powerpc/security: Fix link stack flush instruction

The inline execution path for the hardware assisted branch flush
instruction failed to set CTR to the correct value before bcctr,
causing a crash when the feature is enabled.

Fixes: 4d24e21c ("powerpc/security: Allow for processors that flush the link stack using the special bcctr")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201007080605.64423-1-npiggin@gmail.com

arch/powerpc/include/asm/asm-prototypes.h

@@ -145,7 +145,9 @@ void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
 void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
 
 /* Patch sites */
-extern s32 patch__call_flush_branch_caches;
+extern s32 patch__call_flush_branch_caches1;
+extern s32 patch__call_flush_branch_caches2;
+extern s32 patch__call_flush_branch_caches3;
 extern s32 patch__flush_count_cache_return;
 extern s32 patch__flush_link_stack_return;
 extern s32 patch__call_kvm_flush_link_stack;

arch/powerpc/kernel/entry_64.S

@@ -430,7 +430,11 @@ _ASM_NOKPROBE_SYMBOL(save_nvgprs);
 
 #define FLUSH_COUNT_CACHE	\
 1:	nop;			\
-	patch_site 1b, patch__call_flush_branch_caches
+	patch_site 1b, patch__call_flush_branch_caches1; \
+1:	nop;			\
+	patch_site 1b, patch__call_flush_branch_caches2; \
+1:	nop;			\
+	patch_site 1b, patch__call_flush_branch_caches3
 
 .macro nops number
 	.rept \number
@@ -512,7 +516,7 @@ _GLOBAL(_switch)
 
 	kuap_check_amr r9, r10
 
-	FLUSH_COUNT_CACHE
+	FLUSH_COUNT_CACHE	/* Clobbers r9, ctr */
 
 	/*
 	 * On SMP kernels, care must be taken because a task may be

arch/powerpc/kernel/security.c

@@ -430,30 +430,44 @@ device_initcall(stf_barrier_debugfs_init);
 
 static void update_branch_cache_flush(void)
 {
+	u32 *site;
+
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	site = &patch__call_kvm_flush_link_stack;
 	// This controls the branch from guest_exit_cont to kvm_flush_link_stack
 	if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) {
-		patch_instruction_site(&patch__call_kvm_flush_link_stack,
-				       ppc_inst(PPC_INST_NOP));
+		patch_instruction_site(site, ppc_inst(PPC_INST_NOP));
 	} else {
 		// Could use HW flush, but that could also flush count cache
-		patch_branch_site(&patch__call_kvm_flush_link_stack,
-				  (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
+		patch_branch_site(site, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
 	}
 #endif
 
+	// Patch out the bcctr first, then nop the rest
+	site = &patch__call_flush_branch_caches3;
+	patch_instruction_site(site, ppc_inst(PPC_INST_NOP));
+	site = &patch__call_flush_branch_caches2;
+	patch_instruction_site(site, ppc_inst(PPC_INST_NOP));
+	site = &patch__call_flush_branch_caches1;
+	patch_instruction_site(site, ppc_inst(PPC_INST_NOP));
+
 	// This controls the branch from _switch to flush_branch_caches
 	if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE &&
 	    link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) {
-		patch_instruction_site(&patch__call_flush_branch_caches,
-				       ppc_inst(PPC_INST_NOP));
+		// Nothing to be done
+
 	} else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW &&
 		   link_stack_flush_type == BRANCH_CACHE_FLUSH_HW) {
-		patch_instruction_site(&patch__call_flush_branch_caches,
-				       ppc_inst(PPC_INST_BCCTR_FLUSH));
+		// Patch in the bcctr last
+		site = &patch__call_flush_branch_caches1;
+		patch_instruction_site(site, ppc_inst(0x39207fff)); // li r9,0x7fff
+		site = &patch__call_flush_branch_caches2;
+		patch_instruction_site(site, ppc_inst(0x7d2903a6)); // mtctr r9
+		site = &patch__call_flush_branch_caches3;
+		patch_instruction_site(site, ppc_inst(PPC_INST_BCCTR_FLUSH));
+
 	} else {
-		patch_branch_site(&patch__call_flush_branch_caches,
-				  (u64)&flush_branch_caches, BRANCH_SET_LINK);
+		patch_branch_site(site, (u64)&flush_branch_caches, BRANCH_SET_LINK);
 
 		// If we just need to flush the link stack, early return
 		if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE) {