % BITS_PER_LONG;
+
+ /* Next caller starts at last processed + 1 */
+ __this_cpu_write(current_word_idx,
+ bit_idx ? word_idx :
+ (word_idx+1) % BITS_PER_LONG);
+ __this_cpu_write(current_bit_idx, bit_idx);
+ } while (bit_idx != 0);
+
+ /* Scan start_l1i twice; all others once. */
+ if ((word_idx != start_word_idx) || (i != 0))
+ pending_words &= ~(1UL << word_idx);
+
+ word_idx = (word_idx + 1) % BITS_PER_LONG;
}
BUG_ON(!irqs_disabled());
so there should be a proper type */
BUG_ON(info->type == IRQT_UNBOUND);
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_evtchn_info(evtchn);
+ xen_irq_info_evtchn_init(irq, evtchn);
spin_unlock(&irq_mapping_update_lock);
struct evtchn_bind_vcpu bind_vcpu;
int evtchn = evtchn_from_irq(irq);
- /* events delivered via platform PCI interrupts are always
- * routed to vcpu 0 */
- if (!VALID_EVTCHN(evtchn) ||
- (xen_hvm_domain() && !xen_have_vector_callback))
+ if (!VALID_EVTCHN(evtchn))
+ return -1;
+
+ /*
+ * Events delivered via platform PCI interrupts are always
+ * routed to vcpu 0 and hence cannot be rebound.
+ */
+ if (xen_hvm_domain() && !xen_have_vector_callback)
return -1;
/* Send future instances of this interrupt to other vcpu. */
return 0;
}
-static int set_affinity_irq(unsigned irq, const struct cpumask *dest)
+static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
+ bool force)
{
unsigned tcpu = cpumask_first(dest);
- return rebind_irq_to_cpu(irq, tcpu);
+ return rebind_irq_to_cpu(data->irq, tcpu);
}
int resend_irq_on_evtchn(unsigned int irq)
return 1;
}
-static void enable_dynirq(unsigned int irq)
+static void enable_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
if (VALID_EVTCHN(evtchn))
unmask_evtchn(evtchn);
}
-static void disable_dynirq(unsigned int irq)
+static void disable_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
if (VALID_EVTCHN(evtchn))
mask_evtchn(evtchn);
}
-static void ack_dynirq(unsigned int irq)
+static void ack_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
- move_masked_irq(irq);
+ irq_move_irq(data);
if (VALID_EVTCHN(evtchn))
- unmask_evtchn(evtchn);
+ clear_evtchn(evtchn);
}
-static int retrigger_dynirq(unsigned int irq)
+static void mask_ack_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ disable_dynirq(data);
+ ack_dynirq(data);
+}
+
+static int retrigger_dynirq(struct irq_data *data)
+{
+ int evtchn = evtchn_from_irq(data->irq);
struct shared_info *sh = HYPERVISOR_shared_info;
int ret = 0;
return ret;
}
-static void restore_cpu_pirqs(void)
+static void restore_pirqs(void)
{
int pirq, rc, irq, gsi;
struct physdev_map_pirq map_irq;
+ struct irq_info *info;
- for (pirq = 0; pirq < nr_irqs; pirq++) {
- irq = pirq_to_irq[pirq];
- if (irq == -1)
+ list_for_each_entry(info, &xen_irq_list_head, list) {
+ if (info->type != IRQT_PIRQ)
continue;
+ pirq = info->u.pirq.pirq;
+ gsi = info->u.pirq.gsi;
+ irq = info->irq;
+
/* save/restore of PT devices doesn't work, so at this point the
* only devices present are GSI based emulated devices */
- gsi = gsi_from_irq(irq);
if (!gsi)
continue;
if (rc) {
printk(KERN_WARNING "xen map irq failed gsi=%d irq=%d pirq=%d rc=%d\n",
gsi, irq, pirq, rc);
- irq_info[irq] = mk_unbound_info();
- pirq_to_irq[pirq] = -1;
+ xen_free_irq(irq);
continue;
}
printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);
- startup_pirq(irq);
+ __startup_pirq(irq);
}
}
evtchn = bind_virq.port;
/* Record the new mapping. */
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_virq_info(evtchn, virq);
+ xen_irq_info_virq_init(cpu, irq, evtchn, virq);
bind_evtchn_to_cpu(evtchn, cpu);
}
}
evtchn = bind_ipi.port;
/* Record the new mapping. */
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_ipi_info(evtchn, ipi);
+ xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
bind_evtchn_to_cpu(evtchn, cpu);
}
}
xen_poll_irq_timeout(irq, 0 /* no timeout */);
}
+/* Check whether the IRQ line is shared with other guests. */
+int xen_test_irq_shared(int irq)
+{
+ struct irq_info *info = info_for_irq(irq);
+ struct physdev_irq_status_query irq_status = { .irq = info->u.pirq.pirq };
+
+ if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
+ return 0;
+ return !(irq_status.flags & XENIRQSTAT_shared);
+}
+EXPORT_SYMBOL_GPL(xen_test_irq_shared);
+
void xen_irq_resume(void)
{
- unsigned int cpu, irq, evtchn;
- struct irq_desc *desc;
+ unsigned int cpu, evtchn;
+ struct irq_info *info;
init_evtchn_cpu_bindings();
mask_evtchn(evtchn);
/* No IRQ <-> event-channel mappings. */
- for (irq = 0; irq < nr_irqs; irq++)
- irq_info[irq].evtchn = 0; /* zap event-channel binding */
+ list_for_each_entry(info, &xen_irq_list_head, list)
+ info->evtchn = 0; /* zap event-channel binding */
for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
evtchn_to_irq[evtchn] = -1;
restore_cpu_ipis(cpu);
}
- /*
- * Unmask any IRQF_NO_SUSPEND IRQs which are enabled. These
- * are not handled by the IRQ core.
- */
- for_each_irq_desc(irq, desc) {
- if (!desc->action || !(desc->action->flags & IRQF_NO_SUSPEND))
- continue;
- if (desc->status & IRQ_DISABLED)
- continue;
-
- evtchn = evtchn_from_irq(irq);
- if (evtchn == -1)
- continue;
-
- unmask_evtchn(evtchn);
- }
-
- restore_cpu_pirqs();
+ restore_pirqs();
}
static struct irq_chip xen_dynamic_chip __read_mostly = {
- .name = "xen-dyn",
+ .name = "xen-dyn",
- .disable = disable_dynirq,
- .mask = disable_dynirq,
- .unmask = enable_dynirq,
+ .irq_disable = disable_dynirq,
+ .irq_mask = disable_dynirq,
+ .irq_unmask = enable_dynirq,
- .eoi = ack_dynirq,
- .set_affinity = set_affinity_irq,
- .retrigger = retrigger_dynirq,
+ .irq_ack = ack_dynirq,
+ .irq_mask_ack = mask_ack_dynirq,
+
+ .irq_set_affinity = set_affinity_irq,
+ .irq_retrigger = retrigger_dynirq,
};
static struct irq_chip xen_pirq_chip __read_mostly = {
- .name = "xen-pirq",
-
- .startup = startup_pirq,
- .shutdown = shutdown_pirq,
+ .name = "xen-pirq",
- .enable = enable_pirq,
- .unmask = enable_pirq,
+ .irq_startup = startup_pirq,
+ .irq_shutdown = shutdown_pirq,
+ .irq_enable = enable_pirq,
+ .irq_disable = disable_pirq,
- .disable = disable_pirq,
- .mask = disable_pirq,
+ .irq_mask = disable_dynirq,
+ .irq_unmask = enable_dynirq,
- .ack = ack_pirq,
- .end = end_pirq,
+ .irq_ack = eoi_pirq,
+ .irq_eoi = eoi_pirq,
+ .irq_mask_ack = mask_ack_pirq,
- .set_affinity = set_affinity_irq,
+ .irq_set_affinity = set_affinity_irq,
- .retrigger = retrigger_dynirq,
+ .irq_retrigger = retrigger_dynirq,
};
static struct irq_chip xen_percpu_chip __read_mostly = {
- .name = "xen-percpu",
+ .name = "xen-percpu",
- .disable = disable_dynirq,
- .mask = disable_dynirq,
- .unmask = enable_dynirq,
+ .irq_disable = disable_dynirq,
+ .irq_mask = disable_dynirq,
+ .irq_unmask = enable_dynirq,
- .ack = ack_dynirq,
+ .irq_ack = ack_dynirq,
};
int xen_set_callback_via(uint64_t via)
{
int i;
- cpu_evtchn_mask_p = kcalloc(nr_cpu_ids, sizeof(struct cpu_evtchn_s),
- GFP_KERNEL);
- irq_info = kcalloc(nr_irqs, sizeof(*irq_info), GFP_KERNEL);
-
- /* We are using nr_irqs as the maximum number of pirq available but
- * that number is actually chosen by Xen and we don't know exactly
- * what it is. Be careful choosing high pirq numbers. */
- pirq_to_irq = kcalloc(nr_irqs, sizeof(*pirq_to_irq), GFP_KERNEL);
- for (i = 0; i < nr_irqs; i++)
- pirq_to_irq[i] = -1;
-
evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
GFP_KERNEL);
for (i = 0; i < NR_EVENT_CHANNELS; i++)
git.openpandora.org / pandora-kernel.git / blobdiff