summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Makefile20
-rw-r--r--mm/dmapool.c10
-rw-r--r--mm/huge_memory.c3
-rw-r--r--mm/kasan/Makefile3
-rw-r--r--mm/kasan/kasan.c280
-rw-r--r--mm/kasan/kasan.h51
-rw-r--r--mm/kasan/quarantine.c328
-rw-r--r--mm/kasan/report.c262
-rw-r--r--mm/kmemcheck.c3
-rw-r--r--mm/kmemleak.c18
-rw-r--r--mm/madvise.c2
-rw-r--r--mm/memblock.c28
-rw-r--r--mm/memory_hotplug.c3
-rw-r--r--mm/mempolicy.c7
-rw-r--r--mm/mempool.c24
-rw-r--r--mm/mlock.c2
-rw-r--r--mm/mmap.c55
-rw-r--r--mm/mprotect.c2
-rw-r--r--mm/oom_kill.c3
-rw-r--r--mm/page_alloc.c69
-rw-r--r--mm/percpu.c4
-rw-r--r--mm/shmem.c13
-rw-r--r--mm/slab.c367
-rw-r--r--mm/slab.h2
-rw-r--r--mm/slab_common.c20
-rw-r--r--mm/slob.c2
-rw-r--r--mm/slub.c239
-rw-r--r--mm/sparse-vmemmap.c8
-rw-r--r--mm/sparse.c8
-rw-r--r--mm/swapfile.c3
-rw-r--r--mm/usercopy.c278
-rw-r--r--mm/util.c1
-rw-r--r--mm/vmalloc.c4
33 files changed, 1732 insertions, 390 deletions
diff --git a/mm/Makefile b/mm/Makefile
index 2ed43191fc3b..ec91e951da28 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -3,8 +3,27 @@
#
KASAN_SANITIZE_slab_common.o := n
+KASAN_SANITIZE_slab.o := n
KASAN_SANITIZE_slub.o := n
+# Since __builtin_frame_address does work as used, disable the warning.
+CFLAGS_usercopy.o += $(call cc-disable-warning, frame-address)
+
+# These files are disabled because they produce non-interesting and/or
+# flaky coverage that is not a function of syscall inputs. E.g. slab is out of
+# free pages, or a task is migrated between nodes.
+KCOV_INSTRUMENT_slab_common.o := n
+KCOV_INSTRUMENT_slob.o := n
+KCOV_INSTRUMENT_slab.o := n
+KCOV_INSTRUMENT_slub.o := n
+KCOV_INSTRUMENT_page_alloc.o := n
+KCOV_INSTRUMENT_debug-pagealloc.o := n
+KCOV_INSTRUMENT_kmemleak.o := n
+KCOV_INSTRUMENT_kmemcheck.o := n
+KCOV_INSTRUMENT_memcontrol.o := n
+KCOV_INSTRUMENT_mmzone.o := n
+KCOV_INSTRUMENT_vmstat.o := n
+
mmu-y := nommu.o
mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \
mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
@@ -81,3 +100,4 @@ obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o
obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o
+obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 57312b5d6e12..2821500e8123 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -452,13 +452,11 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
}
spin_unlock_irqrestore(&pool->lock, flags);
if (pool->dev)
- dev_err(pool->dev, "dma_pool_free %s, dma %Lx "
- "already free\n", pool->name,
- (unsigned long long)dma);
+ dev_err(pool->dev, "dma_pool_free %s, dma %Lx already free\n",
+ pool->name, (unsigned long long)dma);
else
- printk(KERN_ERR "dma_pool_free %s, dma %Lx "
- "already free\n", pool->name,
- (unsigned long long)dma);
+ printk(KERN_ERR "dma_pool_free %s, dma %Lx already free\n",
+ pool->name, (unsigned long long)dma);
return;
}
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6404e4fcb4ed..8e035439ec2c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -135,8 +135,7 @@ static void set_recommended_min_free_kbytes(void)
if (recommended_min > min_free_kbytes) {
if (user_min_free_kbytes >= 0)
- pr_info("raising min_free_kbytes from %d to %lu "
- "to help transparent hugepage allocations\n",
+ pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n",
min_free_kbytes, recommended_min);
min_free_kbytes = recommended_min;
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index 64710148941e..e1100433cefe 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -1,8 +1,9 @@
KASAN_SANITIZE := n
+KCOV_INSTRUMENT := n
CFLAGS_REMOVE_kasan.o = -pg
# Function splitter causes unnecessary splits in __asan_load1/__asan_store1
# see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
CFLAGS_kasan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
-obj-y := kasan.o report.o kasan_init.o
+obj-y := kasan.o report.o kasan_init.o quarantine.o
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 410b0fcb0c73..2bfdb3c23e72 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -17,9 +17,12 @@
#define DISABLE_BRANCH_PROFILING
#include <linux/export.h>
+#include <linux/interrupt.h>
#include <linux/init.h>
+#include <linux/kasan.h>
#include <linux/kernel.h>
#include <linux/kmemleak.h>
+#include <linux/linkage.h>
#include <linux/memblock.h>
#include <linux/memory.h>
#include <linux/mm.h>
@@ -31,11 +34,21 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/vmalloc.h>
-#include <linux/kasan.h>
+#include <linux/bug.h>
#include "kasan.h"
#include "../slab.h"
+void kasan_enable_current(void)
+{
+ current->kasan_depth++;
+}
+
+void kasan_disable_current(void)
+{
+ current->kasan_depth--;
+}
+
/*
* Poisons the shadow memory for 'size' bytes starting from 'addr'.
* Memory addresses should be aligned to KASAN_SHADOW_SCALE_SIZE.
@@ -60,6 +73,47 @@ void kasan_unpoison_shadow(const void *address, size_t size)
}
}
+static void __kasan_unpoison_stack(struct task_struct *task, const void *sp)
+{
+ void *base = task_stack_page(task);
+ size_t size = sp - base;
+
+ kasan_unpoison_shadow(base, size);
+}
+
+/* Unpoison the entire stack for a task. */
+void kasan_unpoison_task_stack(struct task_struct *task)
+{
+ __kasan_unpoison_stack(task, task_stack_page(task) + THREAD_SIZE);
+}
+
+/* Unpoison the stack for the current task beyond a watermark sp value. */
+asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
+{
+ /*
+ * Calculate the task stack base address. Avoid using 'current'
+ * because this function is called by early resume code which hasn't
+ * yet set up the percpu register (%gs).
+ */
+ void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1));
+
+ kasan_unpoison_shadow(base, watermark - base);
+}
+
+/*
+ * Clear all poison for the region between the current SP and a provided
+ * watermark value, as is sometimes required prior to hand-crafted asm function
+ * returns in the middle of functions.
+ */
+void kasan_unpoison_stack_above_sp_to(const void *watermark)
+{
+ const void *sp = __builtin_frame_address(0);
+ size_t size = watermark - sp;
+
+ if (WARN_ON(sp > watermark))
+ return;
+ kasan_unpoison_shadow(sp, size);
+}
/*
* All functions below always inlined so compiler could
@@ -330,6 +384,80 @@ void kasan_free_pages(struct page *page, unsigned int order)
KASAN_FREE_PAGE);
}
+/*
+ * Adaptive redzone policy taken from the userspace AddressSanitizer runtime.
+ * For larger allocations larger redzones are used.
+ */
+static size_t optimal_redzone(size_t object_size)
+{
+ int rz =
+ object_size <= 64 - 16 ? 16 :
+ object_size <= 128 - 32 ? 32 :
+ object_size <= 512 - 64 ? 64 :
+ object_size <= 4096 - 128 ? 128 :
+ object_size <= (1 << 14) - 256 ? 256 :
+ object_size <= (1 << 15) - 512 ? 512 :
+ object_size <= (1 << 16) - 1024 ? 1024 : 2048;
+ return rz;
+}
+
+void kasan_cache_create(struct kmem_cache *cache, size_t *size,
+ unsigned long *flags)
+{
+ int redzone_adjust;
+ int orig_size = *size;
+
+ /* Add alloc meta. */
+ cache->kasan_info.alloc_meta_offset = *size;
+ *size += sizeof(struct kasan_alloc_meta);
+
+ /* Add free meta. */
+ if (cache->flags & SLAB_DESTROY_BY_RCU || cache->ctor ||
+ cache->object_size < sizeof(struct kasan_free_meta)) {
+ cache->kasan_info.free_meta_offset = *size;
+ *size += sizeof(struct kasan_free_meta);
+ }
+ redzone_adjust = optimal_redzone(cache->object_size) -
+ (*size - cache->object_size);
+
+ if (redzone_adjust > 0)
+ *size += redzone_adjust;
+
+ *size = min(KMALLOC_MAX_SIZE, max(*size, cache->object_size +
+ optimal_redzone(cache->object_size)));
+
+ /*
+ * If the metadata doesn't fit, don't enable KASAN at all.
+ */
+ if (*size <= cache->kasan_info.alloc_meta_offset ||
+ *size <= cache->kasan_info.free_meta_offset) {
+ cache->kasan_info.alloc_meta_offset = 0;
+ cache->kasan_info.free_meta_offset = 0;
+ *size = orig_size;
+ return;
+ }
+
+ *flags |= SLAB_KASAN;
+}
+
+void kasan_cache_shrink(struct kmem_cache *cache)
+{
+ quarantine_remove_cache(cache);
+}
+
+void kasan_cache_shutdown(struct kmem_cache *cache)
+{
+ quarantine_remove_cache(cache);
+}
+
+size_t kasan_metadata_size(struct kmem_cache *cache)
+{
+ return (cache->kasan_info.alloc_meta_offset ?
+ sizeof(struct kasan_alloc_meta) : 0) +
+ (cache->kasan_info.free_meta_offset ?
+ sizeof(struct kasan_free_meta) : 0);
+}
+
void kasan_poison_slab(struct page *page)
{
kasan_poison_shadow(page_address(page),
@@ -349,12 +477,84 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object)
KASAN_KMALLOC_REDZONE);
}
-void kasan_slab_alloc(struct kmem_cache *cache, void *object)
+static inline int in_irqentry_text(unsigned long ptr)
+{
+ return (ptr >= (unsigned long)&__irqentry_text_start &&
+ ptr < (unsigned long)&__irqentry_text_end) ||
+ (ptr >= (unsigned long)&__softirqentry_text_start &&
+ ptr < (unsigned long)&__softirqentry_text_end);
+}
+
+static inline void filter_irq_stacks(struct stack_trace *trace)
+{
+ int i;
+
+ if (!trace->nr_entries)
+ return;
+ for (i = 0; i < trace->nr_entries; i++)
+ if (in_irqentry_text(trace->entries[i])) {
+ /* Include the irqentry function into the stack. */
+ trace->nr_entries = i + 1;
+ break;
+ }
+}
+
+static inline depot_stack_handle_t save_stack(gfp_t flags)
+{
+ unsigned long entries[KASAN_STACK_DEPTH];
+ struct stack_trace trace = {
+ .nr_entries = 0,
+ .entries = entries,
+ .max_entries = KASAN_STACK_DEPTH,
+ .skip = 0
+ };
+
+ save_stack_trace(&trace);
+ filter_irq_stacks(&trace);
+ if (trace.nr_entries != 0 &&
+ trace.entries[trace.nr_entries-1] == ULONG_MAX)
+ trace.nr_entries--;
+
+ return depot_save_stack(&trace, flags);
+}
+
+static inline void set_track(struct kasan_track *track, gfp_t flags)
+{
+ track->pid = current->pid;
+ track->stack = save_stack(flags);
+}
+
+struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
+ const void *object)
+{
+ BUILD_BUG_ON(sizeof(struct kasan_alloc_meta) > 32);
+ return (void *)object + cache->kasan_info.alloc_meta_offset;
+}
+
+struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
+ const void *object)
+{
+ BUILD_BUG_ON(sizeof(struct kasan_free_meta) > 32);
+ return (void *)object + cache->kasan_info.free_meta_offset;
+}
+
+void kasan_init_slab_obj(struct kmem_cache *cache, const void *object)
+{
+ struct kasan_alloc_meta *alloc_info;
+
+ if (!(cache->flags & SLAB_KASAN))
+ return;
+
+ alloc_info = get_alloc_info(cache, object);
+ __memset(alloc_info, 0, sizeof(*alloc_info));
+}
+
+void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags)
{
- kasan_kmalloc(cache, object, cache->object_size);
+ kasan_kmalloc(cache, object, cache->object_size, flags);
}
-void kasan_slab_free(struct kmem_cache *cache, void *object)
+static void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
{
unsigned long size = cache->object_size;
unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
@@ -366,11 +566,40 @@ void kasan_slab_free(struct kmem_cache *cache, void *object)
kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE);
}
-void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size)
+bool kasan_slab_free(struct kmem_cache *cache, void *object)
+{
+ s8 shadow_byte;
+
+ /* RCU slabs could be legally used after free within the RCU period */
+ if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
+ return false;
+
+ shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object));
+ if (shadow_byte < 0 || shadow_byte >= KASAN_SHADOW_SCALE_SIZE) {
+ kasan_report_double_free(cache, object,
+ __builtin_return_address(1));
+ return true;
+ }
+
+ kasan_poison_slab_free(cache, object);
+
+ if (unlikely(!(cache->flags & SLAB_KASAN)))
+ return false;
+
+ set_track(&get_alloc_info(cache, object)->free_track, GFP_NOWAIT);
+ quarantine_put(get_free_info(cache, object), cache);
+ return true;
+}
+
+void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
+ gfp_t flags)
{
unsigned long redzone_start;
unsigned long redzone_end;
+ if (gfpflags_allow_blocking(flags))
+ quarantine_reduce();
+
if (unlikely(object == NULL))
return;
@@ -382,15 +611,21 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size)
kasan_unpoison_shadow(object, size);
kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
KASAN_KMALLOC_REDZONE);
+
+ if (cache->flags & SLAB_KASAN)
+ set_track(&get_alloc_info(cache, object)->alloc_track, flags);
}
EXPORT_SYMBOL(kasan_kmalloc);
-void kasan_kmalloc_large(const void *ptr, size_t size)
+void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags)
{
struct page *page;
unsigned long redzone_start;
unsigned long redzone_end;
+ if (gfpflags_allow_blocking(flags))
+ quarantine_reduce();
+
if (unlikely(ptr == NULL))
return;
@@ -404,7 +639,7 @@ void kasan_kmalloc_large(const void *ptr, size_t size)
KASAN_PAGE_REDZONE);
}
-void kasan_krealloc(const void *object, size_t size)
+void kasan_krealloc(const void *object, size_t size, gfp_t flags)
{
struct page *page;
@@ -414,12 +649,12 @@ void kasan_krealloc(const void *object, size_t size)
page = virt_to_head_page(object);
if (unlikely(!PageSlab(page)))
- kasan_kmalloc_large(object, size);
+ kasan_kmalloc_large(object, size, flags);
else
- kasan_kmalloc(page->slab_cache, object, size);
+ kasan_kmalloc(page->slab_cache, object, size, flags);
}
-void kasan_kfree(void *ptr)
+void kasan_poison_kfree(void *ptr)
{
struct page *page;
@@ -429,7 +664,7 @@ void kasan_kfree(void *ptr)
kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page),
KASAN_FREE_PAGE);
else
- kasan_slab_free(page->slab_cache, ptr);
+ kasan_poison_slab_free(page->slab_cache, ptr);
}
void kasan_kfree_large(const void *ptr)
@@ -548,6 +783,25 @@ EXPORT_SYMBOL(__asan_storeN_noabort);
void __asan_handle_no_return(void) {}
EXPORT_SYMBOL(__asan_handle_no_return);
+/* Emitted by compiler to poison large objects when they go out of scope. */
+void __asan_poison_stack_memory(const void *addr, size_t size)
+{
+ /*
+ * Addr is KASAN_SHADOW_SCALE_SIZE-aligned and the object is surrounded
+ * by redzones, so we simply round up size to simplify logic.
+ */
+ kasan_poison_shadow(addr, round_up(size, KASAN_SHADOW_SCALE_SIZE),
+ KASAN_USE_AFTER_SCOPE);
+}
+EXPORT_SYMBOL(__asan_poison_stack_memory);
+
+/* Emitted by compiler to unpoison large objects when they go into scope. */
+void __asan_unpoison_stack_memory(const void *addr, size_t size)
+{
+ kasan_unpoison_shadow(addr, size);
+}
+EXPORT_SYMBOL(__asan_unpoison_stack_memory);
+
#ifdef CONFIG_MEMORY_HOTPLUG
static int kasan_mem_notifier(struct notifier_block *nb,
unsigned long action, void *data)
@@ -557,8 +811,8 @@ static int kasan_mem_notifier(struct notifier_block *nb,
static int __init kasan_memhotplug_init(void)
{
- pr_err("WARNING: KASAN doesn't support memory hot-add\n");
- pr_err("Memory hot-add will be disabled\n");
+ pr_info("WARNING: KASAN doesn't support memory hot-add\n");
+ pr_info("Memory hot-add will be disabled\n");
hotplug_memory_notifier(kasan_mem_notifier, 0);
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 37ff0ab6a8ff..1229298cce64 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -2,6 +2,7 @@
#define __MM_KASAN_KASAN_H
#include <linux/kasan.h>
+#include <linux/stackdepot.h>
#define KASAN_SHADOW_SCALE_SIZE (1UL << KASAN_SHADOW_SCALE_SHIFT)
#define KASAN_SHADOW_MASK (KASAN_SHADOW_SCALE_SIZE - 1)
@@ -20,6 +21,7 @@
#define KASAN_STACK_MID 0xF2
#define KASAN_STACK_RIGHT 0xF3
#define KASAN_STACK_PARTIAL 0xF4
+#define KASAN_USE_AFTER_SCOPE 0xF8
/* Don't break randconfig/all*config builds */
#ifndef KASAN_ABI_VERSION
@@ -57,18 +59,57 @@ struct kasan_global {
#endif
};
+/**
+ * Structures to keep alloc and free tracks *
+ */
+
+#define KASAN_STACK_DEPTH 64
+
+struct kasan_track {
+ u32 pid;
+ depot_stack_handle_t stack;
+};
+
+struct kasan_alloc_meta {
+ struct kasan_track alloc_track;
+ struct kasan_track free_track;
+};
+
+struct qlist_node {
+ struct qlist_node *next;
+};
+struct kasan_free_meta {
+ /* This field is used while the object is in the quarantine.
+ * Otherwise it might be used for the allocator freelist.
+ */
+ struct qlist_node quarantine_link;
+};
+
+struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
+ const void *object);
+struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
+ const void *object);
+
static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
{
return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET)
<< KASAN_SHADOW_SCALE_SHIFT);
}
-static inline bool kasan_report_enabled(void)
-{
- return !current->kasan_depth;
-}
-
void kasan_report(unsigned long addr, size_t size,
bool is_write, unsigned long ip);
+void kasan_report_double_free(struct kmem_cache *cache, void *object,
+ void *ip);
+
+#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB)
+void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache);
+void quarantine_reduce(void);
+void quarantine_remove_cache(struct kmem_cache *cache);
+#else
+static inline void quarantine_put(struct kasan_free_meta *info,
+ struct kmem_cache *cache) { }
+static inline void quarantine_reduce(void) { }
+static inline void quarantine_remove_cache(struct kmem_cache *cache) { }
+#endif
#endif
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
new file mode 100644
index 000000000000..3a8ddf8baf7d
--- /dev/null
+++ b/mm/kasan/quarantine.c
@@ -0,0 +1,328 @@
+/*
+ * KASAN quarantine.
+ *
+ * Author: Alexander Potapenko <glider@google.com>
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * Based on code by Dmitry Chernenkov.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ */
+
+#include <linux/gfp.h>
+#include <linux/hash.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/percpu.h>
+#include <linux/printk.h>
+#include <linux/shrinker.h>
+#include <linux/slab.h>
+#include <linux/srcu.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "../slab.h"
+#include "kasan.h"
+
+/* Data structure and operations for quarantine queues. */
+
+/*
+ * Each queue is a signle-linked list, which also stores the total size of
+ * objects inside of it.
+ */
+struct qlist_head {
+ struct qlist_node *head;
+ struct qlist_node *tail;
+ size_t bytes;
+};
+
+#define QLIST_INIT { NULL, NULL, 0 }
+
+static bool qlist_empty(struct qlist_head *q)
+{
+ return !q->head;
+}
+
+static void qlist_init(struct qlist_head *q)
+{
+ q->head = q->tail = NULL;
+ q->bytes = 0;
+}
+
+static void qlist_put(struct qlist_head *q, struct qlist_node *qlink,
+ size_t size)
+{
+ if (unlikely(qlist_empty(q)))
+ q->head = qlink;
+ else
+ q->tail->next = qlink;
+ q->tail = qlink;
+ qlink->next = NULL;
+ q->bytes += size;
+}
+
+static void qlist_move_all(struct qlist_head *from, struct qlist_head *to)
+{
+ if (unlikely(qlist_empty(from)))
+ return;
+
+ if (qlist_empty(to)) {
+ *to = *from;
+ qlist_init(from);
+ return;
+ }
+
+ to->tail->next = from->head;
+ to->tail = from->tail;
+ to->bytes += from->bytes;
+
+ qlist_init(from);
+}
+
+#define QUARANTINE_PERCPU_SIZE (1 << 20)
+#define QUARANTINE_BATCHES \
+ (1024 > 4 * CONFIG_NR_CPUS ? 1024 : 4 * CONFIG_NR_CPUS)
+
+/*
+ * The object quarantine consists of per-cpu queues and a global queue,
+ * guarded by quarantine_lock.
+ */
+static DEFINE_PER_CPU(struct qlist_head, cpu_quarantine);
+
+/* Round-robin FIFO array of batches. */
+static struct qlist_head global_quarantine[QUARANTINE_BATCHES];
+static int quarantine_head;
+static int quarantine_tail;
+/* Total size of all objects in global_quarantine across all batches. */
+static unsigned long quarantine_size;
+static DEFINE_SPINLOCK(quarantine_lock);
+DEFINE_STATIC_SRCU(remove_cache_srcu);
+
+/* Maximum size of the global queue. */
+static unsigned long quarantine_max_size;
+
+/*
+ * Target size of a batch in global_quarantine.
+ * Usually equal to QUARANTINE_PERCPU_SIZE unless we have too much RAM.
+ */
+static unsigned long quarantine_batch_size;
+
+/*
+ * The fraction of physical memory the quarantine is allowed to occupy.
+ * Quarantine doesn't support memory shrinker with SLAB allocator, so we keep
+ * the ratio low to avoid OOM.
+ */
+#define QUARANTINE_FRACTION 32
+
+static struct kmem_cache *qlink_to_cache(struct qlist_node *qlink)
+{
+ return virt_to_head_page(qlink)->slab_cache;
+}
+
+static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache)
+{
+ struct kasan_free_meta *free_info =
+ container_of(qlink, struct kasan_free_meta,
+ quarantine_link);
+
+ return ((void *)free_info) - cache->kasan_info.free_meta_offset;
+}
+
+static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
+{
+ void *object = qlink_to_object(qlink, cache);
+ unsigned long flags;
+
+ if (IS_ENABLED(CONFIG_SLAB))
+ local_irq_save(flags);
+
+ ___cache_free(cache, object, _THIS_IP_);
+
+ if (IS_ENABLED(CONFIG_SLAB))
+ local_irq_restore(flags);
+}
+
+static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache)
+{
+ struct qlist_node *qlink;
+
+ if (unlikely(qlist_empty(q)))
+ return;
+
+ qlink = q->head;
+ while (qlink) {
+ struct kmem_cache *obj_cache =
+ cache ? cache : qlink_to_cache(qlink);
+ struct qlist_node *next = qlink->next;
+
+ qlink_free(qlink, obj_cache);
+ qlink = next;
+ }
+ qlist_init(q);
+}
+
+void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
+{
+ unsigned long flags;
+ struct qlist_head *q;
+ struct qlist_head temp = QLIST_INIT;
+
+ /*
+ * Note: irq must be disabled until after we move the batch to the
+ * global quarantine. Otherwise quarantine_remove_cache() can miss
+ * some objects belonging to the cache if they are in our local temp
+ * list. quarantine_remove_cache() executes on_each_cpu() at the
+ * beginning which ensures that it either sees the objects in per-cpu
+ * lists or in the global quarantine.
+ */
+ local_irq_save(flags);
+
+ q = this_cpu_ptr(&cpu_quarantine);
+ qlist_put(q, &info->quarantine_link, cache->size);
+ if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
+ qlist_move_all(q, &temp);
+
+ spin_lock(&quarantine_lock);
+ WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes);
+ qlist_move_all(&temp, &global_quarantine[quarantine_tail]);
+ if (global_quarantine[quarantine_tail].bytes >=
+ READ_ONCE(quarantine_batch_size)) {
+ int new_tail;
+
+ new_tail = quarantine_tail + 1;
+ if (new_tail == QUARANTINE_BATCHES)
+ new_tail = 0;
+ if (new_tail != quarantine_head)
+ quarantine_tail = new_tail;
+ }
+ spin_unlock(&quarantine_lock);
+ }
+
+ local_irq_restore(flags);
+}
+
+void quarantine_reduce(void)
+{
+ size_t total_size, new_quarantine_size, percpu_quarantines;
+ unsigned long flags;
+ int srcu_idx;
+ struct qlist_head to_free = QLIST_INIT;
+
+ if (likely(READ_ONCE(quarantine_size) <=
+ READ_ONCE(quarantine_max_size)))
+ return;
+
+ /*
+ * srcu critical section ensures that quarantine_remove_cache()
+ * will not miss objects belonging to the cache while they are in our
+ * local to_free list. srcu is chosen because (1) it gives us private
+ * grace period domain that does not interfere with anything else,
+ * and (2) it allows synchronize_srcu() to return without waiting
+ * if there are no pending read critical sections (which is the
+ * expected case).
+ */
+ srcu_idx = srcu_read_lock(&remove_cache_srcu);
+ spin_lock_irqsave(&quarantine_lock, flags);
+
+ /*
+ * Update quarantine size in case of hotplug. Allocate a fraction of
+ * the installed memory to quarantine minus per-cpu queue limits.
+ */
+ total_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
+ QUARANTINE_FRACTION;
+ percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
+ new_quarantine_size = (total_size < percpu_quarantines) ?
+ 0 : total_size - percpu_quarantines;
+ WRITE_ONCE(quarantine_max_size, new_quarantine_size);
+ /* Aim at consuming at most 1/2 of slots in quarantine. */
+ WRITE_ONCE(quarantine_batch_size, max((size_t)QUARANTINE_PERCPU_SIZE,
+ 2 * total_size / QUARANTINE_BATCHES));
+
+ if (likely(quarantine_size > quarantine_max_size)) {
+ qlist_move_all(&global_quarantine[quarantine_head], &to_free);
+ WRITE_ONCE(quarantine_size, quarantine_size - to_free.bytes);
+ quarantine_head++;
+ if (quarantine_head == QUARANTINE_BATCHES)
+ quarantine_head = 0;
+ }
+
+ spin_unlock_irqrestore(&quarantine_lock, flags);
+
+ qlist_free_all(&to_free, NULL);
+ srcu_read_unlock(&remove_cache_srcu, srcu_idx);
+}
+
+static void qlist_move_cache(struct qlist_head *from,
+ struct qlist_head *to,
+ struct kmem_cache *cache)
+{
+ struct qlist_node *curr;
+
+ if (unlikely(qlist_empty(from)))
+ return;
+
+ curr = from->head;
+ qlist_init(from);
+ while (curr) {
+ struct qlist_node *next = curr->next;
+ struct kmem_cache *obj_cache = qlink_to_cache(curr);
+
+ if (obj_cache == cache)
+ qlist_put(to, curr, obj_cache->size);
+ else
+ qlist_put(from, curr, obj_cache->size);
+
+ curr = next;
+ }
+}
+
+static void per_cpu_remove_cache(void *arg)
+{
+ struct kmem_cache *cache = arg;
+ struct qlist_head to_free = QLIST_INIT;
+ struct qlist_head *q;
+
+ q = this_cpu_ptr(&cpu_quarantine);
+ qlist_move_cache(q, &to_free, cache);
+ qlist_free_all(&to_free, cache);
+}
+
+/* Free all quarantined objects belonging to cache. */
+void quarantine_remove_cache(struct kmem_cache *cache)
+{
+ unsigned long flags, i;
+ struct qlist_head to_free = QLIST_INIT;
+
+ /*
+ * Must be careful to not miss any objects that are being moved from
+ * per-cpu list to the global quarantine in quarantine_put(),
+ * nor objects being freed in quarantine_reduce(). on_each_cpu()
+ * achieves the first goal, while synchronize_srcu() achieves the
+ * second.
+ */
+ on_each_cpu(per_cpu_remove_cache, cache, 1);
+
+ spin_lock_irqsave(&quarantine_lock, flags);
+ for (i = 0; i < QUARANTINE_BATCHES; i++) {
+ if (qlist_empty(&global_quarantine[i]))
+ continue;
+ qlist_move_cache(&global_quarantine[i], &to_free, cache);
+ /* Scanning whole quarantine can take a while. */
+ spin_unlock_irqrestore(&quarantine_lock, flags);
+ cond_resched();
+ spin_lock_irqsave(&quarantine_lock, flags);
+ }
+ spin_unlock_irqrestore(&quarantine_lock, flags);
+
+ qlist_free_all(&to_free, cache);
+
+ synchronize_srcu(&remove_cache_srcu);
+}
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index b4e31f78ae69..04bb1d3eb9ec 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -13,12 +13,15 @@
*
*/
+#include <linux/bitops.h>
#include <linux/ftrace.h>
+#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/printk.h>
#include <linux/sched.h>
#include <linux/slab.h>
+#include <linux/stackdepot.h>
#include <linux/stacktrace.h>
#include <linux/string.h>
#include <linux/types.h>
@@ -48,7 +51,13 @@ static const void *find_first_bad_addr(const void *addr, size_t size)
return first_bad_addr;
}
-static void print_error_description(struct kasan_access_info *info)
+static bool addr_has_shadow(struct kasan_access_info *info)
+{
+ return (info->access_addr >=
+ kasan_shadow_to_mem((void *)KASAN_SHADOW_START));
+}
+
+static const char *get_shadow_bug_type(struct kasan_access_info *info)
{
const char *bug_type = "unknown-crash";
u8 *shadow_addr;
@@ -90,14 +99,44 @@ static void print_error_description(struct kasan_access_info *info)
case KASAN_KMALLOC_FREE:
bug_type = "use-after-free";
break;
+ case KASAN_USE_AFTER_SCOPE:
+ bug_type = "use-after-scope";
+ break;
}
- pr_err("BUG: KASAN: %s in %pS at addr %p\n",
- bug_type, (void *)info->ip,
- info->access_addr);
- pr_err("%s of size %zu by task %s/%d\n",
- info->is_write ? "Write" : "Read",
- info->access_size, current->comm, task_pid_nr(current));
+ return bug_type;
+}
+
+static const char *get_wild_bug_type(struct kasan_access_info *info)
+{
+ const char *bug_type = "unknown-crash";
+
+ if ((unsigned long)info->access_addr < PAGE_SIZE)
+ bug_type = "null-ptr-deref";
+ else if ((unsigned long)info->access_addr < TASK_SIZE)
+ bug_type = "user-memory-access";
+ else
+ bug_type = "wild-memory-access";
+
+ return bug_type;
+}
+
+static const char *get_bug_type(struct kasan_access_info *info)
+{
+ if (addr_has_shadow(info))
+ return get_shadow_bug_type(info);
+ return get_wild_bug_type(info);
+}
+
+static void print_error_description(struct kasan_access_info *info)
+{
+ const char *bug_type = get_bug_type(info);
+
+ pr_err("BUG: KASAN: %s in %pS\n",
+ bug_type, (void *)info->ip);
+ pr_err("%s of size %zu at addr %p by task %s/%d\n",
+ info->is_write ? "Write" : "Read", info->access_size,
+ info->access_addr, current->comm, task_pid_nr(current));
}
static inline bool kernel_or_module_addr(const void *addr)
@@ -116,39 +155,119 @@ static inline bool init_task_stack_addr(const void *addr)
sizeof(init_thread_union.stack));
}
-static void print_address_description(struct kasan_access_info *info)
+static DEFINE_SPINLOCK(report_lock);
+
+static void kasan_start_report(unsigned long *flags)
+{
+ /*
+ * Make sure we don't end up in loop.
+ */
+ kasan_disable_current();
+ spin_lock_irqsave(&report_lock, *flags);
+ pr_err("==================================================================\n");
+}
+
+static void kasan_end_report(unsigned long *flags)
+{
+ pr_err("==================================================================\n");
+ add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
+ spin_unlock_irqrestore(&report_lock, *flags);
+ if (panic_on_warn)
+ panic("panic_on_warn set ...\n");
+ kasan_enable_current();
+}
+
+static void print_track(struct kasan_track *track, const char *prefix)
{
- const void *addr = info->access_addr;
+ pr_err("%s by task %u:\n", prefix, track->pid);
+ if (track->stack) {
+ struct stack_trace trace;
+ depot_fetch_stack(track->stack, &trace);
+ print_stack_trace(&trace, 0);
+ } else {
+ pr_err("(stack is not available)\n");
+ }
+}
+
+static struct page *addr_to_page(const void *addr)
+{
if ((addr >= (void *)PAGE_OFFSET) &&
- (addr < high_memory)) {
- struct page *page = virt_to_head_page(addr);
+ (addr < high_memory))
+ return virt_to_head_page(addr);
+ return NULL;
+}
- if (PageSlab(page)) {
- void *object;
- struct kmem_cache *cache = page->slab_cache;
- void *last_object;
+static void describe_object_addr(struct kmem_cache *cache, void *object,
+ const void *addr)
+{
+ unsigned long access_addr = (unsigned long)addr;
+ unsigned long object_addr = (unsigned long)object;
+ const char *rel_type;
+ int rel_bytes;
- object = virt_to_obj(cache, page_address(page), addr);
- last_object = page_address(page) +
- page->objects * cache->size;
+ pr_err("The buggy address belongs to the object at %p\n"
+ " which belongs to the cache %s of size %d\n",
+ object, cache->name, cache->object_size);
- if (unlikely(object > last_object))
- object = last_object; /* we hit into padding */
+ if (!addr)
+ return;
- object_err(cache, page, object,
- "kasan: bad access detected");
- return;
- }
- dump_page(page, "kasan: bad access detected");
+ if (access_addr < object_addr) {
+ rel_type = "to the left";
+ rel_bytes = object_addr - access_addr;
+ } else if (access_addr >= object_addr + cache->object_size) {
+ rel_type = "to the right";
+ rel_bytes = access_addr - (object_addr + cache->object_size);
+ } else {
+ rel_type = "inside";
+ rel_bytes = access_addr - object_addr;
}
- if (kernel_or_module_addr(addr)) {
- if (!init_task_stack_addr(addr))
- pr_err("Address belongs to variable %pS\n", addr);
+ pr_err("The buggy address is located %d bytes %s of\n"
+ " %d-byte region [%p, %p)\n",
+ rel_bytes, rel_type, cache->object_size, (void *)object_addr,
+ (void *)(object_addr + cache->object_size));
+}
+
+static void describe_object(struct kmem_cache *cache, void *object,
+ const void *addr)
+{
+ struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object);
+
+ if (cache->flags & SLAB_KASAN) {
+ print_track(&alloc_info->alloc_track, "Allocated");
+ pr_err("\n");
+ print_track(&alloc_info->free_track, "Freed");
+ pr_err("\n");
}
+ describe_object_addr(cache, object, addr);
+}
+
+static void print_address_description(void *addr)
+{
+ struct page *page = addr_to_page(addr);
+
dump_stack();
+ pr_err("\n");
+
+ if (page && PageSlab(page)) {
+ struct kmem_cache *cache = page->slab_cache;
+ void *object = nearest_obj(cache, page, addr);
+
+ describe_object(cache, object, addr);
+ }
+
+ if (kernel_or_module_addr(addr) && !init_task_stack_addr(addr)) {
+ pr_err("The buggy address belongs to the variable:\n");
+ pr_err(" %pS\n", addr);
+ }
+
+ if (page) {
+ pr_err("The buggy address belongs to the page:\n");
+ dump_page(page, "kasan: bad access detected");
+ }
}
static bool row_is_guilty(const void *row, const void *guilty)
@@ -203,45 +322,72 @@ static void print_shadow_for_address(const void *addr)
}
}
-static DEFINE_SPINLOCK(report_lock);
+void kasan_report_double_free(struct kmem_cache *cache, void *object,
+ void *ip)
+{
+ unsigned long flags;
+
+ kasan_start_report(&flags);
+ pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", ip);
+ pr_err("\n");
+ print_address_description(object);
+ pr_err("\n");
+ print_shadow_for_address(object);
+ kasan_end_report(&flags);
+}
static void kasan_report_error(struct kasan_access_info *info)
{
unsigned long flags;
- const char *bug_type;
- /*
- * Make sure we don't end up in loop.
- */
- kasan_disable_current();
- spin_lock_irqsave(&report_lock, flags);
- pr_err("================================="
- "=================================\n");
- if (info->access_addr <
- kasan_shadow_to_mem((void *)KASAN_SHADOW_START)) {
- if ((unsigned long)info->access_addr < PAGE_SIZE)
- bug_type = "null-ptr-deref";
- else if ((unsigned long)info->access_addr < TASK_SIZE)
- bug_type = "user-memory-access";
- else
- bug_type = "wild-memory-access";
- pr_err("BUG: KASAN: %s on address %p\n",
- bug_type, info->access_addr);
- pr_err("%s of size %zu by task %s/%d\n",
- info->is_write ? "Write" : "Read",
- info->access_size, current->comm,
- task_pid_nr(current));
+ kasan_start_report(&flags);
+
+ print_error_description(info);
+ pr_err("\n");
+
+ if (!addr_has_shadow(info)) {
dump_stack();
} else {
- print_error_description(info);
- print_address_description(info);
+ print_address_description((void *)info->access_addr);
+ pr_err("\n");
print_shadow_for_address(info->first_bad_addr);
}
- pr_err("================================="
- "=================================\n");
- add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
- spin_unlock_irqrestore(&report_lock, flags);
- kasan_enable_current();
+
+ kasan_end_report(&flags);
+}
+
+static unsigned long kasan_flags;
+
+#define KASAN_BIT_REPORTED 0
+#define KASAN_BIT_MULTI_SHOT 1
+
+bool kasan_save_enable_multi_shot(void)
+{
+ return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+}
+EXPORT_SYMBOL_GPL(kasan_save_enable_multi_shot);
+
+void kasan_restore_multi_shot(bool enabled)
+{
+ if (!enabled)
+ clear_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+}
+EXPORT_SYMBOL_GPL(kasan_restore_multi_shot);
+
+static int __init kasan_set_multi_shot(char *str)
+{
+ set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+ return 1;
+}
+__setup("kasan_multi_shot", kasan_set_multi_shot);
+
+static inline bool kasan_report_enabled(void)
+{
+ if (current->kasan_depth)
+ return false;
+ if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags))
+ return true;
+ return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags);
}
void kasan_report(unsigned long addr, size_t size,
diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c
index cab58bb592d8..e6347772bbda 100644
--- a/mm/kmemcheck.c
+++ b/mm/kmemcheck.c
@@ -20,8 +20,7 @@ void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
shadow = alloc_pages_node(node, flags | __GFP_NOTRACK, order);
if (!shadow) {
if (printk_ratelimit())
- printk(KERN_ERR "kmemcheck: failed to allocate "
- "shadow bitmap\n");
+ printk(KERN_ERR "kmemcheck: failed to allocate shadow bitmap\n");
return;
}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index abcf9e47adc5..42eb5e580b3c 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -597,8 +597,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
else if (parent->pointer + parent->size <= ptr)
link = &parent->rb_node.rb_right;
else {
- kmemleak_stop("Cannot insert 0x%lx into the object "
- "search tree (overlaps existing)\n",
+ kmemleak_stop("Cannot insert 0x%lx into the object search tree (overlaps existing)\n",
ptr);
/*
* No need for parent->lock here since "parent" cannot
@@ -671,8 +670,8 @@ static void delete_object_part(unsigned long ptr, size_t size)
object = find_and_remove_object(ptr, 1);
if (!object) {
#ifdef DEBUG
- kmemleak_warn("Partially freeing unknown object at 0x%08lx "
- "(size %zu)\n", ptr, size);
+ kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n",
+ ptr, size);
#endif
return;
}
@@ -718,8 +717,8 @@ static void paint_ptr(unsigned long ptr, int color)
object = find_and_get_object(ptr, 0);
if (!object) {
- kmemleak_warn("Trying to color unknown object "
- "at 0x%08lx as %s\n", ptr,
+ kmemleak_warn("Trying to color unknown object at 0x%08lx as %s\n",
+ ptr,
(color == KMEMLEAK_GREY) ? "Grey" :
(color == KMEMLEAK_BLACK) ? "Black" : "Unknown");
return;
@@ -1466,8 +1465,8 @@ static void kmemleak_scan(void)
if (new_leaks) {
kmemleak_found_leaks = true;
- pr_info("%d new suspected memory leaks (see "
- "/sys/kernel/debug/kmemleak)\n", new_leaks);
+ pr_info("%d new suspected memory leaks (see /sys/kernel/debug/kmemleak)\n",
+ new_leaks);
}
}
@@ -1800,8 +1799,7 @@ static void kmemleak_do_cleanup(struct work_struct *work)
if (!kmemleak_found_leaks)
__kmemleak_do_cleanup();
else
- pr_info("Kmemleak disabled without freeing internal data. "
- "Reclaim the memory with \"echo clear > /sys/kernel/debug/kmemleak\"\n");
+ pr_info("Kmemleak disabled without freeing internal data. Reclaim the memory with \"echo clear > /sys/kernel/debug/kmemleak\".\n");
}
static DECLARE_WORK(cleanup_work, kmemleak_do_cleanup);
diff --git a/mm/madvise.c b/mm/madvise.c
index f548c66154ee..d1d09bdf9a72 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -104,7 +104,7 @@ static long madvise_behavior(struct vm_area_struct *vma,
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx);
+ vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;
diff --git a/mm/memblock.c b/mm/memblock.c
index ff51a37eb86b..516d2fd1feaa 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -785,6 +785,17 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR);
}
+/**
+ * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * Return 0 on success, -errno on failure.
+ */
+int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
+{
+ return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP);
+}
/**
* __next_reserved_mem_region - next function for for_each_reserved_region()
@@ -876,6 +887,10 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
continue;
+ /* skip nomap memory unless we were asked for it explicitly */
+ if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
+ continue;
+
if (!type_b) {
if (out_start)
*out_start = m_start;
@@ -985,6 +1000,10 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags,
if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
continue;
+ /* skip nomap memory unless we were asked for it explicitly */
+ if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
+ continue;
+
if (!type_b) {
if (out_start)
*out_start = m_start;
@@ -1482,6 +1501,15 @@ int __init_memblock memblock_is_memory(phys_addr_t addr)
return memblock_search(&memblock.memory, addr) != -1;
}
+int __init_memblock memblock_is_map_memory(phys_addr_t addr)
+{
+ int i = memblock_search(&memblock.memory, addr);
+
+ if (i == -1)
+ return false;
+ return !memblock_is_nomap(&memblock.memory.regions[i]);
+}
+
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
unsigned long *start_pfn, unsigned long *end_pfn)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 5fa8a3606f40..50bdb897ab00 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1947,8 +1947,7 @@ static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr));
endpa = PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1;
- pr_warn("removing memory fails, because memory "
- "[%pa-%pa] is onlined\n",
+ pr_warn("removing memory fails, because memory [%pa-%pa] is onlined\n",
&beginpa, &endpa);
}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 9ab7969ee7e3..8c757f8e7a14 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -724,7 +724,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
((vmstart - vma->vm_start) >> PAGE_SHIFT);
prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff,
- new_pol, vma->vm_userfaultfd_ctx);
+ new_pol, vma->vm_userfaultfd_ctx,
+ vma_get_anon_name(vma));
if (prev) {
vma = prev;
next = vma->vm_next;
@@ -2569,9 +2570,7 @@ static void __init check_numabalancing_enable(void)
set_numabalancing_state(numabalancing_override == 1);
if (num_online_nodes() > 1 && !numabalancing_override) {
- pr_info("%s automatic NUMA balancing. "
- "Configure with numa_balancing= or the "
- "kernel.numa_balancing sysctl",
+ pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n",
numabalancing_default ? "Enabling" : "Disabling");
set_numabalancing_state(numabalancing_default);
}
diff --git a/mm/mempool.c b/mm/mempool.c
index 7924f4f58a6d..5ba6c8b3b814 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -104,20 +104,16 @@ static inline void poison_element(mempool_t *pool, void *element)
static void kasan_poison_element(mempool_t *pool, void *element)
{
- if (pool->alloc == mempool_alloc_slab)
- kasan_slab_free(pool->pool_data, element);
- if (pool->alloc == mempool_kmalloc)
- kasan_kfree(element);
+ if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
+ kasan_poison_kfree(element);
if (pool->alloc == mempool_alloc_pages)
kasan_free_pages(element, (unsigned long)pool->pool_data);
}
-static void kasan_unpoison_element(mempool_t *pool, void *element)
+static void kasan_unpoison_element(mempool_t *pool, void *element, gfp_t flags)
{
- if (pool->alloc == mempool_alloc_slab)
- kasan_slab_alloc(pool->pool_data, element);
- if (pool->alloc == mempool_kmalloc)
- kasan_krealloc(element, (size_t)pool->pool_data);
+ if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
+ kasan_unpoison_slab(element);
if (pool->alloc == mempool_alloc_pages)
kasan_alloc_pages(element, (unsigned long)pool->pool_data);
}
@@ -130,12 +126,12 @@ static void add_element(mempool_t *pool, void *element)
pool->elements[pool->curr_nr++] = element;
}
-static void *remove_element(mempool_t *pool)
+static void *remove_element(mempool_t *pool, gfp_t flags)
{
void *element = pool->elements[--pool->curr_nr];
BUG_ON(pool->curr_nr < 0);
- kasan_unpoison_element(pool, element);
+ kasan_unpoison_element(pool, element, flags);
check_element(pool, element);
return element;
}
@@ -154,7 +150,7 @@ void mempool_destroy(mempool_t *pool)
return;
while (pool->curr_nr) {
- void *element = remove_element(pool);
+ void *element = remove_element(pool, GFP_KERNEL);
pool->free(element, pool->pool_data);
}
kfree(pool->elements);
@@ -250,7 +246,7 @@ int mempool_resize(mempool_t *pool, int new_min_nr)
spin_lock_irqsave(&pool->lock, flags);
if (new_min_nr <= pool->min_nr) {
while (new_min_nr < pool->curr_nr) {
- element = remove_element(pool);
+ element = remove_element(pool, GFP_KERNEL);
spin_unlock_irqrestore(&pool->lock, flags);
pool->free(element, pool->pool_data);
spin_lock_irqsave(&pool->lock, flags);
@@ -336,7 +332,7 @@ repeat_alloc:
spin_lock_irqsave(&pool->lock, flags);
if (likely(pool->curr_nr)) {
- element = remove_element(pool);
+ element = remove_element(pool, gfp_temp);
spin_unlock_irqrestore(&pool->lock, flags);
/* paired with rmb in mempool_free(), read comment there */
smp_wmb();
diff --git a/mm/mlock.c b/mm/mlock.c
index b03f160c1bdd..966dbdcfc322 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -514,7 +514,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx);
+ vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;
diff --git a/mm/mmap.c b/mm/mmap.c
index d48a654cbd23..8248ba89043c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -59,6 +59,18 @@
#define arch_rebalance_pgtables(addr, len) (addr)
#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
+const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN;
+const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX;
+int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS;
+#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
+const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN;
+const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX;
+int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
+#endif
+
+
static void unmap_region(struct mm_struct *mm,
struct vm_area_struct *vma, struct vm_area_struct *prev,
unsigned long start, unsigned long end);
@@ -940,7 +952,8 @@ again: remove_next = 1 + (end > next->vm_end);
*/
static inline int is_mergeable_vma(struct vm_area_struct *vma,
struct file *file, unsigned long vm_flags,
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
+ const char __user *anon_name)
{
/*
* VM_SOFTDIRTY should not prevent from VMA merging, if we
@@ -958,6 +971,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma,
return 0;
if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx))
return 0;
+ if (vma_get_anon_name(vma) != anon_name)
+ return 0;
return 1;
}
@@ -990,9 +1005,10 @@ static int
can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
pgoff_t vm_pgoff,
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
+ const char __user *anon_name)
{
- if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
+ if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
if (vma->vm_pgoff == vm_pgoff)
return 1;
@@ -1011,9 +1027,10 @@ static int
can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
pgoff_t vm_pgoff,
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
+ const char __user *anon_name)
{
- if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
+ if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
pgoff_t vm_pglen;
vm_pglen = vma_pages(vma);
@@ -1024,9 +1041,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
}
/*
- * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out
- * whether that can be merged with its predecessor or its successor.
- * Or both (it neatly fills a hole).
+ * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name),
+ * figure out whether that can be merged with its predecessor or its
+ * successor. Or both (it neatly fills a hole).
*
* In most cases - when called for mmap, brk or mremap - [addr,end) is
* certain not to be mapped by the time vma_merge is called; but when
@@ -1057,7 +1074,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
unsigned long end, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
pgoff_t pgoff, struct mempolicy *policy,
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
+ const char __user *anon_name)
{
pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
struct vm_area_struct *area, *next;
@@ -1085,7 +1103,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
mpol_equal(vma_policy(prev), policy) &&
can_vma_merge_after(prev, vm_flags,
anon_vma, file, pgoff,
- vm_userfaultfd_ctx)) {
+ vm_userfaultfd_ctx,
+ anon_name)) {
/*
* OK, it can. Can we now merge in the successor as well?
*/
@@ -1094,7 +1113,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
can_vma_merge_before(next, vm_flags,
anon_vma, file,
pgoff+pglen,
- vm_userfaultfd_ctx) &&
+ vm_userfaultfd_ctx,
+ anon_name) &&
is_mergeable_anon_vma(prev->anon_vma,
next->anon_vma, NULL)) {
/* cases 1, 6 */
@@ -1116,7 +1136,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
mpol_equal(policy, vma_policy(next)) &&
can_vma_merge_before(next, vm_flags,
anon_vma, file, pgoff+pglen,
- vm_userfaultfd_ctx)) {
+ vm_userfaultfd_ctx,
+ anon_name)) {
if (prev && addr < prev->vm_end) /* case 4 */
err = vma_adjust(prev, prev->vm_start,
addr, prev->vm_pgoff, NULL);
@@ -1632,7 +1653,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
* Can we just expand an old mapping?
*/
vma = vma_merge(mm, prev, addr, addr + len, vm_flags,
- NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX);
+ NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX, NULL);
if (vma)
goto out;
@@ -2687,6 +2708,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
return 0;
}
+EXPORT_SYMBOL(do_munmap);
int vm_munmap(unsigned long start, size_t len)
{
@@ -2720,8 +2742,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
unsigned long ret = -EINVAL;
struct file *file;
- pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. "
- "See Documentation/vm/remap_file_pages.txt.\n",
+ pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.txt.\n",
current->comm, current->pid);
if (prot)
@@ -2860,7 +2881,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
/* Can we just expand an old private anonymous mapping? */
vma = vma_merge(mm, prev, addr, addr + len, flags,
- NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX);
+ NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX, NULL);
if (vma)
goto out;
@@ -3026,7 +3047,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
return NULL; /* should never get here */
new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx);
+ vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (new_vma) {
/*
* Source vma may have been merged into new_vma
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a277f3412a5d..fcd678c3bd24 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -343,7 +343,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*pprev = vma_merge(mm, *pprev, start, end, newflags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx);
+ vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*pprev) {
vma = *pprev;
goto success;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index bc781cdc0d04..7e5d3467d6d2 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -386,8 +386,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
static void dump_header(struct oom_control *oc, struct task_struct *p,
struct mem_cgroup *memcg)
{
- pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
- "oom_score_adj=%hd\n",
+ pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, oom_score_adj=%hd\n",
current->comm, oc->gfp_mask, oc->order,
current->signal->oom_score_adj);
cpuset_print_current_mems_allowed();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c62d58055baf..3348d88b2b71 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -238,9 +238,21 @@ compound_page_dtor * const compound_page_dtors[] = {
#endif
};
+/*
+ * Try to keep at least this much lowmem free. Do not allow normal
+ * allocations below this point, only high priority ones. Automatically
+ * tuned according to the amount of memory in the system.
+ */
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
+/*
+ * Extra memory for the system to try freeing. Used to temporarily
+ * free memory, to make space for new workloads. Anyone can allocate
+ * down to the min watermarks controlled by min_free_kbytes above.
+ */
+int extra_free_kbytes = 0;
+
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
static unsigned long __meminitdata dma_reserve;
@@ -4030,8 +4042,7 @@ static int __parse_numa_zonelist_order(char *s)
user_zonelist_order = ZONELIST_ORDER_ZONE;
} else {
printk(KERN_WARNING
- "Ignoring invalid numa_zonelist_order value: "
- "%s\n", s);
+ "Ignoring invalid numa_zonelist_order value: %s\n", s);
return -EINVAL;
}
return 0;
@@ -4496,12 +4507,11 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
else
page_group_by_mobility_disabled = 0;
- pr_info("Built %i zonelists in %s order, mobility grouping %s. "
- "Total pages: %ld\n",
- nr_online_nodes,
- zonelist_order_name[current_zonelist_order],
- page_group_by_mobility_disabled ? "off" : "on",
- vm_total_pages);
+ pr_info("Built %i zonelists in %s order, mobility grouping %s. Total pages: %ld\n",
+ nr_online_nodes,
+ zonelist_order_name[current_zonelist_order],
+ page_group_by_mobility_disabled ? "off" : "on",
+ vm_total_pages);
#ifdef CONFIG_NUMA
pr_info("Policy zone: %s\n", zone_names[policy_zone]);
#endif
@@ -5972,22 +5982,21 @@ void __init mem_init_print_info(const char *str)
#undef adj_init_size
- pr_info("Memory: %luK/%luK available "
- "(%luK kernel code, %luK rwdata, %luK rodata, "
- "%luK init, %luK bss, %luK reserved, %luK cma-reserved"
+ pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved"
#ifdef CONFIG_HIGHMEM
- ", %luK highmem"
+ ", %luK highmem"
#endif
- "%s%s)\n",
- nr_free_pages() << (PAGE_SHIFT-10), physpages << (PAGE_SHIFT-10),
- codesize >> 10, datasize >> 10, rosize >> 10,
- (init_data_size + init_code_size) >> 10, bss_size >> 10,
- (physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT-10),
- totalcma_pages << (PAGE_SHIFT-10),
+ "%s%s)\n",
+ nr_free_pages() << (PAGE_SHIFT - 10),
+ physpages << (PAGE_SHIFT - 10),
+ codesize >> 10, datasize >> 10, rosize >> 10,
+ (init_data_size + init_code_size) >> 10, bss_size >> 10,
+ (physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT - 10),
+ totalcma_pages << (PAGE_SHIFT - 10),
#ifdef CONFIG_HIGHMEM
- totalhigh_pages << (PAGE_SHIFT-10),
+ totalhigh_pages << (PAGE_SHIFT - 10),
#endif
- str ? ", " : "", str ? str : "");
+ str ? ", " : "", str ? str : "");
}
/**
@@ -6131,6 +6140,7 @@ static void setup_per_zone_lowmem_reserve(void)
static void __setup_per_zone_wmarks(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+ unsigned long pages_low = extra_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
struct zone *zone;
unsigned long flags;
@@ -6142,11 +6152,14 @@ static void __setup_per_zone_wmarks(void)
}
for_each_zone(zone) {
- u64 tmp;
+ u64 min, low;
spin_lock_irqsave(&zone->lock, flags);
- tmp = (u64)pages_min * zone->managed_pages;
- do_div(tmp, lowmem_pages);
+ min = (u64)pages_min * zone->managed_pages;
+ do_div(min, lowmem_pages);
+ low = (u64)pages_low * zone->managed_pages;
+ do_div(low, vm_total_pages);
+
if (is_highmem(zone)) {
/*
* __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -6167,11 +6180,13 @@ static void __setup_per_zone_wmarks(void)
* If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->watermark[WMARK_MIN] = tmp;
+ zone->watermark[WMARK_MIN] = min;
}
- zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
- zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+ zone->watermark[WMARK_LOW] = min_wmark_pages(zone) +
+ low + (min >> 2);
+ zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) +
+ low + (min >> 1);
__mod_zone_page_state(zone, NR_ALLOC_BATCH,
high_wmark_pages(zone) - low_wmark_pages(zone) -
@@ -6294,7 +6309,7 @@ postcore_initcall(init_per_zone_wmark_min)
/*
* min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
* that we can call two helper functions whenever min_free_kbytes
- * changes.
+ * or extra_free_kbytes changes.
*/
int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
diff --git a/mm/percpu.c b/mm/percpu.c
index 1c784df3bdfe..c5f2a724101a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -890,8 +890,8 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
size = ALIGN(size, 2);
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
- WARN(true, "illegal size (%zu) or align (%zu) for "
- "percpu allocation\n", size, align);
+ WARN(true, "illegal size (%zu) or align (%zu) for percpu allocation\n",
+ size, align);
return NULL;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index 07abbdfb1d22..4cce6ff6e9d3 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3411,6 +3411,14 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags
}
EXPORT_SYMBOL_GPL(shmem_file_setup);
+void shmem_set_file(struct vm_area_struct *vma, struct file *file)
+{
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ vma->vm_file = file;
+ vma->vm_ops = &shmem_vm_ops;
+}
+
/**
* shmem_zero_setup - setup a shared anonymous mapping
* @vma: the vma to be mmapped is prepared by do_mmap_pgoff
@@ -3430,10 +3438,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
if (IS_ERR(file))
return PTR_ERR(file);
- if (vma->vm_file)
- fput(vma->vm_file);
- vma->vm_file = file;
- vma->vm_ops = &shmem_vm_ops;
+ shmem_set_file(vma, file);
return 0;
}
diff --git a/mm/slab.c b/mm/slab.c
index d043b8007f23..e0b0cf86b5b8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -390,36 +390,26 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
#endif
-#define OBJECT_FREE (0)
-#define OBJECT_ACTIVE (1)
-
#ifdef CONFIG_DEBUG_SLAB_LEAK
-static void set_obj_status(struct page *page, int idx, int val)
+static inline bool is_store_user_clean(struct kmem_cache *cachep)
{
- int freelist_size;
- char *status;
- struct kmem_cache *cachep = page->slab_cache;
-
- freelist_size = cachep->num * sizeof(freelist_idx_t);
- status = (char *)page->freelist + freelist_size;
- status[idx] = val;
+ return atomic_read(&cachep->store_user_clean) == 1;
}
-static inline unsigned int get_obj_status(struct page *page, int idx)
+static inline void set_store_user_clean(struct kmem_cache *cachep)
{
- int freelist_size;
- char *status;
- struct kmem_cache *cachep = page->slab_cache;
-
- freelist_size = cachep->num * sizeof(freelist_idx_t);
- status = (char *)page->freelist + freelist_size;
+ atomic_set(&cachep->store_user_clean, 1);
+}
- return status[idx];
+static inline void set_store_user_dirty(struct kmem_cache *cachep)
+{
+ if (is_store_user_clean(cachep))
+ atomic_set(&cachep->store_user_clean, 0);
}
#else
-static inline void set_obj_status(struct page *page, int idx, int val) {}
+static inline void set_store_user_dirty(struct kmem_cache *cachep) {}
#endif
@@ -480,9 +470,6 @@ static size_t calculate_freelist_size(int nr_objs, size_t align)
size_t freelist_size;
freelist_size = nr_objs * sizeof(freelist_idx_t);
- if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
- freelist_size += nr_objs * sizeof(char);
-
if (align)
freelist_size = ALIGN(freelist_size, align);
@@ -495,10 +482,7 @@ static int calculate_nr_objs(size_t slab_size, size_t buffer_size,
int nr_objs;
size_t remained_size;
size_t freelist_size;
- int extra_space = 0;
- if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
- extra_space = sizeof(char);
/*
* Ignore padding for the initial guess. The padding
* is at most @align-1 bytes, and @buffer_size is at
@@ -507,7 +491,7 @@ static int calculate_nr_objs(size_t slab_size, size_t buffer_size,
* into the memory allocation when taking the padding
* into account.
*/
- nr_objs = slab_size / (buffer_size + idx_size + extra_space);
+ nr_objs = slab_size / (buffer_size + idx_size);
/*
* This calculated number will be either the right
@@ -1673,6 +1657,14 @@ static void kmem_rcu_free(struct rcu_head *head)
}
#if DEBUG
+static bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
+{
+ if (debug_pagealloc_enabled() && OFF_SLAB(cachep) &&
+ (cachep->size % PAGE_SIZE) == 0)
+ return true;
+
+ return false;
+}
#ifdef CONFIG_DEBUG_PAGEALLOC
static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
@@ -1706,6 +1698,23 @@ static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
}
*addr++ = 0x87654321;
}
+
+static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
+ int map, unsigned long caller)
+{
+ if (!is_debug_pagealloc_cache(cachep))
+ return;
+
+ if (caller)
+ store_stackinfo(cachep, objp, caller);
+
+ kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
+}
+
+#else
+static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp,
+ int map, unsigned long caller) {}
+
#endif
static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
@@ -1736,11 +1745,9 @@ static void dump_line(char *data, int offset, int limit)
if (bad_count == 1) {
error ^= POISON_FREE;
if (!(error & (error - 1))) {
- printk(KERN_ERR "Single bit error detected. Probably "
- "bad RAM.\n");
+ printk(KERN_ERR "Single bit error detected. Probably bad RAM.\n");
#ifdef CONFIG_X86
- printk(KERN_ERR "Run memtest86+ or a similar memory "
- "test tool.\n");
+ printk(KERN_ERR "Run memtest86+ or a similar memory test tool.\n");
#else
printk(KERN_ERR "Run a memory test tool.\n");
#endif
@@ -1784,6 +1791,9 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
int size, i;
int lines = 0;
+ if (is_debug_pagealloc_cache(cachep))
+ return;
+
realobj = (char *)objp + obj_offset(cachep);
size = cachep->object_size;
@@ -1849,24 +1859,14 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep,
void *objp = index_to_obj(cachep, page, i);
if (cachep->flags & SLAB_POISON) {
-#ifdef CONFIG_DEBUG_PAGEALLOC
- if (cachep->size % PAGE_SIZE == 0 &&
- OFF_SLAB(cachep))
- kernel_map_pages(virt_to_page(objp),
- cachep->size / PAGE_SIZE, 1);
- else
- check_poison_obj(cachep, objp);
-#else
check_poison_obj(cachep, objp);
-#endif
+ slab_kernel_map(cachep, objp, 1, 0);
}
if (cachep->flags & SLAB_RED_ZONE) {
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
- slab_error(cachep, "start of a freed object "
- "was overwritten");
+ slab_error(cachep, "start of a freed object was overwritten");
if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
- slab_error(cachep, "end of a freed object "
- "was overwritten");
+ slab_error(cachep, "end of a freed object was overwritten");
}
}
}
@@ -1948,16 +1948,13 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
break;
if (flags & CFLGS_OFF_SLAB) {
- size_t freelist_size_per_obj = sizeof(freelist_idx_t);
/*
* Max number of objs-per-slab for caches which
* use off-slab slabs. Needed to avoid a possible
* looping condition in cache_grow().
*/
- if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
- freelist_size_per_obj += sizeof(char);
offslab_limit = size;
- offslab_limit /= freelist_size_per_obj;
+ offslab_limit /= sizeof(freelist_idx_t);
if (num > offslab_limit)
break;
@@ -2182,7 +2179,19 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
else
size += BYTES_PER_WORD;
}
-#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
+#endif
+
+ kasan_cache_create(cachep, &size, &flags);
+
+ size = ALIGN(size, cachep->align);
+ /*
+ * We should restrict the number of objects in a slab to implement
+ * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition.
+ */
+ if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
+ size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);
+
+#if DEBUG
/*
* To activate debug pagealloc, off-slab management is necessary
* requirement. In early phase of initialization, small sized slab
@@ -2190,14 +2199,14 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
* to check size >= 256. It guarantees that all necessary small
* sized slab is initialized in current slab initialization sequence.
*/
- if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) &&
+ if (debug_pagealloc_enabled() && (flags & SLAB_POISON) &&
+ !slab_early_init && size >= kmalloc_size(INDEX_NODE) &&
size >= 256 && cachep->object_size > cache_line_size() &&
- ALIGN(size, cachep->align) < PAGE_SIZE) {
- cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
+ size < PAGE_SIZE) {
+ cachep->obj_offset += PAGE_SIZE - size;
size = PAGE_SIZE;
}
#endif
-#endif
/*
* Determine if the slab management is 'on' or 'off' slab.
@@ -2206,20 +2215,13 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
* SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak)
*/
if (size >= OFF_SLAB_MIN_SIZE && !slab_early_init &&
- !(flags & SLAB_NOLEAKTRACE))
+ !(flags & SLAB_NOLEAKTRACE)) {
/*
* Size is large, assume best to place the slab management obj
* off-slab (should allow better packing of objs).
*/
flags |= CFLGS_OFF_SLAB;
-
- size = ALIGN(size, cachep->align);
- /*
- * We should restrict the number of objects in a slab to implement
- * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition.
- */
- if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
- size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);
+ }
left_over = calculate_slab_order(cachep, size, cachep->align, flags);
@@ -2240,15 +2242,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
if (flags & CFLGS_OFF_SLAB) {
/* really off slab. No need for manual alignment */
freelist_size = calculate_freelist_size(cachep->num, 0);
-
-#ifdef CONFIG_PAGE_POISONING
- /* If we're going to use the generic kernel_map_pages()
- * poisoning, then it's going to smash the contents of
- * the redzone and userword anyhow, so switch them off.
- */
- if (size % PAGE_SIZE == 0 && flags & SLAB_POISON)
- flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
-#endif
}
cachep->colour_off = cache_line_size();
@@ -2264,7 +2257,19 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
cachep->size = size;
cachep->reciprocal_buffer_size = reciprocal_value(size);
- if (flags & CFLGS_OFF_SLAB) {
+#if DEBUG
+ /*
+ * If we're going to use the generic kernel_map_pages()
+ * poisoning, then it's going to smash the contents of
+ * the redzone and userword anyhow, so switch them off.
+ */
+ if (IS_ENABLED(CONFIG_PAGE_POISONING) &&
+ (cachep->flags & SLAB_POISON) &&
+ is_debug_pagealloc_cache(cachep))
+ cachep->flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
+#endif
+
+ if (OFF_SLAB(cachep)) {
cachep->freelist_cache = kmalloc_slab(freelist_size, 0u);
/*
* This is a possibility for one of the kmalloc_{dma,}_caches.
@@ -2483,17 +2488,14 @@ static inline void set_free_obj(struct page *page,
((freelist_idx_t *)(page->freelist))[idx] = val;
}
-static void cache_init_objs(struct kmem_cache *cachep,
- struct page *page)
+static void cache_init_objs_debug(struct kmem_cache *cachep, struct page *page)
{
+#if DEBUG
int i;
for (i = 0; i < cachep->num; i++) {
void *objp = index_to_obj(cachep, page, i);
-#if DEBUG
- /* need to poison the objs? */
- if (cachep->flags & SLAB_POISON)
- poison_obj(cachep, objp, POISON_FREE);
+ kasan_init_slab_obj(cachep, objp);
if (cachep->flags & SLAB_STORE_USER)
*dbg_userword(cachep, objp) = NULL;
@@ -2506,26 +2508,46 @@ static void cache_init_objs(struct kmem_cache *cachep,
* cache which they are a constructor for. Otherwise, deadlock.
* They must also be threaded.
*/
- if (cachep->ctor && !(cachep->flags & SLAB_POISON))
+ if (cachep->ctor && !(cachep->flags & SLAB_POISON)) {
+ kasan_unpoison_object_data(cachep,
+ objp + obj_offset(cachep));
cachep->ctor(objp + obj_offset(cachep));
+ kasan_poison_object_data(
+ cachep, objp + obj_offset(cachep));
+ }
if (cachep->flags & SLAB_RED_ZONE) {
if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
- slab_error(cachep, "constructor overwrote the"
- " end of an object");
+ slab_error(cachep, "constructor overwrote the end of an object");
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
- slab_error(cachep, "constructor overwrote the"
- " start of an object");
+ slab_error(cachep, "constructor overwrote the start of an object");
}
- if ((cachep->size % PAGE_SIZE) == 0 &&
- OFF_SLAB(cachep) && cachep->flags & SLAB_POISON)
- kernel_map_pages(virt_to_page(objp),
- cachep->size / PAGE_SIZE, 0);
-#else
- if (cachep->ctor)
- cachep->ctor(objp);
+ /* need to poison the objs? */
+ if (cachep->flags & SLAB_POISON) {
+ poison_obj(cachep, objp, POISON_FREE);
+ slab_kernel_map(cachep, objp, 0, 0);
+ }
+ }
#endif
- set_obj_status(page, i, OBJECT_FREE);
+}
+
+static void cache_init_objs(struct kmem_cache *cachep,
+ struct page *page)
+{
+ int i;
+ void *objp;
+
+ cache_init_objs_debug(cachep, page);
+
+ for (i = 0; i < cachep->num; i++) {
+ /* constructor could break poison info */
+ if (DEBUG == 0 && cachep->ctor) {
+ objp = index_to_obj(cachep, page, i);
+ kasan_unpoison_object_data(cachep, objp);
+ cachep->ctor(objp);
+ kasan_poison_object_data(cachep, objp);
+ }
+
set_free_obj(page, i, i);
}
}
@@ -2551,6 +2573,11 @@ static void *slab_get_obj(struct kmem_cache *cachep, struct page *page,
WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
#endif
+#if DEBUG
+ if (cachep->flags & SLAB_STORE_USER)
+ set_store_user_dirty(cachep);
+#endif
+
return objp;
}
@@ -2567,8 +2594,8 @@ static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
/* Verify double free bug */
for (i = page->active; i < cachep->num; i++) {
if (get_free_obj(page, i) == objnr) {
- printk(KERN_ERR "slab: double free detected in cache "
- "'%s', objp %p\n", cachep->name, objp);
+ printk(KERN_ERR "slab: double free detected in cache '%s', objp %p\n",
+ cachep->name, objp);
BUG();
}
}
@@ -2653,6 +2680,7 @@ static int cache_grow(struct kmem_cache *cachep,
slab_map_pages(cachep, page, freelist);
+ kasan_poison_slab(page);
cache_init_objs(cachep, page);
if (gfpflags_allow_blocking(local_flags))
@@ -2729,27 +2757,19 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
*dbg_redzone1(cachep, objp) = RED_INACTIVE;
*dbg_redzone2(cachep, objp) = RED_INACTIVE;
}
- if (cachep->flags & SLAB_STORE_USER)
+ if (cachep->flags & SLAB_STORE_USER) {
+ set_store_user_dirty(cachep);
*dbg_userword(cachep, objp) = (void *)caller;
+ }
objnr = obj_to_index(cachep, page, objp);
BUG_ON(objnr >= cachep->num);
BUG_ON(objp != index_to_obj(cachep, page, objnr));
- set_obj_status(page, objnr, OBJECT_FREE);
if (cachep->flags & SLAB_POISON) {
-#ifdef CONFIG_DEBUG_PAGEALLOC
- if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
- store_stackinfo(cachep, objp, caller);
- kernel_map_pages(virt_to_page(objp),
- cachep->size / PAGE_SIZE, 0);
- } else {
- poison_obj(cachep, objp, POISON_FREE);
- }
-#else
poison_obj(cachep, objp, POISON_FREE);
-#endif
+ slab_kernel_map(cachep, objp, 0, caller);
}
return objp;
}
@@ -2871,20 +2891,11 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
gfp_t flags, void *objp, unsigned long caller)
{
- struct page *page;
-
if (!objp)
return objp;
if (cachep->flags & SLAB_POISON) {
-#ifdef CONFIG_DEBUG_PAGEALLOC
- if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep))
- kernel_map_pages(virt_to_page(objp),
- cachep->size / PAGE_SIZE, 1);
- else
- check_poison_obj(cachep, objp);
-#else
check_poison_obj(cachep, objp);
-#endif
+ slab_kernel_map(cachep, objp, 1, 0);
poison_obj(cachep, objp, POISON_INUSE);
}
if (cachep->flags & SLAB_STORE_USER)
@@ -2893,8 +2904,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
if (cachep->flags & SLAB_RED_ZONE) {
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE ||
*dbg_redzone2(cachep, objp) != RED_INACTIVE) {
- slab_error(cachep, "double free, or memory outside"
- " object was overwritten");
+ slab_error(cachep, "double free, or memory outside object was overwritten");
printk(KERN_ERR
"%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
objp, *dbg_redzone1(cachep, objp),
@@ -2904,8 +2914,6 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
*dbg_redzone2(cachep, objp) = RED_ACTIVE;
}
- page = virt_to_head_page(objp);
- set_obj_status(page, obj_to_index(cachep, page, objp), OBJECT_ACTIVE);
objp += obj_offset(cachep);
if (cachep->ctor && cachep->flags & SLAB_POISON)
cachep->ctor(objp);
@@ -3369,6 +3377,16 @@ free_done:
static inline void __cache_free(struct kmem_cache *cachep, void *objp,
unsigned long caller)
{
+ /* Put the object into the quarantine, don't touch it for now. */
+ if (kasan_slab_free(cachep, objp))
+ return;
+
+ ___cache_free(cachep, objp, caller);
+}
+
+void ___cache_free(struct kmem_cache *cachep, void *objp,
+ unsigned long caller)
+{
struct array_cache *ac = cpu_cache_get(cachep);
check_irq_off();
@@ -3409,6 +3427,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
void *ret = slab_alloc(cachep, flags, _RET_IP_);
+ kasan_slab_alloc(cachep, ret, flags);
trace_kmem_cache_alloc(_RET_IP_, ret,
cachep->object_size, cachep->size, flags);
@@ -3437,6 +3456,7 @@ kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size)
ret = slab_alloc(cachep, flags, _RET_IP_);
+ kasan_kmalloc(cachep, ret, size, flags);
trace_kmalloc(_RET_IP_, ret,
size, cachep->size, flags);
return ret;
@@ -3460,6 +3480,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
{
void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);
+ kasan_slab_alloc(cachep, ret, flags);
trace_kmem_cache_alloc_node(_RET_IP_, ret,
cachep->object_size, cachep->size,
flags, nodeid);
@@ -3478,6 +3499,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep,
ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);
+ kasan_kmalloc(cachep, ret, size, flags);
trace_kmalloc_node(_RET_IP_, ret,
size, cachep->size,
flags, nodeid);
@@ -3490,11 +3512,15 @@ static __always_inline void *
__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
{
struct kmem_cache *cachep;
+ void *ret;
cachep = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
- return kmem_cache_alloc_node_trace(cachep, flags, node, size);
+ ret = kmem_cache_alloc_node_trace(cachep, flags, node, size);
+ kasan_kmalloc(cachep, ret, size, flags);
+
+ return ret;
}
void *__kmalloc_node(size_t size, gfp_t flags, int node)
@@ -3528,6 +3554,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
return cachep;
ret = slab_alloc(cachep, flags, caller);
+ kasan_kmalloc(cachep, ret, size, flags);
trace_kmalloc(caller, ret,
size, cachep->size, flags);
@@ -4002,8 +4029,7 @@ void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
unsigned long node_frees = cachep->node_frees;
unsigned long overflows = cachep->node_overflow;
- seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu "
- "%4lu %4lu %4lu %4lu %4lu",
+ seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu %4lu %4lu %4lu %4lu %4lu",
allocs, high, grown,
reaped, errors, max_freeable, node_allocs,
node_frees, overflows);
@@ -4108,15 +4134,34 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c,
struct page *page)
{
void *p;
- int i;
+ int i, j;
+ unsigned long v;
if (n[0] == n[1])
return;
for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) {
- if (get_obj_status(page, i) != OBJECT_ACTIVE)
+ bool active = true;
+
+ for (j = page->active; j < c->num; j++) {
+ if (get_free_obj(page, j) == i) {
+ active = false;
+ break;
+ }
+ }
+
+ if (!active)
+ continue;
+
+ /*
+ * probe_kernel_read() is used for DEBUG_PAGEALLOC. page table
+ * mapping is established when actual object allocation and
+ * we could mistakenly access the unmapped object in the cpu
+ * cache.
+ */
+ if (probe_kernel_read(&v, dbg_userword(c, p), sizeof(v)))
continue;
- if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
+ if (!add_caller(n, v))
return;
}
}
@@ -4152,21 +4197,31 @@ static int leaks_show(struct seq_file *m, void *p)
if (!(cachep->flags & SLAB_RED_ZONE))
return 0;
- /* OK, we can do it */
+ /*
+ * Set store_user_clean and start to grab stored user information
+ * for all objects on this cache. If some alloc/free requests comes
+ * during the processing, information would be wrong so restart
+ * whole processing.
+ */
+ do {
+ set_store_user_clean(cachep);
+ drain_cpu_caches(cachep);
- x[1] = 0;
+ x[1] = 0;
- for_each_kmem_cache_node(cachep, node, n) {
+ for_each_kmem_cache_node(cachep, node, n) {
- check_irq_on();
- spin_lock_irq(&n->list_lock);
+ check_irq_on();
+ spin_lock_irq(&n->list_lock);
+
+ list_for_each_entry(page, &n->slabs_full, lru)
+ handle_slab(x, cachep, page);
+ list_for_each_entry(page, &n->slabs_partial, lru)
+ handle_slab(x, cachep, page);
+ spin_unlock_irq(&n->list_lock);
+ }
+ } while (!is_store_user_clean(cachep));
- list_for_each_entry(page, &n->slabs_full, lru)
- handle_slab(x, cachep, page);
- list_for_each_entry(page, &n->slabs_partial, lru)
- handle_slab(x, cachep, page);
- spin_unlock_irq(&n->list_lock);
- }
name = cachep->name;
if (x[0] == x[1]) {
/* Increase the buffer size */
@@ -4232,6 +4287,36 @@ static int __init slab_proc_init(void)
module_init(slab_proc_init);
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
+/*
+ * Rejects objects that are incorrectly sized.
+ *
+ * Returns NULL if check passes, otherwise const char * to name of cache
+ * to indicate an error.
+ */
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page)
+{
+ struct kmem_cache *cachep;
+ unsigned int objnr;
+ unsigned long offset;
+
+ /* Find and validate object. */
+ cachep = page->slab_cache;
+ objnr = obj_to_index(cachep, page, (void *)ptr);
+ BUG_ON(objnr >= cachep->num);
+
+ /* Find offset within object. */
+ offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep);
+
+ /* Allow address range falling entirely within object size. */
+ if (offset <= cachep->object_size && n <= cachep->object_size - offset)
+ return NULL;
+
+ return cachep->name;
+}
+#endif /* CONFIG_HARDENED_USERCOPY */
+
/**
* ksize - get the actual amount of memory allocated for a given object
* @objp: Pointer to the object
@@ -4246,10 +4331,18 @@ module_init(slab_proc_init);
*/
size_t ksize(const void *objp)
{
+ size_t size;
+
BUG_ON(!objp);
if (unlikely(objp == ZERO_SIZE_PTR))
return 0;
- return virt_to_cache(objp)->object_size;
+ size = virt_to_cache(objp)->object_size;
+ /* We assume that ksize callers could use the whole allocated area,
+ * so we need to unpoison this area.
+ */
+ kasan_krealloc(objp, size, GFP_NOWAIT);
+
+ return size;
}
EXPORT_SYMBOL(ksize);
diff --git a/mm/slab.h b/mm/slab.h
index 7b6087197997..66118e967e04 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -371,4 +371,6 @@ void *slab_next(struct seq_file *m, void *p, loff_t *pos);
void slab_stop(struct seq_file *m, void *p);
int memcg_slab_show(struct seq_file *m, void *p);
+void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
+
#endif /* MM_SLAB_H */
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 5d8c809a3ff7..e826dae32573 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -35,7 +35,7 @@ struct kmem_cache *kmem_cache;
*/
#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
- SLAB_FAILSLAB)
+ SLAB_FAILSLAB | SLAB_KASAN)
#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK)
@@ -453,6 +453,9 @@ EXPORT_SYMBOL(kmem_cache_create);
static int shutdown_cache(struct kmem_cache *s,
struct list_head *release, bool *need_rcu_barrier)
{
+ /* free asan quarantined objects */
+ kasan_cache_shutdown(s);
+
if (__kmem_cache_shutdown(s) != 0)
return -EBUSY;
@@ -723,8 +726,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
err = shutdown_cache(s, &release, &need_rcu_barrier);
if (err) {
- pr_err("kmem_cache_destroy %s: "
- "Slab cache still has objects\n", s->name);
+ pr_err("kmem_cache_destroy %s: Slab cache still has objects\n",
+ s->name);
dump_stack();
}
out_unlock:
@@ -750,6 +753,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
get_online_cpus();
get_online_mems();
+ kasan_cache_shrink(cachep);
ret = __kmem_cache_shrink(cachep, false);
put_online_mems();
put_online_cpus();
@@ -1010,7 +1014,7 @@ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
page = alloc_kmem_pages(flags, order);
ret = page ? page_address(page) : NULL;
kmemleak_alloc(ret, size, 1, flags);
- kasan_kmalloc_large(ret, size);
+ kasan_kmalloc_large(ret, size, flags);
return ret;
}
EXPORT_SYMBOL(kmalloc_order);
@@ -1044,13 +1048,11 @@ static void print_slabinfo_header(struct seq_file *m)
#else
seq_puts(m, "slabinfo - version: 2.1\n");
#endif
- seq_puts(m, "# name <active_objs> <num_objs> <objsize> "
- "<objperslab> <pagesperslab>");
+ seq_puts(m, "# name <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab>");
seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
#ifdef CONFIG_DEBUG_SLAB
- seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> "
- "<error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
+ seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> <error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
#endif
seq_putc(m, '\n');
@@ -1191,7 +1193,7 @@ static __always_inline void *__do_krealloc(const void *p, size_t new_size,
ks = ksize(p);
if (ks >= new_size) {
- kasan_krealloc((void *)p, new_size);
+ kasan_krealloc((void *)p, new_size, flags);
return (void *)p;
}
diff --git a/mm/slob.c b/mm/slob.c
index 17e8f8cc7c53..63052d56e79c 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -472,6 +472,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller)
{
return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller);
}
+EXPORT_SYMBOL(__kmalloc_track_caller);
#ifdef CONFIG_NUMA
void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
@@ -479,6 +480,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
{
return __do_kmalloc_node(size, gfp, node, caller);
}
+EXPORT_SYMBOL(__kmalloc_node_track_caller);
#endif
void kfree(const void *block)
diff --git a/mm/slub.c b/mm/slub.c
index 40c7a3fbd031..b58366739890 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -124,6 +124,14 @@ static inline int kmem_cache_debug(struct kmem_cache *s)
#endif
}
+static inline void *fixup_red_left(struct kmem_cache *s, void *p)
+{
+ if (kmem_cache_debug(s) && s->flags & SLAB_RED_ZONE)
+ p += s->red_left_pad;
+
+ return p;
+}
+
static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_CPU_PARTIAL
@@ -224,24 +232,6 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
* Core slab cache functions
*******************************************************************/
-/* Verify that a pointer has an address that is valid within a slab page */
-static inline int check_valid_pointer(struct kmem_cache *s,
- struct page *page, const void *object)
-{
- void *base;
-
- if (!object)
- return 1;
-
- base = page_address(page);
- if (object < base || object >= base + page->objects * s->size ||
- (object - base) % s->size) {
- return 0;
- }
-
- return 1;
-}
-
static inline void *get_freepointer(struct kmem_cache *s, void *object)
{
return *(void **)(object + s->offset);
@@ -271,12 +261,14 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
/* Loop over all objects in a slab */
#define for_each_object(__p, __s, __addr, __objects) \
- for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\
- __p += (__s)->size)
+ for (__p = fixup_red_left(__s, __addr); \
+ __p < (__addr) + (__objects) * (__s)->size; \
+ __p += (__s)->size)
#define for_each_object_idx(__p, __idx, __s, __addr, __objects) \
- for (__p = (__addr), __idx = 1; __idx <= __objects;\
- __p += (__s)->size, __idx++)
+ for (__p = fixup_red_left(__s, __addr), __idx = 1; \
+ __idx <= __objects; \
+ __p += (__s)->size, __idx++)
/* Determine object index from a given position */
static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
@@ -295,6 +287,9 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
return s->object_size;
#endif
+ if (s->flags & SLAB_KASAN)
+ return s->object_size;
+
/*
* If we have the need to store the freelist pointer
* back there or track user information then we can
@@ -456,13 +451,27 @@ static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
set_bit(slab_index(p, s, addr), map);
}
+static inline int size_from_object(struct kmem_cache *s)
+{
+ if (s->flags & SLAB_RED_ZONE)
+ return s->size - s->red_left_pad;
+
+ return s->size;
+}
+
+static inline void *restore_red_left(struct kmem_cache *s, void *p)
+{
+ if (s->flags & SLAB_RED_ZONE)
+ p -= s->red_left_pad;
+
+ return p;
+}
+
/*
* Debug settings:
*/
#if defined(CONFIG_SLUB_DEBUG_ON)
static int slub_debug = DEBUG_DEFAULT_FLAGS;
-#elif defined(CONFIG_KASAN)
-static int slub_debug = SLAB_STORE_USER;
#else
static int slub_debug;
#endif
@@ -489,6 +498,26 @@ static inline void metadata_access_disable(void)
/*
* Object debugging
*/
+
+/* Verify that a pointer has an address that is valid within a slab page */
+static inline int check_valid_pointer(struct kmem_cache *s,
+ struct page *page, void *object)
+{
+ void *base;
+
+ if (!object)
+ return 1;
+
+ base = page_address(page);
+ object = restore_red_left(s, object);
+ if (object < base || object >= base + page->objects * s->size ||
+ (object - base) % s->size) {
+ return 0;
+ }
+
+ return 1;
+}
+
static void print_section(char *text, u8 *addr, unsigned int length)
{
metadata_access_enable();
@@ -628,7 +657,9 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
pr_err("INFO: Object 0x%p @offset=%tu fp=0x%p\n\n",
p, p - addr, get_freepointer(s, p));
- if (p > addr + 16)
+ if (s->flags & SLAB_RED_ZONE)
+ print_section("Redzone ", p - s->red_left_pad, s->red_left_pad);
+ else if (p > addr + 16)
print_section("Bytes b4 ", p - 16, 16);
print_section("Object ", p, min_t(unsigned long, s->object_size,
@@ -645,9 +676,11 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
if (s->flags & SLAB_STORE_USER)
off += 2 * sizeof(struct track);
- if (off != s->size)
+ off += kasan_metadata_size(s);
+
+ if (off != size_from_object(s))
/* Beginning of the filler is the free pointer */
- print_section("Padding ", p + off, s->size - off);
+ print_section("Padding ", p + off, size_from_object(s) - off);
dump_stack();
}
@@ -677,6 +710,9 @@ static void init_object(struct kmem_cache *s, void *object, u8 val)
{
u8 *p = object;
+ if (s->flags & SLAB_RED_ZONE)
+ memset(p - s->red_left_pad, val, s->red_left_pad);
+
if (s->flags & __OBJECT_POISON) {
memset(p, POISON_FREE, s->object_size - 1);
p[s->object_size - 1] = POISON_END;
@@ -769,11 +805,13 @@ static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p)
/* We also have user information there */
off += 2 * sizeof(struct track);
- if (s->size == off)
+ off += kasan_metadata_size(s);
+
+ if (size_from_object(s) == off)
return 1;
return check_bytes_and_report(s, page, p, "Object padding",
- p + off, POISON_INUSE, s->size - off);
+ p + off, POISON_INUSE, size_from_object(s) - off);
}
/* Check the pad bytes at the end of a slab page */
@@ -818,6 +856,10 @@ static int check_object(struct kmem_cache *s, struct page *page,
if (s->flags & SLAB_RED_ZONE) {
if (!check_bytes_and_report(s, page, object, "Redzone",
+ object - s->red_left_pad, val, s->red_left_pad))
+ return 0;
+
+ if (!check_bytes_and_report(s, page, object, "Redzone",
endobject, val, s->inuse - s->object_size))
return 0;
} else {
@@ -928,14 +970,14 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
max_objects = MAX_OBJS_PER_PAGE;
if (page->objects != max_objects) {
- slab_err(s, page, "Wrong number of objects. Found %d but "
- "should be %d", page->objects, max_objects);
+ slab_err(s, page, "Wrong number of objects. Found %d but should be %d",
+ page->objects, max_objects);
page->objects = max_objects;
slab_fix(s, "Number of objects adjusted.");
}
if (page->inuse != page->objects - nr) {
- slab_err(s, page, "Wrong object count. Counter is %d but "
- "counted were %d", page->inuse, page->objects - nr);
+ slab_err(s, page, "Wrong object count. Counter is %d but counted were %d",
+ page->inuse, page->objects - nr);
page->inuse = page->objects - nr;
slab_fix(s, "Object count adjusted.");
}
@@ -1099,8 +1141,8 @@ next_object:
if (unlikely(s != page->slab_cache)) {
if (!PageSlab(page)) {
- slab_err(s, page, "Attempt to free object(0x%p) "
- "outside of slab", object);
+ slab_err(s, page, "Attempt to free object(0x%p) outside of slab",
+ object);
} else if (!page->slab_cache) {
pr_err("SLUB <none>: no slab for object 0x%p.\n",
object);
@@ -1270,7 +1312,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
{
kmemleak_alloc(ptr, size, 1, flags);
- kasan_kmalloc_large(ptr, size);
+ kasan_kmalloc_large(ptr, size, flags);
}
static inline void kfree_hook(const void *x)
@@ -1304,13 +1346,15 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
kmemleak_alloc_recursive(object, s->object_size, 1,
s->flags, flags);
- kasan_slab_alloc(s, object);
+ kasan_slab_alloc(s, object, flags);
}
memcg_kmem_put_cache(s);
}
-static inline void slab_free_hook(struct kmem_cache *s, void *x)
+static inline void *slab_free_hook(struct kmem_cache *s, void *x)
{
+ void *freeptr;
+
kmemleak_free_recursive(x, s->flags);
/*
@@ -1331,7 +1375,13 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
if (!(s->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(x, s->object_size);
+ freeptr = get_freepointer(s, x);
+ /*
+ * kasan_slab_free() may put x into memory quarantine, delaying its
+ * reuse. In this case the object's freelist pointer is changed.
+ */
kasan_slab_free(s, x);
+ return freeptr;
}
static inline void slab_free_freelist_hook(struct kmem_cache *s,
@@ -1349,11 +1399,11 @@ static inline void slab_free_freelist_hook(struct kmem_cache *s,
void *object = head;
void *tail_obj = tail ? : head;
+ void *freeptr;
do {
- slab_free_hook(s, object);
- } while ((object != tail_obj) &&
- (object = get_freepointer(s, object)));
+ freeptr = slab_free_hook(s, object);
+ } while ((object != tail_obj) && (object = freeptr));
#endif
}
@@ -1361,6 +1411,7 @@ static void setup_object(struct kmem_cache *s, struct page *page,
void *object)
{
setup_object_debug(s, page, object);
+ kasan_init_slab_obj(s, object);
if (unlikely(s->ctor)) {
kasan_unpoison_object_data(s, object);
s->ctor(object);
@@ -1468,7 +1519,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
set_freepointer(s, p, NULL);
}
- page->freelist = start;
+ page->freelist = fixup_red_left(s, start);
page->inuse = page->objects;
page->frozen = 1;
@@ -2596,7 +2647,7 @@ void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
{
void *ret = slab_alloc(s, gfpflags, _RET_IP_);
trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
- kasan_kmalloc(s, ret, size);
+ kasan_kmalloc(s, ret, size, gfpflags);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_trace);
@@ -2624,7 +2675,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
trace_kmalloc_node(_RET_IP_, ret,
size, s->size, gfpflags, node);
- kasan_kmalloc(s, ret, size);
+ kasan_kmalloc(s, ret, size, gfpflags);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
@@ -2769,16 +2820,13 @@ slab_empty:
* same page) possible by specifying head and tail ptr, plus objects
* count (cnt). Bulk free indicated by tail pointer being set.
*/
-static __always_inline void slab_free(struct kmem_cache *s, struct page *page,
- void *head, void *tail, int cnt,
- unsigned long addr)
+static __always_inline void do_slab_free(struct kmem_cache *s,
+ struct page *page, void *head, void *tail,
+ int cnt, unsigned long addr)
{
void *tail_obj = tail ? : head;
struct kmem_cache_cpu *c;
unsigned long tid;
-
- slab_free_freelist_hook(s, head, tail);
-
redo:
/*
* Determine the currently cpus per cpu slab.
@@ -2814,6 +2862,27 @@ redo:
}
+static __always_inline void slab_free(struct kmem_cache *s, struct page *page,
+ void *head, void *tail, int cnt,
+ unsigned long addr)
+{
+ slab_free_freelist_hook(s, head, tail);
+ /*
+ * slab_free_freelist_hook() could have put the items into quarantine.
+ * If so, no need to free them.
+ */
+ if (s->flags & SLAB_KASAN && !(s->flags & SLAB_DESTROY_BY_RCU))
+ return;
+ do_slab_free(s, page, head, tail, cnt, addr);
+}
+
+#ifdef CONFIG_KASAN
+void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr)
+{
+ do_slab_free(cache, virt_to_head_page(x), x, NULL, 1, addr);
+}
+#endif
+
void kmem_cache_free(struct kmem_cache *s, void *x)
{
s = cache_from_obj(s, x);
@@ -3179,7 +3248,8 @@ static void early_kmem_cache_node_alloc(int node)
init_object(kmem_cache_node, n, SLUB_RED_ACTIVE);
init_tracking(kmem_cache_node, n);
#endif
- kasan_kmalloc(kmem_cache_node, n, sizeof(struct kmem_cache_node));
+ kasan_kmalloc(kmem_cache_node, n, sizeof(struct kmem_cache_node),
+ GFP_KERNEL);
init_kmem_cache_node(n);
inc_slabs_node(kmem_cache_node, node, page->objects);
@@ -3242,7 +3312,7 @@ static void set_min_partial(struct kmem_cache *s, unsigned long min)
static int calculate_sizes(struct kmem_cache *s, int forced_order)
{
unsigned long flags = s->flags;
- unsigned long size = s->object_size;
+ size_t size = s->object_size;
int order;
/*
@@ -3301,8 +3371,11 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
* the object.
*/
size += 2 * sizeof(struct track);
+#endif
- if (flags & SLAB_RED_ZONE)
+ kasan_cache_create(s, &size, &s->flags);
+#ifdef CONFIG_SLUB_DEBUG
+ if (flags & SLAB_RED_ZONE) {
/*
* Add some empty padding so that we can catch
* overwrites from earlier objects rather than let
@@ -3311,6 +3384,11 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
* of the object.
*/
size += sizeof(void *);
+
+ s->red_left_pad = sizeof(void *);
+ s->red_left_pad = ALIGN(s->red_left_pad, s->align);
+ size += s->red_left_pad;
+ }
#endif
/*
@@ -3425,10 +3503,9 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
free_kmem_cache_nodes(s);
error:
if (flags & SLAB_PANIC)
- panic("Cannot create slab %s size=%lu realsize=%u "
- "order=%u offset=%u flags=%lx\n",
- s->name, (unsigned long)s->size, s->size,
- oo_order(s->oo), s->offset, flags);
+ panic("Cannot create slab %s size=%lu realsize=%u order=%u offset=%u flags=%lx\n",
+ s->name, (unsigned long)s->size, s->size,
+ oo_order(s->oo), s->offset, flags);
return -EINVAL;
}
@@ -3552,7 +3629,7 @@ void *__kmalloc(size_t size, gfp_t flags)
trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
- kasan_kmalloc(s, ret, size);
+ kasan_kmalloc(s, ret, size, flags);
return ret;
}
@@ -3597,13 +3674,53 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node);
- kasan_kmalloc(s, ret, size);
+ kasan_kmalloc(s, ret, size, flags);
return ret;
}
EXPORT_SYMBOL(__kmalloc_node);
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
+/*
+ * Rejects objects that are incorrectly sized.
+ *
+ * Returns NULL if check passes, otherwise const char * to name of cache
+ * to indicate an error.
+ */
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page)
+{
+ struct kmem_cache *s;
+ unsigned long offset;
+ size_t object_size;
+
+ /* Find object and usable object size. */
+ s = page->slab_cache;
+ object_size = slab_ksize(s);
+
+ /* Reject impossible pointers. */
+ if (ptr < page_address(page))
+ return s->name;
+
+ /* Find offset within object. */
+ offset = (ptr - page_address(page)) % s->size;
+
+ /* Adjust for redzone and reject if within the redzone. */
+ if (kmem_cache_debug(s) && s->flags & SLAB_RED_ZONE) {
+ if (offset < s->red_left_pad)
+ return s->name;
+ offset -= s->red_left_pad;
+ }
+
+ /* Allow address range falling entirely within object size. */
+ if (offset <= object_size && n <= object_size - offset)
+ return NULL;
+
+ return s->name;
+}
+#endif /* CONFIG_HARDENED_USERCOPY */
+
static size_t __ksize(const void *object)
{
struct page *page;
@@ -3626,7 +3743,7 @@ size_t ksize(const void *object)
size_t size = __ksize(object);
/* We assume that ksize callers could use whole allocated area,
so we need unpoison this area. */
- kasan_krealloc(object, size);
+ kasan_krealloc(object, size, GFP_NOWAIT);
return size;
}
EXPORT_SYMBOL(ksize);
@@ -4059,6 +4176,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
return ret;
}
+EXPORT_SYMBOL(__kmalloc_track_caller);
#ifdef CONFIG_NUMA
void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
@@ -4089,6 +4207,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
return ret;
}
+EXPORT_SYMBOL(__kmalloc_node_track_caller);
#endif
#ifdef CONFIG_SYSFS
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 4cba9c2783a1..c22065e02084 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -94,8 +94,8 @@ void __meminit vmemmap_verify(pte_t *pte, int node,
int actual_node = early_pfn_to_nid(pfn);
if (node_distance(actual_node, node) > LOCAL_DISTANCE)
- printk(KERN_WARNING "[%lx-%lx] potential offnode "
- "page_structs\n", start, end - 1);
+ printk(KERN_WARNING "[%lx-%lx] potential offnode page_structs\n",
+ start, end - 1);
}
pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
@@ -220,8 +220,8 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
if (map_map[pnum])
continue;
ms = __nr_to_section(pnum);
- printk(KERN_ERR "%s: sparsemem memory map backing failed "
- "some memory will not be available.\n", __func__);
+ printk(KERN_ERR "%s: sparsemem memory map backing failed some memory will not be available.\n",
+ __func__);
ms->section_mem_map = 0;
}
diff --git a/mm/sparse.c b/mm/sparse.c
index d1b48b691ac8..1b7543a775a4 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -428,8 +428,8 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
if (map_map[pnum])
continue;
ms = __nr_to_section(pnum);
- printk(KERN_ERR "%s: sparsemem memory map backing failed "
- "some memory will not be available.\n", __func__);
+ printk(KERN_ERR "%s: sparsemem memory map backing failed some memory will not be available.\n",
+ __func__);
ms->section_mem_map = 0;
}
}
@@ -456,8 +456,8 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
if (map)
return map;
- printk(KERN_ERR "%s: sparsemem memory map backing failed "
- "some memory will not be available.\n", __func__);
+ printk(KERN_ERR "%s: sparsemem memory map backing failed some memory will not be available.\n",
+ __func__);
ms->section_mem_map = 0;
return NULL;
}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b338d8829239..dea145ed1868 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2560,8 +2560,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
(swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map);
- pr_info("Adding %uk swap on %s. "
- "Priority:%d extents:%d across:%lluk %s%s%s%s%s\n",
+ pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s%s\n",
p->pages<<(PAGE_SHIFT-10), name->name, p->prio,
nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
diff --git a/mm/usercopy.c b/mm/usercopy.c
new file mode 100644
index 000000000000..b34996a3860b
--- /dev/null
+++ b/mm/usercopy.c
@@ -0,0 +1,278 @@
+/*
+ * This implements the various checks for CONFIG_HARDENED_USERCOPY*,
+ * which are designed to protect kernel memory from needless exposure
+ * and overwrite under many unintended conditions. This code is based
+ * on PAX_USERCOPY, which is:
+ *
+ * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source
+ * Security Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <asm/sections.h>
+
+enum {
+ BAD_STACK = -1,
+ NOT_STACK = 0,
+ GOOD_FRAME,
+ GOOD_STACK,
+};
+
+/*
+ * Checks if a given pointer and length is contained by the current
+ * stack frame (if possible).
+ *
+ * Returns:
+ * NOT_STACK: not at all on the stack
+ * GOOD_FRAME: fully within a valid stack frame
+ * GOOD_STACK: fully on the stack (when can't do frame-checking)
+ * BAD_STACK: error condition (invalid stack position or bad stack frame)
+ */
+static noinline int check_stack_object(const void *obj, unsigned long len)
+{
+ const void * const stack = task_stack_page(current);
+ const void * const stackend = stack + THREAD_SIZE;
+ int ret;
+
+ /* Object is not on the stack at all. */
+ if (obj + len <= stack || stackend <= obj)
+ return NOT_STACK;
+
+ /*
+ * Reject: object partially overlaps the stack (passing the
+ * the check above means at least one end is within the stack,
+ * so if this check fails, the other end is outside the stack).
+ */
+ if (obj < stack || stackend < obj + len)
+ return BAD_STACK;
+
+ /* Check if object is safely within a valid frame. */
+ ret = arch_within_stack_frames(stack, stackend, obj, len);
+ if (ret)
+ return ret;
+
+ return GOOD_STACK;
+}
+
+static void report_usercopy(const void *ptr, unsigned long len,
+ bool to_user, const char *type)
+{
+ pr_emerg("kernel memory %s attempt detected %s %p (%s) (%lu bytes)\n",
+ to_user ? "exposure" : "overwrite",
+ to_user ? "from" : "to", ptr, type ? : "unknown", len);
+ /*
+ * For greater effect, it would be nice to do do_group_exit(),
+ * but BUG() actually hooks all the lock-breaking and per-arch
+ * Oops code, so that is used here instead.
+ */
+ BUG();
+}
+
+/* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */
+static bool overlaps(const void *ptr, unsigned long n, unsigned long low,
+ unsigned long high)
+{
+ unsigned long check_low = (uintptr_t)ptr;
+ unsigned long check_high = check_low + n;
+
+ /* Does not overlap if entirely above or entirely below. */
+ if (check_low >= high || check_high <= low)
+ return false;
+
+ return true;
+}
+
+/* Is this address range in the kernel text area? */
+static inline const char *check_kernel_text_object(const void *ptr,
+ unsigned long n)
+{
+ unsigned long textlow = (unsigned long)_stext;
+ unsigned long texthigh = (unsigned long)_etext;
+ unsigned long textlow_linear, texthigh_linear;
+
+ if (overlaps(ptr, n, textlow, texthigh))
+ return "<kernel text>";
+
+ /*
+ * Some architectures have virtual memory mappings with a secondary
+ * mapping of the kernel text, i.e. there is more than one virtual
+ * kernel address that points to the kernel image. It is usually
+ * when there is a separate linear physical memory mapping, in that
+ * __pa() is not just the reverse of __va(). This can be detected
+ * and checked:
+ */
+ textlow_linear = (unsigned long)__va(__pa(textlow));
+ /* No different mapping: we're done. */
+ if (textlow_linear == textlow)
+ return NULL;
+
+ /* Check the secondary mapping... */
+ texthigh_linear = (unsigned long)__va(__pa(texthigh));
+ if (overlaps(ptr, n, textlow_linear, texthigh_linear))
+ return "<linear kernel text>";
+
+ return NULL;
+}
+
+static inline const char *check_bogus_address(const void *ptr, unsigned long n)
+{
+ /* Reject if object wraps past end of memory. */
+ if ((unsigned long)ptr + n < (unsigned long)ptr)
+ return "<wrapped address>";
+
+ /* Reject if NULL or ZERO-allocation. */
+ if (ZERO_OR_NULL_PTR(ptr))
+ return "<null>";
+
+ return NULL;
+}
+
+/* Checks for allocs that are marked in some way as spanning multiple pages. */
+static inline const char *check_page_span(const void *ptr, unsigned long n,
+ struct page *page, bool to_user)
+{
+#ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN
+ const void *end = ptr + n - 1;
+ struct page *endpage;
+ bool is_reserved, is_cma;
+
+ /*
+ * Sometimes the kernel data regions are not marked Reserved (see
+ * check below). And sometimes [_sdata,_edata) does not cover
+ * rodata and/or bss, so check each range explicitly.
+ */
+
+ /* Allow reads of kernel rodata region (if not marked as Reserved). */
+ if (ptr >= (const void *)__start_rodata &&
+ end <= (const void *)__end_rodata) {
+ if (!to_user)
+ return "<rodata>";
+ return NULL;
+ }
+
+ /* Allow kernel data region (if not marked as Reserved). */
+ if (ptr >= (const void *)_sdata && end <= (const void *)_edata)
+ return NULL;
+
+ /* Allow kernel bss region (if not marked as Reserved). */
+ if (ptr >= (const void *)__bss_start &&
+ end <= (const void *)__bss_stop)
+ return NULL;
+
+ /* Is the object wholly within one base page? */
+ if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) ==
+ ((unsigned long)end & (unsigned long)PAGE_MASK)))
+ return NULL;
+
+ /* Allow if fully inside the same compound (__GFP_COMP) page. */
+ endpage = virt_to_head_page(end);
+ if (likely(endpage == page))
+ return NULL;
+
+ /*
+ * Reject if range is entirely either Reserved (i.e. special or
+ * device memory), or CMA. Otherwise, reject since the object spans
+ * several independently allocated pages.
+ */
+ is_reserved = PageReserved(page);
+ is_cma = is_migrate_cma_page(page);
+ if (!is_reserved && !is_cma)
+ return "<spans multiple pages>";
+
+ for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) {
+ page = virt_to_head_page(ptr);
+ if (is_reserved && !PageReserved(page))
+ return "<spans Reserved and non-Reserved pages>";
+ if (is_cma && !is_migrate_cma_page(page))
+ return "<spans CMA and non-CMA pages>";
+ }
+#endif
+
+ return NULL;
+}
+
+static inline const char *check_heap_object(const void *ptr, unsigned long n,
+ bool to_user)
+{
+ struct page *page;
+
+ /*
+ * Some architectures (arm64) return true for virt_addr_valid() on
+ * vmalloced addresses. Work around this by checking for vmalloc
+ * first.
+ */
+ if (is_vmalloc_addr(ptr))
+ return NULL;
+
+ if (!virt_addr_valid(ptr))
+ return NULL;
+
+ page = virt_to_head_page(ptr);
+
+ /* Check slab allocator for flags and size. */
+ if (PageSlab(page))
+ return __check_heap_object(ptr, n, page);
+
+ /* Verify object does not incorrectly span multiple pages. */
+ return check_page_span(ptr, n, page, to_user);
+}
+
+/*
+ * Validates that the given object is:
+ * - not bogus address
+ * - known-safe heap or stack object
+ * - not in kernel text
+ */
+void __check_object_size(const void *ptr, unsigned long n, bool to_user)
+{
+ const char *err;
+
+ /* Skip all tests if size is zero. */
+ if (!n)
+ return;
+
+ /* Check for invalid addresses. */
+ err = check_bogus_address(ptr, n);
+ if (err)
+ goto report;
+
+ /* Check for bad heap object. */
+ err = check_heap_object(ptr, n, to_user);
+ if (err)
+ goto report;
+
+ /* Check for bad stack object. */
+ switch (check_stack_object(ptr, n)) {
+ case NOT_STACK:
+ /* Object is not touching the current process stack. */
+ break;
+ case GOOD_FRAME:
+ case GOOD_STACK:
+ /*
+ * Object is either in the correct frame (when it
+ * is possible to check) or just generally on the
+ * process stack (when frame checking not available).
+ */
+ return;
+ default:
+ err = "<process stack>";
+ goto report;
+ }
+
+ /* Check for object in kernel to avoid text exposure. */
+ err = check_kernel_text_object(ptr, n);
+ if (!err)
+ return;
+
+report:
+ report_usercopy(ptr, n, to_user, err);
+}
+EXPORT_SYMBOL(__check_object_size);
diff --git a/mm/util.c b/mm/util.c
index db39235970c6..4d59b4ffe66b 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -372,6 +372,7 @@ struct address_space *page_mapping(struct page *page)
return NULL;
return page->mapping;
}
+EXPORT_SYMBOL(page_mapping);
int overcommit_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 5dafd41d0732..e44eb1aeec4a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -474,8 +474,8 @@ overflow:
goto retry;
}
if (printk_ratelimit())
- pr_warn("vmap allocation for size %lu failed: "
- "use vmalloc=<size> to increase size.\n", size);
+ pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n",
+ size);
kfree(va);
return ERR_PTR(-EBUSY);
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-16 15:11:40 +0000