WSL2-Linux-Kernel/drivers/xen/gntdev.c

1115 строки
28 KiB
C
Исходник Обычный вид История

/******************************************************************************
* 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>
* (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
*
* 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/dma-mapping.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/miscdevice.h>
#include <linux/fs.h>
#include <linux/uaccess.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/refcount.h>
#include <xen/xen.h>
#include <xen/grant_table.h>
#include <xen/balloon.h>
#include <xen/gntdev.h>
#include <xen/events.h>
#include <xen/page.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include "gntdev-common.h"
#ifdef CONFIG_XEN_GNTDEV_DMABUF
#include "gntdev-dmabuf.h"
#endif
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");
2019-11-07 14:15:45 +03:00
static unsigned int limit = 64*1024;
module_param(limit, uint, 0644);
MODULE_PARM_DESC(limit,
"Maximum number of grants that may be mapped by one mapping request");
static int use_ptemod;
static int unmap_grant_pages(struct gntdev_grant_map *map,
int offset, int pages);
static struct miscdevice gntdev_miscdev;
/* ------------------------------------------------------------------ */
2019-11-07 14:15:45 +03:00
bool gntdev_test_page_count(unsigned int count)
{
2019-11-07 14:15:45 +03:00
return !count || count > limit;
}
static void gntdev_print_maps(struct gntdev_priv *priv,
char *text, int text_index)
{
#ifdef DEBUG
struct gntdev_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 gntdev_grant_map *map)
{
if (map == NULL)
return;
#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
if (map->dma_vaddr) {
struct gnttab_dma_alloc_args args;
args.dev = map->dma_dev;
args.coherent = !!(map->dma_flags & GNTDEV_DMA_FLAG_COHERENT);
args.nr_pages = map->count;
args.pages = map->pages;
args.frames = map->frames;
args.vaddr = map->dma_vaddr;
args.dev_bus_addr = map->dma_bus_addr;
gnttab_dma_free_pages(&args);
} else
#endif
if (map->pages)
gnttab_free_pages(map->count, map->pages);
#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
kvfree(map->frames);
#endif
kvfree(map->pages);
kvfree(map->grants);
kvfree(map->map_ops);
kvfree(map->unmap_ops);
kvfree(map->kmap_ops);
kvfree(map->kunmap_ops);
kfree(map);
}
struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
int dma_flags)
{
struct gntdev_grant_map *add;
int i;
add = kzalloc(sizeof(*add), GFP_KERNEL);
if (NULL == add)
return NULL;
add->grants = kvmalloc_array(count, sizeof(add->grants[0]),
GFP_KERNEL);
add->map_ops = kvmalloc_array(count, sizeof(add->map_ops[0]),
GFP_KERNEL);
add->unmap_ops = kvmalloc_array(count, sizeof(add->unmap_ops[0]),
GFP_KERNEL);
add->pages = kvcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
if (NULL == add->grants ||
NULL == add->map_ops ||
NULL == add->unmap_ops ||
NULL == add->pages)
goto err;
if (use_ptemod) {
add->kmap_ops = kvmalloc_array(count, sizeof(add->kmap_ops[0]),
GFP_KERNEL);
add->kunmap_ops = kvmalloc_array(count, sizeof(add->kunmap_ops[0]),
GFP_KERNEL);
if (NULL == add->kmap_ops || NULL == add->kunmap_ops)
goto err;
}
#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
add->dma_flags = dma_flags;
/*
* Check if this mapping is requested to be backed
* by a DMA buffer.
*/
if (dma_flags & (GNTDEV_DMA_FLAG_WC | GNTDEV_DMA_FLAG_COHERENT)) {
struct gnttab_dma_alloc_args args;
add->frames = kvcalloc(count, sizeof(add->frames[0]),
GFP_KERNEL);
if (!add->frames)
goto err;
/* Remember the device, so we can free DMA memory. */
add->dma_dev = priv->dma_dev;
args.dev = priv->dma_dev;
args.coherent = !!(dma_flags & GNTDEV_DMA_FLAG_COHERENT);
args.nr_pages = count;
args.pages = add->pages;
args.frames = add->frames;
if (gnttab_dma_alloc_pages(&args))
goto err;
add->dma_vaddr = args.vaddr;
add->dma_bus_addr = args.dev_bus_addr;
} else
#endif
if (gnttab_alloc_pages(count, add->pages))
goto err;
for (i = 0; i < count; i++) {
add->grants[i].domid = DOMID_INVALID;
add->grants[i].ref = INVALID_GRANT_REF;
add->map_ops[i].handle = INVALID_GRANT_HANDLE;
add->unmap_ops[i].handle = INVALID_GRANT_HANDLE;
if (use_ptemod) {
add->kmap_ops[i].handle = INVALID_GRANT_HANDLE;
add->kunmap_ops[i].handle = INVALID_GRANT_HANDLE;
}
}
add->index = 0;
add->count = count;
refcount_set(&add->users, 1);
return add;
err:
gntdev_free_map(add);
return NULL;
}
void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add)
{
struct gntdev_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 gntdev_grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
int index, int count)
{
struct gntdev_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;
}
void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
{
if (!map)
return;
if (!refcount_dec_and_test(&map->users))
return;
xen/gntdev: fix unmap notification order commit ce2f46f3531a03781181b7f4bd1ff9f8c5086e7e upstream. While working with Xen's libxenvchan library I have faced an issue with unmap notifications sent in wrong order if both UNMAP_NOTIFY_SEND_EVENT and UNMAP_NOTIFY_CLEAR_BYTE were requested: first we send an event channel notification and then clear the notification byte which renders in the below inconsistency (cli_live is the byte which was requested to be cleared on unmap): [ 444.514243] gntdev_put_map UNMAP_NOTIFY_SEND_EVENT map->notify.event 6 libxenvchan_is_open cli_live 1 [ 444.515239] __unmap_grant_pages UNMAP_NOTIFY_CLEAR_BYTE at 14 Thus it is not possible to reliably implement the checks like - wait for the notification (UNMAP_NOTIFY_SEND_EVENT) - check the variable (UNMAP_NOTIFY_CLEAR_BYTE) because it is possible that the variable gets checked before it is cleared by the kernel. To fix that we need to re-order the notifications, so the variable is first gets cleared and then the event channel notification is sent. With this fix I can see the correct order of execution: [ 54.522611] __unmap_grant_pages UNMAP_NOTIFY_CLEAR_BYTE at 14 [ 54.537966] gntdev_put_map UNMAP_NOTIFY_SEND_EVENT map->notify.event 6 libxenvchan_is_open cli_live 0 Cc: stable@vger.kernel.org Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Link: https://lore.kernel.org/r/20211210092817.580718-1-andr2000@gmail.com Signed-off-by: Juergen Gross <jgross@suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-12-10 12:28:17 +03:00
if (map->pages && !use_ptemod)
unmap_grant_pages(map, 0, map->count);
if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
notify_remote_via_evtchn(map->notify.event);
evtchn_put(map->notify.event);
}
gntdev_free_map(map);
}
/* ------------------------------------------------------------------ */
static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data)
{
struct gntdev_grant_map *map = data;
unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT;
int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte |
(1 << _GNTMAP_guest_avail0);
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,
INVALID_GRANT_HANDLE);
return 0;
}
int gntdev_map_grant_pages(struct gntdev_grant_map *map)
{
int i, err = 0;
if (!use_ptemod) {
/* Note: it could already be mapped */
if (map->map_ops[0].handle != INVALID_GRANT_HANDLE)
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, INVALID_GRANT_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.
* Note that GNTMAP_device_map isn't needed here: The
* dev_bus_addr output field gets consumed only from ->map_ops,
* and by not requesting it when mapping we also avoid needing
* to mirror dev_bus_addr into ->unmap_ops (and holding an extra
* reference to the page in the hypervisor).
*/
unsigned int flags = (map->flags & ~GNTMAP_device_map) |
GNTMAP_host_map;
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, flags,
map->grants[i].ref,
map->grants[i].domid);
gnttab_set_unmap_op(&map->kunmap_ops[i], address,
flags, INVALID_GRANT_HANDLE);
}
}
pr_debug("map %d+%d\n", map->index, map->count);
err = gnttab_map_refs(map->map_ops, map->kmap_ops, map->pages,
map->count);
for (i = 0; i < map->count; i++) {
if (map->map_ops[i].status == GNTST_okay)
map->unmap_ops[i].handle = map->map_ops[i].handle;
else if (!err)
err = -EINVAL;
if (map->flags & GNTMAP_device_map)
map->unmap_ops[i].dev_bus_addr = map->map_ops[i].dev_bus_addr;
if (use_ptemod) {
if (map->kmap_ops[i].status == GNTST_okay)
map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
else if (!err)
err = -EINVAL;
}
}
return err;
}
static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
int pages)
{
int i, err = 0;
struct gntab_unmap_queue_data unmap_data;
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;
}
}
unmap_data.unmap_ops = map->unmap_ops + offset;
unmap_data.kunmap_ops = use_ptemod ? map->kunmap_ops + offset : NULL;
unmap_data.pages = map->pages + offset;
unmap_data.count = pages;
err = gnttab_unmap_refs_sync(&unmap_data);
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 = INVALID_GRANT_HANDLE;
if (use_ptemod) {
if (map->kunmap_ops[offset+i].status)
err = -EINVAL;
pr_debug("kunmap handle=%u st=%d\n",
map->kunmap_ops[offset+i].handle,
map->kunmap_ops[offset+i].status);
map->kunmap_ops[offset+i].handle = INVALID_GRANT_HANDLE;
}
}
return err;
}
static int unmap_grant_pages(struct gntdev_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 == INVALID_GRANT_HANDLE) {
offset++;
pages--;
}
range = 0;
while (range < pages) {
if (map->unmap_ops[offset + range].handle ==
INVALID_GRANT_HANDLE)
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 gntdev_grant_map *map = vma->vm_private_data;
pr_debug("gntdev_vma_open %p\n", vma);
refcount_inc(&map->users);
}
static void gntdev_vma_close(struct vm_area_struct *vma)
{
struct gntdev_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) {
WARN_ON(map->vma != vma);
mmu_interval_notifier_remove(&map->notifier);
map->vma = NULL;
}
vma->vm_private_data = NULL;
gntdev_put_map(priv, map);
}
static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma,
unsigned long addr)
{
struct gntdev_grant_map *map = vma->vm_private_data;
return map->pages[(addr - map->pages_vm_start) >> PAGE_SHIFT];
}
static const struct vm_operations_struct gntdev_vmops = {
.open = gntdev_vma_open,
.close = gntdev_vma_close,
.find_special_page = gntdev_vma_find_special_page,
};
/* ------------------------------------------------------------------ */
static bool gntdev_invalidate(struct mmu_interval_notifier *mn,
const struct mmu_notifier_range *range,
unsigned long cur_seq)
{
struct gntdev_grant_map *map =
container_of(mn, struct gntdev_grant_map, notifier);
unsigned long mstart, mend;
int err;
if (!mmu_notifier_range_blockable(range))
return false;
xen/gntdev: fix up blockable calls to mn_invl_range_start Patch series "mmu_notifiers follow ups". Tetsuo has noticed some fallouts from 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers"). One of them has been fixed and picked up by AMD/DRM maintainer [1]. XEN issue is fixed by patch 1. I have also clarified expectations about blockable semantic of invalidate_range_end. Finally the last patch removes MMU_INVALIDATE_DOES_NOT_BLOCK which is no longer used nor needed. [1] http://lkml.kernel.org/r/20180824135257.GU29735@dhcp22.suse.cz This patch (of 3): 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers") has introduced blockable parameter to all mmu_notifiers and the notifier has to back off when called in !blockable case and it could block down the road. The above commit implemented that for mn_invl_range_start but both in_range checks are done unconditionally regardless of the blockable mode and as such they would fail all the time for regular calls. Fix this by checking blockable parameter as well. Once we are there we can remove the stale TODO. The lock has to be sleepable because we wait for completion down in gnttab_unmap_refs_sync. Link: http://lkml.kernel.org/r/20180827112623.8992-2-mhocko@kernel.org Fixes: 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers") Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: David Rientjes <rientjes@google.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Reviewed-by: Juergen Gross <jgross@suse.com> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
2018-09-05 02:21:39 +03:00
/*
* If the VMA is split or otherwise changed the notifier is not
* updated, but we don't want to process VA's outside the modified
* VMA. FIXME: It would be much more understandable to just prevent
* modifying the VMA in the first place.
*/
if (map->vma->vm_start >= range->end ||
map->vma->vm_end <= range->start)
return true;
xen/gntdev: fix up blockable calls to mn_invl_range_start Patch series "mmu_notifiers follow ups". Tetsuo has noticed some fallouts from 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers"). One of them has been fixed and picked up by AMD/DRM maintainer [1]. XEN issue is fixed by patch 1. I have also clarified expectations about blockable semantic of invalidate_range_end. Finally the last patch removes MMU_INVALIDATE_DOES_NOT_BLOCK which is no longer used nor needed. [1] http://lkml.kernel.org/r/20180824135257.GU29735@dhcp22.suse.cz This patch (of 3): 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers") has introduced blockable parameter to all mmu_notifiers and the notifier has to back off when called in !blockable case and it could block down the road. The above commit implemented that for mn_invl_range_start but both in_range checks are done unconditionally regardless of the blockable mode and as such they would fail all the time for regular calls. Fix this by checking blockable parameter as well. Once we are there we can remove the stale TODO. The lock has to be sleepable because we wait for completion down in gnttab_unmap_refs_sync. Link: http://lkml.kernel.org/r/20180827112623.8992-2-mhocko@kernel.org Fixes: 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers") Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: David Rientjes <rientjes@google.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Reviewed-by: Juergen Gross <jgross@suse.com> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
2018-09-05 02:21:39 +03:00
mstart = max(range->start, map->vma->vm_start);
mend = min(range->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,
range->start, range->end, mstart, mend);
err = unmap_grant_pages(map,
(mstart - map->vma->vm_start) >> PAGE_SHIFT,
(mend - mstart) >> PAGE_SHIFT);
WARN_ON(err);
xen/gntdev: fix up blockable calls to mn_invl_range_start Patch series "mmu_notifiers follow ups". Tetsuo has noticed some fallouts from 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers"). One of them has been fixed and picked up by AMD/DRM maintainer [1]. XEN issue is fixed by patch 1. I have also clarified expectations about blockable semantic of invalidate_range_end. Finally the last patch removes MMU_INVALIDATE_DOES_NOT_BLOCK which is no longer used nor needed. [1] http://lkml.kernel.org/r/20180824135257.GU29735@dhcp22.suse.cz This patch (of 3): 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers") has introduced blockable parameter to all mmu_notifiers and the notifier has to back off when called in !blockable case and it could block down the road. The above commit implemented that for mn_invl_range_start but both in_range checks are done unconditionally regardless of the blockable mode and as such they would fail all the time for regular calls. Fix this by checking blockable parameter as well. Once we are there we can remove the stale TODO. The lock has to be sleepable because we wait for completion down in gnttab_unmap_refs_sync. Link: http://lkml.kernel.org/r/20180827112623.8992-2-mhocko@kernel.org Fixes: 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers") Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: David Rientjes <rientjes@google.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Reviewed-by: Juergen Gross <jgross@suse.com> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
2018-09-05 02:21:39 +03:00
return true;
}
static const struct mmu_interval_notifier_ops gntdev_mmu_ops = {
.invalidate = gntdev_invalidate,
};
/* ------------------------------------------------------------------ */
static int gntdev_open(struct inode *inode, struct file *flip)
{
struct gntdev_priv *priv;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
INIT_LIST_HEAD(&priv->maps);
mutex_init(&priv->lock);
#ifdef CONFIG_XEN_GNTDEV_DMABUF
priv->dmabuf_priv = gntdev_dmabuf_init(flip);
if (IS_ERR(priv->dmabuf_priv)) {
int ret = PTR_ERR(priv->dmabuf_priv);
kfree(priv);
return ret;
}
#endif
flip->private_data = priv;
#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
priv->dma_dev = gntdev_miscdev.this_device;
dma_coerce_mask_and_coherent(priv->dma_dev, DMA_BIT_MASK(64));
#endif
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 gntdev_grant_map *map;
pr_debug("priv %p\n", priv);
mutex_lock(&priv->lock);
while (!list_empty(&priv->maps)) {
map = list_entry(priv->maps.next,
struct gntdev_grant_map, next);
list_del(&map->next);
gntdev_put_map(NULL /* already removed */, map);
}
mutex_unlock(&priv->lock);
#ifdef CONFIG_XEN_GNTDEV_DMABUF
gntdev_dmabuf_fini(priv->dmabuf_priv);
#endif
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 gntdev_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);
2019-11-07 14:15:45 +03:00
if (unlikely(gntdev_test_page_count(op.count)))
return -EINVAL;
err = -ENOMEM;
map = gntdev_alloc_map(priv, op.count, 0 /* This is not a dma-buf. */);
if (!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;
}
mutex_lock(&priv->lock);
gntdev_add_map(priv, map);
op.index = map->index << PAGE_SHIFT;
mutex_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 gntdev_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);
mutex_lock(&priv->lock);
map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
if (map) {
list_del(&map->next);
err = 0;
}
mutex_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>
2011-10-11 23:16:06 +04:00
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 gntdev_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);
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 07:33:25 +03:00
mmap_read_lock(current->mm);
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:
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 07:33:25 +03:00
mmap_read_unlock(current->mm);
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 gntdev_grant_map *map;
int rc;
int out_flags;
evtchn_port_t 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;
mutex_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:
mutex_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;
}
#define GNTDEV_COPY_BATCH 16
struct gntdev_copy_batch {
struct gnttab_copy ops[GNTDEV_COPY_BATCH];
struct page *pages[GNTDEV_COPY_BATCH];
s16 __user *status[GNTDEV_COPY_BATCH];
unsigned int nr_ops;
unsigned int nr_pages;
bool writeable;
};
static int gntdev_get_page(struct gntdev_copy_batch *batch, void __user *virt,
unsigned long *gfn)
{
unsigned long addr = (unsigned long)virt;
struct page *page;
unsigned long xen_pfn;
int ret;
ret = pin_user_pages_fast(addr, 1, batch->writeable ? FOLL_WRITE : 0, &page);
if (ret < 0)
return ret;
batch->pages[batch->nr_pages++] = page;
xen_pfn = page_to_xen_pfn(page) + XEN_PFN_DOWN(addr & ~PAGE_MASK);
*gfn = pfn_to_gfn(xen_pfn);
return 0;
}
static void gntdev_put_pages(struct gntdev_copy_batch *batch)
{
unpin_user_pages_dirty_lock(batch->pages, batch->nr_pages, batch->writeable);
batch->nr_pages = 0;
batch->writeable = false;
}
static int gntdev_copy(struct gntdev_copy_batch *batch)
{
unsigned int i;
gnttab_batch_copy(batch->ops, batch->nr_ops);
gntdev_put_pages(batch);
/*
* For each completed op, update the status if the op failed
* and all previous ops for the segment were successful.
*/
for (i = 0; i < batch->nr_ops; i++) {
s16 status = batch->ops[i].status;
s16 old_status;
if (status == GNTST_okay)
continue;
if (__get_user(old_status, batch->status[i]))
return -EFAULT;
if (old_status != GNTST_okay)
continue;
if (__put_user(status, batch->status[i]))
return -EFAULT;
}
batch->nr_ops = 0;
return 0;
}
static int gntdev_grant_copy_seg(struct gntdev_copy_batch *batch,
struct gntdev_grant_copy_segment *seg,
s16 __user *status)
{
uint16_t copied = 0;
/*
* Disallow local -> local copies since there is only space in
* batch->pages for one page per-op and this would be a very
* expensive memcpy().
*/
if (!(seg->flags & (GNTCOPY_source_gref | GNTCOPY_dest_gref)))
return -EINVAL;
/* Can't cross page if source/dest is a grant ref. */
if (seg->flags & GNTCOPY_source_gref) {
if (seg->source.foreign.offset + seg->len > XEN_PAGE_SIZE)
return -EINVAL;
}
if (seg->flags & GNTCOPY_dest_gref) {
if (seg->dest.foreign.offset + seg->len > XEN_PAGE_SIZE)
return -EINVAL;
}
if (put_user(GNTST_okay, status))
return -EFAULT;
while (copied < seg->len) {
struct gnttab_copy *op;
void __user *virt;
size_t len, off;
unsigned long gfn;
int ret;
if (batch->nr_ops >= GNTDEV_COPY_BATCH) {
ret = gntdev_copy(batch);
if (ret < 0)
return ret;
}
len = seg->len - copied;
op = &batch->ops[batch->nr_ops];
op->flags = 0;
if (seg->flags & GNTCOPY_source_gref) {
op->source.u.ref = seg->source.foreign.ref;
op->source.domid = seg->source.foreign.domid;
op->source.offset = seg->source.foreign.offset + copied;
op->flags |= GNTCOPY_source_gref;
} else {
virt = seg->source.virt + copied;
off = (unsigned long)virt & ~XEN_PAGE_MASK;
len = min(len, (size_t)XEN_PAGE_SIZE - off);
batch->writeable = false;
ret = gntdev_get_page(batch, virt, &gfn);
if (ret < 0)
return ret;
op->source.u.gmfn = gfn;
op->source.domid = DOMID_SELF;
op->source.offset = off;
}
if (seg->flags & GNTCOPY_dest_gref) {
op->dest.u.ref = seg->dest.foreign.ref;
op->dest.domid = seg->dest.foreign.domid;
op->dest.offset = seg->dest.foreign.offset + copied;
op->flags |= GNTCOPY_dest_gref;
} else {
virt = seg->dest.virt + copied;
off = (unsigned long)virt & ~XEN_PAGE_MASK;
len = min(len, (size_t)XEN_PAGE_SIZE - off);
batch->writeable = true;
ret = gntdev_get_page(batch, virt, &gfn);
if (ret < 0)
return ret;
op->dest.u.gmfn = gfn;
op->dest.domid = DOMID_SELF;
op->dest.offset = off;
}
op->len = len;
copied += len;
batch->status[batch->nr_ops] = status;
batch->nr_ops++;
}
return 0;
}
static long gntdev_ioctl_grant_copy(struct gntdev_priv *priv, void __user *u)
{
struct ioctl_gntdev_grant_copy copy;
struct gntdev_copy_batch batch;
unsigned int i;
int ret = 0;
if (copy_from_user(&copy, u, sizeof(copy)))
return -EFAULT;
batch.nr_ops = 0;
batch.nr_pages = 0;
for (i = 0; i < copy.count; i++) {
struct gntdev_grant_copy_segment seg;
if (copy_from_user(&seg, &copy.segments[i], sizeof(seg))) {
ret = -EFAULT;
goto out;
}
ret = gntdev_grant_copy_seg(&batch, &seg, &copy.segments[i].status);
if (ret < 0)
goto out;
cond_resched();
}
if (batch.nr_ops)
ret = gntdev_copy(&batch);
return ret;
out:
gntdev_put_pages(&batch);
return ret;
}
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);
case IOCTL_GNTDEV_GRANT_COPY:
return gntdev_ioctl_grant_copy(priv, ptr);
#ifdef CONFIG_XEN_GNTDEV_DMABUF
case IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS:
return gntdev_ioctl_dmabuf_exp_from_refs(priv, use_ptemod, ptr);
case IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED:
return gntdev_ioctl_dmabuf_exp_wait_released(priv, ptr);
case IOCTL_GNTDEV_DMABUF_IMP_TO_REFS:
return gntdev_ioctl_dmabuf_imp_to_refs(priv, ptr);
case IOCTL_GNTDEV_DMABUF_IMP_RELEASE:
return gntdev_ioctl_dmabuf_imp_release(priv, ptr);
#endif
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_pages(vma);
struct gntdev_grant_map *map;
xen/gntdev.c: convert to use vm_map_pages() Convert to use vm_map_pages() to map range of kernel memory to user vma. map->count is passed to vm_map_pages() and internal API verify map->count against count ( count = vma_pages(vma)) for page array boundary overrun condition. Link: http://lkml.kernel.org/r/88e56e82d2db98705c2d842e9c9806c00b366d67.1552921225.git.jrdr.linux@gmail.com Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: David Airlie <airlied@linux.ie> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Joerg Roedel <joro@8bytes.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kees Cook <keescook@chromium.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> Cc: Pawel Osciak <pawel@osciak.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Robin Murphy <robin.murphy@arm.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Sandy Huang <hjc@rock-chips.com> Cc: Stefan Richter <stefanr@s5r6.in-berlin.de> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Thierry Reding <treding@nvidia.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:22:23 +03:00
int 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);
mutex_lock(&priv->lock);
map = gntdev_find_map_index(priv, index, count);
if (!map)
goto unlock_out;
if (use_ptemod && map->vma)
goto unlock_out;
refcount_inc(&map->users);
vma->vm_ops = &gntdev_vmops;
vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_MIXEDMAP;
if (use_ptemod)
vma->vm_flags |= VM_DONTCOPY;
vma->vm_private_data = map;
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;
}
if (use_ptemod) {
map->vma = vma;
err = mmu_interval_notifier_insert_locked(
&map->notifier, vma->vm_mm, vma->vm_start,
vma->vm_end - vma->vm_start, &gntdev_mmu_ops);
if (err) {
map->vma = NULL;
goto out_unlock_put;
}
}
mutex_unlock(&priv->lock);
if (use_ptemod) {
/*
* gntdev takes the address of the PTE in find_grant_ptes() and
* passes it to the hypervisor in gntdev_map_grant_pages(). The
* purpose of the notifier is to prevent the hypervisor pointer
* to the PTE from going stale.
*
* Since this vma's mappings can't be touched without the
* mmap_lock, and we are holding it now, there is no need for
* the notifier_range locking pattern.
*/
mmu_interval_read_begin(&map->notifier);
map->pages_vm_start = vma->vm_start;
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 = gntdev_map_grant_pages(map);
if (err)
goto out_put_map;
if (!use_ptemod) {
xen/gntdev.c: Replace vm_map_pages() with vm_map_pages_zero() 'commit df9bde015a72 ("xen/gntdev.c: convert to use vm_map_pages()")' breaks gntdev driver. If vma->vm_pgoff > 0, vm_map_pages() will: - use map->pages starting at vma->vm_pgoff instead of 0 - verify map->count against vma_pages()+vma->vm_pgoff instead of just vma_pages(). In practice, this breaks using a single gntdev FD for mapping multiple grants. relevant strace output: [pid 857] ioctl(7, IOCTL_GNTDEV_MAP_GRANT_REF, 0x7ffd3407b6d0) = 0 [pid 857] mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, 7, 0) = 0x777f1211b000 [pid 857] ioctl(7, IOCTL_GNTDEV_SET_UNMAP_NOTIFY, 0x7ffd3407b710) = 0 [pid 857] ioctl(7, IOCTL_GNTDEV_MAP_GRANT_REF, 0x7ffd3407b6d0) = 0 [pid 857] mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, 7, 0x1000) = -1 ENXIO (No such device or address) details here: https://github.com/QubesOS/qubes-issues/issues/5199 The reason is -> ( copying Marek's word from discussion) vma->vm_pgoff is used as index passed to gntdev_find_map_index. It's basically using this parameter for "which grant reference to map". map struct returned by gntdev_find_map_index() describes just the pages to be mapped. Specifically map->pages[0] should be mapped at vma->vm_start, not vma->vm_start+vma->vm_pgoff*PAGE_SIZE. When trying to map grant with index (aka vma->vm_pgoff) > 1, __vm_map_pages() will refuse to map it because it will expect map->count to be at least vma_pages(vma)+vma->vm_pgoff, while it is exactly vma_pages(vma). Converting vm_map_pages() to use vm_map_pages_zero() will fix the problem. Marek has tested and confirmed the same. Cc: stable@vger.kernel.org # v5.2+ Fixes: df9bde015a72 ("xen/gntdev.c: convert to use vm_map_pages()") Reported-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com> Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Tested-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Signed-off-by: Juergen Gross <jgross@suse.com>
2019-07-30 21:34:56 +03:00
err = vm_map_pages_zero(vma, map->pages, map->count);
xen/gntdev.c: convert to use vm_map_pages() Convert to use vm_map_pages() to map range of kernel memory to user vma. map->count is passed to vm_map_pages() and internal API verify map->count against count ( count = vma_pages(vma)) for page array boundary overrun condition. Link: http://lkml.kernel.org/r/88e56e82d2db98705c2d842e9c9806c00b366d67.1552921225.git.jrdr.linux@gmail.com Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: David Airlie <airlied@linux.ie> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Joerg Roedel <joro@8bytes.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kees Cook <keescook@chromium.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> Cc: Pawel Osciak <pawel@osciak.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Robin Murphy <robin.murphy@arm.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Sandy Huang <hjc@rock-chips.com> Cc: Stefan Richter <stefanr@s5r6.in-berlin.de> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Thierry Reding <treding@nvidia.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:22:23 +03:00
if (err)
goto out_put_map;
}
return 0;
unlock_out:
mutex_unlock(&priv->lock);
return err;
out_unlock_put:
mutex_unlock(&priv->lock);
out_put_map:
if (use_ptemod) {
unmap_grant_pages(map, 0, map->count);
if (map->vma) {
mmu_interval_notifier_remove(&map->notifier);
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);
/* ------------------------------------------------------------------ */