[PATCH v2 14/20] kvm: x86/mmu: Support changed pte notifier in tdp MMU

From: Ben Gardon
Date: Wed Oct 14 2020 - 14:28:34 EST


In order to interoperate correctly with the rest of KVM and other Linux
subsystems, the TDP MMU must correctly handle various MMU notifiers. Add
a hook and handle the change_pte MMU notifier.

Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell
machine. This series introduced no new failures.

This series can be viewed in Gerrit at:
https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538

Signed-off-by: Ben Gardon <bgardon@xxxxxxxxxx>
---
arch/x86/kvm/mmu/mmu.c | 21 ++++++-------
arch/x86/kvm/mmu/mmu_internal.h | 29 +++++++++++++++++
arch/x86/kvm/mmu/tdp_mmu.c | 56 +++++++++++++++++++++++++++++++++
arch/x86/kvm/mmu/tdp_mmu.h | 3 ++
4 files changed, 98 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e6ab79d8f215f..ef9ea3f45241b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -135,9 +135,6 @@ enum {

#include <trace/events/kvm.h>

-#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
-#define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
-
/* make pte_list_desc fit well in cache line */
#define PTE_LIST_EXT 3

@@ -1615,13 +1612,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
pte_list_remove(rmap_head, sptep);
goto restart;
} else {
- new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
- new_spte |= (u64)new_pfn << PAGE_SHIFT;
-
- new_spte &= ~PT_WRITABLE_MASK;
- new_spte &= ~SPTE_HOST_WRITEABLE;
-
- new_spte = mark_spte_for_access_track(new_spte);
+ new_spte = kvm_mmu_changed_pte_notifier_make_spte(
+ *sptep, new_pfn);

mmu_spte_clear_track_bits(sptep);
mmu_spte_set(sptep, new_spte);
@@ -1777,7 +1769,14 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,

int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
{
- return kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
+ int r;
+
+ r = kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
+
+ if (kvm->arch.tdp_mmu_enabled)
+ r |= kvm_tdp_mmu_set_spte_hva(kvm, hva, &pte);
+
+ return r;
}

static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index d886fe750be38..49c3a04d2b894 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -115,6 +115,12 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
(PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
* PT64_LEVEL_BITS))) - 1))

+#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
+#define PT64_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1))
+#else
+#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#endif
+
#define ACC_EXEC_MASK 1
#define ACC_WRITE_MASK PT_WRITABLE_MASK
#define ACC_USER_MASK PT_USER_MASK
@@ -132,6 +138,12 @@ static u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
*/
static u64 __read_mostly shadow_acc_track_mask;

+#define PT_FIRST_AVAIL_BITS_SHIFT 10
+#define PT64_SECOND_AVAIL_BITS_SHIFT 54
+
+#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
+#define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
+
/* Functions for interpreting SPTEs */
static inline bool is_mmio_spte(u64 spte)
{
@@ -264,4 +276,21 @@ void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);

u64 mark_spte_for_access_track(u64 spte);

+static inline u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte,
+ kvm_pfn_t new_pfn)
+{
+ u64 new_spte;
+
+ new_spte = old_spte & ~PT64_BASE_ADDR_MASK;
+ new_spte |= (u64)new_pfn << PAGE_SHIFT;
+
+ new_spte &= ~PT_WRITABLE_MASK;
+ new_spte &= ~SPTE_HOST_WRITEABLE;
+
+ new_spte = mark_spte_for_access_track(new_spte);
+
+ return new_spte;
+}
+
+
#endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 575970d8805a4..90abd55c89375 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -677,3 +677,59 @@ int kvm_tdp_mmu_test_age_hva(struct kvm *kvm, unsigned long hva)
return kvm_tdp_mmu_handle_hva_range(kvm, hva, hva + 1, 0,
test_age_gfn);
}
+
+/*
+ * Handle the changed_pte MMU notifier for the TDP MMU.
+ * data is a pointer to the new pte_t mapping the HVA specified by the MMU
+ * notifier.
+ * Returns non-zero if a flush is needed before releasing the MMU lock.
+ */
+static int set_tdp_spte(struct kvm *kvm, struct kvm_memory_slot *slot,
+ struct kvm_mmu_page *root, gfn_t gfn, gfn_t unused,
+ unsigned long data)
+{
+ struct tdp_iter iter;
+ pte_t *ptep = (pte_t *)data;
+ kvm_pfn_t new_pfn;
+ u64 new_spte;
+ int need_flush = 0;
+
+ WARN_ON(pte_huge(*ptep));
+
+ new_pfn = pte_pfn(*ptep);
+
+ tdp_root_for_each_pte(iter, root, gfn, gfn + 1) {
+ if (iter.level != PG_LEVEL_4K)
+ continue;
+
+ if (!is_shadow_present_pte(iter.old_spte))
+ break;
+
+ tdp_mmu_set_spte(kvm, &iter, 0);
+
+ kvm_flush_remote_tlbs_with_address(kvm, iter.gfn, 1);
+
+ if (!pte_write(*ptep)) {
+ new_spte = kvm_mmu_changed_pte_notifier_make_spte(
+ iter.old_spte, new_pfn);
+
+ tdp_mmu_set_spte(kvm, &iter, new_spte);
+ }
+
+ need_flush = 1;
+ }
+
+ if (need_flush)
+ kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+
+ return 0;
+}
+
+int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address,
+ pte_t *host_ptep)
+{
+ return kvm_tdp_mmu_handle_hva_range(kvm, address, address + 1,
+ (unsigned long)host_ptep,
+ set_tdp_spte);
+}
+
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index bdb86f61e75eb..6569792f40d4f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -25,4 +25,7 @@ int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start,
int kvm_tdp_mmu_age_hva_range(struct kvm *kvm, unsigned long start,
unsigned long end);
int kvm_tdp_mmu_test_age_hva(struct kvm *kvm, unsigned long hva);
+
+int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address,
+ pte_t *host_ptep);
#endif /* __KVM_X86_MMU_TDP_MMU_H */
--
2.28.0.1011.ga647a8990f-goog