kernel/resource: clean up and optimize iomem_is_exclusive()

Patch series "virtio-mem: disallow mapping virtio-mem memory via /dev/mem", v5.

Let's add the basic infrastructure to exclude some physical memory regions
marked as "IORESOURCE_SYSTEM_RAM" completely from /dev/mem access, even
though they are not marked IORESOURCE_BUSY and even though "iomem=relaxed"
is set.  Resource IORESOURCE_EXCLUSIVE for that purpose instead of adding
new flags to express something similar to "soft-busy" or "not busy yet,
but already prepared by a driver and not to be mapped by user space".

Use it for virtio-mem, to disallow mapping any virtio-mem memory via
/dev/mem to user space after the virtio-mem driver was loaded.

This patch (of 3):

We end up traversing subtrees of ranges we are not interested in; let's
optimize this case, skipping such subtrees, cleaning up the function a
bit.

For example, in the following configuration (/proc/iomem):

  00000000-00000fff : Reserved
  00001000-00057fff : System RAM
  00058000-00058fff : Reserved
  00059000-0009cfff : System RAM
  0009d000-000fffff : Reserved
     000a0000-000bffff : PCI Bus 0000:00
     000c0000-000c3fff : PCI Bus 0000:00
     000c4000-000c7fff : PCI Bus 0000:00
     000c8000-000cbfff : PCI Bus 0000:00
     000cc000-000cffff : PCI Bus 0000:00
     000d0000-000d3fff : PCI Bus 0000:00
     000d4000-000d7fff : PCI Bus 0000:00
     000d8000-000dbfff : PCI Bus 0000:00
     000dc000-000dffff : PCI Bus 0000:00
     000e0000-000e3fff : PCI Bus 0000:00
     000e4000-000e7fff : PCI Bus 0000:00
     000e8000-000ebfff : PCI Bus 0000:00
     000ec000-000effff : PCI Bus 0000:00
     000f0000-000fffff : PCI Bus 0000:00
       000f0000-000fffff : System ROM
  00100000-3fffffff : System RAM
  40000000-403fffff : Reserved
     40000000-403fffff : pnp 00:00
  40400000-80a79fff : System RAM
  ...

We don't have to look at any children of "0009d000-000fffff : Reserved"
if we can just skip these 15 items directly because the parent range is
not of interest.

Link: https://lkml.kernel.org/r/20210920142856.17758-1-david@redhat.com
Link: https://lkml.kernel.org/r/20210920142856.17758-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Andy Shevchenko <andy.shevchenko@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 ca9f5198a01ff9b265f7197c03a0dd88d0b685d7..2999f57da38c35430da699d4e8a369df3c1a5e1e 100644 (file)
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -73,6 +73,18 @@ static struct resource *next_resource(struct resource *p)
        return p->sibling;
 }
 
+static struct resource *next_resource_skip_children(struct resource *p)
+{
+       while (!p->sibling && p->parent)
+               p = p->parent;
+       return p->sibling;
+}
+
+#define for_each_resource(_root, _p, _skip_children) \
+       for ((_p) = (_root)->child; (_p); \
+            (_p) = (_skip_children) ? next_resource_skip_children(_p) : \
+                                      next_resource(_p))
+
 static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 {
        struct resource *p = v;
@@ -1712,10 +1724,9 @@ static int strict_iomem_checks;
  */
 bool iomem_is_exclusive(u64 addr)
 {
-       struct resource *p = &iomem_resource;
-       bool err = false;
-       loff_t l;
+       bool skip_children = false, err = false;
        int size = PAGE_SIZE;
+       struct resource *p;
 
        if (!strict_iomem_checks)
                return false;
@@ -1723,15 +1734,19 @@ bool iomem_is_exclusive(u64 addr)
        addr = addr & PAGE_MASK;
 
        read_lock(&resource_lock);
-       for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+       for_each_resource(&iomem_resource, p, skip_children) {
                /*
                 * We can probably skip the resources without
                 * IORESOURCE_IO attribute?
                 */
                if (p->start >= addr + size)
                        break;
-               if (p->end < addr)
+               if (p->end < addr) {
+                       skip_children = true;
                        continue;
+               }
+               skip_children = false;
+
                /*
                 * A resource is exclusive if IORESOURCE_EXCLUSIVE is set
                 * or CONFIG_IO_STRICT_DEVMEM is enabled and the