2009-02-10 04:05:49 +08:00
|
|
|
/******************************************************************************
|
|
|
|
* privcmd.c
|
|
|
|
*
|
|
|
|
* Interface to privileged domain-0 commands.
|
|
|
|
*
|
|
|
|
* Copyright (c) 2002-2004, K A Fraser, B Dragovic
|
|
|
|
*/
|
|
|
|
|
2013-06-28 18:21:41 +08:00
|
|
|
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
|
|
|
|
|
2009-02-10 04:05:49 +08:00
|
|
|
#include <linux/kernel.h>
|
2011-12-17 00:34:33 +08:00
|
|
|
#include <linux/module.h>
|
2009-02-10 04:05:49 +08:00
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/mman.h>
|
|
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <linux/swap.h>
|
|
|
|
#include <linux/highmem.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/seq_file.h>
|
2011-12-17 00:34:33 +08:00
|
|
|
#include <linux/miscdevice.h>
|
2017-02-14 01:03:23 +08:00
|
|
|
#include <linux/moduleparam.h>
|
2009-02-10 04:05:49 +08:00
|
|
|
|
|
|
|
#include <asm/pgalloc.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/tlb.h>
|
|
|
|
#include <asm/xen/hypervisor.h>
|
|
|
|
#include <asm/xen/hypercall.h>
|
|
|
|
|
|
|
|
#include <xen/xen.h>
|
|
|
|
#include <xen/privcmd.h>
|
|
|
|
#include <xen/interface/xen.h>
|
2017-02-14 01:03:23 +08:00
|
|
|
#include <xen/interface/hvm/dm_op.h>
|
2009-02-10 04:05:49 +08:00
|
|
|
#include <xen/features.h>
|
|
|
|
#include <xen/page.h>
|
2009-05-21 17:09:46 +08:00
|
|
|
#include <xen/xen-ops.h>
|
2012-10-18 08:11:21 +08:00
|
|
|
#include <xen/balloon.h>
|
2009-05-20 22:42:14 +08:00
|
|
|
|
2011-12-17 00:34:33 +08:00
|
|
|
#include "privcmd.h"
|
|
|
|
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
|
2012-10-18 08:11:21 +08:00
|
|
|
#define PRIV_VMA_LOCKED ((void *)1)
|
|
|
|
|
2017-02-14 01:03:23 +08:00
|
|
|
static unsigned int privcmd_dm_op_max_num = 16;
|
|
|
|
module_param_named(dm_op_max_nr_bufs, privcmd_dm_op_max_num, uint, 0644);
|
|
|
|
MODULE_PARM_DESC(dm_op_max_nr_bufs,
|
|
|
|
"Maximum number of buffers per dm_op hypercall");
|
|
|
|
|
|
|
|
static unsigned int privcmd_dm_op_buf_max_size = 4096;
|
|
|
|
module_param_named(dm_op_buf_max_size, privcmd_dm_op_buf_max_size, uint,
|
|
|
|
0644);
|
|
|
|
MODULE_PARM_DESC(dm_op_buf_max_size,
|
|
|
|
"Maximum size of a dm_op hypercall buffer");
|
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
struct privcmd_data {
|
|
|
|
domid_t domid;
|
|
|
|
};
|
|
|
|
|
2013-08-24 01:10:06 +08:00
|
|
|
static int privcmd_vma_range_is_mapped(
|
|
|
|
struct vm_area_struct *vma,
|
|
|
|
unsigned long addr,
|
|
|
|
unsigned long nr_pages);
|
2009-02-10 04:05:49 +08:00
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
static long privcmd_ioctl_hypercall(struct file *file, void __user *udata)
|
2009-02-10 04:05:49 +08:00
|
|
|
{
|
2017-02-14 01:03:24 +08:00
|
|
|
struct privcmd_data *data = file->private_data;
|
2009-02-10 04:05:49 +08:00
|
|
|
struct privcmd_hypercall hypercall;
|
|
|
|
long ret;
|
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
/* Disallow arbitrary hypercalls if restricted */
|
|
|
|
if (data->domid != DOMID_INVALID)
|
|
|
|
return -EPERM;
|
|
|
|
|
2009-02-10 04:05:49 +08:00
|
|
|
if (copy_from_user(&hypercall, udata, sizeof(hypercall)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
2015-02-19 23:23:17 +08:00
|
|
|
xen_preemptible_hcall_begin();
|
2009-02-10 04:05:49 +08:00
|
|
|
ret = privcmd_call(hypercall.op,
|
|
|
|
hypercall.arg[0], hypercall.arg[1],
|
|
|
|
hypercall.arg[2], hypercall.arg[3],
|
|
|
|
hypercall.arg[4]);
|
2015-02-19 23:23:17 +08:00
|
|
|
xen_preemptible_hcall_end();
|
2009-02-10 04:05:49 +08:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void free_page_list(struct list_head *pages)
|
|
|
|
{
|
|
|
|
struct page *p, *n;
|
|
|
|
|
|
|
|
list_for_each_entry_safe(p, n, pages, lru)
|
|
|
|
__free_page(p);
|
|
|
|
|
|
|
|
INIT_LIST_HEAD(pages);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Given an array of items in userspace, return a list of pages
|
|
|
|
* containing the data. If copying fails, either because of memory
|
|
|
|
* allocation failure or a problem reading user memory, return an
|
|
|
|
* error code; its up to the caller to dispose of any partial list.
|
|
|
|
*/
|
|
|
|
static int gather_array(struct list_head *pagelist,
|
|
|
|
unsigned nelem, size_t size,
|
2012-08-31 21:59:30 +08:00
|
|
|
const void __user *data)
|
2009-02-10 04:05:49 +08:00
|
|
|
{
|
|
|
|
unsigned pageidx;
|
|
|
|
void *pagedata;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (size > PAGE_SIZE)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
pageidx = PAGE_SIZE;
|
|
|
|
pagedata = NULL; /* quiet, gcc */
|
|
|
|
while (nelem--) {
|
|
|
|
if (pageidx > PAGE_SIZE-size) {
|
|
|
|
struct page *page = alloc_page(GFP_KERNEL);
|
|
|
|
|
|
|
|
ret = -ENOMEM;
|
|
|
|
if (page == NULL)
|
|
|
|
goto fail;
|
|
|
|
|
|
|
|
pagedata = page_address(page);
|
|
|
|
|
|
|
|
list_add_tail(&page->lru, pagelist);
|
|
|
|
pageidx = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = -EFAULT;
|
|
|
|
if (copy_from_user(pagedata + pageidx, data, size))
|
|
|
|
goto fail;
|
|
|
|
|
|
|
|
data += size;
|
|
|
|
pageidx += size;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = 0;
|
|
|
|
|
|
|
|
fail:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Call function "fn" on each element of the array fragmented
|
|
|
|
* over a list of pages.
|
|
|
|
*/
|
|
|
|
static int traverse_pages(unsigned nelem, size_t size,
|
|
|
|
struct list_head *pos,
|
|
|
|
int (*fn)(void *data, void *state),
|
|
|
|
void *state)
|
|
|
|
{
|
|
|
|
void *pagedata;
|
|
|
|
unsigned pageidx;
|
2009-05-20 22:42:14 +08:00
|
|
|
int ret = 0;
|
2009-02-10 04:05:49 +08:00
|
|
|
|
|
|
|
BUG_ON(size > PAGE_SIZE);
|
|
|
|
|
|
|
|
pageidx = PAGE_SIZE;
|
|
|
|
pagedata = NULL; /* hush, gcc */
|
|
|
|
|
|
|
|
while (nelem--) {
|
|
|
|
if (pageidx > PAGE_SIZE-size) {
|
|
|
|
struct page *page;
|
|
|
|
pos = pos->next;
|
|
|
|
page = list_entry(pos, struct page, lru);
|
|
|
|
pagedata = page_address(page);
|
|
|
|
pageidx = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = (*fn)(pagedata + pageidx, state);
|
|
|
|
if (ret)
|
|
|
|
break;
|
|
|
|
pageidx += size;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2015-03-11 22:49:57 +08:00
|
|
|
/*
|
|
|
|
* Similar to traverse_pages, but use each page as a "block" of
|
|
|
|
* data to be processed as one unit.
|
|
|
|
*/
|
|
|
|
static int traverse_pages_block(unsigned nelem, size_t size,
|
|
|
|
struct list_head *pos,
|
|
|
|
int (*fn)(void *data, int nr, void *state),
|
|
|
|
void *state)
|
|
|
|
{
|
|
|
|
void *pagedata;
|
|
|
|
unsigned pageidx;
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
BUG_ON(size > PAGE_SIZE);
|
|
|
|
|
|
|
|
pageidx = PAGE_SIZE;
|
|
|
|
|
|
|
|
while (nelem) {
|
|
|
|
int nr = (PAGE_SIZE/size);
|
|
|
|
struct page *page;
|
|
|
|
if (nr > nelem)
|
|
|
|
nr = nelem;
|
|
|
|
pos = pos->next;
|
|
|
|
page = list_entry(pos, struct page, lru);
|
|
|
|
pagedata = page_address(page);
|
|
|
|
ret = (*fn)(pagedata, nr, state);
|
|
|
|
if (ret)
|
|
|
|
break;
|
|
|
|
nelem -= nr;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2015-08-08 00:34:41 +08:00
|
|
|
struct mmap_gfn_state {
|
2009-02-10 04:05:49 +08:00
|
|
|
unsigned long va;
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
domid_t domain;
|
|
|
|
};
|
|
|
|
|
2015-08-08 00:34:41 +08:00
|
|
|
static int mmap_gfn_range(void *data, void *state)
|
2009-02-10 04:05:49 +08:00
|
|
|
{
|
|
|
|
struct privcmd_mmap_entry *msg = data;
|
2015-08-08 00:34:41 +08:00
|
|
|
struct mmap_gfn_state *st = state;
|
2009-02-10 04:05:49 +08:00
|
|
|
struct vm_area_struct *vma = st->vma;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
/* Do not allow range to wrap the address space. */
|
|
|
|
if ((msg->npages > (LONG_MAX >> PAGE_SHIFT)) ||
|
|
|
|
((unsigned long)(msg->npages << PAGE_SHIFT) >= -st->va))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
/* Range chunks must be contiguous in va space. */
|
|
|
|
if ((msg->va != st->va) ||
|
|
|
|
((msg->va+(msg->npages<<PAGE_SHIFT)) > vma->vm_end))
|
|
|
|
return -EINVAL;
|
|
|
|
|
2015-08-08 00:34:41 +08:00
|
|
|
rc = xen_remap_domain_gfn_range(vma,
|
2009-05-21 17:09:46 +08:00
|
|
|
msg->va & PAGE_MASK,
|
|
|
|
msg->mfn, msg->npages,
|
|
|
|
vma->vm_page_prot,
|
2012-10-18 04:37:49 +08:00
|
|
|
st->domain, NULL);
|
2009-02-10 04:05:49 +08:00
|
|
|
if (rc < 0)
|
|
|
|
return rc;
|
|
|
|
|
|
|
|
st->va += msg->npages << PAGE_SHIFT;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
static long privcmd_ioctl_mmap(struct file *file, void __user *udata)
|
2009-02-10 04:05:49 +08:00
|
|
|
{
|
2017-02-14 01:03:24 +08:00
|
|
|
struct privcmd_data *data = file->private_data;
|
2009-02-10 04:05:49 +08:00
|
|
|
struct privcmd_mmap mmapcmd;
|
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
int rc;
|
|
|
|
LIST_HEAD(pagelist);
|
2015-08-08 00:34:41 +08:00
|
|
|
struct mmap_gfn_state state;
|
2009-02-10 04:05:49 +08:00
|
|
|
|
2012-10-18 08:11:21 +08:00
|
|
|
/* We only support privcmd_ioctl_mmap_batch for auto translated. */
|
|
|
|
if (xen_feature(XENFEAT_auto_translated_physmap))
|
|
|
|
return -ENOSYS;
|
|
|
|
|
2009-02-10 04:05:49 +08:00
|
|
|
if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
/* If restriction is in place, check the domid matches */
|
|
|
|
if (data->domid != DOMID_INVALID && data->domid != mmapcmd.dom)
|
|
|
|
return -EPERM;
|
|
|
|
|
2009-02-10 04:05:49 +08:00
|
|
|
rc = gather_array(&pagelist,
|
|
|
|
mmapcmd.num, sizeof(struct privcmd_mmap_entry),
|
|
|
|
mmapcmd.entry);
|
|
|
|
|
|
|
|
if (rc || list_empty(&pagelist))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
down_write(&mm->mmap_sem);
|
|
|
|
|
|
|
|
{
|
|
|
|
struct page *page = list_first_entry(&pagelist,
|
|
|
|
struct page, lru);
|
|
|
|
struct privcmd_mmap_entry *msg = page_address(page);
|
|
|
|
|
|
|
|
vma = find_vma(mm, msg->va);
|
|
|
|
rc = -EINVAL;
|
|
|
|
|
2013-08-24 01:10:06 +08:00
|
|
|
if (!vma || (msg->va != vma->vm_start) || vma->vm_private_data)
|
2009-02-10 04:05:49 +08:00
|
|
|
goto out_up;
|
2013-08-24 01:10:06 +08:00
|
|
|
vma->vm_private_data = PRIV_VMA_LOCKED;
|
2009-02-10 04:05:49 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
state.va = vma->vm_start;
|
|
|
|
state.vma = vma;
|
|
|
|
state.domain = mmapcmd.dom;
|
|
|
|
|
|
|
|
rc = traverse_pages(mmapcmd.num, sizeof(struct privcmd_mmap_entry),
|
|
|
|
&pagelist,
|
2015-08-08 00:34:41 +08:00
|
|
|
mmap_gfn_range, &state);
|
2009-02-10 04:05:49 +08:00
|
|
|
|
|
|
|
|
|
|
|
out_up:
|
|
|
|
up_write(&mm->mmap_sem);
|
|
|
|
|
|
|
|
out:
|
|
|
|
free_page_list(&pagelist);
|
|
|
|
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct mmap_batch_state {
|
|
|
|
domid_t domain;
|
|
|
|
unsigned long va;
|
|
|
|
struct vm_area_struct *vma;
|
2012-10-18 08:11:21 +08:00
|
|
|
int index;
|
2012-08-31 21:59:30 +08:00
|
|
|
/* A tristate:
|
|
|
|
* 0 for no errors
|
|
|
|
* 1 if at least one error has happened (and no
|
|
|
|
* -ENOENT errors have happened)
|
|
|
|
* -ENOENT if at least 1 -ENOENT has happened.
|
|
|
|
*/
|
|
|
|
int global_error;
|
2013-01-15 11:35:40 +08:00
|
|
|
int version;
|
2012-08-31 21:59:30 +08:00
|
|
|
|
2015-08-08 00:34:41 +08:00
|
|
|
/* User-space gfn array to store errors in the second pass for V1. */
|
|
|
|
xen_pfn_t __user *user_gfn;
|
2013-01-15 11:35:40 +08:00
|
|
|
/* User-space int array to store errors in the second pass for V2. */
|
|
|
|
int __user *user_err;
|
2009-02-10 04:05:49 +08:00
|
|
|
};
|
|
|
|
|
2015-08-08 00:34:41 +08:00
|
|
|
/* auto translated dom0 note: if domU being created is PV, then gfn is
|
|
|
|
* mfn(addr on bus). If it's auto xlated, then gfn is pfn (input to HAP).
|
2012-10-18 08:11:21 +08:00
|
|
|
*/
|
2015-03-11 22:49:57 +08:00
|
|
|
static int mmap_batch_fn(void *data, int nr, void *state)
|
2009-02-10 04:05:49 +08:00
|
|
|
{
|
2015-08-08 00:34:41 +08:00
|
|
|
xen_pfn_t *gfnp = data;
|
2009-02-10 04:05:49 +08:00
|
|
|
struct mmap_batch_state *st = state;
|
2012-10-18 08:11:21 +08:00
|
|
|
struct vm_area_struct *vma = st->vma;
|
|
|
|
struct page **pages = vma->vm_private_data;
|
2015-03-11 22:49:57 +08:00
|
|
|
struct page **cur_pages = NULL;
|
2012-08-31 21:59:30 +08:00
|
|
|
int ret;
|
|
|
|
|
2012-10-18 08:11:21 +08:00
|
|
|
if (xen_feature(XENFEAT_auto_translated_physmap))
|
2015-03-11 22:49:57 +08:00
|
|
|
cur_pages = &pages[st->index];
|
2012-10-18 08:11:21 +08:00
|
|
|
|
2015-03-11 22:49:57 +08:00
|
|
|
BUG_ON(nr < 0);
|
2015-08-08 00:34:41 +08:00
|
|
|
ret = xen_remap_domain_gfn_array(st->vma, st->va & PAGE_MASK, gfnp, nr,
|
|
|
|
(int *)gfnp, st->vma->vm_page_prot,
|
2015-03-11 22:49:57 +08:00
|
|
|
st->domain, cur_pages);
|
2009-02-10 04:05:49 +08:00
|
|
|
|
2015-03-11 22:49:57 +08:00
|
|
|
/* Adjust the global_error? */
|
|
|
|
if (ret != nr) {
|
2012-08-31 21:59:30 +08:00
|
|
|
if (ret == -ENOENT)
|
|
|
|
st->global_error = -ENOENT;
|
|
|
|
else {
|
|
|
|
/* Record that at least one error has happened. */
|
|
|
|
if (st->global_error == 0)
|
|
|
|
st->global_error = 1;
|
|
|
|
}
|
2009-02-10 04:05:49 +08:00
|
|
|
}
|
2017-05-31 21:03:57 +08:00
|
|
|
st->va += XEN_PAGE_SIZE * nr;
|
|
|
|
st->index += nr / XEN_PFN_PER_PAGE;
|
2009-02-10 04:05:49 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-03-11 22:49:57 +08:00
|
|
|
static int mmap_return_error(int err, struct mmap_batch_state *st)
|
2009-02-10 04:05:49 +08:00
|
|
|
{
|
2015-03-11 22:49:57 +08:00
|
|
|
int ret;
|
2012-08-31 21:59:30 +08:00
|
|
|
|
2013-01-15 11:35:40 +08:00
|
|
|
if (st->version == 1) {
|
2015-03-11 22:49:57 +08:00
|
|
|
if (err) {
|
2015-08-08 00:34:41 +08:00
|
|
|
xen_pfn_t gfn;
|
2015-03-11 22:49:57 +08:00
|
|
|
|
2015-08-08 00:34:41 +08:00
|
|
|
ret = get_user(gfn, st->user_gfn);
|
2015-03-11 22:49:57 +08:00
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
/*
|
|
|
|
* V1 encodes the error codes in the 32bit top
|
2015-08-08 00:34:41 +08:00
|
|
|
* nibble of the gfn (with its known
|
2015-03-11 22:49:57 +08:00
|
|
|
* limitations vis-a-vis 64 bit callers).
|
|
|
|
*/
|
2015-08-08 00:34:41 +08:00
|
|
|
gfn |= (err == -ENOENT) ?
|
2015-03-11 22:49:57 +08:00
|
|
|
PRIVCMD_MMAPBATCH_PAGED_ERROR :
|
|
|
|
PRIVCMD_MMAPBATCH_MFN_ERROR;
|
2015-08-08 00:34:41 +08:00
|
|
|
return __put_user(gfn, st->user_gfn++);
|
2015-03-11 22:49:57 +08:00
|
|
|
} else
|
2015-08-08 00:34:41 +08:00
|
|
|
st->user_gfn++;
|
2013-01-15 11:35:40 +08:00
|
|
|
} else { /* st->version == 2 */
|
|
|
|
if (err)
|
|
|
|
return __put_user(err, st->user_err++);
|
|
|
|
else
|
|
|
|
st->user_err++;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
2009-02-10 04:05:49 +08:00
|
|
|
}
|
|
|
|
|
2015-03-11 22:49:57 +08:00
|
|
|
static int mmap_return_errors(void *data, int nr, void *state)
|
|
|
|
{
|
|
|
|
struct mmap_batch_state *st = state;
|
|
|
|
int *errs = data;
|
|
|
|
int i;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
for (i = 0; i < nr; i++) {
|
|
|
|
ret = mmap_return_error(errs[i], st);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-08-08 00:34:41 +08:00
|
|
|
/* Allocate pfns that are then mapped with gfns from foreign domid. Update
|
2012-10-18 08:11:21 +08:00
|
|
|
* the vma with the page info to use later.
|
|
|
|
* Returns: 0 if success, otherwise -errno
|
|
|
|
*/
|
|
|
|
static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs)
|
|
|
|
{
|
|
|
|
int rc;
|
|
|
|
struct page **pages;
|
|
|
|
|
|
|
|
pages = kcalloc(numpgs, sizeof(pages[0]), GFP_KERNEL);
|
|
|
|
if (pages == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2015-06-25 20:12:46 +08:00
|
|
|
rc = alloc_xenballooned_pages(numpgs, pages);
|
2012-10-18 08:11:21 +08:00
|
|
|
if (rc != 0) {
|
|
|
|
pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__,
|
|
|
|
numpgs, rc);
|
|
|
|
kfree(pages);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
2013-08-24 01:10:06 +08:00
|
|
|
BUG_ON(vma->vm_private_data != NULL);
|
2012-10-18 08:11:21 +08:00
|
|
|
vma->vm_private_data = pages;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-09-10 06:39:26 +08:00
|
|
|
static const struct vm_operations_struct privcmd_vm_ops;
|
2009-03-08 19:10:00 +08:00
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
static long privcmd_ioctl_mmap_batch(
|
|
|
|
struct file *file, void __user *udata, int version)
|
2009-02-10 04:05:49 +08:00
|
|
|
{
|
2017-02-14 01:03:24 +08:00
|
|
|
struct privcmd_data *data = file->private_data;
|
2009-02-10 04:05:49 +08:00
|
|
|
int ret;
|
2012-08-31 21:59:30 +08:00
|
|
|
struct privcmd_mmapbatch_v2 m;
|
2009-02-10 04:05:49 +08:00
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
unsigned long nr_pages;
|
|
|
|
LIST_HEAD(pagelist);
|
|
|
|
struct mmap_batch_state state;
|
|
|
|
|
2012-08-31 21:59:30 +08:00
|
|
|
switch (version) {
|
|
|
|
case 1:
|
|
|
|
if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch)))
|
|
|
|
return -EFAULT;
|
|
|
|
/* Returns per-frame error in m.arr. */
|
|
|
|
m.err = NULL;
|
|
|
|
if (!access_ok(VERIFY_WRITE, m.arr, m.num * sizeof(*m.arr)))
|
|
|
|
return -EFAULT;
|
|
|
|
break;
|
|
|
|
case 2:
|
|
|
|
if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch_v2)))
|
|
|
|
return -EFAULT;
|
|
|
|
/* Returns per-frame error code in m.err. */
|
|
|
|
if (!access_ok(VERIFY_WRITE, m.err, m.num * (sizeof(*m.err))))
|
|
|
|
return -EFAULT;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2009-02-10 04:05:49 +08:00
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
/* If restriction is in place, check the domid matches */
|
|
|
|
if (data->domid != DOMID_INVALID && data->domid != m.dom)
|
|
|
|
return -EPERM;
|
|
|
|
|
2015-05-05 23:54:12 +08:00
|
|
|
nr_pages = DIV_ROUND_UP(m.num, XEN_PFN_PER_PAGE);
|
2009-02-10 04:05:49 +08:00
|
|
|
if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT)))
|
|
|
|
return -EINVAL;
|
|
|
|
|
2012-08-31 21:59:30 +08:00
|
|
|
ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t), m.arr);
|
2009-02-10 04:05:49 +08:00
|
|
|
|
2012-08-31 21:59:30 +08:00
|
|
|
if (ret)
|
2009-02-10 04:05:49 +08:00
|
|
|
goto out;
|
2012-08-31 21:59:30 +08:00
|
|
|
if (list_empty(&pagelist)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2013-01-15 11:35:40 +08:00
|
|
|
if (version == 2) {
|
|
|
|
/* Zero error array now to only copy back actual errors. */
|
|
|
|
if (clear_user(m.err, sizeof(int) * m.num)) {
|
|
|
|
ret = -EFAULT;
|
|
|
|
goto out;
|
|
|
|
}
|
2012-08-31 21:59:30 +08:00
|
|
|
}
|
2009-02-10 04:05:49 +08:00
|
|
|
|
|
|
|
down_write(&mm->mmap_sem);
|
|
|
|
|
|
|
|
vma = find_vma(mm, m.addr);
|
|
|
|
if (!vma ||
|
2013-08-24 01:10:06 +08:00
|
|
|
vma->vm_ops != &privcmd_vm_ops) {
|
2012-11-17 02:36:49 +08:00
|
|
|
ret = -EINVAL;
|
2013-08-24 01:10:06 +08:00
|
|
|
goto out_unlock;
|
2009-02-10 04:05:49 +08:00
|
|
|
}
|
2013-08-24 01:10:06 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Caller must either:
|
|
|
|
*
|
|
|
|
* Map the whole VMA range, which will also allocate all the
|
|
|
|
* pages required for the auto_translated_physmap case.
|
|
|
|
*
|
|
|
|
* Or
|
|
|
|
*
|
|
|
|
* Map unmapped holes left from a previous map attempt (e.g.,
|
|
|
|
* because those foreign frames were previously paged out).
|
|
|
|
*/
|
|
|
|
if (vma->vm_private_data == NULL) {
|
|
|
|
if (m.addr != vma->vm_start ||
|
|
|
|
m.addr + (nr_pages << PAGE_SHIFT) != vma->vm_end) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
if (xen_feature(XENFEAT_auto_translated_physmap)) {
|
2015-05-05 23:54:12 +08:00
|
|
|
ret = alloc_empty_pages(vma, nr_pages);
|
2013-08-24 01:10:06 +08:00
|
|
|
if (ret < 0)
|
|
|
|
goto out_unlock;
|
|
|
|
} else
|
|
|
|
vma->vm_private_data = PRIV_VMA_LOCKED;
|
|
|
|
} else {
|
|
|
|
if (m.addr < vma->vm_start ||
|
|
|
|
m.addr + (nr_pages << PAGE_SHIFT) > vma->vm_end) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
if (privcmd_vma_range_is_mapped(vma, m.addr, nr_pages)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out_unlock;
|
2012-10-18 08:11:21 +08:00
|
|
|
}
|
|
|
|
}
|
2009-02-10 04:05:49 +08:00
|
|
|
|
2012-08-31 21:59:30 +08:00
|
|
|
state.domain = m.dom;
|
|
|
|
state.vma = vma;
|
|
|
|
state.va = m.addr;
|
2012-10-18 08:11:21 +08:00
|
|
|
state.index = 0;
|
2012-08-31 21:59:30 +08:00
|
|
|
state.global_error = 0;
|
2013-01-15 11:35:40 +08:00
|
|
|
state.version = version;
|
2009-02-10 04:05:49 +08:00
|
|
|
|
2015-05-05 23:54:12 +08:00
|
|
|
BUILD_BUG_ON(((PAGE_SIZE / sizeof(xen_pfn_t)) % XEN_PFN_PER_PAGE) != 0);
|
2012-08-31 21:59:30 +08:00
|
|
|
/* mmap_batch_fn guarantees ret == 0 */
|
2015-03-11 22:49:57 +08:00
|
|
|
BUG_ON(traverse_pages_block(m.num, sizeof(xen_pfn_t),
|
|
|
|
&pagelist, mmap_batch_fn, &state));
|
2009-02-10 04:05:49 +08:00
|
|
|
|
|
|
|
up_write(&mm->mmap_sem);
|
|
|
|
|
2013-01-15 11:35:40 +08:00
|
|
|
if (state.global_error) {
|
|
|
|
/* Write back errors in second pass. */
|
2015-08-08 00:34:41 +08:00
|
|
|
state.user_gfn = (xen_pfn_t *)m.arr;
|
2013-01-15 11:35:40 +08:00
|
|
|
state.user_err = m.err;
|
2015-03-11 22:49:57 +08:00
|
|
|
ret = traverse_pages_block(m.num, sizeof(xen_pfn_t),
|
|
|
|
&pagelist, mmap_return_errors, &state);
|
2013-01-15 11:35:40 +08:00
|
|
|
} else
|
|
|
|
ret = 0;
|
2012-08-31 21:59:30 +08:00
|
|
|
|
|
|
|
/* If we have not had any EFAULT-like global errors then set the global
|
|
|
|
* error to -ENOENT if necessary. */
|
|
|
|
if ((ret == 0) && (state.global_error == -ENOENT))
|
|
|
|
ret = -ENOENT;
|
2009-02-10 04:05:49 +08:00
|
|
|
|
|
|
|
out:
|
|
|
|
free_page_list(&pagelist);
|
|
|
|
return ret;
|
2013-08-24 01:10:06 +08:00
|
|
|
|
|
|
|
out_unlock:
|
|
|
|
up_write(&mm->mmap_sem);
|
|
|
|
goto out;
|
2009-02-10 04:05:49 +08:00
|
|
|
}
|
|
|
|
|
2017-02-14 01:03:23 +08:00
|
|
|
static int lock_pages(
|
|
|
|
struct privcmd_dm_op_buf kbufs[], unsigned int num,
|
|
|
|
struct page *pages[], unsigned int nr_pages)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
for (i = 0; i < num; i++) {
|
|
|
|
unsigned int requested;
|
|
|
|
int pinned;
|
|
|
|
|
|
|
|
requested = DIV_ROUND_UP(
|
|
|
|
offset_in_page(kbufs[i].uptr) + kbufs[i].size,
|
|
|
|
PAGE_SIZE);
|
|
|
|
if (requested > nr_pages)
|
|
|
|
return -ENOSPC;
|
|
|
|
|
|
|
|
pinned = get_user_pages_fast(
|
|
|
|
(unsigned long) kbufs[i].uptr,
|
|
|
|
requested, FOLL_WRITE, pages);
|
|
|
|
if (pinned < 0)
|
|
|
|
return pinned;
|
|
|
|
|
|
|
|
nr_pages -= pinned;
|
|
|
|
pages += pinned;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void unlock_pages(struct page *pages[], unsigned int nr_pages)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
if (!pages)
|
|
|
|
return;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
|
|
if (pages[i])
|
|
|
|
put_page(pages[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
|
2017-02-14 01:03:23 +08:00
|
|
|
{
|
2017-02-14 01:03:24 +08:00
|
|
|
struct privcmd_data *data = file->private_data;
|
2017-02-14 01:03:23 +08:00
|
|
|
struct privcmd_dm_op kdata;
|
|
|
|
struct privcmd_dm_op_buf *kbufs;
|
|
|
|
unsigned int nr_pages = 0;
|
|
|
|
struct page **pages = NULL;
|
|
|
|
struct xen_dm_op_buf *xbufs = NULL;
|
|
|
|
unsigned int i;
|
|
|
|
long rc;
|
|
|
|
|
|
|
|
if (copy_from_user(&kdata, udata, sizeof(kdata)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
/* If restriction is in place, check the domid matches */
|
|
|
|
if (data->domid != DOMID_INVALID && data->domid != kdata.dom)
|
|
|
|
return -EPERM;
|
|
|
|
|
2017-02-14 01:03:23 +08:00
|
|
|
if (kdata.num == 0)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (kdata.num > privcmd_dm_op_max_num)
|
|
|
|
return -E2BIG;
|
|
|
|
|
|
|
|
kbufs = kcalloc(kdata.num, sizeof(*kbufs), GFP_KERNEL);
|
|
|
|
if (!kbufs)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
if (copy_from_user(kbufs, kdata.ubufs,
|
|
|
|
sizeof(*kbufs) * kdata.num)) {
|
|
|
|
rc = -EFAULT;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < kdata.num; i++) {
|
|
|
|
if (kbufs[i].size > privcmd_dm_op_buf_max_size) {
|
|
|
|
rc = -E2BIG;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!access_ok(VERIFY_WRITE, kbufs[i].uptr,
|
|
|
|
kbufs[i].size)) {
|
|
|
|
rc = -EFAULT;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
nr_pages += DIV_ROUND_UP(
|
|
|
|
offset_in_page(kbufs[i].uptr) + kbufs[i].size,
|
|
|
|
PAGE_SIZE);
|
|
|
|
}
|
|
|
|
|
|
|
|
pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL);
|
|
|
|
if (!pages) {
|
|
|
|
rc = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
xbufs = kcalloc(kdata.num, sizeof(*xbufs), GFP_KERNEL);
|
|
|
|
if (!xbufs) {
|
|
|
|
rc = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
rc = lock_pages(kbufs, kdata.num, pages, nr_pages);
|
|
|
|
if (rc)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
for (i = 0; i < kdata.num; i++) {
|
|
|
|
set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);
|
|
|
|
xbufs[i].size = kbufs[i].size;
|
|
|
|
}
|
|
|
|
|
|
|
|
xen_preemptible_hcall_begin();
|
|
|
|
rc = HYPERVISOR_dm_op(kdata.dom, kdata.num, xbufs);
|
|
|
|
xen_preemptible_hcall_end();
|
|
|
|
|
|
|
|
out:
|
|
|
|
unlock_pages(pages, nr_pages);
|
|
|
|
kfree(xbufs);
|
|
|
|
kfree(pages);
|
|
|
|
kfree(kbufs);
|
|
|
|
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
static long privcmd_ioctl_restrict(struct file *file, void __user *udata)
|
|
|
|
{
|
|
|
|
struct privcmd_data *data = file->private_data;
|
|
|
|
domid_t dom;
|
|
|
|
|
|
|
|
if (copy_from_user(&dom, udata, sizeof(dom)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
/* Set restriction to the specified domain, or check it matches */
|
|
|
|
if (data->domid == DOMID_INVALID)
|
|
|
|
data->domid = dom;
|
|
|
|
else if (data->domid != dom)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-02-10 04:05:49 +08:00
|
|
|
static long privcmd_ioctl(struct file *file,
|
|
|
|
unsigned int cmd, unsigned long data)
|
|
|
|
{
|
2017-02-14 01:03:22 +08:00
|
|
|
int ret = -ENOTTY;
|
2009-02-10 04:05:49 +08:00
|
|
|
void __user *udata = (void __user *) data;
|
|
|
|
|
|
|
|
switch (cmd) {
|
|
|
|
case IOCTL_PRIVCMD_HYPERCALL:
|
2017-02-14 01:03:24 +08:00
|
|
|
ret = privcmd_ioctl_hypercall(file, udata);
|
2009-02-10 04:05:49 +08:00
|
|
|
break;
|
|
|
|
|
|
|
|
case IOCTL_PRIVCMD_MMAP:
|
2017-02-14 01:03:24 +08:00
|
|
|
ret = privcmd_ioctl_mmap(file, udata);
|
2009-02-10 04:05:49 +08:00
|
|
|
break;
|
|
|
|
|
|
|
|
case IOCTL_PRIVCMD_MMAPBATCH:
|
2017-02-14 01:03:24 +08:00
|
|
|
ret = privcmd_ioctl_mmap_batch(file, udata, 1);
|
2012-08-31 21:59:30 +08:00
|
|
|
break;
|
|
|
|
|
|
|
|
case IOCTL_PRIVCMD_MMAPBATCH_V2:
|
2017-02-14 01:03:24 +08:00
|
|
|
ret = privcmd_ioctl_mmap_batch(file, udata, 2);
|
2009-02-10 04:05:49 +08:00
|
|
|
break;
|
|
|
|
|
2017-02-14 01:03:23 +08:00
|
|
|
case IOCTL_PRIVCMD_DM_OP:
|
2017-02-14 01:03:24 +08:00
|
|
|
ret = privcmd_ioctl_dm_op(file, udata);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case IOCTL_PRIVCMD_RESTRICT:
|
|
|
|
ret = privcmd_ioctl_restrict(file, udata);
|
2017-02-14 01:03:23 +08:00
|
|
|
break;
|
|
|
|
|
2009-02-10 04:05:49 +08:00
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2017-02-14 01:03:24 +08:00
|
|
|
static int privcmd_open(struct inode *ino, struct file *file)
|
|
|
|
{
|
|
|
|
struct privcmd_data *data = kzalloc(sizeof(*data), GFP_KERNEL);
|
|
|
|
|
|
|
|
if (!data)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
/* DOMID_INVALID implies no restriction */
|
|
|
|
data->domid = DOMID_INVALID;
|
|
|
|
|
|
|
|
file->private_data = data;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int privcmd_release(struct inode *ino, struct file *file)
|
|
|
|
{
|
|
|
|
struct privcmd_data *data = file->private_data;
|
|
|
|
|
|
|
|
kfree(data);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-10-18 08:11:21 +08:00
|
|
|
static void privcmd_close(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
struct page **pages = vma->vm_private_data;
|
2016-05-24 08:04:32 +08:00
|
|
|
int numpgs = vma_pages(vma);
|
2015-05-05 23:54:12 +08:00
|
|
|
int numgfns = (vma->vm_end - vma->vm_start) >> XEN_PAGE_SHIFT;
|
2013-12-07 01:55:56 +08:00
|
|
|
int rc;
|
2012-10-18 08:11:21 +08:00
|
|
|
|
2012-11-05 14:42:17 +08:00
|
|
|
if (!xen_feature(XENFEAT_auto_translated_physmap) || !numpgs || !pages)
|
2012-10-18 08:11:21 +08:00
|
|
|
return;
|
|
|
|
|
2015-05-05 23:54:12 +08:00
|
|
|
rc = xen_unmap_domain_gfn_range(vma, numgfns, pages);
|
2013-12-07 01:55:56 +08:00
|
|
|
if (rc == 0)
|
|
|
|
free_xenballooned_pages(numpgs, pages);
|
|
|
|
else
|
|
|
|
pr_crit("unable to unmap MFN range: leaking %d pages. rc=%d\n",
|
|
|
|
numpgs, rc);
|
2012-10-18 08:11:21 +08:00
|
|
|
kfree(pages);
|
|
|
|
}
|
|
|
|
|
2017-02-25 06:56:41 +08:00
|
|
|
static int privcmd_fault(struct vm_fault *vmf)
|
2009-02-10 04:05:49 +08:00
|
|
|
{
|
2009-03-07 01:56:59 +08:00
|
|
|
printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
|
2017-02-25 06:56:41 +08:00
|
|
|
vmf->vma, vmf->vma->vm_start, vmf->vma->vm_end,
|
2016-12-15 07:07:01 +08:00
|
|
|
vmf->pgoff, (void *)vmf->address);
|
2009-03-07 01:56:59 +08:00
|
|
|
|
2009-02-10 04:05:49 +08:00
|
|
|
return VM_FAULT_SIGBUS;
|
|
|
|
}
|
|
|
|
|
2015-09-10 06:39:26 +08:00
|
|
|
static const struct vm_operations_struct privcmd_vm_ops = {
|
2012-10-18 08:11:21 +08:00
|
|
|
.close = privcmd_close,
|
2009-02-10 04:05:49 +08:00
|
|
|
.fault = privcmd_fault
|
|
|
|
};
|
|
|
|
|
|
|
|
static int privcmd_mmap(struct file *file, struct vm_area_struct *vma)
|
|
|
|
{
|
2010-11-12 04:37:43 +08:00
|
|
|
/* DONTCOPY is essential for Xen because copy_page_range doesn't know
|
|
|
|
* how to recreate these mappings */
|
mm: kill vma flag VM_RESERVED and mm->reserved_vm counter
A long time ago, in v2.4, VM_RESERVED kept swapout process off VMA,
currently it lost original meaning but still has some effects:
| effect | alternative flags
-+------------------------+---------------------------------------------
1| account as reserved_vm | VM_IO
2| skip in core dump | VM_IO, VM_DONTDUMP
3| do not merge or expand | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP
4| do not mlock | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP
This patch removes reserved_vm counter from mm_struct. Seems like nobody
cares about it, it does not exported into userspace directly, it only
reduces total_vm showed in proc.
Thus VM_RESERVED can be replaced with VM_IO or pair VM_DONTEXPAND | VM_DONTDUMP.
remap_pfn_range() and io_remap_pfn_range() set VM_IO|VM_DONTEXPAND|VM_DONTDUMP.
remap_vmalloc_range() set VM_DONTEXPAND | VM_DONTDUMP.
[akpm@linux-foundation.org: drivers/vfio/pci/vfio_pci.c fixup]
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Carsten Otte <cotte@de.ibm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Eric Paris <eparis@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Morris <james.l.morris@oracle.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Kentaro Takeda <takedakn@nttdata.co.jp>
Cc: Matt Helsley <matthltc@us.ibm.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Venkatesh Pallipadi <venki@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:29:02 +08:00
|
|
|
vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTCOPY |
|
|
|
|
VM_DONTEXPAND | VM_DONTDUMP;
|
2009-02-10 04:05:49 +08:00
|
|
|
vma->vm_ops = &privcmd_vm_ops;
|
|
|
|
vma->vm_private_data = NULL;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-08-24 01:10:06 +08:00
|
|
|
/*
|
|
|
|
* For MMAPBATCH*. This allows asserting the singleshot mapping
|
|
|
|
* on a per pfn/pte basis. Mapping calls that fail with ENOENT
|
|
|
|
* can be then retried until success.
|
|
|
|
*/
|
|
|
|
static int is_mapped_fn(pte_t *pte, struct page *pmd_page,
|
|
|
|
unsigned long addr, void *data)
|
|
|
|
{
|
|
|
|
return pte_none(*pte) ? 0 : -EBUSY;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int privcmd_vma_range_is_mapped(
|
|
|
|
struct vm_area_struct *vma,
|
|
|
|
unsigned long addr,
|
|
|
|
unsigned long nr_pages)
|
2009-02-10 04:05:49 +08:00
|
|
|
{
|
2013-08-24 01:10:06 +08:00
|
|
|
return apply_to_page_range(vma->vm_mm, addr, nr_pages << PAGE_SHIFT,
|
|
|
|
is_mapped_fn, NULL) != 0;
|
2009-02-10 04:05:49 +08:00
|
|
|
}
|
|
|
|
|
2011-12-17 00:34:33 +08:00
|
|
|
const struct file_operations xen_privcmd_fops = {
|
|
|
|
.owner = THIS_MODULE,
|
2009-02-10 04:05:49 +08:00
|
|
|
.unlocked_ioctl = privcmd_ioctl,
|
2017-02-14 01:03:24 +08:00
|
|
|
.open = privcmd_open,
|
|
|
|
.release = privcmd_release,
|
2009-02-10 04:05:49 +08:00
|
|
|
.mmap = privcmd_mmap,
|
|
|
|
};
|
2011-12-17 00:34:33 +08:00
|
|
|
EXPORT_SYMBOL_GPL(xen_privcmd_fops);
|
|
|
|
|
|
|
|
static struct miscdevice privcmd_dev = {
|
|
|
|
.minor = MISC_DYNAMIC_MINOR,
|
|
|
|
.name = "xen/privcmd",
|
|
|
|
.fops = &xen_privcmd_fops,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init privcmd_init(void)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
|
|
|
|
if (!xen_domain())
|
|
|
|
return -ENODEV;
|
|
|
|
|
|
|
|
err = misc_register(&privcmd_dev);
|
|
|
|
if (err != 0) {
|
2013-06-28 18:21:41 +08:00
|
|
|
pr_err("Could not register Xen privcmd device\n");
|
2011-12-17 00:34:33 +08:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit privcmd_exit(void)
|
|
|
|
{
|
|
|
|
misc_deregister(&privcmd_dev);
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(privcmd_init);
|
|
|
|
module_exit(privcmd_exit);
|