mempolicy.c

最新最稳定的Linux内存管理模块源代码

	err = security_task_movememory(task);
	if (err)
		goto out;

	err = do_migrate_pages(mm, &old, &new,
		capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
out:
	mmput(mm);
	return err;
}


/* Retrieve NUMA policy */
SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
		unsigned long __user *, nmask, unsigned long, maxnode,
		unsigned long, addr, unsigned long, flags)
{
	int err;
	int uninitialized_var(pval);
	nodemask_t nodes;

	if (nmask != NULL && maxnode < MAX_NUMNODES)
		return -EINVAL;

	err = do_get_mempolicy(&pval, &nodes, addr, flags);

	if (err)
		return err;

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

	if (nmask)
		err = copy_nodes_to_user(nmask, maxnode, &nodes);

	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;
	nodemask_t bm;

	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(nodes_addr(bm), nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
	}

	if (err)
		return -EFAULT;

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

#endif

/*
 * get_vma_policy(@task, @vma, @addr)
 * @task - task for fallback if vma policy == default
 * @vma   - virtual memory area whose policy is sought
 * @addr  - address in @vma for shared policy lookup
 *
 * Returns effective policy for a VMA at specified address.
 * Falls back to @task or system default policy, as necessary.
 * Current or other task's task mempolicy and non-shared vma policies
 * are protected by the task's mmap_sem, which must be held for read by
 * the caller.
 * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
 * count--added by the get_policy() vm_op, as appropriate--to protect against
 * freeing by another task.  It is the caller's responsibility to free the
 * extra reference for shared policies.
 */
static struct mempolicy *get_vma_policy(struct task_struct *task,
		struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol = task->mempolicy;

	if (vma) {
		if (vma->vm_ops && vma->vm_ops->get_policy) {
			struct mempolicy *vpol = vma->vm_ops->get_policy(vma,
									addr);
			if (vpol)
				pol = vpol;
		} else if (vma->vm_policy)
			pol = vma->vm_policy;
	}
	if (!pol)
		pol = &default_policy;
	return pol;
}

/*
 * Return a nodemask representing a mempolicy for filtering nodes for
 * page allocation
 */
static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
{
	/* Lower zones don't get a nodemask applied for MPOL_BIND */
	if (unlikely(policy->mode == MPOL_BIND) &&
			gfp_zone(gfp) >= policy_zone &&
			cpuset_nodemask_valid_mems_allowed(&policy->v.nodes))
		return &policy->v.nodes;

	return NULL;
}

/* Return a zonelist indicated by gfp for node representing a mempolicy */
static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy)
{
	int nd = numa_node_id();

	switch (policy->mode) {
	case MPOL_PREFERRED:
		if (!(policy->flags & MPOL_F_LOCAL))
			nd = policy->v.preferred_node;
		break;
	case MPOL_BIND:
		/*
		 * Normally, MPOL_BIND allocations are node-local within the
		 * allowed nodemask.  However, if __GFP_THISNODE is set and the
		 * current node is part of the mask, we use the zonelist for
		 * the first node in the mask instead.
		 */
		if (unlikely(gfp & __GFP_THISNODE) &&
				unlikely(!node_isset(nd, policy->v.nodes)))
			nd = first_node(policy->v.nodes);
		break;
	case MPOL_INTERLEAVE: /* should not happen */
		break;
	default:
		BUG();
	}
	return node_zonelist(nd, gfp);
}

/* 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;
	next = next_node(nid, policy->v.nodes);
	if (next >= MAX_NUMNODES)
		next = first_node(policy->v.nodes);
	if (next < MAX_NUMNODES)
		me->il_next = next;
	return nid;
}

/*
 * Depending on the memory policy provide a node from which to allocate the
 * next slab entry.
 * @policy must be protected by freeing by the caller.  If @policy is
 * the current task's mempolicy, this protection is implicit, as only the
 * task can change it's policy.  The system default policy requires no
 * such protection.
 */
unsigned slab_node(struct mempolicy *policy)
{
	if (!policy || policy->flags & MPOL_F_LOCAL)
		return numa_node_id();

	switch (policy->mode) {
	case MPOL_PREFERRED:
		/*
		 * handled MPOL_F_LOCAL above
		 */
		return policy->v.preferred_node;

	case MPOL_INTERLEAVE:
		return interleave_nodes(policy);

	case MPOL_BIND: {
		/*
		 * Follow bind policy behavior and start allocation at the
		 * first node.
		 */
		struct zonelist *zonelist;
		struct zone *zone;
		enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
		zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
		(void)first_zones_zonelist(zonelist, highest_zoneidx,
							&policy->v.nodes,
							&zone);
		return zone->node;
	}

	default:
		BUG();
	}
}

/* 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 = nodes_weight(pol->v.nodes);
	unsigned target;
	int c;
	int nid = -1;

	if (!nnodes)
		return numa_node_id();
	target = (unsigned int)off % nnodes;
	c = 0;
	do {
		nid = next_node(nid, pol->v.nodes);
		c++;
	} while (c <= target);
	return nid;
}

/* Determine a node number for interleave */
static inline unsigned interleave_nid(struct mempolicy *pol,
		 struct vm_area_struct *vma, unsigned long addr, int shift)
{
	if (vma) {
		unsigned long off;

		/*
		 * for small pages, there is no difference between
		 * shift and PAGE_SHIFT, so the bit-shift is safe.
		 * for huge pages, since vm_pgoff is in units of small
		 * pages, we need to shift off the always 0 bits to get
		 * a useful offset.
		 */
		BUG_ON(shift < PAGE_SHIFT);
		off = vma->vm_pgoff >> (shift - PAGE_SHIFT);
		off += (addr - vma->vm_start) >> shift;
		return offset_il_node(pol, vma, off);
	} else
		return interleave_nodes(pol);
}

#ifdef CONFIG_HUGETLBFS
/*
 * huge_zonelist(@vma, @addr, @gfp_flags, @mpol)
 * @vma = virtual memory area whose policy is sought
 * @addr = address in @vma for shared policy lookup and interleave policy
 * @gfp_flags = for requested zone
 * @mpol = pointer to mempolicy pointer for reference counted mempolicy
 * @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask
 *
 * Returns a zonelist suitable for a huge page allocation and a pointer
 * to the struct mempolicy for conditional unref after allocation.
 * If the effective policy is 'BIND, returns a pointer to the mempolicy's
 * @nodemask for filtering the zonelist.
 */
struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
				gfp_t gfp_flags, struct mempolicy **mpol,
				nodemask_t **nodemask)
{
	struct zonelist *zl;

	*mpol = get_vma_policy(current, vma, addr);
	*nodemask = NULL;	/* assume !MPOL_BIND */

	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
		zl = node_zonelist(interleave_nid(*mpol, vma, addr,
				huge_page_shift(hstate_vma(vma))), gfp_flags);
	} else {
		zl = policy_zonelist(gfp_flags, *mpol);
		if ((*mpol)->mode == MPOL_BIND)
			*nodemask = &(*mpol)->v.nodes;
	}
	return zl;
}
#endif

/* Allocate a page in interleaved policy.
   Own path because it needs to do special accounting. */
static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
					unsigned nid)
{
	struct zonelist *zl;
	struct page *page;

	zl = node_zonelist(nid, gfp);
	page = __alloc_pages(gfp, order, zl);
	if (page && page_zone(page) == zonelist_zone(&zl->_zonerefs[0]))
		inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
	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 *
alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol = get_vma_policy(current, vma, addr);
	struct zonelist *zl;

	cpuset_update_task_memory_state();

	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
		unsigned nid;

		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
		mpol_cond_put(pol);
		return alloc_page_interleave(gfp, 0, nid);
	}
	zl = policy_zonelist(gfp, pol);
	if (unlikely(mpol_needs_cond_ref(pol))) {
		/*
		 * slow path: ref counted shared policy
		 */
		struct page *page =  __alloc_pages_nodemask(gfp, 0,
						zl, policy_nodemask(gfp, pol));
		__mpol_put(pol);
		return page;
	}
	/*
	 * fast path:  default or task policy
	 */
	return __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(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_task_memory_state() unless
 *	1) it's ok to take cpuset_sem (can WAIT), and
 *	2) allocating for current task (not interrupt).
 */
struct page *alloc_pages_current(gfp_t gfp, unsigned order)
{
	struct mempolicy *pol = current->mempolicy;

	if ((gfp & __GFP_WAIT) && !in_interrupt())
		cpuset_update_task_memory_state();
	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
		pol = &default_policy;

	/*
	 * No reference counting needed for current->mempolicy
	 * nor system default_policy
	 */
	if (pol->mode == MPOL_INTERLEAVE)
		return alloc_page_interleave(gfp, order, interleave_nodes(pol));
	return __alloc_pages_nodemask(gfp, order,
			policy_zonelist(gfp, pol), policy_nodemask(gfp, pol));
}
EXPORT_SYMBOL(alloc_pages_current);

/*
 * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it
 * rebinds the mempolicy its copying by calling mpol_rebind_policy()
 * with the mems_allowed returned by cpuset_mems_allowed().  This
 * keeps mempolicies cpuset relative after its cpuset moves.  See
 * further kernel/cpuset.c update_nodemask().
 */

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

	if (!new)
		return ERR_PTR(-ENOMEM);
	if (current_cpuset_is_being_rebound()) {
		nodemask_t mems = cpuset_mems_allowed(current);
		mpol_rebind_policy(old, &mems);
	}
	*new = *old;
	atomic_set(&new->refcnt, 1);
	return new;
}

/*
 * If *frompol needs [has] an extra ref, copy *frompol to *tompol ,
 * eliminate the * MPOL_F_* flags that require conditional ref and
 * [NOTE!!!] drop the extra ref.  Not safe to reference *frompol directly
 * after return.  Use the returned value.
 *
 * Allows use of a mempolicy for, e.g., multiple allocations with a single
 * policy lookup, even if the policy needs/has extra ref on lookup.
 * shmem_readahead needs this.
 */
struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
						struct mempolicy *frompol)
{
	if (!mpol_needs_cond_ref(frompol))
		return frompol;

	*tompol = *frompol;
	tompol->flags &= ~MPOL_F_SHARED;	/* copy doesn't need unref */
	__mpol_put(frompol);
	return tompol;
}

static int mpol_match_intent(const struct mempolicy *a,
			     const struct mempolicy *b)
{
	if (a->flags != b->flags)
		return 0;
	if (!mpol_store_user_nodemask(a))
		return 1;
	return nodes_equal(a->w.user_nodemask, b->w.user_nodemask);
}

/* Slow path of a mempolicy comparison */
int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	if (!a || !b)
		return 0;
	if (a->mode != b->mode)
		return 0;
	if (a->mode != MPOL_DEFAULT && !mpol_match_intent(a, b))
		return 0;
	switch (a->mode) {
	case MPOL_BIND:
		/* Fall through */
	case MPOL_INTERLEAVE:
		return nodes_equal(a->v.nodes, b->v.nodes);
	case MPOL_PREFERRED:
		return a->v.preferred_node == b->v.preferred_node &&
			a->flags == b->flags;
	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);
	pr_debug("inserting %lx-%lx: %d\n", new->start, new->end,
		 new->policy ? new->policy->mode : 0);
}

/* Find shared policy intersecting idx */
struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)