[PATCH] arm64: Work around missing `bti c` in modules

[D Scott Phillips]

GCC does not insert a `bti c` instruction at the beginning of a function
when all callers reach the function through a direct branch[1]. In the case
of cross-section calls (like __init to non __init), a thunk may be inserted
which uses an indirect branch. If that happens, the first instruction in
the callee function will result in a Branch Target Exception due to the
missing `bti c`.

Handle Branch Target Exceptions which happen in the kernel due to module
calls from __init to non-__init by clearing PSTATE.BTYPE and resuming.

[1]: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106671

Signed-off-by: D Scott Phillips <scott at os.amperecomputing.com>
---
 arch/arm64/kernel/entry-common.c | 12 ++++++++++
 arch/arm64/kernel/traps.c        | 39 ++++++++++++++++++++++++++++++--
 2 files changed, 49 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index c75ca36b4a49..dad27e854d8c 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -388,6 +388,15 @@ static void noinstr el1_undef(struct pt_regs *regs)
 	exit_to_kernel_mode(regs);
 }
 
+static void noinstr el1_bti(struct pt_regs *regs)
+{
+	enter_from_kernel_mode(regs);
+	local_daif_inherit(regs);
+	do_bti(regs);
+	local_daif_mask();
+	exit_to_kernel_mode(regs);
+}
+
 static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr)
 {
 	unsigned long far = read_sysreg(far_el1);
@@ -427,6 +436,9 @@ asmlinkage void noinstr el1h_64_sync_handler(struct pt_regs *regs)
 	case ESR_ELx_EC_UNKNOWN:
 		el1_undef(regs);
 		break;
+	case ESR_ELx_EC_BTI:
+		el1_bti(regs);
+		break;
 	case ESR_ELx_EC_BREAKPT_CUR:
 	case ESR_ELx_EC_SOFTSTP_CUR:
 	case ESR_ELx_EC_WATCHPT_CUR:
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index b7fed33981f7..f4f1dfa64137 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -501,8 +501,43 @@ NOKPROBE_SYMBOL(do_undefinstr);
 
 void do_bti(struct pt_regs *regs)
 {
-	BUG_ON(!user_mode(regs));
-	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
+	struct module *mod;
+
+	if (user_mode(regs)) {
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
+		return;
+	}
+
+	/*
+	 * GCC does not insert a `bti c` instruction at the beginning
+	 * of a function when all callers reach the function through a
+	 * direct branch. In the case of cross-section calls (like
+	 * __init to non __init), a thunk may be inserted which uses
+	 * an indirect branch. If that happens, the first instruction
+	 * in the callee function will result in a Branch Target
+	 * Exception due to the missing `bti c`.
+	 *
+	 * If that's the case here, clear PSTATE.BTYPE and resume.
+	 */
+	if (IS_ENABLED(CONFIG_CC_IS_GCC)) {
+		preempt_disable();
+		mod = __module_text_address(regs->pc);
+		preempt_enable();
+
+		if (mod && try_module_get(mod)) {
+			bool from_init;
+
+			from_init = within_module_init(regs->regs[30], mod);
+			module_put(mod);
+
+			if (from_init) {
+				regs->pstate &= ~PSR_BTYPE_MASK;
+				return;
+			}
+		}
+	}
+
+	die("Oops - BTI", regs, 0);
 }
 NOKPROBE_SYMBOL(do_bti);
 
-- 
2.37.2