[PATCH v1 1/1] KVM: s390: pv: fix asynchronous teardown for small VMs

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On machines without the Destroy Secure Configuration Fast UVC, the
topmost level of page tables is set aside and freed asynchronously
as last step of the asynchronous teardown.

Each gmap has a host_to_guest radix tree mapping host (userspace)
addresses (with 1M granularity) to gmap segment table entries (pmds).

If a guest is smaller than 2GB, the topmost level of page tables is the
segment table (i.e. there are only 2 levels). Replacing it means that
the pointers in the host_to_guest mapping would become stale and cause
all kinds of nasty issues.

This patch fixes the issue by synchronously destroying all guests with
only 2 levels of page tables in kvm_s390_pv_set_aside. This will
speed up the process and avoid the issue altogether.

Update s390_replace_asce so it refuses to replace segment type ASCEs.

Signed-off-by: Claudio Imbrenda <imbrenda@xxxxxxxxxxxxx>
Fixes: fb491d5500a7 ("KVM: s390: pv: asynchronous destroy for reboot")
---
 arch/s390/kvm/pv.c  | 35 ++++++++++++++++++++---------------
 arch/s390/mm/gmap.c |  7 +++++++
 2 files changed, 27 insertions(+), 15 deletions(-)

diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index e032ebbf51b9..ceb8cb628d62 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -39,6 +39,7 @@ struct pv_vm_to_be_destroyed {
 	u64 handle;
 	void *stor_var;
 	unsigned long stor_base;
+	bool small;
 };
 
 static void kvm_s390_clear_pv_state(struct kvm *kvm)
@@ -318,7 +319,11 @@ int kvm_s390_pv_set_aside(struct kvm *kvm, u16 *rc, u16 *rrc)
 	if (!priv)
 		return -ENOMEM;
 
-	if (is_destroy_fast_available()) {
+	if ((kvm->arch.gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT) {
+		/* No need to do things asynchronously for VMs under 2GB */
+		res = kvm_s390_pv_deinit_vm(kvm, rc, rrc);
+		priv->small = true;
+	} else if (is_destroy_fast_available()) {
 		res = kvm_s390_pv_deinit_vm_fast(kvm, rc, rrc);
 	} else {
 		priv->stor_var = kvm->arch.pv.stor_var;
@@ -335,7 +340,8 @@ int kvm_s390_pv_set_aside(struct kvm *kvm, u16 *rc, u16 *rrc)
 		return res;
 	}
 
-	kvm_s390_destroy_lower_2g(kvm);
+	if (!priv->small)
+		kvm_s390_destroy_lower_2g(kvm);
 	kvm_s390_clear_pv_state(kvm);
 	kvm->arch.pv.set_aside = priv;
 
@@ -418,7 +424,10 @@ int kvm_s390_pv_deinit_cleanup_all(struct kvm *kvm, u16 *rc, u16 *rrc)
 
 	/* If a previous protected VM was set aside, put it in the need_cleanup list */
 	if (kvm->arch.pv.set_aside) {
-		list_add(kvm->arch.pv.set_aside, &kvm->arch.pv.need_cleanup);
+		if (((struct pv_vm_to_be_destroyed *)kvm->arch.pv.set_aside)->small)
+			kfree(kvm->arch.pv.set_aside);
+		else
+			list_add(kvm->arch.pv.set_aside, &kvm->arch.pv.need_cleanup);
 		kvm->arch.pv.set_aside = NULL;
 	}
 
@@ -485,26 +494,22 @@ int kvm_s390_pv_deinit_aside_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	if (!p)
 		return -EINVAL;
 
-	/* When a fatal signal is received, stop immediately */
-	if (s390_uv_destroy_range_interruptible(kvm->mm, 0, TASK_SIZE_MAX))
+	if (p->small)
 		goto done;
-	if (kvm_s390_pv_dispose_one_leftover(kvm, p, rc, rrc))
-		ret = -EIO;
-	kfree(p);
-	p = NULL;
-done:
-	/*
-	 * p is not NULL if we aborted because of a fatal signal, in which
-	 * case queue the leftover for later cleanup.
-	 */
-	if (p) {
+	/* When a fatal signal is received, stop immediately */
+	if (s390_uv_destroy_range_interruptible(kvm->mm, 0, TASK_SIZE_MAX)) {
 		mutex_lock(&kvm->lock);
 		list_add(&p->list, &kvm->arch.pv.need_cleanup);
 		mutex_unlock(&kvm->lock);
 		/* Did not finish, but pretend things went well */
 		*rc = UVC_RC_EXECUTED;
 		*rrc = 42;
+		return 0;
 	}
+	if (kvm_s390_pv_dispose_one_leftover(kvm, p, rc, rrc))
+		ret = -EIO;
+done:
+	kfree(p);
 	return ret;
 }
 
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 5a716bdcba05..2267cf9819b2 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2833,6 +2833,9 @@ EXPORT_SYMBOL_GPL(s390_unlist_old_asce);
  * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy
  * @gmap: the gmap whose ASCE needs to be replaced
  *
+ * If the ASCE is a SEGMENT type then this function will return -EINVAL,
+ * otherwise the pointers in the host_to_guest radix tree will keep pointing
+ * to the wrong pages, causing use-after-free and memory corruption.
  * If the allocation of the new top level page table fails, the ASCE is not
  * replaced.
  * In any case, the old ASCE is always removed from the gmap CRST list.
@@ -2847,6 +2850,10 @@ int s390_replace_asce(struct gmap *gmap)
 
 	s390_unlist_old_asce(gmap);
 
+	/* Replacing segment type ASCEs would cause serious issues */
+	if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT)
+		return -EINVAL;
+
 	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
 	if (!page)
 		return -ENOMEM;
-- 
2.39.2




[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Index of Archives]     [Kernel Development]     [Kernel Newbies]     [IDE]     [Security]     [Git]     [Netfilter]     [Bugtraq]     [Yosemite Info]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux ATA RAID]     [Samba]     [Linux Media]     [Device Mapper]

  Powered by Linux