linux-kernel - [PATCH 4.14 095/109] ARM: KVM: invalidate BTB on guest exit for Cortex-A12/A17

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: <20181016170530.142174682@linuxfoundation.org>
Date:   Tue, 16 Oct 2018 19:06:03 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Marc Zyngier <marc.zyngier@....com>,
        Russell King <rmk+kernel@...linux.org.uk>,
        Tony Lindgren <tony@...mide.com>,
        "David A. Long" <dave.long@...aro.org>
Subject: [PATCH 4.14 095/109] ARM: KVM: invalidate BTB on guest exit for Cortex-A12/A17

4.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <marc.zyngier@....com>

Commit 3f7e8e2e1ebda787f156ce46e3f0a9ce2833fa4f upstream.

In order to avoid aliasing attacks against the branch predictor,
let's invalidate the BTB on guest exit. This is made complicated
by the fact that we cannot take a branch before invalidating the
BTB.

We only apply this to A12 and A17, which are the only two ARM
cores on which this useful.

Signed-off-by: Marc Zyngier <marc.zyngier@....com>
Signed-off-by: Russell King <rmk+kernel@...linux.org.uk>
Boot-tested-by: Tony Lindgren <tony@...mide.com>
Reviewed-by: Tony Lindgren <tony@...mide.com>
Signed-off-by: David A. Long <dave.long@...aro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
 arch/arm/include/asm/kvm_asm.h |    2 -
 arch/arm/include/asm/kvm_mmu.h |   17 +++++++++
 arch/arm/kvm/hyp/hyp-entry.S   |   71 +++++++++++++++++++++++++++++++++++++++--
 3 files changed, 85 insertions(+), 5 deletions(-)

--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -61,8 +61,6 @@ struct kvm_vcpu;
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
 
-extern char __kvm_hyp_vector[];
-
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -246,7 +246,22 @@ static inline int kvm_read_guest_lock(st
 
 static inline void *kvm_get_hyp_vector(void)
 {
-	return kvm_ksym_ref(__kvm_hyp_vector);
+	switch(read_cpuid_part()) {
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	case ARM_CPU_PART_CORTEX_A12:
+	case ARM_CPU_PART_CORTEX_A17:
+	{
+		extern char __kvm_hyp_vector_bp_inv[];
+		return kvm_ksym_ref(__kvm_hyp_vector_bp_inv);
+	}
+
+#endif
+	default:
+	{
+		extern char __kvm_hyp_vector[];
+		return kvm_ksym_ref(__kvm_hyp_vector);
+	}
+	}
 }
 
 static inline int kvm_map_vectors(void)
--- a/arch/arm/kvm/hyp/hyp-entry.S
+++ b/arch/arm/kvm/hyp/hyp-entry.S
@@ -71,6 +71,66 @@ __kvm_hyp_vector:
 	W(b)	hyp_irq
 	W(b)	hyp_fiq
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	.align 5
+__kvm_hyp_vector_bp_inv:
+	.global __kvm_hyp_vector_bp_inv
+
+	/*
+	 * We encode the exception entry in the bottom 3 bits of
+	 * SP, and we have to guarantee to be 8 bytes aligned.
+	 */
+	W(add)	sp, sp, #1	/* Reset 	  7 */
+	W(add)	sp, sp, #1	/* Undef	  6 */
+	W(add)	sp, sp, #1	/* Syscall	  5 */
+	W(add)	sp, sp, #1	/* Prefetch abort 4 */
+	W(add)	sp, sp, #1	/* Data abort	  3 */
+	W(add)	sp, sp, #1	/* HVC		  2 */
+	W(add)	sp, sp, #1	/* IRQ		  1 */
+	W(nop)			/* FIQ		  0 */
+
+	mcr	p15, 0, r0, c7, c5, 6	/* BPIALL */
+	isb
+
+#ifdef CONFIG_THUMB2_KERNEL
+	/*
+	 * Yet another silly hack: Use VPIDR as a temp register.
+	 * Thumb2 is really a pain, as SP cannot be used with most
+	 * of the bitwise instructions. The vect_br macro ensures
+	 * things gets cleaned-up.
+	 */
+	mcr	p15, 4, r0, c0, c0, 0	/* VPIDR */
+	mov	r0, sp
+	and	r0, r0, #7
+	sub	sp, sp, r0
+	push	{r1, r2}
+	mov	r1, r0
+	mrc	p15, 4, r0, c0, c0, 0	/* VPIDR */
+	mrc	p15, 0, r2, c0, c0, 0	/* MIDR  */
+	mcr	p15, 4, r2, c0, c0, 0	/* VPIDR */
+#endif
+
+.macro vect_br val, targ
+ARM(	eor	sp, sp, #\val	)
+ARM(	tst	sp, #7		)
+ARM(	eorne	sp, sp, #\val	)
+
+THUMB(	cmp	r1, #\val	)
+THUMB(	popeq	{r1, r2}	)
+
+	beq	\targ
+.endm
+
+	vect_br	0, hyp_fiq
+	vect_br	1, hyp_irq
+	vect_br	2, hyp_hvc
+	vect_br	3, hyp_dabt
+	vect_br	4, hyp_pabt
+	vect_br	5, hyp_svc
+	vect_br	6, hyp_undef
+	vect_br	7, hyp_reset
+#endif
+
 .macro invalid_vector label, cause
 	.align
 \label:	mov	r0, #\cause
@@ -149,7 +209,14 @@ hyp_hvc:
 	bx	ip
 
 1:
-	push	{lr}
+	/*
+	 * Pushing r2 here is just a way of keeping the stack aligned to
+	 * 8 bytes on any path that can trigger a HYP exception. Here,
+	 * we may well be about to jump into the guest, and the guest
+	 * exit would otherwise be badly decoded by our fancy
+	 * "decode-exception-without-a-branch" code...
+	 */
+	push	{r2, lr}
 
 	mov	lr, r0
 	mov	r0, r1
@@ -159,7 +226,7 @@ hyp_hvc:
 THUMB(	orr	lr, #1)
 	blx	lr			@ Call the HYP function
 
-	pop	{lr}
+	pop	{r2, lr}
 	eret
 
 guest_trap: