[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250508141012.1411952-2-seanjc@google.com>
Date: Thu, 8 May 2025 07:10:08 -0700
From: Sean Christopherson <seanjc@...gle.com>
To: Paolo Bonzini <pbonzini@...hat.com>
Cc: kvm@...r.kernel.org, linux-kernel@...r.kernel.org,
Peter Xu <peterx@...hat.com>, Yan Zhao <yan.y.zhao@...el.com>,
Maxim Levitsky <mlevitsk@...hat.com>, Sean Christopherson <seanjc@...gle.com>
Subject: [PATCH v2 1/5] KVM: Bound the number of dirty ring entries in a
single reset at INT_MAX
Cap the number of ring entries that are reset in a single ioctl to INT_MAX
to ensure userspace isn't confused by a wrap into negative space, and so
that, in a truly pathological scenario, KVM doesn't miss a TLB flush due
to the count wrapping to zero. While the size of the ring is fixed at
0x10000 entries and KVM (currently) supports at most 4096, userspace is
allowed to harvest entries from the ring while the reset is in-progress,
i.e. it's possible for the ring to always have harvested entries.
Opportunistically return an actual error code from the helper so that a
future fix to handle pending signals can gracefully return -EINTR.
Cc: Peter Xu <peterx@...hat.com>
Cc: Yan Zhao <yan.y.zhao@...el.com>
Cc: Maxim Levitsky <mlevitsk@...hat.com>
Fixes: fb04a1eddb1a ("KVM: X86: Implement ring-based dirty memory tracking")
Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
include/linux/kvm_dirty_ring.h | 8 +++++---
virt/kvm/dirty_ring.c | 10 +++++-----
virt/kvm/kvm_main.c | 9 ++++++---
3 files changed, 16 insertions(+), 11 deletions(-)
diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
index da4d9b5f58f1..ee61ff6c3fe4 100644
--- a/include/linux/kvm_dirty_ring.h
+++ b/include/linux/kvm_dirty_ring.h
@@ -49,9 +49,10 @@ static inline int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *r
}
static inline int kvm_dirty_ring_reset(struct kvm *kvm,
- struct kvm_dirty_ring *ring)
+ struct kvm_dirty_ring *ring,
+ int *nr_entries_reset)
{
- return 0;
+ return -ENOENT;
}
static inline void kvm_dirty_ring_push(struct kvm_vcpu *vcpu,
@@ -82,7 +83,8 @@ int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring,
* called with kvm->slots_lock held, returns the number of
* processed pages.
*/
-int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring);
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring,
+ int *nr_entries_reset);
/*
* returns =0: successfully pushed
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index d14ffc7513ee..77986f34eff8 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -105,19 +105,19 @@ static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn)
return smp_load_acquire(&gfn->flags) & KVM_DIRTY_GFN_F_RESET;
}
-int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring,
+ int *nr_entries_reset)
{
u32 cur_slot, next_slot;
u64 cur_offset, next_offset;
unsigned long mask;
- int count = 0;
struct kvm_dirty_gfn *entry;
bool first_round = true;
/* This is only needed to make compilers happy */
cur_slot = cur_offset = mask = 0;
- while (true) {
+ while (likely((*nr_entries_reset) < INT_MAX)) {
entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)];
if (!kvm_dirty_gfn_harvested(entry))
@@ -130,7 +130,7 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
kvm_dirty_gfn_set_invalid(entry);
ring->reset_index++;
- count++;
+ (*nr_entries_reset)++;
/*
* Try to coalesce the reset operations when the guest is
* scanning pages in the same slot.
@@ -167,7 +167,7 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
trace_kvm_dirty_ring_reset(ring);
- return count;
+ return 0;
}
void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 16fe54cf2808..f9de2c8b9c1e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4903,15 +4903,18 @@ static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm)
{
unsigned long i;
struct kvm_vcpu *vcpu;
- int cleared = 0;
+ int cleared = 0, r;
if (!kvm->dirty_ring_size)
return -EINVAL;
mutex_lock(&kvm->slots_lock);
- kvm_for_each_vcpu(i, vcpu, kvm)
- cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ r = kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring, &cleared);
+ if (r)
+ break;
+ }
mutex_unlock(&kvm->slots_lock);
--
2.49.0.1015.ga840276032-goog
Powered by blists - more mailing lists