linux/drivers/xen/gntdev.c

868 lines
21 KiB
C
Raw Normal View History

/******************************************************************************
* gntdev.c
*
* Device for accessing (in user-space) pages that have been granted by other
* domains.
*
* Copyright (c) 2006-2007, D G Murray.
* (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#undef DEBUG
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/miscdevice.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <xen/xen.h>
#include <xen/grant_table.h>
#include <xen/balloon.h>
#include <xen/gntdev.h>
#include <xen/events.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
"Gerd Hoffmann <kraxel@redhat.com>");
MODULE_DESCRIPTION("User-space granted page access driver");
static int limit = 1024*1024;
module_param(limit, int, 0644);
MODULE_PARM_DESC(limit, "Maximum number of grants that may be mapped by "
"the gntdev device");
static atomic_t pages_mapped = ATOMIC_INIT(0);
static int use_ptemod;
#define populate_freeable_maps use_ptemod
struct gntdev_priv {
/* maps with visible offsets in the file descriptor */
struct list_head maps;
/* maps that are not visible; will be freed on munmap.
* Only populated if populate_freeable_maps == 1 */
struct list_head freeable_maps;
/* lock protects maps and freeable_maps */
spinlock_t lock;
struct mm_struct *mm;
struct mmu_notifier mn;
};
struct unmap_notify {
int flags;
/* Address relative to the start of the grant_map */
int addr;
int event;
};
struct grant_map {
struct list_head next;
struct vm_area_struct *vma;
int index;
int count;
int flags;
atomic_t users;
struct unmap_notify notify;
struct ioctl_gntdev_grant_ref *grants;
struct gnttab_map_grant_ref *map_ops;
struct gnttab_unmap_grant_ref *unmap_ops;
struct gnttab_map_grant_ref *kmap_ops;
struct page **pages;
};
static int unmap_grant_pages(struct grant_map *map, int offset, int pages);
/* ------------------------------------------------------------------ */
static void gntdev_print_maps(struct gntdev_priv *priv,
char *text, int text_index)
{
#ifdef DEBUG
struct grant_map *map;
pr_debug("%s: maps list (priv %p)\n", __func__, priv);
list_for_each_entry(map, &priv->maps, next)
pr_debug(" index %2d, count %2d %s\n",
map->index, map->count,
map->index == text_index && text ? text : "");
#endif
}
static void gntdev_free_map(struct grant_map *map)
{
if (map == NULL)
return;
if (map->pages)
free_xenballooned_pages(map->count, map->pages);
kfree(map->pages);
kfree(map->grants);
kfree(map->map_ops);
kfree(map->unmap_ops);
kfree(map->kmap_ops);
kfree(map);
}
static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
{
struct grant_map *add;
int i;
add = kzalloc(sizeof(struct grant_map), GFP_KERNEL);
if (NULL == add)
return NULL;
add->grants = kcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
add->map_ops = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
add->kmap_ops = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
add->pages = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
if (NULL == add->grants ||
NULL == add->map_ops ||
NULL == add->unmap_ops ||
NULL == add->kmap_ops ||
NULL == add->pages)
goto err;
if (alloc_xenballooned_pages(count, add->pages, false /* lowmem */))
goto err;
for (i = 0; i < count; i++) {
add->map_ops[i].handle = -1;
add->unmap_ops[i].handle = -1;
add->kmap_ops[i].handle = -1;
}
add->index = 0;
add->count = count;
atomic_set(&add->users, 1);
return add;
err:
gntdev_free_map(add);
return NULL;
}
static void gntdev_add_map(struct gntdev_priv *priv, struct grant_map *add)
{
struct grant_map *map;
list_for_each_entry(map, &priv->maps, next) {
if (add->index + add->count < map->index) {
list_add_tail(&add->next, &map->next);
goto done;
}
add->index = map->index + map->count;
}
list_add_tail(&add->next, &priv->maps);
done:
gntdev_print_maps(priv, "[new]", add->index);
}
static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
int index, int count)
{
struct grant_map *map;
list_for_each_entry(map, &priv->maps, next) {
if (map->index != index)
continue;
if (count && map->count != count)
continue;
return map;
}
return NULL;
}
static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
{
if (!map)
return;
if (!atomic_dec_and_test(&map->users))
return;
atomic_sub(map->count, &pages_mapped);
if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
notify_remote_via_evtchn(map->notify.event);
evtchn_put(map->notify.event);
}
if (populate_freeable_maps && priv) {
spin_lock(&priv->lock);
list_del(&map->next);
spin_unlock(&priv->lock);
}
if (map->pages && !use_ptemod)
unmap_grant_pages(map, 0, map->count);
gntdev_free_map(map);
}
/* ------------------------------------------------------------------ */
static int find_grant_ptes(pte_t *pte, pgtable_t token,
unsigned long addr, void *data)
{
struct grant_map *map = data;
unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT;
int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte;
u64 pte_maddr;
BUG_ON(pgnr >= map->count);
pte_maddr = arbitrary_virt_to_machine(pte).maddr;
gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags,
map->grants[pgnr].ref,
map->grants[pgnr].domid);
gnttab_set_unmap_op(&map->unmap_ops[pgnr], pte_maddr, flags,
-1 /* handle */);
return 0;
}
static int map_grant_pages(struct grant_map *map)
{
int i, err = 0;
if (!use_ptemod) {
/* Note: it could already be mapped */
if (map->map_ops[0].handle != -1)
return 0;
for (i = 0; i < map->count; i++) {
unsigned long addr = (unsigned long)
pfn_to_kaddr(page_to_pfn(map->pages[i]));
gnttab_set_map_op(&map->map_ops[i], addr, map->flags,
map->grants[i].ref,
map->grants[i].domid);
gnttab_set_unmap_op(&map->unmap_ops[i], addr,
map->flags, -1 /* handle */);
}
} else {
/*
* Setup the map_ops corresponding to the pte entries pointing
* to the kernel linear addresses of the struct pages.
* These ptes are completely different from the user ptes dealt
* with find_grant_ptes.
*/
for (i = 0; i < map->count; i++) {
unsigned long address = (unsigned long)
pfn_to_kaddr(page_to_pfn(map->pages[i]));
BUG_ON(PageHighMem(map->pages[i]));
gnttab_set_map_op(&map->kmap_ops[i], address,
map->flags | GNTMAP_host_map,
map->grants[i].ref,
map->grants[i].domid);
}
}
pr_debug("map %d+%d\n", map->index, map->count);
err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL,
map->pages, map->count);
if (err)
return err;
for (i = 0; i < map->count; i++) {
if (map->map_ops[i].status)
err = -EINVAL;
else {
BUG_ON(map->map_ops[i].handle == -1);
map->unmap_ops[i].handle = map->map_ops[i].handle;
pr_debug("map handle=%d\n", map->map_ops[i].handle);
}
}
return err;
}
static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
{
int i, err = 0;
if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) {
int pgno = (map->notify.addr >> PAGE_SHIFT);
if (pgno >= offset && pgno < offset + pages) {
/* No need for kmap, pages are in lowmem */
uint8_t *tmp = pfn_to_kaddr(page_to_pfn(map->pages[pgno]));
tmp[map->notify.addr & (PAGE_SIZE-1)] = 0;
map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE;
}
}
err = gnttab_unmap_refs(map->unmap_ops + offset,
use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset,
pages);
if (err)
return err;
for (i = 0; i < pages; i++) {
if (map->unmap_ops[offset+i].status)
err = -EINVAL;
pr_debug("unmap handle=%d st=%d\n",
map->unmap_ops[offset+i].handle,
map->unmap_ops[offset+i].status);
map->unmap_ops[offset+i].handle = -1;
}
return err;
}
static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
{
int range, err = 0;
pr_debug("unmap %d+%d [%d+%d]\n", map->index, map->count, offset, pages);
/* It is possible the requested range will have a "hole" where we
* already unmapped some of the grants. Only unmap valid ranges.
*/
while (pages && !err) {
while (pages && map->unmap_ops[offset].handle == -1) {
offset++;
pages--;
}
range = 0;
while (range < pages) {
if (map->unmap_ops[offset+range].handle == -1) {
range--;
break;
}
range++;
}
err = __unmap_grant_pages(map, offset, range);
offset += range;
pages -= range;
}
return err;
}
/* ------------------------------------------------------------------ */
static void gntdev_vma_open(struct vm_area_struct *vma)
{
struct grant_map *map = vma->vm_private_data;
pr_debug("gntdev_vma_open %p\n", vma);
atomic_inc(&map->users);
}
static void gntdev_vma_close(struct vm_area_struct *vma)
{
struct grant_map *map = vma->vm_private_data;
struct file *file = vma->vm_file;
struct gntdev_priv *priv = file->private_data;
pr_debug("gntdev_vma_close %p\n", vma);
if (use_ptemod) {
/* It is possible that an mmu notifier could be running
* concurrently, so take priv->lock to ensure that the vma won't
* vanishing during the unmap_grant_pages call, since we will
* spin here until that completes. Such a concurrent call will
* not do any unmapping, since that has been done prior to
* closing the vma, but it may still iterate the unmap_ops list.
*/
spin_lock(&priv->lock);
map->vma = NULL;
spin_unlock(&priv->lock);
}
vma->vm_private_data = NULL;
gntdev_put_map(priv, map);
}
static struct vm_operations_struct gntdev_vmops = {
.open = gntdev_vma_open,
.close = gntdev_vma_close,
};
/* ------------------------------------------------------------------ */
static void unmap_if_in_range(struct grant_map *map,
unsigned long start, unsigned long end)
{
unsigned long mstart, mend;
int err;
if (!map->vma)
return;
if (map->vma->vm_start >= end)
return;
if (map->vma->vm_end <= start)
return;
mstart = max(start, map->vma->vm_start);
mend = min(end, map->vma->vm_end);
pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n",
map->index, map->count,
map->vma->vm_start, map->vma->vm_end,
start, end, mstart, mend);
err = unmap_grant_pages(map,
(mstart - map->vma->vm_start) >> PAGE_SHIFT,
(mend - mstart) >> PAGE_SHIFT);
WARN_ON(err);
}
static void mn_invl_range_start(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start, unsigned long end)
{
struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
struct grant_map *map;
spin_lock(&priv->lock);
list_for_each_entry(map, &priv->maps, next) {
unmap_if_in_range(map, start, end);
}
list_for_each_entry(map, &priv->freeable_maps, next) {
unmap_if_in_range(map, start, end);
}
spin_unlock(&priv->lock);
}
static void mn_invl_page(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long address)
{
mn_invl_range_start(mn, mm, address, address + PAGE_SIZE);
}
static void mn_release(struct mmu_notifier *mn,
struct mm_struct *mm)
{
struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
struct grant_map *map;
int err;
spin_lock(&priv->lock);
list_for_each_entry(map, &priv->maps, next) {
if (!map->vma)
continue;
pr_debug("map %d+%d (%lx %lx)\n",
map->index, map->count,
map->vma->vm_start, map->vma->vm_end);
err = unmap_grant_pages(map, /* offset */ 0, map->count);
WARN_ON(err);
}
list_for_each_entry(map, &priv->freeable_maps, next) {
if (!map->vma)
continue;
pr_debug("map %d+%d (%lx %lx)\n",
map->index, map->count,
map->vma->vm_start, map->vma->vm_end);
err = unmap_grant_pages(map, /* offset */ 0, map->count);
WARN_ON(err);
}
spin_unlock(&priv->lock);
}
static struct mmu_notifier_ops gntdev_mmu_ops = {
.release = mn_release,
.invalidate_page = mn_invl_page,
.invalidate_range_start = mn_invl_range_start,
};
/* ------------------------------------------------------------------ */
static int gntdev_open(struct inode *inode, struct file *flip)
{
struct gntdev_priv *priv;
int ret = 0;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
INIT_LIST_HEAD(&priv->maps);
INIT_LIST_HEAD(&priv->freeable_maps);
spin_lock_init(&priv->lock);
if (use_ptemod) {
priv->mm = get_task_mm(current);
if (!priv->mm) {
kfree(priv);
return -ENOMEM;
}
priv->mn.ops = &gntdev_mmu_ops;
ret = mmu_notifier_register(&priv->mn, priv->mm);
mmput(priv->mm);
}
if (ret) {
kfree(priv);
return ret;
}
flip->private_data = priv;
pr_debug("priv %p\n", priv);
return 0;
}
static int gntdev_release(struct inode *inode, struct file *flip)
{
struct gntdev_priv *priv = flip->private_data;
struct grant_map *map;
pr_debug("priv %p\n", priv);
while (!list_empty(&priv->maps)) {
map = list_entry(priv->maps.next, struct grant_map, next);
list_del(&map->next);
gntdev_put_map(NULL /* already removed */, map);
}
WARN_ON(!list_empty(&priv->freeable_maps));
if (use_ptemod)
mmu_notifier_unregister(&priv->mn, priv->mm);
kfree(priv);
return 0;
}
static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
struct ioctl_gntdev_map_grant_ref __user *u)
{
struct ioctl_gntdev_map_grant_ref op;
struct grant_map *map;
int err;
if (copy_from_user(&op, u, sizeof(op)) != 0)
return -EFAULT;
pr_debug("priv %p, add %d\n", priv, op.count);
if (unlikely(op.count <= 0))
return -EINVAL;
err = -ENOMEM;
map = gntdev_alloc_map(priv, op.count);
if (!map)
return err;
if (unlikely(atomic_add_return(op.count, &pages_mapped) > limit)) {
pr_debug("can't map: over limit\n");
gntdev_put_map(NULL, map);
return err;
}
if (copy_from_user(map->grants, &u->refs,
sizeof(map->grants[0]) * op.count) != 0) {
gntdev_put_map(NULL, map);
return -EFAULT;
}
spin_lock(&priv->lock);
gntdev_add_map(priv, map);
op.index = map->index << PAGE_SHIFT;
spin_unlock(&priv->lock);
if (copy_to_user(u, &op, sizeof(op)) != 0)
return -EFAULT;
return 0;
}
static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
struct ioctl_gntdev_unmap_grant_ref __user *u)
{
struct ioctl_gntdev_unmap_grant_ref op;
struct grant_map *map;
int err = -ENOENT;
if (copy_from_user(&op, u, sizeof(op)) != 0)
return -EFAULT;
pr_debug("priv %p, del %d+%d\n", priv, (int)op.index, (int)op.count);
spin_lock(&priv->lock);
map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
if (map) {
list_del(&map->next);
if (populate_freeable_maps)
list_add_tail(&map->next, &priv->freeable_maps);
err = 0;
}
spin_unlock(&priv->lock);
xen/gntdev: Fix sleep-inside-spinlock BUG: sleeping function called from invalid context at /local/scratch/dariof/linux/kernel/mutex.c:271 in_atomic(): 1, irqs_disabled(): 0, pid: 3256, name: qemu-dm 1 lock held by qemu-dm/3256: #0: (&(&priv->lock)->rlock){......}, at: [<ffffffff813223da>] gntdev_ioctl+0x2bd/0x4d5 Pid: 3256, comm: qemu-dm Tainted: G W 3.1.0-rc8+ #5 Call Trace: [<ffffffff81054594>] __might_sleep+0x131/0x135 [<ffffffff816bd64f>] mutex_lock_nested+0x25/0x45 [<ffffffff8131c7c8>] free_xenballooned_pages+0x20/0xb1 [<ffffffff8132194d>] gntdev_put_map+0xa8/0xdb [<ffffffff816be546>] ? _raw_spin_lock+0x71/0x7a [<ffffffff813223da>] ? gntdev_ioctl+0x2bd/0x4d5 [<ffffffff8132243c>] gntdev_ioctl+0x31f/0x4d5 [<ffffffff81007d62>] ? check_events+0x12/0x20 [<ffffffff811433bc>] do_vfs_ioctl+0x488/0x4d7 [<ffffffff81007d4f>] ? xen_restore_fl_direct_reloc+0x4/0x4 [<ffffffff8109168b>] ? lock_release+0x21c/0x229 [<ffffffff81135cdd>] ? rcu_read_unlock+0x21/0x32 [<ffffffff81143452>] sys_ioctl+0x47/0x6a [<ffffffff816bfd82>] system_call_fastpath+0x16/0x1b gntdev_put_map tries to acquire a mutex when freeing pages back to the xenballoon pool, so it cannot be called with a spinlock held. In gntdev_release, the spinlock is not needed as we are freeing the structure later; in the ioctl, only the list manipulation needs to be under the lock. Reported-and-Tested-By: Dario Faggioli <dario.faggioli@citrix.com> Signed-off-by: Daniel De Graaf <dgdegra@tycho.nsa.gov> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2011-10-12 03:16:06 +08:00
if (map)
gntdev_put_map(priv, map);
return err;
}
static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
struct ioctl_gntdev_get_offset_for_vaddr __user *u)
{
struct ioctl_gntdev_get_offset_for_vaddr op;
struct vm_area_struct *vma;
struct grant_map *map;
int rv = -EINVAL;
if (copy_from_user(&op, u, sizeof(op)) != 0)
return -EFAULT;
pr_debug("priv %p, offset for vaddr %lx\n", priv, (unsigned long)op.vaddr);
down_read(&current->mm->mmap_sem);
vma = find_vma(current->mm, op.vaddr);
if (!vma || vma->vm_ops != &gntdev_vmops)
goto out_unlock;
map = vma->vm_private_data;
if (!map)
goto out_unlock;
op.offset = map->index << PAGE_SHIFT;
op.count = map->count;
rv = 0;
out_unlock:
up_read(&current->mm->mmap_sem);
if (rv == 0 && copy_to_user(u, &op, sizeof(op)) != 0)
return -EFAULT;
return rv;
}
static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
{
struct ioctl_gntdev_unmap_notify op;
struct grant_map *map;
int rc;
int out_flags;
unsigned int out_event;
if (copy_from_user(&op, u, sizeof(op)))
return -EFAULT;
if (op.action & ~(UNMAP_NOTIFY_CLEAR_BYTE|UNMAP_NOTIFY_SEND_EVENT))
return -EINVAL;
/* We need to grab a reference to the event channel we are going to use
* to send the notify before releasing the reference we may already have
* (if someone has called this ioctl twice). This is required so that
* it is possible to change the clear_byte part of the notification
* without disturbing the event channel part, which may now be the last
* reference to that event channel.
*/
if (op.action & UNMAP_NOTIFY_SEND_EVENT) {
if (evtchn_get(op.event_channel_port))
return -EINVAL;
}
out_flags = op.action;
out_event = op.event_channel_port;
spin_lock(&priv->lock);
list_for_each_entry(map, &priv->maps, next) {
uint64_t begin = map->index << PAGE_SHIFT;
uint64_t end = (map->index + map->count) << PAGE_SHIFT;
if (op.index >= begin && op.index < end)
goto found;
}
rc = -ENOENT;
goto unlock_out;
found:
if ((op.action & UNMAP_NOTIFY_CLEAR_BYTE) &&
(map->flags & GNTMAP_readonly)) {
rc = -EINVAL;
goto unlock_out;
}
out_flags = map->notify.flags;
out_event = map->notify.event;
map->notify.flags = op.action;
map->notify.addr = op.index - (map->index << PAGE_SHIFT);
map->notify.event = op.event_channel_port;
rc = 0;
unlock_out:
spin_unlock(&priv->lock);
/* Drop the reference to the event channel we did not save in the map */
if (out_flags & UNMAP_NOTIFY_SEND_EVENT)
evtchn_put(out_event);
return rc;
}
static long gntdev_ioctl(struct file *flip,
unsigned int cmd, unsigned long arg)
{
struct gntdev_priv *priv = flip->private_data;
void __user *ptr = (void __user *)arg;
switch (cmd) {
case IOCTL_GNTDEV_MAP_GRANT_REF:
return gntdev_ioctl_map_grant_ref(priv, ptr);
case IOCTL_GNTDEV_UNMAP_GRANT_REF:
return gntdev_ioctl_unmap_grant_ref(priv, ptr);
case IOCTL_GNTDEV_GET_OFFSET_FOR_VADDR:
return gntdev_ioctl_get_offset_for_vaddr(priv, ptr);
case IOCTL_GNTDEV_SET_UNMAP_NOTIFY:
return gntdev_ioctl_notify(priv, ptr);
default:
pr_debug("priv %p, unknown cmd %x\n", priv, cmd);
return -ENOIOCTLCMD;
}
return 0;
}
static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
{
struct gntdev_priv *priv = flip->private_data;
int index = vma->vm_pgoff;
int count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
struct grant_map *map;
int i, err = -EINVAL;
if ((vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_SHARED))
return -EINVAL;
pr_debug("map %d+%d at %lx (pgoff %lx)\n",
index, count, vma->vm_start, vma->vm_pgoff);
spin_lock(&priv->lock);
map = gntdev_find_map_index(priv, index, count);
if (!map)
goto unlock_out;
if (use_ptemod && map->vma)
goto unlock_out;
if (use_ptemod && priv->mm != vma->vm_mm) {
pr_warn("Huh? Other mm?\n");
goto unlock_out;
}
atomic_inc(&map->users);
vma->vm_ops = &gntdev_vmops;
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_DONTEXPAND | VM_DONTDUMP;
if (use_ptemod)
vma->vm_flags |= VM_DONTCOPY;
vma->vm_private_data = map;
if (use_ptemod)
map->vma = vma;
if (map->flags) {
if ((vma->vm_flags & VM_WRITE) &&
(map->flags & GNTMAP_readonly))
goto out_unlock_put;
} else {
map->flags = GNTMAP_host_map;
if (!(vma->vm_flags & VM_WRITE))
map->flags |= GNTMAP_readonly;
}
spin_unlock(&priv->lock);
if (use_ptemod) {
err = apply_to_page_range(vma->vm_mm, vma->vm_start,
vma->vm_end - vma->vm_start,
find_grant_ptes, map);
if (err) {
pr_warn("find_grant_ptes() failure.\n");
goto out_put_map;
}
}
err = map_grant_pages(map);
if (err)
goto out_put_map;
if (!use_ptemod) {
for (i = 0; i < count; i++) {
err = vm_insert_page(vma, vma->vm_start + i*PAGE_SIZE,
map->pages[i]);
if (err)
goto out_put_map;
}
}
return 0;
unlock_out:
spin_unlock(&priv->lock);
return err;
out_unlock_put:
spin_unlock(&priv->lock);
out_put_map:
if (use_ptemod)
map->vma = NULL;
gntdev_put_map(priv, map);
return err;
}
static const struct file_operations gntdev_fops = {
.owner = THIS_MODULE,
.open = gntdev_open,
.release = gntdev_release,
.mmap = gntdev_mmap,
.unlocked_ioctl = gntdev_ioctl
};
static struct miscdevice gntdev_miscdev = {
.minor = MISC_DYNAMIC_MINOR,
.name = "xen/gntdev",
.fops = &gntdev_fops,
};
/* ------------------------------------------------------------------ */
static int __init gntdev_init(void)
{
int err;
if (!xen_domain())
return -ENODEV;
use_ptemod = !xen_feature(XENFEAT_auto_translated_physmap);
err = misc_register(&gntdev_miscdev);
if (err != 0) {
pr_err("Could not register gntdev device\n");
return err;
}
return 0;
}
static void __exit gntdev_exit(void)
{
misc_deregister(&gntdev_miscdev);
}
module_init(gntdev_init);
module_exit(gntdev_exit);
/* ------------------------------------------------------------------ */