stackleak: rework stack low bound handling

In stackleak_task_init(), stackleak_track_stack(), and
__stackleak_erase(), we open-code skipping the STACK_END_MAGIC at the
bottom of the stack. Each case is implemented slightly differently, and
only the __stackleak_erase() case is commented.

In stackleak_task_init() and stackleak_track_stack() we unconditionally
add sizeof(unsigned long) to the lowest stack address. In
stackleak_task_init() we use end_of_stack() for this, and in
stackleak_track_stack() we use task_stack_page(). In __stackleak_erase()
we handle this by detecting if `kstack_ptr` has hit the stack end
boundary, and if so, conditionally moving it above the magic.

This patch adds a new stackleak_task_low_bound() helper which is used in
all three cases, which unconditionally adds sizeof(unsigned long) to the
lowest address on the task stack, with commentary as to why. This uses
end_of_stack() as stackleak_task_init() did prior to this patch, as this
is consistent with the code in kernel/fork.c which initializes the
STACK_END_MAGIC value.

In __stackleak_erase() we no longer need to check whether we've spilled
into the STACK_END_MAGIC value, as stackleak_track_stack() ensures that
`current->lowest_stack` stops immediately above this, and similarly the
poison scan will stop immediately above this.

For stackleak_task_init() and stackleak_track_stack() this results in no
change to code generation. For __stackleak_erase() the generated
assembly is slightly simpler and shorter.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-5-mark.rutland@arm.com

Author: mrutland-arm

include/linux/stackleak.h

@@ -15,9 +15,22 @@
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
 #include <asm/stacktrace.h>
 
+/*
+ * The lowest address on tsk's stack which we can plausibly erase.
+ */
+static __always_inline unsigned long
+stackleak_task_low_bound(const struct task_struct *tsk)
+{
+	/*
+	 * The lowest unsigned long on the task stack contains STACK_END_MAGIC,
+	 * which we must not corrupt.
+	 */
+	return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long);
+}
+
 static inline void stackleak_task_init(struct task_struct *t)
 {
-	t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long);
+	t->lowest_stack = stackleak_task_low_bound(t);
 # ifdef CONFIG_STACKLEAK_METRICS
 	t->prev_lowest_stack = t->lowest_stack;
 # endif

kernel/stackleak.c

@@ -72,9 +72,11 @@ late_initcall(stackleak_sysctls_init);
 
 static __always_inline void __stackleak_erase(void)
 {
+	const unsigned long task_stack_low = stackleak_task_low_bound(current);
+
 	/* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */
 	unsigned long kstack_ptr = current->lowest_stack;
-	unsigned long boundary = (unsigned long)end_of_stack(current);
+	unsigned long boundary = task_stack_low;
 	unsigned int poison_count = 0;
 	const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long);
 
@@ -88,13 +90,6 @@ static __always_inline void __stackleak_erase(void)
 		kstack_ptr -= sizeof(unsigned long);
 	}
 
-	/*
-	 * One 'long int' at the bottom of the thread stack is reserved and
-	 * should not be poisoned (see CONFIG_SCHED_STACK_END_CHECK=y).
-	 */
-	if (kstack_ptr == boundary)
-		kstack_ptr += sizeof(unsigned long);
-
 #ifdef CONFIG_STACKLEAK_METRICS
 	current->prev_lowest_stack = kstack_ptr;
 #endif
@@ -140,8 +135,7 @@ void __used __no_caller_saved_registers noinstr stackleak_track_stack(void)
 	/* 'lowest_stack' should be aligned on the register width boundary */
 	sp = ALIGN(sp, sizeof(unsigned long));
 	if (sp < current->lowest_stack &&
-	    sp >= (unsigned long)task_stack_page(current) +
-						sizeof(unsigned long)) {
+	    sp >= stackleak_task_low_bound(current)) {
 		current->lowest_stack = sp;
 	}
 }