OpenCloudOS-Kernel/drivers/xen/events.c

1639 lines
37 KiB
C
Raw Normal View History

/*
* Xen event channels
*
* Xen models interrupts with abstract event channels. Because each
* 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
* through the normal interrupt processing path.
*
* There are four kinds of events which can be mapped to an event
* channel:
*
* 1. Inter-domain notifications. This includes all the virtual
* device events, since they're driven by front-ends in another domain
* (typically dom0).
* 2. VIRQs, typically used for timers. These are per-cpu events.
* 3. IPIs.
* 4. PIRQs - Hardware interrupts.
*
* Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
*/
#include <linux/linkage.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/bootmem.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/irqnr.h>
#include <linux/pci.h>
#include <asm/desc.h>
#include <asm/ptrace.h>
#include <asm/irq.h>
#include <asm/idle.h>
#include <asm/io_apic.h>
#include <asm/sync_bitops.h>
#include <asm/xen/pci.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include <xen/xen.h>
#include <xen/hvm.h>
#include <xen/xen-ops.h>
#include <xen/events.h>
#include <xen/interface/xen.h>
#include <xen/interface/event_channel.h>
#include <xen/interface/hvm/hvm_op.h>
#include <xen/interface/hvm/params.h>
/*
* This lock protects updates to the following mapping and reference-count
* arrays. The lock does not need to be acquired to read the mapping tables.
*/
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};
/* IRQ <-> IPI mapping */
static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
/* Interrupt types. */
enum xen_irq_type {
IRQT_UNBOUND = 0,
IRQT_PIRQ,
IRQT_VIRQ,
IRQT_IPI,
IRQT_EVTCHN
};
/*
* Packed IRQ information:
* type - enum xen_irq_type
* event channel - irq->event channel mapping
* cpu - cpu this event channel is bound to
* index - type-specific information:
* PIRQ - vector, with MSB being "needs EIO", or physical IRQ of the HVM
* guest, or GSI (real passthrough IRQ) of the device.
* VIRQ - virq number
* IPI - IPI vector
* EVTCHN -
*/
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 */
union {
unsigned short virq;
enum ipi_vector ipi;
struct {
unsigned short pirq;
unsigned short gsi;
unsigned char vector;
unsigned char flags;
} pirq;
} u;
};
#define PIRQ_NEEDS_EOI (1 << 0)
#define PIRQ_SHAREABLE (1 << 1)
static int *evtchn_to_irq;
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;
/* Get info for IRQ */
static struct irq_info *info_for_irq(unsigned irq)
{
return get_irq_data(irq);
}
/* 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)
{
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 void xen_irq_info_evtchn_init(unsigned irq,
unsigned short evtchn)
{
struct irq_info *info = info_for_irq(irq);
xen_irq_info_common_init(info, irq, IRQT_EVTCHN, evtchn, 0);
}
static void xen_irq_info_ipi_init(unsigned cpu,
unsigned irq,
unsigned short evtchn,
enum ipi_vector 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 void xen_irq_info_virq_init(unsigned cpu,
unsigned irq,
unsigned short evtchn,
unsigned short 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 void xen_irq_info_pirq_init(unsigned irq,
unsigned short evtchn,
unsigned short pirq,
unsigned short gsi,
unsigned short vector,
unsigned char flags)
{
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.flags = flags;
}
/*
* Accessors for packed IRQ information.
*/
static unsigned int evtchn_from_irq(unsigned irq)
{
if (unlikely(WARN(irq < 0 || irq >= nr_irqs, "Invalid irq %d!\n", irq)))
return 0;
return info_for_irq(irq)->evtchn;
}
unsigned irq_from_evtchn(unsigned int evtchn)
{
return evtchn_to_irq[evtchn];
}
EXPORT_SYMBOL_GPL(irq_from_evtchn);
static enum ipi_vector ipi_from_irq(unsigned irq)
{
struct irq_info *info = info_for_irq(irq);
BUG_ON(info == NULL);
BUG_ON(info->type != IRQT_IPI);
return info->u.ipi;
}
static unsigned virq_from_irq(unsigned irq)
{
struct irq_info *info = info_for_irq(irq);
BUG_ON(info == NULL);
BUG_ON(info->type != IRQT_VIRQ);
return info->u.virq;
}
static unsigned pirq_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.pirq;
}
static enum xen_irq_type type_from_irq(unsigned irq)
{
return info_for_irq(irq)->type;
}
static unsigned cpu_from_irq(unsigned irq)
{
return info_for_irq(irq)->cpu;
}
static unsigned int cpu_from_evtchn(unsigned int evtchn)
{
int irq = evtchn_to_irq[evtchn];
unsigned ret = 0;
if (irq != -1)
ret = cpu_from_irq(irq);
return ret;
}
static bool pirq_needs_eoi(unsigned irq)
{
struct irq_info *info = info_for_irq(irq);
BUG_ON(info->type != IRQT_PIRQ);
return info->u.pirq.flags & PIRQ_NEEDS_EOI;
}
static inline unsigned long active_evtchns(unsigned int cpu,
struct shared_info *sh,
unsigned int idx)
{
return (sh->evtchn_pending[idx] &
per_cpu(cpu_evtchn_mask, cpu)[idx] &
~sh->evtchn_mask[idx]);
}
static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
{
int irq = evtchn_to_irq[chn];
BUG_ON(irq == -1);
#ifdef CONFIG_SMP
cpumask_copy(irq_to_desc(irq)->irq_data.affinity, cpumask_of(cpu));
#endif
clear_bit(chn, per_cpu(cpu_evtchn_mask, cpu_from_irq(irq)));
set_bit(chn, per_cpu(cpu_evtchn_mask, cpu));
info_for_irq(irq)->cpu = cpu;
}
static void init_evtchn_cpu_bindings(void)
{
int i;
#ifdef CONFIG_SMP
struct irq_info *info;
/* By default all event channels notify CPU#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(per_cpu(cpu_evtchn_mask, i),
(i == 0) ? ~0 : 0, sizeof(*per_cpu(cpu_evtchn_mask, i)));
}
static inline void clear_evtchn(int port)
{
struct shared_info *s = HYPERVISOR_shared_info;
sync_clear_bit(port, &s->evtchn_pending[0]);
}
static inline void set_evtchn(int port)
{
struct shared_info *s = HYPERVISOR_shared_info;
sync_set_bit(port, &s->evtchn_pending[0]);
}
static inline int test_evtchn(int port)
{
struct shared_info *s = HYPERVISOR_shared_info;
return sync_test_bit(port, &s->evtchn_pending[0]);
}
/**
* notify_remote_via_irq - send event to remote end of event channel via irq
* @irq: irq of event channel to send event to
*
* Unlike notify_remote_via_evtchn(), this is safe to use across
* save/restore. Notifications on a broken connection are silently
* dropped.
*/
void notify_remote_via_irq(int irq)
{
int evtchn = evtchn_from_irq(irq);
if (VALID_EVTCHN(evtchn))
notify_remote_via_evtchn(evtchn);
}
EXPORT_SYMBOL_GPL(notify_remote_via_irq);
static void mask_evtchn(int port)
{
struct shared_info *s = HYPERVISOR_shared_info;
sync_set_bit(port, &s->evtchn_mask[0]);
}
static void unmask_evtchn(int port)
{
struct shared_info *s = HYPERVISOR_shared_info;
unsigned int cpu = get_cpu();
BUG_ON(!irqs_disabled());
/* Slow path (hypercall) if this is a non-local port. */
if (unlikely(cpu != cpu_from_evtchn(port))) {
struct evtchn_unmask unmask = { .port = port };
(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
} else {
struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
sync_clear_bit(port, &s->evtchn_mask[0]);
/*
* The following is basically the equivalent of
* 'hw_resend_irq'. Just like a real IO-APIC we 'lose
* the interrupt edge' if the channel is masked.
*/
if (sync_test_bit(port, &s->evtchn_pending[0]) &&
!sync_test_and_set_bit(port / BITS_PER_LONG,
&vcpu_info->evtchn_pending_sel))
vcpu_info->evtchn_upcall_pending = 1;
}
put_cpu();
}
static void xen_irq_init(unsigned irq)
{
struct irq_info *info;
struct irq_desc *desc = irq_to_desc(irq);
#ifdef CONFIG_SMP
/* By default all event channels notify CPU#0. */
cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
#endif
info = kzalloc(sizeof(*info), GFP_KERNEL);
if (info == NULL)
panic("Unable to allocate metadata for IRQ%d\n", irq);
info->type = IRQT_UNBOUND;
set_irq_data(irq, info);
list_add_tail(&info->list, &xen_irq_list_head);
}
static int __must_check xen_allocate_irq_dynamic(void)
{
xen: events: allocate GSIs and dynamic IRQs from separate IRQ ranges. There are three cases which we need to care about, PV guest, PV domain 0 and HVM guest. The PV guest case is simple since it has no access to ACPI or real APICs and therefore has no GSIs therefore we simply dynamically allocate all IRQs. The potentially interesting case here is PIRQ type event channels associated with passed through PCI devices. However even in this case the guest has no direct interaction with the physical GSI since that happens in the PCI backend. The PV domain 0 and HVM guest cases are actually the same. In domain 0 case the kernel sees the host ACPI and GSIs (although it only sees the APIC indirectly via the hypervisor) and in the HVM guest case it sees the virtualised ACPI and emulated APICs. In these cases we start allocating dynamic IRQs at nr_irqs_gsi so that they cannot clash with any GSI. Currently xen_allocate_irq_dynamic starts at nr_irqs and works backwards looking for a free IRQ in order to (try and) avoid clashing with GSIs used in domain 0 and in HVM guests. This change avoids that although we retain the behaviour of allowing dynamic IRQs to encroach on the GSI range if no suitable IRQs are available since a future IRQ clash is deemed preferable to failure right now. Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org>
2011-03-04 00:57:44 +08:00
int first = 0;
int irq;
#ifdef CONFIG_X86_IO_APIC
xen: events: allocate GSIs and dynamic IRQs from separate IRQ ranges. There are three cases which we need to care about, PV guest, PV domain 0 and HVM guest. The PV guest case is simple since it has no access to ACPI or real APICs and therefore has no GSIs therefore we simply dynamically allocate all IRQs. The potentially interesting case here is PIRQ type event channels associated with passed through PCI devices. However even in this case the guest has no direct interaction with the physical GSI since that happens in the PCI backend. The PV domain 0 and HVM guest cases are actually the same. In domain 0 case the kernel sees the host ACPI and GSIs (although it only sees the APIC indirectly via the hypervisor) and in the HVM guest case it sees the virtualised ACPI and emulated APICs. In these cases we start allocating dynamic IRQs at nr_irqs_gsi so that they cannot clash with any GSI. Currently xen_allocate_irq_dynamic starts at nr_irqs and works backwards looking for a free IRQ in order to (try and) avoid clashing with GSIs used in domain 0 and in HVM guests. This change avoids that although we retain the behaviour of allowing dynamic IRQs to encroach on the GSI range if no suitable IRQs are available since a future IRQ clash is deemed preferable to failure right now. Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org>
2011-03-04 00:57:44 +08:00
/*
* For an HVM guest or domain 0 which see "real" (emulated or
* actual repectively) 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.
*/
if (xen_initial_domain() || xen_hvm_domain())
first = get_nr_irqs_gsi();
#endif
xen: events: allocate GSIs and dynamic IRQs from separate IRQ ranges. There are three cases which we need to care about, PV guest, PV domain 0 and HVM guest. The PV guest case is simple since it has no access to ACPI or real APICs and therefore has no GSIs therefore we simply dynamically allocate all IRQs. The potentially interesting case here is PIRQ type event channels associated with passed through PCI devices. However even in this case the guest has no direct interaction with the physical GSI since that happens in the PCI backend. The PV domain 0 and HVM guest cases are actually the same. In domain 0 case the kernel sees the host ACPI and GSIs (although it only sees the APIC indirectly via the hypervisor) and in the HVM guest case it sees the virtualised ACPI and emulated APICs. In these cases we start allocating dynamic IRQs at nr_irqs_gsi so that they cannot clash with any GSI. Currently xen_allocate_irq_dynamic starts at nr_irqs and works backwards looking for a free IRQ in order to (try and) avoid clashing with GSIs used in domain 0 and in HVM guests. This change avoids that although we retain the behaviour of allowing dynamic IRQs to encroach on the GSI range if no suitable IRQs are available since a future IRQ clash is deemed preferable to failure right now. Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org>
2011-03-04 00:57:44 +08:00
irq = irq_alloc_desc_from(first, -1);
xen: Find an unbound irq number in reverse order (high to low). In earlier Xen Linux kernels, the IRQ mapping was a straight 1:1 and the find_unbound_irq started looking around 256 for open IRQs and up. IRQs from 0 to 255 were reserved for PCI devices. Previous to this patch, the 'find_unbound_irq' started looking at get_nr_hw_irqs() number. For privileged domain where the ACPI information is available that returns the upper-bound of what the GSIs. For non-privileged PV domains, where ACPI is no-existent the get_nr_hw_irqs() reports the IRQ_LEGACY (16). With PCI passthrough enabled, and with PCI cards that have IRQs pinned to a higher number than 16 we collide with previously allocated IRQs. Specifically the PCI IRQs collide with the IPI's for Xen functions (as they are allocated earlier). For example: 00:00.11 USB Controller: ATI Technologies Inc SB700 USB OHCI1 Controller (prog-if 10 [OHCI]) ... Interrupt: pin A routed to IRQ 18 [root@localhost ~]# cat /proc/interrupts | head CPU0 CPU1 CPU2 16: 38186 0 0 xen-dyn-virq timer0 17: 149 0 0 xen-dyn-ipi spinlock0 18: 962 0 0 xen-dyn-ipi resched0 and when the USB controller is loaded, the kernel reports: IRQ handler type mismatch for IRQ 18 current handler: resched0 One way to fix this is to reverse the logic when looking for un-used IRQ numbers and start with the highest available number. With that, we would get: CPU0 CPU1 CPU2 ... snip .. 292: 35 0 0 xen-dyn-ipi callfunc0 293: 3992 0 0 xen-dyn-ipi resched0 294: 224 0 0 xen-dyn-ipi spinlock0 295: 57183 0 0 xen-dyn-virq timer0 NMI: 0 0 0 Non-maskable interrupts .. snip .. And interrupts for PCI cards are now accessible. This patch also includes the fix, found by Ian Campbell, titled "xen: fix off-by-one error in find_unbound_irq." [v2: Added an explanation in the code] [v3: Rebased on top of tip/irq/core] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
2010-10-18 22:49:10 +08:00
xen_irq_init(irq);
return irq;
}
static int __must_check xen_allocate_irq_gsi(unsigned gsi)
{
int irq;
xen: events: allocate GSIs and dynamic IRQs from separate IRQ ranges. There are three cases which we need to care about, PV guest, PV domain 0 and HVM guest. The PV guest case is simple since it has no access to ACPI or real APICs and therefore has no GSIs therefore we simply dynamically allocate all IRQs. The potentially interesting case here is PIRQ type event channels associated with passed through PCI devices. However even in this case the guest has no direct interaction with the physical GSI since that happens in the PCI backend. The PV domain 0 and HVM guest cases are actually the same. In domain 0 case the kernel sees the host ACPI and GSIs (although it only sees the APIC indirectly via the hypervisor) and in the HVM guest case it sees the virtualised ACPI and emulated APICs. In these cases we start allocating dynamic IRQs at nr_irqs_gsi so that they cannot clash with any GSI. Currently xen_allocate_irq_dynamic starts at nr_irqs and works backwards looking for a free IRQ in order to (try and) avoid clashing with GSIs used in domain 0 and in HVM guests. This change avoids that although we retain the behaviour of allowing dynamic IRQs to encroach on the GSI range if no suitable IRQs are available since a future IRQ clash is deemed preferable to failure right now. Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org>
2011-03-04 00:57:44 +08:00
/*
* 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 xen_free_irq(unsigned irq)
{
struct irq_info *info = get_irq_data(irq);
list_del(&info->list);
set_irq_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_unmask_notify(int irq)
{
struct physdev_eoi eoi = { .irq = pirq_from_irq(irq) };
if (unlikely(pirq_needs_eoi(irq))) {
int rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
WARN_ON(rc);
}
}
static void pirq_query_unmask(int irq)
{
struct physdev_irq_status_query irq_status;
struct irq_info *info = info_for_irq(irq);
BUG_ON(info->type != IRQT_PIRQ);
irq_status.irq = pirq_from_irq(irq);
if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
irq_status.flags = 0;
info->u.pirq.flags &= ~PIRQ_NEEDS_EOI;
if (irq_status.flags & XENIRQSTAT_needs_eoi)
info->u.pirq.flags |= PIRQ_NEEDS_EOI;
}
static bool probing_irq(int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
return desc && desc->action == NULL;
}
static unsigned int __startup_pirq(unsigned int irq)
{
struct evtchn_bind_pirq bind_pirq;
struct irq_info *info = info_for_irq(irq);
int evtchn = evtchn_from_irq(irq);
int rc;
BUG_ON(info->type != IRQT_PIRQ);
if (VALID_EVTCHN(evtchn))
goto out;
bind_pirq.pirq = pirq_from_irq(irq);
/* NB. We are happy to share unless we are probing. */
bind_pirq.flags = info->u.pirq.flags & PIRQ_SHAREABLE ?
BIND_PIRQ__WILL_SHARE : 0;
rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq);
if (rc != 0) {
if (!probing_irq(irq))
printk(KERN_INFO "Failed to obtain physical IRQ %d\n",
irq);
return 0;
}
evtchn = bind_pirq.port;
pirq_query_unmask(irq);
evtchn_to_irq[evtchn] = irq;
bind_evtchn_to_cpu(evtchn, 0);
info->evtchn = evtchn;
out:
unmask_evtchn(evtchn);
pirq_unmask_notify(irq);
return 0;
}
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);
BUG_ON(info->type != IRQT_PIRQ);
if (!VALID_EVTCHN(evtchn))
return;
mask_evtchn(evtchn);
close.port = evtchn;
if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
BUG();
bind_evtchn_to_cpu(evtchn, 0);
evtchn_to_irq[evtchn] = -1;
info->evtchn = 0;
}
static void enable_pirq(struct irq_data *data)
{
startup_pirq(data);
}
static void disable_pirq(struct irq_data *data)
{
}
static void ack_pirq(struct irq_data *data)
{
int evtchn = evtchn_from_irq(data->irq);
move_native_irq(data->irq);
if (VALID_EVTCHN(evtchn)) {
mask_evtchn(evtchn);
clear_evtchn(evtchn);
}
}
static int find_irq_by_gsi(unsigned gsi)
{
struct irq_info *info;
list_for_each_entry(info, &xen_irq_list_head, list) {
if (info->type != IRQT_PIRQ)
continue;
if (info->u.pirq.gsi == gsi)
return info->irq;
}
return -1;
}
int xen_allocate_pirq_gsi(unsigned gsi)
{
return gsi;
}
/*
* 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_bind_pirq_gsi_to_irq(unsigned gsi,
unsigned pirq, int shareable, char *name)
{
int irq = -1;
struct physdev_irq irq_op;
spin_lock(&irq_mapping_update_lock);
irq = find_irq_by_gsi(gsi);
if (irq != -1) {
printk(KERN_INFO "xen_map_pirq_gsi: returning irq %d for gsi %u\n",
irq, gsi);
goto out; /* XXX need refcount? */
}
irq = xen_allocate_irq_gsi(gsi);
if (irq < 0)
goto out;
set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
handle_level_irq, name);
irq_op.irq = irq;
irq_op.vector = 0;
/* Only the privileged domain can do this. For non-priv, the pcifront
* driver provides a PCI bus that does the call to do exactly
* this in the priv domain. */
if (xen_initial_domain() &&
HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
xen_free_irq(irq);
irq = -ENOSPC;
goto out;
}
xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector,
shareable ? PIRQ_SHAREABLE : 0);
out:
spin_unlock(&irq_mapping_update_lock);
return irq;
}
#ifdef CONFIG_PCI_MSI
int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
{
int rc;
struct physdev_get_free_pirq op_get_free_pirq;
op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI;
rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
WARN_ONCE(rc == -ENOSYS,
"hypervisor does not support the PHYSDEVOP_get_free_pirq interface\n");
return rc ? -1 : op_get_free_pirq.pirq;
}
int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
int pirq, int vector, const char *name)
{
int irq, ret;
spin_lock(&irq_mapping_update_lock);
irq = xen_allocate_irq_dynamic();
if (irq == -1)
goto out;
set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
handle_level_irq, name);
xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, 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
int xen_destroy_irq(int irq)
{
struct irq_desc *desc;
struct physdev_unmap_pirq unmap_irq;
struct irq_info *info = info_for_irq(irq);
int rc = -ENOENT;
spin_lock(&irq_mapping_update_lock);
desc = irq_to_desc(irq);
if (!desc)
goto out;
if (xen_initial_domain()) {
unmap_irq.pirq = info->u.pirq.pirq;
unmap_irq.domid = DOMID_SELF;
rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);
if (rc) {
printk(KERN_WARNING "unmap irq failed %d\n", rc);
goto out;
}
}
xen_free_irq(irq);
out:
spin_unlock(&irq_mapping_update_lock);
return rc;
}
int xen_irq_from_pirq(unsigned pirq)
{
int 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 bind_evtchn_to_irq(unsigned int evtchn)
{
int irq;
spin_lock(&irq_mapping_update_lock);
irq = evtchn_to_irq[evtchn];
if (irq == -1) {
irq = xen_allocate_irq_dynamic();
if (irq == -1)
goto out;
set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
handle_fasteoi_irq, "event");
xen_irq_info_evtchn_init(irq, evtchn);
}
out:
spin_unlock(&irq_mapping_update_lock);
return irq;
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
{
struct evtchn_bind_ipi bind_ipi;
int evtchn, irq;
spin_lock(&irq_mapping_update_lock);
irq = per_cpu(ipi_to_irq, cpu)[ipi];
if (irq == -1) {
irq = xen_allocate_irq_dynamic();
if (irq < 0)
goto out;
set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
handle_percpu_irq, "ipi");
bind_ipi.vcpu = cpu;
if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
&bind_ipi) != 0)
BUG();
evtchn = bind_ipi.port;
xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
bind_evtchn_to_cpu(evtchn, cpu);
}
out:
spin_unlock(&irq_mapping_update_lock);
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)
{
struct evtchn_bind_virq bind_virq;
int evtchn, irq;
spin_lock(&irq_mapping_update_lock);
irq = per_cpu(virq_to_irq, cpu)[virq];
if (irq == -1) {
irq = xen_allocate_irq_dynamic();
if (irq == -1)
goto out;
set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
handle_percpu_irq, "virq");
bind_virq.virq = virq;
bind_virq.vcpu = cpu;
if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
&bind_virq) != 0)
BUG();
evtchn = bind_virq.port;
xen_irq_info_virq_init(cpu, irq, evtchn, virq);
bind_evtchn_to_cpu(evtchn, cpu);
}
out:
spin_unlock(&irq_mapping_update_lock);
return irq;
}
static void unbind_from_irq(unsigned int irq)
{
struct evtchn_close close;
int evtchn = evtchn_from_irq(irq);
spin_lock(&irq_mapping_update_lock);
if (VALID_EVTCHN(evtchn)) {
close.port = evtchn;
if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
BUG();
switch (type_from_irq(irq)) {
case IRQT_VIRQ:
per_cpu(virq_to_irq, cpu_from_evtchn(evtchn))
[virq_from_irq(irq)] = -1;
break;
case IRQT_IPI:
per_cpu(ipi_to_irq, cpu_from_evtchn(evtchn))
[ipi_from_irq(irq)] = -1;
break;
default:
break;
}
/* Closed ports are implicitly re-bound to VCPU0. */
bind_evtchn_to_cpu(evtchn, 0);
evtchn_to_irq[evtchn] = -1;
}
BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
xen_free_irq(irq);
spin_unlock(&irq_mapping_update_lock);
}
int bind_evtchn_to_irqhandler(unsigned int evtchn,
irq_handler_t handler,
unsigned long irqflags,
const char *devname, void *dev_id)
{
unsigned int irq;
int 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);
return retval;
}
return 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;
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);
return retval;
}
return irq;
}
EXPORT_SYMBOL_GPL(bind_virq_to_irqhandler);
int bind_ipi_to_irqhandler(enum ipi_vector ipi,
unsigned int cpu,
irq_handler_t handler,
unsigned long irqflags,
const char *devname,
void *dev_id)
{
int irq, retval;
irq = bind_ipi_to_irq(ipi, cpu);
if (irq < 0)
return irq;
irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME;
retval = request_irq(irq, handler, irqflags, devname, dev_id);
if (retval != 0) {
unbind_from_irq(irq);
return retval;
}
return irq;
}
void unbind_from_irqhandler(unsigned int irq, void *dev_id)
{
free_irq(irq, dev_id);
unbind_from_irq(irq);
}
EXPORT_SYMBOL_GPL(unbind_from_irqhandler);
void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
{
int irq = per_cpu(ipi_to_irq, cpu)[vector];
BUG_ON(irq < 0);
notify_remote_via_irq(irq);
}
irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
{
struct shared_info *sh = HYPERVISOR_shared_info;
int cpu = smp_processor_id();
unsigned long *cpu_evtchn = per_cpu(cpu_evtchn_mask, cpu);
int i;
unsigned long flags;
static DEFINE_SPINLOCK(debug_lock);
struct vcpu_info *v;
spin_lock_irqsave(&debug_lock, flags);
printk("\nvcpu %d\n ", cpu);
for_each_online_cpu(i) {
int pending;
v = per_cpu(xen_vcpu, i);
pending = (get_irq_regs() && i == cpu)
? xen_irqs_disabled(get_irq_regs())
: v->evtchn_upcall_mask;
printk("%d: masked=%d pending=%d event_sel %0*lx\n ", i,
pending, v->evtchn_upcall_pending,
(int)(sizeof(v->evtchn_pending_sel)*2),
v->evtchn_pending_sel);
}
v = per_cpu(xen_vcpu, cpu);
printk("\npending:\n ");
for (i = ARRAY_SIZE(sh->evtchn_pending)-1; i >= 0; i--)
printk("%0*lx%s", (int)sizeof(sh->evtchn_pending[0])*2,
sh->evtchn_pending[i],
i % 8 == 0 ? "\n " : " ");
printk("\nglobal mask:\n ");
for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
printk("%0*lx%s",
(int)(sizeof(sh->evtchn_mask[0])*2),
sh->evtchn_mask[i],
i % 8 == 0 ? "\n " : " ");
printk("\nglobally unmasked:\n ");
for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
sh->evtchn_pending[i] & ~sh->evtchn_mask[i],
i % 8 == 0 ? "\n " : " ");
printk("\nlocal cpu%d mask:\n ", cpu);
for (i = (NR_EVENT_CHANNELS/BITS_PER_LONG)-1; i >= 0; i--)
printk("%0*lx%s", (int)(sizeof(cpu_evtchn[0])*2),
cpu_evtchn[i],
i % 8 == 0 ? "\n " : " ");
printk("\nlocally unmasked:\n ");
for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) {
unsigned long pending = sh->evtchn_pending[i]
& ~sh->evtchn_mask[i]
& cpu_evtchn[i];
printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
pending, i % 8 == 0 ? "\n " : " ");
}
printk("\npending list:\n");
for (i = 0; i < NR_EVENT_CHANNELS; i++) {
if (sync_test_bit(i, sh->evtchn_pending)) {
int word_idx = i / BITS_PER_LONG;
printk(" %d: event %d -> irq %d%s%s%s\n",
cpu_from_evtchn(i), i,
evtchn_to_irq[i],
sync_test_bit(word_idx, &v->evtchn_pending_sel)
? "" : " l2-clear",
!sync_test_bit(i, sh->evtchn_mask)
? "" : " globally-masked",
sync_test_bit(i, cpu_evtchn)
? "" : " locally-masked");
}
}
spin_unlock_irqrestore(&debug_lock, flags);
return IRQ_HANDLED;
}
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
* the event number to an irq, and feed it into do_IRQ() for
* handling.
*
* Xen uses a two-level bitmap to speed searching. The first level is
* a bitset of words which contain pending event bits. The second
* level is a bitset of pending events themselves.
*/
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);
unsigned count;
do {
unsigned long pending_words;
vcpu_info->evtchn_upcall_pending = 0;
if (__this_cpu_inc_return(xed_nesting_count) - 1)
goto out;
#ifndef CONFIG_X86 /* No need for a barrier -- XCHG is a barrier on x86. */
/* Clear master flag /before/ clearing selector flag. */
wmb();
#endif
pending_words = xchg(&vcpu_info->evtchn_pending_sel, 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;
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;
}
do {
unsigned long bits;
int port, irq;
struct irq_desc *desc;
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];
mask_evtchn(port);
clear_evtchn(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());
count = __this_cpu_read(xed_nesting_count);
__this_cpu_write(xed_nesting_count, 0);
} while (count != 1 || vcpu_info->evtchn_upcall_pending);
out:
put_cpu();
}
void xen_evtchn_do_upcall(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
exit_idle();
irq_enter();
__xen_evtchn_do_upcall();
irq_exit();
set_irq_regs(old_regs);
}
void xen_hvm_evtchn_do_upcall(void)
{
__xen_evtchn_do_upcall();
}
EXPORT_SYMBOL_GPL(xen_hvm_evtchn_do_upcall);
/* Rebind a new event channel to an existing irq. */
void rebind_evtchn_irq(int evtchn, int irq)
{
struct irq_info *info = info_for_irq(irq);
/* Make sure the irq is masked, since the new event channel
will also be masked. */
disable_irq(irq);
spin_lock(&irq_mapping_update_lock);
/* After resume the irq<->evtchn mappings are all cleared out */
BUG_ON(evtchn_to_irq[evtchn] != -1);
/* Expect irq to have been bound before,
so there should be a proper type */
BUG_ON(info->type == IRQT_UNBOUND);
xen_irq_info_evtchn_init(irq, evtchn);
spin_unlock(&irq_mapping_update_lock);
/* new event channels are always bound to cpu 0 */
irq_set_affinity(irq, cpumask_of(0));
/* Unmask the event channel. */
enable_irq(irq);
}
/* Rebind an evtchn so that it gets delivered to a specific cpu */
static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
{
struct evtchn_bind_vcpu bind_vcpu;
int evtchn = evtchn_from_irq(irq);
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. */
bind_vcpu.port = evtchn;
bind_vcpu.vcpu = tcpu;
/*
* If this fails, it usually just indicates that we're dealing with a
* virq or IPI channel, which don't actually need to be rebound. Ignore
* it, but don't do the xenlinux-level rebind in that case.
*/
if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
bind_evtchn_to_cpu(evtchn, tcpu);
return 0;
}
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(data->irq, tcpu);
}
int resend_irq_on_evtchn(unsigned int irq)
{
int masked, evtchn = evtchn_from_irq(irq);
struct shared_info *s = HYPERVISOR_shared_info;
if (!VALID_EVTCHN(evtchn))
return 1;
masked = sync_test_and_set_bit(evtchn, s->evtchn_mask);
sync_set_bit(evtchn, s->evtchn_pending);
if (!masked)
unmask_evtchn(evtchn);
return 1;
}
static void enable_dynirq(struct irq_data *data)
{
int evtchn = evtchn_from_irq(data->irq);
if (VALID_EVTCHN(evtchn))
unmask_evtchn(evtchn);
}
static void disable_dynirq(struct irq_data *data)
{
int evtchn = evtchn_from_irq(data->irq);
if (VALID_EVTCHN(evtchn))
mask_evtchn(evtchn);
}
static void ack_dynirq(struct irq_data *data)
{
int evtchn = evtchn_from_irq(data->irq);
move_masked_irq(data->irq);
if (VALID_EVTCHN(evtchn))
unmask_evtchn(evtchn);
}
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;
if (VALID_EVTCHN(evtchn)) {
int masked;
masked = sync_test_and_set_bit(evtchn, sh->evtchn_mask);
sync_set_bit(evtchn, sh->evtchn_pending);
if (!masked)
unmask_evtchn(evtchn);
ret = 1;
}
return ret;
}
static void restore_pirqs(void)
{
int pirq, rc, irq, gsi;
struct physdev_map_pirq map_irq;
struct irq_info *info;
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 */
if (!gsi)
continue;
map_irq.domid = DOMID_SELF;
map_irq.type = MAP_PIRQ_TYPE_GSI;
map_irq.index = gsi;
map_irq.pirq = pirq;
rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
if (rc) {
printk(KERN_WARNING "xen map irq failed gsi=%d irq=%d pirq=%d rc=%d\n",
gsi, irq, pirq, rc);
xen_free_irq(irq);
continue;
}
printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);
__startup_pirq(irq);
}
}
static void restore_cpu_virqs(unsigned int cpu)
{
struct evtchn_bind_virq bind_virq;
int virq, irq, evtchn;
for (virq = 0; virq < NR_VIRQS; virq++) {
if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1)
continue;
BUG_ON(virq_from_irq(irq) != virq);
/* Get a new binding from Xen. */
bind_virq.virq = virq;
bind_virq.vcpu = cpu;
if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
&bind_virq) != 0)
BUG();
evtchn = bind_virq.port;
/* Record the new mapping. */
xen_irq_info_virq_init(cpu, irq, evtchn, virq);
bind_evtchn_to_cpu(evtchn, cpu);
}
}
static void restore_cpu_ipis(unsigned int cpu)
{
struct evtchn_bind_ipi bind_ipi;
int ipi, irq, evtchn;
for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) {
if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1)
continue;
BUG_ON(ipi_from_irq(irq) != ipi);
/* Get a new binding from Xen. */
bind_ipi.vcpu = cpu;
if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
&bind_ipi) != 0)
BUG();
evtchn = bind_ipi.port;
/* Record the new mapping. */
xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
bind_evtchn_to_cpu(evtchn, cpu);
}
}
xen: implement Xen-specific spinlocks The standard ticket spinlocks are very expensive in a virtual environment, because their performance depends on Xen's scheduler giving vcpus time in the order that they're supposed to take the spinlock. This implements a Xen-specific spinlock, which should be much more efficient. The fast-path is essentially the old Linux-x86 locks, using a single lock byte. The locker decrements the byte; if the result is 0, then they have the lock. If the lock is negative, then locker must spin until the lock is positive again. When there's contention, the locker spin for 2^16[*] iterations waiting to get the lock. If it fails to get the lock in that time, it adds itself to the contention count in the lock and blocks on a per-cpu event channel. When unlocking the spinlock, the locker looks to see if there's anyone blocked waiting for the lock by checking for a non-zero waiter count. If there's a waiter, it traverses the per-cpu "lock_spinners" variable, which contains which lock each CPU is waiting on. It picks one CPU waiting on the lock and sends it an event to wake it up. This allows efficient fast-path spinlock operation, while allowing spinning vcpus to give up their processor time while waiting for a contended lock. [*] 2^16 iterations is threshold at which 98% locks have been taken according to Thomas Friebel's Xen Summit talk "Preventing Guests from Spinning Around". Therefore, we'd expect the lock and unlock slow paths will only be entered 2% of the time. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <clameter@linux-foundation.org> Cc: Petr Tesarik <ptesarik@suse.cz> Cc: Virtualization <virtualization@lists.linux-foundation.org> Cc: Xen devel <xen-devel@lists.xensource.com> Cc: Thomas Friebel <thomas.friebel@amd.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 03:07:53 +08:00
/* Clear an irq's pending state, in preparation for polling on it */
void xen_clear_irq_pending(int irq)
{
int evtchn = evtchn_from_irq(irq);
if (VALID_EVTCHN(evtchn))
clear_evtchn(evtchn);
}
EXPORT_SYMBOL(xen_clear_irq_pending);
void xen_set_irq_pending(int irq)
{
int evtchn = evtchn_from_irq(irq);
if (VALID_EVTCHN(evtchn))
set_evtchn(evtchn);
}
bool xen_test_irq_pending(int irq)
{
int evtchn = evtchn_from_irq(irq);
bool ret = false;
if (VALID_EVTCHN(evtchn))
ret = test_evtchn(evtchn);
return ret;
}
/* Poll waiting for an irq to become pending with timeout. In the usual case,
* the irq will be disabled so it won't deliver an interrupt. */
void xen_poll_irq_timeout(int irq, u64 timeout)
xen: implement Xen-specific spinlocks The standard ticket spinlocks are very expensive in a virtual environment, because their performance depends on Xen's scheduler giving vcpus time in the order that they're supposed to take the spinlock. This implements a Xen-specific spinlock, which should be much more efficient. The fast-path is essentially the old Linux-x86 locks, using a single lock byte. The locker decrements the byte; if the result is 0, then they have the lock. If the lock is negative, then locker must spin until the lock is positive again. When there's contention, the locker spin for 2^16[*] iterations waiting to get the lock. If it fails to get the lock in that time, it adds itself to the contention count in the lock and blocks on a per-cpu event channel. When unlocking the spinlock, the locker looks to see if there's anyone blocked waiting for the lock by checking for a non-zero waiter count. If there's a waiter, it traverses the per-cpu "lock_spinners" variable, which contains which lock each CPU is waiting on. It picks one CPU waiting on the lock and sends it an event to wake it up. This allows efficient fast-path spinlock operation, while allowing spinning vcpus to give up their processor time while waiting for a contended lock. [*] 2^16 iterations is threshold at which 98% locks have been taken according to Thomas Friebel's Xen Summit talk "Preventing Guests from Spinning Around". Therefore, we'd expect the lock and unlock slow paths will only be entered 2% of the time. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <clameter@linux-foundation.org> Cc: Petr Tesarik <ptesarik@suse.cz> Cc: Virtualization <virtualization@lists.linux-foundation.org> Cc: Xen devel <xen-devel@lists.xensource.com> Cc: Thomas Friebel <thomas.friebel@amd.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 03:07:53 +08:00
{
evtchn_port_t evtchn = evtchn_from_irq(irq);
if (VALID_EVTCHN(evtchn)) {
struct sched_poll poll;
poll.nr_ports = 1;
poll.timeout = timeout;
set_xen_guest_handle(poll.ports, &evtchn);
xen: implement Xen-specific spinlocks The standard ticket spinlocks are very expensive in a virtual environment, because their performance depends on Xen's scheduler giving vcpus time in the order that they're supposed to take the spinlock. This implements a Xen-specific spinlock, which should be much more efficient. The fast-path is essentially the old Linux-x86 locks, using a single lock byte. The locker decrements the byte; if the result is 0, then they have the lock. If the lock is negative, then locker must spin until the lock is positive again. When there's contention, the locker spin for 2^16[*] iterations waiting to get the lock. If it fails to get the lock in that time, it adds itself to the contention count in the lock and blocks on a per-cpu event channel. When unlocking the spinlock, the locker looks to see if there's anyone blocked waiting for the lock by checking for a non-zero waiter count. If there's a waiter, it traverses the per-cpu "lock_spinners" variable, which contains which lock each CPU is waiting on. It picks one CPU waiting on the lock and sends it an event to wake it up. This allows efficient fast-path spinlock operation, while allowing spinning vcpus to give up their processor time while waiting for a contended lock. [*] 2^16 iterations is threshold at which 98% locks have been taken according to Thomas Friebel's Xen Summit talk "Preventing Guests from Spinning Around". Therefore, we'd expect the lock and unlock slow paths will only be entered 2% of the time. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <clameter@linux-foundation.org> Cc: Petr Tesarik <ptesarik@suse.cz> Cc: Virtualization <virtualization@lists.linux-foundation.org> Cc: Xen devel <xen-devel@lists.xensource.com> Cc: Thomas Friebel <thomas.friebel@amd.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 03:07:53 +08:00
if (HYPERVISOR_sched_op(SCHEDOP_poll, &poll) != 0)
BUG();
}
}
EXPORT_SYMBOL(xen_poll_irq_timeout);
/* Poll waiting for an irq to become pending. In the usual case, the
* irq will be disabled so it won't deliver an interrupt. */
void xen_poll_irq(int irq)
{
xen_poll_irq_timeout(irq, 0 /* no timeout */);
}
xen: implement Xen-specific spinlocks The standard ticket spinlocks are very expensive in a virtual environment, because their performance depends on Xen's scheduler giving vcpus time in the order that they're supposed to take the spinlock. This implements a Xen-specific spinlock, which should be much more efficient. The fast-path is essentially the old Linux-x86 locks, using a single lock byte. The locker decrements the byte; if the result is 0, then they have the lock. If the lock is negative, then locker must spin until the lock is positive again. When there's contention, the locker spin for 2^16[*] iterations waiting to get the lock. If it fails to get the lock in that time, it adds itself to the contention count in the lock and blocks on a per-cpu event channel. When unlocking the spinlock, the locker looks to see if there's anyone blocked waiting for the lock by checking for a non-zero waiter count. If there's a waiter, it traverses the per-cpu "lock_spinners" variable, which contains which lock each CPU is waiting on. It picks one CPU waiting on the lock and sends it an event to wake it up. This allows efficient fast-path spinlock operation, while allowing spinning vcpus to give up their processor time while waiting for a contended lock. [*] 2^16 iterations is threshold at which 98% locks have been taken according to Thomas Friebel's Xen Summit talk "Preventing Guests from Spinning Around". Therefore, we'd expect the lock and unlock slow paths will only be entered 2% of the time. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <clameter@linux-foundation.org> Cc: Petr Tesarik <ptesarik@suse.cz> Cc: Virtualization <virtualization@lists.linux-foundation.org> Cc: Xen devel <xen-devel@lists.xensource.com> Cc: Thomas Friebel <thomas.friebel@amd.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 03:07:53 +08:00
void xen_irq_resume(void)
{
unsigned int cpu, evtchn;
struct irq_info *info;
init_evtchn_cpu_bindings();
/* New event-channel space is not 'live' yet. */
for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
mask_evtchn(evtchn);
/* No IRQ <-> event-channel mappings. */
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;
for_each_possible_cpu(cpu) {
restore_cpu_virqs(cpu);
restore_cpu_ipis(cpu);
}
xen: events: do not unmask event channels on resume The IRQ core code will take care of disabling and reenabling interrupts over suspend resume automatically, therefore we do not need to do this in the Xen event channel code. The only exception is those event channels marked IRQF_NO_SUSPEND which the IRQ core ignores. We must unmask these ourselves, taking care to obey the current IRQ_DISABLED status. Failure check for IRQ_DISABLED leads to enabling polled only event channels, such as that associated with the pv spinlocks, which must never be enabled: [ 21.970432] ------------[ cut here ]------------ [ 21.970432] kernel BUG at arch/x86/xen/spinlock.c:343! [ 21.970432] invalid opcode: 0000 [#1] SMP [ 21.970432] last sysfs file: /sys/devices/virtual/net/lo/operstate [ 21.970432] Modules linked in: [ 21.970432] [ 21.970432] Pid: 0, comm: swapper Not tainted (2.6.32.24-x86_32p-xen-01034-g787c727 #34) [ 21.970432] EIP: 0061:[<c102e209>] EFLAGS: 00010046 CPU: 3 [ 21.970432] EIP is at dummy_handler+0x3/0x7 [ 21.970432] EAX: 0000021c EBX: dfc16880 ECX: 0000001a EDX: 00000000 [ 21.970432] ESI: dfc02c00 EDI: 00000001 EBP: dfc47e10 ESP: dfc47e10 [ 21.970432] DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0069 [ 21.970432] Process swapper (pid: 0, ti=dfc46000 task=dfc39440 task.ti=dfc46000) [ 21.970432] Stack: [ 21.970432] dfc47e30 c10a39f0 0000021c 00000000 00000000 dfc16880 0000021c 00000001 [ 21.970432] <0> dfc47e40 c10a4f08 0000021c 00000000 dfc47e78 c12240a7 c1839284 c1839284 [ 21.970432] <0> 00000200 00000000 00000000 f5720000 c1f3d028 c1f3d02c 00000180 dfc47e90 [ 21.970432] Call Trace: [ 21.970432] [<c10a39f0>] ? handle_IRQ_event+0x5f/0x122 [ 21.970432] [<c10a4f08>] ? handle_percpu_irq+0x2f/0x55 [ 21.970432] [<c12240a7>] ? __xen_evtchn_do_upcall+0xdb/0x15f [ 21.970432] [<c122481e>] ? xen_evtchn_do_upcall+0x20/0x30 [ 21.970432] [<c1030d47>] ? xen_do_upcall+0x7/0xc [ 21.970432] [<c102007b>] ? apic_reg_read+0xd3/0x22d [ 21.970432] [<c1002227>] ? hypercall_page+0x227/0x1005 [ 21.970432] [<c102d30b>] ? xen_force_evtchn_callback+0xf/0x14 [ 21.970432] [<c102da7c>] ? check_events+0x8/0xc [ 21.970432] [<c102da3b>] ? xen_irq_enable_direct_end+0x0/0x1 [ 21.970432] [<c105e485>] ? finish_task_switch+0x62/0xba [ 21.970432] [<c14e3f84>] ? schedule+0x808/0x89d [ 21.970432] [<c1084dc5>] ? hrtimer_start_expires+0x1a/0x22 [ 21.970432] [<c1085154>] ? tick_nohz_restart_sched_tick+0x15a/0x162 [ 21.970432] [<c102f43a>] ? cpu_idle+0x6d/0x6f [ 21.970432] [<c14db29e>] ? cpu_bringup_and_idle+0xd/0xf [ 21.970432] Code: 5d 0f 95 c0 0f b6 c0 c3 55 66 83 78 02 00 89 e5 5d 0f 95 \ c0 0f b6 c0 c3 55 b2 01 86 10 31 c0 84 d2 89 e5 0f 94 c0 5d c3 55 89 e5 <0f> 0b \ eb fe 55 80 3d 4c ce 84 c1 00 89 e5 57 56 89 c6 53 74 15 [ 21.970432] EIP: [<c102e209>] dummy_handler+0x3/0x7 SS:ESP 0069:dfc47e10 [ 21.970432] ---[ end trace c0b71f7e12cf3011 ]--- Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
2010-11-02 00:30:09 +08:00
restore_pirqs();
}
static struct irq_chip xen_dynamic_chip __read_mostly = {
.name = "xen-dyn",
.irq_disable = disable_dynirq,
.irq_mask = disable_dynirq,
.irq_unmask = enable_dynirq,
.irq_eoi = ack_dynirq,
.irq_set_affinity = set_affinity_irq,
.irq_retrigger = retrigger_dynirq,
};
static struct irq_chip xen_pirq_chip __read_mostly = {
.name = "xen-pirq",
.irq_startup = startup_pirq,
.irq_shutdown = shutdown_pirq,
.irq_enable = enable_pirq,
.irq_unmask = enable_pirq,
.irq_disable = disable_pirq,
.irq_mask = disable_pirq,
.irq_ack = ack_pirq,
.irq_set_affinity = set_affinity_irq,
.irq_retrigger = retrigger_dynirq,
};
static struct irq_chip xen_percpu_chip __read_mostly = {
.name = "xen-percpu",
.irq_disable = disable_dynirq,
.irq_mask = disable_dynirq,
.irq_unmask = enable_dynirq,
.irq_ack = ack_dynirq,
};
int xen_set_callback_via(uint64_t via)
{
struct xen_hvm_param a;
a.domid = DOMID_SELF;
a.index = HVM_PARAM_CALLBACK_IRQ;
a.value = via;
return HYPERVISOR_hvm_op(HVMOP_set_param, &a);
}
EXPORT_SYMBOL_GPL(xen_set_callback_via);
#ifdef CONFIG_XEN_PVHVM
/* Vector callbacks are better than PCI interrupts to receive event
* channel notifications because we can receive vector callbacks on any
* vcpu and we don't need PCI support or APIC interactions. */
void xen_callback_vector(void)
{
int rc;
uint64_t callback_via;
if (xen_have_vector_callback) {
callback_via = HVM_CALLBACK_VECTOR(XEN_HVM_EVTCHN_CALLBACK);
rc = xen_set_callback_via(callback_via);
if (rc) {
printk(KERN_ERR "Request for Xen HVM callback vector"
" failed.\n");
xen_have_vector_callback = 0;
return;
}
printk(KERN_INFO "Xen HVM callback vector for event delivery is "
"enabled\n");
/* in the restore case the vector has already been allocated */
if (!test_bit(XEN_HVM_EVTCHN_CALLBACK, used_vectors))
alloc_intr_gate(XEN_HVM_EVTCHN_CALLBACK, xen_hvm_callback_vector);
}
}
#else
void xen_callback_vector(void) {}
#endif
void __init xen_init_IRQ(void)
{
int i;
evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
GFP_KERNEL);
for (i = 0; i < NR_EVENT_CHANNELS; i++)
evtchn_to_irq[i] = -1;
init_evtchn_cpu_bindings();
/* No event channels are 'live' right now. */
for (i = 0; i < NR_EVENT_CHANNELS; i++)
mask_evtchn(i);
if (xen_hvm_domain()) {
xen_callback_vector();
native_init_IRQ();
/* pci_xen_hvm_init must be called after native_init_IRQ so that
* __acpi_register_gsi can point at the right function */
pci_xen_hvm_init();
} else {
irq_ctx_init(smp_processor_id());
if (xen_initial_domain())
xen_setup_pirqs();
}
}