[mirror_ubuntu-zesty-kernel.git] / mm / process_vm_access.c

/*
 * linux/mm/process_vm_access.c
 *
 * Copyright (C) 2010-2011 Christopher Yeoh <cyeoh@au1.ibm.com>, IBM Corp.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/syscalls.h>

#ifdef CONFIG_COMPAT
#include <linux/compat.h>
#endif

/**
 * process_vm_rw_pages - read/write pages from task specified
 * @task: task to read/write from
 * @mm: mm for task
 * @process_pages: struct pages area that can store at least
 *  nr_pages_to_copy struct page pointers
 * @pa: address of page in task to start copying from/to
 * @start_offset: offset in page to start copying from/to
 * @len: number of bytes to copy
 * @lvec: iovec array specifying where to copy to/from
 * @lvec_cnt: number of elements in iovec array
 * @lvec_current: index in iovec array we are up to
 * @lvec_offset: offset in bytes from current iovec iov_base we are up to
 * @vm_write: 0 means copy from, 1 means copy to
 * @nr_pages_to_copy: number of pages to copy
 * @bytes_copied: returns number of bytes successfully copied
 * Returns 0 on success, error code otherwise
 */
static int process_vm_rw_pages(struct task_struct *task,
			       struct mm_struct *mm,
			       struct page **process_pages,
			       unsigned long pa,
			       unsigned long start_offset,
			       unsigned long len,
			       const struct iovec *lvec,
			       unsigned long lvec_cnt,
			       unsigned long *lvec_current,
			       size_t *lvec_offset,
			       int vm_write,
			       unsigned int nr_pages_to_copy,
			       ssize_t *bytes_copied)
{
	int pages_pinned;
	void *target_kaddr;
	int pgs_copied = 0;
	int j;
	int ret;
	ssize_t bytes_to_copy;
	ssize_t rc = 0;
	const struct iovec *iov = lvec + *lvec_current;

	*bytes_copied = 0;

	/* Get the pages we're interested in */
	down_read(&mm->mmap_sem);
	pages_pinned = get_user_pages(task, mm, pa,
				      nr_pages_to_copy,
				      vm_write, 0, process_pages, NULL);
	up_read(&mm->mmap_sem);

	if (pages_pinned != nr_pages_to_copy) {
		rc = -EFAULT;
		goto end;
	}

	/* Do the copy for each page */
	for (pgs_copied = 0;
	     (pgs_copied < nr_pages_to_copy) && (*lvec_current < lvec_cnt);
	     pgs_copied++) {
		/* Make sure we have a non zero length iovec */
		while (*lvec_current < lvec_cnt
		       && iov->iov_len == 0) {
			iov++;
			(*lvec_current)++;
		}
		if (*lvec_current == lvec_cnt)
			break;

		/*
		 * Will copy smallest of:
		 * - bytes remaining in page
		 * - bytes remaining in destination iovec
		 */
		bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset,
				      len - *bytes_copied);
		bytes_to_copy = min_t(ssize_t, bytes_to_copy,
				      iov->iov_len
				      - *lvec_offset);

		target_kaddr = kmap(process_pages[pgs_copied]) + start_offset;

		if (vm_write)
			ret = copy_from_user(target_kaddr,
					     iov->iov_base
					     + *lvec_offset,
					     bytes_to_copy);
		else
			ret = copy_to_user(iov->iov_base
					   + *lvec_offset,
					   target_kaddr, bytes_to_copy);
		kunmap(process_pages[pgs_copied]);
		if (ret) {
			*bytes_copied += bytes_to_copy - ret;
			pgs_copied++;
			rc = -EFAULT;
			goto end;
		}
		*bytes_copied += bytes_to_copy;
		*lvec_offset += bytes_to_copy;
		if (*lvec_offset == iov->iov_len) {
			/*
			 * Need to copy remaining part of page into the
			 * next iovec if there are any bytes left in page
			 */
			(*lvec_current)++;
			iov++;
			*lvec_offset = 0;
			start_offset = (start_offset + bytes_to_copy)
				% PAGE_SIZE;
			if (start_offset)
				pgs_copied--;
		} else {
			start_offset = 0;
		}
	}

end:
	if (vm_write) {
		for (j = 0; j < pages_pinned; j++) {
			if (j < pgs_copied)
				set_page_dirty_lock(process_pages[j]);
			put_page(process_pages[j]);
		}
	} else {
		for (j = 0; j < pages_pinned; j++)
			put_page(process_pages[j]);
	}

	return rc;
}

/* Maximum number of pages kmalloc'd to hold struct page's during copy */
#define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2)

/**
 * process_vm_rw_single_vec - read/write pages from task specified
 * @addr: start memory address of target process
 * @len: size of area to copy to/from
 * @lvec: iovec array specifying where to copy to/from locally
 * @lvec_cnt: number of elements in iovec array
 * @lvec_current: index in iovec array we are up to
 * @lvec_offset: offset in bytes from current iovec iov_base we are up to
 * @process_pages: struct pages area that can store at least
 *  nr_pages_to_copy struct page pointers
 * @mm: mm for task
 * @task: task to read/write from
 * @vm_write: 0 means copy from, 1 means copy to
 * @bytes_copied: returns number of bytes successfully copied
 * Returns 0 on success or on failure error code
 */
static int process_vm_rw_single_vec(unsigned long addr,
				    unsigned long len,
				    const struct iovec *lvec,
				    unsigned long lvec_cnt,
				    unsigned long *lvec_current,
				    size_t *lvec_offset,
				    struct page **process_pages,
				    struct mm_struct *mm,
				    struct task_struct *task,
				    int vm_write,
				    ssize_t *bytes_copied)
{
	unsigned long pa = addr & PAGE_MASK;
	unsigned long start_offset = addr - pa;
	unsigned long nr_pages;
	ssize_t bytes_copied_loop;
	ssize_t rc = 0;
	unsigned long nr_pages_copied = 0;
	unsigned long nr_pages_to_copy;
	unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
		/ sizeof(struct pages *);

	*bytes_copied = 0;

	/* Work out address and page range required */
	if (len == 0)
		return 0;
	nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;

	while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) {
		nr_pages_to_copy = min(nr_pages - nr_pages_copied,
				       max_pages_per_loop);

		rc = process_vm_rw_pages(task, mm, process_pages, pa,
					 start_offset, len,
					 lvec, lvec_cnt,
					 lvec_current, lvec_offset,
					 vm_write, nr_pages_to_copy,
					 &bytes_copied_loop);
		start_offset = 0;
		*bytes_copied += bytes_copied_loop;

		if (rc < 0) {
			return rc;
		} else {
			len -= bytes_copied_loop;
			nr_pages_copied += nr_pages_to_copy;
			pa += nr_pages_to_copy * PAGE_SIZE;
		}
	}

	return rc;
}

/* Maximum number of entries for process pages array
   which lives on stack */
#define PVM_MAX_PP_ARRAY_COUNT 16

/**
 * process_vm_rw_core - core of reading/writing pages from task specified
 * @pid: PID of process to read/write from/to
 * @lvec: iovec array specifying where to copy to/from locally
 * @liovcnt: size of lvec array
 * @rvec: iovec array specifying where to copy to/from in the other process
 * @riovcnt: size of rvec array
 * @flags: currently unused
 * @vm_write: 0 if reading from other process, 1 if writing to other process
 * Returns the number of bytes read/written or error code. May
 *  return less bytes than expected if an error occurs during the copying
 *  process.
 */
static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
				  unsigned long liovcnt,
				  const struct iovec *rvec,
				  unsigned long riovcnt,
				  unsigned long flags, int vm_write)
{
	struct task_struct *task;
	struct page *pp_stack[PVM_MAX_PP_ARRAY_COUNT];
	struct page **process_pages = pp_stack;
	struct mm_struct *mm;
	unsigned long i;
	ssize_t rc = 0;
	ssize_t bytes_copied_loop;
	ssize_t bytes_copied = 0;
	unsigned long nr_pages = 0;
	unsigned long nr_pages_iov;
	unsigned long iov_l_curr_idx = 0;
	size_t iov_l_curr_offset = 0;
	ssize_t iov_len;

	/*
	 * Work out how many pages of struct pages we're going to need
	 * when eventually calling get_user_pages
	 */
	for (i = 0; i < riovcnt; i++) {
		iov_len = rvec[i].iov_len;
		if (iov_len > 0) {
			nr_pages_iov = ((unsigned long)rvec[i].iov_base
					+ iov_len)
				/ PAGE_SIZE - (unsigned long)rvec[i].iov_base
				/ PAGE_SIZE + 1;
			nr_pages = max(nr_pages, nr_pages_iov);
		}
	}

	if (nr_pages == 0)
		return 0;

	if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) {
		/* For reliability don't try to kmalloc more than
		   2 pages worth */
		process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES,
					      sizeof(struct pages *)*nr_pages),
					GFP_KERNEL);

		if (!process_pages)
			return -ENOMEM;
	}

	/* Get process information */
	rcu_read_lock();
	task = find_task_by_vpid(pid);
	if (task)
		get_task_struct(task);
	rcu_read_unlock();
	if (!task) {
		rc = -ESRCH;
		goto free_proc_pages;
	}

	mm = mm_access(task, PTRACE_MODE_ATTACH);
	if (!mm || IS_ERR(mm)) {
		rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
		/*
		 * Explicitly map EACCES to EPERM as EPERM is a more a
		 * appropriate error code for process_vw_readv/writev
		 */
		if (rc == -EACCES)
			rc = -EPERM;
		goto put_task_struct;
	}

	for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) {
		rc = process_vm_rw_single_vec(
			(unsigned long)rvec[i].iov_base, rvec[i].iov_len,
			lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset,
			process_pages, mm, task, vm_write, &bytes_copied_loop);
		bytes_copied += bytes_copied_loop;
		if (rc != 0) {
			/* If we have managed to copy any data at all then
			   we return the number of bytes copied. Otherwise
			   we return the error code */
			if (bytes_copied)
				rc = bytes_copied;
			goto put_mm;
		}
	}

	rc = bytes_copied;
put_mm:
	mmput(mm);

put_task_struct:
	put_task_struct(task);

free_proc_pages:
	if (process_pages != pp_stack)
		kfree(process_pages);
	return rc;
}

/**
 * process_vm_rw - check iovecs before calling core routine
 * @pid: PID of process to read/write from/to
 * @lvec: iovec array specifying where to copy to/from locally
 * @liovcnt: size of lvec array
 * @rvec: iovec array specifying where to copy to/from in the other process
 * @riovcnt: size of rvec array
 * @flags: currently unused
 * @vm_write: 0 if reading from other process, 1 if writing to other process
 * Returns the number of bytes read/written or error code. May
 *  return less bytes than expected if an error occurs during the copying
 *  process.
 */
static ssize_t process_vm_rw(pid_t pid,
			     const struct iovec __user *lvec,
			     unsigned long liovcnt,
			     const struct iovec __user *rvec,
			     unsigned long riovcnt,
			     unsigned long flags, int vm_write)
{
	struct iovec iovstack_l[UIO_FASTIOV];
	struct iovec iovstack_r[UIO_FASTIOV];
	struct iovec *iov_l = iovstack_l;
	struct iovec *iov_r = iovstack_r;
	ssize_t rc;

	if (flags != 0)
		return -EINVAL;

	/* Check iovecs */
	if (vm_write)
		rc = rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV,
					   iovstack_l, &iov_l);
	else
		rc = rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV,
					   iovstack_l, &iov_l);
	if (rc <= 0)
		goto free_iovecs;

	rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
				   iovstack_r, &iov_r);
	if (rc <= 0)
		goto free_iovecs;

	rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
				vm_write);

free_iovecs:
	if (iov_r != iovstack_r)
		kfree(iov_r);
	if (iov_l != iovstack_l)
		kfree(iov_l);

	return rc;
}

SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec,
		unsigned long, liovcnt, const struct iovec __user *, rvec,
		unsigned long, riovcnt,	unsigned long, flags)
{
	return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0);
}

SYSCALL_DEFINE6(process_vm_writev, pid_t, pid,
		const struct iovec __user *, lvec,
		unsigned long, liovcnt, const struct iovec __user *, rvec,
		unsigned long, riovcnt,	unsigned long, flags)
{
	return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1);
}

#ifdef CONFIG_COMPAT

asmlinkage ssize_t
compat_process_vm_rw(compat_pid_t pid,
		     const struct compat_iovec __user *lvec,
		     unsigned long liovcnt,
		     const struct compat_iovec __user *rvec,
		     unsigned long riovcnt,
		     unsigned long flags, int vm_write)
{
	struct iovec iovstack_l[UIO_FASTIOV];
	struct iovec iovstack_r[UIO_FASTIOV];
	struct iovec *iov_l = iovstack_l;
	struct iovec *iov_r = iovstack_r;
	ssize_t rc = -EFAULT;

	if (flags != 0)
		return -EINVAL;

	if (vm_write)
		rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt,
						  UIO_FASTIOV, iovstack_l,
						  &iov_l);
	else
		rc = compat_rw_copy_check_uvector(READ, lvec, liovcnt,
						  UIO_FASTIOV, iovstack_l,
						  &iov_l);
	if (rc <= 0)
		goto free_iovecs;
	rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
					  UIO_FASTIOV, iovstack_r,
					  &iov_r);
	if (rc <= 0)
		goto free_iovecs;

	rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
			   vm_write);

free_iovecs:
	if (iov_r != iovstack_r)
		kfree(iov_r);
	if (iov_l != iovstack_l)
		kfree(iov_l);
	return rc;
}

asmlinkage ssize_t
compat_sys_process_vm_readv(compat_pid_t pid,
			    const struct compat_iovec __user *lvec,
			    unsigned long liovcnt,
			    const struct compat_iovec __user *rvec,
			    unsigned long riovcnt,
			    unsigned long flags)
{
	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
				    riovcnt, flags, 0);
}

asmlinkage ssize_t
compat_sys_process_vm_writev(compat_pid_t pid,
			     const struct compat_iovec __user *lvec,
			     unsigned long liovcnt,
			     const struct compat_iovec __user *rvec,
			     unsigned long riovcnt,
			     unsigned long flags)
{
	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
				    riovcnt, flags, 1);
}

#endif
Commit	Line	Data
fcf63409 CY	1	/*
	2	* linux/mm/process_vm_access.c
	3	*
	4	* Copyright (C) 2010-2011 Christopher Yeoh <cyeoh@au1.ibm.com>, IBM Corp.
	5	*
	6	* This program is free software; you can redistribute it and/or
	7	* modify it under the terms of the GNU General Public License
	8	* as published by the Free Software Foundation; either version
	9	* 2 of the License, or (at your option) any later version.
	10	*/
	11
	12	#include <linux/mm.h>
	13	#include <linux/uio.h>
	14	#include <linux/sched.h>
	15	#include <linux/highmem.h>
	16	#include <linux/ptrace.h>
	17	#include <linux/slab.h>
	18	#include <linux/syscalls.h>
	19
	20	#ifdef CONFIG_COMPAT
	21	#include <linux/compat.h>
	22	#endif
	23
	24	/**
	25	* process_vm_rw_pages - read/write pages from task specified
	26	* @task: task to read/write from
	27	* @mm: mm for task
	28	* @process_pages: struct pages area that can store at least
	29	* nr_pages_to_copy struct page pointers
	30	* @pa: address of page in task to start copying from/to
	31	* @start_offset: offset in page to start copying from/to
	32	* @len: number of bytes to copy
	33	* @lvec: iovec array specifying where to copy to/from
	34	* @lvec_cnt: number of elements in iovec array
	35	* @lvec_current: index in iovec array we are up to
	36	* @lvec_offset: offset in bytes from current iovec iov_base we are up to
	37	* @vm_write: 0 means copy from, 1 means copy to
	38	* @nr_pages_to_copy: number of pages to copy
	39	* @bytes_copied: returns number of bytes successfully copied
	40	* Returns 0 on success, error code otherwise
	41	*/
	42	static int process_vm_rw_pages(struct task_struct *task,
	43	struct mm_struct *mm,
	44	struct page **process_pages,
	45	unsigned long pa,
	46	unsigned long start_offset,
	47	unsigned long len,
	48	const struct iovec *lvec,
	49	unsigned long lvec_cnt,
	50	unsigned long *lvec_current,
	51	size_t *lvec_offset,
	52	int vm_write,
	53	unsigned int nr_pages_to_copy,
	54	ssize_t *bytes_copied)
	55	{
	56	int pages_pinned;
	57	void *target_kaddr;
	58	int pgs_copied = 0;
	59	int j;
	60	int ret;
	61	ssize_t bytes_to_copy;
	62	ssize_t rc = 0;
480402e1	63	const struct iovec iov = lvec + lvec_current;
fcf63409 CY	64
	65	*bytes_copied = 0;
	66
	67	/* Get the pages we're interested in */
	68	down_read(&mm->mmap_sem);
	69	pages_pinned = get_user_pages(task, mm, pa,
	70	nr_pages_to_copy,
	71	vm_write, 0, process_pages, NULL);
	72	up_read(&mm->mmap_sem);
	73
	74	if (pages_pinned != nr_pages_to_copy) {
	75	rc = -EFAULT;
	76	goto end;
	77	}
	78
	79	/* Do the copy for each page */
	80	for (pgs_copied = 0;
	81	(pgs_copied < nr_pages_to_copy) && (*lvec_current < lvec_cnt);
	82	pgs_copied++) {
	83	/* Make sure we have a non zero length iovec */
	84	while (*lvec_current < lvec_cnt
480402e1 AV	85	&& iov->iov_len == 0) {
480402e1 AV	86	iov++;
fcf63409	87	(*lvec_current)++;
480402e1	88	}
fcf63409 CY	89	if (*lvec_current == lvec_cnt)
	90	break;
	91
	92	/*
	93	* Will copy smallest of:
	94	* - bytes remaining in page
	95	* - bytes remaining in destination iovec
	96	*/
	97	bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset,
	98	len - *bytes_copied);
	99	bytes_to_copy = min_t(ssize_t, bytes_to_copy,
480402e1	100	iov->iov_len
fcf63409 CY	101	- *lvec_offset);
	102
	103	target_kaddr = kmap(process_pages[pgs_copied]) + start_offset;
	104
	105	if (vm_write)
	106	ret = copy_from_user(target_kaddr,
480402e1	107	iov->iov_base
fcf63409 CY	108	+ *lvec_offset,
	109	bytes_to_copy);
	110	else
480402e1	111	ret = copy_to_user(iov->iov_base
fcf63409 CY	112	+ *lvec_offset,
	113	target_kaddr, bytes_to_copy);
	114	kunmap(process_pages[pgs_copied]);
	115	if (ret) {
	116	*bytes_copied += bytes_to_copy - ret;
	117	pgs_copied++;
	118	rc = -EFAULT;
	119	goto end;
	120	}
	121	*bytes_copied += bytes_to_copy;
	122	*lvec_offset += bytes_to_copy;
480402e1	123	if (*lvec_offset == iov->iov_len) {
fcf63409 CY	124	/*
	125	* Need to copy remaining part of page into the
	126	* next iovec if there are any bytes left in page
	127	*/
	128	(*lvec_current)++;
480402e1	129	iov++;
fcf63409 CY	130	*lvec_offset = 0;
	131	start_offset = (start_offset + bytes_to_copy)
	132	% PAGE_SIZE;
	133	if (start_offset)
	134	pgs_copied--;
	135	} else {
	136	start_offset = 0;
	137	}
	138	}
	139
	140	end:
	141	if (vm_write) {
	142	for (j = 0; j < pages_pinned; j++) {
	143	if (j < pgs_copied)
	144	set_page_dirty_lock(process_pages[j]);
	145	put_page(process_pages[j]);
	146	}
	147	} else {
	148	for (j = 0; j < pages_pinned; j++)
	149	put_page(process_pages[j]);
	150	}
	151
	152	return rc;
	153	}
	154
	155	/* Maximum number of pages kmalloc'd to hold struct page's during copy */
	156	#define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2)
	157
	158	/**
	159	* process_vm_rw_single_vec - read/write pages from task specified
	160	* @addr: start memory address of target process
	161	* @len: size of area to copy to/from
	162	* @lvec: iovec array specifying where to copy to/from locally
	163	* @lvec_cnt: number of elements in iovec array
	164	* @lvec_current: index in iovec array we are up to
	165	* @lvec_offset: offset in bytes from current iovec iov_base we are up to
	166	* @process_pages: struct pages area that can store at least
	167	* nr_pages_to_copy struct page pointers
	168	* @mm: mm for task
	169	* @task: task to read/write from
	170	* @vm_write: 0 means copy from, 1 means copy to
	171	* @bytes_copied: returns number of bytes successfully copied
	172	* Returns 0 on success or on failure error code
	173	*/
	174	static int process_vm_rw_single_vec(unsigned long addr,
	175	unsigned long len,
	176	const struct iovec *lvec,
	177	unsigned long lvec_cnt,
	178	unsigned long *lvec_current,
	179	size_t *lvec_offset,
	180	struct page **process_pages,
	181	struct mm_struct *mm,
	182	struct task_struct *task,
	183	int vm_write,
	184	ssize_t *bytes_copied)
	185	{
	186	unsigned long pa = addr & PAGE_MASK;
	187	unsigned long start_offset = addr - pa;
	188	unsigned long nr_pages;
	189	ssize_t bytes_copied_loop;
	190	ssize_t rc = 0;
	191	unsigned long nr_pages_copied = 0;
	192	unsigned long nr_pages_to_copy;
	193	unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
194	/ sizeof(struct pages *);
195
196	*bytes_copied = 0;
197
198	/* Work out address and page range required */
199	if (len == 0)
200	return 0;
201	nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
202
203	while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) {
204	nr_pages_to_copy = min(nr_pages - nr_pages_copied,
205	max_pages_per_loop);
206
207	rc = process_vm_rw_pages(task, mm, process_pages, pa,
208	start_offset, len,
209	lvec, lvec_cnt,
210	lvec_current, lvec_offset,
211	vm_write, nr_pages_to_copy,
212	&bytes_copied_loop);
213	start_offset = 0;
214	*bytes_copied += bytes_copied_loop;
215
216	if (rc < 0) {
217	return rc;
218	} else {
219	len -= bytes_copied_loop;
220	nr_pages_copied += nr_pages_to_copy;
221	pa += nr_pages_to_copy * PAGE_SIZE;
222	}
223	}
224
225	return rc;
226	}
227
228	/* Maximum number of entries for process pages array
229	which lives on stack */
230	#define PVM_MAX_PP_ARRAY_COUNT 16
231
232	/**
233	* process_vm_rw_core - core of reading/writing pages from task specified
234	* @pid: PID of process to read/write from/to
235	* @lvec: iovec array specifying where to copy to/from locally
236	* @liovcnt: size of lvec array
237	* @rvec: iovec array specifying where to copy to/from in the other process
238	* @riovcnt: size of rvec array
239	* @flags: currently unused
240	* @vm_write: 0 if reading from other process, 1 if writing to other process
241	* Returns the number of bytes read/written or error code. May
242	* return less bytes than expected if an error occurs during the copying
243	* process.
244	*/
245	static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
246	unsigned long liovcnt,
247	const struct iovec *rvec,
248	unsigned long riovcnt,
249	unsigned long flags, int vm_write)
250	{
251	struct task_struct *task;
252	struct page *pp_stack[PVM_MAX_PP_ARRAY_COUNT];
253	struct page **process_pages = pp_stack;
254	struct mm_struct *mm;
255	unsigned long i;
256	ssize_t rc = 0;
257	ssize_t bytes_copied_loop;
258	ssize_t bytes_copied = 0;
259	unsigned long nr_pages = 0;
260	unsigned long nr_pages_iov;
261	unsigned long iov_l_curr_idx = 0;
262	size_t iov_l_curr_offset = 0;
263	ssize_t iov_len;
264
265	/*
266	* Work out how many pages of struct pages we're going to need
267	* when eventually calling get_user_pages
268	*/
269	for (i = 0; i < riovcnt; i++) {
270	iov_len = rvec[i].iov_len;
271	if (iov_len > 0) {
272	nr_pages_iov = ((unsigned long)rvec[i].iov_base
273	+ iov_len)
274	/ PAGE_SIZE - (unsigned long)rvec[i].iov_base
275	/ PAGE_SIZE + 1;
276	nr_pages = max(nr_pages, nr_pages_iov);
277	}
278	}
279
280	if (nr_pages == 0)
281	return 0;
282
283	if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) {
284	/* For reliability don't try to kmalloc more than
285	2 pages worth */
286	process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES,
287	sizeof(struct pages )nr_pages),
288	GFP_KERNEL);
289
290	if (!process_pages)
291	return -ENOMEM;
292	}
293
294	/* Get process information */
295	rcu_read_lock();
296	task = find_task_by_vpid(pid);
297	if (task)
298	get_task_struct(task);
299	rcu_read_unlock();
300	if (!task) {
301	rc = -ESRCH;
302	goto free_proc_pages;
303	}
304
8cdb878d CY	305	mm = mm_access(task, PTRACE_MODE_ATTACH);
	306	if (!mm \|\| IS_ERR(mm)) {
	307	rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
	308	/*
	309	* Explicitly map EACCES to EPERM as EPERM is a more a
	310	* appropriate error code for process_vw_readv/writev
	311	*/
	312	if (rc == -EACCES)
	313	rc = -EPERM;
fcf63409 CY	314	goto put_task_struct;
	315	}
	316
fcf63409 CY	317	for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) {
	318	rc = process_vm_rw_single_vec(
	319	(unsigned long)rvec[i].iov_base, rvec[i].iov_len,
	320	lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset,
	321	process_pages, mm, task, vm_write, &bytes_copied_loop);
	322	bytes_copied += bytes_copied_loop;
	323	if (rc != 0) {
	324	/* If we have managed to copy any data at all then
	325	we return the number of bytes copied. Otherwise
	326	we return the error code */
	327	if (bytes_copied)
	328	rc = bytes_copied;
	329	goto put_mm;
	330	}
	331	}
	332
	333	rc = bytes_copied;
	334	put_mm:
	335	mmput(mm);
	336
	337	put_task_struct:
	338	put_task_struct(task);
	339
	340	free_proc_pages:
	341	if (process_pages != pp_stack)
	342	kfree(process_pages);
	343	return rc;
	344	}
	345
	346	/**
	347	* process_vm_rw - check iovecs before calling core routine
	348	* @pid: PID of process to read/write from/to
	349	* @lvec: iovec array specifying where to copy to/from locally
	350	* @liovcnt: size of lvec array
	351	* @rvec: iovec array specifying where to copy to/from in the other process
	352	* @riovcnt: size of rvec array
	353	* @flags: currently unused
	354	* @vm_write: 0 if reading from other process, 1 if writing to other process
	355	* Returns the number of bytes read/written or error code. May
	356	* return less bytes than expected if an error occurs during the copying
	357	* process.
	358	*/
	359	static ssize_t process_vm_rw(pid_t pid,
	360	const struct iovec __user *lvec,
	361	unsigned long liovcnt,
	362	const struct iovec __user *rvec,
	363	unsigned long riovcnt,
	364	unsigned long flags, int vm_write)
	365	{
	366	struct iovec iovstack_l[UIO_FASTIOV];
	367	struct iovec iovstack_r[UIO_FASTIOV];
	368	struct iovec *iov_l = iovstack_l;
	369	struct iovec *iov_r = iovstack_r;
	370	ssize_t rc;
	371
	372	if (flags != 0)
	373	return -EINVAL;
	374
	375	/* Check iovecs */
	376	if (vm_write)
	377	rc = rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV,
ac34ebb3	378	iovstack_l, &iov_l);
fcf63409 CY	379	else
fcf63409 CY	380	rc = rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV,
ac34ebb3	381	iovstack_l, &iov_l);
fcf63409 CY	382	if (rc <= 0)
	383	goto free_iovecs;
	384
ac34ebb3 CY	385	rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
ac34ebb3 CY	386	iovstack_r, &iov_r);
fcf63409 CY	387	if (rc <= 0)
	388	goto free_iovecs;
	389
	390	rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
	391	vm_write);
	392
	393	free_iovecs:
	394	if (iov_r != iovstack_r)
	395	kfree(iov_r);
	396	if (iov_l != iovstack_l)
	397	kfree(iov_l);
	398
	399	return rc;
	400	}
	401
	402	SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec,
	403	unsigned long, liovcnt, const struct iovec __user *, rvec,
	404	unsigned long, riovcnt, unsigned long, flags)
	405	{
	406	return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0);
	407	}
	408
	409	SYSCALL_DEFINE6(process_vm_writev, pid_t, pid,
	410	const struct iovec __user *, lvec,
	411	unsigned long, liovcnt, const struct iovec __user *, rvec,
	412	unsigned long, riovcnt, unsigned long, flags)
	413	{
	414	return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1);
	415	}
	416
	417	#ifdef CONFIG_COMPAT
	418
	419	asmlinkage ssize_t
	420	compat_process_vm_rw(compat_pid_t pid,
	421	const struct compat_iovec __user *lvec,
	422	unsigned long liovcnt,
	423	const struct compat_iovec __user *rvec,
	424	unsigned long riovcnt,
	425	unsigned long flags, int vm_write)
	426	{
	427	struct iovec iovstack_l[UIO_FASTIOV];
	428	struct iovec iovstack_r[UIO_FASTIOV];
	429	struct iovec *iov_l = iovstack_l;
	430	struct iovec *iov_r = iovstack_r;
	431	ssize_t rc = -EFAULT;
	432
	433	if (flags != 0)
	434	return -EINVAL;
	435
fcf63409 CY	436	if (vm_write)
	437	rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt,
	438	UIO_FASTIOV, iovstack_l,
ac34ebb3	439	&iov_l);
fcf63409 CY	440	else
	441	rc = compat_rw_copy_check_uvector(READ, lvec, liovcnt,
	442	UIO_FASTIOV, iovstack_l,
ac34ebb3	443	&iov_l);
fcf63409 CY	444	if (rc <= 0)
fcf63409 CY	445	goto free_iovecs;
ac34ebb3	446	rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
fcf63409	447	UIO_FASTIOV, iovstack_r,
ac34ebb3	448	&iov_r);
fcf63409 CY	449	if (rc <= 0)
	450	goto free_iovecs;
	451
	452	rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
	453	vm_write);
	454
	455	free_iovecs:
	456	if (iov_r != iovstack_r)
	457	kfree(iov_r);
	458	if (iov_l != iovstack_l)
	459	kfree(iov_l);
fcf63409 CY	460	return rc;
	461	}
	462
	463	asmlinkage ssize_t
	464	compat_sys_process_vm_readv(compat_pid_t pid,
	465	const struct compat_iovec __user *lvec,
	466	unsigned long liovcnt,
	467	const struct compat_iovec __user *rvec,
	468	unsigned long riovcnt,
	469	unsigned long flags)
	470	{
	471	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
	472	riovcnt, flags, 0);
	473	}
	474
	475	asmlinkage ssize_t
	476	compat_sys_process_vm_writev(compat_pid_t pid,
	477	const struct compat_iovec __user *lvec,
	478	unsigned long liovcnt,
	479	const struct compat_iovec __user *rvec,
	480	unsigned long riovcnt,
	481	unsigned long flags)
	482	{
	483	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
	484	riovcnt, flags, 1);
	485	}
	486
	487	#endif