[linux-2.6-block.git] / mm / util.c

#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/security.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mman.h>
#include <linux/hugetlb.h>
#include <linux/vmalloc.h>

#include <asm/sections.h>
#include <asm/uaccess.h>

#include "internal.h"

static inline int is_kernel_rodata(unsigned long addr)
{
	return addr >= (unsigned long)__start_rodata &&
		addr < (unsigned long)__end_rodata;
}

/**
 * kfree_const - conditionally free memory
 * @x: pointer to the memory
 *
 * Function calls kfree only if @x is not in .rodata section.
 */
void kfree_const(const void *x)
{
	if (!is_kernel_rodata((unsigned long)x))
		kfree(x);
}
EXPORT_SYMBOL(kfree_const);

/**
 * kstrdup - allocate space for and copy an existing string
 * @s: the string to duplicate
 * @gfp: the GFP mask used in the kmalloc() call when allocating memory
 */
char *kstrdup(const char *s, gfp_t gfp)
{
	size_t len;
	char *buf;

	if (!s)
		return NULL;

	len = strlen(s) + 1;
	buf = kmalloc_track_caller(len, gfp);
	if (buf)
		memcpy(buf, s, len);
	return buf;
}
EXPORT_SYMBOL(kstrdup);

/**
 * kstrdup_const - conditionally duplicate an existing const string
 * @s: the string to duplicate
 * @gfp: the GFP mask used in the kmalloc() call when allocating memory
 *
 * Function returns source string if it is in .rodata section otherwise it
 * fallbacks to kstrdup.
 * Strings allocated by kstrdup_const should be freed by kfree_const.
 */
const char *kstrdup_const(const char *s, gfp_t gfp)
{
	if (is_kernel_rodata((unsigned long)s))
		return s;

	return kstrdup(s, gfp);
}
EXPORT_SYMBOL(kstrdup_const);

/**
 * kstrndup - allocate space for and copy an existing string
 * @s: the string to duplicate
 * @max: read at most @max chars from @s
 * @gfp: the GFP mask used in the kmalloc() call when allocating memory
 */
char *kstrndup(const char *s, size_t max, gfp_t gfp)
{
	size_t len;
	char *buf;

	if (!s)
		return NULL;

	len = strnlen(s, max);
	buf = kmalloc_track_caller(len+1, gfp);
	if (buf) {
		memcpy(buf, s, len);
		buf[len] = '\0';
	}
	return buf;
}
EXPORT_SYMBOL(kstrndup);

/**
 * kmemdup - duplicate region of memory
 *
 * @src: memory region to duplicate
 * @len: memory region length
 * @gfp: GFP mask to use
 */
void *kmemdup(const void *src, size_t len, gfp_t gfp)
{
	void *p;

	p = kmalloc_track_caller(len, gfp);
	if (p)
		memcpy(p, src, len);
	return p;
}
EXPORT_SYMBOL(kmemdup);

/**
 * memdup_user - duplicate memory region from user space
 *
 * @src: source address in user space
 * @len: number of bytes to copy
 *
 * Returns an ERR_PTR() on failure.
 */
void *memdup_user(const void __user *src, size_t len)
{
	void *p;

	/*
	 * Always use GFP_KERNEL, since copy_from_user() can sleep and
	 * cause pagefault, which makes it pointless to use GFP_NOFS
	 * or GFP_ATOMIC.
	 */
	p = kmalloc_track_caller(len, GFP_KERNEL);
	if (!p)
		return ERR_PTR(-ENOMEM);

	if (copy_from_user(p, src, len)) {
		kfree(p);
		return ERR_PTR(-EFAULT);
	}

	return p;
}
EXPORT_SYMBOL(memdup_user);

/*
 * strndup_user - duplicate an existing string from user space
 * @s: The string to duplicate
 * @n: Maximum number of bytes to copy, including the trailing NUL.
 */
char *strndup_user(const char __user *s, long n)
{
	char *p;
	long length;

	length = strnlen_user(s, n);

	if (!length)
		return ERR_PTR(-EFAULT);

	if (length > n)
		return ERR_PTR(-EINVAL);

	p = memdup_user(s, length);

	if (IS_ERR(p))
		return p;

	p[length - 1] = '\0';

	return p;
}
EXPORT_SYMBOL(strndup_user);

void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
		struct vm_area_struct *prev, struct rb_node *rb_parent)
{
	struct vm_area_struct *next;

	vma->vm_prev = prev;
	if (prev) {
		next = prev->vm_next;
		prev->vm_next = vma;
	} else {
		mm->mmap = vma;
		if (rb_parent)
			next = rb_entry(rb_parent,
					struct vm_area_struct, vm_rb);
		else
			next = NULL;
	}
	vma->vm_next = next;
	if (next)
		next->vm_prev = vma;
}

/* Check if the vma is being used as a stack by this task */
static int vm_is_stack_for_task(struct task_struct *t,
				struct vm_area_struct *vma)
{
	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
}

/*
 * Check if the vma is being used as a stack.
 * If is_group is non-zero, check in the entire thread group or else
 * just check in the current task. Returns the task_struct of the task
 * that the vma is stack for. Must be called under rcu_read_lock().
 */
struct task_struct *task_of_stack(struct task_struct *task,
				struct vm_area_struct *vma, bool in_group)
{
	if (vm_is_stack_for_task(task, vma))
		return task;

	if (in_group) {
		struct task_struct *t;

		for_each_thread(task, t) {
			if (vm_is_stack_for_task(t, vma))
				return t;
		}
	}

	return NULL;
}

#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
void arch_pick_mmap_layout(struct mm_struct *mm)
{
	mm->mmap_base = TASK_UNMAPPED_BASE;
	mm->get_unmapped_area = arch_get_unmapped_area;
}
#endif

/*
 * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
 * back to the regular GUP.
 * If the architecture not support this function, simply return with no
 * page pinned
 */
int __weak __get_user_pages_fast(unsigned long start,
				 int nr_pages, int write, struct page **pages)
{
	return 0;
}
EXPORT_SYMBOL_GPL(__get_user_pages_fast);

/**
 * get_user_pages_fast() - pin user pages in memory
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @write:	whether pages will be written to
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long.
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno.
 *
 * get_user_pages_fast provides equivalent functionality to get_user_pages,
 * operating on current and current->mm, with force=0 and vma=NULL. However
 * unlike get_user_pages, it must be called without mmap_sem held.
 *
 * get_user_pages_fast may take mmap_sem and page table locks, so no
 * assumptions can be made about lack of locking. get_user_pages_fast is to be
 * implemented in a way that is advantageous (vs get_user_pages()) when the
 * user memory area is already faulted in and present in ptes. However if the
 * pages have to be faulted in, it may turn out to be slightly slower so
 * callers need to carefully consider what to use. On many architectures,
 * get_user_pages_fast simply falls back to get_user_pages.
 */
int __weak get_user_pages_fast(unsigned long start,
				int nr_pages, int write, struct page **pages)
{
	struct mm_struct *mm = current->mm;
	return get_user_pages_unlocked(current, mm, start, nr_pages,
				       write, 0, pages);
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);

unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
	unsigned long flag, unsigned long pgoff)
{
	unsigned long ret;
	struct mm_struct *mm = current->mm;
	unsigned long populate;

	ret = security_mmap_file(file, prot, flag);
	if (!ret) {
		down_write(&mm->mmap_sem);
		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
				    &populate);
		up_write(&mm->mmap_sem);
		if (populate)
			mm_populate(ret, populate);
	}
	return ret;
}

unsigned long vm_mmap(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
	unsigned long flag, unsigned long offset)
{
	if (unlikely(offset + PAGE_ALIGN(len) < offset))
		return -EINVAL;
	if (unlikely(offset & ~PAGE_MASK))
		return -EINVAL;

	return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
}
EXPORT_SYMBOL(vm_mmap);

void kvfree(const void *addr)
{
	if (is_vmalloc_addr(addr))
		vfree(addr);
	else
		kfree(addr);
}
EXPORT_SYMBOL(kvfree);

static inline void *__page_rmapping(struct page *page)
{
	unsigned long mapping;

	mapping = (unsigned long)page->mapping;
	mapping &= ~PAGE_MAPPING_FLAGS;

	return (void *)mapping;
}

/* Neutral page->mapping pointer to address_space or anon_vma or other */
void *page_rmapping(struct page *page)
{
	page = compound_head(page);
	return __page_rmapping(page);
}

struct anon_vma *page_anon_vma(struct page *page)
{
	unsigned long mapping;

	page = compound_head(page);
	mapping = (unsigned long)page->mapping;
	if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
		return NULL;
	return __page_rmapping(page);
}

struct address_space *page_mapping(struct page *page)
{
	unsigned long mapping;

	/* This happens if someone calls flush_dcache_page on slab page */
	if (unlikely(PageSlab(page)))
		return NULL;

	if (unlikely(PageSwapCache(page))) {
		swp_entry_t entry;

		entry.val = page_private(page);
		return swap_address_space(entry);
	}

	mapping = (unsigned long)page->mapping;
	if (mapping & PAGE_MAPPING_FLAGS)
		return NULL;
	return page->mapping;
}

int overcommit_ratio_handler(struct ctl_table *table, int write,
			     void __user *buffer, size_t *lenp,
			     loff_t *ppos)
{
	int ret;

	ret = proc_dointvec(table, write, buffer, lenp, ppos);
	if (ret == 0 && write)
		sysctl_overcommit_kbytes = 0;
	return ret;
}

int overcommit_kbytes_handler(struct ctl_table *table, int write,
			     void __user *buffer, size_t *lenp,
			     loff_t *ppos)
{
	int ret;

	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
	if (ret == 0 && write)
		sysctl_overcommit_ratio = 0;
	return ret;
}

/*
 * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
 */
unsigned long vm_commit_limit(void)
{
	unsigned long allowed;

	if (sysctl_overcommit_kbytes)
		allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
	else
		allowed = ((totalram_pages - hugetlb_total_pages())
			   * sysctl_overcommit_ratio / 100);
	allowed += total_swap_pages;

	return allowed;
}

/**
 * get_cmdline() - copy the cmdline value to a buffer.
 * @task:     the task whose cmdline value to copy.
 * @buffer:   the buffer to copy to.
 * @buflen:   the length of the buffer. Larger cmdline values are truncated
 *            to this length.
 * Returns the size of the cmdline field copied. Note that the copy does
 * not guarantee an ending NULL byte.
 */
int get_cmdline(struct task_struct *task, char *buffer, int buflen)
{
	int res = 0;
	unsigned int len;
	struct mm_struct *mm = get_task_mm(task);
	if (!mm)
		goto out;
	if (!mm->arg_end)
		goto out_mm;	/* Shh! No looking before we're done */

	len = mm->arg_end - mm->arg_start;

	if (len > buflen)
		len = buflen;

	res = access_process_vm(task, mm->arg_start, buffer, len, 0);

	/*
	 * If the nul at the end of args has been overwritten, then
	 * assume application is using setproctitle(3).
	 */
	if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
		len = strnlen(buffer, res);
		if (len < res) {
			res = len;
		} else {
			len = mm->env_end - mm->env_start;
			if (len > buflen - res)
				len = buflen - res;
			res += access_process_vm(task, mm->env_start,
						 buffer+res, len, 0);
			res = strnlen(buffer, res);
		}
	}
out_mm:
	mmput(mm);
out:
	return res;
}
Commit	Line	Data
16d69265	1	#include <linux/mm.h>
30992c97 MM	2	#include <linux/slab.h>
30992c97 MM	3	#include <linux/string.h>
3b32123d	4	#include <linux/compiler.h>
b95f1b31	5	#include <linux/export.h>
96840aa0	6	#include <linux/err.h>
3b8f14b4	7	#include <linux/sched.h>
eb36c587	8	#include <linux/security.h>
9800339b	9	#include <linux/swap.h>
33806f06	10	#include <linux/swapops.h>
00619bcc JM	11	#include <linux/mman.h>
00619bcc JM	12	#include <linux/hugetlb.h>
39f1f78d	13	#include <linux/vmalloc.h>
00619bcc	14
a4bb1e43	15	#include <asm/sections.h>
96840aa0	16	#include <asm/uaccess.h>
30992c97	17
6038def0 NK	18	#include "internal.h"
6038def0 NK	19
a4bb1e43 AH	20	static inline int is_kernel_rodata(unsigned long addr)
	21	{
	22	return addr >= (unsigned long)__start_rodata &&
	23	addr < (unsigned long)__end_rodata;
	24	}
	25
	26	/**
	27	* kfree_const - conditionally free memory
	28	* @x: pointer to the memory
	29	*
	30	* Function calls kfree only if @x is not in .rodata section.
	31	*/
	32	void kfree_const(const void *x)
	33	{
	34	if (!is_kernel_rodata((unsigned long)x))
	35	kfree(x);
	36	}
	37	EXPORT_SYMBOL(kfree_const);
	38
30992c97	39	/**
30992c97	40	* kstrdup - allocate space for and copy an existing string
30992c97 MM	41	* @s: the string to duplicate
	42	* @gfp: the GFP mask used in the kmalloc() call when allocating memory
	43	*/
	44	char kstrdup(const char s, gfp_t gfp)
	45	{
	46	size_t len;
	47	char *buf;
	48
	49	if (!s)
	50	return NULL;
	51
	52	len = strlen(s) + 1;
1d2c8eea	53	buf = kmalloc_track_caller(len, gfp);
30992c97 MM	54	if (buf)
	55	memcpy(buf, s, len);
	56	return buf;
	57	}
	58	EXPORT_SYMBOL(kstrdup);
96840aa0	59
a4bb1e43 AH	60	/**
	61	* kstrdup_const - conditionally duplicate an existing const string
	62	* @s: the string to duplicate
	63	* @gfp: the GFP mask used in the kmalloc() call when allocating memory
	64	*
	65	* Function returns source string if it is in .rodata section otherwise it
	66	* fallbacks to kstrdup.
	67	* Strings allocated by kstrdup_const should be freed by kfree_const.
	68	*/
	69	const char kstrdup_const(const char s, gfp_t gfp)
	70	{
	71	if (is_kernel_rodata((unsigned long)s))
	72	return s;
	73
	74	return kstrdup(s, gfp);
	75	}
	76	EXPORT_SYMBOL(kstrdup_const);
	77
1e66df3e JF	78	/**
	79	* kstrndup - allocate space for and copy an existing string
	80	* @s: the string to duplicate
	81	* @max: read at most @max chars from @s
	82	* @gfp: the GFP mask used in the kmalloc() call when allocating memory
	83	*/
	84	char kstrndup(const char s, size_t max, gfp_t gfp)
	85	{
	86	size_t len;
	87	char *buf;
	88
	89	if (!s)
	90	return NULL;
	91
	92	len = strnlen(s, max);
	93	buf = kmalloc_track_caller(len+1, gfp);
	94	if (buf) {
	95	memcpy(buf, s, len);
	96	buf[len] = '\0';
	97	}
	98	return buf;
	99	}
	100	EXPORT_SYMBOL(kstrndup);
	101
1a2f67b4 AD	102	/**
	103	* kmemdup - duplicate region of memory
	104	*
	105	* @src: memory region to duplicate
	106	* @len: memory region length
	107	* @gfp: GFP mask to use
	108	*/
	109	void kmemdup(const void src, size_t len, gfp_t gfp)
	110	{
	111	void *p;
	112
1d2c8eea	113	p = kmalloc_track_caller(len, gfp);
1a2f67b4 AD	114	if (p)
	115	memcpy(p, src, len);
	116	return p;
	117	}
	118	EXPORT_SYMBOL(kmemdup);
	119
610a77e0 LZ	120	/**
	121	* memdup_user - duplicate memory region from user space
	122	*
	123	* @src: source address in user space
	124	* @len: number of bytes to copy
	125	*
	126	* Returns an ERR_PTR() on failure.
	127	*/
	128	void memdup_user(const void __user src, size_t len)
	129	{
	130	void *p;
	131
	132	/*
	133	* Always use GFP_KERNEL, since copy_from_user() can sleep and
	134	* cause pagefault, which makes it pointless to use GFP_NOFS
	135	* or GFP_ATOMIC.
	136	*/
	137	p = kmalloc_track_caller(len, GFP_KERNEL);
	138	if (!p)
	139	return ERR_PTR(-ENOMEM);
	140
	141	if (copy_from_user(p, src, len)) {
	142	kfree(p);
	143	return ERR_PTR(-EFAULT);
	144	}
	145
	146	return p;
	147	}
	148	EXPORT_SYMBOL(memdup_user);
	149
96840aa0 DA	150	/*
96840aa0 DA	151	* strndup_user - duplicate an existing string from user space
96840aa0 DA	152	* @s: The string to duplicate
	153	* @n: Maximum number of bytes to copy, including the trailing NUL.
	154	*/
	155	char strndup_user(const char __user s, long n)
	156	{
	157	char *p;
	158	long length;
	159
	160	length = strnlen_user(s, n);
	161
	162	if (!length)
	163	return ERR_PTR(-EFAULT);
	164
	165	if (length > n)
	166	return ERR_PTR(-EINVAL);
	167
90d74045	168	p = memdup_user(s, length);
96840aa0	169
90d74045 JL	170	if (IS_ERR(p))
90d74045 JL	171	return p;
96840aa0 DA	172
	173	p[length - 1] = '\0';
	174
	175	return p;
	176	}
	177	EXPORT_SYMBOL(strndup_user);
16d69265	178
6038def0 NK	179	void __vma_link_list(struct mm_struct mm, struct vm_area_struct vma,
	180	struct vm_area_struct prev, struct rb_node rb_parent)
	181	{
	182	struct vm_area_struct *next;
	183
	184	vma->vm_prev = prev;
	185	if (prev) {
	186	next = prev->vm_next;
	187	prev->vm_next = vma;
	188	} else {
	189	mm->mmap = vma;
	190	if (rb_parent)
	191	next = rb_entry(rb_parent,
	192	struct vm_area_struct, vm_rb);
	193	else
	194	next = NULL;
	195	}
	196	vma->vm_next = next;
	197	if (next)
	198	next->vm_prev = vma;
	199	}
	200
b7643757 SP	201	/* Check if the vma is being used as a stack by this task */
	202	static int vm_is_stack_for_task(struct task_struct *t,
	203	struct vm_area_struct *vma)
	204	{
	205	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
	206	}
	207
	208	/*
	209	* Check if the vma is being used as a stack.
	210	* If is_group is non-zero, check in the entire thread group or else
58cb6548 ON	211	* just check in the current task. Returns the task_struct of the task
58cb6548 ON	212	* that the vma is stack for. Must be called under rcu_read_lock().
b7643757	213	*/
58cb6548 ON	214	struct task_struct task_of_stack(struct task_struct task,
58cb6548 ON	215	struct vm_area_struct *vma, bool in_group)
b7643757	216	{
b7643757	217	if (vm_is_stack_for_task(task, vma))
58cb6548	218	return task;
b7643757 SP	219
	220	if (in_group) {
	221	struct task_struct *t;
b7643757	222
4449a51a	223	for_each_thread(task, t) {
58cb6548 ON	224	if (vm_is_stack_for_task(t, vma))
58cb6548 ON	225	return t;
4449a51a	226	}
b7643757 SP	227	}
b7643757 SP	228
58cb6548	229	return NULL;
b7643757 SP	230	}
b7643757 SP	231
efc1a3b1	232	#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
16d69265 AM	233	void arch_pick_mmap_layout(struct mm_struct *mm)
	234	{
	235	mm->mmap_base = TASK_UNMAPPED_BASE;
	236	mm->get_unmapped_area = arch_get_unmapped_area;
16d69265 AM	237	}
16d69265 AM	238	#endif
912985dc	239
45888a0c XG	240	/*
	241	* Like get_user_pages_fast() except its IRQ-safe in that it won't fall
	242	* back to the regular GUP.
25985edc	243	* If the architecture not support this function, simply return with no
45888a0c XG	244	* page pinned
45888a0c XG	245	*/
3b32123d	246	int __weak __get_user_pages_fast(unsigned long start,
45888a0c XG	247	int nr_pages, int write, struct page **pages)
	248	{
	249	return 0;
	250	}
	251	EXPORT_SYMBOL_GPL(__get_user_pages_fast);
	252
9de100d0 AG	253	/**
	254	* get_user_pages_fast() - pin user pages in memory
	255	* @start: starting user address
	256	* @nr_pages: number of pages from start to pin
	257	* @write: whether pages will be written to
	258	* @pages: array that receives pointers to the pages pinned.
	259	* Should be at least nr_pages long.
	260	*
9de100d0 AG	261	* Returns number of pages pinned. This may be fewer than the number
	262	* requested. If nr_pages is 0 or negative, returns 0. If no pages
	263	* were pinned, returns -errno.
d2bf6be8 NP	264	*
	265	* get_user_pages_fast provides equivalent functionality to get_user_pages,
	266	* operating on current and current->mm, with force=0 and vma=NULL. However
	267	* unlike get_user_pages, it must be called without mmap_sem held.
	268	*
	269	* get_user_pages_fast may take mmap_sem and page table locks, so no
	270	* assumptions can be made about lack of locking. get_user_pages_fast is to be
	271	* implemented in a way that is advantageous (vs get_user_pages()) when the
	272	* user memory area is already faulted in and present in ptes. However if the
	273	* pages have to be faulted in, it may turn out to be slightly slower so
	274	* callers need to carefully consider what to use. On many architectures,
	275	* get_user_pages_fast simply falls back to get_user_pages.
9de100d0	276	*/
3b32123d	277	int __weak get_user_pages_fast(unsigned long start,
912985dc RR	278	int nr_pages, int write, struct page **pages)
	279	{
	280	struct mm_struct *mm = current->mm;
a7b78075 AA	281	return get_user_pages_unlocked(current, mm, start, nr_pages,
a7b78075 AA	282	write, 0, pages);
912985dc RR	283	}
912985dc RR	284	EXPORT_SYMBOL_GPL(get_user_pages_fast);
ca2b84cb	285
eb36c587 AV	286	unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
	287	unsigned long len, unsigned long prot,
	288	unsigned long flag, unsigned long pgoff)
	289	{
	290	unsigned long ret;
	291	struct mm_struct *mm = current->mm;
41badc15	292	unsigned long populate;
eb36c587 AV	293
	294	ret = security_mmap_file(file, prot, flag);
	295	if (!ret) {
	296	down_write(&mm->mmap_sem);
bebeb3d6 ML	297	ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
bebeb3d6 ML	298	&populate);
eb36c587	299	up_write(&mm->mmap_sem);
41badc15 ML	300	if (populate)
41badc15 ML	301	mm_populate(ret, populate);
eb36c587 AV	302	}
	303	return ret;
	304	}
	305
	306	unsigned long vm_mmap(struct file *file, unsigned long addr,
	307	unsigned long len, unsigned long prot,
	308	unsigned long flag, unsigned long offset)
	309	{
	310	if (unlikely(offset + PAGE_ALIGN(len) < offset))
	311	return -EINVAL;
	312	if (unlikely(offset & ~PAGE_MASK))
	313	return -EINVAL;
	314
	315	return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
	316	}
	317	EXPORT_SYMBOL(vm_mmap);
	318
39f1f78d AV	319	void kvfree(const void *addr)
	320	{
	321	if (is_vmalloc_addr(addr))
	322	vfree(addr);
	323	else
	324	kfree(addr);
	325	}
	326	EXPORT_SYMBOL(kvfree);
	327
e39155ea KS	328	static inline void __page_rmapping(struct page page)
	329	{
	330	unsigned long mapping;
	331
	332	mapping = (unsigned long)page->mapping;
	333	mapping &= ~PAGE_MAPPING_FLAGS;
	334
	335	return (void *)mapping;
	336	}
	337
	338	/* Neutral page->mapping pointer to address_space or anon_vma or other */
	339	void page_rmapping(struct page page)
	340	{
	341	page = compound_head(page);
	342	return __page_rmapping(page);
	343	}
	344
	345	struct anon_vma page_anon_vma(struct page page)
	346	{
	347	unsigned long mapping;
	348
	349	page = compound_head(page);
	350	mapping = (unsigned long)page->mapping;
	351	if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
	352	return NULL;
	353	return __page_rmapping(page);
	354	}
	355
9800339b SL	356	struct address_space page_mapping(struct page page)
9800339b SL	357	{
e39155ea	358	unsigned long mapping;
9800339b	359
03e5ac2f MP	360	/* This happens if someone calls flush_dcache_page on slab page */
	361	if (unlikely(PageSlab(page)))
	362	return NULL;
	363
33806f06 SL	364	if (unlikely(PageSwapCache(page))) {
	365	swp_entry_t entry;
	366
	367	entry.val = page_private(page);
e39155ea KS	368	return swap_address_space(entry);
	369	}
	370
	371	mapping = (unsigned long)page->mapping;
	372	if (mapping & PAGE_MAPPING_FLAGS)
	373	return NULL;
	374	return page->mapping;
9800339b SL	375	}
9800339b SL	376
49f0ce5f JM	377	int overcommit_ratio_handler(struct ctl_table *table, int write,
	378	void __user buffer, size_t lenp,
	379	loff_t *ppos)
	380	{
	381	int ret;
	382
	383	ret = proc_dointvec(table, write, buffer, lenp, ppos);
	384	if (ret == 0 && write)
	385	sysctl_overcommit_kbytes = 0;
	386	return ret;
	387	}
	388
	389	int overcommit_kbytes_handler(struct ctl_table *table, int write,
	390	void __user buffer, size_t lenp,
	391	loff_t *ppos)
	392	{
	393	int ret;
	394
	395	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
	396	if (ret == 0 && write)
	397	sysctl_overcommit_ratio = 0;
	398	return ret;
	399	}
	400
00619bcc JM	401	/*
	402	* Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
	403	*/
	404	unsigned long vm_commit_limit(void)
	405	{
49f0ce5f JM	406	unsigned long allowed;
	407
	408	if (sysctl_overcommit_kbytes)
	409	allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
	410	else
	411	allowed = ((totalram_pages - hugetlb_total_pages())
	412	* sysctl_overcommit_ratio / 100);
	413	allowed += total_swap_pages;
	414
	415	return allowed;
00619bcc JM	416	}
00619bcc JM	417
a9090253 WR	418	/**
	419	* get_cmdline() - copy the cmdline value to a buffer.
	420	* @task: the task whose cmdline value to copy.
	421	* @buffer: the buffer to copy to.
	422	* @buflen: the length of the buffer. Larger cmdline values are truncated
	423	* to this length.
	424	* Returns the size of the cmdline field copied. Note that the copy does
	425	* not guarantee an ending NULL byte.
	426	*/
	427	int get_cmdline(struct task_struct task, char buffer, int buflen)
	428	{
	429	int res = 0;
	430	unsigned int len;
	431	struct mm_struct *mm = get_task_mm(task);
	432	if (!mm)
	433	goto out;
	434	if (!mm->arg_end)
	435	goto out_mm; /* Shh! No looking before we're done */
	436
	437	len = mm->arg_end - mm->arg_start;
	438
	439	if (len > buflen)
	440	len = buflen;
	441
	442	res = access_process_vm(task, mm->arg_start, buffer, len, 0);
	443
	444	/*
	445	* If the nul at the end of args has been overwritten, then
	446	* assume application is using setproctitle(3).
	447	*/
	448	if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
	449	len = strnlen(buffer, res);
	450	if (len < res) {
	451	res = len;
	452	} else {
	453	len = mm->env_end - mm->env_start;
	454	if (len > buflen - res)
	455	len = buflen - res;
	456	res += access_process_vm(task, mm->env_start,
	457	buffer+res, len, 0);
	458	res = strnlen(buffer, res);
	459	}
	460	}
	461	out_mm:
	462	mmput(mm);
	463	out:
	464	return res;
	465	}