kernel/resource: fix locking in request_free_mem_region

request_free_mem_region() is used to find an empty range of physical
addresses for hotplugging ZONE_DEVICE memory.  It does this by iterating
over the range of possible addresses using region_intersects() to see if
the range is free before calling request_mem_region() to allocate the
region.

However the resource_lock is dropped between these two calls meaning by
the time request_mem_region() is called in request_free_mem_region()
another thread may have already reserved the requested region.  This
results in unexpected failures and a message in the kernel log from
hitting this condition:

        /*
         * mm/hmm.c reserves physical addresses which then
         * become unavailable to other users.  Conflicts are
         * not expected.  Warn to aid debugging if encountered.
         */
        if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) {
                pr_warn("Unaddressable device %s %pR conflicts with %pR",
                        conflict->name, conflict, res);

These unexpected failures can be corrected by holding resource_lock across
the two calls.  This also requires memory allocation to be performed prior
to taking the lock.

Link: https://lkml.kernel.org/r/20210419070109.4780-3-apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Muchun Song <smuchun@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/resource.c b/kernel/resource.c
index c8e473b68f17c2e8ff532dfa671bb1a6f5a59ca3..028a5ab18818fd01c5c8313fe89168ed18b4bdbf 100644 (file)
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1780,25 +1780,56 @@ static struct resource *__request_free_mem_region(struct device *dev,
 {
        resource_size_t end, addr;
        struct resource *res;
+       struct region_devres *dr = NULL;
 
        size = ALIGN(size, 1UL << PA_SECTION_SHIFT);
        end = min_t(unsigned long, base->end, (1UL << MAX_PHYSMEM_BITS) - 1);
        addr = end - size + 1UL;
 
+       res = alloc_resource(GFP_KERNEL);
+       if (!res)
+               return ERR_PTR(-ENOMEM);
+
+       if (dev) {
+               dr = devres_alloc(devm_region_release,
+                               sizeof(struct region_devres), GFP_KERNEL);
+               if (!dr) {
+                       free_resource(res);
+                       return ERR_PTR(-ENOMEM);
+               }
+       }
+
+       write_lock(&resource_lock);
        for (; addr > size && addr >= base->start; addr -= size) {
-               if (region_intersects(addr, size, 0, IORES_DESC_NONE) !=
+               if (__region_intersects(addr, size, 0, IORES_DESC_NONE) !=
                                REGION_DISJOINT)
                        continue;
 
-               if (dev)
-                       res = devm_request_mem_region(dev, addr, size, name);
-               else
-                       res = request_mem_region(addr, size, name);
-               if (!res)
-                       return ERR_PTR(-ENOMEM);
+               if (!__request_region_locked(res, &iomem_resource, addr, size,
+                                               name, 0))
+                       break;
+
+               if (dev) {
+                       dr->parent = &iomem_resource;
+                       dr->start = addr;
+                       dr->n = size;
+                       devres_add(dev, dr);
+               }
+
                res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY;
+               write_unlock(&resource_lock);
+
+               /*
+                * A driver is claiming this region so revoke any mappings.
+                */
+               revoke_iomem(res);
                return res;
        }
+       write_unlock(&resource_lock);
+
+       free_resource(res);
+       if (dr)
+               devres_free(dr);
 
        return ERR_PTR(-ERANGE);
 }