fix CVE-2017-12188: nested KVM stack overflow

Makefile

@@ -238,6 +238,7 @@ ${KERNEL_SRC}/README: ${KERNEL_SRC_SUBMODULE} | submodule
 	cp -a ${KERNEL_SRC_SUBMODULE} ${KERNEL_SRC}
 	cat ${KERNEL_SRC}/debian.master/config/config.common.ubuntu ${KERNEL_SRC}/debian.master/config/${ARCH}/config.common.${ARCH} ${KERNEL_SRC}/debian.master/config/${ARCH}/config.flavour.generic > ${KERNEL_CFG_ORG}
 	cd ${KERNEL_SRC}; for patch in ../patches/kernel/*.patch; do patch --verbose -p1 < $${patch}; done
+	cd ${KERNEL_SRC}; for patch in ../patches/kernel-cves/*.patch; do patch --verbose -p1 < $${patch}; done
 	sed -i ${KERNEL_SRC}/Makefile -e 's/^EXTRAVERSION.*$$/EXTRAVERSION=${EXTRAVERSION}/'
 	touch $@
 

patches/kernel-cves/CVE-2017-12188_0001-KVM-nVMX-update-last_nonleaf_level-when-initializing.patch

@@ -0,0 +1,38 @@
+From 8da45fe7977a1866ea95d5d281485e6f139d75c8 Mon Sep 17 00:00:00 2001
+From: Ladi Prosek <lprosek@redhat.com>
+Date: Tue, 10 Oct 2017 17:30:58 +0200
+Subject: [CVE-2017-12188 1/2] KVM: nVMX: update last_nonleaf_level when
+ initializing nested EPT
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+The function updates context->root_level but didn't call
+update_last_nonleaf_level so the previous and potentially wrong value
+was used for page walks.  For example, a zero value of last_nonleaf_level
+would allow a potential out-of-bounds access in arch/x86/mmu/paging_tmpl.h's
+walk_addr_generic function (CVE-2017-12188).
+
+Fixes: 155a97a3d7c78b46cef6f1a973c831bc5a4f82bb
+Signed-off-by: Ladi Prosek <lprosek@redhat.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
+---
+ arch/x86/kvm/mmu.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
+index 56e68dfac974..ca0112742343 100644
+--- a/arch/x86/kvm/mmu.c
++++ b/arch/x86/kvm/mmu.c
+@@ -4459,6 +4459,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
+ 
+ 	update_permission_bitmask(vcpu, context, true);
+ 	update_pkru_bitmask(vcpu, context, true);
++	update_last_nonleaf_level(vcpu, context);
+ 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
+ 	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
+ }
+-- 
+2.14.1
+

patches/kernel-cves/CVE-2017-12188_0002-KVM-MMU-always-terminate-page-walks-at-level-1.patch

@@ -0,0 +1,88 @@
+From ebe182a7c6221878cbb5d03e1eafa8002494f8cb Mon Sep 17 00:00:00 2001
+From: Ladi Prosek <lprosek@redhat.com>
+Date: Tue, 10 Oct 2017 17:30:59 +0200
+Subject: [CVE-2017-12188 2/2] KVM: MMU: always terminate page walks at level 1
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+is_last_gpte() is not equivalent to the pseudo-code given in commit
+6bb69c9b69c31 ("KVM: MMU: simplify last_pte_bitmap") because an incorrect
+value of last_nonleaf_level may override the result even if level == 1.
+
+It is critical for is_last_gpte() to return true on level == 1 to
+terminate page walks. Otherwise memory corruption may occur as level
+is used as an index to various data structures throughout the page
+walking code.  Even though the actual bug would be wherever the MMU is
+initialized (as in the previous patch), be defensive and ensure here
+that is_last_gpte() returns the correct value.
+
+This patch is also enough to fix CVE-2017-12188, and suggested for
+stable and distro kernels.
+
+Fixes: 6bb69c9b69c315200ddc2bc79aee14c0184cf5b2
+Cc: stable@vger.kernel.org
+Cc: Andy Honig <ahonig@google.com>
+Signed-off-by: Ladi Prosek <lprosek@redhat.com>
+[Panic if walk_addr_generic gets an incorrect level; this is a serious
+ bug and it's not worth a WARN_ON where the recovery path might hide
+ further exploitable issues; suggested by Andrew Honig. - Paolo]
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
+---
+ arch/x86/kvm/paging_tmpl.h |  3 ++-
+ arch/x86/kvm/mmu.c         | 14 +++++++-------
+ 2 files changed, 9 insertions(+), 8 deletions(-)
+
+diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
+index b0454c7e4cff..da06dc8c4fc4 100644
+--- a/arch/x86/kvm/paging_tmpl.h
++++ b/arch/x86/kvm/paging_tmpl.h
+@@ -334,10 +334,11 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
+ 		--walker->level;
+ 
+ 		index = PT_INDEX(addr, walker->level);
+-
+ 		table_gfn = gpte_to_gfn(pte);
+ 		offset    = index * sizeof(pt_element_t);
+ 		pte_gpa   = gfn_to_gpa(table_gfn) + offset;
++
++		BUG_ON(walker->level < 1);
+ 		walker->table_gfn[walker->level - 1] = table_gfn;
+ 		walker->pte_gpa[walker->level - 1] = pte_gpa;
+ 
+diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
+index ca0112742343..2e4a6732aaa9 100644
+--- a/arch/x86/kvm/mmu.c
++++ b/arch/x86/kvm/mmu.c
+@@ -3934,13 +3934,6 @@ static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
+ static inline bool is_last_gpte(struct kvm_mmu *mmu,
+ 				unsigned level, unsigned gpte)
+ {
+-	/*
+-	 * PT_PAGE_TABLE_LEVEL always terminates.  The RHS has bit 7 set
+-	 * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
+-	 * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
+-	 */
+-	gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
+-
+ 	/*
+ 	 * The RHS has bit 7 set iff level < mmu->last_nonleaf_level.
+ 	 * If it is clear, there are no large pages at this level, so clear
+@@ -3948,6 +3941,13 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu,
+ 	 */
+ 	gpte &= level - mmu->last_nonleaf_level;
+ 
++	/*
++	 * PT_PAGE_TABLE_LEVEL always terminates.  The RHS has bit 7 set
++	 * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
++	 * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
++	 */
++	gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
++
+ 	return gpte & PT_PAGE_SIZE_MASK;
+ }
+ 
+-- 
+2.14.1
+