Free Electrons

Embedded Linux Experts

  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
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
#ifndef _LINUX_MM_TYPES_H
#define _LINUX_MM_TYPES_H

#include <linux/mm_types_task.h>

#include <linux/auxvec.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/rbtree.h>
#include <linux/rwsem.h>
#include <linux/completion.h>
#include <linux/cpumask.h>
#include <linux/uprobes.h>
#include <linux/page-flags-layout.h>
#include <linux/workqueue.h>

#include <asm/mmu.h>

#ifndef AT_VECTOR_SIZE_ARCH
#define AT_VECTOR_SIZE_ARCH 0
#endif
#define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))

struct address_space;
struct mem_cgroup;

/*
 * Each physical page in the system has a struct page associated with
 * it to keep track of whatever it is we are using the page for at the
 * moment. Note that we have no way to track which tasks are using
 * a page, though if it is a pagecache page, rmap structures can tell us
 * who is mapping it.
 *
 * The objects in struct page are organized in double word blocks in
 * order to allows us to use atomic double word operations on portions
 * of struct page. That is currently only used by slub but the arrangement
 * allows the use of atomic double word operations on the flags/mapping
 * and lru list pointers also.
 */
struct page {
	/* First double word block */
	unsigned long flags;		/* Atomic flags, some possibly
					 * updated asynchronously */
	union {
		struct address_space *mapping;	/* If low bit clear, points to
						 * inode address_space, or NULL.
						 * If page mapped as anonymous
						 * memory, low bit is set, and
						 * it points to anon_vma object:
						 * see PAGE_MAPPING_ANON below.
						 */
		void *s_mem;			/* slab first object */
		atomic_t compound_mapcount;	/* first tail page */
		/* page_deferred_list().next	 -- second tail page */
	};

	/* Second double word */
	union {
		pgoff_t index;		/* Our offset within mapping. */
		void *freelist;		/* sl[aou]b first free object */
		/* page_deferred_list().prev	-- second tail page */
	};

	union {
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
	defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
		/* Used for cmpxchg_double in slub */
		unsigned long counters;
#else
		/*
		 * Keep _refcount separate from slub cmpxchg_double data.
		 * As the rest of the double word is protected by slab_lock
		 * but _refcount is not.
		 */
		unsigned counters;
#endif
		struct {

			union {
				/*
				 * Count of ptes mapped in mms, to show when
				 * page is mapped & limit reverse map searches.
				 *
				 * Extra information about page type may be
				 * stored here for pages that are never mapped,
				 * in which case the value MUST BE <= -2.
				 * See page-flags.h for more details.
				 */
				atomic_t _mapcount;

				unsigned int active;		/* SLAB */
				struct {			/* SLUB */
					unsigned inuse:16;
					unsigned objects:15;
					unsigned frozen:1;
				};
				int units;			/* SLOB */
			};
			/*
			 * Usage count, *USE WRAPPER FUNCTION* when manual
			 * accounting. See page_ref.h
			 */
			atomic_t _refcount;
		};
	};

	/*
	 * Third double word block
	 *
	 * WARNING: bit 0 of the first word encode PageTail(). That means
	 * the rest users of the storage space MUST NOT use the bit to
	 * avoid collision and false-positive PageTail().
	 */
	union {
		struct list_head lru;	/* Pageout list, eg. active_list
					 * protected by zone_lru_lock !
					 * Can be used as a generic list
					 * by the page owner.
					 */
		struct dev_pagemap *pgmap; /* ZONE_DEVICE pages are never on an
					    * lru or handled by a slab
					    * allocator, this points to the
					    * hosting device page map.
					    */
		struct {		/* slub per cpu partial pages */
			struct page *next;	/* Next partial slab */
#ifdef CONFIG_64BIT
			int pages;	/* Nr of partial slabs left */
			int pobjects;	/* Approximate # of objects */
#else
			short int pages;
			short int pobjects;
#endif
		};

		struct rcu_head rcu_head;	/* Used by SLAB
						 * when destroying via RCU
						 */
		/* Tail pages of compound page */
		struct {
			unsigned long compound_head; /* If bit zero is set */

			/* First tail page only */
#ifdef CONFIG_64BIT
			/*
			 * On 64 bit system we have enough space in struct page
			 * to encode compound_dtor and compound_order with
			 * unsigned int. It can help compiler generate better or
			 * smaller code on some archtectures.
			 */
			unsigned int compound_dtor;
			unsigned int compound_order;
#else
			unsigned short int compound_dtor;
			unsigned short int compound_order;
#endif
		};

#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
		struct {
			unsigned long __pad;	/* do not overlay pmd_huge_pte
						 * with compound_head to avoid
						 * possible bit 0 collision.
						 */
			pgtable_t pmd_huge_pte; /* protected by page->ptl */
		};
#endif
	};

	/* Remainder is not double word aligned */
	union {
		unsigned long private;		/* Mapping-private opaque data:
					 	 * usually used for buffer_heads
						 * if PagePrivate set; used for
						 * swp_entry_t if PageSwapCache;
						 * indicates order in the buddy
						 * system if PG_buddy is set.
						 */
#if USE_SPLIT_PTE_PTLOCKS
#if ALLOC_SPLIT_PTLOCKS
		spinlock_t *ptl;
#else
		spinlock_t ptl;
#endif
#endif
		struct kmem_cache *slab_cache;	/* SL[AU]B: Pointer to slab */
	};

#ifdef CONFIG_MEMCG
	struct mem_cgroup *mem_cgroup;
#endif

	/*
	 * On machines where all RAM is mapped into kernel address space,
	 * we can simply calculate the virtual address. On machines with
	 * highmem some memory is mapped into kernel virtual memory
	 * dynamically, so we need a place to store that address.
	 * Note that this field could be 16 bits on x86 ... ;)
	 *
	 * Architectures with slow multiplication can define
	 * WANT_PAGE_VIRTUAL in asm/page.h
	 */
#if defined(WANT_PAGE_VIRTUAL)
	void *virtual;			/* Kernel virtual address (NULL if
					   not kmapped, ie. highmem) */
#endif /* WANT_PAGE_VIRTUAL */

#ifdef CONFIG_KMEMCHECK
	/*
	 * kmemcheck wants to track the status of each byte in a page; this
	 * is a pointer to such a status block. NULL if not tracked.
	 */
	void *shadow;
#endif

#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
	int _last_cpupid;
#endif
}
/*
 * The struct page can be forced to be double word aligned so that atomic ops
 * on double words work. The SLUB allocator can make use of such a feature.
 */
#ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE
	__aligned(2 * sizeof(unsigned long))
#endif
;

#define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
#define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)

struct page_frag_cache {
	void * va;
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
	__u16 offset;
	__u16 size;
#else
	__u32 offset;
#endif
	/* we maintain a pagecount bias, so that we dont dirty cache line
	 * containing page->_refcount every time we allocate a fragment.
	 */
	unsigned int		pagecnt_bias;
	bool pfmemalloc;
};

typedef unsigned long vm_flags_t;

/*
 * A region containing a mapping of a non-memory backed file under NOMMU
 * conditions.  These are held in a global tree and are pinned by the VMAs that
 * map parts of them.
 */
struct vm_region {
	struct rb_node	vm_rb;		/* link in global region tree */
	vm_flags_t	vm_flags;	/* VMA vm_flags */
	unsigned long	vm_start;	/* start address of region */
	unsigned long	vm_end;		/* region initialised to here */
	unsigned long	vm_top;		/* region allocated to here */
	unsigned long	vm_pgoff;	/* the offset in vm_file corresponding to vm_start */
	struct file	*vm_file;	/* the backing file or NULL */

	int		vm_usage;	/* region usage count (access under nommu_region_sem) */
	bool		vm_icache_flushed : 1; /* true if the icache has been flushed for
						* this region */
};

#ifdef CONFIG_USERFAULTFD
#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, })
struct vm_userfaultfd_ctx {
	struct userfaultfd_ctx *ctx;
};
#else /* CONFIG_USERFAULTFD */
#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {})
struct vm_userfaultfd_ctx {};
#endif /* CONFIG_USERFAULTFD */

/*
 * This struct defines a memory VMM memory area. There is one of these
 * per VM-area/task.  A VM area is any part of the process virtual memory
 * space that has a special rule for the page-fault handlers (ie a shared
 * library, the executable area etc).
 */
struct vm_area_struct {
	/* The first cache line has the info for VMA tree walking. */

	unsigned long vm_start;		/* Our start address within vm_mm. */
	unsigned long vm_end;		/* The first byte after our end address
					   within vm_mm. */

	/* linked list of VM areas per task, sorted by address */
	struct vm_area_struct *vm_next, *vm_prev;

	struct rb_node vm_rb;

	/*
	 * Largest free memory gap in bytes to the left of this VMA.
	 * Either between this VMA and vma->vm_prev, or between one of the
	 * VMAs below us in the VMA rbtree and its ->vm_prev. This helps
	 * get_unmapped_area find a free area of the right size.
	 */
	unsigned long rb_subtree_gap;

	/* Second cache line starts here. */

	struct mm_struct *vm_mm;	/* The address space we belong to. */
	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
	unsigned long vm_flags;		/* Flags, see mm.h. */

	/*
	 * For areas with an address space and backing store,
	 * linkage into the address_space->i_mmap interval tree.
	 */
	struct {
		struct rb_node rb;
		unsigned long rb_subtree_last;
	} shared;

	/*
	 * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
	 * list, after a COW of one of the file pages.	A MAP_SHARED vma
	 * can only be in the i_mmap tree.  An anonymous MAP_PRIVATE, stack
	 * or brk vma (with NULL file) can only be in an anon_vma list.
	 */
	struct list_head anon_vma_chain; /* Serialized by mmap_sem &
					  * page_table_lock */
	struct anon_vma *anon_vma;	/* Serialized by page_table_lock */

	/* Function pointers to deal with this struct. */
	const struct vm_operations_struct *vm_ops;

	/* Information about our backing store: */
	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
					   units */
	struct file * vm_file;		/* File we map to (can be NULL). */
	void * vm_private_data;		/* was vm_pte (shared mem) */

#ifndef CONFIG_MMU
	struct vm_region *vm_region;	/* NOMMU mapping region */
#endif
#ifdef CONFIG_NUMA
	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
#endif
	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
} __randomize_layout;

struct core_thread {
	struct task_struct *task;
	struct core_thread *next;
};

struct core_state {
	atomic_t nr_threads;
	struct core_thread dumper;
	struct completion startup;
};

struct kioctx_table;
struct mm_struct {
	struct vm_area_struct *mmap;		/* list of VMAs */
	struct rb_root mm_rb;
	u32 vmacache_seqnum;                   /* per-thread vmacache */
#ifdef CONFIG_MMU
	unsigned long (*get_unmapped_area) (struct file *filp,
				unsigned long addr, unsigned long len,
				unsigned long pgoff, unsigned long flags);
#endif
	unsigned long mmap_base;		/* base of mmap area */
	unsigned long mmap_legacy_base;         /* base of mmap area in bottom-up allocations */
#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
	/* Base adresses for compatible mmap() */
	unsigned long mmap_compat_base;
	unsigned long mmap_compat_legacy_base;
#endif
	unsigned long task_size;		/* size of task vm space */
	unsigned long highest_vm_end;		/* highest vma end address */
	pgd_t * pgd;

	/**
	 * @mm_users: The number of users including userspace.
	 *
	 * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops
	 * to 0 (i.e. when the task exits and there are no other temporary
	 * reference holders), we also release a reference on @mm_count
	 * (which may then free the &struct mm_struct if @mm_count also
	 * drops to 0).
	 */
	atomic_t mm_users;

	/**
	 * @mm_count: The number of references to &struct mm_struct
	 * (@mm_users count as 1).
	 *
	 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
	 * &struct mm_struct is freed.
	 */
	atomic_t mm_count;

	atomic_long_t nr_ptes;			/* PTE page table pages */
#if CONFIG_PGTABLE_LEVELS > 2
	atomic_long_t nr_pmds;			/* PMD page table pages */
#endif
	int map_count;				/* number of VMAs */

	spinlock_t page_table_lock;		/* Protects page tables and some counters */
	struct rw_semaphore mmap_sem;

	struct list_head mmlist;		/* List of maybe swapped mm's.	These are globally strung
						 * together off init_mm.mmlist, and are protected
						 * by mmlist_lock
						 */


	unsigned long hiwater_rss;	/* High-watermark of RSS usage */
	unsigned long hiwater_vm;	/* High-water virtual memory usage */

	unsigned long total_vm;		/* Total pages mapped */
	unsigned long locked_vm;	/* Pages that have PG_mlocked set */
	unsigned long pinned_vm;	/* Refcount permanently increased */
	unsigned long data_vm;		/* VM_WRITE & ~VM_SHARED & ~VM_STACK */
	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE & ~VM_STACK */
	unsigned long stack_vm;		/* VM_STACK */
	unsigned long def_flags;
	unsigned long start_code, end_code, start_data, end_data;
	unsigned long start_brk, brk, start_stack;
	unsigned long arg_start, arg_end, env_start, env_end;

	unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */

	/*
	 * Special counters, in some configurations protected by the
	 * page_table_lock, in other configurations by being atomic.
	 */
	struct mm_rss_stat rss_stat;

	struct linux_binfmt *binfmt;

	cpumask_var_t cpu_vm_mask_var;

	/* Architecture-specific MM context */
	mm_context_t context;

	unsigned long flags; /* Must use atomic bitops to access the bits */

	struct core_state *core_state; /* coredumping support */
#ifdef CONFIG_AIO
	spinlock_t			ioctx_lock;
	struct kioctx_table __rcu	*ioctx_table;
#endif
#ifdef CONFIG_MEMCG
	/*
	 * "owner" points to a task that is regarded as the canonical
	 * user/owner of this mm. All of the following must be true in
	 * order for it to be changed:
	 *
	 * current == mm->owner
	 * current->mm != mm
	 * new_owner->mm == mm
	 * new_owner->alloc_lock is held
	 */
	struct task_struct __rcu *owner;
#endif
	struct user_namespace *user_ns;

	/* store ref to file /proc/<pid>/exe symlink points to */
	struct file __rcu *exe_file;
#ifdef CONFIG_MMU_NOTIFIER
	struct mmu_notifier_mm *mmu_notifier_mm;
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
#endif
#ifdef CONFIG_CPUMASK_OFFSTACK
	struct cpumask cpumask_allocation;
#endif
#ifdef CONFIG_NUMA_BALANCING
	/*
	 * numa_next_scan is the next time that the PTEs will be marked
	 * pte_numa. NUMA hinting faults will gather statistics and migrate
	 * pages to new nodes if necessary.
	 */
	unsigned long numa_next_scan;

	/* Restart point for scanning and setting pte_numa */
	unsigned long numa_scan_offset;

	/* numa_scan_seq prevents two threads setting pte_numa */
	int numa_scan_seq;
#endif
	/*
	 * An operation with batched TLB flushing is going on. Anything that
	 * can move process memory needs to flush the TLB when moving a
	 * PROT_NONE or PROT_NUMA mapped page.
	 */
	atomic_t tlb_flush_pending;
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
	/* See flush_tlb_batched_pending() */
	bool tlb_flush_batched;
#endif
	struct uprobes_state uprobes_state;
#ifdef CONFIG_HUGETLB_PAGE
	atomic_long_t hugetlb_usage;
#endif
	struct work_struct async_put_work;
} __randomize_layout;

extern struct mm_struct init_mm;

static inline void mm_init_cpumask(struct mm_struct *mm)
{
#ifdef CONFIG_CPUMASK_OFFSTACK
	mm->cpu_vm_mask_var = &mm->cpumask_allocation;
#endif
	cpumask_clear(mm->cpu_vm_mask_var);
}

/* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
{
	return mm->cpu_vm_mask_var;
}

struct mmu_gather;
extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
				unsigned long start, unsigned long end);
extern void tlb_finish_mmu(struct mmu_gather *tlb,
				unsigned long start, unsigned long end);

/*
 * Memory barriers to keep this state in sync are graciously provided by
 * the page table locks, outside of which no page table modifications happen.
 * The barriers are used to ensure the order between tlb_flush_pending updates,
 * which happen while the lock is not taken, and the PTE updates, which happen
 * while the lock is taken, are serialized.
 */
static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
{
	return atomic_read(&mm->tlb_flush_pending) > 0;
}

/*
 * Returns true if there are two above TLB batching threads in parallel.
 */
static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
{
	return atomic_read(&mm->tlb_flush_pending) > 1;
}

static inline void init_tlb_flush_pending(struct mm_struct *mm)
{
	atomic_set(&mm->tlb_flush_pending, 0);
}

static inline void inc_tlb_flush_pending(struct mm_struct *mm)
{
	atomic_inc(&mm->tlb_flush_pending);

	/*
	 * Guarantee that the tlb_flush_pending increase does not leak into the
	 * critical section updating the page tables
	 */
	smp_mb__before_spinlock();
}

/* Clearing is done after a TLB flush, which also provides a barrier. */
static inline void dec_tlb_flush_pending(struct mm_struct *mm)
{
	/*
	 * Guarantee that the tlb_flush_pending does not not leak into the
	 * critical section, since we must order the PTE change and changes to
	 * the pending TLB flush indication. We could have relied on TLB flush
	 * as a memory barrier, but this behavior is not clearly documented.
	 */
	smp_mb__before_atomic();
	atomic_dec(&mm->tlb_flush_pending);
}

struct vm_fault;

struct vm_special_mapping {
	const char *name;	/* The name, e.g. "[vdso]". */

	/*
	 * If .fault is not provided, this points to a
	 * NULL-terminated array of pages that back the special mapping.
	 *
	 * This must not be NULL unless .fault is provided.
	 */
	struct page **pages;

	/*
	 * If non-NULL, then this is called to resolve page faults
	 * on the special mapping.  If used, .pages is not checked.
	 */
	int (*fault)(const struct vm_special_mapping *sm,
		     struct vm_area_struct *vma,
		     struct vm_fault *vmf);

	int (*mremap)(const struct vm_special_mapping *sm,
		     struct vm_area_struct *new_vma);
};

enum tlb_flush_reason {
	TLB_FLUSH_ON_TASK_SWITCH,
	TLB_REMOTE_SHOOTDOWN,
	TLB_LOCAL_SHOOTDOWN,
	TLB_LOCAL_MM_SHOOTDOWN,
	TLB_REMOTE_SEND_IPI,
	NR_TLB_FLUSH_REASONS,
};

 /*
  * A swap entry has to fit into a "unsigned long", as the entry is hidden
  * in the "index" field of the swapper address space.
  */
typedef struct {
	unsigned long val;
} swp_entry_t;

#endif /* _LINUX_MM_TYPES_H */