KVM: arm64: Add templates for BHB mitigation sequences

KVM writes the Spectre-v2 mitigation template at the beginning of each
vector when a CPU requires a specific sequence to run.
Because the template is copied, it can not be modified by the alternatives
at runtime. As the KVM template code is intertwined with the bp-hardening
callbacks all templates must have a bp-hardening callback.
Add templates for calling ARCH_WORKAROUND_3  and one for each value of K
in the brancy-loop. Identify these sequences by a new parameter
template_start, and add a copy of install_bp_hardening_cb() that is able to
install them.

Change-Id: I3dbb2d1e06663cbf39b1d212547ac64d569fd72e
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Git-commit: a68912a3ae
Git-repo: https://android.googlesource.com/kernel/common/
Signed-off-by: Kishor Krishna Bhat <quic_kishkris@quicinc.com>

arch/arm64/include/asm/cpucaps.h

@@ -56,6 +56,7 @@
 #define ARM64_WORKAROUND_1188873		35
 #define ARM64_WORKAROUND_1542418		36
 #define ARM64_WORKAROUND_1542419		37
+#define ARM64_SPECTRE_BHB			38
 
 /* kabi: reserve 38 - 62 for future cpu capabilities */
 #define ARM64_NCAPS				62

arch/arm64/include/asm/kvm_mmu.h

@@ -439,7 +439,8 @@ static inline void *kvm_get_hyp_vector(void)
 	void *vect = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
 	int slot = -1;
 
-	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) {
+	if ((cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) ||
+		cpus_have_const_cap(ARM64_SPECTRE_BHB)) && data->template_start) {
 		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs_start));
 		slot = data->hyp_vectors_slot;
 	}
@@ -468,7 +469,8 @@ static inline int kvm_map_vectors(void)
 	 * !HBP +  HEL2 -> allocate one vector slot and use exec mapping
 	 *  HBP +  HEL2 -> use hardened vertors and use exec mapping
 	 */
-	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) {
+	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) ||
+		cpus_have_const_cap(ARM64_SPECTRE_BHB)) {
 		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs_start);
 		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
 	}

arch/arm64/include/asm/mmu.h

@@ -49,6 +49,12 @@ typedef void (*bp_hardening_cb_t)(void);
 struct bp_hardening_data {
 	int			hyp_vectors_slot;
 	bp_hardening_cb_t	fn;
+
+	/*
+	 * template_start is only used by the BHB mitigation to identify the
+	 * hyp_vectors_slot sequence.
+	 */
+	const char *template_start;
 };
 
 #if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\

arch/arm64/kernel/cpu_errata.c

@@ -98,6 +98,14 @@ DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
 extern char __smccc_workaround_1_smc_start[];
 extern char __smccc_workaround_1_smc_end[];
+extern char __smccc_workaround_3_smc_start[];
+extern char __smccc_workaround_3_smc_end[];
+extern char __spectre_bhb_loop_k8_start[];
+extern char __spectre_bhb_loop_k8_end[];
+extern char __spectre_bhb_loop_k24_start[];
+extern char __spectre_bhb_loop_k24_end[];
+extern char __spectre_bhb_loop_k32_start[];
+extern char __spectre_bhb_loop_k32_end[];
 
 static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 				const char *hyp_vecs_end)
@@ -111,11 +119,11 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
 }
 
+static DEFINE_SPINLOCK(bp_lock);
 static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 				    const char *hyp_vecs_start,
 				    const char *hyp_vecs_end)
 {
-	static DEFINE_SPINLOCK(bp_lock);
 	int cpu, slot = -1;
 
 	spin_lock(&bp_lock);
@@ -134,6 +142,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 
 	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
 	__this_cpu_write(bp_hardening_data.fn, fn);
+	__this_cpu_write(bp_hardening_data.template_start, hyp_vecs_start);
 	spin_unlock(&bp_lock);
 }
 #else
@@ -982,6 +991,60 @@ enum mitigation_state arm64_get_spectre_bhb_state(void)
 	return spectre_bhb_state;
 }
 
+#ifdef CONFIG_KVM_INDIRECT_VECTORS
+static const char *kvm_bhb_get_vecs_end(const char *start)
+{
+	if (start == __smccc_workaround_3_smc_start)
+		return __smccc_workaround_3_smc_end;
+	else if (start == __spectre_bhb_loop_k8_start)
+		return __spectre_bhb_loop_k8_end;
+else if (start == __spectre_bhb_loop_k24_start)
+		return __spectre_bhb_loop_k24_end;
+else if (start == __spectre_bhb_loop_k32_start)
+		return __spectre_bhb_loop_k32_end;
+
+	return NULL;
+
+
+void kvm_setup_bhb_slot(const char *hyp_vecs_start)
+{
+	int cpu, slot = -1;
+	const char *hyp_vecs_end;
+
+if (!IS_ENABLED(CONFIG_KVM) || !is_hyp_mode_available())
+		return;
+
+	hyp_vecs_end = kvm_bhb_get_vecs_end(hyp_vecs_start);
+	if (WARN_ON_ONCE(!hyp_vecs_start || !hyp_vecs_end))
+		return;
+
+	spin_lock(&bp_lock);
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(bp_hardening_data.template_start, cpu) == hyp_vecs_start) {
+			slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu);
+			break;
+		}
+	}
+
+	if (slot == -1) {
+		slot = atomic_inc_return(&arm64_el2_vector_last_slot);
+		BUG_ON(slot >= BP_HARDEN_EL2_SLOTS);
+		__copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end);
+	}
+
+	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
+	__this_cpu_write(bp_hardening_data.template_start, hyp_vecs_start);
+	spin_unlock(&bp_lock);
+}
+#else
+#define __smccc_workaround_3_smc_start NULL
+#define __spectre_bhb_loop_k8_start NULL
+#define __spectre_bhb_loop_k24_start NULL
+#define __spectre_bhb_loop_k32_start NULL
+
+void kvm_setup_bhb_slot(const char *hyp_vecs_start) { };
+#endif
+
 ssize_t cpu_show_spec_store_bypass(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {

arch/arm64/kvm/hyp/hyp-entry.S

@@ -334,4 +334,59 @@ ENTRY(__smccc_workaround_1_smc_start)
 	ldp	x0, x1, [sp, #(8 * 2)]
 	add	sp, sp, #(8 * 4)
 ENTRY(__smccc_workaround_1_smc_end)
+
+ENTRY(__smccc_workaround_3_smc_start)
+	esb
+	sub	sp, sp, #(8 * 4)
+	stp	x2, x3, [sp, #(8 * 0)]
+	stp	x0, x1, [sp, #(8 * 2)]
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_3
+	smc	#0
+	ldp	x2, x3, [sp, #(8 * 0)]
+	ldp	x0, x1, [sp, #(8 * 2)]
+	add	sp, sp, #(8 * 4)
+ENTRY(__smccc_workaround_3_smc_end)
+
+ENTRY(__spectre_bhb_loop_k8_start)
+	esb
+	sub	sp, sp, #(8 * 2)
+	stp	x0, x1, [sp, #(8 * 0)]
+	mov	x0, #8
+2:	b	. + 4
+	subs	x0, x0, #1
+	b.ne	2b
+	dsb	nsh
+	isb
+	ldp	x0, x1, [sp, #(8 * 0)]
+	add	sp, sp, #(8 * 2)
+ENTRY(__spectre_bhb_loop_k8_end)
+
+ENTRY(__spectre_bhb_loop_k24_start)
+	esb
+	sub	sp, sp, #(8 * 2)
+	stp	x0, x1, [sp, #(8 * 0)]
+	mov	x0, #24
+2:	b	. + 4
+	subs	x0, x0, #1
+	b.ne	2b
+	dsb	nsh
+	isb
+	ldp	x0, x1, [sp, #(8 * 0)]
+	add	sp, sp, #(8 * 2)
+ENTRY(__spectre_bhb_loop_k24_end)
+
+ENTRY(__spectre_bhb_loop_k32_start)
+	esb
+	sub	sp, sp, #(8 * 2)
+	stp	x0, x1, [sp, #(8 * 0)]
+	mov     x0, #32
+2:	b	. + 4
+	subs	x0, x0, #1
+	b.ne	2b
+	dsb	nsh
+	isb
+	ldp	x0, x1, [sp, #(8 * 0)]
+	add	sp, sp, #(8 * 2)
+ENTRY(__spectre_bhb_loop_k32_end)
+
 #endif