[PATCH v2 26/34] kfence: Enable capability analysis

[Marco Elver <elver@google.com>]

Enable capability analysis for the KFENCE subsystem.

Notable, kfence_handle_page_fault() required minor restructure, which
also fixed a subtle race; arguably that function is more readable now.

Signed-off-by: Marco Elver <elver@google.com>
---
v2:
* Remove disable/enable_capability_analysis() around headers.
* Use __capability_unsafe() instead of __no_capability_analysis.
---
 mm/kfence/Makefile |  2 ++
 mm/kfence/core.c   | 20 +++++++++++++-------
 mm/kfence/kfence.h | 14 ++++++++------
 mm/kfence/report.c |  4 ++--
 4 files changed, 25 insertions(+), 15 deletions(-)

diff --git a/mm/kfence/Makefile b/mm/kfence/Makefile
index 2de2a58d11a1..b3640bdc3c69 100644
--- a/mm/kfence/Makefile
+++ b/mm/kfence/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
+CAPABILITY_ANALYSIS := y
+
 obj-y := core.o report.o
 
 CFLAGS_kfence_test.o := -fno-omit-frame-pointer -fno-optimize-sibling-calls
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 102048821c22..f75c3c11c0be 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -132,8 +132,8 @@ struct kfence_metadata *kfence_metadata __read_mostly;
 static struct kfence_metadata *kfence_metadata_init __read_mostly;
 
 /* Freelist with available objects. */
-static struct list_head kfence_freelist = LIST_HEAD_INIT(kfence_freelist);
-static DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */
+DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */
+static struct list_head kfence_freelist __guarded_by(&kfence_freelist_lock) = LIST_HEAD_INIT(kfence_freelist);
 
 /*
  * The static key to set up a KFENCE allocation; or if static keys are not used
@@ -253,6 +253,7 @@ static bool kfence_unprotect(unsigned long addr)
 }
 
 static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta)
+	__must_hold(&meta->lock)
 {
 	unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2;
 	unsigned long pageaddr = (unsigned long)&__kfence_pool[offset];
@@ -288,6 +289,7 @@ static inline bool kfence_obj_allocated(const struct kfence_metadata *meta)
 static noinline void
 metadata_update_state(struct kfence_metadata *meta, enum kfence_object_state next,
 		      unsigned long *stack_entries, size_t num_stack_entries)
+	__must_hold(&meta->lock)
 {
 	struct kfence_track *track =
 		next == KFENCE_OBJECT_ALLOCATED ? &meta->alloc_track : &meta->free_track;
@@ -485,7 +487,7 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g
 	alloc_covered_add(alloc_stack_hash, 1);
 
 	/* Set required slab fields. */
-	slab = virt_to_slab((void *)meta->addr);
+	slab = virt_to_slab(addr);
 	slab->slab_cache = cache;
 	slab->objects = 1;
 
@@ -514,6 +516,7 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g
 static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool zombie)
 {
 	struct kcsan_scoped_access assert_page_exclusive;
+	u32 alloc_stack_hash;
 	unsigned long flags;
 	bool init;
 
@@ -546,9 +549,10 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z
 	/* Mark the object as freed. */
 	metadata_update_state(meta, KFENCE_OBJECT_FREED, NULL, 0);
 	init = slab_want_init_on_free(meta->cache);
+	alloc_stack_hash = meta->alloc_stack_hash;
 	raw_spin_unlock_irqrestore(&meta->lock, flags);
 
-	alloc_covered_add(meta->alloc_stack_hash, -1);
+	alloc_covered_add(alloc_stack_hash, -1);
 
 	/* Check canary bytes for memory corruption. */
 	check_canary(meta);
@@ -593,6 +597,7 @@ static void rcu_guarded_free(struct rcu_head *h)
  * which partial initialization succeeded.
  */
 static unsigned long kfence_init_pool(void)
+	__capability_unsafe(/* constructor */)
 {
 	unsigned long addr;
 	struct page *pages;
@@ -1192,6 +1197,7 @@ bool kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs
 {
 	const int page_index = (addr - (unsigned long)__kfence_pool) / PAGE_SIZE;
 	struct kfence_metadata *to_report = NULL;
+	unsigned long unprotected_page = 0;
 	enum kfence_error_type error_type;
 	unsigned long flags;
 
@@ -1225,9 +1231,8 @@ bool kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs
 		if (!to_report)
 			goto out;
 
-		raw_spin_lock_irqsave(&to_report->lock, flags);
-		to_report->unprotected_page = addr;
 		error_type = KFENCE_ERROR_OOB;
+		unprotected_page = addr;
 
 		/*
 		 * If the object was freed before we took the look we can still
@@ -1239,7 +1244,6 @@ bool kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs
 		if (!to_report)
 			goto out;
 
-		raw_spin_lock_irqsave(&to_report->lock, flags);
 		error_type = KFENCE_ERROR_UAF;
 		/*
 		 * We may race with __kfence_alloc(), and it is possible that a
@@ -1251,6 +1255,8 @@ bool kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs
 
 out:
 	if (to_report) {
+		raw_spin_lock_irqsave(&to_report->lock, flags);
+		to_report->unprotected_page = unprotected_page;
 		kfence_report_error(addr, is_write, regs, to_report, error_type);
 		raw_spin_unlock_irqrestore(&to_report->lock, flags);
 	} else {
diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h
index dfba5ea06b01..f9caea007246 100644
--- a/mm/kfence/kfence.h
+++ b/mm/kfence/kfence.h
@@ -34,6 +34,8 @@
 /* Maximum stack depth for reports. */
 #define KFENCE_STACK_DEPTH 64
 
+extern raw_spinlock_t kfence_freelist_lock;
+
 /* KFENCE object states. */
 enum kfence_object_state {
 	KFENCE_OBJECT_UNUSED,		/* Object is unused. */
@@ -53,7 +55,7 @@ struct kfence_track {
 
 /* KFENCE metadata per guarded allocation. */
 struct kfence_metadata {
-	struct list_head list;		/* Freelist node; access under kfence_freelist_lock. */
+	struct list_head list __guarded_by(&kfence_freelist_lock);	/* Freelist node. */
 	struct rcu_head rcu_head;	/* For delayed freeing. */
 
 	/*
@@ -91,13 +93,13 @@ struct kfence_metadata {
 	 * In case of an invalid access, the page that was unprotected; we
 	 * optimistically only store one address.
 	 */
-	unsigned long unprotected_page;
+	unsigned long unprotected_page __guarded_by(&lock);
 
 	/* Allocation and free stack information. */
-	struct kfence_track alloc_track;
-	struct kfence_track free_track;
+	struct kfence_track alloc_track __guarded_by(&lock);
+	struct kfence_track free_track __guarded_by(&lock);
 	/* For updating alloc_covered on frees. */
-	u32 alloc_stack_hash;
+	u32 alloc_stack_hash __guarded_by(&lock);
 #ifdef CONFIG_MEMCG
 	struct slabobj_ext obj_exts;
 #endif
@@ -141,6 +143,6 @@ enum kfence_error_type {
 void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *regs,
 			 const struct kfence_metadata *meta, enum kfence_error_type type);
 
-void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta);
+void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta) __must_hold(&meta->lock);
 
 #endif /* MM_KFENCE_KFENCE_H */
diff --git a/mm/kfence/report.c b/mm/kfence/report.c
index 10e6802a2edf..787e87c26926 100644
--- a/mm/kfence/report.c
+++ b/mm/kfence/report.c
@@ -106,6 +106,7 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
 
 static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadata *meta,
 			       bool show_alloc)
+	__must_hold(&meta->lock)
 {
 	const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track;
 	u64 ts_sec = track->ts_nsec;
@@ -207,8 +208,6 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
 	if (WARN_ON(type != KFENCE_ERROR_INVALID && !meta))
 		return;
 
-	if (meta)
-		lockdep_assert_held(&meta->lock);
 	/*
 	 * Because we may generate reports in printk-unfriendly parts of the
 	 * kernel, such as scheduler code, the use of printk() could deadlock.
@@ -263,6 +262,7 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
 	stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr, 0);
 
 	if (meta) {
+		lockdep_assert_held(&meta->lock);
 		pr_err("\n");
 		kfence_print_object(NULL, meta);
 	}
-- 
2.48.1.711.g2feabab25a-goog