from:"Feng Wu"

[PATCH 00/13] Add VT-d Posted-Interrupts support for KVM

2014-11-09 Thread Feng Wu

VT-d Posted-Interrupts is an enhancement to CPU side Posted-Interrupt.
With VT-d Posted-Interrupts enabled, external interrupts from
direct-assigned devices can be delivered to guests without VMM
intervention when guest is running in non-root mode.

You can find the VT-d Posted-Interrtups Spec. in the following URL:
http://www.intel.com/content/www/us/en/intelligent-systems/intel-technology/vt-directed-io-spec.html

Feng Wu (13):
  iommu/vt-d: VT-d Posted-Interrupts feature detection
  KVM: Initialize VT-d Posted-Interrtups Descriptor
  KVM: Add KVM_CAP_PI to detect VT-d Posted-Interrtups
  iommu/vt-d: Adjust 'struct irte' to better suit for VT-d
Posted-Interrupts
  KVM: Update IRTE according to guest interrupt configuration changes
  KVM: Add some helper functions for Posted-Interrupts
  x86, irq: Define a global vector for VT-d Posted-Interrupts
  KVM: Update Posted-Interrupts descriptor during VCPU scheduling
  KVM: Change NDST field after VCPU scheduling
  KVM: Add the handler for Wake-up Vector
  KVM: Suppress posted-interrupt when 'SN' is set
  iommu/vt-d: No need to migrating irq for VT-d Posted-Interrtups
  iommu/vt-d: Add a command line parameter for VT-d posted-interrupts

 arch/x86/include/asm/entry_arch.h|2 +
 arch/x86/include/asm/hardirq.h   |1 +
 arch/x86/include/asm/hw_irq.h|2 +
 arch/x86/include/asm/irq_remapping.h |7 +
 arch/x86/include/asm/irq_vectors.h   |1 +
 arch/x86/include/asm/kvm_host.h  |9 ++
 arch/x86/kernel/apic/apic.c  |1 +
 arch/x86/kernel/entry_64.S   |2 +
 arch/x86/kernel/irq.c|   27 
 arch/x86/kernel/irqinit.c|2 +
 arch/x86/kvm/vmx.c   |  257 +-
 arch/x86/kvm/x86.c   |   53 ++-
 drivers/iommu/amd_iommu.c|6 +
 drivers/iommu/intel_irq_remapping.c  |   83 +--
 drivers/iommu/irq_remapping.c|   20 +++
 drivers/iommu/irq_remapping.h|8 +
 include/linux/dmar.h |   30 -
 include/linux/intel-iommu.h  |1 +
 include/linux/kvm_host.h |   25 
 include/uapi/linux/kvm.h |2 +
 virt/kvm/assigned-dev.c  |  141 +++
 virt/kvm/irq_comm.c  |4 +-
 virt/kvm/irqchip.c   |   11 --
 virt/kvm/kvm_main.c  |   14 ++
 24 files changed, 667 insertions(+), 42 deletions(-)

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 08/13] KVM: Update Posted-Interrupts descriptor during VCPU scheduling

2014-11-09 Thread Feng Wu

Update Posted-Interrupts descriptor according to the
following rules:
- Before VCPU block, set 'NV' to POSTED_INTR_WAKEUP_VECTOR
- After VCPU block, set 'NV' back to POSTED_INTR_VECTOR

Signed-off-by: Feng Wu 
---
 arch/x86/include/asm/kvm_host.h |5 ++
 arch/x86/kvm/vmx.c  |   83 +++
 arch/x86/kvm/x86.c  |   16 +++
 virt/kvm/kvm_main.c |   11 +
 4 files changed, 115 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0630161..71cfe3e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -773,6 +773,8 @@ struct kvm_x86_ops {
 
void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
u64 (*get_pi_desc_addr)(struct kvm_vcpu *vcpu);
+   int (*vcpu_pre_block)(struct kvm_vcpu *vcpu);
+   void (*vcpu_post_block)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_arch_async_pf {
@@ -1095,4 +1097,7 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, 
u64 *data);
 void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
 void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
 
+int kvm_arch_vcpu_pre_block(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_post_block(struct kvm_vcpu *vcpu);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f4f..4c1a966 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9153,6 +9153,86 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
shrink_ple_window(vcpu);
 }
 
+static int vmx_vcpu_pre_block(struct kvm_vcpu *vcpu)
+{
+   struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+   struct pi_desc old;
+   struct pi_desc new;
+
+   if (!irq_post_enabled)
+   return 0;
+
+   memset(&old, 0, sizeof(old));
+   memset(&new, 0, sizeof(new));
+
+   do {
+   old.control = new.control = pi_desc->control;
+
+   /*
+* A posted-interrupt happened in the one of the
+* following two cases:
+* 1. After the latest pir-to-virr sync operation
+* in kvm_arch_vcpu_runnable() function
+* 2. In this do-while() loop, a posted-interrupt
+* occurs.
+*
+* For either of above cases, we should not block
+* the VCPU.
+*/
+   if (pi_test_on(pi_desc) == 1) {
+   /*
+* Need to set this flag, then the inject will
+* be synced from PIR to vIRR before VM-ENTRY.
+* In fact, for guest IPI case, in function
+* vmx_deliver_posted_interrupt(), this flags
+* has already been set, but if the interrupt
+* is injected by VT-d PI hardware, we need
+* to set this.
+*/
+   kvm_make_request(KVM_REQ_EVENT, vcpu);
+   return 1;
+   }
+
+   pi_clear_sn(&new);
+
+   /* set 'NV' to 'wakeup vector' */
+   new.nv = POSTED_INTR_WAKEUP_VECTOR;
+   } while (cmpxchg(&pi_desc->control, old.control, new.control)
+   != old.control);
+
+   return 0;
+}
+
+static void vmx_vcpu_post_block(struct kvm_vcpu *vcpu)
+{
+   struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+   struct pi_desc old;
+   struct pi_desc new;
+   unsigned int dest = 0;
+
+   if (!irq_post_enabled)
+   return;
+
+   pi_set_sn(pi_desc);
+
+   do {
+   old.control = new.control = pi_desc->control;
+
+   dest = cpu_physical_id(vcpu->cpu);
+
+   if (x2apic_mode)
+   new.ndst = dest;
+   else
+   new.ndst = (dest << 8) & 0xFF00;
+
+   /* set 'NV' to 'notification vector' */
+   new.nv = POSTED_INTR_VECTOR;
+   } while (cmpxchg(&pi_desc->control, old.control, new.control)
+   != old.control);
+
+   pi_clear_sn(pi_desc);
+}
+
 static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
@@ -9262,6 +9342,9 @@ static struct kvm_x86_ops vmx_x86_ops = {
.sched_in = vmx_sched_in,
 
.get_pi_desc_addr = vmx_get_pi_desc_addr,
+
+   .vcpu_pre_block = vmx_vcpu_pre_block,
+   .vcpu_post_block = vmx_vcpu_post_block,
 };
 
 static int __init vmx_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0c19d15..d0c8bb2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7746,6 +7746,22 @@ int kvm_update_pi_irte_common(struct kvm *kvm, struct 
kvm_vcpu *vcpu,
retu

[PATCH 06/13] KVM: Add some helper functions for Posted-Interrupts

2014-11-09 Thread Feng Wu

This patch adds three helper functions to manipulate the Posted-
Interrtups Decriptor.

Signed-off-by: Feng Wu 
---
 arch/x86/kvm/vmx.c |   18 ++
 1 files changed, 18 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ae91b72..f4f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -435,6 +435,24 @@ static void pi_clear_sn(struct pi_desc *pi_desc)
(unsigned long *)&pi_desc->control);
 }
 
+static void pi_set_sn(struct pi_desc *pi_desc)
+{
+   return set_bit(POSTED_INTR_SN,
+   (unsigned long *)&pi_desc->control);
+}
+
+static int pi_test_on(struct pi_desc *pi_desc)
+{
+   return test_bit(POSTED_INTR_ON,
+   (unsigned long *)&pi_desc->control);
+}
+
+static int pi_test_sn(struct pi_desc *pi_desc)
+{
+   return test_bit(POSTED_INTR_SN,
+   (unsigned long *)&pi_desc->control);
+}
+
 static bool pi_test_and_set_on(struct pi_desc *pi_desc)
 {
return test_and_set_bit(POSTED_INTR_ON,
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 13/13] iommu/vt-d: Add a command line parameter for VT-d posted-interrupts

2014-11-09 Thread Feng Wu

Enable VT-d Posted-Interrtups and add a command line
parameter for it.

Signed-off-by: Feng Wu 
---
 drivers/iommu/irq_remapping.c |9 -
 1 files changed, 8 insertions(+), 1 deletions(-)

diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
index 0e36860..3cb9429 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -23,7 +23,7 @@ int irq_remap_broken;
 int disable_sourceid_checking;
 int no_x2apic_optout;
 
-int disable_irq_post = 1;
+int disable_irq_post = 0;
 int irq_post_enabled = 0;
 EXPORT_SYMBOL_GPL(irq_post_enabled);
 
@@ -206,6 +206,13 @@ static __init int setup_irqremap(char *str)
 }
 early_param("intremap", setup_irqremap);
 
+static __init int setup_nointpost(char *str)
+{
+   disable_irq_post = 1;
+   return 0;
+}
+early_param("nointpost", setup_nointpost);
+
 void __init setup_irq_remapping_ops(void)
 {
remap_ops = &intel_irq_remap_ops;
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 12/13] iommu/vt-d: No need to migrating irq for VT-d Posted-Interrtups

2014-11-09 Thread Feng Wu

We don't need to migrate the irqs for VT-d Posted-Interrtups here.
When 'pst' is set in IRTE, the associated irq will be posted to
guests instead of interrupt remapping. The destination of the
interrupt is set in Posted-Interrupts Descriptor, and the migration
happens during VCPU scheduling.

Signed-off-by: Feng Wu 
---
 drivers/iommu/intel_irq_remapping.c |7 +++
 1 files changed, 7 insertions(+), 0 deletions(-)

diff --git a/drivers/iommu/intel_irq_remapping.c 
b/drivers/iommu/intel_irq_remapping.c
index 87c02fe..249e2b1 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -1038,6 +1038,13 @@ intel_ioapic_set_affinity(struct irq_data *data, const 
struct cpumask *mask,
if (get_irte(irq, &irte))
return -EBUSY;
 
+   /*
+* If the interrupt is for posting, it is used by guests,
+* we cannot change IRTE here.
+*/
+   if (irte.irq_post_low.pst == 1)
+   return 0;
+
err = assign_irq_vector(irq, cfg, mask);
if (err)
return err;
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 07/13] x86, irq: Define a global vector for VT-d Posted-Interrupts

2014-11-09 Thread Feng Wu

Currently, we use a global vector as the Posted-Interrupts
Notification Event for all the VCPUs in the system. We need
to introduce another global vector for VT-d Posted-Interrtups,
which will be used to wakeup the sleep VCPU when an external
interrupt from a direct-assigned device happens for that VCPU.

Signed-off-by: Feng Wu 
---
 arch/x86/include/asm/entry_arch.h  |2 ++
 arch/x86/include/asm/hardirq.h |1 +
 arch/x86/include/asm/hw_irq.h  |2 ++
 arch/x86/include/asm/irq_vectors.h |1 +
 arch/x86/kernel/entry_64.S |2 ++
 arch/x86/kernel/irq.c  |   27 +++
 arch/x86/kernel/irqinit.c  |2 ++
 7 files changed, 37 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/entry_arch.h 
b/arch/x86/include/asm/entry_arch.h
index dc5fa66..27ca0af 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -23,6 +23,8 @@ BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
 #ifdef CONFIG_HAVE_KVM
 BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
 smp_kvm_posted_intr_ipi)
+BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR,
+smp_kvm_posted_intr_wakeup_ipi)
 #endif
 
 /*
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 0f5fb6b..9866065 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -14,6 +14,7 @@ typedef struct {
 #endif
 #ifdef CONFIG_HAVE_KVM
unsigned int kvm_posted_intr_ipis;
+   unsigned int kvm_posted_intr_wakeup_ipis;
 #endif
unsigned int x86_platform_ipis; /* arch dependent */
unsigned int apic_perf_irqs;
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 4615906..559563c 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -29,6 +29,7 @@
 extern asmlinkage void apic_timer_interrupt(void);
 extern asmlinkage void x86_platform_ipi(void);
 extern asmlinkage void kvm_posted_intr_ipi(void);
+extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
 extern asmlinkage void error_interrupt(void);
 extern asmlinkage void irq_work_interrupt(void);
 
@@ -92,6 +93,7 @@ extern void trace_call_function_single_interrupt(void);
 #define trace_irq_move_cleanup_interrupt  irq_move_cleanup_interrupt
 #define trace_reboot_interrupt  reboot_interrupt
 #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
+#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi
 #endif /* CONFIG_TRACING */
 
 /* IOAPIC */
diff --git a/arch/x86/include/asm/irq_vectors.h 
b/arch/x86/include/asm/irq_vectors.h
index 5702d7e..1343349 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -105,6 +105,7 @@
 /* Vector for KVM to deliver posted interrupt IPI */
 #ifdef CONFIG_HAVE_KVM
 #define POSTED_INTR_VECTOR 0xf2
+#define POSTED_INTR_WAKEUP_VECTOR  0xf1
 #endif
 
 /*
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index df088bb..7663aaa 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1004,6 +1004,8 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR \
 #ifdef CONFIG_HAVE_KVM
 apicinterrupt3 POSTED_INTR_VECTOR \
kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR \
+   kvm_posted_intr_wakeup_ipi smp_kvm_posted_intr_wakeup_ipi
 #endif
 
 #ifdef CONFIG_X86_MCE_THRESHOLD
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 922d285..47408c3 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -237,6 +237,9 @@ __visible void smp_x86_platform_ipi(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_HAVE_KVM
+void (*wakeup_handler_callback)(void) = NULL;
+EXPORT_SYMBOL_GPL(wakeup_handler_callback);
+
 /*
  * Handler for POSTED_INTERRUPT_VECTOR.
  */
@@ -256,6 +259,30 @@ __visible void smp_kvm_posted_intr_ipi(struct pt_regs 
*regs)
 
set_irq_regs(old_regs);
 }
+
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
+{
+   struct pt_regs *old_regs = set_irq_regs(regs);
+
+   ack_APIC_irq();
+
+   irq_enter();
+
+   exit_idle();
+
+   inc_irq_stat(kvm_posted_intr_wakeup_ipis);
+
+   if (wakeup_handler_callback)
+   wakeup_handler_callback();
+
+   irq_exit();
+
+   set_irq_regs(old_regs);
+}
+
 #endif
 
 __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 4de73ee..659cde3 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -168,6 +168,8 @@ static void __init apic_intr_init(void)
 #ifdef CONFIG_HAVE_KVM
/* IPI for KVM to deliver posted interrupt */
alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
+   /* IPI for KVM to deliver interrupt to wake up tasks */
+   alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR

[PATCH 11/13] KVM: Suppress posted-interrupt when 'SN' is set

2014-11-09 Thread Feng Wu

Currently, we don't support urgent interrupt, all interrupts
are recognized as non-urgent interrupt, so we cannot send
posted-interrupt when 'SN' is set.

Signed-off-by: Feng Wu 
---
 arch/x86/kvm/vmx.c |   11 +--
 1 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 51d2c8a..495cfbd 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4306,15 +4306,22 @@ static int vmx_vm_has_apicv(struct kvm *kvm)
 static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 {
struct vcpu_vmx *vmx = to_vmx(vcpu);
-   int r;
+   int r, sn;
 
if (pi_test_and_set_pir(vector, &vmx->pi_desc))
return;
 
+   /*
+* Currently, we don't support urgent interrupt, all interrupts
+* are recognized as non-urgent interrupt, so we cannot send
+* posted-interrupt when 'SN' is set.
+*/
+   sn = pi_test_sn(&vmx->pi_desc);
+
r = pi_test_and_set_on(&vmx->pi_desc);
kvm_make_request(KVM_REQ_EVENT, vcpu);
 #ifdef CONFIG_SMP
-   if (!r && (vcpu->mode == IN_GUEST_MODE))
+   if (!r && !sn && (vcpu->mode == IN_GUEST_MODE))
apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
POSTED_INTR_VECTOR);
else
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 10/13] KVM: Add the handler for Wake-up Vector

2014-11-09 Thread Feng Wu

When VCPU is blocked and an external interrupts from assigned
devices is delivered to it, VT-d Posted-Interrupts mechanism
will deliver a interrrupt to the associated physical CPU with
Wake-up Vector. In its handler, we find the destination VCPU
and wake up it.

Signed-off-by: Feng Wu 
---
 arch/x86/include/asm/kvm_host.h |2 +
 arch/x86/kvm/vmx.c  |   52 +++
 arch/x86/kvm/x86.c  |   22 +++-
 include/linux/kvm_host.h|3 ++
 virt/kvm/kvm_main.c |3 ++
 5 files changed, 75 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 71cfe3e..ca231a3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -99,6 +99,8 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, 
int level)
 
 #define ASYNC_PF_PER_VCPU 64
 
+extern void (*wakeup_handler_callback)(void);
+
 enum kvm_reg {
VCPU_REGS_RAX = 0,
VCPU_REGS_RCX = 1,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fa77714..51d2c8a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -822,6 +822,13 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
 static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);
 static DEFINE_PER_CPU(struct desc_ptr, host_gdt);
 
+/*
+ * We maintian a per-CPU linked-list of VCPU, so in wakeup_handler() we
+ * can find which VCPU should be waken up.
+ */
+static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
+static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
+
 static unsigned long *vmx_io_bitmap_a;
 static unsigned long *vmx_io_bitmap_b;
 static unsigned long *vmx_msr_bitmap_legacy;
@@ -2813,6 +2820,8 @@ static int hardware_enable(void)
return -EBUSY;
 
INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+   INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+   spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
 
/*
 * Now we can enable the vmclear operation in kdump
@@ -9183,6 +9192,7 @@ static int vmx_vcpu_pre_block(struct kvm_vcpu *vcpu)
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
struct pi_desc old;
struct pi_desc new;
+   unsigned long flags;
 
if (!irq_post_enabled)
return 0;
@@ -9222,9 +9232,22 @@ static int vmx_vcpu_pre_block(struct kvm_vcpu *vcpu)
 
/* set 'NV' to 'wakeup vector' */
new.nv = POSTED_INTR_WAKEUP_VECTOR;
+
+   /*
+* We should save physical cpu id here, vcpu->cpu may
+* be changed due to preemption, in that case, this
+* do-while loop will run again.
+*/
+   vcpu->wakeup_cpu = vcpu->cpu;
} while (cmpxchg(&pi_desc->control, old.control, new.control)
!= old.control);
 
+   spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
+   vcpu->wakeup_cpu), flags);
+   list_add_tail(&vcpu->blocked_vcpu_list,
+   &per_cpu(blocked_vcpu_on_cpu, vcpu->wakeup_cpu));
+   spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
+   vcpu->wakeup_cpu), flags);
return 0;
 }
 
@@ -9234,6 +9257,7 @@ static void vmx_vcpu_post_block(struct kvm_vcpu *vcpu)
struct pi_desc old;
struct pi_desc new;
unsigned int dest = 0;
+   unsigned long flags;
 
if (!irq_post_enabled)
return;
@@ -9255,6 +9279,13 @@ static void vmx_vcpu_post_block(struct kvm_vcpu *vcpu)
} while (cmpxchg(&pi_desc->control, old.control, new.control)
!= old.control);
 
+   spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
+   vcpu->wakeup_cpu), flags);
+   list_del(&vcpu->blocked_vcpu_list);
+   spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
+   vcpu->wakeup_cpu), flags);
+   vcpu->wakeup_cpu = -1;
+
pi_clear_sn(pi_desc);
 }
 
@@ -9372,6 +9403,25 @@ static struct kvm_x86_ops vmx_x86_ops = {
.vcpu_post_block = vmx_vcpu_post_block,
 };
 
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+void wakeup_handler(void)
+{
+   struct kvm_vcpu *vcpu;
+   int cpu = smp_processor_id();
+
+   spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+   list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
+   blocked_vcpu_list) {
+   struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+   if (pi_test_on(pi_desc) == 1)
+   kvm_vcpu_kick(vcpu);
+   }
+   spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+}
+
 static int __init vmx_init(void)
 {
int r, i, msr;
@@ -9486,6 +9536,8 @@ static

[PATCH] Add VT-d Posted-Interrupts support in QEMU

2014-11-09 Thread Feng Wu

VT-d Posted-Interrupts is an enhancement to CPU side Posted-Interrupt.
With VT-d Posted-Interrupts enabled, external interrupts from
direct-assigned devices can be delivered to guests without VMM
intervention when guest is running in non-root mode.

This patch is used together with the patches in KVM side.

You can find the VT-d Posted-Interrtups Spec. in the following URL:
http://www.intel.com/content/www/us/en/intelligent-systems/intel-technology/vt-directed-io-spec.html

Feng Wu (1):
  x86: Update VT-d Posted-Interrupts related information

 hw/i386/kvm/pci-assign.c  |   24 
 linux-headers/linux/kvm.h |2 ++
 target-i386/kvm.c |5 +
 target-i386/kvm_i386.h|1 +
 4 files changed, 32 insertions(+), 0 deletions(-)

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 05/13] KVM: Update IRTE according to guest interrupt configuration changes

2014-11-09 Thread Feng Wu

When guest changes its interrupt configuration (such as, vector, etc.)
for direct-assigned devices, we need to update the associated IRTE
with the new guest vector, so external interrupts from the assigned
devices can be injected to guests without VM-Exit.

The current method of handling guest lowest priority interrtups
is to use a counter 'apic_arb_prio' for each VCPU, we choose the
VCPU with smallest 'apic_arb_prio' and then increase it by 1.
However, for VT-d PI, we cannot re-use this, since we no longer
have control to 'apic_arb_prio' with posted interrupt direct
delivery by Hardware.

Here, we introduce a similiar way with 'apic_arb_prio' to handle
guest lowest priority interrtups when VT-d PI is used. Here is the
ideas:
- Each VCPU has a counter 'round_robin_counter'.
- When guests sets an interrupts to lowest priority, we choose
the VCPU with smallest 'round_robin_counter' as the destination,
then increase it.

Signed-off-by: Feng Wu 
---
 arch/x86/include/asm/irq_remapping.h |6 ++
 arch/x86/include/asm/kvm_host.h  |2 +
 arch/x86/kvm/vmx.c   |   12 +++
 arch/x86/kvm/x86.c   |   11 +++
 drivers/iommu/amd_iommu.c|6 ++
 drivers/iommu/intel_irq_remapping.c  |   28 +++
 drivers/iommu/irq_remapping.c|9 ++
 drivers/iommu/irq_remapping.h|3 +
 include/linux/dmar.h |   26 ++
 include/linux/kvm_host.h |   22 +
 include/uapi/linux/kvm.h |1 +
 virt/kvm/assigned-dev.c  |  141 ++
 virt/kvm/irq_comm.c  |4 +-
 virt/kvm/irqchip.c   |   11 ---
 14 files changed, 269 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/irq_remapping.h 
b/arch/x86/include/asm/irq_remapping.h
index a3cc437..32d6cc4 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -51,6 +51,7 @@ extern void compose_remapped_msi_msg(struct pci_dev *pdev,
 unsigned int irq, unsigned int dest,
 struct msi_msg *msg, u8 hpet_id);
 extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id);
+extern int update_pi_irte(unsigned int irq, u64 pi_desc_addr, u32 vector);
 extern void panic_if_irq_remap(const char *msg);
 extern bool setup_remapped_irq(int irq,
   struct irq_cfg *cfg,
@@ -88,6 +89,11 @@ static inline int setup_hpet_msi_remapped(unsigned int irq, 
unsigned int id)
return -ENODEV;
 }
 
+static inline int update_pi_irte(unsigned int irq, u64 pi_desc_addr, u32 
vector)
+{
+   return -ENODEV;
+}
+
 static inline void panic_if_irq_remap(const char *msg)
 {
 }
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6ed0c30..0630161 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -358,6 +358,7 @@ struct kvm_vcpu_arch {
struct kvm_lapic *apic;/* kernel irqchip context */
unsigned long apic_attention;
int32_t apic_arb_prio;
+   int32_t round_robin_counter;
int mp_state;
u64 ia32_misc_enable_msr;
bool tpr_access_reporting;
@@ -771,6 +772,7 @@ struct kvm_x86_ops {
int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
 
void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
+   u64 (*get_pi_desc_addr)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_arch_async_pf {
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a4670d3..ae91b72 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -544,6 +544,11 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu 
*vcpu)
return container_of(vcpu, struct vcpu_vmx, vcpu);
 }
 
+struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
+{
+   return &(to_vmx(vcpu)->pi_desc);
+}
+
 #define VMCS12_OFFSET(x) offsetof(struct vmcs12, x)
 #define FIELD(number, name)[number] = VMCS12_OFFSET(name)
 #define FIELD64(number, name)  [number] = VMCS12_OFFSET(name), \
@@ -4280,6 +4285,11 @@ static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu 
*vcpu)
return;
 }
 
+static u64 vmx_get_pi_desc_addr(struct kvm_vcpu *vcpu)
+{
+   return __pa((u64)vcpu_to_pi_desc(vcpu));
+}
+
 /*
  * Set up the vmcs's constant host-state fields, i.e., host-state fields that
  * will not change in the lifetime of the guest.
@@ -9232,6 +9242,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
.check_nested_events = vmx_check_nested_events,
 
.sched_in = vmx_sched_in,
+
+   .get_pi_desc_addr = vmx_get_pi_desc_addr,
 };
 
 static int __init vmx_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b447a98..0c19d15 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7735,6 +7735,17 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_no

[PATCH 09/13] KVM: Change NDST field after VCPU scheduling

2014-11-09 Thread Feng Wu

This patch changes the NDST filed of Posted-Interrupts
Descriptor after VCPU is scheduled to another physical
CPU.

Signed-off-by: Feng Wu 
---
 arch/x86/kvm/vmx.c |   25 +
 1 files changed, 25 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4c1a966..fa77714 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1906,6 +1906,31 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
vmx->loaded_vmcs->cpu = cpu;
}
+
+   if (irq_post_enabled && (vcpu->cpu != cpu)) {
+   struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+   struct pi_desc old, new;
+   unsigned int dest;
+
+   memset(&old, 0, sizeof(old));
+   memset(&new, 0, sizeof(new));
+
+   pi_set_sn(pi_desc);
+
+   do {
+   old.control = new.control = pi_desc->control;
+
+   dest = cpu_physical_id(cpu);
+
+   if (x2apic_mode)
+   new.ndst = dest;
+   else
+   new.ndst = (dest << 8) & 0xFF00;
+
+   } while (cmpxchg(&pi_desc->control, old.control,
+   new.control) != old.control);
+   pi_clear_sn(pi_desc);
+   }
 }
 
 static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH] x86: Update VT-d Posted-Interrupts related information

2014-11-09 Thread Feng Wu

VT-d Posted-Interrupts(PI) is an enhancement to CPU side Posted-Interrupt.
With VT-d Posted-Interrupts enabled, external interrupts from
direct-assigned devices can be delivered to guests without VMM
involvement when guest is running in non-root mode.

If VT-d PI is supported by KVM, we need to update the IRTE with
the new guest interrtup configuration.

Signed-off-by: Feng Wu 
---
 hw/i386/kvm/pci-assign.c  |   24 
 linux-headers/linux/kvm.h |2 ++
 target-i386/kvm.c |5 +
 target-i386/kvm_i386.h|1 +
 4 files changed, 32 insertions(+), 0 deletions(-)

diff --git a/hw/i386/kvm/pci-assign.c b/hw/i386/kvm/pci-assign.c
index bb206da..e55a99b 100644
--- a/hw/i386/kvm/pci-assign.c
+++ b/hw/i386/kvm/pci-assign.c
@@ -1005,6 +1005,12 @@ static void assigned_dev_update_msi(PCIDevice *pci_dev)
 assigned_dev->intx_route.mode = PCI_INTX_DISABLED;
 assigned_dev->intx_route.irq = -1;
 assigned_dev->assigned_irq_type = ASSIGNED_IRQ_MSI;
+
+if (kvm_check_extension(kvm_state, KVM_CAP_PI)) {
+if (kvm_device_pi_update(kvm_state, assigned_dev->dev_id) < 0) {
+perror("assigned_dev_update_msi: kvm_device_pi_update");
+}
+}
 } else {
 Error *local_err = NULL;
 
@@ -1029,6 +1035,12 @@ static void assigned_dev_update_msi_msg(PCIDevice 
*pci_dev)
 
 kvm_irqchip_update_msi_route(kvm_state, assigned_dev->msi_virq[0],
  msi_get_message(pci_dev, 0));
+
+if (kvm_check_extension(kvm_state, KVM_CAP_PI)) {
+if (kvm_device_pi_update(kvm_state, assigned_dev->dev_id) < 0) {
+perror("assigned_dev_update_msi_msg: kvm_device_pi_update");
+}
+}
 }
 
 static bool assigned_dev_msix_masked(MSIXTableEntry *entry)
@@ -1149,6 +1161,12 @@ static void assigned_dev_update_msix(PCIDevice *pci_dev)
 perror("assigned_dev_enable_msix: assign irq");
 return;
 }
+
+if (kvm_check_extension(kvm_state, KVM_CAP_PI)) {
+if (kvm_device_pi_update(kvm_state, assigned_dev->dev_id) < 0) 
{
+perror("assigned_dev_update_msix: kvm_device_pi_update");
+}
+}
 }
 assigned_dev->intx_route.mode = PCI_INTX_DISABLED;
 assigned_dev->intx_route.irq = -1;
@@ -1618,6 +1636,12 @@ static void assigned_dev_msix_mmio_write(void *opaque, 
hwaddr addr,
 if (ret) {
 error_report("Error updating irq routing entry (%d)", ret);
 }
+if (kvm_check_extension(kvm_state, KVM_CAP_PI)) {
+if (kvm_device_pi_update(kvm_state, adev->dev_id) < 0) {
+perror("assigned_dev_update_msi_msg: "
+"kvm_device_pi_update");
+}
+}
 }
 }
 }
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index 2669938..b34f3c4 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -765,6 +765,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_FIXUP_HCALL 103
 #define KVM_CAP_PPC_ENABLE_HCALL 104
 #define KVM_CAP_CHECK_EXTENSION_VM 105
+#define KVM_CAP_PI 106
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1020,6 +1021,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_XEN_HVM_CONFIG_IOW(KVMIO,  0x7a, struct kvm_xen_hvm_config)
 #define KVM_SET_CLOCK _IOW(KVMIO,  0x7b, struct kvm_clock_data)
 #define KVM_GET_CLOCK _IOR(KVMIO,  0x7c, struct kvm_clock_data)
+#define KVM_ASSIGN_DEV_PI_UPDATE  _IOR(KVMIO,  0x7d, __u32)
 /* Available with KVM_CAP_PIT_STATE2 */
 #define KVM_GET_PIT2  _IOR(KVMIO,  0x9f, struct kvm_pit_state2)
 #define KVM_SET_PIT2  _IOW(KVMIO,  0xa0, struct kvm_pit_state2)
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index ccf36e8..3dd8e5e 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -2660,6 +2660,11 @@ int kvm_device_msi_assign(KVMState *s, uint32_t dev_id, 
int virq)
   KVM_DEV_IRQ_GUEST_MSI, virq);
 }
 
+int kvm_device_pi_update(KVMState *s, uint32_t dev_id)
+{
+return kvm_vm_ioctl(s, KVM_ASSIGN_DEV_PI_UPDATE, &dev_id);
+}
+
 int kvm_device_msi_deassign(KVMState *s, uint32_t dev_id)
 {
 return kvm_deassign_irq_internal(s, dev_id, KVM_DEV_IRQ_GUEST_MSI |
diff --git a/target-i386/kvm_i386.h b/target-i386/kvm_i386.h
index cac30fd..c119b3e 100644
--- a/target-i386/kvm_i386.h
+++ b/target-i386/kvm_i386.h
@@ -37,4 +37,5 @@ int kvm_device_msix_set_vector(KVMState *s, uint32_t dev_id, 
uint32_t vector,
 int kvm_device_msix_assign(KVMState *s, uint32_t dev_id);
 int kvm_device_msix_deassign(KVMState *s, uint32_t dev_id);
 
+int kvm_device_pi_update(KVMState *s, uint32_t dev_id);
 #endif
-- 
1.7.1

--
To un

[PATCH 02/13] KVM: Initialize VT-d Posted-Interrtups Descriptor

2014-11-09 Thread Feng Wu

This patch initialize the VT-d Posted-interrupt Descritpor.

Signed-off-by: Feng Wu 
---
 arch/x86/include/asm/irq_remapping.h |1 +
 arch/x86/kernel/apic/apic.c  |1 +
 arch/x86/kvm/vmx.c   |   56 -
 3 files changed, 56 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/irq_remapping.h 
b/arch/x86/include/asm/irq_remapping.h
index b7747c4..a3cc437 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -57,6 +57,7 @@ extern bool setup_remapped_irq(int irq,
   struct irq_chip *chip);
 
 void irq_remap_modify_chip_defaults(struct irq_chip *chip);
+extern int irq_post_enabled;
 
 #else  /* CONFIG_IRQ_REMAP */
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index ba6cc04..987408d 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -162,6 +162,7 @@ __setup("apicpmtimer", setup_apicpmtimer);
 #endif
 
 int x2apic_mode;
+EXPORT_SYMBOL_GPL(x2apic_mode);
 #ifdef CONFIG_X86_X2APIC
 /* x2apic enabled before OS handover */
 int x2apic_preenabled;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3e556c6..a4670d3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -45,6 +45,7 @@
 #include 
 #include 
 #include 
+#include 
 
 #include "trace.h"
 
@@ -408,13 +409,32 @@ struct nested_vmx {
 };
 
 #define POSTED_INTR_ON  0
+#define POSTED_INTR_SN  1
+
 /* Posted-Interrupt Descriptor */
 struct pi_desc {
u32 pir[8]; /* Posted interrupt requested */
-   u32 control;/* bit 0 of control is outstanding notification bit */
-   u32 rsvd[7];
+   union {
+   struct {
+   u64 on  : 1,
+   sn  : 1,
+   rsvd_1  : 13,
+   ndm : 1,
+   nv  : 8,
+   rsvd_2  : 8,
+   ndst: 32;
+   };
+   u64 control;
+   };
+   u32 rsvd[6];
 } __aligned(64);
 
+static void pi_clear_sn(struct pi_desc *pi_desc)
+{
+   return clear_bit(POSTED_INTR_SN,
+   (unsigned long *)&pi_desc->control);
+}
+
 static bool pi_test_and_set_on(struct pi_desc *pi_desc)
 {
return test_and_set_bit(POSTED_INTR_ON,
@@ -4396,6 +4416,33 @@ static void ept_set_mmio_spte_mask(void)
kvm_mmu_set_mmio_spte_mask((0x3ull << 62) | 0x6ull);
 }
 
+static bool pi_desc_init(struct vcpu_vmx *vmx)
+{
+   unsigned int dest;
+
+   if (irq_post_enabled == 0)
+   return true;
+
+   /*
+* Initialize Posted-Interrupt Descriptor
+*/
+
+   pi_clear_sn(&vmx->pi_desc);
+   vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+
+   /* Physical mode for Notificaiton Event */
+   vmx->pi_desc.ndm = 0;
+   dest = cpu_physical_id(vmx->vcpu.cpu);
+
+   if (x2apic_mode)
+   vmx->pi_desc.ndst = dest;
+   else
+   vmx->pi_desc.ndst = (dest << 8) & 0xFF00;
+
+   return true;
+}
+
+
 /*
  * Sets up the vmcs for emulated real mode.
  */
@@ -4439,6 +4486,11 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR);
vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
+
+   if (!pi_desc_init(vmx)) {
+   printk(KERN_ERR "Initialize PI descriptor error!\n");
+   return 1;
+   }
}
 
if (ple_gap) {
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 01/13] iommu/vt-d: VT-d Posted-Interrupts feature detection

2014-11-09 Thread Feng Wu

VT-d Posted-Interrupts is an enhancement to CPU side Posted-Interrupt.
With VT-d Posted-Interrupts enabled, external interrupts from
direct-assigned devices can be delivered to guests without VMM
intervention when guest is running in non-root mode.

This patch adds feature detection logic for VT-d posted-interrupt.

Signed-off-by: Feng Wu 
---
 drivers/iommu/intel_irq_remapping.c |   13 +
 drivers/iommu/irq_remapping.c   |4 
 drivers/iommu/irq_remapping.h   |5 +
 include/linux/intel-iommu.h |1 +
 4 files changed, 23 insertions(+), 0 deletions(-)

diff --git a/drivers/iommu/intel_irq_remapping.c 
b/drivers/iommu/intel_irq_remapping.c
index 7c80661..f99f0f1 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -580,6 +580,19 @@ static int __init intel_irq_remapping_supported(void)
if (!ecap_ir_support(iommu->ecap))
return 0;
 
+   /* VT-d posted-interrupt feature detection*/
+   if (disable_irq_post == 0)
+   for_each_drhd_unit(drhd) {
+   struct intel_iommu *iommu = drhd->iommu;
+
+   if (!cap_pi_support(iommu->cap)) {
+   irq_post_enabled = 0;
+   disable_irq_post = 1;
+   break;
+   }
+   irq_post_enabled = 1;
+   }
+
return 1;
 }
 
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
index 74a1767..2f8ee00 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -23,6 +23,10 @@ int irq_remap_broken;
 int disable_sourceid_checking;
 int no_x2apic_optout;
 
+int disable_irq_post = 1;
+int irq_post_enabled = 0;
+EXPORT_SYMBOL_GPL(irq_post_enabled);
+
 static struct irq_remap_ops *remap_ops;
 
 static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec);
diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
index fde250f..7bb5913 100644
--- a/drivers/iommu/irq_remapping.h
+++ b/drivers/iommu/irq_remapping.h
@@ -37,6 +37,9 @@ extern int disable_sourceid_checking;
 extern int no_x2apic_optout;
 extern int irq_remapping_enabled;
 
+extern int disable_irq_post;
+extern int irq_post_enabled;
+
 struct irq_remap_ops {
/* Check whether Interrupt Remapping is supported */
int (*supported)(void);
@@ -91,6 +94,8 @@ extern struct irq_remap_ops amd_iommu_irq_ops;
 #define irq_remapping_enabled 0
 #define disable_irq_remap 1
 #define irq_remap_broken  0
+#define disable_irq_post  1
+#define irq_post_enabled  0
 
 #endif /* CONFIG_IRQ_REMAP */
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index a65208a..5b1a124 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -87,6 +87,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 /*
  * Decoding Capability Register
  */
+#define cap_pi_support(c)  (((c) >> 59) & 1)
 #define cap_read_drain(c)  (((c) >> 55) & 1)
 #define cap_write_drain(c) (((c) >> 54) & 1)
 #define cap_max_amask_val(c)   (((c) >> 48) & 0x3f)
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 03/13] KVM: Add KVM_CAP_PI to detect VT-d Posted-Interrtups

2014-11-09 Thread Feng Wu

This patch adds KVM_CAP_PI to detect VT-d Posted-Interrtups
feature for QEMU.

Signed-off-by: Feng Wu 
---
 arch/x86/kvm/x86.c   |4 
 include/uapi/linux/kvm.h |1 +
 2 files changed, 5 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0033df3..b447a98 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -63,6 +63,7 @@
 #include 
 #include 
 #include 
+#include 
 
 #define MAX_IO_MSRS 256
 #define KVM_MAX_MCE_BANKS 32
@@ -2775,6 +2776,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long 
ext)
case KVM_CAP_TSC_DEADLINE_TIMER:
r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER);
break;
+   case KVM_CAP_PI:
+   r = irq_post_enabled;
+   break;
default:
r = 0;
break;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 6076882..7593c52 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -761,6 +761,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_FIXUP_HCALL 103
 #define KVM_CAP_PPC_ENABLE_HCALL 104
 #define KVM_CAP_CHECK_EXTENSION_VM 105
+#define KVM_CAP_PI 106
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 04/13] iommu/vt-d: Adjust 'struct irte' to better suit for VT-d Posted-Interrupts

2014-11-09 Thread Feng Wu

This patch adjusts the definition of 'struct irte', so that we can
add the VT-d Posted-Interrtups format in this structure later.

Signed-off-by: Feng Wu 
---
 drivers/iommu/intel_irq_remapping.c |   35 +++
 include/linux/dmar.h|4 ++--
 2 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/drivers/iommu/intel_irq_remapping.c 
b/drivers/iommu/intel_irq_remapping.c
index f99f0f1..776da10 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -310,9 +310,9 @@ static void set_irte_sid(struct irte *irte, unsigned int 
svt,
 {
if (disable_sourceid_checking)
svt = SVT_NO_VERIFY;
-   irte->svt = svt;
-   irte->sq = sq;
-   irte->sid = sid;
+   irte->irq_remap_high.svt = svt;
+   irte->irq_remap_high.sq = sq;
+   irte->irq_remap_high.sid = sid;
 }
 
 static int set_ioapic_sid(struct irte *irte, int apic)
@@ -917,8 +917,8 @@ static void prepare_irte(struct irte *irte, int vector,
 {
memset(irte, 0, sizeof(*irte));
 
-   irte->present = 1;
-   irte->dst_mode = apic->irq_dest_mode;
+   irte->irq_remap_low.present = 1;
+   irte->irq_remap_low.dst_mode = apic->irq_dest_mode;
/*
 * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
 * actual level or edge trigger will be setup in the IO-APIC
@@ -926,11 +926,11 @@ static void prepare_irte(struct irte *irte, int vector,
 * For more details, see the comments (in io_apic.c) explainig IO-APIC
 * irq migration in the presence of interrupt-remapping.
*/
-   irte->trigger_mode = 0;
-   irte->dlvry_mode = apic->irq_delivery_mode;
-   irte->vector = vector;
-   irte->dest_id = IRTE_DEST(dest);
-   irte->redir_hint = 1;
+   irte->irq_remap_low.trigger_mode = 0;
+   irte->irq_remap_low.dlvry_mode = apic->irq_delivery_mode;
+   irte->irq_remap_low.vector = vector;
+   irte->irq_remap_low.dest_id = IRTE_DEST(dest);
+   irte->irq_remap_low.redir_hint = 1;
 }
 
 static int intel_setup_ioapic_entry(int irq,
@@ -973,10 +973,13 @@ static int intel_setup_ioapic_entry(int irq,
"Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X "
"Avail:%X Vector:%02X Dest:%08X "
"SID:%04X SQ:%X SVT:%X)\n",
-   attr->ioapic, irte.present, irte.fpd, irte.dst_mode,
-   irte.redir_hint, irte.trigger_mode, irte.dlvry_mode,
-   irte.avail, irte.vector, irte.dest_id,
-   irte.sid, irte.sq, irte.svt);
+   attr->ioapic, irte.irq_remap_low.present,
+   irte.irq_remap_low.fpd, irte.irq_remap_low.dst_mode,
+   irte.irq_remap_low.redir_hint, irte.irq_remap_low.trigger_mode,
+   irte.irq_remap_low.dlvry_mode, irte.irq_remap_low.avail,
+   irte.irq_remap_low.vector, irte.irq_remap_low.dest_id,
+   irte.irq_remap_high.sid, irte.irq_remap_high.sq,
+   irte.irq_remap_high.svt);
 
entry = (struct IR_IO_APIC_route_entry *)route_entry;
memset(entry, 0, sizeof(*entry));
@@ -1046,8 +1049,8 @@ intel_ioapic_set_affinity(struct irq_data *data, const 
struct cpumask *mask,
return err;
}
 
-   irte.vector = cfg->vector;
-   irte.dest_id = IRTE_DEST(dest);
+   irte.irq_remap_low.vector = cfg->vector;
+   irte.irq_remap_low.dest_id = IRTE_DEST(dest);
 
/*
 * Atomically updates the IRTE with the new destination, vector
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 593fff9..8be5d42 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -159,7 +159,7 @@ struct irte {
vector  : 8,
__reserved_2: 8,
dest_id : 32;
-   };
+   } irq_remap_low;
__u64 low;
};
 
@@ -169,7 +169,7 @@ struct irte {
sq  : 2,
svt : 2,
__reserved_3: 44;
-   };
+   } irq_remap_high;
__u64 high;
};
 };
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[RFC PATCH v1 0/2] Define some VFIO interfaces for VT-d Posted-Interrupts

2014-11-20 Thread Feng Wu

VT-d Posted-Interrupts is an enhancement to CPU side Posted-Interrupt.
With VT-d Posted-Interrupts enabled, external interrupts from
direct-assigned devices can be delivered to guests without VMM
intervention when guest is running in non-root mode.

You can find the VT-d Posted-Interrtups Spec. in the following URL:
http://www.intel.com/content/www/us/en/intelligent-systems/intel-technology/vt-directed-io-spec.html

This patch set does the following things:

- Define a new VFIO group KVM_DEV_VFIO_INTERRUPT and it's attributes
KVM_DEV_VFIO_INTERRUPT_POSTING_IRQ. Qemu can use this interface to
configure VT-d PI when guest updates the interrupt configuration
(MSI/MSI-X configuration).

- Define a new VFIO API: vfio_msi_get_irq(), which can be used by KVM
to get the host irq of the assigned devices. Then KVM can update the
associated IRTE for VT-d PI.

Feng Wu (2):
  vfio: Add new interrupt group for VFIO
  vfio: Add VFIO API vfio_msi_get_irq

 Documentation/virtual/kvm/devices/vfio.txt |8 
 drivers/vfio/pci/vfio_pci.c|   10 ++
 include/linux/vfio.h   |2 ++
 include/uapi/linux/kvm.h   |   14 ++
 4 files changed, 34 insertions(+), 0 deletions(-)

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[RFC PATCH v1 2/2] vfio: Add VFIO API vfio_msi_get_irq

2014-11-20 Thread Feng Wu

This API returns the host irq for the MSI/MSI-X interrrupts.

Signed-off-by: Feng Wu 
---
 drivers/vfio/pci/vfio_pci.c |   10 ++
 include/linux/vfio.h|2 ++
 2 files changed, 12 insertions(+), 0 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 9558da3..4fb9828 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1009,6 +1009,16 @@ put_devs:
kfree(devs.devices);
 }
 
+unsigned int vfio_msi_get_irq(struct vfio_device *device, int vector, bool 
msix)
+{
+   struct vfio_pci_device *vdev =
+   (struct vfio_pci_device *)vfio_device_data(device);
+   struct pci_dev *pdev = vdev->pdev;
+
+   return msix ? vdev->msix[vector].vector : pdev->irq + vector;
+}
+EXPORT_SYMBOL_GPL(vfio_msi_get_irq);
+
 static void __exit vfio_pci_cleanup(void)
 {
pci_unregister_driver(&vfio_pci_driver);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index d320411..007ca55 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -92,6 +92,8 @@ extern void vfio_unregister_iommu_driver(
 /*
  * External user API
  */
+extern unsigned int vfio_msi_get_irq(struct vfio_device *device, int vector,
+ bool msix);
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
 extern int vfio_external_user_iommu_id(struct vfio_group *group);
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[RFC PATCH v1 1/2] vfio: Add new interrupt group for VFIO

2014-11-20 Thread Feng Wu

Add new group KVM_DEV_VFIO_INTERRUPT and command
KVM_DEV_VFIO_DEVIE_POSTING_IRQ related to it.

This is used for VT-d Posted-Interrupts setup.

Signed-off-by: Feng Wu 
---
 Documentation/virtual/kvm/devices/vfio.txt |8 
 include/uapi/linux/kvm.h   |   14 ++
 2 files changed, 22 insertions(+), 0 deletions(-)

diff --git a/Documentation/virtual/kvm/devices/vfio.txt 
b/Documentation/virtual/kvm/devices/vfio.txt
index ef51740..bd99176 100644
--- a/Documentation/virtual/kvm/devices/vfio.txt
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -13,6 +13,7 @@ VFIO-group is held by KVM.
 
 Groups:
   KVM_DEV_VFIO_GROUP
+  KVM_DEV_VFIO_INTERRUPT
 
 KVM_DEV_VFIO_GROUP attributes:
   KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
@@ -20,3 +21,10 @@ KVM_DEV_VFIO_GROUP attributes:
 
 For each, kvm_device_attr.addr points to an int32_t file descriptor
 for the VFIO group.
+
+KVM_DEV_VFIO_INTERRUPT attributes:
+  KVM_DEV_VFIO_INTERRUPT_POSTING_IRQ: Set up the interrupt configuration for
+VT-d Posted-Interrrupts
+
+For each, kvm_device_attr.addr points to struct kvm_posted_intr, which
+include the needed information for VT-d Posted-Interrupts setup.
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 6076882..5544fcc 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -943,9 +943,23 @@ struct kvm_device_attr {
__u64   addr;   /* userspace address of attr data */
 };
 
+struct virq_info {
+   __u32   index;  /* index of the msi/msix entry */
+   int virq;   /* virq of the interrupt */
+};
+
+struct kvm_posted_intr {
+   __u32   fd; /* file descriptor of the VFIO device */
+   __u32   count;
+   boolmsix;
+   struct virq_info virq_info[0];
+};
+
 #define  KVM_DEV_VFIO_GROUP1
 #define   KVM_DEV_VFIO_GROUP_ADD   1
 #define   KVM_DEV_VFIO_GROUP_DEL   2
+#define  KVM_DEV_VFIO_INTERRUPT2
+#define   KVM_DEV_VFIO_INTERRUPT_POSTING_IRQ   1
 
 enum kvm_device_type {
KVM_DEV_TYPE_FSL_MPIC_20= 1,
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[RFC PATCH v2 1/2] KVM: kvm-vfio: User API for VT-d Posted-Interrupts

2014-11-25 Thread Feng Wu

This patch adds and documents a new attribute
KVM_DEV_VFIO_DEVICE_POSTING_IRQ in KVM_DEV_VFIO_DEVICE group.
This new attribute is used for VT-d Posted-Interrupts.

When guest OS changes the interrupt configuration for an
assigned device, such as, MSI/MSIx data/address fields,
QEMU will use this IRQ attribute to tell KVM to update the
related IRTE according the VT-d Posted-Interrrupts Specification,
such as, the guest vector should be updated in the related IRTE.

Signed-off-by: Feng Wu 
---
 Documentation/virtual/kvm/devices/vfio.txt |9 +
 include/uapi/linux/kvm.h   |   10 ++
 2 files changed, 19 insertions(+), 0 deletions(-)

diff --git a/Documentation/virtual/kvm/devices/vfio.txt 
b/Documentation/virtual/kvm/devices/vfio.txt
index f7aff29..39dee86 100644
--- a/Documentation/virtual/kvm/devices/vfio.txt
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -42,3 +42,12 @@ activated before VFIO_DEVICE_SET_IRQS has been called to 
trigger the IRQ
 or associate an eventfd to it. Unforwarding can only be called while the
 signaling has been disabled with VFIO_DEVICE_SET_IRQS. If this condition is
 not satisfied, the command returns an -EBUSY.
+
+  KVM_DEV_VFIO_DEVICE_POSTING_IRQ: Use posted interrtups mechanism to post
+   the IRQ to guests.
+For this attribute, kvm_device_attr.addr points to a kvm_posted_intr struct.
+
+When guest OS changes the interrupt configuration for an assigned device,
+such as, MSI/MSIx data/address fields, QEMU will use this IRQ attribute
+to tell KVM to update the related IRTE according the VT-d Posted-Interrrupts
+Specification, such as, the guest vector should be updated in the related IRTE.
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index a269a42..e5f86ad 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -949,6 +949,7 @@ struct kvm_device_attr {
 #define  KVM_DEV_VFIO_DEVICE   2
 #define   KVM_DEV_VFIO_DEVICE_FORWARD_IRQ  1
 #define   KVM_DEV_VFIO_DEVICE_UNFORWARD_IRQ2
+#define   KVM_DEV_VFIO_DEVICE_POSTING_IRQ  3
 
 enum kvm_device_type {
KVM_DEV_TYPE_FSL_MPIC_20= 1,
@@ -973,6 +974,15 @@ struct kvm_arch_forwarded_irq {
__u32 gsi; /* gsi, ie. virtual IRQ number */
 };
 
+struct kvm_posted_intr {
+   __u32   argsz;
+   __u32   fd; /* file descriptor of the VFIO device */
+   __u32   index;  /* VFIO device IRQ index */
+   __u32   start;
+   __u32   count;
+   int virq[0];/* gsi, ie. virtual IRQ number */
+};
+
 /*
  * ioctls for VM fds
  */
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[RFC PATCH v2 0/2] kvm-vfio: implement the vfio skeleton for VT-d Posted-Interrupts

2014-11-25 Thread Feng Wu

VT-d Posted-Interrupts is an enhancement to CPU side Posted-Interrupt.
With VT-d Posted-Interrupts enabled, external interrupts from
direct-assigned devices can be delivered to guests without VMM
intervention when guest is running in non-root mode.

You can find the VT-d Posted-Interrtups Spec. in the following URL:
http://www.intel.com/content/www/us/en/intelligent-systems/intel-technology/vt-directed-io-spec.html

This patchset adds the kvm-vfio interface for VT-d Posted-Interrrupts.

In the second patch of this patchset, I leave function
kvm_update_pi_irte() empty, since the purpose of this patch set is
to implement the VFIO related stuff for VT-d PI. kvm_update_pi_irte()
will do the real things, such as, updating IRTE. In fact, I think this
function will be implemented in another file instead of vfio.c. At the
current stage I just list it here to make the build successful. After
some other dependencies (such as, irq core changes in Linux kernel) is
resolved, I will send out the rest part of the VT-d PI patchset.

This patchset is based on the following Eric's VFIO patchset:
[PATCH v3 0/8] KVM-VFIO IRQ forward control

v1->v2
- Re-use KVM_DEV_VFIO_DEVICE group for VT-d PI.
- Define a new attribute in KVM_DEV_VFIO_DEVICE group.
- Teach KVM about sturct pci_dev, and get host irq from it.

Feng Wu (2):
KVM: kvm-vfio: User API for VT-d Posted-Interrupts
KVM: kvm-vfio: implement the VFIO skeleton for VT-d Posted-Interrupts

Documentation/virtual/kvm/devices/vfio.txt |9 ++
include/uapi/linux/kvm.h | 10 +++
virt/kvm/vfio.c| 115
3 files changed, 134 insertions(+), 0 deletions(-)

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html

[RFC PATCH v2 2/2] KVM: kvm-vfio: implement the VFIO skeleton for VT-d Posted-Interrupts

2014-11-25 Thread Feng Wu

This patch adds the kvm-vfio interface for VT-d Posted-Interrrupts.
When guests updates MSI/MSI-x information for an assigned-device,
QEMU will use KVM_DEV_VFIO_DEVICE_POSTING_IRQ attribute to setup
IRTE for VT-d PI. This patch implement this IRQ attribute.

Signed-off-by: Feng Wu 
---
 virt/kvm/vfio.c |  115 +++
 1 files changed, 115 insertions(+), 0 deletions(-)

diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 6bc7001..435adf4 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -446,6 +446,115 @@ out:
return ret;
 }
 
+static int kvm_update_pi_irte(struct kvm *kvm, int host_irq, int guest_irq)
+{
+   /*
+* TODO: need to add the real code to update the related IRTE,
+* Basically, This fucntion will do the following things:
+* - Get struct kvm_kernel_irq_routing_entry from guest irq
+* - Get the destination vCPU of the interrupts
+* - Update the IRTE according the VT-d PI Spec.
+*   1) guest vector
+*   2) Posted-Interrupts descritpor addresss
+*/
+
+   return 0;
+}
+
+static int kvm_vfio_pci_get_irq_count(struct pci_dev *pdev, int irq_type)
+{
+   if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) {
+   u8 pin;
+   pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
+   if (pin)
+   return 1;
+   } else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) {
+   u8 pos;
+   u16 flags;
+
+   pos = pdev->msi_cap;
+   if (pos) {
+   pci_read_config_word(pdev,
+pos + PCI_MSI_FLAGS, &flags);
+   return 1 << ((flags & PCI_MSI_FLAGS_QMASK) >> 1);
+   }
+   } else if (irq_type == VFIO_PCI_MSIX_IRQ_INDEX) {
+   u8 pos;
+   u16 flags;
+
+   pos = pdev->msix_cap;
+   if (pos) {
+   pci_read_config_word(pdev,
+pos + PCI_MSIX_FLAGS, &flags);
+
+   return (flags & PCI_MSIX_FLAGS_QSIZE) + 1;
+   }
+   } else if (irq_type == VFIO_PCI_ERR_IRQ_INDEX)
+   if (pci_is_pcie(pdev))
+   return 1;
+
+   return 0;
+}
+
+static int kvm_vfio_set_pi(struct kvm_device *kdev, int32_t __user *argp)
+{
+   struct kvm_posted_intr pi_info;
+   int *virq;
+   unsigned long minsz;
+   struct vfio_device *vdev;
+   struct msi_desc *entry;
+   struct device *dev;
+   struct pci_dev *pdev;
+   int i, max, ret;
+
+   minsz = offsetofend(struct kvm_posted_intr, count);
+
+   if (copy_from_user(&pi_info, (void __user *)argp, minsz))
+   return -EFAULT;
+
+   if (pi_info.argsz < minsz || pi_info.index >= VFIO_PCI_NUM_IRQS)
+   return -EINVAL;
+
+   vdev = kvm_vfio_get_vfio_device(pi_info.fd);
+   if (IS_ERR(vdev))
+   return PTR_ERR(vdev);
+
+   dev = kvm_vfio_external_base_device(vdev);
+   if (!dev)
+   return -EFAULT;
+
+   pdev = to_pci_dev(dev);
+
+   max = kvm_vfio_pci_get_irq_count(pdev, pi_info.index);
+
+   if (pi_info.argsz - minsz < pi_info.count * sizeof(int) ||
+   pi_info.start >= max || pi_info.start + pi_info.count > max)
+   return -EINVAL;
+
+   virq = memdup_user((void __user *)((unsigned long)argp + minsz),
+  pi_info.count * sizeof(int));
+   if (IS_ERR(virq))
+   return PTR_ERR(virq);
+
+   for (i=0; imsi_list, list) {
+   if (entry->msi_attrib.entry_nr != pi_info.start+i)
+   continue;
+
+   ret = kvm_update_pi_irte(kdev->kvm,
+entry->irq, virq[i]);
+   if (ret) {
+   kfree(virq);
+   return -EFAULT;
+   }
+   }
+   }
+
+   kfree(virq);
+
+   return 0;
+}
+
 static int kvm_vfio_set_device(struct kvm_device *kdev, long attr, u64 arg)
 {
int32_t __user *argp = (int32_t __user *)(unsigned long)arg;
@@ -456,6 +565,9 @@ static int kvm_vfio_set_device(struct kvm_device *kdev, 
long attr, u64 arg)
case KVM_DEV_VFIO_DEVICE_UNFORWARD_IRQ:
ret = kvm_vfio_control_irq_forward(kdev, attr, argp);
break;
+   case KVM_DEV_VFIO_DEVICE_POSTING_IRQ:
+   ret = kvm_vfio_set_pi(kdev, argp);
+   break;
default:
ret = -ENXIO;
}
@@ -511,6 +623,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
case KVM_DEV_VFIO_DEVICE_UNFORWARD_IRQ:
return 0;
 #endif
+   case KVM_DEV_VFIO_DEVICE_POSTING_IRQ:
+

1 2 3 >

1 - 100 of 221 matches

Mail list logo