 7e33912849
			
		
	
	
	7e33912849
	
	
	
		
			
			This allows those get_user_pages calls to pass FAULT_FLAG_ALLOW_RETRY to the page fault in order to release the mmap_sem during the I/O. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Peter Feiner <pfeiner@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
		
			
				
	
	
		
			376 lines
		
	
	
	
		
			10 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			376 lines
		
	
	
	
		
			10 KiB
			
		
	
	
	
		
			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
 | |
|  * @pages: array of pointers to pages we want to copy
 | |
|  * @start_offset: offset in page to start copying from/to
 | |
|  * @len: number of bytes to copy
 | |
|  * @iter: where to copy to/from locally
 | |
|  * @vm_write: 0 means copy from, 1 means copy to
 | |
|  * Returns 0 on success, error code otherwise
 | |
|  */
 | |
| static int process_vm_rw_pages(struct page **pages,
 | |
| 			       unsigned offset,
 | |
| 			       size_t len,
 | |
| 			       struct iov_iter *iter,
 | |
| 			       int vm_write)
 | |
| {
 | |
| 	/* Do the copy for each page */
 | |
| 	while (len && iov_iter_count(iter)) {
 | |
| 		struct page *page = *pages++;
 | |
| 		size_t copy = PAGE_SIZE - offset;
 | |
| 		size_t copied;
 | |
| 
 | |
| 		if (copy > len)
 | |
| 			copy = len;
 | |
| 
 | |
| 		if (vm_write) {
 | |
| 			copied = copy_page_from_iter(page, offset, copy, iter);
 | |
| 			set_page_dirty_lock(page);
 | |
| 		} else {
 | |
| 			copied = copy_page_to_iter(page, offset, copy, iter);
 | |
| 		}
 | |
| 		len -= copied;
 | |
| 		if (copied < copy && iov_iter_count(iter))
 | |
| 			return -EFAULT;
 | |
| 		offset = 0;
 | |
| 	}
 | |
| 	return 0;
 | |
| }
 | |
| 
 | |
| /* 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
 | |
|  * @iter: where to copy to/from locally
 | |
|  * @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
 | |
|  * Returns 0 on success or on failure error code
 | |
|  */
 | |
| static int process_vm_rw_single_vec(unsigned long addr,
 | |
| 				    unsigned long len,
 | |
| 				    struct iov_iter *iter,
 | |
| 				    struct page **process_pages,
 | |
| 				    struct mm_struct *mm,
 | |
| 				    struct task_struct *task,
 | |
| 				    int vm_write)
 | |
| {
 | |
| 	unsigned long pa = addr & PAGE_MASK;
 | |
| 	unsigned long start_offset = addr - pa;
 | |
| 	unsigned long nr_pages;
 | |
| 	ssize_t rc = 0;
 | |
| 	unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
 | |
| 		/ sizeof(struct pages *);
 | |
| 
 | |
| 	/* Work out address and page range required */
 | |
| 	if (len == 0)
 | |
| 		return 0;
 | |
| 	nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
 | |
| 
 | |
| 	while (!rc && nr_pages && iov_iter_count(iter)) {
 | |
| 		int pages = min(nr_pages, max_pages_per_loop);
 | |
| 		size_t bytes;
 | |
| 
 | |
| 		/* Get the pages we're interested in */
 | |
| 		pages = get_user_pages_unlocked(task, mm, pa, pages,
 | |
| 						vm_write, 0, process_pages);
 | |
| 		if (pages <= 0)
 | |
| 			return -EFAULT;
 | |
| 
 | |
| 		bytes = pages * PAGE_SIZE - start_offset;
 | |
| 		if (bytes > len)
 | |
| 			bytes = len;
 | |
| 
 | |
| 		rc = process_vm_rw_pages(process_pages,
 | |
| 					 start_offset, bytes, iter,
 | |
| 					 vm_write);
 | |
| 		len -= bytes;
 | |
| 		start_offset = 0;
 | |
| 		nr_pages -= pages;
 | |
| 		pa += pages * PAGE_SIZE;
 | |
| 		while (pages)
 | |
| 			put_page(process_pages[--pages]);
 | |
| 	}
 | |
| 
 | |
| 	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
 | |
|  * @iter: where to copy to/from locally
 | |
|  * @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, struct iov_iter *iter,
 | |
| 				  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;
 | |
| 	unsigned long nr_pages = 0;
 | |
| 	unsigned long nr_pages_iov;
 | |
| 	ssize_t iov_len;
 | |
| 	size_t total_len = iov_iter_count(iter);
 | |
| 
 | |
| 	/*
 | |
| 	 * 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_iter_count(iter) && !rc; i++)
 | |
| 		rc = process_vm_rw_single_vec(
 | |
| 			(unsigned long)rvec[i].iov_base, rvec[i].iov_len,
 | |
| 			iter, process_pages, mm, task, vm_write);
 | |
| 
 | |
| 	/* copied = space before - space after */
 | |
| 	total_len -= iov_iter_count(iter);
 | |
| 
 | |
| 	/* 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 (total_len)
 | |
| 		rc = total_len;
 | |
| 
 | |
| 	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;
 | |
| 	struct iov_iter iter;
 | |
| 	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;
 | |
| 
 | |
| 	iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
 | |
| 
 | |
| 	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, &iter, 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
 | |
| 
 | |
| static 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;
 | |
| 	struct iov_iter iter;
 | |
| 	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;
 | |
| 	iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
 | |
| 	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, &iter, 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;
 | |
| }
 | |
| 
 | |
| COMPAT_SYSCALL_DEFINE6(process_vm_readv, compat_pid_t, pid,
 | |
| 		       const struct compat_iovec __user *, lvec,
 | |
| 		       compat_ulong_t, liovcnt,
 | |
| 		       const struct compat_iovec __user *, rvec,
 | |
| 		       compat_ulong_t, riovcnt,
 | |
| 		       compat_ulong_t, flags)
 | |
| {
 | |
| 	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
 | |
| 				    riovcnt, flags, 0);
 | |
| }
 | |
| 
 | |
| COMPAT_SYSCALL_DEFINE6(process_vm_writev, compat_pid_t, pid,
 | |
| 		       const struct compat_iovec __user *, lvec,
 | |
| 		       compat_ulong_t, liovcnt,
 | |
| 		       const struct compat_iovec __user *, rvec,
 | |
| 		       compat_ulong_t, riovcnt,
 | |
| 		       compat_ulong_t, flags)
 | |
| {
 | |
| 	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
 | |
| 				    riovcnt, flags, 1);
 | |
| }
 | |
| 
 | |
| #endif
 |