[PATCH V6 3/6] kvm: fix double free for fast mmio eventfd

From: Jason Wang <jasowang@redhat.com>
To: gleb@kernel.org, pbonzini@redhat.com, kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org
Cc: mst@redhat.com, cornelia.huck@de.ibm.com,
	Jason Wang <jasowang@redhat.com>,
	stable@vger.kernel.org
Subject: [PATCH V6 3/6] kvm: fix double free for fast mmio eventfd
Date: Tue, 15 Sep 2015 14:41:56 +0800	[thread overview]
Message-ID: <1442299319-5253-4-git-send-email-jasowang@redhat.com> (raw)
In-Reply-To: <1442299319-5253-1-git-send-email-jasowang@redhat.com>

We register wildcard mmio eventfd on two buses, once for KVM_MMIO_BUS
and once on KVM_FAST_MMIO_BUS but with a single iodev
instance. This will lead to an issue: kvm_io_bus_destroy() knows
nothing about the devices on two buses pointing to a single dev. Which
will lead to double free[1] during exit. Fix this by allocating two
instances of iodevs then registering one on KVM_MMIO_BUS and another
on KVM_FAST_MMIO_BUS.

CPU: 1 PID: 2894 Comm: qemu-system-x86 Not tainted 3.19.0-26-generic #28-Ubuntu
Hardware name: LENOVO 2356BG6/2356BG6, BIOS G7ET96WW (2.56 ) 09/12/2013
task: ffff88009ae0c4b0 ti: ffff88020e7f0000 task.ti: ffff88020e7f0000
RIP: 0010:[<ffffffffc07e25d8>]  [<ffffffffc07e25d8>] ioeventfd_release+0x28/0x60 [kvm]
RSP: 0018:ffff88020e7f3bc8  EFLAGS: 00010292
RAX: dead000000200200 RBX: ffff8801ec19c900 RCX: 000000018200016d
RDX: ffff8801ec19cf80 RSI: ffffea0008bf1d40 RDI: ffff8801ec19c900
RBP: ffff88020e7f3bd8 R08: 000000002fc75a01 R09: 000000018200016d
R10: ffffffffc07df6ae R11: ffff88022fc75a98 R12: ffff88021e7cc000
R13: ffff88021e7cca48 R14: ffff88021e7cca50 R15: ffff8801ec19c880
FS:  00007fc1ee3e6700(0000) GS:ffff88023e240000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f8f389d8000 CR3: 000000023dc13000 CR4: 00000000001427e0
Stack:
ffff88021e7cc000 0000000000000000 ffff88020e7f3be8 ffffffffc07e2622
ffff88020e7f3c38 ffffffffc07df69a ffff880232524160 ffff88020e792d80
 0000000000000000 ffff880219b78c00 0000000000000008 ffff8802321686a8
Call Trace:
[<ffffffffc07e2622>] ioeventfd_destructor+0x12/0x20 [kvm]
[<ffffffffc07df69a>] kvm_put_kvm+0xca/0x210 [kvm]
[<ffffffffc07df818>] kvm_vcpu_release+0x18/0x20 [kvm]
[<ffffffff811f69f7>] __fput+0xe7/0x250
[<ffffffff811f6bae>] ____fput+0xe/0x10
[<ffffffff81093f04>] task_work_run+0xd4/0xf0
[<ffffffff81079358>] do_exit+0x368/0xa50
[<ffffffff81082c8f>] ? recalc_sigpending+0x1f/0x60
[<ffffffff81079ad5>] do_group_exit+0x45/0xb0
[<ffffffff81085c71>] get_signal+0x291/0x750
[<ffffffff810144d8>] do_signal+0x28/0xab0
[<ffffffff810f3a3b>] ? do_futex+0xdb/0x5d0
[<ffffffff810b7028>] ? __wake_up_locked_key+0x18/0x20
[<ffffffff810f3fa6>] ? SyS_futex+0x76/0x170
[<ffffffff81014fc9>] do_notify_resume+0x69/0xb0
[<ffffffff817cb9af>] int_signal+0x12/0x17
Code: 5d c3 90 0f 1f 44 00 00 55 48 89 e5 53 48 89 fb 48 83 ec 08 48 8b 7f 20 e8 06 d6 a5 c0 48 8b 43 08 48 8b 13 48 89 df 48 89 42 08 <48> 89 10 48 b8 00 01 10 00 00
 RIP  [<ffffffffc07e25d8>] ioeventfd_release+0x28/0x60 [kvm]
 RSP <ffff88020e7f3bc8>

Cc: stable@vger.kernel.org
Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 virt/kvm/eventfd.c | 43 +++++++++++++++++++++++++------------------
 1 file changed, 25 insertions(+), 18 deletions(-)

diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 0829c7f..79db453 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -817,16 +817,6 @@ static int kvm_assign_ioeventfd_idx(struct kvm *kvm,
 	if (ret < 0)
 		goto unlock_fail;
 
-	/* When length is ignored, MMIO is also put on a separate bus, for
-	 * faster lookups.
-	 */
-	if (!args->len && bus_idx == KVM_MMIO_BUS) {
-		ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS,
-					      p->addr, 0, &p->dev);
-		if (ret < 0)
-			goto register_fail;
-	}
-
 	kvm->buses[bus_idx]->ioeventfd_count++;
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
@@ -834,8 +824,6 @@ static int kvm_assign_ioeventfd_idx(struct kvm *kvm,
 
 	return 0;
 
-register_fail:
-	kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
 unlock_fail:
 	mutex_unlock(&kvm->slots_lock);
 
@@ -874,10 +862,6 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
-		if (!p->length && p->bus_idx == KVM_MMIO_BUS) {
-			kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS,
-						  &p->dev);
-		}
 		kvm->buses[bus_idx]->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
@@ -894,14 +878,19 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 static int kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
 	enum kvm_bus bus_idx = ioeventfd_bus_from_flags(args->flags);
+	int ret = kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
+
+	if (!args->len && bus_idx == KVM_MMIO_BUS)
+		kvm_deassign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);
 
-	return kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
+	return ret;
 }
 
 static int
 kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
 	enum kvm_bus              bus_idx;
+	int ret;
 
 	bus_idx = ioeventfd_bus_from_flags(args->flags);
 	/* must be natural-word sized, or 0 to ignore length */
@@ -930,7 +919,25 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 			   KVM_IOEVENTFD_FLAG_DATAMATCH))
 		return -EINVAL;
 
-	return kvm_assign_ioeventfd_idx(kvm, bus_idx, args);
+	ret = kvm_assign_ioeventfd_idx(kvm, bus_idx, args);
+	if (ret)
+		goto fail;
+
+	/* When length is ignored, MMIO is also put on a separate bus, for
+	 * faster lookups.
+	 */
+	if (!args->len && bus_idx == KVM_MMIO_BUS) {
+		ret = kvm_assign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);
+		if (ret < 0)
+			goto fast_fail;
+	}
+
+	return 0;
+
+fast_fail:
+	kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
+fail:
+	return ret;
 }
 
 int
-- 
2.1.4

