mempolicy.c 29.8 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
 * Simple NUMA memory policy for the Linux kernel.
 *
 * Copyright 2003,2004 Andi Kleen, SuSE Labs.
 * Subject to the GNU Public License, version 2.
 *
 * NUMA policy allows the user to give hints in which node(s) memory should
 * be allocated.
 *
 * Support four policies per VMA and per process:
 *
 * The VMA policy has priority over the process policy for a page fault.
 *
 * interleave     Allocate memory interleaved over a set of nodes,
 *                with normal fallback if it fails.
 *                For VMA based allocations this interleaves based on the
 *                offset into the backing object or offset into the mapping
 *                for anonymous memory. For process policy an process counter
 *                is used.
 * bind           Only allocate memory on a specific set of nodes,
 *                no fallback.
 * preferred       Try a specific node first before normal fallback.
 *                As a special case node -1 here means do the allocation
 *                on the local CPU. This is normally identical to default,
 *                but useful to set in a VMA when you have a non default
 *                process policy.
 * default        Allocate on the local node first, or when on a VMA
 *                use the process policy. This is what Linux always did
 *		  in a NUMA aware kernel and still does by, ahem, default.
 *
 * The process policy is applied for most non interrupt memory allocations
 * in that process' context. Interrupts ignore the policies and always
 * try to allocate on the local CPU. The VMA policy is only applied for memory
 * allocations for a VMA in the VM.
 *
 * Currently there are a few corner cases in swapping where the policy
 * is not applied, but the majority should be handled. When process policy
 * is used it is not remembered over swap outs/swap ins.
 *
 * Only the highest zone in the zone hierarchy gets policied. Allocations
 * requesting a lower zone just use default policy. This implies that
 * on systems with highmem kernel lowmem allocation don't get policied.
 * Same with GFP_DMA allocations.
 *
 * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between
 * all users and remembered even when nobody has memory mapped.
 */

/* Notebook:
   fix mmap readahead to honour policy and enable policy for any page cache
   object
   statistics for bigpages
   global policy for page cache? currently it uses process policy. Requires
   first item above.
   handle mremap for shared memory (currently ignored for the policy)
   grows down?
   make bind policy root only? It can trigger oom much faster and the
   kernel is not always grateful with that.
   could replace all the switch()es with a mempolicy_ops structure.
*/

#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/nodemask.h>
#include <linux/cpuset.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compat.h>
#include <linux/mempolicy.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.h>

static kmem_cache_t *policy_cache;
static kmem_cache_t *sn_cache;

#define PDprintk(fmt...)

/* Highest zone. An specific allocation for a zone below that is not
   policied. */
static int policy_zone;

91
struct mempolicy default_policy = {
L
Linus Torvalds 已提交
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
	.refcnt = ATOMIC_INIT(1), /* never free it */
	.policy = MPOL_DEFAULT,
};

/* Check if all specified nodes are online */
static int nodes_online(unsigned long *nodes)
{
	DECLARE_BITMAP(online2, MAX_NUMNODES);

	bitmap_copy(online2, nodes_addr(node_online_map), MAX_NUMNODES);
	if (bitmap_empty(online2, MAX_NUMNODES))
		set_bit(0, online2);
	if (!bitmap_subset(nodes, online2, MAX_NUMNODES))
		return -EINVAL;
	return 0;
}

/* Do sanity checking on a policy */
static int mpol_check_policy(int mode, unsigned long *nodes)
{
	int empty = bitmap_empty(nodes, MAX_NUMNODES);

	switch (mode) {
	case MPOL_DEFAULT:
		if (!empty)
			return -EINVAL;
		break;
	case MPOL_BIND:
	case MPOL_INTERLEAVE:
		/* Preferred will only use the first bit, but allow
		   more for now. */
		if (empty)
			return -EINVAL;
		break;
	}
	return nodes_online(nodes);
}

/* Copy a node mask from user space. */
static int get_nodes(unsigned long *nodes, unsigned long __user *nmask,
		     unsigned long maxnode, int mode)
{
	unsigned long k;
	unsigned long nlongs;
	unsigned long endmask;

	--maxnode;
	bitmap_zero(nodes, MAX_NUMNODES);
	if (maxnode == 0 || !nmask)
		return 0;

	nlongs = BITS_TO_LONGS(maxnode);
	if ((maxnode % BITS_PER_LONG) == 0)
		endmask = ~0UL;
	else
		endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;

	/* When the user specified more nodes than supported just check
	   if the non supported part is all zero. */
	if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
		if (nlongs > PAGE_SIZE/sizeof(long))
			return -EINVAL;
		for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
			unsigned long t;
			if (get_user(t,  nmask + k))
				return -EFAULT;
			if (k == nlongs - 1) {
				if (t & endmask)
					return -EINVAL;
			} else if (t)
				return -EINVAL;
		}
		nlongs = BITS_TO_LONGS(MAX_NUMNODES);
		endmask = ~0UL;
	}

	if (copy_from_user(nodes, nmask, nlongs*sizeof(unsigned long)))
		return -EFAULT;
	nodes[nlongs-1] &= endmask;
	/* Update current mems_allowed */
	cpuset_update_current_mems_allowed();
	/* Ignore nodes not set in current->mems_allowed */
	cpuset_restrict_to_mems_allowed(nodes);
	return mpol_check_policy(mode, nodes);
}

/* Generate a custom zonelist for the BIND policy. */
static struct zonelist *bind_zonelist(unsigned long *nodes)
{
	struct zonelist *zl;
	int num, max, nd;

	max = 1 + MAX_NR_ZONES * bitmap_weight(nodes, MAX_NUMNODES);
	zl = kmalloc(sizeof(void *) * max, GFP_KERNEL);
	if (!zl)
		return NULL;
	num = 0;
	for (nd = find_first_bit(nodes, MAX_NUMNODES);
	     nd < MAX_NUMNODES;
	     nd = find_next_bit(nodes, MAX_NUMNODES, 1+nd)) {
		int k;
		for (k = MAX_NR_ZONES-1; k >= 0; k--) {
			struct zone *z = &NODE_DATA(nd)->node_zones[k];
			if (!z->present_pages)
				continue;
			zl->zones[num++] = z;
			if (k > policy_zone)
				policy_zone = k;
		}
	}
	BUG_ON(num >= max);
	zl->zones[num] = NULL;
	return zl;
}

/* Create a new policy */
static struct mempolicy *mpol_new(int mode, unsigned long *nodes)
{
	struct mempolicy *policy;

	PDprintk("setting mode %d nodes[0] %lx\n", mode, nodes[0]);
	if (mode == MPOL_DEFAULT)
		return NULL;
	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
	if (!policy)
		return ERR_PTR(-ENOMEM);
	atomic_set(&policy->refcnt, 1);
	switch (mode) {
	case MPOL_INTERLEAVE:
		bitmap_copy(policy->v.nodes, nodes, MAX_NUMNODES);
		break;
	case MPOL_PREFERRED:
		policy->v.preferred_node = find_first_bit(nodes, MAX_NUMNODES);
		if (policy->v.preferred_node >= MAX_NUMNODES)
			policy->v.preferred_node = -1;
		break;
	case MPOL_BIND:
		policy->v.zonelist = bind_zonelist(nodes);
		if (policy->v.zonelist == NULL) {
			kmem_cache_free(policy_cache, policy);
			return ERR_PTR(-ENOMEM);
		}
		break;
	}
	policy->policy = mode;
	return policy;
}

/* Ensure all existing pages follow the policy. */
241 242
static int check_pte_range(struct mm_struct *mm, pmd_t *pmd,
		unsigned long addr, unsigned long end, unsigned long *nodes)
L
Linus Torvalds 已提交
243
{
244 245
	pte_t *orig_pte;
	pte_t *pte;
246 247

	spin_lock(&mm->page_table_lock);
248 249 250 251 252 253
	orig_pte = pte = pte_offset_map(pmd, addr);
	do {
		unsigned long pfn;
		unsigned int nid;

		if (!pte_present(*pte))
L
Linus Torvalds 已提交
254
			continue;
255 256
		pfn = pte_pfn(*pte);
		if (!pfn_valid(pfn))
L
Linus Torvalds 已提交
257
			continue;
258 259 260 261 262
		nid = pfn_to_nid(pfn);
		if (!test_bit(nid, nodes))
			break;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap(orig_pte);
263
	spin_unlock(&mm->page_table_lock);
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
	return addr != end;
}

static inline int check_pmd_range(struct mm_struct *mm, pud_t *pud,
		unsigned long addr, unsigned long end, unsigned long *nodes)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		if (check_pte_range(mm, pmd, addr, next, nodes))
			return -EIO;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int check_pud_range(struct mm_struct *mm, pgd_t *pgd,
		unsigned long addr, unsigned long end, unsigned long *nodes)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		if (check_pmd_range(mm, pud, addr, next, nodes))
			return -EIO;
	} while (pud++, addr = next, addr != end);
	return 0;
}

static inline int check_pgd_range(struct mm_struct *mm,
		unsigned long addr, unsigned long end, unsigned long *nodes)
{
	pgd_t *pgd;
	unsigned long next;

	pgd = pgd_offset(mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		if (check_pud_range(mm, pgd, addr, next, nodes))
			return -EIO;
	} while (pgd++, addr = next, addr != end);
	return 0;
L
Linus Torvalds 已提交
316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335
}

/* Step 1: check the range */
static struct vm_area_struct *
check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
	    unsigned long *nodes, unsigned long flags)
{
	int err;
	struct vm_area_struct *first, *vma, *prev;

	first = find_vma(mm, start);
	if (!first)
		return ERR_PTR(-EFAULT);
	prev = NULL;
	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
		if (!vma->vm_next && vma->vm_end < end)
			return ERR_PTR(-EFAULT);
		if (prev && prev->vm_end < vma->vm_start)
			return ERR_PTR(-EFAULT);
		if ((flags & MPOL_MF_STRICT) && !is_vm_hugetlb_page(vma)) {
A
Andi Kleen 已提交
336 337 338 339 340
			unsigned long endvma = vma->vm_end;
			if (endvma > end)
				endvma = end;
			if (vma->vm_start > start)
				start = vma->vm_start;
341
			err = check_pgd_range(vma->vm_mm,
A
Andi Kleen 已提交
342
					   start, endvma, nodes);
L
Linus Torvalds 已提交
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
			if (err) {
				first = ERR_PTR(err);
				break;
			}
		}
		prev = vma;
	}
	return first;
}

/* Apply policy to a single VMA */
static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
{
	int err = 0;
	struct mempolicy *old = vma->vm_policy;

	PDprintk("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
		 vma->vm_start, vma->vm_end, vma->vm_pgoff,
		 vma->vm_ops, vma->vm_file,
		 vma->vm_ops ? vma->vm_ops->set_policy : NULL);

	if (vma->vm_ops && vma->vm_ops->set_policy)
		err = vma->vm_ops->set_policy(vma, new);
	if (!err) {
		mpol_get(new);
		vma->vm_policy = new;
		mpol_free(old);
	}
	return err;
}

/* Step 2: apply policy to a range and do splits. */
static int mbind_range(struct vm_area_struct *vma, unsigned long start,
		       unsigned long end, struct mempolicy *new)
{
	struct vm_area_struct *next;
	int err;

	err = 0;
	for (; vma && vma->vm_start < end; vma = next) {
		next = vma->vm_next;
		if (vma->vm_start < start)
			err = split_vma(vma->vm_mm, vma, start, 1);
		if (!err && vma->vm_end > end)
			err = split_vma(vma->vm_mm, vma, end, 0);
		if (!err)
			err = policy_vma(vma, new);
		if (err)
			break;
	}
	return err;
}

/* Change policy for a memory range */
asmlinkage long sys_mbind(unsigned long start, unsigned long len,
			  unsigned long mode,
			  unsigned long __user *nmask, unsigned long maxnode,
			  unsigned flags)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm = current->mm;
	struct mempolicy *new;
	unsigned long end;
	DECLARE_BITMAP(nodes, MAX_NUMNODES);
	int err;

	if ((flags & ~(unsigned long)(MPOL_MF_STRICT)) || mode > MPOL_MAX)
		return -EINVAL;
	if (start & ~PAGE_MASK)
		return -EINVAL;
	if (mode == MPOL_DEFAULT)
		flags &= ~MPOL_MF_STRICT;
	len = (len + PAGE_SIZE - 1) & PAGE_MASK;
	end = start + len;
	if (end < start)
		return -EINVAL;
	if (end == start)
		return 0;

	err = get_nodes(nodes, nmask, maxnode, mode);
	if (err)
		return err;

	new = mpol_new(mode, nodes);
	if (IS_ERR(new))
		return PTR_ERR(new);

	PDprintk("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,
			mode,nodes[0]);

	down_write(&mm->mmap_sem);
	vma = check_range(mm, start, end, nodes, flags);
	err = PTR_ERR(vma);
	if (!IS_ERR(vma))
		err = mbind_range(vma, start, end, new);
	up_write(&mm->mmap_sem);
	mpol_free(new);
	return err;
}

/* Set the process memory policy */
asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
				   unsigned long maxnode)
{
	int err;
	struct mempolicy *new;
	DECLARE_BITMAP(nodes, MAX_NUMNODES);

451
	if (mode < 0 || mode > MPOL_MAX)
L
Linus Torvalds 已提交
452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671
		return -EINVAL;
	err = get_nodes(nodes, nmask, maxnode, mode);
	if (err)
		return err;
	new = mpol_new(mode, nodes);
	if (IS_ERR(new))
		return PTR_ERR(new);
	mpol_free(current->mempolicy);
	current->mempolicy = new;
	if (new && new->policy == MPOL_INTERLEAVE)
		current->il_next = find_first_bit(new->v.nodes, MAX_NUMNODES);
	return 0;
}

/* Fill a zone bitmap for a policy */
static void get_zonemask(struct mempolicy *p, unsigned long *nodes)
{
	int i;

	bitmap_zero(nodes, MAX_NUMNODES);
	switch (p->policy) {
	case MPOL_BIND:
		for (i = 0; p->v.zonelist->zones[i]; i++)
			__set_bit(p->v.zonelist->zones[i]->zone_pgdat->node_id, nodes);
		break;
	case MPOL_DEFAULT:
		break;
	case MPOL_INTERLEAVE:
		bitmap_copy(nodes, p->v.nodes, MAX_NUMNODES);
		break;
	case MPOL_PREFERRED:
		/* or use current node instead of online map? */
		if (p->v.preferred_node < 0)
			bitmap_copy(nodes, nodes_addr(node_online_map), MAX_NUMNODES);
		else
			__set_bit(p->v.preferred_node, nodes);
		break;
	default:
		BUG();
	}
}

static int lookup_node(struct mm_struct *mm, unsigned long addr)
{
	struct page *p;
	int err;

	err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, 0, &p, NULL);
	if (err >= 0) {
		err = page_to_nid(p);
		put_page(p);
	}
	return err;
}

/* Copy a kernel node mask to user space */
static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
			      void *nodes, unsigned nbytes)
{
	unsigned long copy = ALIGN(maxnode-1, 64) / 8;

	if (copy > nbytes) {
		if (copy > PAGE_SIZE)
			return -EINVAL;
		if (clear_user((char __user *)mask + nbytes, copy - nbytes))
			return -EFAULT;
		copy = nbytes;
	}
	return copy_to_user(mask, nodes, copy) ? -EFAULT : 0;
}

/* Retrieve NUMA policy */
asmlinkage long sys_get_mempolicy(int __user *policy,
				  unsigned long __user *nmask,
				  unsigned long maxnode,
				  unsigned long addr, unsigned long flags)
{
	int err, pval;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = NULL;
	struct mempolicy *pol = current->mempolicy;

	if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR))
		return -EINVAL;
	if (nmask != NULL && maxnode < MAX_NUMNODES)
		return -EINVAL;
	if (flags & MPOL_F_ADDR) {
		down_read(&mm->mmap_sem);
		vma = find_vma_intersection(mm, addr, addr+1);
		if (!vma) {
			up_read(&mm->mmap_sem);
			return -EFAULT;
		}
		if (vma->vm_ops && vma->vm_ops->get_policy)
			pol = vma->vm_ops->get_policy(vma, addr);
		else
			pol = vma->vm_policy;
	} else if (addr)
		return -EINVAL;

	if (!pol)
		pol = &default_policy;

	if (flags & MPOL_F_NODE) {
		if (flags & MPOL_F_ADDR) {
			err = lookup_node(mm, addr);
			if (err < 0)
				goto out;
			pval = err;
		} else if (pol == current->mempolicy &&
				pol->policy == MPOL_INTERLEAVE) {
			pval = current->il_next;
		} else {
			err = -EINVAL;
			goto out;
		}
	} else
		pval = pol->policy;

	if (vma) {
		up_read(&current->mm->mmap_sem);
		vma = NULL;
	}

	if (policy && put_user(pval, policy))
		return -EFAULT;

	err = 0;
	if (nmask) {
		DECLARE_BITMAP(nodes, MAX_NUMNODES);
		get_zonemask(pol, nodes);
		err = copy_nodes_to_user(nmask, maxnode, nodes, sizeof(nodes));
	}

 out:
	if (vma)
		up_read(&current->mm->mmap_sem);
	return err;
}

#ifdef CONFIG_COMPAT

asmlinkage long compat_sys_get_mempolicy(int __user *policy,
				     compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode,
				     compat_ulong_t addr, compat_ulong_t flags)
{
	long err;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask)
		nm = compat_alloc_user_space(alloc_size);

	err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);

	if (!err && nmask) {
		err = copy_from_user(bm, nm, alloc_size);
		/* ensure entire bitmap is zeroed */
		err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8);
		err |= compat_put_bitmap(nmask, bm, nr_bits);
	}

	return err;
}

asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(bm, nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, bm, alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_set_mempolicy(mode, nm, nr_bits+1);
}

asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
			     compat_ulong_t mode, compat_ulong_t __user *nmask,
			     compat_ulong_t maxnode, compat_ulong_t flags)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(bm, nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, bm, alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}

#endif

/* Return effective policy for a VMA */
672 673
struct mempolicy *
get_vma_policy(struct task_struct *task, struct vm_area_struct *vma, unsigned long addr)
L
Linus Torvalds 已提交
674
{
675
	struct mempolicy *pol = task->mempolicy;
L
Linus Torvalds 已提交
676 677 678 679 680 681 682 683 684 685 686 687 688 689

	if (vma) {
		if (vma->vm_ops && vma->vm_ops->get_policy)
		        pol = vma->vm_ops->get_policy(vma, addr);
		else if (vma->vm_policy &&
				vma->vm_policy->policy != MPOL_DEFAULT)
			pol = vma->vm_policy;
	}
	if (!pol)
		pol = &default_policy;
	return pol;
}

/* Return a zonelist representing a mempolicy */
A
Al Viro 已提交
690
static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
L
Linus Torvalds 已提交
691 692 693 694 695 696 697 698 699 700 701 702
{
	int nd;

	switch (policy->policy) {
	case MPOL_PREFERRED:
		nd = policy->v.preferred_node;
		if (nd < 0)
			nd = numa_node_id();
		break;
	case MPOL_BIND:
		/* Lower zones don't get a policy applied */
		/* Careful: current->mems_allowed might have moved */
A
Al Viro 已提交
703
		if (gfp_zone(gfp) >= policy_zone)
L
Linus Torvalds 已提交
704 705 706 707 708 709 710 711 712 713 714
			if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist))
				return policy->v.zonelist;
		/*FALL THROUGH*/
	case MPOL_INTERLEAVE: /* should not happen */
	case MPOL_DEFAULT:
		nd = numa_node_id();
		break;
	default:
		nd = 0;
		BUG();
	}
A
Al Viro 已提交
715
	return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
L
Linus Torvalds 已提交
716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753
}

/* Do dynamic interleaving for a process */
static unsigned interleave_nodes(struct mempolicy *policy)
{
	unsigned nid, next;
	struct task_struct *me = current;

	nid = me->il_next;
	BUG_ON(nid >= MAX_NUMNODES);
	next = find_next_bit(policy->v.nodes, MAX_NUMNODES, 1+nid);
	if (next >= MAX_NUMNODES)
		next = find_first_bit(policy->v.nodes, MAX_NUMNODES);
	me->il_next = next;
	return nid;
}

/* Do static interleaving for a VMA with known offset. */
static unsigned offset_il_node(struct mempolicy *pol,
		struct vm_area_struct *vma, unsigned long off)
{
	unsigned nnodes = bitmap_weight(pol->v.nodes, MAX_NUMNODES);
	unsigned target = (unsigned)off % nnodes;
	int c;
	int nid = -1;

	c = 0;
	do {
		nid = find_next_bit(pol->v.nodes, MAX_NUMNODES, nid+1);
		c++;
	} while (c <= target);
	BUG_ON(nid >= MAX_NUMNODES);
	BUG_ON(!test_bit(nid, pol->v.nodes));
	return nid;
}

/* Allocate a page in interleaved policy.
   Own path because it needs to do special accounting. */
A
Al Viro 已提交
754
static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, unsigned nid)
L
Linus Torvalds 已提交
755 756 757 758 759
{
	struct zonelist *zl;
	struct page *page;

	BUG_ON(!node_online(nid));
A
Al Viro 已提交
760
	zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
L
Linus Torvalds 已提交
761 762
	page = __alloc_pages(gfp, order, zl);
	if (page && page_zone(page) == zl->zones[0]) {
763
		zone_pcp(zl->zones[0],get_cpu())->interleave_hit++;
L
Linus Torvalds 已提交
764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791
		put_cpu();
	}
	return page;
}

/**
 * 	alloc_page_vma	- Allocate a page for a VMA.
 *
 * 	@gfp:
 *      %GFP_USER    user allocation.
 *      %GFP_KERNEL  kernel allocations,
 *      %GFP_HIGHMEM highmem/user allocations,
 *      %GFP_FS      allocation should not call back into a file system.
 *      %GFP_ATOMIC  don't sleep.
 *
 * 	@vma:  Pointer to VMA or NULL if not available.
 *	@addr: Virtual Address of the allocation. Must be inside the VMA.
 *
 * 	This function allocates a page from the kernel page pool and applies
 *	a NUMA policy associated with the VMA or the current process.
 *	When VMA is not NULL caller must hold down_read on the mmap_sem of the
 *	mm_struct of the VMA to prevent it from going away. Should be used for
 *	all allocations for pages that will be mapped into
 * 	user space. Returns NULL when no page can be allocated.
 *
 *	Should be called with the mm_sem of the vma hold.
 */
struct page *
A
Al Viro 已提交
792
alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
L
Linus Torvalds 已提交
793
{
794
	struct mempolicy *pol = get_vma_policy(current, vma, addr);
L
Linus Torvalds 已提交
795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834

	cpuset_update_current_mems_allowed();

	if (unlikely(pol->policy == MPOL_INTERLEAVE)) {
		unsigned nid;
		if (vma) {
			unsigned long off;
			BUG_ON(addr >= vma->vm_end);
			BUG_ON(addr < vma->vm_start);
			off = vma->vm_pgoff;
			off += (addr - vma->vm_start) >> PAGE_SHIFT;
			nid = offset_il_node(pol, vma, off);
		} else {
			/* fall back to process interleaving */
			nid = interleave_nodes(pol);
		}
		return alloc_page_interleave(gfp, 0, nid);
	}
	return __alloc_pages(gfp, 0, zonelist_policy(gfp, pol));
}

/**
 * 	alloc_pages_current - Allocate pages.
 *
 *	@gfp:
 *		%GFP_USER   user allocation,
 *      	%GFP_KERNEL kernel allocation,
 *      	%GFP_HIGHMEM highmem allocation,
 *      	%GFP_FS     don't call back into a file system.
 *      	%GFP_ATOMIC don't sleep.
 *	@order: Power of two of allocation size in pages. 0 is a single page.
 *
 *	Allocate a page from the kernel page pool.  When not in
 *	interrupt context and apply the current process NUMA policy.
 *	Returns NULL when no page can be allocated.
 *
 *	Don't call cpuset_update_current_mems_allowed() unless
 *	1) it's ok to take cpuset_sem (can WAIT), and
 *	2) allocating for current task (not interrupt).
 */
A
Al Viro 已提交
835
struct page *alloc_pages_current(gfp_t gfp, unsigned order)
L
Linus Torvalds 已提交
836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915
{
	struct mempolicy *pol = current->mempolicy;

	if ((gfp & __GFP_WAIT) && !in_interrupt())
		cpuset_update_current_mems_allowed();
	if (!pol || in_interrupt())
		pol = &default_policy;
	if (pol->policy == MPOL_INTERLEAVE)
		return alloc_page_interleave(gfp, order, interleave_nodes(pol));
	return __alloc_pages(gfp, order, zonelist_policy(gfp, pol));
}
EXPORT_SYMBOL(alloc_pages_current);

/* Slow path of a mempolicy copy */
struct mempolicy *__mpol_copy(struct mempolicy *old)
{
	struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);

	if (!new)
		return ERR_PTR(-ENOMEM);
	*new = *old;
	atomic_set(&new->refcnt, 1);
	if (new->policy == MPOL_BIND) {
		int sz = ksize(old->v.zonelist);
		new->v.zonelist = kmalloc(sz, SLAB_KERNEL);
		if (!new->v.zonelist) {
			kmem_cache_free(policy_cache, new);
			return ERR_PTR(-ENOMEM);
		}
		memcpy(new->v.zonelist, old->v.zonelist, sz);
	}
	return new;
}

/* Slow path of a mempolicy comparison */
int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	if (!a || !b)
		return 0;
	if (a->policy != b->policy)
		return 0;
	switch (a->policy) {
	case MPOL_DEFAULT:
		return 1;
	case MPOL_INTERLEAVE:
		return bitmap_equal(a->v.nodes, b->v.nodes, MAX_NUMNODES);
	case MPOL_PREFERRED:
		return a->v.preferred_node == b->v.preferred_node;
	case MPOL_BIND: {
		int i;
		for (i = 0; a->v.zonelist->zones[i]; i++)
			if (a->v.zonelist->zones[i] != b->v.zonelist->zones[i])
				return 0;
		return b->v.zonelist->zones[i] == NULL;
	}
	default:
		BUG();
		return 0;
	}
}

/* Slow path of a mpol destructor. */
void __mpol_free(struct mempolicy *p)
{
	if (!atomic_dec_and_test(&p->refcnt))
		return;
	if (p->policy == MPOL_BIND)
		kfree(p->v.zonelist);
	p->policy = MPOL_DEFAULT;
	kmem_cache_free(policy_cache, p);
}

/*
 * Hugetlb policy. Same as above, just works with node numbers instead of
 * zonelists.
 */

/* Find first node suitable for an allocation */
int mpol_first_node(struct vm_area_struct *vma, unsigned long addr)
{
916
	struct mempolicy *pol = get_vma_policy(current, vma, addr);
L
Linus Torvalds 已提交
917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935

	switch (pol->policy) {
	case MPOL_DEFAULT:
		return numa_node_id();
	case MPOL_BIND:
		return pol->v.zonelist->zones[0]->zone_pgdat->node_id;
	case MPOL_INTERLEAVE:
		return interleave_nodes(pol);
	case MPOL_PREFERRED:
		return pol->v.preferred_node >= 0 ?
				pol->v.preferred_node : numa_node_id();
	}
	BUG();
	return 0;
}

/* Find secondary valid nodes for an allocation */
int mpol_node_valid(int nid, struct vm_area_struct *vma, unsigned long addr)
{
936
	struct mempolicy *pol = get_vma_policy(current, vma, addr);
L
Linus Torvalds 已提交
937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145

	switch (pol->policy) {
	case MPOL_PREFERRED:
	case MPOL_DEFAULT:
	case MPOL_INTERLEAVE:
		return 1;
	case MPOL_BIND: {
		struct zone **z;
		for (z = pol->v.zonelist->zones; *z; z++)
			if ((*z)->zone_pgdat->node_id == nid)
				return 1;
		return 0;
	}
	default:
		BUG();
		return 0;
	}
}

/*
 * Shared memory backing store policy support.
 *
 * Remember policies even when nobody has shared memory mapped.
 * The policies are kept in Red-Black tree linked from the inode.
 * They are protected by the sp->lock spinlock, which should be held
 * for any accesses to the tree.
 */

/* lookup first element intersecting start-end */
/* Caller holds sp->lock */
static struct sp_node *
sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
{
	struct rb_node *n = sp->root.rb_node;

	while (n) {
		struct sp_node *p = rb_entry(n, struct sp_node, nd);

		if (start >= p->end)
			n = n->rb_right;
		else if (end <= p->start)
			n = n->rb_left;
		else
			break;
	}
	if (!n)
		return NULL;
	for (;;) {
		struct sp_node *w = NULL;
		struct rb_node *prev = rb_prev(n);
		if (!prev)
			break;
		w = rb_entry(prev, struct sp_node, nd);
		if (w->end <= start)
			break;
		n = prev;
	}
	return rb_entry(n, struct sp_node, nd);
}

/* Insert a new shared policy into the list. */
/* Caller holds sp->lock */
static void sp_insert(struct shared_policy *sp, struct sp_node *new)
{
	struct rb_node **p = &sp->root.rb_node;
	struct rb_node *parent = NULL;
	struct sp_node *nd;

	while (*p) {
		parent = *p;
		nd = rb_entry(parent, struct sp_node, nd);
		if (new->start < nd->start)
			p = &(*p)->rb_left;
		else if (new->end > nd->end)
			p = &(*p)->rb_right;
		else
			BUG();
	}
	rb_link_node(&new->nd, parent, p);
	rb_insert_color(&new->nd, &sp->root);
	PDprintk("inserting %lx-%lx: %d\n", new->start, new->end,
		 new->policy ? new->policy->policy : 0);
}

/* Find shared policy intersecting idx */
struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
{
	struct mempolicy *pol = NULL;
	struct sp_node *sn;

	if (!sp->root.rb_node)
		return NULL;
	spin_lock(&sp->lock);
	sn = sp_lookup(sp, idx, idx+1);
	if (sn) {
		mpol_get(sn->policy);
		pol = sn->policy;
	}
	spin_unlock(&sp->lock);
	return pol;
}

static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
	PDprintk("deleting %lx-l%x\n", n->start, n->end);
	rb_erase(&n->nd, &sp->root);
	mpol_free(n->policy);
	kmem_cache_free(sn_cache, n);
}

struct sp_node *
sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol)
{
	struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL);

	if (!n)
		return NULL;
	n->start = start;
	n->end = end;
	mpol_get(pol);
	n->policy = pol;
	return n;
}

/* Replace a policy range. */
static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
				 unsigned long end, struct sp_node *new)
{
	struct sp_node *n, *new2 = NULL;

restart:
	spin_lock(&sp->lock);
	n = sp_lookup(sp, start, end);
	/* Take care of old policies in the same range. */
	while (n && n->start < end) {
		struct rb_node *next = rb_next(&n->nd);
		if (n->start >= start) {
			if (n->end <= end)
				sp_delete(sp, n);
			else
				n->start = end;
		} else {
			/* Old policy spanning whole new range. */
			if (n->end > end) {
				if (!new2) {
					spin_unlock(&sp->lock);
					new2 = sp_alloc(end, n->end, n->policy);
					if (!new2)
						return -ENOMEM;
					goto restart;
				}
				n->end = start;
				sp_insert(sp, new2);
				new2 = NULL;
				break;
			} else
				n->end = start;
		}
		if (!next)
			break;
		n = rb_entry(next, struct sp_node, nd);
	}
	if (new)
		sp_insert(sp, new);
	spin_unlock(&sp->lock);
	if (new2) {
		mpol_free(new2->policy);
		kmem_cache_free(sn_cache, new2);
	}
	return 0;
}

int mpol_set_shared_policy(struct shared_policy *info,
			struct vm_area_struct *vma, struct mempolicy *npol)
{
	int err;
	struct sp_node *new = NULL;
	unsigned long sz = vma_pages(vma);

	PDprintk("set_shared_policy %lx sz %lu %d %lx\n",
		 vma->vm_pgoff,
		 sz, npol? npol->policy : -1,
		npol ? npol->v.nodes[0] : -1);

	if (npol) {
		new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol);
		if (!new)
			return -ENOMEM;
	}
	err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
	if (err && new)
		kmem_cache_free(sn_cache, new);
	return err;
}

/* Free a backing policy store on inode delete. */
void mpol_free_shared_policy(struct shared_policy *p)
{
	struct sp_node *n;
	struct rb_node *next;

	if (!p->root.rb_node)
		return;
	spin_lock(&p->lock);
	next = rb_first(&p->root);
	while (next) {
		n = rb_entry(next, struct sp_node, nd);
		next = rb_next(&n->nd);
1146
		rb_erase(&n->nd, &p->root);
L
Linus Torvalds 已提交
1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
		mpol_free(n->policy);
		kmem_cache_free(sn_cache, n);
	}
	spin_unlock(&p->lock);
}

/* assumes fs == KERNEL_DS */
void __init numa_policy_init(void)
{
	policy_cache = kmem_cache_create("numa_policy",
					 sizeof(struct mempolicy),
					 0, SLAB_PANIC, NULL, NULL);

	sn_cache = kmem_cache_create("shared_policy_node",
				     sizeof(struct sp_node),
				     0, SLAB_PANIC, NULL, NULL);

	/* Set interleaving policy for system init. This way not all
	   the data structures allocated at system boot end up in node zero. */

	if (sys_set_mempolicy(MPOL_INTERLEAVE, nodes_addr(node_online_map),
							MAX_NUMNODES) < 0)
		printk("numa_policy_init: interleaving failed\n");
}

/* Reset policy of current process to default.
 * Assumes fs == KERNEL_DS */
void numa_default_policy(void)
{
	sys_set_mempolicy(MPOL_DEFAULT, NULL, 0);
}