LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
* [PATCH] virt: acrn: Do hcall_destroy_vm() before resource release
@ 2021-07-22  6:27 Fei Li
  2021-07-27 14:47 ` Greg Kroah-Hartman
  0 siblings, 1 reply; 3+ messages in thread
From: Fei Li @ 2021-07-22  6:27 UTC (permalink / raw)
  To: Greg Kroah-Hartman
  Cc: linux-kernel, Shuo Liu, Reinette Chatre, Zhi Wang, Fei Li, yu1.wang

From: Shuo Liu <shuo.a.liu@intel.com>

The ACRN hypervisor has scenarios which could run a real-time guest VM.
The real-time guest VM occupies dedicated CPU cores, be assigned with
dedicated PCI devices. It can run without the Service VM after boot up.
hcall_destroy_vm() returns failure when a real-time guest VM refuses.
The clearing of flag ACRN_VM_FLAG_DESTROYED causes some kernel resource
double-freed in a later acrn_vm_destroy().

Do hcall_destroy_vm() before resource release to drop this chance to
destroy the VM if hypercall fails.

Fixes: 9c5137aedd11 ("virt: acrn: Introduce VM management interfaces")
Signed-off-by: Shuo Liu <shuo.a.liu@intel.com>
Signed-off-by: Fei Li <fei1.li@intel.com>
---
 drivers/virt/acrn/vm.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c
index 0d002a355a93..fbc9f1042000 100644
--- a/drivers/virt/acrn/vm.c
+++ b/drivers/virt/acrn/vm.c
@@ -64,6 +64,14 @@ int acrn_vm_destroy(struct acrn_vm *vm)
 	    test_and_set_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags))
 		return 0;
 
+	ret = hcall_destroy_vm(vm->vmid);
+	if (ret < 0) {
+		dev_err(acrn_dev.this_device,
+			"Failed to destroy VM %u\n", vm->vmid);
+		clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags);
+		return ret;
+	}
+
 	/* Remove from global VM list */
 	write_lock_bh(&acrn_vm_list_lock);
 	list_del_init(&vm->list);
@@ -78,14 +86,6 @@ int acrn_vm_destroy(struct acrn_vm *vm)
 		vm->monitor_page = NULL;
 	}
 
-	ret = hcall_destroy_vm(vm->vmid);
-	if (ret < 0) {
-		dev_err(acrn_dev.this_device,
-			"Failed to destroy VM %u\n", vm->vmid);
-		clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags);
-		return ret;
-	}
-
 	acrn_vm_all_ram_unmap(vm);
 
 	dev_dbg(acrn_dev.this_device, "VM %u destroyed.\n", vm->vmid);

base-commit: c453db6cd96418c79702eaf38259002755ab23ff
-- 
2.17.1


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] virt: acrn: Do hcall_destroy_vm() before resource release
  2021-07-22  6:27 [PATCH] virt: acrn: Do hcall_destroy_vm() before resource release Fei Li
@ 2021-07-27 14:47 ` Greg Kroah-Hartman
  2021-07-29  3:22   ` Li Fei1
  0 siblings, 1 reply; 3+ messages in thread
From: Greg Kroah-Hartman @ 2021-07-27 14:47 UTC (permalink / raw)
  To: Fei Li; +Cc: linux-kernel, Shuo Liu, Reinette Chatre, Zhi Wang, yu1.wang

On Thu, Jul 22, 2021 at 02:27:36PM +0800, Fei Li wrote:
> From: Shuo Liu <shuo.a.liu@intel.com>
> 
> The ACRN hypervisor has scenarios which could run a real-time guest VM.
> The real-time guest VM occupies dedicated CPU cores, be assigned with
> dedicated PCI devices. It can run without the Service VM after boot up.
> hcall_destroy_vm() returns failure when a real-time guest VM refuses.
> The clearing of flag ACRN_VM_FLAG_DESTROYED causes some kernel resource
> double-freed in a later acrn_vm_destroy().
> 
> Do hcall_destroy_vm() before resource release to drop this chance to
> destroy the VM if hypercall fails.
> 
> Fixes: 9c5137aedd11 ("virt: acrn: Introduce VM management interfaces")
> Signed-off-by: Shuo Liu <shuo.a.liu@intel.com>
> Signed-off-by: Fei Li <fei1.li@intel.com>
> ---

Do you also want this backported to older kernels?  If so, you need to
put a cc: stable in here, right?  I'll go add it myself, but be more
careful next time please.

greg k-h

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] virt: acrn: Do hcall_destroy_vm() before resource release
  2021-07-27 14:47 ` Greg Kroah-Hartman
@ 2021-07-29  3:22   ` Li Fei1
  0 siblings, 0 replies; 3+ messages in thread
From: Li Fei1 @ 2021-07-29  3:22 UTC (permalink / raw)
  To: Greg Kroah-Hartman
  Cc: linux-kernel, shuox.liu, reinette.chatre, zhi.a.wang, yu1.wang

On Tue, Jul 27, 2021 at 10:47:58PM +0800, Greg Kroah-Hartman wrote:
> On Thu, Jul 22, 2021 at 02:27:36PM +0800, Fei Li wrote:
> > From: Shuo Liu <shuo.a.liu@intel.com>
> >
> > The ACRN hypervisor has scenarios which could run a real-time guest VM.
> > The real-time guest VM occupies dedicated CPU cores, be assigned with
> > dedicated PCI devices. It can run without the Service VM after boot up.
> > hcall_destroy_vm() returns failure when a real-time guest VM refuses.
> > The clearing of flag ACRN_VM_FLAG_DESTROYED causes some kernel resource
> > double-freed in a later acrn_vm_destroy().
> >
> > Do hcall_destroy_vm() before resource release to drop this chance to
> > destroy the VM if hypercall fails.
> >
> > Fixes: 9c5137aedd11 ("virt: acrn: Introduce VM management interfaces")
> > Signed-off-by: Shuo Liu <shuo.a.liu@intel.com>
> > Signed-off-by: Fei Li <fei1.li@intel.com>
> > ---
> 
> Do you also want this backported to older kernels?  If so, you need to
> put a cc: stable in here, right?  I'll go add it myself, but be more
> careful next time please.
yes, thanks for your kind reminder.
I will pay great attention next time.

> 
> greg k-h

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2021-07-29  3:22 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-07-22  6:27 [PATCH] virt: acrn: Do hcall_destroy_vm() before resource release Fei Li
2021-07-27 14:47 ` Greg Kroah-Hartman
2021-07-29  3:22   ` Li Fei1

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).