diff mbox

[Xen-devel,v7,3/6] xen/arm: inflight irqs during migration

Message ID 1404406394-18231-3-git-send-email-stefano.stabellini@eu.citrix.com
State New
Headers show

Commit Message

Stefano Stabellini July 3, 2014, 4:53 p.m. UTC
We need to take special care when migrating irqs that are already
inflight from one vcpu to another. See "The effect of changes to an
GICD_ITARGETSR", part of chapter 4.3.12 of the ARM Generic Interrupt
Controller Architecture Specification.

The main issue from the Xen point of view is that the lr_pending and
inflight lists are per-vcpu. The lock we take to protect them is also
per-vcpu.

In order to avoid issues, if the irq is still lr_pending, we can
immediately move it to the new vcpu for injection.

Otherwise if it is in a GICH_LR register, set a new flag
GIC_IRQ_GUEST_MIGRATING, so that we can recognize when we receive an irq
while the previous one is still inflight (given that we are only dealing
with hardware interrupts here, it just means that its LR hasn't been
cleared yet on the old vcpu).  If GIC_IRQ_GUEST_MIGRATING is set, we
only set GIC_IRQ_GUEST_QUEUED and interrupt the old vcpu. To know which
one is the old vcpu, we introduce a new field to pending_irq, called
vcpu_migrate_from.
When clearing the LR on the old vcpu, we take special care of injecting
the interrupt into the new vcpu. To do that we need to release the old
vcpu lock before taking the new vcpu lock.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>

---

Changes in v7:
- move the _VPF_down check before setting GIC_IRQ_GUEST_QUEUED;
- fix comments;
- rename trl to target;
- introduce vcpu_migrate_from;
- do not kick new vcpu on MIGRATING, kick the old vcpu instead;
- separate moving GIC_IRQ_GUEST_QUEUED earlier into a different patch.

Changes in v6:
- remove unnecessary casts to (const unsigned long *) to the arguments
of find_first_bit and find_next_bit;
- instroduce a corresponding smb_rmb call;
- deal with migrating an irq that is inflight and still lr_pending;
- replace the dsb with smb_wmb and smb_rmb, use them to ensure the order
of accesses to GIC_IRQ_GUEST_QUEUED and GIC_IRQ_GUEST_MIGRATING;

Changes in v5:
- pass unsigned long to find_next_bit for alignment on aarch64;
- call vgic_get_target_vcpu instead of gic_add_to_lr_pending to add the
irq in the right inflight queue;
- add barrier and bit tests to make sure that vgic_migrate_irq and
gic_update_one_lr can run simultaneously on different cpus without
issues;
- rework the loop to identify the new vcpu when ITARGETSR is written;
- use find_first_bit instead of find_next_bit.
---
 xen/arch/arm/gic.c           |   28 +++++++++++-
 xen/arch/arm/vgic.c          |   99 ++++++++++++++++++++++++++++++++++++++----
 xen/include/asm-arm/domain.h |    7 +++
 3 files changed, 123 insertions(+), 11 deletions(-)

Comments

Julien Grall July 4, 2014, 10:26 a.m. UTC | #1
On 07/03/2014 05:53 PM, Stefano Stabellini wrote:
>  static void vgic_disable_irqs(struct vcpu *v, uint32_t r, int n)
>  {
>      const unsigned long mask = r;
> @@ -598,35 +638,60 @@ static int vgic_distr_mmio_write(struct vcpu *v, mmio_info_t *info)
>          goto write_ignore;
>  
>      case GICD_ITARGETSR + 8 ... GICD_ITARGETSRN:
> +    {
> +        /* unsigned long needed for find_next_bit */
> +        unsigned long target;
> +        int i;
>          if ( dabt.size != 0 && dabt.size != 2 ) goto bad_width;
>          rank = vgic_rank_offset(v, 8, gicd_reg - GICD_ITARGETSR);
>          if ( rank == NULL) goto write_ignore;
>          /* 8-bit vcpu mask for this domain */
>          BUG_ON(v->domain->max_vcpus > 8);
> -        tr = (1 << v->domain->max_vcpus) - 1;
> +        target = (1 << v->domain->max_vcpus) - 1;
>          if ( dabt.size == 2 )
> -            tr = tr | (tr << 8) | (tr << 16) | (tr << 24);
> +            target = target | (target << 8) | (target << 16) | (target << 24);
>          else
> -            tr = (tr << (8 * (offset & 0x3)));
> -        tr &= *r;
> +            target = (target << (8 * (offset & 0x3)));
> +        target &= *r;
>          /* ignore zero writes */
> -        if ( !tr )
> +        if ( !target )
>              goto write_ignore;
>          /* For word reads ignore writes where any single byte is zero */
>          if ( dabt.size == 2 &&
> -            !((tr & 0xff) && (tr & (0xff << 8)) &&
> -             (tr & (0xff << 16)) && (tr & (0xff << 24))))
> +            !((target & 0xff) && (target & (0xff << 8)) &&
> +             (target & (0xff << 16)) && (target & (0xff << 24))))
>              goto write_ignore;
>          vgic_lock_rank(v, rank);
> +        i = 0;
> +        while ( (i = find_next_bit(&target, 32, i)) < 32 )
> +        {
> +            unsigned int irq, target, old_target;

target is already defined above, and this will shadow this previous
definition. I would rename one of them to avoid coding error later.
diff mbox

Patch

diff --git a/xen/arch/arm/gic.c b/xen/arch/arm/gic.c
index e1e27b35..b5269d4 100644
--- a/xen/arch/arm/gic.c
+++ b/xen/arch/arm/gic.c
@@ -33,6 +33,7 @@ 
 #include <asm/device.h>
 #include <asm/io.h>
 #include <asm/gic.h>
+#include <asm/vgic.h>
 
 static void gic_restore_pending_irqs(struct vcpu *v);
 
@@ -372,10 +373,33 @@  static void gic_update_one_lr(struct vcpu *v, int i)
         clear_bit(GIC_IRQ_GUEST_ACTIVE, &p->status);
         p->lr = GIC_INVALID_LR;
         if ( test_bit(GIC_IRQ_GUEST_ENABLED, &p->status) &&
-             test_bit(GIC_IRQ_GUEST_QUEUED, &p->status) )
+             test_bit(GIC_IRQ_GUEST_QUEUED, &p->status) &&
+             !test_bit(GIC_IRQ_GUEST_MIGRATING, &p->status) )
             gic_raise_guest_irq(v, irq, p->priority);
-        else
+        else {
+            int m, q;
             list_del_init(&p->inflight);
+
+            m = test_and_clear_bit(GIC_IRQ_GUEST_MIGRATING, &p->status);
+            p->vcpu_migrate_from = NULL;
+            /* check MIGRATING before QUEUED */
+            smp_rmb();
+            q = test_bit(GIC_IRQ_GUEST_QUEUED, &p->status);
+            if ( m && q )
+            {
+                struct vcpu *v_target;
+
+                /* It is safe to temporarily drop the lock because we
+                 * are finished dealing with this LR. We'll take the
+                 * lock before reading the next. */
+                spin_unlock(&v->arch.vgic.lock);
+                /* vgic_get_target_vcpu takes the rank lock, ensuring
+                 * consistency with other itarget changes. */
+                v_target = vgic_get_target_vcpu(v, irq);
+                vgic_vcpu_inject_irq(v_target, irq);
+                spin_lock(&v->arch.vgic.lock);
+            }
+        }
     }
 }
 
diff --git a/xen/arch/arm/vgic.c b/xen/arch/arm/vgic.c
index e928879..8827a77 100644
--- a/xen/arch/arm/vgic.c
+++ b/xen/arch/arm/vgic.c
@@ -382,6 +382,46 @@  struct vcpu *vgic_get_target_vcpu(struct vcpu *v, unsigned int irq)
     return v_target;
 }
 
+static void vgic_migrate_irq(struct vcpu *old, struct vcpu *new, unsigned int irq)
+{
+    unsigned long flags;
+    struct pending_irq *p = irq_to_pending(old, irq);
+
+    /* nothing to do for virtual interrupts */
+    if ( p->desc == NULL )
+        return;
+
+    /* migration already in progress, no need to do anything */
+    if ( test_bit(GIC_IRQ_GUEST_MIGRATING, &p->status) )
+        return;
+
+    spin_lock_irqsave(&old->arch.vgic.lock, flags);
+
+    if ( list_empty(&p->inflight) )
+    {
+        spin_unlock_irqrestore(&old->arch.vgic.lock, flags);
+        return;
+    }
+    /* If the IRQ is still lr_pending, re-inject it to the new vcpu */
+    if ( !list_empty(&p->lr_queue) )
+    {
+        list_del_init(&p->lr_queue);
+        list_del_init(&p->inflight);
+        spin_unlock_irqrestore(&old->arch.vgic.lock, flags);
+        vgic_vcpu_inject_irq(new, irq);
+        return;
+    }
+    /* if the IRQ is in a GICH_LR register, set GIC_IRQ_GUEST_MIGRATING
+     * and wait for the EOI */
+    if ( !list_empty(&p->inflight) )
+    {
+        p->vcpu_migrate_from = old;
+        set_bit(GIC_IRQ_GUEST_MIGRATING, &p->status);
+    }
+
+    spin_unlock_irqrestore(&old->arch.vgic.lock, flags);
+}
+
 static void vgic_disable_irqs(struct vcpu *v, uint32_t r, int n)
 {
     const unsigned long mask = r;
@@ -598,35 +638,60 @@  static int vgic_distr_mmio_write(struct vcpu *v, mmio_info_t *info)
         goto write_ignore;
 
     case GICD_ITARGETSR + 8 ... GICD_ITARGETSRN:
+    {
+        /* unsigned long needed for find_next_bit */
+        unsigned long target;
+        int i;
         if ( dabt.size != 0 && dabt.size != 2 ) goto bad_width;
         rank = vgic_rank_offset(v, 8, gicd_reg - GICD_ITARGETSR);
         if ( rank == NULL) goto write_ignore;
         /* 8-bit vcpu mask for this domain */
         BUG_ON(v->domain->max_vcpus > 8);
-        tr = (1 << v->domain->max_vcpus) - 1;
+        target = (1 << v->domain->max_vcpus) - 1;
         if ( dabt.size == 2 )
-            tr = tr | (tr << 8) | (tr << 16) | (tr << 24);
+            target = target | (target << 8) | (target << 16) | (target << 24);
         else
-            tr = (tr << (8 * (offset & 0x3)));
-        tr &= *r;
+            target = (target << (8 * (offset & 0x3)));
+        target &= *r;
         /* ignore zero writes */
-        if ( !tr )
+        if ( !target )
             goto write_ignore;
         /* For word reads ignore writes where any single byte is zero */
         if ( dabt.size == 2 &&
-            !((tr & 0xff) && (tr & (0xff << 8)) &&
-             (tr & (0xff << 16)) && (tr & (0xff << 24))))
+            !((target & 0xff) && (target & (0xff << 8)) &&
+             (target & (0xff << 16)) && (target & (0xff << 24))))
             goto write_ignore;
         vgic_lock_rank(v, rank);
+        i = 0;
+        while ( (i = find_next_bit(&target, 32, i)) < 32 )
+        {
+            unsigned int irq, target, old_target;
+            unsigned long old_target_mask;
+            struct vcpu *v_target, *v_old;
+
+            target = i % 8;
+            old_target_mask = vgic_byte_read(rank->itargets[REG_RANK_INDEX(8, gicd_reg - GICD_ITARGETSR)], 0, i/8);
+            old_target = find_first_bit(&old_target_mask, 8);
+
+            if ( target != old_target )
+            {
+                irq = offset + (i / 8);
+                v_target = v->domain->vcpu[target];
+                v_old = v->domain->vcpu[old_target];
+                vgic_migrate_irq(v_old, v_target, irq);
+            }
+            i += 8 - target;
+        }
         if ( dabt.size == 2 )
-            rank->itargets[REG_RANK_INDEX(8, gicd_reg - GICD_ITARGETSR)] = tr;
+            rank->itargets[REG_RANK_INDEX(8, gicd_reg - GICD_ITARGETSR)] = target;
         else
         {
             int ri = REG_RANK_INDEX(8, gicd_reg - GICD_ITARGETSR);
-            vgic_byte_write(&rank->itargets[ri], tr, offset);
+            vgic_byte_write(&rank->itargets[ri], target, offset);
         }
         vgic_unlock_rank(v, rank);
         return 1;
+    }
 
     case GICD_IPRIORITYR ... GICD_IPRIORITYRN:
         if ( dabt.size != 0 && dabt.size != 2 ) goto bad_width;
@@ -747,6 +812,7 @@  void vgic_vcpu_inject_irq(struct vcpu *v, unsigned int irq)
     struct pending_irq *iter, *n = irq_to_pending(v, irq);
     unsigned long flags;
     bool_t running;
+    struct vcpu *vcpu_migrate_from;
 
     spin_lock_irqsave(&v->arch.vgic.lock, flags);
 
@@ -758,6 +824,21 @@  void vgic_vcpu_inject_irq(struct vcpu *v, unsigned int irq)
     }
 
     set_bit(GIC_IRQ_GUEST_QUEUED, &n->status);
+    vcpu_migrate_from = n->vcpu_migrate_from;
+    /* update QUEUED before MIGRATING */
+    smp_wmb();
+    if ( test_bit(GIC_IRQ_GUEST_MIGRATING, &n->status) )
+    {
+        spin_unlock_irqrestore(&v->arch.vgic.lock, flags);
+
+        /* The old vcpu must have EOIed the SGI but not cleared the LR.
+         * Give it a kick. */
+        running = n->vcpu_migrate_from->is_running;
+        vcpu_unblock(n->vcpu_migrate_from);
+        if ( running )
+            smp_send_event_check_mask(cpumask_of(n->vcpu_migrate_from->processor));
+        return;
+    }
 
     if ( !list_empty(&n->inflight) )
     {
diff --git a/xen/include/asm-arm/domain.h b/xen/include/asm-arm/domain.h
index 077ac1e..70c1215 100644
--- a/xen/include/asm-arm/domain.h
+++ b/xen/include/asm-arm/domain.h
@@ -48,17 +48,24 @@  struct pending_irq
      * GIC_IRQ_GUEST_ENABLED: the guest IRQ is enabled at the VGICD
      * level (GICD_ICENABLER/GICD_ISENABLER).
      *
+     * GIC_IRQ_GUEST_MIGRATING: the irq is being migrated to a different
+     * vcpu while it is still inflight and on an GICH_LR register on the
+     * old vcpu.
+     *
      */
 #define GIC_IRQ_GUEST_QUEUED   0
 #define GIC_IRQ_GUEST_ACTIVE   1
 #define GIC_IRQ_GUEST_VISIBLE  2
 #define GIC_IRQ_GUEST_ENABLED  3
+#define GIC_IRQ_GUEST_MIGRATING   4
     unsigned long status;
     struct irq_desc *desc; /* only set it the irq corresponds to a physical irq */
     int irq;
 #define GIC_INVALID_LR         ~(uint8_t)0
     uint8_t lr;
     uint8_t priority;
+    /* keeps track of the vcpu this irq is currently migrating from */
+    struct vcpu *vcpu_migrate_from;
     /* inflight is used to append instances of pending_irq to
      * vgic.inflight_irqs */
     struct list_head inflight;