| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20120119072123.GE9571@redhat.com>
Date: Thu, 19 Jan 2012 09:21:23 +0200
From: Gleb Natapov <gleb@...hat.com>
To: "Michael S. Tsirkin" <mst@...hat.com>
Cc: Alex Williamson <alex.williamson@...hat.com>,
jan.kiszka@...mens.com, Avi Kivity <avi@...hat.com>,
Marcelo Tosatti <mtosatti@...hat.com>, kvm@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH RFC] kvm: deliver msix interrupts from irq handler
On Wed, Jan 18, 2012 at 08:10:24PM +0200, Michael S. Tsirkin wrote:
> We can deliver certain interrupts, notably MSIX,
> from atomic context. Add a new API kvm_set_irq_inatomic,
> that does exactly that, and use it to implement
> an irq handler for msi.
>
> This reduces the pressure on scheduler in case
> where host and guest irq share a host cpu.
>
> Signed-off-by: Michael S. Tsirkin <mst@...hat.com>
>
> Untested.
> Note: this is on top of my host irq patch.
> Probably needs to be rebased to be independent
> and split up to new API + usage.
>
> ---
> include/linux/kvm_host.h | 2 +
> virt/kvm/assigned-dev.c | 31 +++++++++++++++++++++++++-
> virt/kvm/irq_comm.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 83 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index f0361bc..e2b89ea 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -548,6 +548,8 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
> #endif
> int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
> int host_irq);
> +int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level,
> + int host_irq);
> int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
> int irq_source_id, int level, int host_irq);
> void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
> diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
> index cc4bb7a..73bb001 100644
> --- a/virt/kvm/assigned-dev.c
> +++ b/virt/kvm/assigned-dev.c
> @@ -57,6 +57,14 @@ static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
> return index;
> }
>
> +static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id)
> +{
> + int ret = kvm_set_irq_inatomic(assigned_dev->kvm,
> + assigned_dev->irq_source_id,
> + assigned_dev->guest_irq, 1, irq);
> + return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
> +}
> +
> static irqreturn_t kvm_assigned_dev_thread(int irq, void *dev_id)
> {
> struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
> @@ -75,6 +83,23 @@ static irqreturn_t kvm_assigned_dev_thread(int irq, void *dev_id)
> }
>
> #ifdef __KVM_HAVE_MSIX
> +static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id)
> +{
> + struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
> + int index = find_index_from_host_irq(assigned_dev, irq);
> + u32 vector;
> + int ret = 0;
> +
> + if (index >= 0) {
> + vector = assigned_dev->guest_msix_entries[index].vector;
> + ret = kvm_set_irq_inatomic(assigned_dev->kvm,
> + assigned_dev->irq_source_id,
> + vector, 1, irq);
> + }
> +
> + return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
> +}
> +
> static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
> {
> struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
> @@ -266,7 +291,8 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
> }
>
> dev->host_irq = dev->dev->irq;
> - if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
> + if (request_threaded_irq(dev->host_irq, kvm_assigned_dev_msi,
> + kvm_assigned_dev_thread,
> 0, dev->irq_name, dev)) {
> pci_disable_msi(dev->dev);
> return -EIO;
> @@ -293,7 +319,8 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
>
> for (i = 0; i < dev->entries_nr; i++) {
> r = request_threaded_irq(dev->host_msix_entries[i].vector,
> - NULL, kvm_assigned_dev_thread_msix,
> + kvm_assigned_dev_msix,
> + kvm_assigned_dev_thread_msix,
> 0, dev->irq_name, dev);
> if (r)
> goto err;
> diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
> index ba892df..68cd127 100644
> --- a/virt/kvm/irq_comm.c
> +++ b/virt/kvm/irq_comm.c
> @@ -201,6 +201,58 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
> return ret;
> }
>
> +static inline struct kvm_kernel_irq_routing_entry *
> +kvm_get_entry(struct kvm *kvm, struct kvm_irq_routing_table *irq_rq, u32 irq)
> +{
> + struct kvm_kernel_irq_routing_entry *e;
> + if (likely(irq < irq_rt->nr_rt_entries))
> + hlist_for_each_entry(e, n, &irq_rt->map[irq], link)
> + if (e->type == KVM_IRQ_ROUTING_MSI)
> + return e;
> + else
> + return ERR_PTR(-EWOULDBLOCK);
> + return ERR_PTR(-EINVAL);
> +}
Unused?
> +
> +/*
> + * Deliver an IRQ in an atomic context if we can, or return a failure,
> + * user can retry in a process context.
> + * Return value:
> + * -EWOULDBLOCK Can't deliver in atomic context
> + * < 0 Interrupt was ignored (masked or not delivered for other reasons)
> + * = 0 Interrupt was coalesced (previous irq is still pending)
> + * > 0 Number of CPUs interrupt was delivered to
> + */
> +int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level,
> + int host_irq)
> +{
> + struct kvm_kernel_irq_routing_entry *e;
> + int ret = -EINVAL;
> + struct kvm_irq_routing_table *irq_rt;
> + struct hlist_node *n;
> +
> + trace_kvm_set_irq(irq, level, irq_source_id);
> +
> + /*
> + * We know MSI are safe in interrupt context. They are also
> + * easy as there's a single routing entry for these GSIs.
> + * So only handle MSI in an atomic context, for now.
> + */
> + rcu_read_lock_bh();
_bh?
/**
* rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section
*
* This is equivalent of rcu_read_lock(), but to be used when updates
* are being done using call_rcu_bh() or synchronize_rcu_bh().
....
Since updates to irq routing table are not done using _bh variant I
doubt rcu_read_lock_bh() is justified here.
> + irq_rt = rcu_dereference(kvm->irq_routing);
> + if (irq < irq_rt->nr_rt_entries)
> + hlist_for_each_entry(e, n, &irq_rt->map[irq], link) {
> + if (ei->type == KVM_IRQ_ROUTING_MSI)
> + ret = kvm_set_msi(e, kvm, irq_source_id, level,
> + host_irq);
> + else
> + ret = -EWOULDBLOCK;
> + break;
> + }
> + rcu_read_unlock_bh();
> + return ret;
> +}
> +
Share implementation with kvm_set_irq().
> void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
> {
> struct kvm_irq_ack_notifier *kian;
> --
> 1.7.8.2.325.g247f9
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
--
Gleb.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists