virtio-mem: add memory via add_memory_driver_managed()

Virtio-mem managed memory is always detected and added by the virtio-mem
driver, never using something like the firmware-provided memory map.
This is the case after an ordinary system reboot, and has to be guaranteed
after kexec. Especially, virtio-mem added memory resources can contain
inaccessible parts ("unblocked memory blocks"), blindly forwarding them
to a kexec kernel is dangerous, as unplugged memory will get accessed
(esp. written).

Let's use the new way of adding special driver-managed memory introduced
in commit 7b7b27214bba ("mm/memory_hotplug: introduce
add_memory_driver_managed()").

This will result in no entries in /sys/firmware/memmap ("raw firmware-
provided memory map"), the memory resource will be flagged
IORESOURCE_MEM_DRIVER_MANAGED (esp., kexec_file_load() will not place
kexec images on this memory), and it is exposed as "System RAM
(virtio_mem)" in /proc/iomem, so esp. kexec-tools can properly handle it.

Example /proc/iomem before this change:
  [...]
  140000000-333ffffff : virtio0
    140000000-147ffffff : System RAM
  334000000-533ffffff : virtio1
    338000000-33fffffff : System RAM
    340000000-347ffffff : System RAM
    348000000-34fffffff : System RAM
  [...]

Example /proc/iomem after this change:
  [...]
  140000000-333ffffff : virtio0
    140000000-147ffffff : System RAM (virtio_mem)
  334000000-533ffffff : virtio1
    338000000-33fffffff : System RAM (virtio_mem)
    340000000-347ffffff : System RAM (virtio_mem)
    348000000-34fffffff : System RAM (virtio_mem)
  [...]

Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: teawater <teawaterz@linux.alibaba.com>
Fixes: 5f1f79bbc9e26 ("virtio-mem: Paravirtualized memory hotplug")
Signed-off-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20200611093518.5737-1-david@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>

diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 5210ff0c5681bb8b6e315d4459bfce2f9e505b25..f26f5f64ae822c03966c6e7cab55c400fdf4a4e2 100644 (file)
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -101,6 +101,11 @@ struct virtio_mem {
 
        /* The parent resource for all memory added via this device. */
        struct resource *parent_resource;
+       /*
+        * Copy of "System RAM (virtio_mem)" to be used for
+        * add_memory_driver_managed().
+        */
+       const char *resource_name;
 
        /* Summary of all memory block states. */
        unsigned long nb_mb_state[VIRTIO_MEM_MB_STATE_COUNT];
@@ -414,8 +419,20 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
        if (nid == NUMA_NO_NODE)
                nid = memory_add_physaddr_to_nid(addr);
 
+       /*
+        * When force-unloading the driver and we still have memory added to
+        * Linux, the resource name has to stay.
+        */
+       if (!vm->resource_name) {
+               vm->resource_name = kstrdup_const("System RAM (virtio_mem)",
+                                                 GFP_KERNEL);
+               if (!vm->resource_name)
+                       return -ENOMEM;
+       }
+
        dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
-       return add_memory(nid, addr, memory_block_size_bytes());
+       return add_memory_driver_managed(nid, addr, memory_block_size_bytes(),
+                                        vm->resource_name);
 }
 
 /*
@@ -1890,10 +1907,12 @@ static void virtio_mem_remove(struct virtio_device *vdev)
            vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL] ||
            vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE] ||
            vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL] ||
-           vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE])
+           vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE]) {
                dev_warn(&vdev->dev, "device still has system memory added\n");
-       else
+       } else {
                virtio_mem_delete_resource(vm);
+               kfree_const(vm->resource_name);
+       }
 
        /* remove all tracking data - no locking needed */
        vfree(vm->mb_state);