kasan: add support for kasan.fault=panic_on_write

KASAN's boot time kernel parameter 'kasan.fault=' currently supports
'report' and 'panic', which results in either only reporting bugs or also
panicking on reports.

However, some users may wish to have more control over when KASAN reports
result in a kernel panic: in particular, KASAN reported invalid _writes_
are of special interest, because they have greater potential to corrupt
random kernel memory or be more easily exploited.

To panic on invalid writes only, introduce 'kasan.fault=panic_on_write',
which allows users to choose to continue running on invalid reads, but
panic only on invalid writes.

Link: https://lkml.kernel.org/r/20230614095158.1133673-1-elver@google.com
Signed-off-by: Marco Elver <elver@google.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Aleksandr Nogikh <nogikh@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Taras Madan <tarasmadan@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 30 insertions, 8 deletions

diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index e66916a483cd..7f37a46af574 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -107,9 +107,10 @@ effectively disables ``panic_on_warn`` for KASAN reports.
 Alternatively, independent of ``panic_on_warn``, the ``kasan.fault=`` boot
 parameter can be used to control panic and reporting behaviour:
 
-- ``kasan.fault=report`` or ``=panic`` controls whether to only print a KASAN
-  report or also panic the kernel (default: ``report``). The panic happens even
-  if ``kasan_multi_shot`` is enabled.
+- ``kasan.fault=report``, ``=panic``, or ``=panic_on_write`` controls whether
+  to only print a KASAN report, panic the kernel, or panic the kernel on
+  invalid writes only (default: ``report``). The panic happens even if
+  ``kasan_multi_shot`` is enabled.
 
 Software and Hardware Tag-Based KASAN modes (see the section about various
 modes below) support altering stack trace collection behavior:
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 84d9f3b37014..ca4b6ff080a6 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -43,6 +43,7 @@ enum kasan_arg_fault {
 	KASAN_ARG_FAULT_DEFAULT,
 	KASAN_ARG_FAULT_REPORT,
 	KASAN_ARG_FAULT_PANIC,
+	KASAN_ARG_FAULT_PANIC_ON_WRITE,
 };
 
 static enum kasan_arg_fault kasan_arg_fault __ro_after_init = KASAN_ARG_FAULT_DEFAULT;
@@ -57,6 +58,8 @@ static int __init early_kasan_fault(char *arg)
 		kasan_arg_fault = KASAN_ARG_FAULT_REPORT;
 	else if (!strcmp(arg, "panic"))
 		kasan_arg_fault = KASAN_ARG_FAULT_PANIC;
+	else if (!strcmp(arg, "panic_on_write"))
+		kasan_arg_fault = KASAN_ARG_FAULT_PANIC_ON_WRITE;
 	else
 		return -EINVAL;
 
@@ -211,7 +214,7 @@ static void start_report(unsigned long *flags, bool sync)
 	pr_err("==================================================================\n");
 }
 
-static void end_report(unsigned long *flags, const void *addr)
+static void end_report(unsigned long *flags, const void *addr, bool is_write)
 {
 	if (addr)
 		trace_error_report_end(ERROR_DETECTOR_KASAN,
@@ -220,8 +223,18 @@ static void end_report(unsigned long *flags, const void *addr)
 	spin_unlock_irqrestore(&report_lock, *flags);
 	if (!test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags))
 		check_panic_on_warn("KASAN");
-	if (kasan_arg_fault == KASAN_ARG_FAULT_PANIC)
+	switch (kasan_arg_fault) {
+	case KASAN_ARG_FAULT_DEFAULT:
+	case KASAN_ARG_FAULT_REPORT:
+		break;
+	case KASAN_ARG_FAULT_PANIC:
 		panic("kasan.fault=panic set ...\n");
+		break;
+	case KASAN_ARG_FAULT_PANIC_ON_WRITE:
+		if (is_write)
+			panic("kasan.fault=panic_on_write set ...\n");
+		break;
+	}
 	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 	lockdep_on();
 	report_suppress_stop();
@@ -536,7 +549,11 @@ void kasan_report_invalid_free(void *ptr, unsigned long ip, enum kasan_report_ty
 
 	print_report(&info);
 
-	end_report(&flags, ptr);
+	/*
+	 * Invalid free is considered a "write" since the allocator's metadata
+	 * updates involves writes.
+	 */
+	end_report(&flags, ptr, true);
 }
 
 /*
@@ -570,7 +587,7 @@ bool kasan_report(const void *addr, size_t size, bool is_write,
 
 	print_report(&info);
 
-	end_report(&irq_flags, (void *)addr);
+	end_report(&irq_flags, (void *)addr, is_write);
 
 out:
 	user_access_restore(ua_flags);
@@ -596,7 +613,11 @@ void kasan_report_async(void)
 	pr_err("Asynchronous fault: no details available\n");
 	pr_err("\n");
 	dump_stack_lvl(KERN_ERR);
-	end_report(&flags, NULL);
+	/*
+	 * Conservatively set is_write=true, because no details are available.
+	 * In this mode, kasan.fault=panic_on_write is like kasan.fault=panic.
+	 */
+	end_report(&flags, NULL, true);
 }
 #endif /* CONFIG_KASAN_HW_TAGS */