Merge branch 'cve-2019-3016' into kvm-next-5.6

From Boris Ostrovsky:

The KVM hypervisor may provide a guest with ability to defer remote TLB
flush when the remote VCPU is not running. When this feature is used,
the TLB flush will happen only when the remote VPCU is scheduled to run
again. This will avoid unnecessary (and expensive) IPIs.

Under certain circumstances, when a guest initiates such deferred action,
the hypervisor may miss the request. It is also possible that the guest
may mistakenly assume that it has already marked remote VCPU as needing
a flush when in fact that request had already been processed by the
hypervisor. In both cases this will result in an invalid translation
being present in a vCPU, potentially allowing accesses to memory locations
in that guest's address space that should not be accessible.

Note that only intra-guest memory is vulnerable.

The five patches address both of these problems:
1. The first patch makes sure the hypervisor doesn't accidentally clear
a guest's remote flush request
2. The rest of the patches prevent the race between hypervisor
acknowledging a remote flush request and guest issuing a new one.

Conflicts:
	arch/x86/kvm/x86.c [move from kvm_arch_vcpu_free to kvm_arch_vcpu_destroy]

9 files changed, 65 insertions, 46 deletions

diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index 41b16f21beec..0b8b63d0bec1 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -162,7 +162,7 @@
 #endif
 
 #ifdef CONFIG_ARC_HAS_ACCL_REGS
-	ST2	r58, r59, PT_sp + 12
+	ST2	r58, r59, PT_r58
 #endif
 
 .endm
@@ -172,8 +172,8 @@
 
 	LD2	gp, fp, PT_r26		; gp (r26), fp (r27)
 
-	ld	r12, [sp, PT_sp + 4]
-	ld	r30, [sp, PT_sp + 8]
+	ld	r12, [sp, PT_r12]
+	ld	r30, [sp, PT_r30]
 
 	; Restore SP (into AUX_USER_SP) only if returning to U mode
 	;  - for K mode, it will be implicitly restored as stack is unwound
@@ -190,7 +190,7 @@
 #endif
 
 #ifdef CONFIG_ARC_HAS_ACCL_REGS
-	LD2	r58, r59, PT_sp + 12
+	LD2	r58, r59, PT_r58
 #endif
 .endm
 
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index 9a74ce71a767..30ac40fed2c5 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -8,7 +8,6 @@
 #define _ASM_ARC_HUGEPAGE_H
 
 #include <linux/types.h>
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 static inline pte_t pmd_pte(pmd_t pmd)
diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c
index 1f621e416521..c783bcd35eb8 100644
--- a/arch/arc/kernel/asm-offsets.c
+++ b/arch/arc/kernel/asm-offsets.c
@@ -66,7 +66,15 @@ int main(void)
 
 	DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs));
 	DEFINE(SZ_PT_REGS, sizeof(struct pt_regs));
-	DEFINE(PT_user_r25, offsetof(struct pt_regs, user_r25));
+
+#ifdef CONFIG_ISA_ARCV2
+	OFFSET(PT_r12, pt_regs, r12);
+	OFFSET(PT_r30, pt_regs, r30);
+#endif
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	OFFSET(PT_r58, pt_regs, r58);
+	OFFSET(PT_r59, pt_regs, r59);
+#endif
 
 	return 0;
 }
diff --git a/arch/arc/plat-eznps/Kconfig b/arch/arc/plat-eznps/Kconfig
index a376a50d3fea..a931d0a256d0 100644
--- a/arch/arc/plat-eznps/Kconfig
+++ b/arch/arc/plat-eznps/Kconfig
@@ -7,7 +7,7 @@
 menuconfig ARC_PLAT_EZNPS
 	bool "\"EZchip\" ARC dev platform"
 	select CPU_BIG_ENDIAN
-	select CLKSRC_NPS
+	select CLKSRC_NPS if !PHYS_ADDR_T_64BIT
 	select EZNPS_GIC
 	select EZCHIP_NPS_MANAGEMENT_ENET if ETHERNET
 	help
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 8dc6c5cdabe6..baf52baaa2a5 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -85,13 +85,12 @@
 #define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
-#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
 
 #define __P000  PAGE_NONE
 #define __P001  PAGE_READONLY
 #define __P010  PAGE_READONLY
 #define __P011  PAGE_READONLY
-#define __P100  PAGE_EXECONLY
+#define __P100  PAGE_READONLY_EXEC
 #define __P101  PAGE_READONLY_EXEC
 #define __P110  PAGE_READONLY_EXEC
 #define __P111  PAGE_READONLY_EXEC
@@ -100,7 +99,7 @@
 #define __S001  PAGE_READONLY
 #define __S010  PAGE_SHARED
 #define __S011  PAGE_SHARED
-#define __S100  PAGE_EXECONLY
+#define __S100  PAGE_READONLY_EXEC
 #define __S101  PAGE_READONLY_EXEC
 #define __S110  PAGE_SHARED_EXEC
 #define __S111  PAGE_SHARED_EXEC
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 5d15b4735a0e..cd5de0e40bfa 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -96,12 +96,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-/*
- * Execute-only user mappings do not have the PTE_USER bit set. All valid
- * kernel mappings have the PTE_UXN bit set.
- */
 #define pte_valid_not_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 #define pte_valid_young(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
 #define pte_valid_user(pte) \
@@ -117,8 +113,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
 /*
  * p??_access_permitted() is true for valid user mappings (subject to the
- * write permission check) other than user execute-only which do not have the
- * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set.
+ * write permission check). PROT_NONE mappings do not have the PTE_VALID bit
+ * set.
  */
 #define pte_access_permitted(pte, write) \
 	(pte_valid_user(pte) && (!(write) || pte_write(pte)))
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 077b02a2d4d3..85566d32958f 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -445,7 +445,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	const struct fault_info *inf;
 	struct mm_struct *mm = current->mm;
 	vm_fault_t fault, major = 0;
-	unsigned long vm_flags = VM_READ | VM_WRITE;
+	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (kprobe_page_fault(regs, esr))
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 69e31dbdfdc2..329d01c689b7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -690,10 +690,10 @@ struct kvm_vcpu_arch {
 	bool pvclock_set_guest_stopped_request;
 
 	struct {
+		u8 preempted;
 		u64 msr_val;
 		u64 last_steal;
-		struct gfn_to_hva_cache stime;
-		struct kvm_steal_time steal;
+		struct gfn_to_pfn_cache cache;
 	} st;
 
 	u64 tsc_offset;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7e118883d8f1..0b0b143f0ab6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2648,45 +2648,47 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
 
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
+	/* -EAGAIN is returned in atomic context so we can just return. */
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT,
+			&map, &vcpu->arch.st.cache, false))
 		return;
 
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+
 	/*
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
 	 * expensive IPIs.
 	 */
 	trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
-		vcpu->arch.st.steal.preempted & KVM_VCPU_FLUSH_TLB);
-	if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB)
+		st->preempted & KVM_VCPU_FLUSH_TLB);
+	if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
 		kvm_vcpu_flush_tlb(vcpu, false);
 
-	if (vcpu->arch.st.steal.version & 1)
-		vcpu->arch.st.steal.version += 1;  /* first time write, random junk */
+	vcpu->arch.st.preempted = 0;
 
-	vcpu->arch.st.steal.version += 1;
+	if (st->version & 1)
+		st->version += 1;  /* first time write, random junk */
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	st->version += 1;
 
 	smp_wmb();
 
-	vcpu->arch.st.steal.steal += current->sched_info.run_delay -
+	st->steal += current->sched_info.run_delay -
 		vcpu->arch.st.last_steal;
 	vcpu->arch.st.last_steal = current->sched_info.run_delay;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
-
 	smp_wmb();
 
-	vcpu->arch.st.steal.version += 1;
+	st->version += 1;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false);
 }
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
@@ -2853,11 +2855,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (data & KVM_STEAL_RESERVED_MASK)
 			return 1;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
-						data & KVM_STEAL_VALID_BITS,
-						sizeof(struct kvm_steal_time)))
-			return 1;
-
 		vcpu->arch.st.msr_val = data;
 
 		if (!(data & KVM_MSR_ENABLED))
@@ -3567,15 +3564,25 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED;
+	if (vcpu->arch.st.preempted)
+		return;
+
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map,
+			&vcpu->arch.st.cache, true))
+		return;
+
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+
+	st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
 
-	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
-			&vcpu->arch.st.steal.preempted,
-			offsetof(struct kvm_steal_time, preempted),
-			sizeof(vcpu->arch.st.steal.preempted));
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -9325,8 +9332,11 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache;
 	int idx;
 
+	kvm_release_pfn(cache->pfn, cache->dirty, cache);
+
 	kvmclock_reset(vcpu);
 
 	kvm_x86_ops->vcpu_free(vcpu);
@@ -9855,11 +9865,18 @@ out_free:
 
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 {
+	struct kvm_vcpu *vcpu;
+	int i;
+
 	/*
 	 * memslots->generation has been incremented.
 	 * mmio generation may have reached its maximum value.
 	 */
 	kvm_mmu_invalidate_mmio_sptes(kvm, gen);
+
+	/* Force re-initialization of steal_time cache */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vcpu_kick(vcpu);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,