mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-12-28 16:56:26 +00:00
9e9e085eff
When compiling kernel source 'make -j $(nproc)' with the up-and-running
KASAN-enabled kernel on a 256-core machine, the following soft lockup is
shown:
watchdog: BUG: soft lockup - CPU#28 stuck for 22s! [kworker/28:1:1760]
CPU: 28 PID: 1760 Comm: kworker/28:1 Kdump: loaded Not tainted 6.10.0-rc5 #95
Workqueue: events drain_vmap_area_work
RIP: 0010:smp_call_function_many_cond+0x1d8/0xbb0
Code: 38 c8 7c 08 84 c9 0f 85 49 08 00 00 8b 45 08 a8 01 74 2e 48 89 f1 49 89 f7 48 c1 e9 03 41 83 e7 07 4c 01 e9 41 83 c7 03 f3 90 <0f> b6 01 41 38 c7 7c 08 84 c0 0f 85 d4 06 00 00 8b 45 08 a8 01 75
RSP: 0018:ffffc9000cb3fb60 EFLAGS: 00000202
RAX: 0000000000000011 RBX: ffff8883bc4469c0 RCX: ffffed10776e9949
RDX: 0000000000000002 RSI: ffff8883bb74ca48 RDI: ffffffff8434dc50
RBP: ffff8883bb74ca40 R08: ffff888103585dc0 R09: ffff8884533a1800
R10: 0000000000000004 R11: ffffffffffffffff R12: ffffed1077888d39
R13: dffffc0000000000 R14: ffffed1077888d38 R15: 0000000000000003
FS: 0000000000000000(0000) GS:ffff8883bc400000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005577b5c8d158 CR3: 0000000004850000 CR4: 0000000000350ef0
Call Trace:
<IRQ>
? watchdog_timer_fn+0x2cd/0x390
? __pfx_watchdog_timer_fn+0x10/0x10
? __hrtimer_run_queues+0x300/0x6d0
? sched_clock_cpu+0x69/0x4e0
? __pfx___hrtimer_run_queues+0x10/0x10
? srso_return_thunk+0x5/0x5f
? ktime_get_update_offsets_now+0x7f/0x2a0
? srso_return_thunk+0x5/0x5f
? srso_return_thunk+0x5/0x5f
? hrtimer_interrupt+0x2ca/0x760
? __sysvec_apic_timer_interrupt+0x8c/0x2b0
? sysvec_apic_timer_interrupt+0x6a/0x90
</IRQ>
<TASK>
? asm_sysvec_apic_timer_interrupt+0x16/0x20
? smp_call_function_many_cond+0x1d8/0xbb0
? __pfx_do_kernel_range_flush+0x10/0x10
on_each_cpu_cond_mask+0x20/0x40
flush_tlb_kernel_range+0x19b/0x250
? srso_return_thunk+0x5/0x5f
? kasan_release_vmalloc+0xa7/0xc0
purge_vmap_node+0x357/0x820
? __pfx_purge_vmap_node+0x10/0x10
__purge_vmap_area_lazy+0x5b8/0xa10
drain_vmap_area_work+0x21/0x30
process_one_work+0x661/0x10b0
worker_thread+0x844/0x10e0
? srso_return_thunk+0x5/0x5f
? __kthread_parkme+0x82/0x140
? __pfx_worker_thread+0x10/0x10
kthread+0x2a5/0x370
? __pfx_kthread+0x10/0x10
ret_from_fork+0x30/0x70
? __pfx_kthread+0x10/0x10
ret_from_fork_asm+0x1a/0x30
</TASK>
Debugging Analysis:
1. The following ftrace log shows that the lockup CPU spends too much
time iterating vmap_nodes and flushing TLB when purging vm_area
structures. (Some info is trimmed).
kworker: funcgraph_entry: | drain_vmap_area_work() {
kworker: funcgraph_entry: | mutex_lock() {
kworker: funcgraph_entry: 1.092 us | __cond_resched();
kworker: funcgraph_exit: 3.306 us | }
... ...
kworker: funcgraph_entry: | flush_tlb_kernel_range() {
... ...
kworker: funcgraph_exit: # 7533.649 us | }
... ...
kworker: funcgraph_entry: 2.344 us | mutex_unlock();
kworker: funcgraph_exit: $ 23871554 us | }
The drain_vmap_area_work() spends over 23 seconds.
There are 2805 flush_tlb_kernel_range() calls in the ftrace log.
* One is called in __purge_vmap_area_lazy().
* Others are called by purge_vmap_node->kasan_release_vmalloc.
purge_vmap_node() iteratively releases kasan vmalloc
allocations and flushes TLB for each vmap_area.
- [Rough calculation] Each flush_tlb_kernel_range() runs
about 7.5ms.
-- 2804 * 7.5ms = 21.03 seconds.
-- That's why a soft lock is triggered.
2. Extending the soft lockup time can work around the issue (For example,
# echo 60 > /proc/sys/kernel/watchdog_thresh). This confirms the
above-mentioned speculation: drain_vmap_area_work() spends too much
time.
If we combine all TLB flush operations of the KASAN shadow virtual
address into one operation in the call path
'purge_vmap_node()->kasan_release_vmalloc()', the running time of
drain_vmap_area_work() can be saved greatly. The idea is from the
flush_tlb_kernel_range() call in __purge_vmap_area_lazy(). And, the
soft lockup won't be triggered.
Here is the test result based on 6.10:
[6.10 wo/ the patch]
1. ftrace latency profiling (record a trace if the latency > 20s).
echo 20000000 > /sys/kernel/debug/tracing/tracing_thresh
echo drain_vmap_area_work > /sys/kernel/debug/tracing/set_graph_function
echo function_graph > /sys/kernel/debug/tracing/current_tracer
echo 1 > /sys/kernel/debug/tracing/tracing_on
2. Run `make -j $(nproc)` to compile the kernel source
3. Once the soft lockup is reproduced, check the ftrace log:
cat /sys/kernel/debug/tracing/trace
# tracer: function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
76) $ 50412985 us | } /* __purge_vmap_area_lazy */
76) $ 50412997 us | } /* drain_vmap_area_work */
76) $ 29165911 us | } /* __purge_vmap_area_lazy */
76) $ 29165926 us | } /* drain_vmap_area_work */
91) $ 53629423 us | } /* __purge_vmap_area_lazy */
91) $ 53629434 us | } /* drain_vmap_area_work */
91) $ 28121014 us | } /* __purge_vmap_area_lazy */
91) $ 28121026 us | } /* drain_vmap_area_work */
[6.10 w/ the patch]
1. Repeat step 1-2 in "[6.10 wo/ the patch]"
2. The soft lockup is not triggered and ftrace log is empty.
cat /sys/kernel/debug/tracing/trace
# tracer: function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
3. Setting 'tracing_thresh' to 10/5 seconds does not get any ftrace
log.
4. Setting 'tracing_thresh' to 1 second gets ftrace log.
cat /sys/kernel/debug/tracing/trace
# tracer: function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
23) $ 1074942 us | } /* __purge_vmap_area_lazy */
23) $ 1074950 us | } /* drain_vmap_area_work */
The worst execution time of drain_vmap_area_work() is about 1 second.
Link: https://lore.kernel.org/lkml/ZqFlawuVnOMY2k3E@pc638.lan/
Link: https://lkml.kernel.org/r/20240726165246.31326-1-ahuang12@lenovo.com
Fixes: 282631cb24
("mm: vmalloc: remove global purge_vmap_area_root rb-tree")
Signed-off-by: Adrian Huang <ahuang12@lenovo.com>
Co-developed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Tested-by: Jiwei Sun <sunjw10@lenovo.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
661 lines
21 KiB
C
661 lines
21 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_KASAN_H
|
|
#define _LINUX_KASAN_H
|
|
|
|
#include <linux/bug.h>
|
|
#include <linux/kasan-enabled.h>
|
|
#include <linux/kasan-tags.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/static_key.h>
|
|
#include <linux/types.h>
|
|
|
|
struct kmem_cache;
|
|
struct page;
|
|
struct slab;
|
|
struct vm_struct;
|
|
struct task_struct;
|
|
|
|
#ifdef CONFIG_KASAN
|
|
|
|
#include <linux/linkage.h>
|
|
#include <asm/kasan.h>
|
|
|
|
#endif
|
|
|
|
typedef unsigned int __bitwise kasan_vmalloc_flags_t;
|
|
|
|
#define KASAN_VMALLOC_NONE ((__force kasan_vmalloc_flags_t)0x00u)
|
|
#define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u)
|
|
#define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u)
|
|
#define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u)
|
|
|
|
#define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */
|
|
#define KASAN_VMALLOC_TLB_FLUSH 0x2 /* TLB flush */
|
|
|
|
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
|
|
|
|
#include <linux/pgtable.h>
|
|
|
|
/* Software KASAN implementations use shadow memory. */
|
|
|
|
#ifdef CONFIG_KASAN_SW_TAGS
|
|
/* This matches KASAN_TAG_INVALID. */
|
|
#define KASAN_SHADOW_INIT 0xFE
|
|
#else
|
|
#define KASAN_SHADOW_INIT 0
|
|
#endif
|
|
|
|
#ifndef PTE_HWTABLE_PTRS
|
|
#define PTE_HWTABLE_PTRS 0
|
|
#endif
|
|
|
|
extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
|
|
extern pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS];
|
|
extern pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD];
|
|
extern pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD];
|
|
extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
|
|
|
|
int kasan_populate_early_shadow(const void *shadow_start,
|
|
const void *shadow_end);
|
|
|
|
#ifndef kasan_mem_to_shadow
|
|
static inline void *kasan_mem_to_shadow(const void *addr)
|
|
{
|
|
return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT)
|
|
+ KASAN_SHADOW_OFFSET;
|
|
}
|
|
#endif
|
|
|
|
int kasan_add_zero_shadow(void *start, unsigned long size);
|
|
void kasan_remove_zero_shadow(void *start, unsigned long size);
|
|
|
|
/* Enable reporting bugs after kasan_disable_current() */
|
|
extern void kasan_enable_current(void);
|
|
|
|
/* Disable reporting bugs for current task */
|
|
extern void kasan_disable_current(void);
|
|
|
|
#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
|
|
|
|
static inline int kasan_add_zero_shadow(void *start, unsigned long size)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void kasan_remove_zero_shadow(void *start,
|
|
unsigned long size)
|
|
{}
|
|
|
|
static inline void kasan_enable_current(void) {}
|
|
static inline void kasan_disable_current(void) {}
|
|
|
|
#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
|
|
|
|
#ifdef CONFIG_KASAN_HW_TAGS
|
|
|
|
#else /* CONFIG_KASAN_HW_TAGS */
|
|
|
|
#endif /* CONFIG_KASAN_HW_TAGS */
|
|
|
|
static inline bool kasan_has_integrated_init(void)
|
|
{
|
|
return kasan_hw_tags_enabled();
|
|
}
|
|
|
|
#ifdef CONFIG_KASAN
|
|
void __kasan_unpoison_range(const void *addr, size_t size);
|
|
static __always_inline void kasan_unpoison_range(const void *addr, size_t size)
|
|
{
|
|
if (kasan_enabled())
|
|
__kasan_unpoison_range(addr, size);
|
|
}
|
|
|
|
void __kasan_poison_pages(struct page *page, unsigned int order, bool init);
|
|
static __always_inline void kasan_poison_pages(struct page *page,
|
|
unsigned int order, bool init)
|
|
{
|
|
if (kasan_enabled())
|
|
__kasan_poison_pages(page, order, init);
|
|
}
|
|
|
|
bool __kasan_unpoison_pages(struct page *page, unsigned int order, bool init);
|
|
static __always_inline bool kasan_unpoison_pages(struct page *page,
|
|
unsigned int order, bool init)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_unpoison_pages(page, order, init);
|
|
return false;
|
|
}
|
|
|
|
void __kasan_poison_slab(struct slab *slab);
|
|
static __always_inline void kasan_poison_slab(struct slab *slab)
|
|
{
|
|
if (kasan_enabled())
|
|
__kasan_poison_slab(slab);
|
|
}
|
|
|
|
void __kasan_unpoison_new_object(struct kmem_cache *cache, void *object);
|
|
/**
|
|
* kasan_unpoison_new_object - Temporarily unpoison a new slab object.
|
|
* @cache: Cache the object belong to.
|
|
* @object: Pointer to the object.
|
|
*
|
|
* This function is intended for the slab allocator's internal use. It
|
|
* temporarily unpoisons an object from a newly allocated slab without doing
|
|
* anything else. The object must later be repoisoned by
|
|
* kasan_poison_new_object().
|
|
*/
|
|
static __always_inline void kasan_unpoison_new_object(struct kmem_cache *cache,
|
|
void *object)
|
|
{
|
|
if (kasan_enabled())
|
|
__kasan_unpoison_new_object(cache, object);
|
|
}
|
|
|
|
void __kasan_poison_new_object(struct kmem_cache *cache, void *object);
|
|
/**
|
|
* kasan_unpoison_new_object - Repoison a new slab object.
|
|
* @cache: Cache the object belong to.
|
|
* @object: Pointer to the object.
|
|
*
|
|
* This function is intended for the slab allocator's internal use. It
|
|
* repoisons an object that was previously unpoisoned by
|
|
* kasan_unpoison_new_object() without doing anything else.
|
|
*/
|
|
static __always_inline void kasan_poison_new_object(struct kmem_cache *cache,
|
|
void *object)
|
|
{
|
|
if (kasan_enabled())
|
|
__kasan_poison_new_object(cache, object);
|
|
}
|
|
|
|
void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
|
|
const void *object);
|
|
static __always_inline void * __must_check kasan_init_slab_obj(
|
|
struct kmem_cache *cache, const void *object)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_init_slab_obj(cache, object);
|
|
return (void *)object;
|
|
}
|
|
|
|
bool __kasan_slab_pre_free(struct kmem_cache *s, void *object,
|
|
unsigned long ip);
|
|
/**
|
|
* kasan_slab_pre_free - Check whether freeing a slab object is safe.
|
|
* @object: Object to be freed.
|
|
*
|
|
* This function checks whether freeing the given object is safe. It may
|
|
* check for double-free and invalid-free bugs and report them.
|
|
*
|
|
* This function is intended only for use by the slab allocator.
|
|
*
|
|
* @Return true if freeing the object is unsafe; false otherwise.
|
|
*/
|
|
static __always_inline bool kasan_slab_pre_free(struct kmem_cache *s,
|
|
void *object)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_slab_pre_free(s, object, _RET_IP_);
|
|
return false;
|
|
}
|
|
|
|
bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init,
|
|
bool still_accessible);
|
|
/**
|
|
* kasan_slab_free - Poison, initialize, and quarantine a slab object.
|
|
* @object: Object to be freed.
|
|
* @init: Whether to initialize the object.
|
|
* @still_accessible: Whether the object contents are still accessible.
|
|
*
|
|
* This function informs that a slab object has been freed and is not
|
|
* supposed to be accessed anymore, except when @still_accessible is set
|
|
* (indicating that the object is in a SLAB_TYPESAFE_BY_RCU cache and an RCU
|
|
* grace period might not have passed yet).
|
|
*
|
|
* For KASAN modes that have integrated memory initialization
|
|
* (kasan_has_integrated_init() == true), this function also initializes
|
|
* the object's memory. For other modes, the @init argument is ignored.
|
|
*
|
|
* This function might also take ownership of the object to quarantine it.
|
|
* When this happens, KASAN will defer freeing the object to a later
|
|
* stage and handle it internally until then. The return value indicates
|
|
* whether KASAN took ownership of the object.
|
|
*
|
|
* This function is intended only for use by the slab allocator.
|
|
*
|
|
* @Return true if KASAN took ownership of the object; false otherwise.
|
|
*/
|
|
static __always_inline bool kasan_slab_free(struct kmem_cache *s,
|
|
void *object, bool init,
|
|
bool still_accessible)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_slab_free(s, object, init, still_accessible);
|
|
return false;
|
|
}
|
|
|
|
void __kasan_kfree_large(void *ptr, unsigned long ip);
|
|
static __always_inline void kasan_kfree_large(void *ptr)
|
|
{
|
|
if (kasan_enabled())
|
|
__kasan_kfree_large(ptr, _RET_IP_);
|
|
}
|
|
|
|
void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
|
|
void *object, gfp_t flags, bool init);
|
|
static __always_inline void * __must_check kasan_slab_alloc(
|
|
struct kmem_cache *s, void *object, gfp_t flags, bool init)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_slab_alloc(s, object, flags, init);
|
|
return object;
|
|
}
|
|
|
|
void * __must_check __kasan_kmalloc(struct kmem_cache *s, const void *object,
|
|
size_t size, gfp_t flags);
|
|
static __always_inline void * __must_check kasan_kmalloc(struct kmem_cache *s,
|
|
const void *object, size_t size, gfp_t flags)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_kmalloc(s, object, size, flags);
|
|
return (void *)object;
|
|
}
|
|
|
|
void * __must_check __kasan_kmalloc_large(const void *ptr,
|
|
size_t size, gfp_t flags);
|
|
static __always_inline void * __must_check kasan_kmalloc_large(const void *ptr,
|
|
size_t size, gfp_t flags)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_kmalloc_large(ptr, size, flags);
|
|
return (void *)ptr;
|
|
}
|
|
|
|
void * __must_check __kasan_krealloc(const void *object,
|
|
size_t new_size, gfp_t flags);
|
|
static __always_inline void * __must_check kasan_krealloc(const void *object,
|
|
size_t new_size, gfp_t flags)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_krealloc(object, new_size, flags);
|
|
return (void *)object;
|
|
}
|
|
|
|
bool __kasan_mempool_poison_pages(struct page *page, unsigned int order,
|
|
unsigned long ip);
|
|
/**
|
|
* kasan_mempool_poison_pages - Check and poison a mempool page allocation.
|
|
* @page: Pointer to the page allocation.
|
|
* @order: Order of the allocation.
|
|
*
|
|
* This function is intended for kernel subsystems that cache page allocations
|
|
* to reuse them instead of freeing them back to page_alloc (e.g. mempool).
|
|
*
|
|
* This function is similar to kasan_mempool_poison_object() but operates on
|
|
* page allocations.
|
|
*
|
|
* Before the poisoned allocation can be reused, it must be unpoisoned via
|
|
* kasan_mempool_unpoison_pages().
|
|
*
|
|
* Return: true if the allocation can be safely reused; false otherwise.
|
|
*/
|
|
static __always_inline bool kasan_mempool_poison_pages(struct page *page,
|
|
unsigned int order)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_mempool_poison_pages(page, order, _RET_IP_);
|
|
return true;
|
|
}
|
|
|
|
void __kasan_mempool_unpoison_pages(struct page *page, unsigned int order,
|
|
unsigned long ip);
|
|
/**
|
|
* kasan_mempool_unpoison_pages - Unpoison a mempool page allocation.
|
|
* @page: Pointer to the page allocation.
|
|
* @order: Order of the allocation.
|
|
*
|
|
* This function is intended for kernel subsystems that cache page allocations
|
|
* to reuse them instead of freeing them back to page_alloc (e.g. mempool).
|
|
*
|
|
* This function unpoisons a page allocation that was previously poisoned by
|
|
* kasan_mempool_poison_pages() without zeroing the allocation's memory. For
|
|
* the tag-based modes, this function assigns a new tag to the allocation.
|
|
*/
|
|
static __always_inline void kasan_mempool_unpoison_pages(struct page *page,
|
|
unsigned int order)
|
|
{
|
|
if (kasan_enabled())
|
|
__kasan_mempool_unpoison_pages(page, order, _RET_IP_);
|
|
}
|
|
|
|
bool __kasan_mempool_poison_object(void *ptr, unsigned long ip);
|
|
/**
|
|
* kasan_mempool_poison_object - Check and poison a mempool slab allocation.
|
|
* @ptr: Pointer to the slab allocation.
|
|
*
|
|
* This function is intended for kernel subsystems that cache slab allocations
|
|
* to reuse them instead of freeing them back to the slab allocator (e.g.
|
|
* mempool).
|
|
*
|
|
* This function poisons a slab allocation and saves a free stack trace for it
|
|
* without initializing the allocation's memory and without putting it into the
|
|
* quarantine (for the Generic mode).
|
|
*
|
|
* This function also performs checks to detect double-free and invalid-free
|
|
* bugs and reports them. The caller can use the return value of this function
|
|
* to find out if the allocation is buggy.
|
|
*
|
|
* Before the poisoned allocation can be reused, it must be unpoisoned via
|
|
* kasan_mempool_unpoison_object().
|
|
*
|
|
* This function operates on all slab allocations including large kmalloc
|
|
* allocations (the ones returned by kmalloc_large() or by kmalloc() with the
|
|
* size > KMALLOC_MAX_SIZE).
|
|
*
|
|
* Return: true if the allocation can be safely reused; false otherwise.
|
|
*/
|
|
static __always_inline bool kasan_mempool_poison_object(void *ptr)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_mempool_poison_object(ptr, _RET_IP_);
|
|
return true;
|
|
}
|
|
|
|
void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip);
|
|
/**
|
|
* kasan_mempool_unpoison_object - Unpoison a mempool slab allocation.
|
|
* @ptr: Pointer to the slab allocation.
|
|
* @size: Size to be unpoisoned.
|
|
*
|
|
* This function is intended for kernel subsystems that cache slab allocations
|
|
* to reuse them instead of freeing them back to the slab allocator (e.g.
|
|
* mempool).
|
|
*
|
|
* This function unpoisons a slab allocation that was previously poisoned via
|
|
* kasan_mempool_poison_object() and saves an alloc stack trace for it without
|
|
* initializing the allocation's memory. For the tag-based modes, this function
|
|
* does not assign a new tag to the allocation and instead restores the
|
|
* original tags based on the pointer value.
|
|
*
|
|
* This function operates on all slab allocations including large kmalloc
|
|
* allocations (the ones returned by kmalloc_large() or by kmalloc() with the
|
|
* size > KMALLOC_MAX_SIZE).
|
|
*/
|
|
static __always_inline void kasan_mempool_unpoison_object(void *ptr,
|
|
size_t size)
|
|
{
|
|
if (kasan_enabled())
|
|
__kasan_mempool_unpoison_object(ptr, size, _RET_IP_);
|
|
}
|
|
|
|
/*
|
|
* Unlike kasan_check_read/write(), kasan_check_byte() is performed even for
|
|
* the hardware tag-based mode that doesn't rely on compiler instrumentation.
|
|
*/
|
|
bool __kasan_check_byte(const void *addr, unsigned long ip);
|
|
static __always_inline bool kasan_check_byte(const void *addr)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_check_byte(addr, _RET_IP_);
|
|
return true;
|
|
}
|
|
|
|
#else /* CONFIG_KASAN */
|
|
|
|
static inline void kasan_unpoison_range(const void *address, size_t size) {}
|
|
static inline void kasan_poison_pages(struct page *page, unsigned int order,
|
|
bool init) {}
|
|
static inline bool kasan_unpoison_pages(struct page *page, unsigned int order,
|
|
bool init)
|
|
{
|
|
return false;
|
|
}
|
|
static inline void kasan_poison_slab(struct slab *slab) {}
|
|
static inline void kasan_unpoison_new_object(struct kmem_cache *cache,
|
|
void *object) {}
|
|
static inline void kasan_poison_new_object(struct kmem_cache *cache,
|
|
void *object) {}
|
|
static inline void *kasan_init_slab_obj(struct kmem_cache *cache,
|
|
const void *object)
|
|
{
|
|
return (void *)object;
|
|
}
|
|
|
|
static inline bool kasan_slab_pre_free(struct kmem_cache *s, void *object)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
|
|
bool init, bool still_accessible)
|
|
{
|
|
return false;
|
|
}
|
|
static inline void kasan_kfree_large(void *ptr) {}
|
|
static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
|
|
gfp_t flags, bool init)
|
|
{
|
|
return object;
|
|
}
|
|
static inline void *kasan_kmalloc(struct kmem_cache *s, const void *object,
|
|
size_t size, gfp_t flags)
|
|
{
|
|
return (void *)object;
|
|
}
|
|
static inline void *kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags)
|
|
{
|
|
return (void *)ptr;
|
|
}
|
|
static inline void *kasan_krealloc(const void *object, size_t new_size,
|
|
gfp_t flags)
|
|
{
|
|
return (void *)object;
|
|
}
|
|
static inline bool kasan_mempool_poison_pages(struct page *page, unsigned int order)
|
|
{
|
|
return true;
|
|
}
|
|
static inline void kasan_mempool_unpoison_pages(struct page *page, unsigned int order) {}
|
|
static inline bool kasan_mempool_poison_object(void *ptr)
|
|
{
|
|
return true;
|
|
}
|
|
static inline void kasan_mempool_unpoison_object(void *ptr, size_t size) {}
|
|
|
|
static inline bool kasan_check_byte(const void *address)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
#endif /* CONFIG_KASAN */
|
|
|
|
#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
|
|
void kasan_unpoison_task_stack(struct task_struct *task);
|
|
asmlinkage void kasan_unpoison_task_stack_below(const void *watermark);
|
|
#else
|
|
static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
|
|
static inline void kasan_unpoison_task_stack_below(const void *watermark) {}
|
|
#endif
|
|
|
|
#ifdef CONFIG_KASAN_GENERIC
|
|
|
|
struct kasan_cache {
|
|
int alloc_meta_offset;
|
|
int free_meta_offset;
|
|
};
|
|
|
|
size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object);
|
|
void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
|
|
slab_flags_t *flags);
|
|
|
|
void kasan_cache_shrink(struct kmem_cache *cache);
|
|
void kasan_cache_shutdown(struct kmem_cache *cache);
|
|
void kasan_record_aux_stack(void *ptr);
|
|
void kasan_record_aux_stack_noalloc(void *ptr);
|
|
|
|
#else /* CONFIG_KASAN_GENERIC */
|
|
|
|
/* Tag-based KASAN modes do not use per-object metadata. */
|
|
static inline size_t kasan_metadata_size(struct kmem_cache *cache,
|
|
bool in_object)
|
|
{
|
|
return 0;
|
|
}
|
|
/* And no cache-related metadata initialization is required. */
|
|
static inline void kasan_cache_create(struct kmem_cache *cache,
|
|
unsigned int *size,
|
|
slab_flags_t *flags) {}
|
|
|
|
static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
|
|
static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}
|
|
static inline void kasan_record_aux_stack(void *ptr) {}
|
|
static inline void kasan_record_aux_stack_noalloc(void *ptr) {}
|
|
|
|
#endif /* CONFIG_KASAN_GENERIC */
|
|
|
|
#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
|
|
|
|
static inline void *kasan_reset_tag(const void *addr)
|
|
{
|
|
return (void *)arch_kasan_reset_tag(addr);
|
|
}
|
|
|
|
/**
|
|
* kasan_report - print a report about a bad memory access detected by KASAN
|
|
* @addr: address of the bad access
|
|
* @size: size of the bad access
|
|
* @is_write: whether the bad access is a write or a read
|
|
* @ip: instruction pointer for the accessibility check or the bad access itself
|
|
*/
|
|
bool kasan_report(const void *addr, size_t size,
|
|
bool is_write, unsigned long ip);
|
|
|
|
#else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
|
|
|
|
static inline void *kasan_reset_tag(const void *addr)
|
|
{
|
|
return (void *)addr;
|
|
}
|
|
|
|
#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS*/
|
|
|
|
#ifdef CONFIG_KASAN_HW_TAGS
|
|
|
|
void kasan_report_async(void);
|
|
|
|
#endif /* CONFIG_KASAN_HW_TAGS */
|
|
|
|
#ifdef CONFIG_KASAN_SW_TAGS
|
|
void __init kasan_init_sw_tags(void);
|
|
#else
|
|
static inline void kasan_init_sw_tags(void) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_KASAN_HW_TAGS
|
|
void kasan_init_hw_tags_cpu(void);
|
|
void __init kasan_init_hw_tags(void);
|
|
#else
|
|
static inline void kasan_init_hw_tags_cpu(void) { }
|
|
static inline void kasan_init_hw_tags(void) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_KASAN_VMALLOC
|
|
|
|
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
|
|
|
|
void kasan_populate_early_vm_area_shadow(void *start, unsigned long size);
|
|
int kasan_populate_vmalloc(unsigned long addr, unsigned long size);
|
|
void kasan_release_vmalloc(unsigned long start, unsigned long end,
|
|
unsigned long free_region_start,
|
|
unsigned long free_region_end,
|
|
unsigned long flags);
|
|
|
|
#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
|
|
|
|
static inline void kasan_populate_early_vm_area_shadow(void *start,
|
|
unsigned long size)
|
|
{ }
|
|
static inline int kasan_populate_vmalloc(unsigned long start,
|
|
unsigned long size)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void kasan_release_vmalloc(unsigned long start,
|
|
unsigned long end,
|
|
unsigned long free_region_start,
|
|
unsigned long free_region_end,
|
|
unsigned long flags) { }
|
|
|
|
#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
|
|
|
|
void *__kasan_unpoison_vmalloc(const void *start, unsigned long size,
|
|
kasan_vmalloc_flags_t flags);
|
|
static __always_inline void *kasan_unpoison_vmalloc(const void *start,
|
|
unsigned long size,
|
|
kasan_vmalloc_flags_t flags)
|
|
{
|
|
if (kasan_enabled())
|
|
return __kasan_unpoison_vmalloc(start, size, flags);
|
|
return (void *)start;
|
|
}
|
|
|
|
void __kasan_poison_vmalloc(const void *start, unsigned long size);
|
|
static __always_inline void kasan_poison_vmalloc(const void *start,
|
|
unsigned long size)
|
|
{
|
|
if (kasan_enabled())
|
|
__kasan_poison_vmalloc(start, size);
|
|
}
|
|
|
|
#else /* CONFIG_KASAN_VMALLOC */
|
|
|
|
static inline void kasan_populate_early_vm_area_shadow(void *start,
|
|
unsigned long size) { }
|
|
static inline int kasan_populate_vmalloc(unsigned long start,
|
|
unsigned long size)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void kasan_release_vmalloc(unsigned long start,
|
|
unsigned long end,
|
|
unsigned long free_region_start,
|
|
unsigned long free_region_end,
|
|
unsigned long flags) { }
|
|
|
|
static inline void *kasan_unpoison_vmalloc(const void *start,
|
|
unsigned long size,
|
|
kasan_vmalloc_flags_t flags)
|
|
{
|
|
return (void *)start;
|
|
}
|
|
static inline void kasan_poison_vmalloc(const void *start, unsigned long size)
|
|
{ }
|
|
|
|
#endif /* CONFIG_KASAN_VMALLOC */
|
|
|
|
#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
|
|
!defined(CONFIG_KASAN_VMALLOC)
|
|
|
|
/*
|
|
* These functions allocate and free shadow memory for kernel modules.
|
|
* They are only required when KASAN_VMALLOC is not supported, as otherwise
|
|
* shadow memory is allocated by the generic vmalloc handlers.
|
|
*/
|
|
int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask);
|
|
void kasan_free_module_shadow(const struct vm_struct *vm);
|
|
|
|
#else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */
|
|
|
|
static inline int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask) { return 0; }
|
|
static inline void kasan_free_module_shadow(const struct vm_struct *vm) {}
|
|
|
|
#endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */
|
|
|
|
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
|
|
void kasan_non_canonical_hook(unsigned long addr);
|
|
#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
|
|
static inline void kasan_non_canonical_hook(unsigned long addr) { }
|
|
#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
|
|
|
|
#endif /* LINUX_KASAN_H */
|