diff options
Diffstat (limited to 'mm/kmsan')
| -rw-r--r-- | mm/kmsan/Makefile | 28 | ||||
| -rw-r--r-- | mm/kmsan/core.c | 450 | ||||
| -rw-r--r-- | mm/kmsan/hooks.c | 424 | ||||
| -rw-r--r-- | mm/kmsan/init.c | 235 | ||||
| -rw-r--r-- | mm/kmsan/instrumentation.c | 308 | ||||
| -rw-r--r-- | mm/kmsan/kmsan.h | 211 | ||||
| -rw-r--r-- | mm/kmsan/kmsan_test.c | 582 | ||||
| -rw-r--r-- | mm/kmsan/report.c | 219 | ||||
| -rw-r--r-- | mm/kmsan/shadow.c | 308 |
9 files changed, 2765 insertions, 0 deletions
diff --git a/mm/kmsan/Makefile b/mm/kmsan/Makefile new file mode 100644 index 000000000..98eab2856 --- /dev/null +++ b/mm/kmsan/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for KernelMemorySanitizer (KMSAN). +# +# +obj-y := core.o instrumentation.o init.o hooks.o report.o shadow.o + +KMSAN_SANITIZE := n +KCOV_INSTRUMENT := n +UBSAN_SANITIZE := n + +# Disable instrumentation of KMSAN runtime with other tools. +CC_FLAGS_KMSAN_RUNTIME := -fno-stack-protector +CC_FLAGS_KMSAN_RUNTIME += $(call cc-option,-fno-conserve-stack) +CC_FLAGS_KMSAN_RUNTIME += -DDISABLE_BRANCH_PROFILING + +CFLAGS_REMOVE.o = $(CC_FLAGS_FTRACE) + +CFLAGS_core.o := $(CC_FLAGS_KMSAN_RUNTIME) +CFLAGS_hooks.o := $(CC_FLAGS_KMSAN_RUNTIME) +CFLAGS_init.o := $(CC_FLAGS_KMSAN_RUNTIME) +CFLAGS_instrumentation.o := $(CC_FLAGS_KMSAN_RUNTIME) +CFLAGS_report.o := $(CC_FLAGS_KMSAN_RUNTIME) +CFLAGS_shadow.o := $(CC_FLAGS_KMSAN_RUNTIME) + +obj-$(CONFIG_KMSAN_KUNIT_TEST) += kmsan_test.o +KMSAN_SANITIZE_kmsan_test.o := y +CFLAGS_kmsan_test.o += $(call cc-disable-warning, uninitialized) diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c new file mode 100644 index 000000000..112dce135 --- /dev/null +++ b/mm/kmsan/core.c @@ -0,0 +1,450 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KMSAN runtime library. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#include <asm/page.h> +#include <linux/compiler.h> +#include <linux/export.h> +#include <linux/highmem.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kmsan_types.h> +#include <linux/memory.h> +#include <linux/mm.h> +#include <linux/mm_types.h> +#include <linux/mmzone.h> +#include <linux/percpu-defs.h> +#include <linux/preempt.h> +#include <linux/slab.h> +#include <linux/stackdepot.h> +#include <linux/stacktrace.h> +#include <linux/types.h> +#include <linux/vmalloc.h> + +#include "../slab.h" +#include "kmsan.h" + +bool kmsan_enabled __read_mostly; + +/* + * Per-CPU KMSAN context to be used in interrupts, where current->kmsan is + * unavaliable. + */ +DEFINE_PER_CPU(struct kmsan_ctx, kmsan_percpu_ctx); + +void kmsan_internal_task_create(struct task_struct *task) +{ + struct kmsan_ctx *ctx = &task->kmsan_ctx; + struct thread_info *info = current_thread_info(); + + __memset(ctx, 0, sizeof(*ctx)); + ctx->allow_reporting = true; + kmsan_internal_unpoison_memory(info, sizeof(*info), false); +} + +void kmsan_internal_poison_memory(void *address, size_t size, gfp_t flags, + unsigned int poison_flags) +{ + u32 extra_bits = + kmsan_extra_bits(/*depth*/ 0, poison_flags & KMSAN_POISON_FREE); + bool checked = poison_flags & KMSAN_POISON_CHECK; + depot_stack_handle_t handle; + + handle = kmsan_save_stack_with_flags(flags, extra_bits); + kmsan_internal_set_shadow_origin(address, size, -1, handle, checked); +} + +void kmsan_internal_unpoison_memory(void *address, size_t size, bool checked) +{ + kmsan_internal_set_shadow_origin(address, size, 0, 0, checked); +} + +depot_stack_handle_t kmsan_save_stack_with_flags(gfp_t flags, + unsigned int extra) +{ + unsigned long entries[KMSAN_STACK_DEPTH]; + unsigned int nr_entries; + + nr_entries = stack_trace_save(entries, KMSAN_STACK_DEPTH, 0); + + /* Don't sleep (see might_sleep_if() in __alloc_pages_nodemask()). */ + flags &= ~__GFP_DIRECT_RECLAIM; + + return __stack_depot_save(entries, nr_entries, extra, flags, true); +} + +/* Copy the metadata following the memmove() behavior. */ +void kmsan_internal_memmove_metadata(void *dst, void *src, size_t n) +{ + depot_stack_handle_t old_origin = 0, new_origin = 0; + int src_slots, dst_slots, i, iter, step, skip_bits; + depot_stack_handle_t *origin_src, *origin_dst; + void *shadow_src, *shadow_dst; + u32 *align_shadow_src, shadow; + bool backwards; + + shadow_dst = kmsan_get_metadata(dst, KMSAN_META_SHADOW); + if (!shadow_dst) + return; + KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(dst, n)); + + shadow_src = kmsan_get_metadata(src, KMSAN_META_SHADOW); + if (!shadow_src) { + /* + * @src is untracked: zero out destination shadow, ignore the + * origins, we're done. + */ + __memset(shadow_dst, 0, n); + return; + } + KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(src, n)); + + __memmove(shadow_dst, shadow_src, n); + + origin_dst = kmsan_get_metadata(dst, KMSAN_META_ORIGIN); + origin_src = kmsan_get_metadata(src, KMSAN_META_ORIGIN); + KMSAN_WARN_ON(!origin_dst || !origin_src); + src_slots = (ALIGN((u64)src + n, KMSAN_ORIGIN_SIZE) - + ALIGN_DOWN((u64)src, KMSAN_ORIGIN_SIZE)) / + KMSAN_ORIGIN_SIZE; + dst_slots = (ALIGN((u64)dst + n, KMSAN_ORIGIN_SIZE) - + ALIGN_DOWN((u64)dst, KMSAN_ORIGIN_SIZE)) / + KMSAN_ORIGIN_SIZE; + KMSAN_WARN_ON((src_slots < 1) || (dst_slots < 1)); + KMSAN_WARN_ON((src_slots - dst_slots > 1) || + (dst_slots - src_slots < -1)); + + backwards = dst > src; + i = backwards ? min(src_slots, dst_slots) - 1 : 0; + iter = backwards ? -1 : 1; + + align_shadow_src = + (u32 *)ALIGN_DOWN((u64)shadow_src, KMSAN_ORIGIN_SIZE); + for (step = 0; step < min(src_slots, dst_slots); step++, i += iter) { + KMSAN_WARN_ON(i < 0); + shadow = align_shadow_src[i]; + if (i == 0) { + /* + * If @src isn't aligned on KMSAN_ORIGIN_SIZE, don't + * look at the first @src % KMSAN_ORIGIN_SIZE bytes + * of the first shadow slot. + */ + skip_bits = ((u64)src % KMSAN_ORIGIN_SIZE) * 8; + shadow = (shadow >> skip_bits) << skip_bits; + } + if (i == src_slots - 1) { + /* + * If @src + n isn't aligned on + * KMSAN_ORIGIN_SIZE, don't look at the last + * (@src + n) % KMSAN_ORIGIN_SIZE bytes of the + * last shadow slot. + */ + skip_bits = (((u64)src + n) % KMSAN_ORIGIN_SIZE) * 8; + shadow = (shadow << skip_bits) >> skip_bits; + } + /* + * Overwrite the origin only if the corresponding + * shadow is nonempty. + */ + if (origin_src[i] && (origin_src[i] != old_origin) && shadow) { + old_origin = origin_src[i]; + new_origin = kmsan_internal_chain_origin(old_origin); + /* + * kmsan_internal_chain_origin() may return + * NULL, but we don't want to lose the previous + * origin value. + */ + if (!new_origin) + new_origin = old_origin; + } + if (shadow) + origin_dst[i] = new_origin; + else + origin_dst[i] = 0; + } + /* + * If dst_slots is greater than src_slots (i.e. + * dst_slots == src_slots + 1), there is an extra origin slot at the + * beginning or end of the destination buffer, for which we take the + * origin from the previous slot. + * This is only done if the part of the source shadow corresponding to + * slot is non-zero. + * + * E.g. if we copy 8 aligned bytes that are marked as uninitialized + * and have origins o111 and o222, to an unaligned buffer with offset 1, + * these two origins are copied to three origin slots, so one of then + * needs to be duplicated, depending on the copy direction (@backwards) + * + * src shadow: |uuuu|uuuu|....| + * src origin: |o111|o222|....| + * + * backwards = 0: + * dst shadow: |.uuu|uuuu|u...| + * dst origin: |....|o111|o222| - fill the empty slot with o111 + * backwards = 1: + * dst shadow: |.uuu|uuuu|u...| + * dst origin: |o111|o222|....| - fill the empty slot with o222 + */ + if (src_slots < dst_slots) { + if (backwards) { + shadow = align_shadow_src[src_slots - 1]; + skip_bits = (((u64)dst + n) % KMSAN_ORIGIN_SIZE) * 8; + shadow = (shadow << skip_bits) >> skip_bits; + if (shadow) + /* src_slots > 0, therefore dst_slots is at least 2 */ + origin_dst[dst_slots - 1] = + origin_dst[dst_slots - 2]; + } else { + shadow = align_shadow_src[0]; + skip_bits = ((u64)dst % KMSAN_ORIGIN_SIZE) * 8; + shadow = (shadow >> skip_bits) << skip_bits; + if (shadow) + origin_dst[0] = origin_dst[1]; + } + } +} + +depot_stack_handle_t kmsan_internal_chain_origin(depot_stack_handle_t id) +{ + unsigned long entries[3]; + u32 extra_bits; + int depth; + bool uaf; + + if (!id) + return id; + /* + * Make sure we have enough spare bits in @id to hold the UAF bit and + * the chain depth. + */ + BUILD_BUG_ON( + (1 << STACK_DEPOT_EXTRA_BITS) <= (KMSAN_MAX_ORIGIN_DEPTH << 1)); + + extra_bits = stack_depot_get_extra_bits(id); + depth = kmsan_depth_from_eb(extra_bits); + uaf = kmsan_uaf_from_eb(extra_bits); + + /* + * Stop chaining origins once the depth reached KMSAN_MAX_ORIGIN_DEPTH. + * This mostly happens in the case structures with uninitialized padding + * are copied around many times. Origin chains for such structures are + * usually periodic, and it does not make sense to fully store them. + */ + if (depth == KMSAN_MAX_ORIGIN_DEPTH) + return id; + + depth++; + extra_bits = kmsan_extra_bits(depth, uaf); + + entries[0] = KMSAN_CHAIN_MAGIC_ORIGIN; + entries[1] = kmsan_save_stack_with_flags(GFP_ATOMIC, 0); + entries[2] = id; + /* + * @entries is a local var in non-instrumented code, so KMSAN does not + * know it is initialized. Explicitly unpoison it to avoid false + * positives when __stack_depot_save() passes it to instrumented code. + */ + kmsan_internal_unpoison_memory(entries, sizeof(entries), false); + return __stack_depot_save(entries, ARRAY_SIZE(entries), extra_bits, + GFP_ATOMIC, true); +} + +void kmsan_internal_set_shadow_origin(void *addr, size_t size, int b, + u32 origin, bool checked) +{ + u64 address = (u64)addr; + void *shadow_start; + u32 *origin_start; + size_t pad = 0; + + KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(addr, size)); + shadow_start = kmsan_get_metadata(addr, KMSAN_META_SHADOW); + if (!shadow_start) { + /* + * kmsan_metadata_is_contiguous() is true, so either all shadow + * and origin pages are NULL, or all are non-NULL. + */ + if (checked) { + pr_err("%s: not memsetting %ld bytes starting at %px, because the shadow is NULL\n", + __func__, size, addr); + KMSAN_WARN_ON(true); + } + return; + } + __memset(shadow_start, b, size); + + if (!IS_ALIGNED(address, KMSAN_ORIGIN_SIZE)) { + pad = address % KMSAN_ORIGIN_SIZE; + address -= pad; + size += pad; + } + size = ALIGN(size, KMSAN_ORIGIN_SIZE); + origin_start = + (u32 *)kmsan_get_metadata((void *)address, KMSAN_META_ORIGIN); + + for (int i = 0; i < size / KMSAN_ORIGIN_SIZE; i++) + origin_start[i] = origin; +} + +struct page *kmsan_vmalloc_to_page_or_null(void *vaddr) +{ + struct page *page; + + if (!kmsan_internal_is_vmalloc_addr(vaddr) && + !kmsan_internal_is_module_addr(vaddr)) + return NULL; + page = vmalloc_to_page(vaddr); + if (pfn_valid(page_to_pfn(page))) + return page; + else + return NULL; +} + +void kmsan_internal_check_memory(void *addr, size_t size, const void *user_addr, + int reason) +{ + depot_stack_handle_t cur_origin = 0, new_origin = 0; + unsigned long addr64 = (unsigned long)addr; + depot_stack_handle_t *origin = NULL; + unsigned char *shadow = NULL; + int cur_off_start = -1; + int chunk_size; + size_t pos = 0; + + if (!size) + return; + KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(addr, size)); + while (pos < size) { + chunk_size = min(size - pos, + PAGE_SIZE - ((addr64 + pos) % PAGE_SIZE)); + shadow = kmsan_get_metadata((void *)(addr64 + pos), + KMSAN_META_SHADOW); + if (!shadow) { + /* + * This page is untracked. If there were uninitialized + * bytes before, report them. + */ + if (cur_origin) { + kmsan_enter_runtime(); + kmsan_report(cur_origin, addr, size, + cur_off_start, pos - 1, user_addr, + reason); + kmsan_leave_runtime(); + } + cur_origin = 0; + cur_off_start = -1; + pos += chunk_size; + continue; + } + for (int i = 0; i < chunk_size; i++) { + if (!shadow[i]) { + /* + * This byte is unpoisoned. If there were + * poisoned bytes before, report them. + */ + if (cur_origin) { + kmsan_enter_runtime(); + kmsan_report(cur_origin, addr, size, + cur_off_start, pos + i - 1, + user_addr, reason); + kmsan_leave_runtime(); + } + cur_origin = 0; + cur_off_start = -1; + continue; + } + origin = kmsan_get_metadata((void *)(addr64 + pos + i), + KMSAN_META_ORIGIN); + KMSAN_WARN_ON(!origin); + new_origin = *origin; + /* + * Encountered new origin - report the previous + * uninitialized range. + */ + if (cur_origin != new_origin) { + if (cur_origin) { + kmsan_enter_runtime(); + kmsan_report(cur_origin, addr, size, + cur_off_start, pos + i - 1, + user_addr, reason); + kmsan_leave_runtime(); + } + cur_origin = new_origin; + cur_off_start = pos + i; + } + } + pos += chunk_size; + } + KMSAN_WARN_ON(pos != size); + if (cur_origin) { + kmsan_enter_runtime(); + kmsan_report(cur_origin, addr, size, cur_off_start, pos - 1, + user_addr, reason); + kmsan_leave_runtime(); + } +} + +bool kmsan_metadata_is_contiguous(void *addr, size_t size) +{ + char *cur_shadow = NULL, *next_shadow = NULL, *cur_origin = NULL, + *next_origin = NULL; + u64 cur_addr = (u64)addr, next_addr = cur_addr + PAGE_SIZE; + depot_stack_handle_t *origin_p; + bool all_untracked = false; + + if (!size) + return true; + + /* The whole range belongs to the same page. */ + if (ALIGN_DOWN(cur_addr + size - 1, PAGE_SIZE) == + ALIGN_DOWN(cur_addr, PAGE_SIZE)) + return true; + + cur_shadow = kmsan_get_metadata((void *)cur_addr, /*is_origin*/ false); + if (!cur_shadow) + all_untracked = true; + cur_origin = kmsan_get_metadata((void *)cur_addr, /*is_origin*/ true); + if (all_untracked && cur_origin) + goto report; + + for (; next_addr < (u64)addr + size; + cur_addr = next_addr, cur_shadow = next_shadow, + cur_origin = next_origin, next_addr += PAGE_SIZE) { + next_shadow = kmsan_get_metadata((void *)next_addr, false); + next_origin = kmsan_get_metadata((void *)next_addr, true); + if (all_untracked) { + if (next_shadow || next_origin) + goto report; + if (!next_shadow && !next_origin) + continue; + } + if (((u64)cur_shadow == ((u64)next_shadow - PAGE_SIZE)) && + ((u64)cur_origin == ((u64)next_origin - PAGE_SIZE))) + continue; + goto report; + } + return true; + +report: + pr_err("%s: attempting to access two shadow page ranges.\n", __func__); + pr_err("Access of size %ld at %px.\n", size, addr); + pr_err("Addresses belonging to different ranges: %px and %px\n", + (void *)cur_addr, (void *)next_addr); + pr_err("page[0].shadow: %px, page[1].shadow: %px\n", cur_shadow, + next_shadow); + pr_err("page[0].origin: %px, page[1].origin: %px\n", cur_origin, + next_origin); + origin_p = kmsan_get_metadata(addr, KMSAN_META_ORIGIN); + if (origin_p) { + pr_err("Origin: %08x\n", *origin_p); + kmsan_print_origin(*origin_p); + } else { + pr_err("Origin: unavailable\n"); + } + return false; +} diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c new file mode 100644 index 000000000..ec0da72e6 --- /dev/null +++ b/mm/kmsan/hooks.c @@ -0,0 +1,424 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KMSAN hooks for kernel subsystems. + * + * These functions handle creation of KMSAN metadata for memory allocations. + * + * Copyright (C) 2018-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#include <linux/cacheflush.h> +#include <linux/dma-direction.h> +#include <linux/gfp.h> +#include <linux/kmsan.h> +#include <linux/mm.h> +#include <linux/mm_types.h> +#include <linux/scatterlist.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/usb.h> + +#include "../internal.h" +#include "../slab.h" +#include "kmsan.h" + +/* + * Instrumented functions shouldn't be called under + * kmsan_enter_runtime()/kmsan_leave_runtime(), because this will lead to + * skipping effects of functions like memset() inside instrumented code. + */ + +void kmsan_task_create(struct task_struct *task) +{ + kmsan_enter_runtime(); + kmsan_internal_task_create(task); + kmsan_leave_runtime(); +} + +void kmsan_task_exit(struct task_struct *task) +{ + struct kmsan_ctx *ctx = &task->kmsan_ctx; + + if (!kmsan_enabled || kmsan_in_runtime()) + return; + + ctx->allow_reporting = false; +} + +void kmsan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags) +{ + if (unlikely(object == NULL)) + return; + if (!kmsan_enabled || kmsan_in_runtime()) + return; + /* + * There's a ctor or this is an RCU cache - do nothing. The memory + * status hasn't changed since last use. + */ + if (s->ctor || (s->flags & SLAB_TYPESAFE_BY_RCU)) + return; + + kmsan_enter_runtime(); + if (flags & __GFP_ZERO) + kmsan_internal_unpoison_memory(object, s->object_size, + KMSAN_POISON_CHECK); + else + kmsan_internal_poison_memory(object, s->object_size, flags, + KMSAN_POISON_CHECK); + kmsan_leave_runtime(); +} + +void kmsan_slab_free(struct kmem_cache *s, void *object) +{ + if (!kmsan_enabled || kmsan_in_runtime()) + return; + + /* RCU slabs could be legally used after free within the RCU period */ + if (unlikely(s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))) + return; + /* + * If there's a constructor, freed memory must remain in the same state + * until the next allocation. We cannot save its state to detect + * use-after-free bugs, instead we just keep it unpoisoned. + */ + if (s->ctor) + return; + kmsan_enter_runtime(); + kmsan_internal_poison_memory(object, s->object_size, GFP_KERNEL, + KMSAN_POISON_CHECK | KMSAN_POISON_FREE); + kmsan_leave_runtime(); +} + +void kmsan_kmalloc_large(const void *ptr, size_t size, gfp_t flags) +{ + if (unlikely(ptr == NULL)) + return; + if (!kmsan_enabled || kmsan_in_runtime()) + return; + kmsan_enter_runtime(); + if (flags & __GFP_ZERO) + kmsan_internal_unpoison_memory((void *)ptr, size, + /*checked*/ true); + else + kmsan_internal_poison_memory((void *)ptr, size, flags, + KMSAN_POISON_CHECK); + kmsan_leave_runtime(); +} + +void kmsan_kfree_large(const void *ptr) +{ + struct page *page; + + if (!kmsan_enabled || kmsan_in_runtime()) + return; + kmsan_enter_runtime(); + page = virt_to_head_page((void *)ptr); + KMSAN_WARN_ON(ptr != page_address(page)); + kmsan_internal_poison_memory((void *)ptr, + PAGE_SIZE << compound_order(page), + GFP_KERNEL, + KMSAN_POISON_CHECK | KMSAN_POISON_FREE); + kmsan_leave_runtime(); +} + +static unsigned long vmalloc_shadow(unsigned long addr) +{ + return (unsigned long)kmsan_get_metadata((void *)addr, + KMSAN_META_SHADOW); +} + +static unsigned long vmalloc_origin(unsigned long addr) +{ + return (unsigned long)kmsan_get_metadata((void *)addr, + KMSAN_META_ORIGIN); +} + +void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end) +{ + __vunmap_range_noflush(vmalloc_shadow(start), vmalloc_shadow(end)); + __vunmap_range_noflush(vmalloc_origin(start), vmalloc_origin(end)); + flush_cache_vmap(vmalloc_shadow(start), vmalloc_shadow(end)); + flush_cache_vmap(vmalloc_origin(start), vmalloc_origin(end)); +} + +/* + * This function creates new shadow/origin pages for the physical pages mapped + * into the virtual memory. If those physical pages already had shadow/origin, + * those are ignored. + */ +int kmsan_ioremap_page_range(unsigned long start, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift) +{ + gfp_t gfp_mask = GFP_KERNEL | __GFP_ZERO; + struct page *shadow, *origin; + unsigned long off = 0; + int nr, err = 0, clean = 0, mapped; + + if (!kmsan_enabled || kmsan_in_runtime()) + return 0; + + nr = (end - start) / PAGE_SIZE; + kmsan_enter_runtime(); + for (int i = 0; i < nr; i++, off += PAGE_SIZE, clean = i) { + shadow = alloc_pages(gfp_mask, 1); + origin = alloc_pages(gfp_mask, 1); + if (!shadow || !origin) { + err = -ENOMEM; + goto ret; + } + mapped = __vmap_pages_range_noflush( + vmalloc_shadow(start + off), + vmalloc_shadow(start + off + PAGE_SIZE), prot, &shadow, + PAGE_SHIFT); + if (mapped) { + err = mapped; + goto ret; + } + shadow = NULL; + mapped = __vmap_pages_range_noflush( + vmalloc_origin(start + off), + vmalloc_origin(start + off + PAGE_SIZE), prot, &origin, + PAGE_SHIFT); + if (mapped) { + __vunmap_range_noflush( + vmalloc_shadow(start + off), + vmalloc_shadow(start + off + PAGE_SIZE)); + err = mapped; + goto ret; + } + origin = NULL; + } + /* Page mapping loop finished normally, nothing to clean up. */ + clean = 0; + +ret: + if (clean > 0) { + /* + * Something went wrong. Clean up shadow/origin pages allocated + * on the last loop iteration, then delete mappings created + * during the previous iterations. + */ + if (shadow) + __free_pages(shadow, 1); + if (origin) + __free_pages(origin, 1); + __vunmap_range_noflush( + vmalloc_shadow(start), + vmalloc_shadow(start + clean * PAGE_SIZE)); + __vunmap_range_noflush( + vmalloc_origin(start), + vmalloc_origin(start + clean * PAGE_SIZE)); + } + flush_cache_vmap(vmalloc_shadow(start), vmalloc_shadow(end)); + flush_cache_vmap(vmalloc_origin(start), vmalloc_origin(end)); + kmsan_leave_runtime(); + return err; +} + +void kmsan_iounmap_page_range(unsigned long start, unsigned long end) +{ + unsigned long v_shadow, v_origin; + struct page *shadow, *origin; + int nr; + + if (!kmsan_enabled || kmsan_in_runtime()) + return; + + nr = (end - start) / PAGE_SIZE; + kmsan_enter_runtime(); + v_shadow = (unsigned long)vmalloc_shadow(start); + v_origin = (unsigned long)vmalloc_origin(start); + for (int i = 0; i < nr; + i++, v_shadow += PAGE_SIZE, v_origin += PAGE_SIZE) { + shadow = kmsan_vmalloc_to_page_or_null((void *)v_shadow); + origin = kmsan_vmalloc_to_page_or_null((void *)v_origin); + __vunmap_range_noflush(v_shadow, vmalloc_shadow(end)); + __vunmap_range_noflush(v_origin, vmalloc_origin(end)); + if (shadow) + __free_pages(shadow, 1); + if (origin) + __free_pages(origin, 1); + } + flush_cache_vmap(vmalloc_shadow(start), vmalloc_shadow(end)); + flush_cache_vmap(vmalloc_origin(start), vmalloc_origin(end)); + kmsan_leave_runtime(); +} + +void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy, + size_t left) +{ + unsigned long ua_flags; + + if (!kmsan_enabled || kmsan_in_runtime()) + return; + /* + * At this point we've copied the memory already. It's hard to check it + * before copying, as the size of actually copied buffer is unknown. + */ + + /* copy_to_user() may copy zero bytes. No need to check. */ + if (!to_copy) + return; + /* Or maybe copy_to_user() failed to copy anything. */ + if (to_copy <= left) + return; + + ua_flags = user_access_save(); + if ((u64)to < TASK_SIZE) { + /* This is a user memory access, check it. */ + kmsan_internal_check_memory((void *)from, to_copy - left, to, + REASON_COPY_TO_USER); + } else { + /* Otherwise this is a kernel memory access. This happens when a + * compat syscall passes an argument allocated on the kernel + * stack to a real syscall. + * Don't check anything, just copy the shadow of the copied + * bytes. + */ + kmsan_internal_memmove_metadata((void *)to, (void *)from, + to_copy - left); + } + user_access_restore(ua_flags); +} +EXPORT_SYMBOL(kmsan_copy_to_user); + +/* Helper function to check an URB. */ +void kmsan_handle_urb(const struct urb *urb, bool is_out) +{ + if (!urb) + return; + if (is_out) + kmsan_internal_check_memory(urb->transfer_buffer, + urb->transfer_buffer_length, + /*user_addr*/ 0, REASON_SUBMIT_URB); + else + kmsan_internal_unpoison_memory(urb->transfer_buffer, + urb->transfer_buffer_length, + /*checked*/ false); +} +EXPORT_SYMBOL_GPL(kmsan_handle_urb); + +static void kmsan_handle_dma_page(const void *addr, size_t size, + enum dma_data_direction dir) +{ + switch (dir) { + case DMA_BIDIRECTIONAL: + kmsan_internal_check_memory((void *)addr, size, /*user_addr*/ 0, + REASON_ANY); + kmsan_internal_unpoison_memory((void *)addr, size, + /*checked*/ false); + break; + case DMA_TO_DEVICE: + kmsan_internal_check_memory((void *)addr, size, /*user_addr*/ 0, + REASON_ANY); + break; + case DMA_FROM_DEVICE: + kmsan_internal_unpoison_memory((void *)addr, size, + /*checked*/ false); + break; + case DMA_NONE: + break; + } +} + +/* Helper function to handle DMA data transfers. */ +void kmsan_handle_dma(struct page *page, size_t offset, size_t size, + enum dma_data_direction dir) +{ + u64 page_offset, to_go, addr; + + if (PageHighMem(page)) + return; + addr = (u64)page_address(page) + offset; + /* + * The kernel may occasionally give us adjacent DMA pages not belonging + * to the same allocation. Process them separately to avoid triggering + * internal KMSAN checks. + */ + while (size > 0) { + page_offset = addr % PAGE_SIZE; + to_go = min(PAGE_SIZE - page_offset, (u64)size); + kmsan_handle_dma_page((void *)addr, to_go, dir); + addr += to_go; + size -= to_go; + } +} + +void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, + enum dma_data_direction dir) +{ + struct scatterlist *item; + int i; + + for_each_sg(sg, item, nents, i) + kmsan_handle_dma(sg_page(item), item->offset, item->length, + dir); +} + +/* Functions from kmsan-checks.h follow. */ +void kmsan_poison_memory(const void *address, size_t size, gfp_t flags) +{ + if (!kmsan_enabled || kmsan_in_runtime()) + return; + kmsan_enter_runtime(); + /* The users may want to poison/unpoison random memory. */ + kmsan_internal_poison_memory((void *)address, size, flags, + KMSAN_POISON_NOCHECK); + kmsan_leave_runtime(); +} +EXPORT_SYMBOL(kmsan_poison_memory); + +void kmsan_unpoison_memory(const void *address, size_t size) +{ + unsigned long ua_flags; + + if (!kmsan_enabled || kmsan_in_runtime()) + return; + + ua_flags = user_access_save(); + kmsan_enter_runtime(); + /* The users may want to poison/unpoison random memory. */ + kmsan_internal_unpoison_memory((void *)address, size, + KMSAN_POISON_NOCHECK); + kmsan_leave_runtime(); + user_access_restore(ua_flags); +} +EXPORT_SYMBOL(kmsan_unpoison_memory); + +/* + * Version of kmsan_unpoison_memory() that can be called from within the KMSAN + * runtime. + * + * Non-instrumented IRQ entry functions receive struct pt_regs from assembly + * code. Those regs need to be unpoisoned, otherwise using them will result in + * false positives. + * Using kmsan_unpoison_memory() is not an option in entry code, because the + * return value of in_task() is inconsistent - as a result, certain calls to + * kmsan_unpoison_memory() are ignored. kmsan_unpoison_entry_regs() ensures that + * the registers are unpoisoned even if kmsan_in_runtime() is true in the early + * entry code. + */ +void kmsan_unpoison_entry_regs(const struct pt_regs *regs) +{ + unsigned long ua_flags; + + if (!kmsan_enabled) + return; + + ua_flags = user_access_save(); + kmsan_internal_unpoison_memory((void *)regs, sizeof(*regs), + KMSAN_POISON_NOCHECK); + user_access_restore(ua_flags); +} + +void kmsan_check_memory(const void *addr, size_t size) +{ + if (!kmsan_enabled) + return; + return kmsan_internal_check_memory((void *)addr, size, /*user_addr*/ 0, + REASON_ANY); +} +EXPORT_SYMBOL(kmsan_check_memory); diff --git a/mm/kmsan/init.c b/mm/kmsan/init.c new file mode 100644 index 000000000..7fb794242 --- /dev/null +++ b/mm/kmsan/init.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KMSAN initialization routines. + * + * Copyright (C) 2017-2021 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#include "kmsan.h" + +#include <asm/sections.h> +#include <linux/mm.h> +#include <linux/memblock.h> + +#include "../internal.h" + +#define NUM_FUTURE_RANGES 128 +struct start_end_pair { + u64 start, end; +}; + +static struct start_end_pair start_end_pairs[NUM_FUTURE_RANGES] __initdata; +static int future_index __initdata; + +/* + * Record a range of memory for which the metadata pages will be created once + * the page allocator becomes available. + */ +static void __init kmsan_record_future_shadow_range(void *start, void *end) +{ + u64 nstart = (u64)start, nend = (u64)end, cstart, cend; + bool merged = false; + + KMSAN_WARN_ON(future_index == NUM_FUTURE_RANGES); + KMSAN_WARN_ON((nstart >= nend) || !nstart || !nend); + nstart = ALIGN_DOWN(nstart, PAGE_SIZE); + nend = ALIGN(nend, PAGE_SIZE); + + /* + * Scan the existing ranges to see if any of them overlaps with + * [start, end). In that case, merge the two ranges instead of + * creating a new one. + * The number of ranges is less than 20, so there is no need to organize + * them into a more intelligent data structure. + */ + for (int i = 0; i < future_index; i++) { + cstart = start_end_pairs[i].start; + cend = start_end_pairs[i].end; + if ((cstart < nstart && cend < nstart) || + (cstart > nend && cend > nend)) + /* ranges are disjoint - do not merge */ + continue; + start_end_pairs[i].start = min(nstart, cstart); + start_end_pairs[i].end = max(nend, cend); + merged = true; + break; + } + if (merged) + return; + start_end_pairs[future_index].start = nstart; + start_end_pairs[future_index].end = nend; + future_index++; +} + +/* + * Initialize the shadow for existing mappings during kernel initialization. + * These include kernel text/data sections, NODE_DATA and future ranges + * registered while creating other data (e.g. percpu). + * + * Allocations via memblock can be only done before slab is initialized. + */ +void __init kmsan_init_shadow(void) +{ + const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); + phys_addr_t p_start, p_end; + u64 loop; + int nid; + + for_each_reserved_mem_range(loop, &p_start, &p_end) + kmsan_record_future_shadow_range(phys_to_virt(p_start), + phys_to_virt(p_end)); + /* Allocate shadow for .data */ + kmsan_record_future_shadow_range(_sdata, _edata); + + for_each_online_node(nid) + kmsan_record_future_shadow_range( + NODE_DATA(nid), (char *)NODE_DATA(nid) + nd_size); + + for (int i = 0; i < future_index; i++) + kmsan_init_alloc_meta_for_range( + (void *)start_end_pairs[i].start, + (void *)start_end_pairs[i].end); +} + +struct metadata_page_pair { + struct page *shadow, *origin; +}; +static struct metadata_page_pair held_back[MAX_ORDER] __initdata; + +/* + * Eager metadata allocation. When the memblock allocator is freeing pages to + * pagealloc, we use 2/3 of them as metadata for the remaining 1/3. + * We store the pointers to the returned blocks of pages in held_back[] grouped + * by their order: when kmsan_memblock_free_pages() is called for the first + * time with a certain order, it is reserved as a shadow block, for the second + * time - as an origin block. On the third time the incoming block receives its + * shadow and origin ranges from the previously saved shadow and origin blocks, + * after which held_back[order] can be used again. + * + * At the very end there may be leftover blocks in held_back[]. They are + * collected later by kmsan_memblock_discard(). + */ +bool kmsan_memblock_free_pages(struct page *page, unsigned int order) +{ + struct page *shadow, *origin; + + if (!held_back[order].shadow) { + held_back[order].shadow = page; + return false; + } + if (!held_back[order].origin) { + held_back[order].origin = page; + return false; + } + shadow = held_back[order].shadow; + origin = held_back[order].origin; + kmsan_setup_meta(page, shadow, origin, order); + + held_back[order].shadow = NULL; + held_back[order].origin = NULL; + return true; +} + +#define MAX_BLOCKS 8 +struct smallstack { + struct page *items[MAX_BLOCKS]; + int index; + int order; +}; + +static struct smallstack collect = { + .index = 0, + .order = MAX_ORDER, +}; + +static void smallstack_push(struct smallstack *stack, struct page *pages) +{ + KMSAN_WARN_ON(stack->index == MAX_BLOCKS); + stack->items[stack->index] = pages; + stack->index++; +} +#undef MAX_BLOCKS + +static struct page *smallstack_pop(struct smallstack *stack) +{ + struct page *ret; + + KMSAN_WARN_ON(stack->index == 0); + stack->index--; + ret = stack->items[stack->index]; + stack->items[stack->index] = NULL; + return ret; +} + +static void do_collection(void) +{ + struct page *page, *shadow, *origin; + + while (collect.index >= 3) { + page = smallstack_pop(&collect); + shadow = smallstack_pop(&collect); + origin = smallstack_pop(&collect); + kmsan_setup_meta(page, shadow, origin, collect.order); + __free_pages_core(page, collect.order); + } +} + +static void collect_split(void) +{ + struct smallstack tmp = { + .order = collect.order - 1, + .index = 0, + }; + struct page *page; + + if (!collect.order) + return; + while (collect.index) { + page = smallstack_pop(&collect); + smallstack_push(&tmp, &page[0]); + smallstack_push(&tmp, &page[1 << tmp.order]); + } + __memcpy(&collect, &tmp, sizeof(tmp)); +} + +/* + * Memblock is about to go away. Split the page blocks left over in held_back[] + * and return 1/3 of that memory to the system. + */ +static void kmsan_memblock_discard(void) +{ + /* + * For each order=N: + * - push held_back[N].shadow and .origin to @collect; + * - while there are >= 3 elements in @collect, do garbage collection: + * - pop 3 ranges from @collect; + * - use two of them as shadow and origin for the third one; + * - repeat; + * - split each remaining element from @collect into 2 ranges of + * order=N-1, + * - repeat. + */ + collect.order = MAX_ORDER - 1; + for (int i = MAX_ORDER - 1; i >= 0; i--) { + if (held_back[i].shadow) + smallstack_push(&collect, held_back[i].shadow); + if (held_back[i].origin) + smallstack_push(&collect, held_back[i].origin); + held_back[i].shadow = NULL; + held_back[i].origin = NULL; + do_collection(); + collect_split(); + } +} + +void __init kmsan_init_runtime(void) +{ + /* Assuming current is init_task */ + kmsan_internal_task_create(current); + kmsan_memblock_discard(); + pr_info("Starting KernelMemorySanitizer\n"); + pr_info("ATTENTION: KMSAN is a debugging tool! Do not use it on production machines!\n"); + kmsan_enabled = true; +} diff --git a/mm/kmsan/instrumentation.c b/mm/kmsan/instrumentation.c new file mode 100644 index 000000000..271f135f9 --- /dev/null +++ b/mm/kmsan/instrumentation.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KMSAN compiler API. + * + * This file implements __msan_XXX hooks that Clang inserts into the code + * compiled with -fsanitize=kernel-memory. + * See Documentation/dev-tools/kmsan.rst for more information on how KMSAN + * instrumentation works. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#include "kmsan.h" +#include <linux/gfp.h> +#include <linux/kmsan_string.h> +#include <linux/mm.h> +#include <linux/uaccess.h> + +static inline bool is_bad_asm_addr(void *addr, uintptr_t size, bool is_store) +{ + if ((u64)addr < TASK_SIZE) + return true; + if (!kmsan_get_metadata(addr, KMSAN_META_SHADOW)) + return true; + return false; +} + +static inline struct shadow_origin_ptr +get_shadow_origin_ptr(void *addr, u64 size, bool store) +{ + unsigned long ua_flags = user_access_save(); + struct shadow_origin_ptr ret; + + ret = kmsan_get_shadow_origin_ptr(addr, size, store); + user_access_restore(ua_flags); + return ret; +} + +/* Get shadow and origin pointers for a memory load with non-standard size. */ +struct shadow_origin_ptr __msan_metadata_ptr_for_load_n(void *addr, + uintptr_t size) +{ + return get_shadow_origin_ptr(addr, size, /*store*/ false); +} +EXPORT_SYMBOL(__msan_metadata_ptr_for_load_n); + +/* Get shadow and origin pointers for a memory store with non-standard size. */ +struct shadow_origin_ptr __msan_metadata_ptr_for_store_n(void *addr, + uintptr_t size) +{ + return get_shadow_origin_ptr(addr, size, /*store*/ true); +} +EXPORT_SYMBOL(__msan_metadata_ptr_for_store_n); + +/* + * Declare functions that obtain shadow/origin pointers for loads and stores + * with fixed size. + */ +#define DECLARE_METADATA_PTR_GETTER(size) \ + struct shadow_origin_ptr __msan_metadata_ptr_for_load_##size( \ + void *addr) \ + { \ + return get_shadow_origin_ptr(addr, size, /*store*/ false); \ + } \ + EXPORT_SYMBOL(__msan_metadata_ptr_for_load_##size); \ + struct shadow_origin_ptr __msan_metadata_ptr_for_store_##size( \ + void *addr) \ + { \ + return get_shadow_origin_ptr(addr, size, /*store*/ true); \ + } \ + EXPORT_SYMBOL(__msan_metadata_ptr_for_store_##size) + +DECLARE_METADATA_PTR_GETTER(1); +DECLARE_METADATA_PTR_GETTER(2); +DECLARE_METADATA_PTR_GETTER(4); +DECLARE_METADATA_PTR_GETTER(8); + +/* + * Handle a memory store performed by inline assembly. KMSAN conservatively + * attempts to unpoison the outputs of asm() directives to prevent false + * positives caused by missed stores. + */ +void __msan_instrument_asm_store(void *addr, uintptr_t size) +{ + unsigned long ua_flags; + + if (!kmsan_enabled || kmsan_in_runtime()) + return; + + ua_flags = user_access_save(); + /* + * Most of the accesses are below 32 bytes. The two exceptions so far + * are clwb() (64 bytes) and FPU state (512 bytes). + * It's unlikely that the assembly will touch more than 512 bytes. + */ + if (size > 512) { + WARN_ONCE(1, "assembly store size too big: %ld\n", size); + size = 8; + } + if (is_bad_asm_addr(addr, size, /*is_store*/ true)) { + user_access_restore(ua_flags); + return; + } + kmsan_enter_runtime(); + /* Unpoisoning the memory on best effort. */ + kmsan_internal_unpoison_memory(addr, size, /*checked*/ false); + kmsan_leave_runtime(); + user_access_restore(ua_flags); +} +EXPORT_SYMBOL(__msan_instrument_asm_store); + +/* + * KMSAN instrumentation pass replaces LLVM memcpy, memmove and memset + * intrinsics with calls to respective __msan_ functions. We use + * get_param0_metadata() and set_retval_metadata() to store the shadow/origin + * values for the destination argument of these functions and use them for the + * functions' return values. + */ +static inline void get_param0_metadata(u64 *shadow, + depot_stack_handle_t *origin) +{ + struct kmsan_ctx *ctx = kmsan_get_context(); + + *shadow = *(u64 *)(ctx->cstate.param_tls); + *origin = ctx->cstate.param_origin_tls[0]; +} + +static inline void set_retval_metadata(u64 shadow, depot_stack_handle_t origin) +{ + struct kmsan_ctx *ctx = kmsan_get_context(); + + *(u64 *)(ctx->cstate.retval_tls) = shadow; + ctx->cstate.retval_origin_tls = origin; +} + +/* Handle llvm.memmove intrinsic. */ +void *__msan_memmove(void *dst, const void *src, uintptr_t n) +{ + depot_stack_handle_t origin; + void *result; + u64 shadow; + + get_param0_metadata(&shadow, &origin); + result = __memmove(dst, src, n); + if (!n) + /* Some people call memmove() with zero length. */ + return result; + if (!kmsan_enabled || kmsan_in_runtime()) + return result; + + kmsan_enter_runtime(); + kmsan_internal_memmove_metadata(dst, (void *)src, n); + kmsan_leave_runtime(); + + set_retval_metadata(shadow, origin); + return result; +} +EXPORT_SYMBOL(__msan_memmove); + +/* Handle llvm.memcpy intrinsic. */ +void *__msan_memcpy(void *dst, const void *src, uintptr_t n) +{ + depot_stack_handle_t origin; + void *result; + u64 shadow; + + get_param0_metadata(&shadow, &origin); + result = __memcpy(dst, src, n); + if (!n) + /* Some people call memcpy() with zero length. */ + return result; + + if (!kmsan_enabled || kmsan_in_runtime()) + return result; + + kmsan_enter_runtime(); + /* Using memmove instead of memcpy doesn't affect correctness. */ + kmsan_internal_memmove_metadata(dst, (void *)src, n); + kmsan_leave_runtime(); + + set_retval_metadata(shadow, origin); + return result; +} +EXPORT_SYMBOL(__msan_memcpy); + +/* Handle llvm.memset intrinsic. */ +void *__msan_memset(void *dst, int c, uintptr_t n) +{ + depot_stack_handle_t origin; + void *result; + u64 shadow; + + get_param0_metadata(&shadow, &origin); + result = __memset(dst, c, n); + if (!kmsan_enabled || kmsan_in_runtime()) + return result; + + kmsan_enter_runtime(); + /* + * Clang doesn't pass parameter metadata here, so it is impossible to + * use shadow of @c to set up the shadow for @dst. + */ + kmsan_internal_unpoison_memory(dst, n, /*checked*/ false); + kmsan_leave_runtime(); + + set_retval_metadata(shadow, origin); + return result; +} +EXPORT_SYMBOL(__msan_memset); + +/* + * Create a new origin from an old one. This is done when storing an + * uninitialized value to memory. When reporting an error, KMSAN unrolls and + * prints the whole chain of stores that preceded the use of this value. + */ +depot_stack_handle_t __msan_chain_origin(depot_stack_handle_t origin) +{ + depot_stack_handle_t ret = 0; + unsigned long ua_flags; + + if (!kmsan_enabled || kmsan_in_runtime()) + return ret; + + ua_flags = user_access_save(); + + /* Creating new origins may allocate memory. */ + kmsan_enter_runtime(); + ret = kmsan_internal_chain_origin(origin); + kmsan_leave_runtime(); + user_access_restore(ua_flags); + return ret; +} +EXPORT_SYMBOL(__msan_chain_origin); + +/* Poison a local variable when entering a function. */ +void __msan_poison_alloca(void *address, uintptr_t size, char *descr) +{ + depot_stack_handle_t handle; + unsigned long entries[4]; + unsigned long ua_flags; + + if (!kmsan_enabled || kmsan_in_runtime()) + return; + + ua_flags = user_access_save(); + entries[0] = KMSAN_ALLOCA_MAGIC_ORIGIN; + entries[1] = (u64)descr; + entries[2] = (u64)__builtin_return_address(0); + /* + * With frame pointers enabled, it is possible to quickly fetch the + * second frame of the caller stack without calling the unwinder. + * Without them, simply do not bother. + */ + if (IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER)) + entries[3] = (u64)__builtin_return_address(1); + else + entries[3] = 0; + + /* stack_depot_save() may allocate memory. */ + kmsan_enter_runtime(); + handle = stack_depot_save(entries, ARRAY_SIZE(entries), GFP_ATOMIC); + kmsan_leave_runtime(); + + kmsan_internal_set_shadow_origin(address, size, -1, handle, + /*checked*/ true); + user_access_restore(ua_flags); +} +EXPORT_SYMBOL(__msan_poison_alloca); + +/* Unpoison a local variable. */ +void __msan_unpoison_alloca(void *address, uintptr_t size) +{ + if (!kmsan_enabled || kmsan_in_runtime()) + return; + + kmsan_enter_runtime(); + kmsan_internal_unpoison_memory(address, size, /*checked*/ true); + kmsan_leave_runtime(); +} +EXPORT_SYMBOL(__msan_unpoison_alloca); + +/* + * Report that an uninitialized value with the given origin was used in a way + * that constituted undefined behavior. + */ +void __msan_warning(u32 origin) +{ + if (!kmsan_enabled || kmsan_in_runtime()) + return; + kmsan_enter_runtime(); + kmsan_report(origin, /*address*/ 0, /*size*/ 0, + /*off_first*/ 0, /*off_last*/ 0, /*user_addr*/ 0, + REASON_ANY); + kmsan_leave_runtime(); +} +EXPORT_SYMBOL(__msan_warning); + +/* + * At the beginning of an instrumented function, obtain the pointer to + * `struct kmsan_context_state` holding the metadata for function parameters. + */ +struct kmsan_context_state *__msan_get_context_state(void) +{ + return &kmsan_get_context()->cstate; +} +EXPORT_SYMBOL(__msan_get_context_state); diff --git a/mm/kmsan/kmsan.h b/mm/kmsan/kmsan.h new file mode 100644 index 000000000..a14744205 --- /dev/null +++ b/mm/kmsan/kmsan.h @@ -0,0 +1,211 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Functions used by the KMSAN runtime. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#ifndef __MM_KMSAN_KMSAN_H +#define __MM_KMSAN_KMSAN_H + +#include <asm/pgtable_64_types.h> +#include <linux/irqflags.h> +#include <linux/sched.h> +#include <linux/stackdepot.h> +#include <linux/stacktrace.h> +#include <linux/nmi.h> +#include <linux/mm.h> +#include <linux/printk.h> + +#define KMSAN_ALLOCA_MAGIC_ORIGIN 0xabcd0100 +#define KMSAN_CHAIN_MAGIC_ORIGIN 0xabcd0200 + +#define KMSAN_POISON_NOCHECK 0x0 +#define KMSAN_POISON_CHECK 0x1 +#define KMSAN_POISON_FREE 0x2 + +#define KMSAN_ORIGIN_SIZE 4 +#define KMSAN_MAX_ORIGIN_DEPTH 7 + +#define KMSAN_STACK_DEPTH 64 + +#define KMSAN_META_SHADOW (false) +#define KMSAN_META_ORIGIN (true) + +extern bool kmsan_enabled; +extern int panic_on_kmsan; + +/* + * KMSAN performs a lot of consistency checks that are currently enabled by + * default. BUG_ON is normally discouraged in the kernel, unless used for + * debugging, but KMSAN itself is a debugging tool, so it makes little sense to + * recover if something goes wrong. + */ +#define KMSAN_WARN_ON(cond) \ + ({ \ + const bool __cond = WARN_ON(cond); \ + if (unlikely(__cond)) { \ + WRITE_ONCE(kmsan_enabled, false); \ + if (panic_on_kmsan) { \ + /* Can't call panic() here because */ \ + /* of uaccess checks. */ \ + BUG(); \ + } \ + } \ + __cond; \ + }) + +/* + * A pair of metadata pointers to be returned by the instrumentation functions. + */ +struct shadow_origin_ptr { + void *shadow, *origin; +}; + +struct shadow_origin_ptr kmsan_get_shadow_origin_ptr(void *addr, u64 size, + bool store); +void *kmsan_get_metadata(void *addr, bool is_origin); +void __init kmsan_init_alloc_meta_for_range(void *start, void *end); + +enum kmsan_bug_reason { + REASON_ANY, + REASON_COPY_TO_USER, + REASON_SUBMIT_URB, +}; + +void kmsan_print_origin(depot_stack_handle_t origin); + +/** + * kmsan_report() - Report a use of uninitialized value. + * @origin: Stack ID of the uninitialized value. + * @address: Address at which the memory access happens. + * @size: Memory access size. + * @off_first: Offset (from @address) of the first byte to be reported. + * @off_last: Offset (from @address) of the last byte to be reported. + * @user_addr: When non-NULL, denotes the userspace address to which the kernel + * is leaking data. + * @reason: Error type from enum kmsan_bug_reason. + * + * kmsan_report() prints an error message for a consequent group of bytes + * sharing the same origin. If an uninitialized value is used in a comparison, + * this function is called once without specifying the addresses. When checking + * a memory range, KMSAN may call kmsan_report() multiple times with the same + * @address, @size, @user_addr and @reason, but different @off_first and + * @off_last corresponding to different @origin values. + */ +void kmsan_report(depot_stack_handle_t origin, void *address, int size, + int off_first, int off_last, const void *user_addr, + enum kmsan_bug_reason reason); + +DECLARE_PER_CPU(struct kmsan_ctx, kmsan_percpu_ctx); + +static __always_inline struct kmsan_ctx *kmsan_get_context(void) +{ + return in_task() ? ¤t->kmsan_ctx : raw_cpu_ptr(&kmsan_percpu_ctx); +} + +/* + * When a compiler hook or KMSAN runtime function is invoked, it may make a + * call to instrumented code and eventually call itself recursively. To avoid + * that, we guard the runtime entry regions with + * kmsan_enter_runtime()/kmsan_leave_runtime() and exit the hook if + * kmsan_in_runtime() is true. + * + * Non-runtime code may occasionally get executed in nested IRQs from the + * runtime code (e.g. when called via smp_call_function_single()). Because some + * KMSAN routines may take locks (e.g. for memory allocation), we conservatively + * bail out instead of calling them. To minimize the effect of this (potentially + * missing initialization events) kmsan_in_runtime() is not checked in + * non-blocking runtime functions. + */ +static __always_inline bool kmsan_in_runtime(void) +{ + if ((hardirq_count() >> HARDIRQ_SHIFT) > 1) + return true; + if (in_nmi()) + return true; + return kmsan_get_context()->kmsan_in_runtime; +} + +static __always_inline void kmsan_enter_runtime(void) +{ + struct kmsan_ctx *ctx; + + ctx = kmsan_get_context(); + KMSAN_WARN_ON(ctx->kmsan_in_runtime++); +} + +static __always_inline void kmsan_leave_runtime(void) +{ + struct kmsan_ctx *ctx = kmsan_get_context(); + + KMSAN_WARN_ON(--ctx->kmsan_in_runtime); +} + +depot_stack_handle_t kmsan_save_stack(void); +depot_stack_handle_t kmsan_save_stack_with_flags(gfp_t flags, + unsigned int extra_bits); + +/* + * Pack and unpack the origin chain depth and UAF flag to/from the extra bits + * provided by the stack depot. + * The UAF flag is stored in the lowest bit, followed by the depth in the upper + * bits. + * set_dsh_extra_bits() is responsible for clamping the value. + */ +static __always_inline unsigned int kmsan_extra_bits(unsigned int depth, + bool uaf) +{ + return (depth << 1) | uaf; +} + +static __always_inline bool kmsan_uaf_from_eb(unsigned int extra_bits) +{ + return extra_bits & 1; +} + +static __always_inline unsigned int kmsan_depth_from_eb(unsigned int extra_bits) +{ + return extra_bits >> 1; +} + +/* + * kmsan_internal_ functions are supposed to be very simple and not require the + * kmsan_in_runtime() checks. + */ +void kmsan_internal_memmove_metadata(void *dst, void *src, size_t n); +void kmsan_internal_poison_memory(void *address, size_t size, gfp_t flags, + unsigned int poison_flags); +void kmsan_internal_unpoison_memory(void *address, size_t size, bool checked); +void kmsan_internal_set_shadow_origin(void *address, size_t size, int b, + u32 origin, bool checked); +depot_stack_handle_t kmsan_internal_chain_origin(depot_stack_handle_t id); + +void kmsan_internal_task_create(struct task_struct *task); + +bool kmsan_metadata_is_contiguous(void *addr, size_t size); +void kmsan_internal_check_memory(void *addr, size_t size, const void *user_addr, + int reason); + +struct page *kmsan_vmalloc_to_page_or_null(void *vaddr); +void kmsan_setup_meta(struct page *page, struct page *shadow, + struct page *origin, int order); + +/* + * kmsan_internal_is_module_addr() and kmsan_internal_is_vmalloc_addr() are + * non-instrumented versions of is_module_address() and is_vmalloc_addr() that + * are safe to call from KMSAN runtime without recursion. + */ +static inline bool kmsan_internal_is_module_addr(void *vaddr) +{ + return ((u64)vaddr >= MODULES_VADDR) && ((u64)vaddr < MODULES_END); +} + +static inline bool kmsan_internal_is_vmalloc_addr(void *addr) +{ + return ((u64)addr >= VMALLOC_START) && ((u64)addr < VMALLOC_END); +} + +#endif /* __MM_KMSAN_KMSAN_H */ diff --git a/mm/kmsan/kmsan_test.c b/mm/kmsan/kmsan_test.c new file mode 100644 index 000000000..1328636cb --- /dev/null +++ b/mm/kmsan/kmsan_test.c @@ -0,0 +1,582 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test cases for KMSAN. + * For each test case checks the presence (or absence) of generated reports. + * Relies on 'console' tracepoint to capture reports as they appear in the + * kernel log. + * + * Copyright (C) 2021-2022, Google LLC. + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#include <kunit/test.h> +#include "kmsan.h" + +#include <linux/jiffies.h> +#include <linux/kernel.h> +#include <linux/kmsan.h> +#include <linux/mm.h> +#include <linux/random.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/tracepoint.h> +#include <linux/vmalloc.h> +#include <trace/events/printk.h> + +static DEFINE_PER_CPU(int, per_cpu_var); + +/* Report as observed from console. */ +static struct { + spinlock_t lock; + bool available; + bool ignore; /* Stop console output collection. */ + char header[256]; +} observed = { + .lock = __SPIN_LOCK_UNLOCKED(observed.lock), +}; + +/* Probe for console output: obtains observed lines of interest. */ +static void probe_console(void *ignore, const char *buf, size_t len) +{ + unsigned long flags; + + if (observed.ignore) + return; + spin_lock_irqsave(&observed.lock, flags); + + if (strnstr(buf, "BUG: KMSAN: ", len)) { + /* + * KMSAN report and related to the test. + * + * The provided @buf is not NUL-terminated; copy no more than + * @len bytes and let strscpy() add the missing NUL-terminator. + */ + strscpy(observed.header, buf, + min(len + 1, sizeof(observed.header))); + WRITE_ONCE(observed.available, true); + observed.ignore = true; + } + spin_unlock_irqrestore(&observed.lock, flags); +} + +/* Check if a report related to the test exists. */ +static bool report_available(void) +{ + return READ_ONCE(observed.available); +} + +/* Information we expect in a report. */ +struct expect_report { + const char *error_type; /* Error type. */ + /* + * Kernel symbol from the error header, or NULL if no report is + * expected. + */ + const char *symbol; +}; + +/* Check observed report matches information in @r. */ +static bool report_matches(const struct expect_report *r) +{ + typeof(observed.header) expected_header; + unsigned long flags; + bool ret = false; + const char *end; + char *cur; + + /* Doubled-checked locking. */ + if (!report_available() || !r->symbol) + return (!report_available() && !r->symbol); + + /* Generate expected report contents. */ + + /* Title */ + cur = expected_header; + end = &expected_header[sizeof(expected_header) - 1]; + + cur += scnprintf(cur, end - cur, "BUG: KMSAN: %s", r->error_type); + + scnprintf(cur, end - cur, " in %s", r->symbol); + /* The exact offset won't match, remove it; also strip module name. */ + cur = strchr(expected_header, '+'); + if (cur) + *cur = '\0'; + + spin_lock_irqsave(&observed.lock, flags); + if (!report_available()) + goto out; /* A new report is being captured. */ + + /* Finally match expected output to what we actually observed. */ + ret = strstr(observed.header, expected_header); +out: + spin_unlock_irqrestore(&observed.lock, flags); + + return ret; +} + +/* ===== Test cases ===== */ + +/* Prevent replacing branch with select in LLVM. */ +static noinline void check_true(char *arg) +{ + pr_info("%s is true\n", arg); +} + +static noinline void check_false(char *arg) +{ + pr_info("%s is false\n", arg); +} + +#define USE(x) \ + do { \ + if (x) \ + check_true(#x); \ + else \ + check_false(#x); \ + } while (0) + +#define EXPECTATION_ETYPE_FN(e, reason, fn) \ + struct expect_report e = { \ + .error_type = reason, \ + .symbol = fn, \ + } + +#define EXPECTATION_NO_REPORT(e) EXPECTATION_ETYPE_FN(e, NULL, NULL) +#define EXPECTATION_UNINIT_VALUE_FN(e, fn) \ + EXPECTATION_ETYPE_FN(e, "uninit-value", fn) +#define EXPECTATION_UNINIT_VALUE(e) EXPECTATION_UNINIT_VALUE_FN(e, __func__) +#define EXPECTATION_USE_AFTER_FREE(e) \ + EXPECTATION_ETYPE_FN(e, "use-after-free", __func__) + +/* Test case: ensure that kmalloc() returns uninitialized memory. */ +static void test_uninit_kmalloc(struct kunit *test) +{ + EXPECTATION_UNINIT_VALUE(expect); + int *ptr; + + kunit_info(test, "uninitialized kmalloc test (UMR report)\n"); + ptr = kmalloc(sizeof(*ptr), GFP_KERNEL); + USE(*ptr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * Test case: ensure that kmalloc'ed memory becomes initialized after memset(). + */ +static void test_init_kmalloc(struct kunit *test) +{ + EXPECTATION_NO_REPORT(expect); + int *ptr; + + kunit_info(test, "initialized kmalloc test (no reports)\n"); + ptr = kmalloc(sizeof(*ptr), GFP_KERNEL); + memset(ptr, 0, sizeof(*ptr)); + USE(*ptr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test case: ensure that kzalloc() returns initialized memory. */ +static void test_init_kzalloc(struct kunit *test) +{ + EXPECTATION_NO_REPORT(expect); + int *ptr; + + kunit_info(test, "initialized kzalloc test (no reports)\n"); + ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); + USE(*ptr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test case: ensure that local variables are uninitialized by default. */ +static void test_uninit_stack_var(struct kunit *test) +{ + EXPECTATION_UNINIT_VALUE(expect); + volatile int cond; + + kunit_info(test, "uninitialized stack variable (UMR report)\n"); + USE(cond); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test case: ensure that local variables with initializers are initialized. */ +static void test_init_stack_var(struct kunit *test) +{ + EXPECTATION_NO_REPORT(expect); + volatile int cond = 1; + + kunit_info(test, "initialized stack variable (no reports)\n"); + USE(cond); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static noinline void two_param_fn_2(int arg1, int arg2) +{ + USE(arg1); + USE(arg2); +} + +static noinline void one_param_fn(int arg) +{ + two_param_fn_2(arg, arg); + USE(arg); +} + +static noinline void two_param_fn(int arg1, int arg2) +{ + int init = 0; + + one_param_fn(init); + USE(arg1); + USE(arg2); +} + +static void test_params(struct kunit *test) +{ +#ifdef CONFIG_KMSAN_CHECK_PARAM_RETVAL + /* + * With eager param/retval checking enabled, KMSAN will report an error + * before the call to two_param_fn(). + */ + EXPECTATION_UNINIT_VALUE_FN(expect, "test_params"); +#else + EXPECTATION_UNINIT_VALUE_FN(expect, "two_param_fn"); +#endif + volatile int uninit, init = 1; + + kunit_info(test, + "uninit passed through a function parameter (UMR report)\n"); + two_param_fn(uninit, init); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static int signed_sum3(int a, int b, int c) +{ + return a + b + c; +} + +/* + * Test case: ensure that uninitialized values are tracked through function + * arguments. + */ +static void test_uninit_multiple_params(struct kunit *test) +{ + EXPECTATION_UNINIT_VALUE(expect); + volatile char b = 3, c; + volatile int a; + + kunit_info(test, "uninitialized local passed to fn (UMR report)\n"); + USE(signed_sum3(a, b, c)); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Helper function to make an array uninitialized. */ +static noinline void do_uninit_local_array(char *array, int start, int stop) +{ + volatile char uninit; + + for (int i = start; i < stop; i++) + array[i] = uninit; +} + +/* + * Test case: ensure kmsan_check_memory() reports an error when checking + * uninitialized memory. + */ +static void test_uninit_kmsan_check_memory(struct kunit *test) +{ + EXPECTATION_UNINIT_VALUE_FN(expect, "test_uninit_kmsan_check_memory"); + volatile char local_array[8]; + + kunit_info( + test, + "kmsan_check_memory() called on uninit local (UMR report)\n"); + do_uninit_local_array((char *)local_array, 5, 7); + + kmsan_check_memory((char *)local_array, 8); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * Test case: check that a virtual memory range created with vmap() from + * initialized pages is still considered as initialized. + */ +static void test_init_kmsan_vmap_vunmap(struct kunit *test) +{ + EXPECTATION_NO_REPORT(expect); + const int npages = 2; + struct page **pages; + void *vbuf; + + kunit_info(test, "pages initialized via vmap (no reports)\n"); + + pages = kmalloc_array(npages, sizeof(*pages), GFP_KERNEL); + for (int i = 0; i < npages; i++) + pages[i] = alloc_page(GFP_KERNEL); + vbuf = vmap(pages, npages, VM_MAP, PAGE_KERNEL); + memset(vbuf, 0xfe, npages * PAGE_SIZE); + for (int i = 0; i < npages; i++) + kmsan_check_memory(page_address(pages[i]), PAGE_SIZE); + + if (vbuf) + vunmap(vbuf); + for (int i = 0; i < npages; i++) { + if (pages[i]) + __free_page(pages[i]); + } + kfree(pages); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * Test case: ensure that memset() can initialize a buffer allocated via + * vmalloc(). + */ +static void test_init_vmalloc(struct kunit *test) +{ + EXPECTATION_NO_REPORT(expect); + int npages = 8; + char *buf; + + kunit_info(test, "vmalloc buffer can be initialized (no reports)\n"); + buf = vmalloc(PAGE_SIZE * npages); + buf[0] = 1; + memset(buf, 0xfe, PAGE_SIZE * npages); + USE(buf[0]); + for (int i = 0; i < npages; i++) + kmsan_check_memory(&buf[PAGE_SIZE * i], PAGE_SIZE); + vfree(buf); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test case: ensure that use-after-free reporting works. */ +static void test_uaf(struct kunit *test) +{ + EXPECTATION_USE_AFTER_FREE(expect); + volatile int value; + volatile int *var; + + kunit_info(test, "use-after-free in kmalloc-ed buffer (UMR report)\n"); + var = kmalloc(80, GFP_KERNEL); + var[3] = 0xfeedface; + kfree((int *)var); + /* Copy the invalid value before checking it. */ + value = var[3]; + USE(value); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * Test case: ensure that uninitialized values are propagated through per-CPU + * memory. + */ +static void test_percpu_propagate(struct kunit *test) +{ + EXPECTATION_UNINIT_VALUE(expect); + volatile int uninit, check; + + kunit_info(test, + "uninit local stored to per_cpu memory (UMR report)\n"); + + this_cpu_write(per_cpu_var, uninit); + check = this_cpu_read(per_cpu_var); + USE(check); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * Test case: ensure that passing uninitialized values to printk() leads to an + * error report. + */ +static void test_printk(struct kunit *test) +{ +#ifdef CONFIG_KMSAN_CHECK_PARAM_RETVAL + /* + * With eager param/retval checking enabled, KMSAN will report an error + * before the call to pr_info(). + */ + EXPECTATION_UNINIT_VALUE_FN(expect, "test_printk"); +#else + EXPECTATION_UNINIT_VALUE_FN(expect, "number"); +#endif + volatile int uninit; + + kunit_info(test, "uninit local passed to pr_info() (UMR report)\n"); + pr_info("%px contains %d\n", &uninit, uninit); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * Test case: ensure that memcpy() correctly copies uninitialized values between + * aligned `src` and `dst`. + */ +static void test_memcpy_aligned_to_aligned(struct kunit *test) +{ + EXPECTATION_UNINIT_VALUE_FN(expect, "test_memcpy_aligned_to_aligned"); + volatile int uninit_src; + volatile int dst = 0; + + kunit_info( + test, + "memcpy()ing aligned uninit src to aligned dst (UMR report)\n"); + memcpy((void *)&dst, (void *)&uninit_src, sizeof(uninit_src)); + kmsan_check_memory((void *)&dst, sizeof(dst)); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * Test case: ensure that memcpy() correctly copies uninitialized values between + * aligned `src` and unaligned `dst`. + * + * Copying aligned 4-byte value to an unaligned one leads to touching two + * aligned 4-byte values. This test case checks that KMSAN correctly reports an + * error on the first of the two values. + */ +static void test_memcpy_aligned_to_unaligned(struct kunit *test) +{ + EXPECTATION_UNINIT_VALUE_FN(expect, "test_memcpy_aligned_to_unaligned"); + volatile int uninit_src; + volatile char dst[8] = { 0 }; + + kunit_info( + test, + "memcpy()ing aligned uninit src to unaligned dst (UMR report)\n"); + memcpy((void *)&dst[1], (void *)&uninit_src, sizeof(uninit_src)); + kmsan_check_memory((void *)dst, 4); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * Test case: ensure that memcpy() correctly copies uninitialized values between + * aligned `src` and unaligned `dst`. + * + * Copying aligned 4-byte value to an unaligned one leads to touching two + * aligned 4-byte values. This test case checks that KMSAN correctly reports an + * error on the second of the two values. + */ +static void test_memcpy_aligned_to_unaligned2(struct kunit *test) +{ + EXPECTATION_UNINIT_VALUE_FN(expect, + "test_memcpy_aligned_to_unaligned2"); + volatile int uninit_src; + volatile char dst[8] = { 0 }; + + kunit_info( + test, + "memcpy()ing aligned uninit src to unaligned dst - part 2 (UMR report)\n"); + memcpy((void *)&dst[1], (void *)&uninit_src, sizeof(uninit_src)); + kmsan_check_memory((void *)&dst[4], sizeof(uninit_src)); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static noinline void fibonacci(int *array, int size, int start) { + if (start < 2 || (start == size)) + return; + array[start] = array[start - 1] + array[start - 2]; + fibonacci(array, size, start + 1); +} + +static void test_long_origin_chain(struct kunit *test) +{ + EXPECTATION_UNINIT_VALUE_FN(expect, + "test_long_origin_chain"); + /* (KMSAN_MAX_ORIGIN_DEPTH * 2) recursive calls to fibonacci(). */ + volatile int accum[KMSAN_MAX_ORIGIN_DEPTH * 2 + 2]; + int last = ARRAY_SIZE(accum) - 1; + + kunit_info( + test, + "origin chain exceeding KMSAN_MAX_ORIGIN_DEPTH (UMR report)\n"); + /* + * We do not set accum[1] to 0, so the uninitializedness will be carried + * over to accum[2..last]. + */ + accum[0] = 1; + fibonacci((int *)accum, ARRAY_SIZE(accum), 2); + kmsan_check_memory((void *)&accum[last], sizeof(int)); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static struct kunit_case kmsan_test_cases[] = { + KUNIT_CASE(test_uninit_kmalloc), + KUNIT_CASE(test_init_kmalloc), + KUNIT_CASE(test_init_kzalloc), + KUNIT_CASE(test_uninit_stack_var), + KUNIT_CASE(test_init_stack_var), + KUNIT_CASE(test_params), + KUNIT_CASE(test_uninit_multiple_params), + KUNIT_CASE(test_uninit_kmsan_check_memory), + KUNIT_CASE(test_init_kmsan_vmap_vunmap), + KUNIT_CASE(test_init_vmalloc), + KUNIT_CASE(test_uaf), + KUNIT_CASE(test_percpu_propagate), + KUNIT_CASE(test_printk), + KUNIT_CASE(test_memcpy_aligned_to_aligned), + KUNIT_CASE(test_memcpy_aligned_to_unaligned), + KUNIT_CASE(test_memcpy_aligned_to_unaligned2), + KUNIT_CASE(test_long_origin_chain), + {}, +}; + +/* ===== End test cases ===== */ + +static int test_init(struct kunit *test) +{ + unsigned long flags; + + spin_lock_irqsave(&observed.lock, flags); + observed.header[0] = '\0'; + observed.ignore = false; + observed.available = false; + spin_unlock_irqrestore(&observed.lock, flags); + + return 0; +} + +static void test_exit(struct kunit *test) +{ +} + +static void register_tracepoints(struct tracepoint *tp, void *ignore) +{ + check_trace_callback_type_console(probe_console); + if (!strcmp(tp->name, "console")) + WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); +} + +static void unregister_tracepoints(struct tracepoint *tp, void *ignore) +{ + if (!strcmp(tp->name, "console")) + tracepoint_probe_unregister(tp, probe_console, NULL); +} + +static int kmsan_suite_init(struct kunit_suite *suite) +{ + /* + * Because we want to be able to build the test as a module, we need to + * iterate through all known tracepoints, since the static registration + * won't work here. + */ + for_each_kernel_tracepoint(register_tracepoints, NULL); + return 0; +} + +static void kmsan_suite_exit(struct kunit_suite *suite) +{ + for_each_kernel_tracepoint(unregister_tracepoints, NULL); + tracepoint_synchronize_unregister(); +} + +static struct kunit_suite kmsan_test_suite = { + .name = "kmsan", + .test_cases = kmsan_test_cases, + .init = test_init, + .exit = test_exit, + .suite_init = kmsan_suite_init, + .suite_exit = kmsan_suite_exit, +}; +kunit_test_suites(&kmsan_test_suite); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Alexander Potapenko <glider@google.com>"); diff --git a/mm/kmsan/report.c b/mm/kmsan/report.c new file mode 100644 index 000000000..02736ec75 --- /dev/null +++ b/mm/kmsan/report.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KMSAN error reporting routines. + * + * Copyright (C) 2019-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#include <linux/console.h> +#include <linux/moduleparam.h> +#include <linux/stackdepot.h> +#include <linux/stacktrace.h> +#include <linux/uaccess.h> + +#include "kmsan.h" + +static DEFINE_RAW_SPINLOCK(kmsan_report_lock); +#define DESCR_SIZE 128 +/* Protected by kmsan_report_lock */ +static char report_local_descr[DESCR_SIZE]; +int panic_on_kmsan __read_mostly; + +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "kmsan." +module_param_named(panic, panic_on_kmsan, int, 0); + +/* + * Skip internal KMSAN frames. + */ +static int get_stack_skipnr(const unsigned long stack_entries[], + int num_entries) +{ + int len, skip; + char buf[64]; + + for (skip = 0; skip < num_entries; ++skip) { + len = scnprintf(buf, sizeof(buf), "%ps", + (void *)stack_entries[skip]); + + /* Never show __msan_* or kmsan_* functions. */ + if ((strnstr(buf, "__msan_", len) == buf) || + (strnstr(buf, "kmsan_", len) == buf)) + continue; + + /* + * No match for runtime functions -- @skip entries to skip to + * get to first frame of interest. + */ + break; + } + + return skip; +} + +/* + * Currently the descriptions of locals generated by Clang look as follows: + * ----local_name@function_name + * We want to print only the name of the local, as other information in that + * description can be confusing. + * The meaningful part of the description is copied to a global buffer to avoid + * allocating memory. + */ +static char *pretty_descr(char *descr) +{ + int pos = 0, len = strlen(descr); + + for (int i = 0; i < len; i++) { + if (descr[i] == '@') + break; + if (descr[i] == '-') + continue; + report_local_descr[pos] = descr[i]; + if (pos + 1 == DESCR_SIZE) + break; + pos++; + } + report_local_descr[pos] = 0; + return report_local_descr; +} + +void kmsan_print_origin(depot_stack_handle_t origin) +{ + unsigned long *entries = NULL, *chained_entries = NULL; + unsigned int nr_entries, chained_nr_entries, skipnr; + void *pc1 = NULL, *pc2 = NULL; + depot_stack_handle_t head; + unsigned long magic; + char *descr = NULL; + unsigned int depth; + + if (!origin) + return; + + while (true) { + nr_entries = stack_depot_fetch(origin, &entries); + depth = kmsan_depth_from_eb(stack_depot_get_extra_bits(origin)); + magic = nr_entries ? entries[0] : 0; + if ((nr_entries == 4) && (magic == KMSAN_ALLOCA_MAGIC_ORIGIN)) { + descr = (char *)entries[1]; + pc1 = (void *)entries[2]; + pc2 = (void *)entries[3]; + pr_err("Local variable %s created at:\n", + pretty_descr(descr)); + if (pc1) + pr_err(" %pSb\n", pc1); + if (pc2) + pr_err(" %pSb\n", pc2); + break; + } + if ((nr_entries == 3) && (magic == KMSAN_CHAIN_MAGIC_ORIGIN)) { + /* + * Origin chains deeper than KMSAN_MAX_ORIGIN_DEPTH are + * not stored, so the output may be incomplete. + */ + if (depth == KMSAN_MAX_ORIGIN_DEPTH) + pr_err("<Zero or more stacks not recorded to save memory>\n\n"); + head = entries[1]; + origin = entries[2]; + pr_err("Uninit was stored to memory at:\n"); + chained_nr_entries = + stack_depot_fetch(head, &chained_entries); + kmsan_internal_unpoison_memory( + chained_entries, + chained_nr_entries * sizeof(*chained_entries), + /*checked*/ false); + skipnr = get_stack_skipnr(chained_entries, + chained_nr_entries); + stack_trace_print(chained_entries + skipnr, + chained_nr_entries - skipnr, 0); + pr_err("\n"); + continue; + } + pr_err("Uninit was created at:\n"); + if (nr_entries) { + skipnr = get_stack_skipnr(entries, nr_entries); + stack_trace_print(entries + skipnr, nr_entries - skipnr, + 0); + } else { + pr_err("(stack is not available)\n"); + } + break; + } +} + +void kmsan_report(depot_stack_handle_t origin, void *address, int size, + int off_first, int off_last, const void *user_addr, + enum kmsan_bug_reason reason) +{ + unsigned long stack_entries[KMSAN_STACK_DEPTH]; + int num_stack_entries, skipnr; + char *bug_type = NULL; + unsigned long ua_flags; + bool is_uaf; + + if (!kmsan_enabled) + return; + if (!current->kmsan_ctx.allow_reporting) + return; + if (!origin) + return; + + current->kmsan_ctx.allow_reporting = false; + ua_flags = user_access_save(); + raw_spin_lock(&kmsan_report_lock); + pr_err("=====================================================\n"); + is_uaf = kmsan_uaf_from_eb(stack_depot_get_extra_bits(origin)); + switch (reason) { + case REASON_ANY: + bug_type = is_uaf ? "use-after-free" : "uninit-value"; + break; + case REASON_COPY_TO_USER: + bug_type = is_uaf ? "kernel-infoleak-after-free" : + "kernel-infoleak"; + break; + case REASON_SUBMIT_URB: + bug_type = is_uaf ? "kernel-usb-infoleak-after-free" : + "kernel-usb-infoleak"; + break; + } + + num_stack_entries = + stack_trace_save(stack_entries, KMSAN_STACK_DEPTH, 1); + skipnr = get_stack_skipnr(stack_entries, num_stack_entries); + + pr_err("BUG: KMSAN: %s in %pSb\n", bug_type, + (void *)stack_entries[skipnr]); + stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr, + 0); + pr_err("\n"); + + kmsan_print_origin(origin); + + if (size) { + pr_err("\n"); + if (off_first == off_last) + pr_err("Byte %d of %d is uninitialized\n", off_first, + size); + else + pr_err("Bytes %d-%d of %d are uninitialized\n", + off_first, off_last, size); + } + if (address) + pr_err("Memory access of size %d starts at %px\n", size, + address); + if (user_addr && reason == REASON_COPY_TO_USER) + pr_err("Data copied to user address %px\n", user_addr); + pr_err("\n"); + dump_stack_print_info(KERN_ERR); + pr_err("=====================================================\n"); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + raw_spin_unlock(&kmsan_report_lock); + if (panic_on_kmsan) + panic("kmsan.panic set ...\n"); + user_access_restore(ua_flags); + current->kmsan_ctx.allow_reporting = true; +} diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c new file mode 100644 index 000000000..b8bb95eea --- /dev/null +++ b/mm/kmsan/shadow.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KMSAN shadow implementation. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#include <asm/kmsan.h> +#include <asm/tlbflush.h> +#include <linux/cacheflush.h> +#include <linux/memblock.h> +#include <linux/mm_types.h> +#include <linux/slab.h> +#include <linux/smp.h> +#include <linux/stddef.h> + +#include "../internal.h" +#include "kmsan.h" + +#define shadow_page_for(page) ((page)->kmsan_shadow) + +#define origin_page_for(page) ((page)->kmsan_origin) + +static void *shadow_ptr_for(struct page *page) +{ + return page_address(shadow_page_for(page)); +} + +static void *origin_ptr_for(struct page *page) +{ + return page_address(origin_page_for(page)); +} + +static bool page_has_metadata(struct page *page) +{ + return shadow_page_for(page) && origin_page_for(page); +} + +static void set_no_shadow_origin_page(struct page *page) +{ + shadow_page_for(page) = NULL; + origin_page_for(page) = NULL; +} + +/* + * Dummy load and store pages to be used when the real metadata is unavailable. + * There are separate pages for loads and stores, so that every load returns a + * zero, and every store doesn't affect other loads. + */ +static char dummy_load_page[PAGE_SIZE] __aligned(PAGE_SIZE); +static char dummy_store_page[PAGE_SIZE] __aligned(PAGE_SIZE); + +static unsigned long vmalloc_meta(void *addr, bool is_origin) +{ + unsigned long addr64 = (unsigned long)addr, off; + + KMSAN_WARN_ON(is_origin && !IS_ALIGNED(addr64, KMSAN_ORIGIN_SIZE)); + if (kmsan_internal_is_vmalloc_addr(addr)) { + off = addr64 - VMALLOC_START; + return off + (is_origin ? KMSAN_VMALLOC_ORIGIN_START : + KMSAN_VMALLOC_SHADOW_START); + } + if (kmsan_internal_is_module_addr(addr)) { + off = addr64 - MODULES_VADDR; + return off + (is_origin ? KMSAN_MODULES_ORIGIN_START : + KMSAN_MODULES_SHADOW_START); + } + return 0; +} + +static struct page *virt_to_page_or_null(void *vaddr) +{ + if (kmsan_virt_addr_valid(vaddr)) + return virt_to_page(vaddr); + else + return NULL; +} + +struct shadow_origin_ptr kmsan_get_shadow_origin_ptr(void *address, u64 size, + bool store) +{ + struct shadow_origin_ptr ret; + void *shadow; + + /* + * Even if we redirect this memory access to the dummy page, it will + * go out of bounds. + */ + KMSAN_WARN_ON(size > PAGE_SIZE); + + if (!kmsan_enabled) + goto return_dummy; + + KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(address, size)); + shadow = kmsan_get_metadata(address, KMSAN_META_SHADOW); + if (!shadow) + goto return_dummy; + + ret.shadow = shadow; + ret.origin = kmsan_get_metadata(address, KMSAN_META_ORIGIN); + return ret; + +return_dummy: + if (store) { + /* Ignore this store. */ + ret.shadow = dummy_store_page; + ret.origin = dummy_store_page; + } else { + /* This load will return zero. */ + ret.shadow = dummy_load_page; + ret.origin = dummy_load_page; + } + return ret; +} + +/* + * Obtain the shadow or origin pointer for the given address, or NULL if there's + * none. The caller must check the return value for being non-NULL if needed. + * The return value of this function should not depend on whether we're in the + * runtime or not. + */ +void *kmsan_get_metadata(void *address, bool is_origin) +{ + u64 addr = (u64)address, pad, off; + struct page *page; + void *ret; + + if (is_origin && !IS_ALIGNED(addr, KMSAN_ORIGIN_SIZE)) { + pad = addr % KMSAN_ORIGIN_SIZE; + addr -= pad; + } + address = (void *)addr; + if (kmsan_internal_is_vmalloc_addr(address) || + kmsan_internal_is_module_addr(address)) + return (void *)vmalloc_meta(address, is_origin); + + ret = arch_kmsan_get_meta_or_null(address, is_origin); + if (ret) + return ret; + + page = virt_to_page_or_null(address); + if (!page) + return NULL; + if (!page_has_metadata(page)) + return NULL; + off = addr % PAGE_SIZE; + + return (is_origin ? origin_ptr_for(page) : shadow_ptr_for(page)) + off; +} + +void kmsan_copy_page_meta(struct page *dst, struct page *src) +{ + if (!kmsan_enabled || kmsan_in_runtime()) + return; + if (!dst || !page_has_metadata(dst)) + return; + if (!src || !page_has_metadata(src)) { + kmsan_internal_unpoison_memory(page_address(dst), PAGE_SIZE, + /*checked*/ false); + return; + } + + kmsan_enter_runtime(); + __memcpy(shadow_ptr_for(dst), shadow_ptr_for(src), PAGE_SIZE); + __memcpy(origin_ptr_for(dst), origin_ptr_for(src), PAGE_SIZE); + kmsan_leave_runtime(); +} +EXPORT_SYMBOL(kmsan_copy_page_meta); + +void kmsan_alloc_page(struct page *page, unsigned int order, gfp_t flags) +{ + bool initialized = (flags & __GFP_ZERO) || !kmsan_enabled; + struct page *shadow, *origin; + depot_stack_handle_t handle; + int pages = 1 << order; + + if (!page) + return; + + shadow = shadow_page_for(page); + origin = origin_page_for(page); + + if (initialized) { + __memset(page_address(shadow), 0, PAGE_SIZE * pages); + __memset(page_address(origin), 0, PAGE_SIZE * pages); + return; + } + + /* Zero pages allocated by the runtime should also be initialized. */ + if (kmsan_in_runtime()) + return; + + __memset(page_address(shadow), -1, PAGE_SIZE * pages); + kmsan_enter_runtime(); + handle = kmsan_save_stack_with_flags(flags, /*extra_bits*/ 0); + kmsan_leave_runtime(); + /* + * Addresses are page-aligned, pages are contiguous, so it's ok + * to just fill the origin pages with @handle. + */ + for (int i = 0; i < PAGE_SIZE * pages / sizeof(handle); i++) + ((depot_stack_handle_t *)page_address(origin))[i] = handle; +} + +void kmsan_free_page(struct page *page, unsigned int order) +{ + if (!kmsan_enabled || kmsan_in_runtime()) + return; + kmsan_enter_runtime(); + kmsan_internal_poison_memory(page_address(page), + PAGE_SIZE << compound_order(page), + GFP_KERNEL, + KMSAN_POISON_CHECK | KMSAN_POISON_FREE); + kmsan_leave_runtime(); +} + +int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift) +{ + unsigned long shadow_start, origin_start, shadow_end, origin_end; + struct page **s_pages, **o_pages; + int nr, mapped, err = 0; + + if (!kmsan_enabled) + return 0; + + shadow_start = vmalloc_meta((void *)start, KMSAN_META_SHADOW); + shadow_end = vmalloc_meta((void *)end, KMSAN_META_SHADOW); + if (!shadow_start) + return 0; + + nr = (end - start) / PAGE_SIZE; + s_pages = kcalloc(nr, sizeof(*s_pages), GFP_KERNEL); + o_pages = kcalloc(nr, sizeof(*o_pages), GFP_KERNEL); + if (!s_pages || !o_pages) { + err = -ENOMEM; + goto ret; + } + for (int i = 0; i < nr; i++) { + s_pages[i] = shadow_page_for(pages[i]); + o_pages[i] = origin_page_for(pages[i]); + } + prot = __pgprot(pgprot_val(prot) | _PAGE_NX); + prot = PAGE_KERNEL; + + origin_start = vmalloc_meta((void *)start, KMSAN_META_ORIGIN); + origin_end = vmalloc_meta((void *)end, KMSAN_META_ORIGIN); + kmsan_enter_runtime(); + mapped = __vmap_pages_range_noflush(shadow_start, shadow_end, prot, + s_pages, page_shift); + if (mapped) { + err = mapped; + goto ret; + } + mapped = __vmap_pages_range_noflush(origin_start, origin_end, prot, + o_pages, page_shift); + if (mapped) { + err = mapped; + goto ret; + } + kmsan_leave_runtime(); + flush_tlb_kernel_range(shadow_start, shadow_end); + flush_tlb_kernel_range(origin_start, origin_end); + flush_cache_vmap(shadow_start, shadow_end); + flush_cache_vmap(origin_start, origin_end); + +ret: + kfree(s_pages); + kfree(o_pages); + return err; +} + +/* Allocate metadata for pages allocated at boot time. */ +void __init kmsan_init_alloc_meta_for_range(void *start, void *end) +{ + struct page *shadow_p, *origin_p; + void *shadow, *origin; + struct page *page; + u64 size; + + start = (void *)ALIGN_DOWN((u64)start, PAGE_SIZE); + size = ALIGN((u64)end - (u64)start, PAGE_SIZE); + shadow = memblock_alloc(size, PAGE_SIZE); + origin = memblock_alloc(size, PAGE_SIZE); + for (u64 addr = 0; addr < size; addr += PAGE_SIZE) { + page = virt_to_page_or_null((char *)start + addr); + shadow_p = virt_to_page_or_null((char *)shadow + addr); + set_no_shadow_origin_page(shadow_p); + shadow_page_for(page) = shadow_p; + origin_p = virt_to_page_or_null((char *)origin + addr); + set_no_shadow_origin_page(origin_p); + origin_page_for(page) = origin_p; + } +} + +void kmsan_setup_meta(struct page *page, struct page *shadow, + struct page *origin, int order) +{ + for (int i = 0; i < (1 << order); i++) { + set_no_shadow_origin_page(&shadow[i]); + set_no_shadow_origin_page(&origin[i]); + shadow_page_for(&page[i]) = &shadow[i]; + origin_page_for(&page[i]) = &origin[i]; + } +} |