[208/262] kfence: limit currently covered allocations when pool nearly full

Commit Message

Andrew Morton Nov. 5, 2021, 8:45 p.m. UTC

From: Marco Elver <[e-mail]>
Subject: kfence: limit currently covered allocations when pool nearly full

One of KFENCE's main design principles is that with increasing uptime,
allocation coverage increases sufficiently to detect previously undetected
bugs.

We have observed that frequent long-lived allocations of the same source
(e.g.  pagecache) tend to permanently fill up the KFENCE pool with
increasing system uptime, thus breaking the above requirement.  The
workaround thus far had been increasing the sample interval and/or
increasing the KFENCE pool size, but is no reliable solution.

To ensure diverse coverage of allocations, limit currently covered
allocations of the same source once pool utilization reaches 75%
(configurable via `kfence.skip_covered_thresh`) or above.  The effect is
retaining reasonable allocation coverage when the pool is close to full.

A side-effect is that this also limits frequent long-lived allocations of
the same source filling up the pool permanently.

Uniqueness of an allocation for coverage purposes is based on its
(partial) allocation stack trace (the source).  A Counting Bloom filter is
used to check if an allocation is covered; if the allocation is currently
covered, the allocation is skipped by KFENCE.

Testing was done using:

	(a) a synthetic workload that performs frequent long-lived
	    allocations (default config values; sample_interval=1;
	    num_objects=63), and

	(b) normal desktop workloads on an otherwise idle machine where
	    the problem was first reported after a few days of uptime
	    (default config values).

In both test cases the sampled allocation rate no longer drops to zero at
any point.  In the case of (b) we observe (after 2 days uptime) 15% unique
allocations in the pool, 77% pool utilization, with 20% "skipped
allocations (covered)".

[[e-mail]: simplify and just use hash_32(), use more random stack_hash_seed]
  Link: https://lkml.kernel.org/r/[e-mail]
[[e-mail]: fix 32 bit]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Marco Elver <[e-mail]>
Reviewed-by: Dmitry Vyukov <[e-mail]>
Acked-by: Alexander Potapenko <[e-mail]>
Cc: Aleksandr Nogikh <[e-mail]>
Cc: Jann Horn <[e-mail]>
Cc: Taras Madan <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 mm/kfence/core.c   |  109 ++++++++++++++++++++++++++++++++++++++++++-
 mm/kfence/kfence.h |    2 
 2 files changed, 109 insertions(+), 2 deletions(-)

Patch

--- a/mm/kfence/core.c~kfence-limit-currently-covered-allocations-when-pool-nearly-full
+++ a/mm/kfence/core.c
@@ -10,12 +10,15 @@ 
 #include <linux/atomic.h>
 #include <linux/bug.h>
 #include <linux/debugfs.h>
+#include <linux/hash.h>
 #include <linux/irq_work.h>
+#include <linux/jhash.h>
 #include <linux/kcsan-checks.h>
 #include <linux/kfence.h>
 #include <linux/kmemleak.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
+#include <linux/log2.h>
 #include <linux/memblock.h>
 #include <linux/moduleparam.h>
 #include <linux/random.h>
@@ -82,6 +85,10 @@  static const struct kernel_param_ops sam
 };
 module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_interval, 0600);
 
+/* Pool usage% threshold when currently covered allocations are skipped. */
+static unsigned long kfence_skip_covered_thresh __read_mostly = 75;
+module_param_named(skip_covered_thresh, kfence_skip_covered_thresh, ulong, 0644);
+
 /* The pool of pages used for guard pages and objects. */
 char *__kfence_pool __ro_after_init;
 EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */
@@ -105,6 +112,32 @@  DEFINE_STATIC_KEY_FALSE(kfence_allocatio
 /* Gates the allocation, ensuring only one succeeds in a given period. */
 atomic_t kfence_allocation_gate = ATOMIC_INIT(1);
 
+/*
+ * A Counting Bloom filter of allocation coverage: limits currently covered
+ * allocations of the same source filling up the pool.
+ *
+ * Assuming a range of 15%-85% unique allocations in the pool at any point in
+ * time, the below parameters provide a probablity of 0.02-0.33 for false
+ * positive hits respectively:
+ *
+ *	P(alloc_traces) = (1 - e^(-HNUM * (alloc_traces / SIZE)) ^ HNUM
+ */
+#define ALLOC_COVERED_HNUM	2
+#define ALLOC_COVERED_ORDER	(const_ilog2(CONFIG_KFENCE_NUM_OBJECTS) + 2)
+#define ALLOC_COVERED_SIZE	(1 << ALLOC_COVERED_ORDER)
+#define ALLOC_COVERED_HNEXT(h)	hash_32(h, ALLOC_COVERED_ORDER)
+#define ALLOC_COVERED_MASK	(ALLOC_COVERED_SIZE - 1)
+static atomic_t alloc_covered[ALLOC_COVERED_SIZE];
+
+/* Stack depth used to determine uniqueness of an allocation. */
+#define UNIQUE_ALLOC_STACK_DEPTH ((size_t)8)
+
+/*
+ * Randomness for stack hashes, making the same collisions across reboots and
+ * different machines less likely.
+ */
+static u32 stack_hash_seed __ro_after_init;
+
 /* Statistics counters for debugfs. */
 enum kfence_counter_id {
 	KFENCE_COUNTER_ALLOCATED,
@@ -114,6 +147,7 @@  enum kfence_counter_id {
 	KFENCE_COUNTER_BUGS,
 	KFENCE_COUNTER_SKIP_INCOMPAT,
 	KFENCE_COUNTER_SKIP_CAPACITY,
+	KFENCE_COUNTER_SKIP_COVERED,
 	KFENCE_COUNTER_COUNT,
 };
 static atomic_long_t counters[KFENCE_COUNTER_COUNT];
@@ -125,11 +159,57 @@  static const char *const counter_names[]
 	[KFENCE_COUNTER_BUGS]		= "total bugs",
 	[KFENCE_COUNTER_SKIP_INCOMPAT]	= "skipped allocations (incompatible)",
 	[KFENCE_COUNTER_SKIP_CAPACITY]	= "skipped allocations (capacity)",
+	[KFENCE_COUNTER_SKIP_COVERED]	= "skipped allocations (covered)",
 };
 static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT);
 
 /* === Internals ============================================================ */
 
+static inline bool should_skip_covered(void)
+{
+	unsigned long thresh = (CONFIG_KFENCE_NUM_OBJECTS * kfence_skip_covered_thresh) / 100;
+
+	return atomic_long_read(&counters[KFENCE_COUNTER_ALLOCATED]) > thresh;
+}
+
+static u32 get_alloc_stack_hash(unsigned long *stack_entries, size_t num_entries)
+{
+	num_entries = min(num_entries, UNIQUE_ALLOC_STACK_DEPTH);
+	num_entries = filter_irq_stacks(stack_entries, num_entries);
+	return jhash(stack_entries, num_entries * sizeof(stack_entries[0]), stack_hash_seed);
+}
+
+/*
+ * Adds (or subtracts) count @val for allocation stack trace hash
+ * @alloc_stack_hash from Counting Bloom filter.
+ */
+static void alloc_covered_add(u32 alloc_stack_hash, int val)
+{
+	int i;
+
+	for (i = 0; i < ALLOC_COVERED_HNUM; i++) {
+		atomic_add(val, &alloc_covered[alloc_stack_hash & ALLOC_COVERED_MASK]);
+		alloc_stack_hash = ALLOC_COVERED_HNEXT(alloc_stack_hash);
+	}
+}
+
+/*
+ * Returns true if the allocation stack trace hash @alloc_stack_hash is
+ * currently contained (non-zero count) in Counting Bloom filter.
+ */
+static bool alloc_covered_contains(u32 alloc_stack_hash)
+{
+	int i;
+
+	for (i = 0; i < ALLOC_COVERED_HNUM; i++) {
+		if (!atomic_read(&alloc_covered[alloc_stack_hash & ALLOC_COVERED_MASK]))
+			return false;
+		alloc_stack_hash = ALLOC_COVERED_HNEXT(alloc_stack_hash);
+	}
+
+	return true;
+}
+
 static bool kfence_protect(unsigned long addr)
 {
 	return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), true));
@@ -269,7 +349,8 @@  static __always_inline void for_each_can
 }
 
 static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp,
-				  unsigned long *stack_entries, size_t num_stack_entries)
+				  unsigned long *stack_entries, size_t num_stack_entries,
+				  u32 alloc_stack_hash)
 {
 	struct kfence_metadata *meta = NULL;
 	unsigned long flags;
@@ -332,6 +413,8 @@  static void *kfence_guarded_alloc(struct
 	/* Pairs with READ_ONCE() in kfence_shutdown_cache(). */
 	WRITE_ONCE(meta->cache, cache);
 	meta->size = size;
+	meta->alloc_stack_hash = alloc_stack_hash;
+
 	for_each_canary(meta, set_canary_byte);
 
 	/* Set required struct page fields. */
@@ -344,6 +427,8 @@  static void *kfence_guarded_alloc(struct
 
 	raw_spin_unlock_irqrestore(&meta->lock, flags);
 
+	alloc_covered_add(alloc_stack_hash, 1);
+
 	/* Memory initialization. */
 
 	/*
@@ -412,6 +497,8 @@  static void kfence_guarded_free(void *ad
 
 	raw_spin_unlock_irqrestore(&meta->lock, flags);
 
+	alloc_covered_add(meta->alloc_stack_hash, -1);
+
 	/* Protect to detect use-after-frees. */
 	kfence_protect((unsigned long)addr);
 
@@ -677,6 +764,7 @@  void __init kfence_init(void)
 	if (!kfence_sample_interval)
 		return;
 
+	stack_hash_seed = (u32)random_get_entropy();
 	if (!kfence_init_pool()) {
 		pr_err("%s failed\n", __func__);
 		return;
@@ -752,6 +840,7 @@  void *__kfence_alloc(struct kmem_cache *
 {
 	unsigned long stack_entries[KFENCE_STACK_DEPTH];
 	size_t num_stack_entries;
+	u32 alloc_stack_hash;
 
 	/*
 	 * Perform size check before switching kfence_allocation_gate, so that
@@ -799,7 +888,23 @@  void *__kfence_alloc(struct kmem_cache *
 
 	num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 0);
 
-	return kfence_guarded_alloc(s, size, flags, stack_entries, num_stack_entries);
+	/*
+	 * Do expensive check for coverage of allocation in slow-path after
+	 * allocation_gate has already become non-zero, even though it might
+	 * mean not making any allocation within a given sample interval.
+	 *
+	 * This ensures reasonable allocation coverage when the pool is almost
+	 * full, including avoiding long-lived allocations of the same source
+	 * filling up the pool (e.g. pagecache allocations).
+	 */
+	alloc_stack_hash = get_alloc_stack_hash(stack_entries, num_stack_entries);
+	if (should_skip_covered() && alloc_covered_contains(alloc_stack_hash)) {
+		atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_COVERED]);
+		return NULL;
+	}
+
+	return kfence_guarded_alloc(s, size, flags, stack_entries, num_stack_entries,
+				    alloc_stack_hash);
 }
 
 size_t kfence_ksize(const void *addr)
--- a/mm/kfence/kfence.h~kfence-limit-currently-covered-allocations-when-pool-nearly-full
+++ a/mm/kfence/kfence.h
@@ -87,6 +87,8 @@  struct kfence_metadata {
 	/* Allocation and free stack information. */
 	struct kfence_track alloc_track;
 	struct kfence_track free_track;
+	/* For updating alloc_covered on frees. */
+	u32 alloc_stack_hash;
 };
 
 extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS];