[PATCH 3/8] KVM: arm64: Propagate and use kvm_s2_fault_result on S2 fault

[Lorenzo Stoakes (ARM)]

When stage 2 page tables fault the net result may either be that a page is
mapped, an error occurred or the fault should be retried (-EAGAIN).

When a fault succeeds it may be upgraded to a PMD size via
transparent_hugepage_adjust().

In order to support KVM pre-faulting the outcome of the fault and the
mapping size must be recorded.

Track this in the new kvm_s2_fault_result struct, which is threaded through
gmem_abort(), user_mem_abort() and kvm_s2_fault_map().

PKVM and SEA aren't relevant to synthetic pre-faulting so neither
kvm_inject_sea() nor pkvm_mem_abort() are altered.

Actual hardware faulting doesn't require this information, so
kvm_handle_guest_abort() simply passes NULL kvm_s2_fault_result to
gmem_abort() and user_mem_abort().

Faults are necessarily ephemeral and pre-faulting can't guarantee what may
happen in parallel, so do not store the GFN or PFN in
kvm_s2_fault_result. Pre-faulting only needs to know what was mapped in at
the point of the fault.

This struct could be replaced with a pointer to an unsigned long, however
it's clearer to separate out the mapped flag and having a struct allows us
to easily add additional fields in future as needed.

No functional change intended.

Suggested-by: Vincent Donnefort <vdonnefort@xxxxxxxxxx>
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@xxxxxxxxxx>
---
 arch/arm64/kvm/mmu.c | 33 +++++++++++++++++++++++++++------
 1 file changed, 27 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 80cb520e25b9..da15da4e40e6 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1607,6 +1607,11 @@ struct kvm_s2_fault_desc {
 	struct kvm_s2_mmu	*mmu;
 };
 
+struct kvm_s2_fault_result {
+	unsigned long mapping_size;
+	bool mapped;
+};
+
 static bool kvm_s2_fault_is_perm(const struct kvm_s2_fault_desc *s2fd)
 {
 	return esr_fsc_is_permission_fault(s2fd->esr);
@@ -1632,7 +1637,17 @@ static u64 kvm_s2_perm_fault_granule(const struct kvm_s2_fault_desc *s2fd)
 	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
 }
 
-static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
+static void populate_fault_result(struct kvm_s2_fault_result *result,
+				  unsigned long mapping_size)
+{
+	/* A THP upgrade may have altered mapping size. */
+	result->mapping_size = mapping_size;
+	/* -EAGAIN is swallowed so be explicit when we actually map. */
+	result->mapped = true;
+}
+
+static int gmem_abort(const struct kvm_s2_fault_desc *s2fd,
+		      struct kvm_s2_fault_result *result)
 {
 	bool write_fault, exec_fault;
 	const bool perm_fault = kvm_s2_fault_is_perm(s2fd);
@@ -1714,6 +1729,8 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 	if ((prot & KVM_PGTABLE_PROT_W) && !ret)
 		mark_page_dirty_in_slot(kvm, s2fd->memslot, gfn);
 
+	if (result && !ret)
+		populate_fault_result(result, PAGE_SIZE);
 	return ret != -EAGAIN ? ret : 0;
 }
 
@@ -2038,7 +2055,8 @@ static int kvm_s2_fault_compute_prot(const struct kvm_s2_fault_desc *s2fd,
 static int kvm_s2_fault_map(const struct kvm_s2_fault_desc *s2fd,
 			    const struct kvm_s2_fault_vma_info *s2vi,
 			    enum kvm_pgtable_prot prot,
-			    void *memcache)
+			    void *memcache,
+			    struct kvm_s2_fault_result *result)
 {
 	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
 	bool writable = prot & KVM_PGTABLE_PROT_W;
@@ -2117,12 +2135,15 @@ static int kvm_s2_fault_map(const struct kvm_s2_fault_desc *s2fd,
 		mark_page_dirty_in_slot(kvm, s2fd->memslot, gpa_to_gfn(ipa));
 	}
 
+	if (result && !ret)
+		populate_fault_result(result, mapping_size);
 	if (ret != -EAGAIN)
 		return ret;
 	return 0;
 }
 
-static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd)
+static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd,
+			  struct kvm_s2_fault_result *result)
 {
 	const bool perm_fault = kvm_s2_fault_is_perm(s2fd);
 	struct kvm_s2_fault_vma_info s2vi = {};
@@ -2161,7 +2182,7 @@ static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd)
 		return ret;
 	}
 
-	return kvm_s2_fault_map(s2fd, &s2vi, prot, memcache);
+	return kvm_s2_fault_map(s2fd, &s2vi, prot, memcache, result);
 }
 
 /* Resolve the access fault by making the page young again. */
@@ -2440,9 +2461,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 				!kvm_s2_fault_is_exec(&s2fd));
 
 		if (kvm_slot_has_gmem(memslot))
-			ret = gmem_abort(&s2fd);
+			ret = gmem_abort(&s2fd, NULL);
 		else
-			ret = user_mem_abort(&s2fd);
+			ret = user_mem_abort(&s2fd, NULL);
 	}
 
 	if (ret == 0)

-- 
2.55.0