summaryrefslogtreecommitdiffstats
path: root/virt
diff options
context:
space:
mode:
authorDavid Matlack <dmatlack@google.com>2014-08-18 15:46:06 -0700
committerPaolo Bonzini <pbonzini@redhat.com>2014-09-03 10:03:41 +0200
commitee3d1570b58677885b4552bce8217fda7b226a68 (patch)
treebfc831cf5b242321553fbd6a702085a1916fd04c /virt
parent00f034a12fdd81210d58116326d92780aac5c238 (diff)
downloadop-kernel-dev-ee3d1570b58677885b4552bce8217fda7b226a68.zip
op-kernel-dev-ee3d1570b58677885b4552bce8217fda7b226a68.tar.gz
kvm: fix potentially corrupt mmio cache
vcpu exits and memslot mutations can run concurrently as long as the vcpu does not aquire the slots mutex. Thus it is theoretically possible for memslots to change underneath a vcpu that is handling an exit. If we increment the memslot generation number again after synchronize_srcu_expedited(), vcpus can safely cache memslot generation without maintaining a single rcu_dereference through an entire vm exit. And much of the x86/kvm code does not maintain a single rcu_dereference of the current memslots during each exit. We can prevent the following case: vcpu (CPU 0) | thread (CPU 1) --------------------------------------------+-------------------------- 1 vm exit | 2 srcu_read_unlock(&kvm->srcu) | 3 decide to cache something based on | old memslots | 4 | change memslots | (increments generation) 5 | synchronize_srcu(&kvm->srcu); 6 retrieve generation # from new memslots | 7 tag cache with new memslot generation | 8 srcu_read_unlock(&kvm->srcu) | ... | <action based on cache occurs even | though the caching decision was based | on the old memslots> | ... | <action *continues* to occur until next | memslot generation change, which may | be never> | | By incrementing the generation after synchronizing with kvm->srcu readers, we ensure that the generation retrieved in (6) will become invalid soon after (8). Keeping the existing increment is not strictly necessary, but we do keep it and just move it for consistency from update_memslots to install_new_memslots. It invalidates old cached MMIOs immediately, instead of having to wait for the end of synchronize_srcu_expedited, which makes the code more clearly correct in case CPU 1 is preempted right after synchronize_srcu() returns. To avoid halving the generation space in SPTEs, always presume that the low bit of the generation is zero when reconstructing a generation number out of an SPTE. This effectively disables MMIO caching in SPTEs during the call to synchronize_srcu_expedited. Using the low bit this way is somewhat like a seqcount---where the protected thing is a cache, and instead of retrying we can simply punt if we observe the low bit to be 1. Cc: stable@vger.kernel.org Signed-off-by: David Matlack <dmatlack@google.com> Reviewed-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Reviewed-by: David Matlack <dmatlack@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'virt')
-rw-r--r--virt/kvm/kvm_main.c23
1 files changed, 16 insertions, 7 deletions
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0bfdb67..bb8641b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -95,8 +95,6 @@ static int hardware_enable_all(void);
static void hardware_disable_all(void);
static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-static void update_memslots(struct kvm_memslots *slots,
- struct kvm_memory_slot *new, u64 last_generation);
static void kvm_release_pfn_dirty(pfn_t pfn);
static void mark_page_dirty_in_slot(struct kvm *kvm,
@@ -695,8 +693,7 @@ static void sort_memslots(struct kvm_memslots *slots)
}
static void update_memslots(struct kvm_memslots *slots,
- struct kvm_memory_slot *new,
- u64 last_generation)
+ struct kvm_memory_slot *new)
{
if (new) {
int id = new->id;
@@ -707,8 +704,6 @@ static void update_memslots(struct kvm_memslots *slots,
if (new->npages != npages)
sort_memslots(slots);
}
-
- slots->generation = last_generation + 1;
}
static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
@@ -730,10 +725,24 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
{
struct kvm_memslots *old_memslots = kvm->memslots;
- update_memslots(slots, new, kvm->memslots->generation);
+ /*
+ * Set the low bit in the generation, which disables SPTE caching
+ * until the end of synchronize_srcu_expedited.
+ */
+ WARN_ON(old_memslots->generation & 1);
+ slots->generation = old_memslots->generation + 1;
+
+ update_memslots(slots, new);
rcu_assign_pointer(kvm->memslots, slots);
synchronize_srcu_expedited(&kvm->srcu);
+ /*
+ * Increment the new memslot generation a second time. This prevents
+ * vm exits that race with memslot updates from caching a memslot
+ * generation that will (potentially) be valid forever.
+ */
+ slots->generation++;
+
kvm_arch_memslots_updated(kvm);
return old_memslots;
OpenPOWER on IntegriCloud