summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--include/linux/kfence.h216
-rw-r--r--init/main.c3
-rw-r--r--lib/Kconfig.debug1
-rw-r--r--lib/Kconfig.kfence67
-rw-r--r--mm/Makefile1
-rw-r--r--mm/kfence/Makefile3
-rw-r--r--mm/kfence/core.c840
-rw-r--r--mm/kfence/kfence.h113
-rw-r--r--mm/kfence/report.c240
9 files changed, 1484 insertions, 0 deletions
diff --git a/include/linux/kfence.h b/include/linux/kfence.h
new file mode 100644
index 000000000000..81f3911cb298
--- /dev/null
+++ b/include/linux/kfence.h
@@ -0,0 +1,216 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Kernel Electric-Fence (KFENCE). Public interface for allocator and fault
+ * handler integration. For more info see Documentation/dev-tools/kfence.rst.
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef _LINUX_KFENCE_H
+#define _LINUX_KFENCE_H
+
+#include <linux/mm.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_KFENCE
+
+/*
+ * We allocate an even number of pages, as it simplifies calculations to map
+ * address to metadata indices; effectively, the very first page serves as an
+ * extended guard page, but otherwise has no special purpose.
+ */
+#define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE)
+extern char *__kfence_pool;
+
+#ifdef CONFIG_KFENCE_STATIC_KEYS
+#include <linux/static_key.h>
+DECLARE_STATIC_KEY_FALSE(kfence_allocation_key);
+#else
+#include <linux/atomic.h>
+extern atomic_t kfence_allocation_gate;
+#endif
+
+/**
+ * is_kfence_address() - check if an address belongs to KFENCE pool
+ * @addr: address to check
+ *
+ * Return: true or false depending on whether the address is within the KFENCE
+ * object range.
+ *
+ * KFENCE objects live in a separate page range and are not to be intermixed
+ * with regular heap objects (e.g. KFENCE objects must never be added to the
+ * allocator freelists). Failing to do so may and will result in heap
+ * corruptions, therefore is_kfence_address() must be used to check whether
+ * an object requires specific handling.
+ *
+ * Note: This function may be used in fast-paths, and is performance critical.
+ * Future changes should take this into account; for instance, we want to avoid
+ * introducing another load and therefore need to keep KFENCE_POOL_SIZE a
+ * constant (until immediate patching support is added to the kernel).
+ */
+static __always_inline bool is_kfence_address(const void *addr)
+{
+ /*
+ * The non-NULL check is required in case the __kfence_pool pointer was
+ * never initialized; keep it in the slow-path after the range-check.
+ */
+ return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && addr);
+}
+
+/**
+ * kfence_alloc_pool() - allocate the KFENCE pool via memblock
+ */
+void __init kfence_alloc_pool(void);
+
+/**
+ * kfence_init() - perform KFENCE initialization at boot time
+ *
+ * Requires that kfence_alloc_pool() was called before. This sets up the
+ * allocation gate timer, and requires that workqueues are available.
+ */
+void __init kfence_init(void);
+
+/**
+ * kfence_shutdown_cache() - handle shutdown_cache() for KFENCE objects
+ * @s: cache being shut down
+ *
+ * Before shutting down a cache, one must ensure there are no remaining objects
+ * allocated from it. Because KFENCE objects are not referenced from the cache
+ * directly, we need to check them here.
+ *
+ * Note that shutdown_cache() is internal to SL*B, and kmem_cache_destroy() does
+ * not return if allocated objects still exist: it prints an error message and
+ * simply aborts destruction of a cache, leaking memory.
+ *
+ * If the only such objects are KFENCE objects, we will not leak the entire
+ * cache, but instead try to provide more useful debug info by making allocated
+ * objects "zombie allocations". Objects may then still be used or freed (which
+ * is handled gracefully), but usage will result in showing KFENCE error reports
+ * which include stack traces to the user of the object, the original allocation
+ * site, and caller to shutdown_cache().
+ */
+void kfence_shutdown_cache(struct kmem_cache *s);
+
+/*
+ * Allocate a KFENCE object. Allocators must not call this function directly,
+ * use kfence_alloc() instead.
+ */
+void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags);
+
+/**
+ * kfence_alloc() - allocate a KFENCE object with a low probability
+ * @s: struct kmem_cache with object requirements
+ * @size: exact size of the object to allocate (can be less than @s->size
+ * e.g. for kmalloc caches)
+ * @flags: GFP flags
+ *
+ * Return:
+ * * NULL - must proceed with allocating as usual,
+ * * non-NULL - pointer to a KFENCE object.
+ *
+ * kfence_alloc() should be inserted into the heap allocation fast path,
+ * allowing it to transparently return KFENCE-allocated objects with a low
+ * probability using a static branch (the probability is controlled by the
+ * kfence.sample_interval boot parameter).
+ */
+static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
+{
+#ifdef CONFIG_KFENCE_STATIC_KEYS
+ if (static_branch_unlikely(&kfence_allocation_key))
+#else
+ if (unlikely(!atomic_read(&kfence_allocation_gate)))
+#endif
+ return __kfence_alloc(s, size, flags);
+ return NULL;
+}
+
+/**
+ * kfence_ksize() - get actual amount of memory allocated for a KFENCE object
+ * @addr: pointer to a heap object
+ *
+ * Return:
+ * * 0 - not a KFENCE object, must call __ksize() instead,
+ * * non-0 - this many bytes can be accessed without causing a memory error.
+ *
+ * kfence_ksize() returns the number of bytes requested for a KFENCE object at
+ * allocation time. This number may be less than the object size of the
+ * corresponding struct kmem_cache.
+ */
+size_t kfence_ksize(const void *addr);
+
+/**
+ * kfence_object_start() - find the beginning of a KFENCE object
+ * @addr: address within a KFENCE-allocated object
+ *
+ * Return: address of the beginning of the object.
+ *
+ * SL[AU]B-allocated objects are laid out within a page one by one, so it is
+ * easy to calculate the beginning of an object given a pointer inside it and
+ * the object size. The same is not true for KFENCE, which places a single
+ * object at either end of the page. This helper function is used to find the
+ * beginning of a KFENCE-allocated object.
+ */
+void *kfence_object_start(const void *addr);
+
+/**
+ * __kfence_free() - release a KFENCE heap object to KFENCE pool
+ * @addr: object to be freed
+ *
+ * Requires: is_kfence_address(addr)
+ *
+ * Release a KFENCE object and mark it as freed.
+ */
+void __kfence_free(void *addr);
+
+/**
+ * kfence_free() - try to release an arbitrary heap object to KFENCE pool
+ * @addr: object to be freed
+ *
+ * Return:
+ * * false - object doesn't belong to KFENCE pool and was ignored,
+ * * true - object was released to KFENCE pool.
+ *
+ * Release a KFENCE object and mark it as freed. May be called on any object,
+ * even non-KFENCE objects, to simplify integration of the hooks into the
+ * allocator's free codepath. The allocator must check the return value to
+ * determine if it was a KFENCE object or not.
+ */
+static __always_inline __must_check bool kfence_free(void *addr)
+{
+ if (!is_kfence_address(addr))
+ return false;
+ __kfence_free(addr);
+ return true;
+}
+
+/**
+ * kfence_handle_page_fault() - perform page fault handling for KFENCE pages
+ * @addr: faulting address
+ *
+ * Return:
+ * * false - address outside KFENCE pool,
+ * * true - page fault handled by KFENCE, no additional handling required.
+ *
+ * A page fault inside KFENCE pool indicates a memory error, such as an
+ * out-of-bounds access, a use-after-free or an invalid memory access. In these
+ * cases KFENCE prints an error message and marks the offending page as
+ * present, so that the kernel can proceed.
+ */
+bool __must_check kfence_handle_page_fault(unsigned long addr);
+
+#else /* CONFIG_KFENCE */
+
+static inline bool is_kfence_address(const void *addr) { return false; }
+static inline void kfence_alloc_pool(void) { }
+static inline void kfence_init(void) { }
+static inline void kfence_shutdown_cache(struct kmem_cache *s) { }
+static inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { return NULL; }
+static inline size_t kfence_ksize(const void *addr) { return 0; }
+static inline void *kfence_object_start(const void *addr) { return NULL; }
+static inline void __kfence_free(void *addr) { }
+static inline bool __must_check kfence_free(void *addr) { return false; }
+static inline bool __must_check kfence_handle_page_fault(unsigned long addr) { return false; }
+
+#endif
+
+#endif /* _LINUX_KFENCE_H */
diff --git a/init/main.c b/init/main.c
index e9933cbf60d4..261051070e3c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -40,6 +40,7 @@
#include <linux/security.h>
#include <linux/smp.h>
#include <linux/profile.h>
+#include <linux/kfence.h>
#include <linux/rcupdate.h>
#include <linux/moduleparam.h>
#include <linux/kallsyms.h>
@@ -824,6 +825,7 @@ static void __init mm_init(void)
*/
page_ext_init_flatmem();
init_mem_debugging_and_hardening();
+ kfence_alloc_pool();
report_meminit();
mem_init();
/* page_owner must be initialized after buddy is ready */
@@ -955,6 +957,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
hrtimers_init();
softirq_init();
timekeeping_init();
+ kfence_init();
/*
* For best initial stack canary entropy, prepare it after:
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index f9febffffc21..2779c29d9981 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -938,6 +938,7 @@ config DEBUG_STACKOVERFLOW
If in doubt, say "N".
source "lib/Kconfig.kasan"
+source "lib/Kconfig.kfence"
endmenu # "Memory Debugging"
diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence
new file mode 100644
index 000000000000..b88ac9d6b2e6
--- /dev/null
+++ b/lib/Kconfig.kfence
@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config HAVE_ARCH_KFENCE
+ bool
+
+menuconfig KFENCE
+ bool "KFENCE: low-overhead sampling-based memory safety error detector"
+ depends on HAVE_ARCH_KFENCE && !KASAN && (SLAB || SLUB)
+ select STACKTRACE
+ help
+ KFENCE is a low-overhead sampling-based detector of heap out-of-bounds
+ access, use-after-free, and invalid-free errors. KFENCE is designed
+ to have negligible cost to permit enabling it in production
+ environments.
+
+ Note that, KFENCE is not a substitute for explicit testing with tools
+ such as KASAN. KFENCE can detect a subset of bugs that KASAN can
+ detect, albeit at very different performance profiles. If you can
+ afford to use KASAN, continue using KASAN, for example in test
+ environments. If your kernel targets production use, and cannot
+ enable KASAN due to its cost, consider using KFENCE.
+
+if KFENCE
+
+config KFENCE_STATIC_KEYS
+ bool "Use static keys to set up allocations"
+ default y
+ depends on JUMP_LABEL # To ensure performance, require jump labels
+ help
+ Use static keys (static branches) to set up KFENCE allocations. Using
+ static keys is normally recommended, because it avoids a dynamic
+ branch in the allocator's fast path. However, with very low sample
+ intervals, or on systems that do not support jump labels, a dynamic
+ branch may still be an acceptable performance trade-off.
+
+config KFENCE_SAMPLE_INTERVAL
+ int "Default sample interval in milliseconds"
+ default 100
+ help
+ The KFENCE sample interval determines the frequency with which heap
+ allocations will be guarded by KFENCE. May be overridden via boot
+ parameter "kfence.sample_interval".
+
+ Set this to 0 to disable KFENCE by default, in which case only
+ setting "kfence.sample_interval" to a non-zero value enables KFENCE.
+
+config KFENCE_NUM_OBJECTS
+ int "Number of guarded objects available"
+ range 1 65535
+ default 255
+ help
+ The number of guarded objects available. For each KFENCE object, 2
+ pages are required; with one containing the object and two adjacent
+ ones used as guard pages.
+
+config KFENCE_STRESS_TEST_FAULTS
+ int "Stress testing of fault handling and error reporting" if EXPERT
+ default 0
+ help
+ The inverse probability with which to randomly protect KFENCE object
+ pages, resulting in spurious use-after-frees. The main purpose of
+ this option is to stress test KFENCE with concurrent error reports
+ and allocations/frees. A value of 0 disables stress testing logic.
+
+ Only for KFENCE testing; set to 0 if you are not a KFENCE developer.
+
+endif # KFENCE
diff --git a/mm/Makefile b/mm/Makefile
index 135bbb65511a..72227b24a616 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -81,6 +81,7 @@ obj-$(CONFIG_PAGE_POISONING) += page_poison.o
obj-$(CONFIG_SLAB) += slab.o
obj-$(CONFIG_SLUB) += slub.o
obj-$(CONFIG_KASAN) += kasan/
+obj-$(CONFIG_KFENCE) += kfence/
obj-$(CONFIG_FAILSLAB) += failslab.o
obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
obj-$(CONFIG_MEMTEST) += memtest.o
diff --git a/mm/kfence/Makefile b/mm/kfence/Makefile
new file mode 100644
index 000000000000..d991e9a349f0
--- /dev/null
+++ b/mm/kfence/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_KFENCE) := core.o report.o
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
new file mode 100644
index 000000000000..d6a32c13336b
--- /dev/null
+++ b/mm/kfence/core.c
@@ -0,0 +1,840 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KFENCE guarded object allocator and fault handling.
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#define pr_fmt(fmt) "kfence: " fmt
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/debugfs.h>
+#include <linux/kcsan-checks.h>
+#include <linux/kfence.h>
+#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/memblock.h>
+#include <linux/moduleparam.h>
+#include <linux/random.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+
+#include <asm/kfence.h>
+
+#include "kfence.h"
+
+/* Disables KFENCE on the first warning assuming an irrecoverable error. */
+#define KFENCE_WARN_ON(cond) \
+ ({ \
+ const bool __cond = WARN_ON(cond); \
+ if (unlikely(__cond)) \
+ WRITE_ONCE(kfence_enabled, false); \
+ __cond; \
+ })
+
+/* === Data ================================================================= */
+
+static bool kfence_enabled __read_mostly;
+
+static unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL;
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "kfence."
+
+static int param_set_sample_interval(const char *val, const struct kernel_param *kp)
+{
+ unsigned long num;
+ int ret = kstrtoul(val, 0, &num);
+
+ if (ret < 0)
+ return ret;
+
+ if (!num) /* Using 0 to indicate KFENCE is disabled. */
+ WRITE_ONCE(kfence_enabled, false);
+ else if (!READ_ONCE(kfence_enabled) && system_state != SYSTEM_BOOTING)
+ return -EINVAL; /* Cannot (re-)enable KFENCE on-the-fly. */
+
+ *((unsigned long *)kp->arg) = num;
+ return 0;
+}
+
+static int param_get_sample_interval(char *buffer, const struct kernel_param *kp)
+{
+ if (!READ_ONCE(kfence_enabled))
+ return sprintf(buffer, "0\n");
+
+ return param_get_ulong(buffer, kp);
+}
+
+static const struct kernel_param_ops sample_interval_param_ops = {
+ .set = param_set_sample_interval,
+ .get = param_get_sample_interval,
+};
+module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_interval, 0600);
+
+/* The pool of pages used for guard pages and objects. */
+char *__kfence_pool __ro_after_init;
+EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */
+
+/*
+ * Per-object metadata, with one-to-one mapping of object metadata to
+ * backing pages (in __kfence_pool).
+ */
+static_assert(CONFIG_KFENCE_NUM_OBJECTS > 0);
+struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS];
+
+/* 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. */
+
+#ifdef CONFIG_KFENCE_STATIC_KEYS
+/* The static key to set up a KFENCE allocation. */
+DEFINE_STATIC_KEY_FALSE(kfence_allocation_key);
+#endif
+
+/* Gates the allocation, ensuring only one succeeds in a given period. */
+atomic_t kfence_allocation_gate = ATOMIC_INIT(1);
+
+/* Statistics counters for debugfs. */
+enum kfence_counter_id {
+ KFENCE_COUNTER_ALLOCATED,
+ KFENCE_COUNTER_ALLOCS,
+ KFENCE_COUNTER_FREES,
+ KFENCE_COUNTER_ZOMBIES,
+ KFENCE_COUNTER_BUGS,
+ KFENCE_COUNTER_COUNT,
+};
+static atomic_long_t counters[KFENCE_COUNTER_COUNT];
+static const char *const counter_names[] = {
+ [KFENCE_COUNTER_ALLOCATED] = "currently allocated",
+ [KFENCE_COUNTER_ALLOCS] = "total allocations",
+ [KFENCE_COUNTER_FREES] = "total frees",
+ [KFENCE_COUNTER_ZOMBIES] = "zombie allocations",
+ [KFENCE_COUNTER_BUGS] = "total bugs",
+};
+static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT);
+
+/* === Internals ============================================================ */
+
+static bool kfence_protect(unsigned long addr)
+{
+ return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), true));
+}
+
+static bool kfence_unprotect(unsigned long addr)
+{
+ return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false));
+}
+
+static inline struct kfence_metadata *addr_to_metadata(unsigned long addr)
+{
+ long index;
+
+ /* The checks do not affect performance; only called from slow-paths. */
+
+ if (!is_kfence_address((void *)addr))
+ return NULL;
+
+ /*
+ * May be an invalid index if called with an address at the edge of
+ * __kfence_pool, in which case we would report an "invalid access"
+ * error.
+ */
+ index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1;
+ if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS)
+ return NULL;
+
+ return &kfence_metadata[index];
+}
+
+static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta)
+{
+ unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2;
+ unsigned long pageaddr = (unsigned long)&__kfence_pool[offset];
+
+ /* The checks do not affect performance; only called from slow-paths. */
+
+ /* Only call with a pointer into kfence_metadata. */
+ if (KFENCE_WARN_ON(meta < kfence_metadata ||
+ meta >= kfence_metadata + CONFIG_KFENCE_NUM_OBJECTS))
+ return 0;
+
+ /*
+ * This metadata object only ever maps to 1 page; verify that the stored
+ * address is in the expected range.
+ */
+ if (KFENCE_WARN_ON(ALIGN_DOWN(meta->addr, PAGE_SIZE) != pageaddr))
+ return 0;
+
+ return pageaddr;
+}
+
+/*
+ * Update the object's metadata state, including updating the alloc/free stacks
+ * depending on the state transition.
+ */
+static noinline void metadata_update_state(struct kfence_metadata *meta,
+ enum kfence_object_state next)
+{
+ struct kfence_track *track =
+ next == KFENCE_OBJECT_FREED ? &meta->free_track : &meta->alloc_track;
+
+ lockdep_assert_held(&meta->lock);
+
+ /*
+ * Skip over 1 (this) functions; noinline ensures we do not accidentally
+ * skip over the caller by never inlining.
+ */
+ track->num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1);
+ track->pid = task_pid_nr(current);
+
+ /*
+ * Pairs with READ_ONCE() in
+ * kfence_shutdown_cache(),
+ * kfence_handle_page_fault().
+ */
+ WRITE_ONCE(meta->state, next);
+}
+
+/* Write canary byte to @addr. */
+static inline bool set_canary_byte(u8 *addr)
+{
+ *addr = KFENCE_CANARY_PATTERN(addr);
+ return true;
+}
+
+/* Check canary byte at @addr. */
+static inline bool check_canary_byte(u8 *addr)
+{
+ if (likely(*addr == KFENCE_CANARY_PATTERN(addr)))
+ return true;
+
+ atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]);
+ kfence_report_error((unsigned long)addr, addr_to_metadata((unsigned long)addr),
+ KFENCE_ERROR_CORRUPTION);
+ return false;
+}
+
+/* __always_inline this to ensure we won't do an indirect call to fn. */
+static __always_inline void for_each_canary(const struct kfence_metadata *meta, bool (*fn)(u8 *))
+{
+ const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE);
+ unsigned long addr;
+
+ lockdep_assert_held(&meta->lock);
+
+ /*
+ * We'll iterate over each canary byte per-side until fn() returns
+ * false. However, we'll still iterate over the canary bytes to the
+ * right of the object even if there was an error in the canary bytes to
+ * the left of the object. Specifically, if check_canary_byte()
+ * generates an error, showing both sides might give more clues as to
+ * what the error is about when displaying which bytes were corrupted.
+ */
+
+ /* Apply to left of object. */
+ for (addr = pageaddr; addr < meta->addr; addr++) {
+ if (!fn((u8 *)addr))
+ break;
+ }
+
+ /* Apply to right of object. */
+ for (addr = meta->addr + meta->size; addr < pageaddr + PAGE_SIZE; addr++) {
+ if (!fn((u8 *)addr))
+ break;
+ }
+}
+
+static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp)
+{
+ struct kfence_metadata *meta = NULL;
+ unsigned long flags;
+ struct page *page;
+ void *addr;
+
+ /* Try to obtain a free object. */
+ raw_spin_lock_irqsave(&kfence_freelist_lock, flags);
+ if (!list_empty(&kfence_freelist)) {
+ meta = list_entry(kfence_freelist.next, struct kfence_metadata, list);
+ list_del_init(&meta->list);
+ }
+ raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags);
+ if (!meta)
+ return NULL;
+
+ if (unlikely(!raw_spin_trylock_irqsave(&meta->lock, flags))) {
+ /*
+ * This is extremely unlikely -- we are reporting on a
+ * use-after-free, which locked meta->lock, and the reporting
+ * code via printk calls kmalloc() which ends up in
+ * kfence_alloc() and tries to grab the same object that we're
+ * reporting on. While it has never been observed, lockdep does
+ * report that there is a possibility of deadlock. Fix it by
+ * using trylock and bailing out gracefully.
+ */
+ raw_spin_lock_irqsave(&kfence_freelist_lock, flags);
+ /* Put the object back on the freelist. */
+ list_add_tail(&meta->list, &kfence_freelist);
+ raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags);
+
+ return NULL;
+ }
+
+ meta->addr = metadata_to_pageaddr(meta);
+ /* Unprotect if we're reusing this page. */
+ if (meta->state == KFENCE_OBJECT_FREED)
+ kfence_unprotect(meta->addr);
+
+ /*
+ * Note: for allocations made before RNG initialization, will always
+ * return zero. We still benefit from enabling KFENCE as early as
+ * possible, even when the RNG is not yet available, as this will allow
+ * KFENCE to detect bugs due to earlier allocations. The only downside
+ * is that the out-of-bounds accesses detected are deterministic for
+ * such allocations.
+ */
+ if (prandom_u32_max(2)) {
+ /* Allocate on the "right" side, re-calculate address. */
+ meta->addr += PAGE_SIZE - size;
+ meta->addr = ALIGN_DOWN(meta->addr, cache->align);
+ }
+
+ addr = (void *)meta->addr;
+
+ /* Update remaining metadata. */
+ metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED);
+ /* Pairs with READ_ONCE() in kfence_shutdown_cache(). */
+ WRITE_ONCE(meta->cache, cache);
+ meta->size = size;
+ for_each_canary(meta, set_canary_byte);
+
+ /* Set required struct page fields. */
+ page = virt_to_page(meta->addr);
+ page->slab_cache = cache;
+
+ raw_spin_unlock_irqrestore(&meta->lock, flags);
+
+ /* Memory initialization. */
+
+ /*
+ * We check slab_want_init_on_alloc() ourselves, rather than letting
+ * SL*B do the initialization, as otherwise we might overwrite KFENCE's
+ * redzone.
+ */
+ if (unlikely(slab_want_init_on_alloc(gfp, cache)))
+ memzero_explicit(addr, size);
+ if (cache->ctor)
+ cache->ctor(addr);
+
+ if (CONFIG_KFENCE_STRESS_TEST_FAULTS && !prandom_u32_max(CONFIG_KFENCE_STRESS_TEST_FAULTS))
+ kfence_protect(meta->addr); /* Random "faults" by protecting the object. */
+
+ atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCATED]);
+ atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCS]);
+
+ return addr;
+}
+
+static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool zombie)
+{
+ struct kcsan_scoped_access assert_page_exclusive;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&meta->lock, flags);
+
+ if (meta->state != KFENCE_OBJECT_ALLOCATED || meta->addr != (unsigned long)addr) {
+ /* Invalid or double-free, bail out. */
+ atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]);
+ kfence_report_error((unsigned long)addr, meta, KFENCE_ERROR_INVALID_FREE);
+ raw_spin_unlock_irqrestore(&meta->lock, flags);
+ return;
+ }
+
+ /* Detect racy use-after-free, or incorrect reallocation of this page by KFENCE. */
+ kcsan_begin_scoped_access((void *)ALIGN_DOWN((unsigned long)addr, PAGE_SIZE), PAGE_SIZE,
+ KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT,
+ &assert_page_exclusive);
+
+ if (CONFIG_KFENCE_STRESS_TEST_FAULTS)
+ kfence_unprotect((unsigned long)addr); /* To check canary bytes. */
+
+ /* Restore page protection if there was an OOB access. */
+ if (meta->unprotected_page) {
+ kfence_protect(meta->unprotected_page);
+ meta->unprotected_page = 0;
+ }
+
+ /* Check canary bytes for memory corruption. */
+ for_each_canary(meta, check_canary_byte);
+
+ /*
+ * Clear memory if init-on-free is set. While we protect the page, the
+ * data is still there, and after a use-after-free is detected, we
+ * unprotect the page, so the data is still accessible.
+ */
+ if (!zombie && unlikely(slab_want_init_on_free(meta->cache)))
+ memzero_explicit(addr, meta->size);
+
+ /* Mark the object as freed. */
+ metadata_update_state(meta, KFENCE_OBJECT_FREED);
+
+ raw_spin_unlock_irqrestore(&meta->lock, flags);
+
+ /* Protect to detect use-after-frees. */
+ kfence_protect((unsigned long)addr);
+
+ kcsan_end_scoped_access(&assert_page_exclusive);
+ if (!zombie) {
+ /* Add it to the tail of the freelist for reuse. */
+ raw_spin_lock_irqsave(&kfence_freelist_lock, flags);
+ KFENCE_WARN_ON(!list_empty(&meta->list));
+ list_add_tail(&meta->list, &kfence_freelist);
+ raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags);
+
+ atomic_long_dec(&counters[KFENCE_COUNTER_ALLOCATED]);
+ atomic_long_inc(&counters[KFENCE_COUNTER_FREES]);
+ } else {
+ /* See kfence_shutdown_cache(). */
+ atomic_long_inc(&counters[KFENCE_COUNTER_ZOMBIES]);
+ }
+}
+
+static void rcu_guarded_free(struct rcu_head *h)
+{
+ struct kfence_metadata *meta = container_of(h, struct kfence_metadata, rcu_head);
+
+ kfence_guarded_free((void *)meta->addr, meta, false);
+}
+
+static bool __init kfence_init_pool(void)
+{
+ unsigned long addr = (unsigned long)__kfence_pool;
+ struct page *pages;
+ int i;
+
+ if (!__kfence_pool)
+ return false;
+
+ if (!arch_kfence_init_pool())
+ goto err;
+
+ pages = virt_to_page(addr);
+
+ /*
+ * Set up object pages: they must have PG_slab set, to avoid freeing
+ * these as real pages.
+ *
+ * We also want to avoid inserting kfence_free() in the kfree()
+ * fast-path in SLUB, and therefore need to ensure kfree() correctly
+ * enters __slab_free() slow-path.
+ */
+ for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) {
+ if (!i || (i % 2))
+ continue;
+
+ /* Verify we do not have a compound head page. */
+ if (WARN_ON(compound_head(&pages[i]) != &pages[i]))
+ goto err;
+
+ __SetPageSlab(&pages[i]);
+ }
+
+ /*
+ * Protect the first 2 pages. The first page is mostly unnecessary, and
+ * merely serves as an extended guard page. However, adding one
+ * additional page in the beginning gives us an even number of pages,
+ * which simplifies the mapping of address to metadata index.
+ */
+ for (i = 0; i < 2; i++) {
+ if (unlikely(!kfence_protect(addr)))
+ goto err;
+
+ addr += PAGE_SIZE;
+ }
+
+ for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) {
+ struct kfence_metadata *meta = &kfence_metadata[i];
+
+ /* Initialize metadata. */
+ INIT_LIST_HEAD(&meta->list);
+ raw_spin_lock_init(&meta->lock);
+ meta->state = KFENCE_OBJECT_UNUSED;
+ meta->addr = addr; /* Initialize for validation in metadata_to_pageaddr(). */
+ list_add_tail(&meta->list, &kfence_freelist);
+
+ /* Protect the right redzone. */
+ if (unlikely(!kfence_protect(addr + PAGE_SIZE)))
+ goto err;
+
+ addr += 2 * PAGE_SIZE;
+ }
+
+ return true;
+
+err:
+ /*
+ * Only release unprotected pages, and do not try to go back and change
+ * page attributes due to risk of failing to do so as well. If changing
+ * page attributes for some pages fails, it is very likely that it also
+ * fails for the first page, and therefore expect addr==__kfence_pool in
+ * most failure cases.
+ */
+ memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool));
+ __kfence_pool = NULL;
+ return false;
+}
+
+/* === DebugFS Interface ==================================================== */
+
+static int stats_show(struct seq_file *seq, void *v)
+{
+ int i;
+
+ seq_printf(seq, "enabled: %i\n", READ_ONCE(kfence_enabled));
+ for (i = 0; i < KFENCE_COUNTER_COUNT; i++)
+ seq_printf(seq, "%s: %ld\n", counter_names[i], atomic_long_read(&counters[i]));
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(stats);
+
+/*
+ * debugfs seq_file operations for /sys/kernel/debug/kfence/objects.
+ * start_object() and next_object() return the object index + 1, because NULL is used
+ * to stop iteration.
+ */
+static void *start_object(struct seq_file *seq, loff_t *pos)
+{
+ if (*pos < CONFIG_KFENCE_NUM_OBJECTS)
+ return (void *)((long)*pos + 1);
+ return NULL;
+}
+
+static void stop_object(struct seq_file *seq, void *v)
+{
+}
+
+static void *next_object(struct seq_file *seq, void *v, loff_t *pos)
+{
+ ++*pos;
+ if (*pos < CONFIG_KFENCE_NUM_OBJECTS)
+ return (void *)((long)*pos + 1);
+ return NULL;
+}
+
+static int show_object(struct seq_file *seq, void *v)
+{
+ struct kfence_metadata *meta = &kfence_metadata[(long)v - 1];
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&meta->lock, flags);
+ kfence_print_object(seq, meta);
+ raw_spin_unlock_irqrestore(&meta->lock, flags);
+ seq_puts(seq, "---------------------------------\n");
+
+ return 0;
+}
+
+static const struct seq_operations object_seqops = {
+ .start = start_object,
+ .next = next_object,
+ .stop = stop_object,
+ .show = show_object,
+};
+
+static int open_objects(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &object_seqops);
+}
+
+static const struct file_operations objects_fops = {
+ .open = open_objects,
+ .read = seq_read,
+ .llseek = seq_lseek,
+};
+
+static int __init kfence_debugfs_init(void)
+{
+ struct dentry *kfence_dir = debugfs_create_dir("kfence", NULL);
+
+ debugfs_create_file("stats", 0444, kfence_dir, NULL, &stats_fops);
+ debugfs_create_file("objects", 0400, kfence_dir, NULL, &objects_fops);
+ return 0;
+}
+
+late_initcall(kfence_debugfs_init);
+
+/* === Allocation Gate Timer ================================================ */
+
+/*
+ * Set up delayed work, which will enable and disable the static key. We need to
+ * use a work queue (rather than a simple timer), since enabling and disabling a
+ * static key cannot be done from an interrupt.
+ *
+ * Note: Toggling a static branch currently causes IPIs, and here we'll end up
+ * with a total of 2 IPIs to all CPUs. If this ends up a problem in future (with
+ * more aggressive sampling intervals), we could get away with a variant that
+ * avoids IPIs, at the cost of not immediately capturing allocations if the
+ * instructions remain cached.
+ */
+static struct delayed_work kfence_timer;
+static void toggle_allocation_gate(struct work_struct *work)
+{
+ if (!READ_ONCE(kfence_enabled))
+ return;
+
+ /* Enable static key, and await allocation to happen. */
+ atomic_set(&kfence_allocation_gate, 0);
+#ifdef CONFIG_KFENCE_STATIC_KEYS
+ static_branch_enable(&kfence_allocation_key);
+ /*
+ * Await an allocation. Timeout after 1 second, in case the kernel stops
+ * doing allocations, to avoid stalling this worker task for too long.
+ */
+ {
+ unsigned long end_wait = jiffies + HZ;
+
+ do {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ if (atomic_read(&kfence_allocation_gate) != 0)
+ break;
+ schedule_timeout(1);
+ } while (time_before(jiffies, end_wait));
+ __set_current_state(TASK_RUNNING);
+ }
+ /* Disable static key and reset timer. */
+ static_branch_disable(&kfence_allocation_key);
+#endif
+ schedule_delayed_work(&kfence_timer, msecs_to_jiffies(kfence_sample_interval));
+}
+static DECLARE_DELAYED_WORK(kfence_timer, toggle_allocation_gate);
+
+/* === Public interface ===================================================== */
+
+void __init kfence_alloc_pool(void)
+{
+ if (!kfence_sample_interval)
+ return;
+
+ __kfence_pool = memblock_alloc(KFENCE_POOL_SIZE, PAGE_SIZE);
+
+ if (!__kfence_pool)
+ pr_err("failed to allocate pool\n");
+}
+
+void __init kfence_init(void)
+{
+ /* Setting kfence_sample_interval to 0 on boot disables KFENCE. */
+ if (!kfence_sample_interval)
+ return;
+
+ if (!kfence_init_pool()) {
+ pr_err("%s failed\n", __func__);
+ return;
+ }
+
+ WRITE_ONCE(kfence_enabled, true);
+ schedule_delayed_work(&kfence_timer, 0);
+ pr_info("initialized - using %lu bytes for %d objects", KFENCE_POOL_SIZE,
+ CONFIG_KFENCE_NUM_OBJECTS);
+ if (IS_ENABLED(CONFIG_DEBUG_KERNEL))
+ pr_cont(" at 0x%px-0x%px\n", (void *)__kfence_pool,
+ (void *)(__kfence_pool + KFENCE_POOL_SIZE));
+ else
+ pr_cont("\n");
+}
+
+void kfence_shutdown_cache(struct kmem_cache *s)
+{
+ unsigned long flags;
+ struct kfence_metadata *meta;
+ int i;
+
+ for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) {
+ bool in_use;
+
+ meta = &kfence_metadata[i];
+
+ /*
+ * If we observe some inconsistent cache and state pair where we
+ * should have returned false here, cache destruction is racing
+ * with either kmem_cache_alloc() or kmem_cache_free(). Taking
+ * the lock will not help, as different critical section
+ * serialization will have the same outcome.
+ */
+ if (READ_ONCE(meta->cache) != s ||
+ READ_ONCE(meta->state) != KFENCE_OBJECT_ALLOCATED)
+ continue;
+
+ raw_spin_lock_irqsave(&meta->lock, flags);
+ in_use = meta->cache == s && meta->state == KFENCE_OBJECT_ALLOCATED;
+ raw_spin_unlock_irqrestore(&meta->lock, flags);
+
+ if (in_use) {
+ /*
+ * This cache still has allocations, and we should not
+ * release them back into the freelist so they can still
+ * safely be used and retain the kernel's default
+ * behaviour of keeping the allocations alive (leak the
+ * cache); however, they effectively become "zombie
+ * allocations" as the KFENCE objects are the only ones
+ * still in use and the owning cache is being destroyed.
+ *
+ * We mark them freed, so that any subsequent use shows
+ * more useful error messages that will include stack
+ * traces of the user of the object, the original
+ * allocation, and caller to shutdown_cache().
+ */
+ kfence_guarded_free((void *)meta->addr, meta, /*zombie=*/true);
+ }
+ }
+
+ for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) {
+ meta = &kfence_metadata[i];
+
+ /* See above. */
+ if (READ_ONCE(meta->cache) != s || READ_ONCE(meta->state) != KFENCE_OBJECT_FREED)
+ continue;
+
+ raw_spin_lock_irqsave(&meta->lock, flags);
+ if (meta->cache == s && meta->state == KFENCE_OBJECT_FREED)
+ meta->cache = NULL;
+ raw_spin_unlock_irqrestore(&meta->lock, flags);
+ }
+}
+
+void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
+{
+ /*
+ * allocation_gate only needs to become non-zero, so it doesn't make
+ * sense to continue writing to it and pay the associated contention
+ * cost, in case we have a large number of concurrent allocations.
+ */
+ if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1)
+ return NULL;
+
+ if (!READ_ONCE(kfence_enabled))
+ return NULL;
+
+ if (size > PAGE_SIZE)
+ return NULL;
+
+ return kfence_guarded_alloc(s, size, flags);
+}
+
+size_t kfence_ksize(const void *addr)
+{
+ const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr);
+
+ /*
+ * Read locklessly -- if there is a race with __kfence_alloc(), this is
+ * either a use-after-free or invalid access.
+ */
+ return meta ? meta->size : 0;
+}
+
+void *kfence_object_start(const void *addr)
+{
+ const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr);
+
+ /*
+ * Read locklessly -- if there is a race with __kfence_alloc(), this is
+ * either a use-after-free or invalid access.
+ */
+ return meta ? (void *)meta->addr : NULL;
+}
+
+void __kfence_free(void *addr)
+{
+ struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr);
+
+ /*
+ * If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing
+ * the object, as the object page may be recycled for other-typed
+ * objects once it has been freed. meta->cache may be NULL if the cache
+ * was destroyed.
+ */
+ if (unlikely(meta->cache && (meta->cache->flags & SLAB_TYPESAFE_BY_RCU)))
+ call_rcu(&meta->rcu_head, rcu_guarded_free);
+ else
+ kfence_guarded_free(addr, meta, false);
+}
+
+bool kfence_handle_page_fault(unsigned long addr)
+{
+ const int page_index = (addr - (unsigned long)__kfence_pool) / PAGE_SIZE;
+ struct kfence_metadata *to_report = NULL;
+ enum kfence_error_type error_type;
+ unsigned long flags;
+
+ if (!is_kfence_address((void *)addr))
+ return false;
+
+ if (!READ_ONCE(kfence_enabled)) /* If disabled at runtime ... */
+ return kfence_unprotect(addr); /* ... unprotect and proceed. */
+
+ atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]);
+
+ if (page_index % 2) {
+ /* This is a redzone, report a buffer overflow. */
+ struct kfence_metadata *meta;
+ int distance = 0;
+
+ meta = addr_to_metadata(addr - PAGE_SIZE);
+ if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) {
+ to_report = meta;
+ /* Data race ok; distance calculation approximate. */
+ distance = addr - data_race(meta->addr + meta->size);
+ }
+
+ meta = addr_to_metadata(addr + PAGE_SIZE);
+ if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) {
+ /* Data race ok; distance calculation approximate. */
+ if (!to_report || distance > data_race(meta->addr) - addr)
+ to_report = meta;
+ }
+
+ if (!to_report)
+ goto out;
+
+ raw_spin_lock_irqsave(&to_report->lock, flags);
+ to_report->unprotected_page = addr;
+ error_type = KFENCE_ERROR_OOB;
+
+ /*
+ * If the object was freed before we took the look we can still
+ * report this as an OOB -- the report will simply show the
+ * stacktrace of the free as well.
+ */
+ } else {
+ to_report = addr_to_metadata(addr);
+ 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
+ * freed object may be reallocated. We simply report this as a
+ * use-after-free, with the stack trace showing the place where
+ * the object was re-allocated.
+ */
+ }
+
+out:
+ if (to_report) {
+ kfence_report_error(addr, to_report, error_type);
+ raw_spin_unlock_irqrestore(&to_report->lock, flags);
+ } else {
+ /* This may be a UAF or OOB access, but we can't be sure. */
+ kfence_report_error(addr, NULL, KFENCE_ERROR_INVALID);
+ }
+
+ return kfence_unprotect(addr); /* Unprotect and let access proceed. */
+}
diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h
new file mode 100644
index 000000000000..1014060f9707
--- /dev/null
+++ b/mm/kfence/kfence.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Kernel Electric-Fence (KFENCE). For more info please see
+ * Documentation/dev-tools/kfence.rst.
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef MM_KFENCE_KFENCE_H
+#define MM_KFENCE_KFENCE_H
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include "../slab.h" /* for struct kmem_cache */
+
+/* For non-debug builds, avoid leaking kernel pointers into dmesg. */
+#ifdef CONFIG_DEBUG_KERNEL
+#define PTR_FMT "%px"
+#else
+#define PTR_FMT "%p"
+#endif
+
+/*
+ * Get the canary byte pattern for @addr. Use a pattern that varies based on the
+ * lower 3 bits of the address, to detect memory corruptions with higher
+ * probability, where similar constants are used.
+ */
+#define KFENCE_CANARY_PATTERN(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7))
+
+/* Maximum stack depth for reports. */
+#define KFENCE_STACK_DEPTH 64
+
+/* KFENCE object states. */
+enum kfence_object_state {
+ KFENCE_OBJECT_UNUSED, /* Object is unused. */
+ KFENCE_OBJECT_ALLOCATED, /* Object is currently allocated. */
+ KFENCE_OBJECT_FREED, /* Object was allocated, and then freed. */
+};
+
+/* Alloc/free tracking information. */
+struct kfence_track {
+ pid_t pid;
+ int num_stack_entries;
+ unsigned long stack_entries[KFENCE_STACK_DEPTH];
+};
+
+/* KFENCE metadata per guarded allocation. */
+struct kfence_metadata {
+ struct list_head list; /* Freelist node; access under kfence_freelist_lock. */
+ struct rcu_head rcu_head; /* For delayed freeing. */
+
+ /*
+ * Lock protecting below data; to ensure consistency of the below data,
+ * since the following may execute concurrently: __kfence_alloc(),
+ * __kfence_free(), kfence_handle_page_fault(). However, note that we
+ * cannot grab the same metadata off the freelist twice, and multiple
+ * __kfence_alloc() cannot run concurrently on the same metadata.
+ */
+ raw_spinlock_t lock;
+
+ /* The current state of the object; see above. */
+ enum kfence_object_state state;
+
+ /*
+ * Allocated object address; cannot be calculated from size, because of
+ * alignment requirements.
+ *
+ * Invariant: ALIGN_DOWN(addr, PAGE_SIZE) is constant.
+ */
+ unsigned long addr;
+
+ /*
+ * The size of the original allocation.
+ */
+ size_t size;
+
+ /*
+ * The kmem_cache cache of the last allocation; NULL if never allocated
+ * or the cache has already been destroyed.
+ */
+ struct kmem_cache *cache;
+
+ /*
+ * In case of an invalid access, the page that was unprotected; we
+ * optimistically only store one address.
+ */
+ unsigned long unprotected_page;
+
+ /* Allocation and free stack information. */
+ struct kfence_track alloc_track;
+ struct kfence_track free_track;
+};
+
+extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS];
+
+/* KFENCE error types for report generation. */
+enum kfence_error_type {
+ KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */
+ KFENCE_ERROR_UAF, /* Detected a use-after-free access. */
+ KFENCE_ERROR_CORRUPTION, /* Detected a memory corruption on free. */
+ KFENCE_ERROR_INVALID, /* Invalid access of unknown type. */
+ KFENCE_ERROR_INVALID_FREE, /* Invalid free. */
+};
+
+void kfence_report_error(unsigned long address, const struct kfence_metadata *meta,
+ enum kfence_error_type type);
+
+void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta);
+
+#endif /* MM_KFENCE_KFENCE_H */
diff --git a/mm/kfence/report.c b/mm/kfence/report.c
new file mode 100644
index 000000000000..64f27c8d46a3
--- /dev/null
+++ b/mm/kfence/report.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KFENCE reporting.
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#include <stdarg.h>
+
+#include <linux/kernel.h>
+#include <linux/lockdep.h>
+#include <linux/printk.h>
+#include <linux/seq_file.h>
+#include <linux/stacktrace.h>
+#include <linux/string.h>
+
+#include <asm/kfence.h>
+
+#include "kfence.h"
+
+/* Helper function to either print to a seq_file or to console. */
+__printf(2, 3)
+static void seq_con_printf(struct seq_file *seq, const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ if (seq)
+ seq_vprintf(seq, fmt, args);
+ else
+ vprintk(fmt, args);
+ va_end(args);
+}
+
+/*
+ * Get the number of stack entries to skip to get out of MM internals. @type is
+ * optional, and if set to NULL, assumes an allocation or free stack.
+ */
+static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries,
+ const enum kfence_error_type *type)
+{
+ char buf[64];
+ int skipnr, fallback = 0;
+ bool is_access_fault = false;
+
+ if (type) {
+ /* Depending on error type, find different stack entries. */
+ switch (*type) {
+ case KFENCE_ERROR_UAF:
+ case KFENCE_ERROR_OOB:
+ case KFENCE_ERROR_INVALID:
+ is_access_fault = true;
+ break;
+ case KFENCE_ERROR_CORRUPTION:
+ case KFENCE_ERROR_INVALID_FREE:
+ break;
+ }
+ }
+
+ for (skipnr = 0; skipnr < num_entries; skipnr++) {
+ int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]);
+
+ if (is_access_fault) {
+ if (!strncmp(buf, KFENCE_SKIP_ARCH_FAULT_HANDLER, len))
+ goto found;
+ } else {
+ if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") ||
+ !strncmp(buf, "__slab_free", len)) {
+ /*
+ * In case of tail calls from any of the below
+ * to any of the above.
+ */
+ fallback = skipnr + 1;
+ }
+
+ /* Also the *_bulk() variants by only checking prefixes. */
+ if (str_has_prefix(buf, "kfree") ||
+ str_has_prefix(buf, "kmem_cache_free") ||
+ str_has_prefix(buf, "__kmalloc") ||
+ str_has_prefix(buf, "kmem_cache_alloc"))
+ goto found;
+ }
+ }
+ if (fallback < num_entries)
+ return fallback;
+found:
+ skipnr++;
+ return skipnr < num_entries ? skipnr : 0;
+}
+
+static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadata *meta,
+ bool show_alloc)
+{
+ const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track;
+
+ if (track->num_stack_entries) {
+ /* Skip allocation/free internals stack. */
+ int i = get_stack_skipnr(track->stack_entries, track->num_stack_entries, NULL);
+
+ /* stack_trace_seq_print() does not exist; open code our own. */
+ for (; i < track->num_stack_entries; i++)
+ seq_con_printf(seq, " %pS\n", (void *)track->stack_entries[i]);
+ } else {
+ seq_con_printf(seq, " no %s stack\n", show_alloc ? "allocation" : "deallocation");
+ }
+}
+
+void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta)
+{
+ const int size = abs(meta->size);
+ const unsigned long start = meta->addr;
+ const struct kmem_cache *const cache = meta->cache;
+
+ lockdep_assert_held(&meta->lock);
+
+ if (meta->state == KFENCE_OBJECT_UNUSED) {
+ seq_con_printf(seq, "kfence-#%zd unused\n", meta - kfence_metadata);
+ return;
+ }
+
+ seq_con_printf(seq,
+ "kfence-#%zd [0x" PTR_FMT "-0x" PTR_FMT
+ ", size=%d, cache=%s] allocated by task %d:\n",
+ meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size,
+ (cache && cache->name) ? cache->name : "<destroyed>", meta->alloc_track.pid);
+ kfence_print_stack(seq, meta, true);
+
+ if (meta->state == KFENCE_OBJECT_FREED) {
+ seq_con_printf(seq, "\nfreed by task %d:\n", meta->free_track.pid);
+ kfence_print_stack(seq, meta, false);
+ }
+}
+
+/*
+ * Show bytes at @addr that are different from the expected canary values, up to
+ * @max_bytes.
+ */
+static void print_diff_canary(unsigned long address, size_t bytes_to_show,
+ const struct kfence_metadata *meta)
+{
+ const unsigned long show_until_addr = address + bytes_to_show;
+ const u8 *cur, *end;
+
+ /* Do not show contents of object nor read into following guard page. */
+ end = (const u8 *)(address < meta->addr ? min(show_until_addr, meta->addr)
+ : min(show_until_addr, PAGE_ALIGN(address)));
+
+ pr_cont("[");
+ for (cur = (const u8 *)address; cur < end; cur++) {
+ if (*cur == KFENCE_CANARY_PATTERN(cur))
+ pr_cont(" .");
+ else if (IS_ENABLED(CONFIG_DEBUG_KERNEL))
+ pr_cont(" 0x%02x", *cur);
+ else /* Do not leak kernel memory in non-debug builds. */
+ pr_cont(" !");
+ }
+ pr_cont(" ]");
+}
+
+void kfence_report_error(unsigned long address, const struct kfence_metadata *meta,
+ enum kfence_error_type type)
+{
+ unsigned long stack_entries[KFENCE_STACK_DEPTH] = { 0 };
+ int num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 1);
+ int skipnr = get_stack_skipnr(stack_entries, num_stack_entries, &type);
+ const ptrdiff_t object_index = meta ? meta - kfence_metadata : -1;
+
+ /* Require non-NULL meta, except if KFENCE_ERROR_INVALID. */
+ 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.
+ * Until such time that all printing code here is safe in all parts of
+ * the kernel, accept the risk, and just get our message out (given the
+ * system might already behave unpredictably due to the memory error).
+ * As such, also disable lockdep to hide warnings, and avoid disabling
+ * lockdep for the rest of the kernel.
+ */
+ lockdep_off();
+
+ pr_err("==================================================================\n");
+ /* Print report header. */
+ switch (type) {
+ case KFENCE_ERROR_OOB: {
+ const bool left_of_object = address < meta->addr;
+
+ pr_err("BUG: KFENCE: out-of-bounds in %pS\n\n", (void *)stack_entries[skipnr]);
+ pr_err("Out-of-bounds access at 0x" PTR_FMT " (%luB %s of kfence-#%zd):\n",
+ (void *)address,
+ left_of_object ? meta->addr - address : address - meta->addr,
+ left_of_object ? "left" : "right", object_index);
+ break;
+ }
+ case KFENCE_ERROR_UAF:
+ pr_err("BUG: KFENCE: use-after-free in %pS\n\n", (void *)stack_entries[skipnr]);
+ pr_err("Use-after-free access at 0x" PTR_FMT " (in kfence-#%zd):\n",
+ (void *)address, object_index);
+ break;
+ case KFENCE_ERROR_CORRUPTION:
+ pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]);
+ pr_err("Corrupted memory at 0x" PTR_FMT " ", (void *)address);
+ print_diff_canary(address, 16, meta);
+ pr_cont(" (in kfence-#%zd):\n", object_index);
+ break;
+ case KFENCE_ERROR_INVALID:
+ pr_err("BUG: KFENCE: invalid access in %pS\n\n", (void *)stack_entries[skipnr]);
+ pr_err("Invalid access at 0x" PTR_FMT ":\n", (void *)address);
+ break;
+ case KFENCE_ERROR_INVALID_FREE:
+ pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]);
+ pr_err("Invalid free of 0x" PTR_FMT " (in kfence-#%zd):\n", (void *)address,
+ object_index);
+ break;
+ }
+
+ /* Print stack trace and object info. */
+ stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr, 0);
+
+ if (meta) {
+ pr_err("\n");
+ kfence_print_object(NULL, meta);
+ }
+
+ /* Print report footer. */
+ pr_err("\n");
+ dump_stack_print_info(KERN_ERR);
+ pr_err("==================================================================\n");
+
+ lockdep_on();
+
+ if (panic_on_warn)
+ panic("panic_on_warn set ...\n");
+
+ /* We encountered a memory unsafety error, taint the kernel! */
+ add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK);
+}