Add helpers to read and write TDP MMU SPTEs instead of open coding
rcu_dereference() all over the place, and to provide a convenient
location to document why KVM doesn't exempt holding mmu_lock for write
from having to hold RCU (and any future changes to the rules).
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Reviewed-by: Ben Gardon <bgardon@xxxxxxxxxx>
---
arch/x86/kvm/mmu/tdp_iter.c | 6 +++---
arch/x86/kvm/mmu/tdp_iter.h | 16 ++++++++++++++++
arch/x86/kvm/mmu/tdp_mmu.c | 14 +++++++-------
3 files changed, 26 insertions(+), 10 deletions(-)
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index caa96c270b95..de31f3e68668 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -12,7 +12,7 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter)
{
iter->sptep = iter->pt_path[iter->level - 1] +
SHADOW_PT_INDEX(iter->gfn << PAGE_SHIFT, iter->level);
- iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep));
+ iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
}
static gfn_t round_gfn_for_level(gfn_t gfn, int level)
@@ -87,7 +87,7 @@ static bool try_step_down(struct tdp_iter *iter)
* Reread the SPTE before stepping down to avoid traversing into page
* tables that are no longer linked from this entry.
*/
- iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep));
+ iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
child_pt = spte_to_child_pt(iter->old_spte, iter->level);
if (!child_pt)
@@ -121,7 +121,7 @@ static bool try_step_side(struct tdp_iter *iter)
iter->gfn += KVM_PAGES_PER_HPAGE(iter->level);
iter->next_last_level_gfn = iter->gfn;
iter->sptep++;
- iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep));
+ iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
return true;
}
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index e19cabbcb65c..3cdfaf391a49 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -9,6 +9,22 @@
typedef u64 __rcu *tdp_ptep_t;
+/*
+ * TDP MMU SPTEs are RCU protected to allow paging structures (non-leaf SPTEs)
+ * to be zapped while holding mmu_lock for read. Holding RCU isn't required for
+ * correctness if mmu_lock is held for write, but plumbing "struct kvm" down to
+ * the lower* depths of the TDP MMU just to make lockdep happy is a nightmare,
+ * so all* accesses to SPTEs are must be done under RCU protection.
+ */
+static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep)
+{
+ return READ_ONCE(*rcu_dereference(sptep));
+}
+static inline void kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 val)
+{
+ WRITE_ONCE(*rcu_dereference(sptep), val);
+}
+
/*
* A TDP iterator performs a pre-order walk over a TDP paging structure.
*/
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 47424e22a681..41c3a1cff3e7 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -603,7 +603,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm,
* here since the SPTE is going from non-present
* to non-present.
*/
- WRITE_ONCE(*rcu_dereference(iter->sptep), 0);
+ kvm_tdp_mmu_write_spte(iter->sptep, 0);
return true;
}
@@ -642,7 +642,7 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
*/
WARN_ON(is_removed_spte(iter->old_spte));
- WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
+ kvm_tdp_mmu_write_spte(iter->sptep, new_spte);
__handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
new_spte, iter->level, false);
@@ -807,7 +807,7 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
* The iter must explicitly re-read the SPTE because
* the atomic cmpxchg failed.
*/
- iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+ iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
goto retry;
}
}
@@ -1011,7 +1011,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
* because the new value informs the !present
* path below.
*/
- iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+ iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
}
if (!is_shadow_present_pte(iter.old_spte)) {
@@ -1217,7 +1217,7 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
* The iter must explicitly re-read the SPTE because
* the atomic cmpxchg failed.
*/
- iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+ iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
goto retry;
}
spte_set = true;
@@ -1288,7 +1288,7 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
* The iter must explicitly re-read the SPTE because
* the atomic cmpxchg failed.
*/
- iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+ iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
goto retry;
}
spte_set = true;
@@ -1419,7 +1419,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
* The iter must explicitly re-read the SPTE because
* the atomic cmpxchg failed.
*/
- iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+ iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
goto retry;
}
}
--
2.34.1.448.ga2b2bfdf31-goog
