summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--arch/x86/kernel/Makefile1
-rw-r--r--include/linux/stackdepot.h32
-rw-r--r--lib/Kconfig4
-rw-r--r--lib/Kconfig.kasan1
-rw-r--r--lib/Makefile3
-rw-r--r--lib/stackdepot.c284
-rw-r--r--mm/kasan/kasan.c55
-rw-r--r--mm/kasan/kasan.h11
-rw-r--r--mm/kasan/report.c12
9 files changed, 391 insertions, 12 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index adaae2c781c1..616ebd22ef9a 100644
--- a/arch/x86/kernel/Makefile
+++ b/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
diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
new file mode 100644
index 000000000000..7978b3e2c1e1
--- /dev/null
+++ b/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
diff --git a/lib/Kconfig b/lib/Kconfig
index 133ebc0c1773..3cca1222578e 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -536,4 +536,8 @@ config ARCH_HAS_PMEM_API
config ARCH_HAS_MMIO_FLUSH
bool
+config STACKDEPOT
+ bool
+ select STACKTRACE
+
endmenu
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 0e4d2b3b0aee..67d8c6838ba9 100644
--- a/lib/Kconfig.kasan
+++ b/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.
diff --git a/lib/Makefile b/lib/Makefile
index a1de5b61ff40..7bd6fd436c97 100644
--- a/lib/Makefile
+++ b/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), \
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
new file mode 100644
index 000000000000..654c9d87e83a
--- /dev/null
+++ b/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;
+}
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index cb998e0ec9d3..acb3b6c4dd89 100644
--- a/mm/kasan/kasan.c
+++ b/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)
+{
+ 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->cpu = raw_smp_processor_id();
track->pid = current->pid;
- track->when = jiffies;
+ 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
}
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 7b9e4ab9b66b..30a2f0ba0e09 100644
--- a/mm/kasan/kasan.h
+++ b/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 {
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 3e3385cc97ac..60869a5a0124 100644
--- a/mm/kasan/report.c
+++ b/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,