summaryrefslogtreecommitdiff
path: root/include/linux/sched/mm.h
blob: e6770012db1819e3c8d2975ffbd1a9e84fdac372 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_MM_H
#define _LINUX_SCHED_MM_H

#include <linux/kernel.h>
#include <linux/atomic.h>
#include <linux/sched.h>
#include <linux/mm_types.h>
#include <linux/gfp.h>
#include <linux/sync_core.h>

/*
 * Routines for handling mm_structs
 */
extern struct mm_struct *mm_alloc(void);

/**
 * mmgrab() - Pin a &struct mm_struct.
 * @mm: The &struct mm_struct to pin.
 *
 * Make sure that @mm will not get freed even after the owning task
 * exits. This doesn't guarantee that the associated address space
 * will still exist later on and mmget_not_zero() has to be used before
 * accessing it.
 *
 * This is a preferred way to to pin @mm for a longer/unbounded amount
 * of time.
 *
 * Use mmdrop() to release the reference acquired by mmgrab().
 *
 * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
 * of &mm_struct.mm_count vs &mm_struct.mm_users.
 */
static inline void mmgrab(struct mm_struct *mm)
{
	atomic_inc(&mm->mm_count);
}

extern void __mmdrop(struct mm_struct *mm);

static inline void mmdrop(struct mm_struct *mm)
{
	/*
	 * The implicit full barrier implied by atomic_dec_and_test() is
	 * required by the membarrier system call before returning to
	 * user-space, after storing to rq->curr.
	 */
	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
		__mmdrop(mm);
}

/*
 * This has to be called after a get_task_mm()/mmget_not_zero()
 * followed by taking the mmap_sem for writing before modifying the
 * vmas or anything the coredump pretends not to change from under it.
 *
 * It also has to be called when mmgrab() is used in the context of
 * the process, but then the mm_count refcount is transferred outside
 * the context of the process to run down_write() on that pinned mm.
 *
 * NOTE: find_extend_vma() called from GUP context is the only place
 * that can modify the "mm" (notably the vm_start/end) under mmap_sem
 * for reading and outside the context of the process, so it is also
 * the only case that holds the mmap_sem for reading that must call
 * this function. Generally if the mmap_sem is hold for reading
 * there's no need of this check after get_task_mm()/mmget_not_zero().
 *
 * This function can be obsoleted and the check can be removed, after
 * the coredump code will hold the mmap_sem for writing before
 * invoking the ->core_dump methods.
 */
static inline bool mmget_still_valid(struct mm_struct *mm)
{
	return likely(!mm->core_state);
}

/**
 * mmget() - Pin the address space associated with a &struct mm_struct.
 * @mm: The address space to pin.
 *
 * Make sure that the address space of the given &struct mm_struct doesn't
 * go away. This does not protect against parts of the address space being
 * modified or freed, however.
 *
 * Never use this function to pin this address space for an
 * unbounded/indefinite amount of time.
 *
 * Use mmput() to release the reference acquired by mmget().
 *
 * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
 * of &mm_struct.mm_count vs &mm_struct.mm_users.
 */
static inline void mmget(struct mm_struct *mm)
{
	atomic_inc(&mm->mm_users);
}

static inline bool mmget_not_zero(struct mm_struct *mm)
{
	return atomic_inc_not_zero(&mm->mm_users);
}

/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
#ifdef CONFIG_MMU
/* same as above but performs the slow path from the async context. Can
 * be called from the atomic context as well
 */
void mmput_async(struct mm_struct *);
#endif

/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
/*
 * Grab a reference to a task's mm, if it is not already going away
 * and ptrace_may_access with the mode parameter passed to it
 * succeeds.
 */
extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);

#ifdef CONFIG_MEMCG
extern void mm_update_next_owner(struct mm_struct *mm);
#else
static inline void mm_update_next_owner(struct mm_struct *mm)
{
}
#endif /* CONFIG_MEMCG */

#ifdef CONFIG_MMU
extern void arch_pick_mmap_layout(struct mm_struct *mm,
				  struct rlimit *rlim_stack);
extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
		       unsigned long, unsigned long);
extern unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
			  unsigned long len, unsigned long pgoff,
			  unsigned long flags);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm,
					 struct rlimit *rlim_stack) {}
#endif

static inline bool in_vfork(struct task_struct *tsk)
{
	bool ret;

	/*
	 * need RCU to access ->real_parent if CLONE_VM was used along with
	 * CLONE_PARENT.
	 *
	 * We check real_parent->mm == tsk->mm because CLONE_VFORK does not
	 * imply CLONE_VM
	 *
	 * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus
	 * ->real_parent is not necessarily the task doing vfork(), so in
	 * theory we can't rely on task_lock() if we want to dereference it.
	 *
	 * And in this case we can't trust the real_parent->mm == tsk->mm
	 * check, it can be false negative. But we do not care, if init or
	 * another oom-unkillable task does this it should blame itself.
	 */
	rcu_read_lock();
	ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm;
	rcu_read_unlock();

	return ret;
}

/*
 * Applies per-task gfp context to the given allocation flags.
 * PF_MEMALLOC_NOIO implies GFP_NOIO
 * PF_MEMALLOC_NOFS implies GFP_NOFS
 * PF_MEMALLOC_NOCMA implies no allocation from CMA region.
 */
static inline gfp_t current_gfp_context(gfp_t flags)
{
	if (unlikely(current->flags &
		     (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
		/*
		 * NOIO implies both NOIO and NOFS and it is a weaker context
		 * so always make sure it makes precedence
		 */
		if (current->flags & PF_MEMALLOC_NOIO)
			flags &= ~(__GFP_IO | __GFP_FS);
		else if (current->flags & PF_MEMALLOC_NOFS)
			flags &= ~__GFP_FS;
#ifdef CONFIG_CMA
		if (current->flags & PF_MEMALLOC_NOCMA)
			flags &= ~__GFP_MOVABLE;
#endif
	}
	return flags;
}

#ifdef CONFIG_LOCKDEP
extern void __fs_reclaim_acquire(void);
extern void __fs_reclaim_release(void);
extern void fs_reclaim_acquire(gfp_t gfp_mask);
extern void fs_reclaim_release(gfp_t gfp_mask);
#else
static inline void __fs_reclaim_acquire(void) { }
static inline void __fs_reclaim_release(void) { }
static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
static inline void fs_reclaim_release(gfp_t gfp_mask) { }
#endif

/**
 * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
 *
 * This functions marks the beginning of the GFP_NOIO allocation scope.
 * All further allocations will implicitly drop __GFP_IO flag and so
 * they are safe for the IO critical section from the allocation recursion
 * point of view. Use memalloc_noio_restore to end the scope with flags
 * returned by this function.
 *
 * This function is safe to be used from any context.
 */
static inline unsigned int memalloc_noio_save(void)
{
	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
	current->flags |= PF_MEMALLOC_NOIO;
	return flags;
}

/**
 * memalloc_noio_restore - Ends the implicit GFP_NOIO scope.
 * @flags: Flags to restore.
 *
 * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
 * Always make sure that that the given flags is the return value from the
 * pairing memalloc_noio_save call.
 */
static inline void memalloc_noio_restore(unsigned int flags)
{
	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
}

/**
 * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope.
 *
 * This functions marks the beginning of the GFP_NOFS allocation scope.
 * All further allocations will implicitly drop __GFP_FS flag and so
 * they are safe for the FS critical section from the allocation recursion
 * point of view. Use memalloc_nofs_restore to end the scope with flags
 * returned by this function.
 *
 * This function is safe to be used from any context.
 */
static inline unsigned int memalloc_nofs_save(void)
{
	unsigned int flags = current->flags & PF_MEMALLOC_NOFS;
	current->flags |= PF_MEMALLOC_NOFS;
	return flags;
}

/**
 * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope.
 * @flags: Flags to restore.
 *
 * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
 * Always make sure that that the given flags is the return value from the
 * pairing memalloc_nofs_save call.
 */
static inline void memalloc_nofs_restore(unsigned int flags)
{
	current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags;
}

static inline unsigned int memalloc_noreclaim_save(void)
{
	unsigned int flags = current->flags & PF_MEMALLOC;
	current->flags |= PF_MEMALLOC;
	return flags;
}

static inline void memalloc_noreclaim_restore(unsigned int flags)
{
	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
}

#ifdef CONFIG_CMA
static inline unsigned int memalloc_nocma_save(void)
{
	unsigned int flags = current->flags & PF_MEMALLOC_NOCMA;

	current->flags |= PF_MEMALLOC_NOCMA;
	return flags;
}

static inline void memalloc_nocma_restore(unsigned int flags)
{
	current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags;
}
#else
static inline unsigned int memalloc_nocma_save(void)
{
	return 0;
}

static inline void memalloc_nocma_restore(unsigned int flags)
{
}
#endif

#ifdef CONFIG_MEMCG
/**
 * memalloc_use_memcg - Starts the remote memcg charging scope.
 * @memcg: memcg to charge.
 *
 * This function marks the beginning of the remote memcg charging scope. All the
 * __GFP_ACCOUNT allocations till the end of the scope will be charged to the
 * given memcg.
 *
 * NOTE: This function is not nesting safe.
 */
static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
{
	WARN_ON_ONCE(current->active_memcg);
	current->active_memcg = memcg;
}

/**
 * memalloc_unuse_memcg - Ends the remote memcg charging scope.
 *
 * This function marks the end of the remote memcg charging scope started by
 * memalloc_use_memcg().
 */
static inline void memalloc_unuse_memcg(void)
{
	current->active_memcg = NULL;
}
#else
static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
{
}

static inline void memalloc_unuse_memcg(void)
{
}
#endif

#ifdef CONFIG_MEMBARRIER
enum {
	MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY		= (1U << 0),
	MEMBARRIER_STATE_PRIVATE_EXPEDITED			= (1U << 1),
	MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY			= (1U << 2),
	MEMBARRIER_STATE_GLOBAL_EXPEDITED			= (1U << 3),
	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY	= (1U << 4),
	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE		= (1U << 5),
};

enum {
	MEMBARRIER_FLAG_SYNC_CORE	= (1U << 0),
};

#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
#include <asm/membarrier.h>
#endif

static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
{
	if (current->mm != mm)
		return;
	if (likely(!(atomic_read(&mm->membarrier_state) &
		     MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE)))
		return;
	sync_core_before_usermode();
}

extern void membarrier_exec_mmap(struct mm_struct *mm);

#else
#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
					     struct mm_struct *next,
					     struct task_struct *tsk)
{
}
#endif
static inline void membarrier_exec_mmap(struct mm_struct *mm)
{
}
static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
{
}
#endif

#endif /* _LINUX_SCHED_MM_H */