linux-next: manual merge of the kvm-fixes tree with Linus' tree

From: Stephen Rothwell
Date: Wed Jan 19 2022 - 17:25:35 EST

Hi all,

Today's linux-next merge of the kvm-fixes tree got a conflict in:

arch/x86/kvm/vmx/posted_intr.c

between commits:

c95717218add ("KVM: VMX: Drop unnecessary PI logic to handle impossible conditions")
29802380b679 ("KVM: VMX: Drop pointless PI.NDST update when blocking")
89ef0f21cf96 ("KVM: VMX: Save/restore IRQs (instead of CLI/STI) during PI pre/post block")
cfb0e1306a37 ("KVM: VMX: Read Posted Interrupt "control" exactly once per loop iteration")
baed82c8e489 ("KVM: VMX: Remove vCPU from PI wakeup list before updating PID.NV")
45af1bb99b72 ("KVM: VMX: Clean up PI pre/post-block WARNs")

from Linus' tree and commit:

5f02ef741a78 ("KVM: VMX: switch blocked_vcpu_on_cpu_lock to raw spinlock")

from the kvm-fixes tree.

I fixed it up (I think - see below) and can carry the fix as
necessary. This is now fixed as far as linux-next is concerned, but any
non trivial conflicts should be mentioned to your upstream maintainer
when your tree is submitted for merging. You may also want to consider
cooperating with the maintainer of the conflicting tree to minimise any
particularly complex conflicts.

It may be worth while rebasing this fix on top of Linus' current tree.

--
Cheers,
Stephen Rothwell

diff --cc arch/x86/kvm/vmx/posted_intr.c
index 88c53c521094,21ea58d25771..000000000000
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@@ -11,23 -11,11 +11,23 @@@
#include "vmx.h"

/*
- * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we
- * can find which vCPU should be waken up.
+ * Maintain a per-CPU list of vCPUs that need to be awakened by wakeup_handler()
+ * when a WAKEUP_VECTOR interrupted is posted. vCPUs are added to the list when
+ * the vCPU is scheduled out and is blocking (e.g. in HLT) with IRQs enabled.
+ * The vCPUs posted interrupt descriptor is updated at the same time to set its
+ * notification vector to WAKEUP_VECTOR, so that posted interrupt from devices
+ * wake the target vCPUs. vCPUs are removed from the list and the notification
+ * vector is reset when the vCPU is scheduled in.
*/
static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
+/*
- * Protect the per-CPU list with a per-CPU spinlock to handle task migration.
++ * Protect the per-CPU list with a per-CPU raw_spinlock to handle task migration.
+ * When a blocking vCPU is awakened _and_ migrated to a different pCPU, the
+ * ->sched_in() path will need to take the vCPU off the list of the _previous_
+ * CPU. IRQs must be disabled when taking this lock, otherwise deadlock will
+ * occur if a wakeup IRQ arrives and attempts to acquire the lock.
+ */
- static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
+ static DEFINE_PER_CPU(raw_spinlock_t, blocked_vcpu_on_cpu_lock);

static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
{
@@@ -129,25 -103,17 +129,25 @@@ static void __pi_post_block(struct kvm_
struct pi_desc old, new;
unsigned int dest;

- do {
- old.control = new.control = pi_desc->control;
- WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
- "Wakeup handler not enabled while the VCPU is blocked\n");
+ /*
+ * Remove the vCPU from the wakeup list of the _previous_ pCPU, which
+ * will not be the same as the current pCPU if the task was migrated.
+ */
- spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
++ raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_del(&vcpu->blocked_vcpu_list);
- spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
++ raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));

- dest = cpu_physical_id(vcpu->cpu);
+ dest = cpu_physical_id(vcpu->cpu);
+ if (!x2apic_mode)
+ dest = (dest << 8) & 0xFF00;

- if (x2apic_mode)
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
+ WARN(pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR,
+ "Wakeup handler not enabled while the vCPU was blocking");
+
+ do {
+ old.control = new.control = READ_ONCE(pi_desc->control);
+
+ new.ndst = dest;

/* set 'NV' to 'notification vector' */
new.nv = POSTED_INTR_VECTOR;
@@@ -170,27 -143,45 +170,27 @@@
*/
int pi_pre_block(struct kvm_vcpu *vcpu)
{
- unsigned int dest;
struct pi_desc old, new;
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+ unsigned long flags;

- if (!vmx_can_use_vtd_pi(vcpu->kvm))
+ if (!vmx_can_use_vtd_pi(vcpu->kvm) ||
+ vmx_interrupt_blocked(vcpu))
return 0;

- WARN_ON(irqs_disabled());
- local_irq_disable();
- if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
- vcpu->pre_pcpu = vcpu->cpu;
- raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
- list_add_tail(&vcpu->blocked_vcpu_list,
- &per_cpu(blocked_vcpu_on_cpu,
- vcpu->pre_pcpu));
- raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
- }
+ local_irq_save(flags);
+
+ vcpu->pre_pcpu = vcpu->cpu;
- spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
++ raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
+ list_add_tail(&vcpu->blocked_vcpu_list,
+ &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu));
- spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
++ raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
+
+ WARN(pi_desc->sn == 1,
+ "Posted Interrupt Suppress Notification set before blocking");

do {
- old.control = new.control = pi_desc->control;
-
- WARN((pi_desc->sn == 1),
- "Warning: SN field of posted-interrupts "
- "is set before blocking\n");
-
- /*
- * Since vCPU can be preempted during this process,
- * vcpu->cpu could be different with pre_pcpu, we
- * need to set pre_pcpu as the destination of wakeup
- * notification event, then we can find the right vCPU
- * to wakeup in wakeup handler if interrupts happen
- * when the vCPU is in blocked state.
- */
- dest = cpu_physical_id(vcpu->pre_pcpu);
-
- if (x2apic_mode)
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
+ old.control = new.control = READ_ONCE(pi_desc->control);

/* set 'NV' to 'wakeup vector' */
new.nv = POSTED_INTR_WAKEUP_VECTOR;
@@@ -229,10 -220,10 +229,10 @@@ void pi_wakeup_handler(void
blocked_vcpu_list) {
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);

- if (pi_test_on(pi_desc) == 1)
+ if (pi_test_on(pi_desc))
kvm_vcpu_kick(vcpu);
}
- spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+ raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
}

void __init pi_init_cpu(int cpu)

Attachment: pgpfY2jkQ6GWs.pgp
Description: OpenPGP digital signature