linux-kernel - RE: [PATCH] KVM: Destroy target device if coalesced MMIO unregistration fails

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <DS0PR11MB637301E9103F92EE5617D5B2DCEA9@DS0PR11MB6373.namprd11.prod.outlook.com>
Date:   Tue, 20 Dec 2022 03:04:55 +0000
From:   "Wang, Wei W" <wei.w.wang@...el.com>
To:     "Christopherson,, Sean" <seanjc@...gle.com>,
        Paolo Bonzini <pbonzini@...hat.com>
CC:     "kvm@...r.kernel.org" <kvm@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        柳菁峰 <liujingfeng@...nxin.com>
Subject: RE: [PATCH] KVM: Destroy target device if coalesced MMIO
 unregistration fails

On Tuesday, December 20, 2022 1:19 AM, Sean Christopherson wrote:
> diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index
> 0be80c213f7f..5ef88f5a0864 100644
> --- a/virt/kvm/coalesced_mmio.c
> +++ b/virt/kvm/coalesced_mmio.c
> @@ -187,15 +187,17 @@ int
> kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
>  			r = kvm_io_bus_unregister_dev(kvm,
>  				zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
> 
> +			kvm_iodevice_destructor(&dev->dev);
> +
>  			/*
>  			 * On failure, unregister destroys all devices on the
>  			 * bus _except_ the target device, i.e. coalesced_zones
> -			 * has been modified.  No need to restart the walk as
> -			 * there aren't any zones left.
> +			 * has been modified.  Bail after destroying the target
> +			 * device, there's no need to restart the walk as there
> +			 * aren't any zones left.
>  			 */
>  			if (r)
>  				break;
> -			kvm_iodevice_destructor(&dev->dev);
>  		}
>  	}

Another option is to let kvm_io_bus_unregister_dev handle this, and no need for callers
to make the extra kvm_iodevice_destructor() call. This simplifies the usage for callers
(e.g. reducing LOCs and no leakages like this):

diff --git a/include/kvm/iodev.h b/include/kvm/iodev.h
index d75fc4365746..56619e33251e 100644
--- a/include/kvm/iodev.h
+++ b/include/kvm/iodev.h
@@ -55,10 +55,4 @@ static inline int kvm_iodevice_write(struct kvm_vcpu *vcpu,
                                 : -EOPNOTSUPP;
 }

-static inline void kvm_iodevice_destructor(struct kvm_io_device *dev)
-{
-       if (dev->ops->destructor)
-               dev->ops->destructor(dev);
-}
-
 #endif /* __KVM_IODEV_H__ */
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 0be80c213f7f..d7135a5e76f8 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -195,7 +195,6 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
                         */
                        if (r)
                                break;
-                       kvm_iodevice_destructor(&dev->dev);
                }
        }

diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 2a3ed401ce46..1b277afb545b 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -898,7 +898,6 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
                bus = kvm_get_bus(kvm, bus_idx);
                if (bus)
                        bus->ioeventfd_count--;
-               ioeventfd_release(p);
                ret = 0;
                break;
        }
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 13e88297f999..582757ebdce6 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5200,6 +5200,12 @@ static struct notifier_block kvm_reboot_notifier = {
        .priority = 0,
 };

+static void kvm_iodevice_destructor(struct kvm_io_device *dev)
+{
+       if (dev->ops->destructor)
+               dev->ops->destructor(dev);
+}
+
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 {
        int i;
@@ -5423,7 +5429,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
                              struct kvm_io_device *dev)
 {
-       int i, j;
+       int i;
        struct kvm_io_bus *new_bus, *bus;

        lockdep_assert_held(&kvm->slots_lock);
@@ -5453,18 +5459,18 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
        rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
        synchronize_srcu_expedited(&kvm->srcu);

-       /* Destroy the old bus _after_ installing the (null) bus. */
+       /*
+        * If (null) bus is installed, destroy the old bus, including all the
+        * attached devices. Otherwise, destroy the caller's device only.
+        */
        if (!new_bus) {
                pr_err("kvm: failed to shrink bus, removing it completely\n");
-               for (j = 0; j < bus->dev_count; j++) {
-                       if (j == i)
-                               continue;
-                       kvm_iodevice_destructor(bus->range[j].dev);
-               }
+               kvm_io_bus_destroy(bus);
+               return -ENOMEM;
        }

-       kfree(bus);
-       return new_bus ? 0 : -ENOMEM;
+       kvm_iodevice_destructor(dev);
+       return 0;
 }

 struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,