KVM: PPC: Book3S HV: Don't use kvm_memslots() in real mode

With HV KVM, some high-frequency hypercalls such as H_ENTER are handled
in real mode, and need to access the memslots array for the guest.
Accessing the memslots array is safe, because we hold the SRCU read
lock for the whole time that a guest vcpu is running.  However, the
checks that kvm_memslots() does when lockdep is enabled are potentially
unsafe in real mode, when only the linear mapping is available.
Furthermore, kvm_memslots() can be called from a secondary CPU thread,
which is an offline CPU from the point of view of the host kernel,
and is not running the task which holds the SRCU read lock.

To avoid false positives in the checks in kvm_memslots(), and to avoid
possible side effects from doing the checks in real mode, this replaces
kvm_memslots() with kvm_memslots_raw() in all the places that execute
in real mode.  kvm_memslots_raw() is a new function that is like
kvm_memslots() but uses rcu_dereference_raw_notrace() instead of
kvm_dereference_check().

Signed-off-by: Paul Mackerras <paulus@samba.org>

3 files changed, 16 insertions, 4 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 70dd25c3832771..73ec36e268cffe 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -279,6 +279,18 @@ static inline void note_hpte_modification(struct kvm *kvm,
 	if (atomic_read(&kvm->arch.hpte_mod_interest))
 		rev->guest_rpte |= HPTE_GR_MODIFIED;
 }
+
+/*
+ * Like kvm_memslots(), but for use in real mode when we can't do
+ * any RCU stuff (since the secondary threads are offline from the
+ * kernel's point of view), and we can't print anything.
+ * Thus we use rcu_dereference_raw() rather than rcu_dereference_check().
+ */
+static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
+{
+	return rcu_dereference_raw_notrace(kvm->memslots);
+}
+
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index a59aa5f88f5032..8ed948426d47bc 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -187,7 +187,7 @@ static unsigned long kvmppc_rm_gpa_to_hpa_and_get(struct kvm_vcpu *vcpu,
 	}
 
 	/* System page size case */
-	memslot = search_memslots(kvm_memslots(vcpu->kvm), gfn);
+	memslot = search_memslots(kvm_memslots_raw(vcpu->kvm), gfn);
 	if (!memslot)
 		return ERROR_ADDR;
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 105b00f24f27ba..0357cc3b1cfb0f 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -111,7 +111,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 	rcbits = hpte_r & (HPTE_R_R | HPTE_R_C);
 	ptel = rev->guest_rpte |= rcbits;
 	gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
-	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
 	if (!memslot)
 		return;
 
@@ -194,7 +194,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	/* Find the memslot (if any) for this address */
 	gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
 	gfn = gpa >> PAGE_SHIFT;
-	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
 	pa = 0;
 	is_io = ~0ul;
 	rmap = NULL;
@@ -666,7 +666,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 
 			psize = hpte_page_size(v, r);
 			gfn = ((r & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
-			memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+			memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
 			if (memslot) {
 				hva = __gfn_to_hva_memslot(memslot, gfn);
 				pte = lookup_linux_pte(pgdir, hva, 1, &psize);