[PATCH v6 14/18] vmx: posted-interrupt handling when vCPU is blocked

[Feng Wu <feng.wu@intel.com>]

This patch includes the following aspects:
- Add a global vector to wake up the blocked vCPU
  when an interrupt is being posted to it (This
  part was sugguested by Yang Zhang <yang.z.zhang@intel.com>).
- Adds a new per-vCPU tasklet to wakeup the blocked
  vCPU. It can be used in the case vcpu_unblock
  cannot be called directly.
- Define two per-cpu variables:
      * pi_blocked_vcpu:
      A list storing the vCPUs which were blocked on this pCPU.

      * pi_blocked_vcpu_lock:
      The spinlock to protect pi_blocked_vcpu.

CC: Kevin Tian <kevin.tian@intel.com>
CC: Keir Fraser <keir@xen.org>
CC: Jan Beulich <jbeulich@suse.com>
CC: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Feng Wu <feng.wu@intel.com>
---
v6:
- Fix some typos
- Ack the interrupt right after the spin_unlock in pi_wakeup_interrupt()

v4:
- Use local variables in pi_wakeup_interrupt()
- Remove vcpu from the blocked list when pi_desc.on==1, this
- avoid kick vcpu multiple times.
- Remove tasklet

v3:
- This patch is generated by merging the following three patches in v2:
   [RFC v2 09/15] Add a new per-vCPU tasklet to wakeup the blocked vCPU
   [RFC v2 10/15] vmx: Define two per-cpu variables
   [RFC v2 11/15] vmx: Add a global wake-up vector for VT-d Posted-Interrupts
- rename 'vcpu_wakeup_tasklet' to 'pi_vcpu_wakeup_tasklet'
- Move the definition of 'pi_vcpu_wakeup_tasklet' to 'struct arch_vmx_struct'
- rename 'vcpu_wakeup_tasklet_handler' to 'pi_vcpu_wakeup_tasklet_handler'
- Make pi_wakeup_interrupt() static
- Rename 'blocked_vcpu_list' to 'pi_blocked_vcpu_list'
- move 'pi_blocked_vcpu_list' to 'struct arch_vmx_struct'
- Rename 'blocked_vcpu' to 'pi_blocked_vcpu'
- Rename 'blocked_vcpu_lock' to 'pi_blocked_vcpu_lock'

 xen/arch/x86/hvm/vmx/vmcs.c        |  3 ++
 xen/arch/x86/hvm/vmx/vmx.c         | 64 ++++++++++++++++++++++++++++++++++++++
 xen/include/asm-x86/hvm/vmx/vmcs.h |  3 ++
 xen/include/asm-x86/hvm/vmx/vmx.h  |  5 +++
 4 files changed, 75 insertions(+)

diff --git a/xen/arch/x86/hvm/vmx/vmcs.c b/xen/arch/x86/hvm/vmx/vmcs.c
index 28c553f..2dabf16 100644
--- a/xen/arch/x86/hvm/vmx/vmcs.c
+++ b/xen/arch/x86/hvm/vmx/vmcs.c
@@ -661,6 +661,9 @@ int vmx_cpu_up(void)
     if ( cpu_has_vmx_vpid )
         vpid_sync_all();
 
+    INIT_LIST_HEAD(&per_cpu(pi_blocked_vcpu, cpu));
+    spin_lock_init(&per_cpu(pi_blocked_vcpu_lock, cpu));
+
     return 0;
 }
 
diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 2c1c770..9cde9a4 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -83,7 +83,15 @@ static int vmx_msr_write_intercept(unsigned int msr, uint64_t msr_content);
 static void vmx_invlpg_intercept(unsigned long vaddr);
 static int vmx_vmfunc_intercept(struct cpu_user_regs *regs);
 
+/*
+ * We maintain a per-CPU linked-list of vCPU, so in PI wakeup handler we
+ * can find which vCPU should be woken up.
+ */
+DEFINE_PER_CPU(struct list_head, pi_blocked_vcpu);
+DEFINE_PER_CPU(spinlock_t, pi_blocked_vcpu_lock);
+
 uint8_t __read_mostly posted_intr_vector;
+uint8_t __read_mostly pi_wakeup_vector;
 
 static int vmx_domain_initialise(struct domain *d)
 {
@@ -106,6 +114,9 @@ static int vmx_vcpu_initialise(struct vcpu *v)
 
     spin_lock_init(&v->arch.hvm_vmx.vmcs_lock);
 
+    INIT_LIST_HEAD(&v->arch.hvm_vmx.pi_blocked_vcpu_list);
+    INIT_LIST_HEAD(&v->arch.hvm_vmx.pi_vcpu_on_set_list);
+
     v->arch.schedule_tail    = vmx_do_resume;
     v->arch.ctxt_switch_from = vmx_ctxt_switch_from;
     v->arch.ctxt_switch_to   = vmx_ctxt_switch_to;
@@ -1976,6 +1987,54 @@ static struct hvm_function_table __initdata vmx_function_table = {
     .altp2m_vcpu_emulate_vmfunc = vmx_vcpu_emulate_vmfunc,
 };
 
+/*
+ * Handle VT-d posted-interrupt when VCPU is blocked.
+ */
+static void pi_wakeup_interrupt(struct cpu_user_regs *regs)
+{
+    struct arch_vmx_struct *vmx, *tmp;
+    struct vcpu *v;
+    spinlock_t *lock = &this_cpu(pi_blocked_vcpu_lock);
+    struct list_head *blocked_vcpus = &this_cpu(pi_blocked_vcpu);
+    LIST_HEAD(list);
+
+    spin_lock(lock);
+
+    /*
+     * XXX: The length of the list depends on how many vCPU is current
+     * blocked on this specific pCPU. This may hurt the interrupt latency
+     * if the list grows to too many entries.
+     */
+    list_for_each_entry_safe(vmx, tmp, blocked_vcpus, pi_blocked_vcpu_list)
+    {
+        if ( pi_test_on(&vmx->pi_desc) )
+        {
+            list_del_init(&vmx->pi_blocked_vcpu_list);
+
+            /*
+             * We cannot call vcpu_unblock here, since it also needs
+             * 'pi_blocked_vcpu_lock', we store the vCPUs with ON
+             * set in another list and unblock them after we release
+             * 'pi_blocked_vcpu_lock'.
+             */
+            list_add_tail(&vmx->pi_vcpu_on_set_list, &list);
+        }
+    }
+
+    spin_unlock(lock);
+
+    ack_APIC_irq();
+
+    list_for_each_entry_safe(vmx, tmp, &list, pi_vcpu_on_set_list)
+    {
+        v = container_of(vmx, struct vcpu, arch.hvm_vmx);
+        list_del_init(&vmx->pi_vcpu_on_set_list);
+        vcpu_unblock(v);
+    }
+
+    this_cpu(irq_count)++;
+}
+
 const struct hvm_function_table * __init start_vmx(void)
 {
     set_in_cr4(X86_CR4_VMXE);
@@ -2013,7 +2072,12 @@ const struct hvm_function_table * __init start_vmx(void)
     }
 
     if ( cpu_has_vmx_posted_intr_processing )
+    {
         alloc_direct_apic_vector(&posted_intr_vector, event_check_interrupt);
+
+        if ( iommu_intpost )
+            alloc_direct_apic_vector(&pi_wakeup_vector, pi_wakeup_interrupt);
+    }
     else
     {
         vmx_function_table.deliver_posted_intr = NULL;
diff --git a/xen/include/asm-x86/hvm/vmx/vmcs.h b/xen/include/asm-x86/hvm/vmx/vmcs.h
index 7e81752..9a986d0 100644
--- a/xen/include/asm-x86/hvm/vmx/vmcs.h
+++ b/xen/include/asm-x86/hvm/vmx/vmcs.h
@@ -161,6 +161,9 @@ struct arch_vmx_struct {
     struct page_info     *vmwrite_bitmap;
 
     struct page_info     *pml_pg;
+
+    struct list_head     pi_blocked_vcpu_list;
+    struct list_head     pi_vcpu_on_set_list;
 };
 
 int vmx_create_vmcs(struct vcpu *v);
diff --git a/xen/include/asm-x86/hvm/vmx/vmx.h b/xen/include/asm-x86/hvm/vmx/vmx.h
index 03c529c..3fd66ba 100644
--- a/xen/include/asm-x86/hvm/vmx/vmx.h
+++ b/xen/include/asm-x86/hvm/vmx/vmx.h
@@ -28,6 +28,11 @@
 #include <asm/hvm/trace.h>
 #include <asm/hvm/vmx/vmcs.h>
 
+DECLARE_PER_CPU(struct list_head, pi_blocked_vcpu);
+DECLARE_PER_CPU(spinlock_t, pi_blocked_vcpu_lock);
+
+extern uint8_t pi_wakeup_vector;
+
 typedef union {
     struct {
         u64 r       :   1,  /* bit 0 - Read permission */
-- 
2.1.0