From 404381c5839d67aa0c275ad1da96ef3d3928ca2c Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Mon, 24 Feb 2014 13:59:32 -0300 Subject: KVM: MMU: drop read-only large sptes when creating lower level sptes Read-only large sptes can be created due to read-only faults as follows: - QEMU pagetable entry that maps guest memory is read-only due to COW. - Guest read faults such memory, COW is not broken, because it is a read-only fault. - Enable dirty logging, large spte not nuked because it is read-only. - Write-fault on such memory causes guest to loop endlessly (which must go down to level 1 because dirty logging is enabled). Fix by dropping large spte when necessary. Signed-off-by: Marcelo Tosatti Signed-off-by: Paolo Bonzini --- 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 e50425d0f5f7..9b531351a587 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2672,6 +2672,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, break; } + drop_large_spte(vcpu, iterator.sptep); if (!is_shadow_present_pte(*iterator.sptep)) { u64 base_addr = iterator.addr; -- cgit v1.2.3 From b20c9f29c5c25921c6ad18b50d4b61e6d181c3cc Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 26 Feb 2014 18:47:36 +0000 Subject: arm/arm64: KVM: detect CPU reset on CPU_PM_EXIT Commit 1fcf7ce0c602 (arm: kvm: implement CPU PM notifier) added support for CPU power-management, using a cpu_notifier to re-init KVM on a CPU that entered CPU idle. The code assumed that a CPU entering idle would actually be powered off, loosing its state entierely, and would then need to be reinitialized. It turns out that this is not always the case, and some HW performs CPU PM without actually killing the core. In this case, we try to reinitialize KVM while it is still live. It ends up badly, as reported by Andre Przywara (using a Calxeda Midway): [ 3.663897] Kernel panic - not syncing: unexpected prefetch abort in Hyp mode at: 0x685760 [ 3.663897] unexpected data abort in Hyp mode at: 0xc067d150 [ 3.663897] unexpected HVC/SVC trap in Hyp mode at: 0xc0901dd0 The trick here is to detect if we've been through a full re-init or not by looking at HVBAR (VBAR_EL2 on arm64). This involves implementing the backend for __hyp_get_vectors in the main KVM HYP code (rather small), and checking the return value against the default one when the CPU notifier is called on CPU_PM_EXIT. Reported-by: Andre Przywara Tested-by: Andre Przywara Cc: Lorenzo Pieralisi Cc: Rob Herring Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier Signed-off-by: Paolo Bonzini --- arch/arm/kvm/arm.c | 3 ++- arch/arm/kvm/interrupts.S | 11 ++++++++++- arch/arm64/kvm/hyp.S | 27 +++++++++++++++++++++++++-- 3 files changed, 37 insertions(+), 4 deletions(-) diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 1d8248ea5669..bd18bb8b2770 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -878,7 +878,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { - if (cmd == CPU_PM_EXIT) { + if (cmd == CPU_PM_EXIT && + __hyp_get_vectors() == hyp_default_vectors) { cpu_init_hyp_mode(NULL); return NOTIFY_OK; } diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index ddc15539bad2..0d68d4073068 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -220,6 +220,10 @@ after_vfp_restore: * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are * passed in r0 and r1. * + * A function pointer with a value of 0xffffffff has a special meaning, + * and is used to implement __hyp_get_vectors in the same way as in + * arch/arm/kernel/hyp_stub.S. + * * The calling convention follows the standard AAPCS: * r0 - r3: caller save * r12: caller save @@ -363,6 +367,11 @@ hyp_hvc: host_switch_to_hyp: pop {r0, r1, r2} + /* Check for __hyp_get_vectors */ + cmp r0, #-1 + mrceq p15, 4, r0, c12, c0, 0 @ get HVBAR + beq 1f + push {lr} mrs lr, SPSR push {lr} @@ -378,7 +387,7 @@ THUMB( orr lr, #1) pop {lr} msr SPSR_csxf, lr pop {lr} - eret +1: eret guest_trap: load_vcpu @ Load VCPU pointer to r0 diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 3b47c36e10ff..2c56012cb2d2 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -694,6 +694,24 @@ __hyp_panic_str: .align 2 +/* + * u64 kvm_call_hyp(void *hypfn, ...); + * + * This is not really a variadic function in the classic C-way and care must + * be taken when calling this to ensure parameters are passed in registers + * only, since the stack will change between the caller and the callee. + * + * Call the function with the first argument containing a pointer to the + * function you wish to call in Hyp mode, and subsequent arguments will be + * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the + * function pointer can be passed). The function being called must be mapped + * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are + * passed in r0 and r1. + * + * A function pointer with a value of 0 has a special meaning, and is + * used to implement __hyp_get_vectors in the same way as in + * arch/arm64/kernel/hyp_stub.S. + */ ENTRY(kvm_call_hyp) hvc #0 ret @@ -737,7 +755,12 @@ el1_sync: // Guest trapped into EL2 pop x2, x3 pop x0, x1 - push lr, xzr + /* Check for __hyp_get_vectors */ + cbnz x0, 1f + mrs x0, vbar_el2 + b 2f + +1: push lr, xzr /* * Compute the function address in EL2, and shuffle the parameters. @@ -750,7 +773,7 @@ el1_sync: // Guest trapped into EL2 blr lr pop lr, xzr - eret +2: eret el1_trap: /* -- cgit v1.2.3 From a08d3b3b99efd509133946056531cdf8f3a0c09b Mon Sep 17 00:00:00 2001 From: Andrew Honig Date: Thu, 27 Feb 2014 19:35:14 +0100 Subject: kvm: x86: fix emulator buffer overflow (CVE-2014-0049) The problem occurs when the guest performs a pusha with the stack address pointing to an mmio address (or an invalid guest physical address) to start with, but then extending into an ordinary guest physical address. When doing repeated emulated pushes emulator_read_write sets mmio_needed to 1 on the first one. On a later push when the stack points to regular memory, mmio_nr_fragments is set to 0, but mmio_is_needed is not set to 0. As a result, KVM exits to userspace, and then returns to complete_emulated_mmio. In complete_emulated_mmio vcpu->mmio_cur_fragment is incremented. The termination condition of vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments is never achieved. The code bounces back and fourth to userspace incrementing mmio_cur_fragment past it's buffer. If the guest does nothing else it eventually leads to a a crash on a memcpy from invalid memory address. However if a guest code can cause the vm to be destroyed in another vcpu with excellent timing, then kvm_clear_async_pf_completion_queue can be used by the guest to control the data that's pointed to by the call to cancel_work_item, which can be used to gain execution. Fixes: f78146b0f9230765c6315b2e14f56112513389ad Signed-off-by: Andrew Honig Cc: stable@vger.kernel.org (3.5+) Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 39c28f09dfd5..2b8578432d5b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6186,7 +6186,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) frag->len -= len; } - if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) { + if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { vcpu->mmio_needed = 0; /* FIXME: return into emulator if single-stepping. */ -- cgit v1.2.3 From 1b385cbdd74aa803e966e01e5fe49490d6044e30 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 27 Feb 2014 22:54:11 +0100 Subject: kvm, vmx: Really fix lazy FPU on nested guest Commit e504c9098ed6 (kvm, vmx: Fix lazy FPU on nested guest, 2013-11-13) highlighted a real problem, but the fix was subtly wrong. nested_read_cr0 is the CR0 as read by L2, but here we want to look at the CR0 value reflecting L1's setup. In other words, L2 might think that TS=0 (so nested_read_cr0 has the bit clear); but if L1 is actually running it with TS=1, we should inject the fault into L1. The effective value of CR0 in L2 is contained in vmcs12->guest_cr0, use it. Fixes: e504c9098ed6acd9e1079c5e10e4910724ad429f Reported-by: Kashyap Chamarty Reported-by: Stefan Bader Tested-by: Kashyap Chamarty Tested-by: Anthoine Bourgeois Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a06f101ef64b..392752834751 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6688,7 +6688,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) else if (is_page_fault(intr_info)) return enable_ept; else if (is_no_device(intr_info) && - !(nested_read_cr0(vmcs12) & X86_CR0_TS)) + !(vmcs12->guest_cr0 & X86_CR0_TS)) return 0; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); -- cgit v1.2.3