linux-kernel - [PATCH v2 15/22] powerpc/kvm/book3s: use find_kvm_host_pte in pute

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20200319035609.158654-16-aneesh.kumar@linux.ibm.com>
Date:   Thu, 19 Mar 2020 09:26:02 +0530
From:   "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>
To:     linuxppc-dev@...ts.ozlabs.org, mpe@...erman.id.au,
        linux-mm@...ck.org, linux-kernel@...r.kernel.org,
        kvm-ppc@...r.kernel.org
Cc:     npiggin@...il.com, paulus@...abs.org, leonardo@...ux.ibm.com,
        kirill@...temov.name,
        "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>,
        Alexey Kardashevskiy <aik@...abs.ru>
Subject: [PATCH v2 15/22] powerpc/kvm/book3s: use find_kvm_host_pte in pute_tce functions

Current code just hold rmap lock to ensure parallel page table update is
prevented. That is not sufficient. The kernel should also check whether
a mmu_notifer callback was running in parallel.

Cc: Alexey Kardashevskiy <aik@...abs.ru>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@...ux.ibm.com>
---
 arch/powerpc/kvm/book3s_64_vio_hv.c | 30 +++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index ab6eeb8e753e..8a6bf12d2e88 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -438,8 +438,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	return H_SUCCESS;
 }
 
-static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
-		unsigned long ua, unsigned long *phpa)
+static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu, unsigned long mmu_seq,
+				unsigned long ua, unsigned long *phpa)
 {
 	pte_t *ptep, pte;
 	unsigned shift = 0;
@@ -453,10 +453,17 @@ static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
 	 * to exit which will agains result in the below page table walk
 	 * to finish.
 	 */
-	ptep = __find_linux_pte(vcpu->arch.pgdir, ua, NULL, &shift);
-	if (!ptep || !pte_present(*ptep))
+	/* an rmap lock won't make it safe. because that just ensure hash
+	 * page table entries are removed with rmap lock held. After that
+	 * mmu notifier returns and we go ahead and removing ptes from Qemu page table.
+	 */
+	ptep = find_kvm_host_pte(vcpu->kvm, mmu_seq, ua, &shift);
+	if (!ptep)
+		return -ENXIO;
+
+	pte = READ_ONCE(*ptep);
+	if (!pte_present(pte))
 		return -ENXIO;
-	pte = *ptep;
 
 	if (!shift)
 		shift = PAGE_SHIFT;
@@ -478,10 +485,12 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		unsigned long liobn, unsigned long ioba,
 		unsigned long tce_list,	unsigned long npages)
 {
+	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret = H_SUCCESS;
 	unsigned long tces, entry, ua = 0;
 	unsigned long *rmap = NULL;
+	unsigned long mmu_seq;
 	bool prereg = false;
 	struct kvmppc_spapr_tce_iommu_table *stit;
 
@@ -489,6 +498,12 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (kvm_is_radix(vcpu->kvm))
 		return H_TOO_HARD;
 
+	/*
+	 * used to check for invalidations in progress
+	 */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
@@ -548,7 +563,9 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 * real page.
 		 */
 		lock_rmap(rmap);
-		if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
+
+		arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);
+		if (kvmppc_rm_ua_to_hpa(vcpu, mmu_seq, ua, &tces)) {
 			ret = H_TOO_HARD;
 			goto unlock_exit;
 		}
@@ -594,6 +611,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (rmap)
 		unlock_rmap(rmap);
 
+	arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock);
 	return ret;
 }
 
-- 
2.24.1