mm, kasan: stackdepot implementation. Enable stackdepot for SLAB

Implement the stack depot and provide CONFIG_STACKDEPOT.  Stack depot
will allow KASAN store allocation/deallocation stack traces for memory
chunks.  The stack traces are stored in a hash table and referenced by
handles which reside in the kasan_alloc_meta and kasan_free_meta
structures in the allocated memory chunks.

IRQ stack traces are cut below the IRQ entry point to avoid unnecessary
duplication.

Right now stackdepot support is only enabled in SLAB allocator.  Once
KASAN features in SLAB are on par with those in SLUB we can switch SLUB
to stackdepot as well, thus removing the dependency on SLUB stack
bookkeeping, which wastes a lot of memory.

This patch is based on the "mm: kasan: stack depots" patch originally
prepared by Dmitry Chernenkov.

Joonsoo has said that he plans to reuse the stackdepot code for the
mm/page_owner.c debugging facility.

[akpm@linux-foundation.org: s/depot_stack_handle/depot_stack_handle_t]
[aryabinin@virtuozzo.com: comment style fixes]
Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/kernel/Makefile

@@ -19,6 +19,7 @@ endif
 KASAN_SANITIZE_head$(BITS).o				:= n
 KASAN_SANITIZE_dumpstack.o				:= n
 KASAN_SANITIZE_dumpstack_$(BITS).o			:= n
+KASAN_SANITIZE_stacktrace.o := n
 
 OBJECT_FILES_NON_STANDARD_head_$(BITS).o		:= y
 OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o	:= y

include/linux/stackdepot.h

@@ -0,0 +1,32 @@
+/*
+ * A generic stack depot implementation
+ *
+ * Author: Alexander Potapenko <glider@google.com>
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * Based on code by Dmitry Chernenkov.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_STACKDEPOT_H
+#define _LINUX_STACKDEPOT_H
+
+typedef u32 depot_stack_handle_t;
+
+struct stack_trace;
+
+depot_stack_handle_t depot_save_stack(struct stack_trace *trace, gfp_t flags);
+
+void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace);
+
+#endif

lib/Kconfig

@@ -536,4 +536,8 @@ config ARCH_HAS_PMEM_API
 config ARCH_HAS_MMIO_FLUSH
 	bool
 
+config STACKDEPOT
+	bool
+	select STACKTRACE
+
 endmenu

lib/Kconfig.kasan

@@ -7,6 +7,7 @@ config KASAN
 	bool "KASan: runtime memory debugger"
 	depends on SLUB_DEBUG || (SLAB && !DEBUG_SLAB)
 	select CONSTRUCTORS
+	select STACKDEPOT if SLAB
 	help
 	  Enables kernel address sanitizer - runtime memory debugger,
 	  designed to find out-of-bounds accesses and use-after-free bugs.

lib/Makefile

@@ -181,6 +181,9 @@ obj-$(CONFIG_SG_SPLIT) += sg_split.o
 obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
 obj-$(CONFIG_IRQ_POLL) += irq_poll.o
 
+obj-$(CONFIG_STACKDEPOT) += stackdepot.o
+KASAN_SANITIZE_stackdepot.o := n
+
 libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \
 	       fdt_empty_tree.o
 $(foreach file, $(libfdt_files), \

lib/stackdepot.c

@@ -0,0 +1,284 @@
+/*
+ * Generic stack depot for storing stack traces.
+ *
+ * Some debugging tools need to save stack traces of certain events which can
+ * be later presented to the user. For example, KASAN needs to safe alloc and
+ * free stacks for each object, but storing two stack traces per object
+ * requires too much memory (e.g. SLUB_DEBUG needs 256 bytes per object for
+ * that).
+ *
+ * Instead, stack depot maintains a hashtable of unique stacktraces. Since alloc
+ * and free stacks repeat a lot, we save about 100x space.
+ * Stacks are never removed from depot, so we store them contiguously one after
+ * another in a contiguos memory allocation.
+ *
+ * Author: Alexander Potapenko <glider@google.com>
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * Based on code by Dmitry Chernenkov.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ */
+
+#include <linux/gfp.h>
+#include <linux/jhash.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/percpu.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/stacktrace.h>
+#include <linux/stackdepot.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#define DEPOT_STACK_BITS (sizeof(depot_stack_handle_t) * 8)
+
+#define STACK_ALLOC_ORDER 2 /* 'Slab' size order for stack depot, 4 pages */
+#define STACK_ALLOC_SIZE (1LL << (PAGE_SHIFT + STACK_ALLOC_ORDER))
+#define STACK_ALLOC_ALIGN 4
+#define STACK_ALLOC_OFFSET_BITS (STACK_ALLOC_ORDER + PAGE_SHIFT - \
+					STACK_ALLOC_ALIGN)
+#define STACK_ALLOC_INDEX_BITS (DEPOT_STACK_BITS - STACK_ALLOC_OFFSET_BITS)
+#define STACK_ALLOC_SLABS_CAP 1024
+#define STACK_ALLOC_MAX_SLABS \
+	(((1LL << (STACK_ALLOC_INDEX_BITS)) < STACK_ALLOC_SLABS_CAP) ? \
+	 (1LL << (STACK_ALLOC_INDEX_BITS)) : STACK_ALLOC_SLABS_CAP)
+
+/* The compact structure to store the reference to stacks. */
+union handle_parts {
+	depot_stack_handle_t handle;
+	struct {
+		u32 slabindex : STACK_ALLOC_INDEX_BITS;
+		u32 offset : STACK_ALLOC_OFFSET_BITS;
+	};
+};
+
+struct stack_record {
+	struct stack_record *next;	/* Link in the hashtable */
+	u32 hash;			/* Hash in the hastable */
+	u32 size;			/* Number of frames in the stack */
+	union handle_parts handle;
+	unsigned long entries[1];	/* Variable-sized array of entries. */
+};
+
+static void *stack_slabs[STACK_ALLOC_MAX_SLABS];
+
+static int depot_index;
+static int next_slab_inited;
+static size_t depot_offset;
+static DEFINE_SPINLOCK(depot_lock);
+
+static bool init_stack_slab(void **prealloc)
+{
+	if (!*prealloc)
+		return false;
+	/*
+	 * This smp_load_acquire() pairs with smp_store_release() to
+	 * |next_slab_inited| below and in depot_alloc_stack().
+	 */
+	if (smp_load_acquire(&next_slab_inited))
+		return true;
+	if (stack_slabs[depot_index] == NULL) {
+		stack_slabs[depot_index] = *prealloc;
+	} else {
+		stack_slabs[depot_index + 1] = *prealloc;
+		/*
+		 * This smp_store_release pairs with smp_load_acquire() from
+		 * |next_slab_inited| above and in depot_save_stack().
+		 */
+		smp_store_release(&next_slab_inited, 1);
+	}
+	*prealloc = NULL;
+	return true;
+}
+
+/* Allocation of a new stack in raw storage */
+static struct stack_record *depot_alloc_stack(unsigned long *entries, int size,
+		u32 hash, void **prealloc, gfp_t alloc_flags)
+{
+	int required_size = offsetof(struct stack_record, entries) +
+		sizeof(unsigned long) * size;
+	struct stack_record *stack;
+
+	required_size = ALIGN(required_size, 1 << STACK_ALLOC_ALIGN);
+
+	if (unlikely(depot_offset + required_size > STACK_ALLOC_SIZE)) {
+		if (unlikely(depot_index + 1 >= STACK_ALLOC_MAX_SLABS)) {
+			WARN_ONCE(1, "Stack depot reached limit capacity");
+			return NULL;
+		}
+		depot_index++;
+		depot_offset = 0;
+		/*
+		 * smp_store_release() here pairs with smp_load_acquire() from
+		 * |next_slab_inited| in depot_save_stack() and
+		 * init_stack_slab().
+		 */
+		if (depot_index + 1 < STACK_ALLOC_MAX_SLABS)
+			smp_store_release(&next_slab_inited, 0);
+	}
+	init_stack_slab(prealloc);
+	if (stack_slabs[depot_index] == NULL)
+		return NULL;
+
+	stack = stack_slabs[depot_index] + depot_offset;
+
+	stack->hash = hash;
+	stack->size = size;
+	stack->handle.slabindex = depot_index;
+	stack->handle.offset = depot_offset >> STACK_ALLOC_ALIGN;
+	memcpy(stack->entries, entries, size * sizeof(unsigned long));
+	depot_offset += required_size;
+
+	return stack;
+}
+
+#define STACK_HASH_ORDER 20
+#define STACK_HASH_SIZE (1L << STACK_HASH_ORDER)
+#define STACK_HASH_MASK (STACK_HASH_SIZE - 1)
+#define STACK_HASH_SEED 0x9747b28c
+
+static struct stack_record *stack_table[STACK_HASH_SIZE] = {
+	[0 ...	STACK_HASH_SIZE - 1] = NULL
+};
+
+/* Calculate hash for a stack */
+static inline u32 hash_stack(unsigned long *entries, unsigned int size)
+{
+	return jhash2((u32 *)entries,
+			       size * sizeof(unsigned long) / sizeof(u32),
+			       STACK_HASH_SEED);
+}
+
+/* Find a stack that is equal to the one stored in entries in the hash */
+static inline struct stack_record *find_stack(struct stack_record *bucket,
+					     unsigned long *entries, int size,
+					     u32 hash)
+{
+	struct stack_record *found;
+
+	for (found = bucket; found; found = found->next) {
+		if (found->hash == hash &&
+		    found->size == size &&
+		    !memcmp(entries, found->entries,
+			    size * sizeof(unsigned long))) {
+			return found;
+		}
+	}
+	return NULL;
+}
+
+void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace)
+{
+	union handle_parts parts = { .handle = handle };
+	void *slab = stack_slabs[parts.slabindex];
+	size_t offset = parts.offset << STACK_ALLOC_ALIGN;
+	struct stack_record *stack = slab + offset;
+
+	trace->nr_entries = trace->max_entries = stack->size;
+	trace->entries = stack->entries;
+	trace->skip = 0;
+}
+
+/**
+ * depot_save_stack - save stack in a stack depot.
+ * @trace - the stacktrace to save.
+ * @alloc_flags - flags for allocating additional memory if required.
+ *
+ * Returns the handle of the stack struct stored in depot.
+ */
+depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
+				    gfp_t alloc_flags)
+{
+	u32 hash;
+	depot_stack_handle_t retval = 0;
+	struct stack_record *found = NULL, **bucket;
+	unsigned long flags;
+	struct page *page = NULL;
+	void *prealloc = NULL;
+
+	if (unlikely(trace->nr_entries == 0))
+		goto fast_exit;
+
+	hash = hash_stack(trace->entries, trace->nr_entries);
+	/* Bad luck, we won't store this stack. */
+	if (hash == 0)
+		goto exit;
+
+	bucket = &stack_table[hash & STACK_HASH_MASK];
+
+	/*
+	 * Fast path: look the stack trace up without locking.
+	 * The smp_load_acquire() here pairs with smp_store_release() to
+	 * |bucket| below.
+	 */
+	found = find_stack(smp_load_acquire(bucket), trace->entries,
+			   trace->nr_entries, hash);
+	if (found)
+		goto exit;
+
+	/*
+	 * Check if the current or the next stack slab need to be initialized.
+	 * If so, allocate the memory - we won't be able to do that under the
+	 * lock.
+	 *
+	 * The smp_load_acquire() here pairs with smp_store_release() to
+	 * |next_slab_inited| in depot_alloc_stack() and init_stack_slab().
+	 */
+	if (unlikely(!smp_load_acquire(&next_slab_inited))) {
+		/*
+		 * Zero out zone modifiers, as we don't have specific zone
+		 * requirements. Keep the flags related to allocation in atomic
+		 * contexts and I/O.
+		 */
+		alloc_flags &= ~GFP_ZONEMASK;
+		alloc_flags &= (GFP_ATOMIC | GFP_KERNEL);
+		page = alloc_pages(alloc_flags, STACK_ALLOC_ORDER);
+		if (page)
+			prealloc = page_address(page);
+	}
+
+	spin_lock_irqsave(&depot_lock, flags);
+
+	found = find_stack(*bucket, trace->entries, trace->nr_entries, hash);
+	if (!found) {
+		struct stack_record *new =
+			depot_alloc_stack(trace->entries, trace->nr_entries,
+					  hash, &prealloc, alloc_flags);
+		if (new) {
+			new->next = *bucket;
+			/*
+			 * This smp_store_release() pairs with
+			 * smp_load_acquire() from |bucket| above.
+			 */
+			smp_store_release(bucket, new);
+			found = new;
+		}
+	} else if (prealloc) {
+		/*
+		 * We didn't need to store this stack trace, but let's keep
+		 * the preallocated memory for the future.
+		 */
+		WARN_ON(!init_stack_slab(&prealloc));
+	}
+
+	spin_unlock_irqrestore(&depot_lock, flags);
+exit:
+	if (prealloc) {
+		/* Nobody used this memory, ok to free it. */
+		free_pages((unsigned long)prealloc, STACK_ALLOC_ORDER);
+	}
+	if (found)
+		retval = found->handle.handle;
+fast_exit:
+	return retval;
+}

mm/kasan/kasan.c

@@ -17,7 +17,9 @@
 #define DISABLE_BRANCH_PROFILING
 
 #include <linux/export.h>
+#include <linux/interrupt.h>
 #include <linux/init.h>
+#include <linux/kasan.h>
 #include <linux/kernel.h>
 #include <linux/kmemleak.h>
 #include <linux/linkage.h>
@@ -32,7 +34,6 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
-#include <linux/kasan.h>
 
 #include "kasan.h"
 #include "../slab.h"
@@ -413,23 +414,65 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object)
 #endif
 }
 
-static inline void set_track(struct kasan_track *track)
+#ifdef CONFIG_SLAB
+static inline int in_irqentry_text(unsigned long ptr)
 {
-	track->cpu = raw_smp_processor_id();
-	track->pid = current->pid;
-	track->when = jiffies;
+	return (ptr >= (unsigned long)&__irqentry_text_start &&
+		ptr < (unsigned long)&__irqentry_text_end) ||
+		(ptr >= (unsigned long)&__softirqentry_text_start &&
+		 ptr < (unsigned long)&__softirqentry_text_end);
+}
+
+static inline void filter_irq_stacks(struct stack_trace *trace)
+{
+	int i;
+
+	if (!trace->nr_entries)
+		return;
+	for (i = 0; i < trace->nr_entries; i++)
+		if (in_irqentry_text(trace->entries[i])) {
+			/* Include the irqentry function into the stack. */
+			trace->nr_entries = i + 1;
+			break;
+		}
+}
+
+static inline depot_stack_handle_t save_stack(gfp_t flags)
+{
+	unsigned long entries[KASAN_STACK_DEPTH];
+	struct stack_trace trace = {
+		.nr_entries = 0,
+		.entries = entries,
+		.max_entries = KASAN_STACK_DEPTH,
+		.skip = 0
+	};
+
+	save_stack_trace(&trace);
+	filter_irq_stacks(&trace);
+	if (trace.nr_entries != 0 &&
+	    trace.entries[trace.nr_entries-1] == ULONG_MAX)
+		trace.nr_entries--;
+
+	return depot_save_stack(&trace, flags);
+}
+
+static inline void set_track(struct kasan_track *track, gfp_t flags)
+{
+	track->pid = current->pid;
+	track->stack = save_stack(flags);
 }
 
-#ifdef CONFIG_SLAB
 struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
 					const void *object)
 {
+	BUILD_BUG_ON(sizeof(struct kasan_alloc_meta) > 32);
 	return (void *)object + cache->kasan_info.alloc_meta_offset;
 }
 
 struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
 				      const void *object)
 {
+	BUILD_BUG_ON(sizeof(struct kasan_free_meta) > 32);
 	return (void *)object + cache->kasan_info.free_meta_offset;
 }
 #endif
@@ -486,7 +529,7 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
 
 		alloc_info->state = KASAN_STATE_ALLOC;
 		alloc_info->alloc_size = size;
-		set_track(&alloc_info->track);
+		set_track(&alloc_info->track, flags);
 	}
 #endif
 }

mm/kasan/kasan.h

@@ -2,6 +2,7 @@
 #define __MM_KASAN_KASAN_H
 
 #include <linux/kasan.h>
+#include <linux/stackdepot.h>
 
 #define KASAN_SHADOW_SCALE_SIZE (1UL << KASAN_SHADOW_SCALE_SHIFT)
 #define KASAN_SHADOW_MASK       (KASAN_SHADOW_SCALE_SIZE - 1)
@@ -64,16 +65,18 @@ enum kasan_state {
 	KASAN_STATE_FREE
 };
 
+#define KASAN_STACK_DEPTH 64
+
 struct kasan_track {
-	u64 cpu : 6;			/* for NR_CPUS = 64 */
-	u64 pid : 16;			/* 65536 processes */
-	u64 when : 42;			/* ~140 years */
+	u32 pid;
+	depot_stack_handle_t stack;
 };
 
 struct kasan_alloc_meta {
+	struct kasan_track track;
 	u32 state : 2;	/* enum kasan_state */
 	u32 alloc_size : 30;
-	struct kasan_track track;
+	u32 reserved;
 };
 
 struct kasan_free_meta {

mm/kasan/report.c

@@ -18,6 +18,7 @@
 #include <linux/printk.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/stackdepot.h>
 #include <linux/stacktrace.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -118,8 +119,15 @@ static inline bool init_task_stack_addr(const void *addr)
 #ifdef CONFIG_SLAB
 static void print_track(struct kasan_track *track)
 {
-	pr_err("PID = %u, CPU = %u, timestamp = %lu\n", track->pid,
-	       track->cpu, (unsigned long)track->when);
+	pr_err("PID = %u\n", track->pid);
+	if (track->stack) {
+		struct stack_trace trace;
+
+		depot_fetch_stack(track->stack, &trace);
+		print_stack_trace(&trace, 0);
+	} else {
+		pr_err("(stack is not available)\n");
+	}
 }
 
 static void object_err(struct kmem_cache *cache, struct page *page,