[PATCH v3 3/3] list_debug: Introduce CONFIG_DEBUG_LIST_MINIMAL

From: Marco Elver
Date: Tue Aug 08 2023 - 13:27:32 EST

Numerous production kernel configs (see [1, 2]) are choosing to enable
CONFIG_DEBUG_LIST, which is also being recommended by KSPP for hardened
configs [3]. The feature has never been designed with performance in
mind, yet common list manipulation is happening across hot paths all
over the kernel.

Introduce CONFIG_DEBUG_LIST_MINIMAL, which performs list pointer
checking inline, and only upon list corruption delegates to the
reporting slow path.

To generate optimal machine code with CONFIG_DEBUG_LIST_MINIMAL:

1. Elide checking for pointer values which upon dereference would
result in an immediate access fault -- therefore "minimal" checks.
The trade-off is lower-quality error reports.

2. Use the newly introduced __preserve_most function attribute
(available with Clang, but not yet with GCC) to minimize the code
footprint for calling the reporting slow path. As a result,
function size of callers is reduced by avoiding saving registers
before calling the rarely called reporting slow path.

Note that all TUs in lib/Makefile already disable function tracing,
including list_debug.c, and __preserve_most's implied notrace has
no effect in this case.

3. Because the inline checks are a subset of the full set of checks in
___list_*_valid(), always return false if the inline checks failed.
This avoids redundant compare and conditional branch right after
return from the slow path.

As a side-effect of the checks being inline, if the compiler can prove
some condition to always be true, it can completely elide some checks.

Running netperf with CONFIG_DEBUG_LIST_MINIMAL (using a Clang compiler
with "preserve_most") shows throughput improvements, in my case of ~7%
on average (up to 20-30% on some test cases).

Link: https://r.android.com/1266735 [1]
Link: https://gitlab.archlinux.org/archlinux/packaging/packages/linux/-/blob/main/config [2]
Link: https://kernsec.org/wiki/index.php/Kernel_Self_Protection_Project/Recommended_Settings [3]
Signed-off-by: Marco Elver <elver@xxxxxxxxxx>
---
v3:
* Rename ___list_*_valid() to __list_*_valid_or_report().
* More comments.

v2:
* Note that lib/Makefile disables function tracing for everything and
__preserve_most's implied notrace is a noop here.
---
arch/arm64/kvm/hyp/nvhe/list_debug.c | 2 +
include/linux/list.h | 64 +++++++++++++++++++++++++---
lib/Kconfig.debug | 15 +++++++
lib/list_debug.c | 2 +
4 files changed, 77 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/list_debug.c b/arch/arm64/kvm/hyp/nvhe/list_debug.c
index 16266a939a4c..46a2d4f2b3c6 100644
--- a/arch/arm64/kvm/hyp/nvhe/list_debug.c
+++ b/arch/arm64/kvm/hyp/nvhe/list_debug.c
@@ -26,6 +26,7 @@ static inline __must_check bool nvhe_check_data_corruption(bool v)

/* The predicates checked here are taken from lib/list_debug.c. */

+__list_valid_slowpath
bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev,
struct list_head *next)
{
@@ -37,6 +38,7 @@ bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev,
return true;
}

+__list_valid_slowpath
bool __list_del_entry_valid_or_report(struct list_head *entry)
{
struct list_head *prev, *next;
diff --git a/include/linux/list.h b/include/linux/list.h
index 130c6a1bb45c..066fe33e99bf 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -39,38 +39,90 @@ static inline void INIT_LIST_HEAD(struct list_head *list)
}

#ifdef CONFIG_DEBUG_LIST
+
+#ifdef CONFIG_DEBUG_LIST_MINIMAL
+# define __list_valid_slowpath __cold __preserve_most
+#else
+# define __list_valid_slowpath
+#endif
+
/*
* Performs the full set of list corruption checks before __list_add().
* On list corruption reports a warning, and returns false.
*/
-extern bool __list_add_valid_or_report(struct list_head *new,
- struct list_head *prev,
- struct list_head *next);
+extern bool __list_valid_slowpath __list_add_valid_or_report(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next);

/*
* Performs list corruption checks before __list_add(). Returns false if a
* corruption is detected, true otherwise.
+ *
+ * With CONFIG_DEBUG_LIST_MINIMAL set, performs minimal list integrity checking
+ * (that do not result in a fault) inline, and only if a corruption is detected
+ * calls the reporting function __list_add_valid_or_report().
*/
static __always_inline bool __list_add_valid(struct list_head *new,
struct list_head *prev,
struct list_head *next)
{
- return __list_add_valid_or_report(new, prev, next);
+ bool ret = true;
+
+ if (IS_ENABLED(CONFIG_DEBUG_LIST_MINIMAL)) {
+ /*
+ * In the minimal config, elide checking if next and prev are
+ * NULL, since the immediate dereference of them below would
+ * result in a fault if NULL.
+ *
+ * With the minimal config we can afford to inline the checks,
+ * which also gives the compiler a chance to elide some of them
+ * completely if they can be proven at compile-time. If one of
+ * the pre-conditions does not hold, the slow-path will show a
+ * report which pre-condition failed.
+ */
+ if (likely(next->prev == prev && prev->next == next && new != prev && new != next))
+ return true;
+ ret = false;
+ }
+
+ ret &= __list_add_valid_or_report(new, prev, next);
+ return ret;
}

/*
* Performs the full set of list corruption checks before __list_del_entry().
* On list corruption reports a warning, and returns false.
*/
-extern bool __list_del_entry_valid_or_report(struct list_head *entry);
+extern bool __list_valid_slowpath __list_del_entry_valid_or_report(struct list_head *entry);

/*
* Performs list corruption checks before __list_del_entry(). Returns false if a
* corruption is detected, true otherwise.
+ *
+ * With CONFIG_DEBUG_LIST_MINIMAL set, performs minimal list integrity checking
+ * (that do not result in a fault) inline, and only if a corruption is detected
+ * calls the reporting function __list_del_entry_valid_or_report().
*/
static __always_inline bool __list_del_entry_valid(struct list_head *entry)
{
- return __list_del_entry_valid_or_report(entry);
+ bool ret = true;
+
+ if (IS_ENABLED(CONFIG_DEBUG_LIST_MINIMAL)) {
+ struct list_head *prev = entry->prev;
+ struct list_head *next = entry->next;
+
+ /*
+ * In the minimal config, elide checking if next and prev are
+ * NULL, LIST_POISON1 or LIST_POISON2, since the immediate
+ * dereference of them below would result in a fault.
+ */
+ if (likely(prev->next == entry && next->prev == entry))
+ return true;
+ ret = false;
+ }
+
+ ret &= __list_del_entry_valid_or_report(entry);
+ return ret;
}
#else
static inline bool __list_add_valid(struct list_head *new,
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index fbc89baf7de6..e72cf08af0fa 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1680,6 +1680,21 @@ config DEBUG_LIST

If unsure, say N.

+config DEBUG_LIST_MINIMAL
+ bool "Minimal linked list debug checks"
+ default !DEBUG_KERNEL
+ depends on DEBUG_LIST
+ help
+ Only perform the minimal set of checks in the linked-list walking
+ routines to catch corruptions that are not guaranteed to result in an
+ immediate access fault.
+
+ This trades lower quality error reports for improved performance: the
+ generated code should be more optimal and provide trade-offs that may
+ better serve safety- and performance- critical environments.
+
+ If unsure, say Y.
+
config DEBUG_PLIST
bool "Debug priority linked list manipulation"
depends on DEBUG_KERNEL
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 2def33b1491f..0ff547910dd0 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -17,6 +17,7 @@
* attempt).
*/

+__list_valid_slowpath
bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev,
struct list_head *next)
{
@@ -39,6 +40,7 @@ bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev,
}
EXPORT_SYMBOL(__list_add_valid_or_report);

+__list_valid_slowpath
bool __list_del_entry_valid_or_report(struct list_head *entry)
{
struct list_head *prev, *next;
--
2.41.0.640.ga95def55d0-goog