Update Linux to v5.10.157
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.157.tar.xz
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
Change-Id: I7b30d9e98d8c465d6b44de8e7433b4a40b3289ba
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 54778aa..16acdda 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -35,6 +35,7 @@
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/refcount.h>
+#include <linux/workqueue.h>
#include <xen/xen.h>
#include <xen/grant_table.h>
@@ -60,10 +61,11 @@
MODULE_PARM_DESC(limit,
"Maximum number of grants that may be mapped by one mapping request");
+/* True in PV mode, false otherwise */
static int use_ptemod;
-static int unmap_grant_pages(struct gntdev_grant_map *map,
- int offset, int pages);
+static void unmap_grant_pages(struct gntdev_grant_map *map,
+ int offset, int pages);
static struct miscdevice gntdev_miscdev;
@@ -120,6 +122,7 @@
kvfree(map->unmap_ops);
kvfree(map->kmap_ops);
kvfree(map->kunmap_ops);
+ kvfree(map->being_removed);
kfree(map);
}
@@ -140,12 +143,15 @@
add->kunmap_ops = kvcalloc(count,
sizeof(add->kunmap_ops[0]), GFP_KERNEL);
add->pages = kvcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
+ add->being_removed =
+ kvcalloc(count, sizeof(add->being_removed[0]), GFP_KERNEL);
if (NULL == add->grants ||
NULL == add->map_ops ||
NULL == add->unmap_ops ||
NULL == add->kmap_ops ||
NULL == add->kunmap_ops ||
- NULL == add->pages)
+ NULL == add->pages ||
+ NULL == add->being_removed)
goto err;
#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
@@ -240,9 +246,39 @@
if (!refcount_dec_and_test(&map->users))
return;
- if (map->pages && !use_ptemod)
+ if (map->pages && !use_ptemod) {
+ /*
+ * Increment the reference count. This ensures that the
+ * subsequent call to unmap_grant_pages() will not wind up
+ * re-entering itself. It *can* wind up calling
+ * gntdev_put_map() recursively, but such calls will be with a
+ * reference count greater than 1, so they will return before
+ * this code is reached. The recursion depth is thus limited to
+ * 1. Do NOT use refcount_inc() here, as it will detect that
+ * the reference count is zero and WARN().
+ */
+ refcount_set(&map->users, 1);
+
+ /*
+ * Unmap the grants. This may or may not be asynchronous, so it
+ * is possible that the reference count is 1 on return, but it
+ * could also be greater than 1.
+ */
unmap_grant_pages(map, 0, map->count);
+ /* Check if the memory now needs to be freed */
+ if (!refcount_dec_and_test(&map->users))
+ return;
+
+ /*
+ * All pages have been returned to the hypervisor, so free the
+ * map.
+ */
+ }
+
+ if (use_ptemod && map->notifier_init)
+ mmu_interval_notifier_remove(&map->notifier);
+
if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
notify_remote_via_evtchn(map->notify.event);
evtchn_put(map->notify.event);
@@ -255,21 +291,14 @@
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;
+ unsigned int pgnr = (addr - map->pages_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;
- /*
- * Set the PTE as special to force get_user_pages_fast() fall
- * back to the slow path. If this is not supported as part of
- * the grant map, it will be done afterwards.
- */
- if (xen_feature(XENFEAT_gnttab_map_avail_bits))
- flags |= (1 << _GNTMAP_guest_avail0);
-
gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags,
map->grants[pgnr].ref,
map->grants[pgnr].domid);
@@ -278,16 +307,9 @@
return 0;
}
-#ifdef CONFIG_X86
-static int set_grant_ptes_as_special(pte_t *pte, unsigned long addr, void *data)
-{
- set_pte_at(current->mm, addr, pte, pte_mkspecial(*pte));
- return 0;
-}
-#endif
-
int gntdev_map_grant_pages(struct gntdev_grant_map *map)
{
+ size_t alloced = 0;
int i, err = 0;
if (!use_ptemod) {
@@ -336,87 +358,130 @@
map->pages, map->count);
for (i = 0; i < map->count; i++) {
- if (map->map_ops[i].status == GNTST_okay)
+ if (map->map_ops[i].status == GNTST_okay) {
map->unmap_ops[i].handle = map->map_ops[i].handle;
- else if (!err)
+ alloced++;
+ } 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)
+ if (map->kmap_ops[i].status == GNTST_okay) {
+ alloced++;
map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
- else if (!err)
+ } else if (!err)
err = -EINVAL;
}
}
+ atomic_add(alloced, &map->live_grants);
return err;
}
-static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+static void __unmap_grant_pages_done(int result,
+ struct gntab_unmap_queue_data *data)
+{
+ unsigned int i;
+ struct gntdev_grant_map *map = data->data;
+ unsigned int offset = data->unmap_ops - map->unmap_ops;
+ int successful_unmaps = 0;
+ int live_grants;
+
+ for (i = 0; i < data->count; i++) {
+ if (map->unmap_ops[offset + i].status == GNTST_okay &&
+ map->unmap_ops[offset + i].handle != -1)
+ successful_unmaps++;
+
+ WARN_ON(map->unmap_ops[offset+i].status &&
+ map->unmap_ops[offset+i].handle != -1);
+ 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;
+ if (use_ptemod) {
+ if (map->kunmap_ops[offset + i].status == GNTST_okay &&
+ map->kunmap_ops[offset + i].handle != -1)
+ successful_unmaps++;
+
+ WARN_ON(map->kunmap_ops[offset+i].status &&
+ map->kunmap_ops[offset+i].handle != -1);
+ 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 = -1;
+ }
+ }
+
+ /*
+ * Decrease the live-grant counter. This must happen after the loop to
+ * prevent premature reuse of the grants by gnttab_mmap().
+ */
+ live_grants = atomic_sub_return(successful_unmaps, &map->live_grants);
+ if (WARN_ON(live_grants < 0))
+ pr_err("%s: live_grants became negative (%d) after unmapping %d pages!\n",
+ __func__, live_grants, successful_unmaps);
+
+ /* Release reference taken by __unmap_grant_pages */
+ gntdev_put_map(NULL, map);
+}
+
+static void __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;
+ map->unmap_data.unmap_ops = map->unmap_ops + offset;
+ map->unmap_data.kunmap_ops = use_ptemod ? map->kunmap_ops + offset : NULL;
+ map->unmap_data.pages = map->pages + offset;
+ map->unmap_data.count = pages;
+ map->unmap_data.done = __unmap_grant_pages_done;
+ map->unmap_data.data = map;
+ refcount_inc(&map->users); /* to keep map alive during async call below */
- 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 = -1;
- }
- return err;
+ gnttab_unmap_refs_async(&map->unmap_data);
}
-static int unmap_grant_pages(struct gntdev_grant_map *map, int offset,
- int pages)
+static void unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+ int pages)
{
- int range, err = 0;
+ int range;
+
+ if (atomic_read(&map->live_grants) == 0)
+ return; /* Nothing to do */
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) {
+ while (pages) {
+ while (pages && map->being_removed[offset]) {
offset++;
pages--;
}
range = 0;
while (range < pages) {
- if (map->unmap_ops[offset+range].handle == -1)
+ if (map->being_removed[offset + range])
break;
+ map->being_removed[offset + range] = true;
range++;
}
- err = __unmap_grant_pages(map, offset, range);
+ if (range)
+ __unmap_grant_pages(map, offset, range);
offset += range;
pages -= range;
}
-
- return err;
}
/* ------------------------------------------------------------------ */
@@ -436,11 +501,7 @@
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);
}
@@ -468,31 +529,30 @@
struct gntdev_grant_map *map =
container_of(mn, struct gntdev_grant_map, notifier);
unsigned long mstart, mend;
- int err;
+ unsigned long map_start, map_end;
if (!mmu_notifier_range_blockable(range))
return false;
+ map_start = map->pages_vm_start;
+ map_end = map->pages_vm_start + (map->count << PAGE_SHIFT);
+
/*
* 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)
+ if (map_start >= range->end || map_end <= range->start)
return true;
- mstart = max(range->start, map->vma->vm_start);
- mend = min(range->end, map->vma->vm_end);
+ mstart = max(range->start, map_start);
+ mend = min(range->end, map_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);
+ map->index, map->count, map_start, map_end,
+ range->start, range->end, mstart, mend);
+ unmap_grant_pages(map, (mstart - map_start) >> PAGE_SHIFT,
+ (mend - mstart) >> PAGE_SHIFT);
return true;
}
@@ -972,14 +1032,15 @@
return -EINVAL;
pr_debug("map %d+%d at %lx (pgoff %lx)\n",
- index, count, vma->vm_start, vma->vm_pgoff);
+ 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)
+ if (!atomic_add_unless(&map->in_use, 1, 1))
goto unlock_out;
+
refcount_inc(&map->users);
vma->vm_ops = &gntdev_vmops;
@@ -1000,15 +1061,16 @@
map->flags |= GNTMAP_readonly;
}
+ map->pages_vm_start = vma->vm_start;
+
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;
+ if (err)
goto out_unlock_put;
- }
+
+ map->notifier_init = true;
}
mutex_unlock(&priv->lock);
@@ -1025,7 +1087,6 @@
*/
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);
@@ -1043,23 +1104,6 @@
err = vm_map_pages_zero(vma, map->pages, map->count);
if (err)
goto out_put_map;
- } else {
-#ifdef CONFIG_X86
- /*
- * If the PTEs were not made special by the grant map
- * hypercall, do so here.
- *
- * This is racy since the mapping is already visible
- * to userspace but userspace should be well-behaved
- * enough to not touch it until the mmap() call
- * returns.
- */
- if (!xen_feature(XENFEAT_gnttab_map_avail_bits)) {
- apply_to_page_range(vma->vm_mm, vma->vm_start,
- vma->vm_end - vma->vm_start,
- set_grant_ptes_as_special, NULL);
- }
-#endif
}
return 0;
@@ -1071,13 +1115,8 @@
out_unlock_put:
mutex_unlock(&priv->lock);
out_put_map:
- if (use_ptemod) {
+ 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;
}