x86/boot: make sure KASLR does not step over KHO preserved memory

During kexec handover (KHO) memory contains data that should be preserved
and this data would be consumed by kexec'ed kernel.

To make sure that the preserved memory is not overwritten, KHO uses
"scratch regions" to bootstrap kexec'ed kernel.  These regions are
guaranteed to not have any memory that KHO would preserve and are used as
the only memory the kernel sees during the early boot.

The scratch regions are passed in the setup_data by the first kernel with
other KHO parameters.  If the setup_data contains the KHO parameters,
limit randomization to scratch areas only to make sure preserved memory
won't get overwritten.

Since all the pointers in setup_data are represented by u64, they require
double casting (first to unsigned long and then to the actual pointer
type) to compile on 32-bits.  This looks goofy out of context, but it is
unfortunately the way that this is handled across the tree.  There are at
least a dozen instances of casting like this.

Link: https://lkml.kernel.org/r/20250509074635.3187114-14-changyuanl@google.com
Signed-off-by: Alexander Graf <graf@amazon.com>
Co-developed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Co-developed-by: Changyuan Lyu <changyuanl@google.com>
Signed-off-by: Changyuan Lyu <changyuanl@google.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Anthony Yznaga <anthony.yznaga@oracle.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Ashish Kalra <ashish.kalra@amd.com>
Cc: Ben Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Gowans <jgowans@amazon.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Marc Rutland <mark.rutland@arm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Pratyush Yadav <ptyadav@amazon.de>
Cc: Rob Herring <robh@kernel.org>
Cc: Saravana Kannan <saravanak@google.com>
Cc: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: Thomas Lendacky <thomas.lendacky@amd.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index f03d59ea6e40fcdff143b9a484122fd30b96929a..3b0948ad449f945e5a5ebb85b16cce4166f473d5 100644 (file)
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -760,6 +760,49 @@ static void process_e820_entries(unsigned long minimum,
        }
 }
 
+/*
+ * If KHO is active, only process its scratch areas to ensure we are not
+ * stepping onto preserved memory.
+ */
+static bool process_kho_entries(unsigned long minimum, unsigned long image_size)
+{
+       struct kho_scratch *kho_scratch;
+       struct setup_data *ptr;
+       struct kho_data *kho;
+       int i, nr_areas = 0;
+
+       if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER))
+               return false;
+
+       ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data;
+       while (ptr) {
+               if (ptr->type == SETUP_KEXEC_KHO) {
+                       kho = (struct kho_data *)(unsigned long)ptr->data;
+                       kho_scratch = (void *)(unsigned long)kho->scratch_addr;
+                       nr_areas = kho->scratch_size / sizeof(*kho_scratch);
+                       break;
+               }
+
+               ptr = (struct setup_data *)(unsigned long)ptr->next;
+       }
+
+       if (!nr_areas)
+               return false;
+
+       for (i = 0; i < nr_areas; i++) {
+               struct kho_scratch *area = &kho_scratch[i];
+               struct mem_vector region = {
+                       .start = area->addr,
+                       .size = area->size,
+               };
+
+               if (process_mem_region(&region, minimum, image_size))
+                       break;
+       }
+
+       return true;
+}
+
 static unsigned long find_random_phys_addr(unsigned long minimum,
                                           unsigned long image_size)
 {
@@ -775,7 +818,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum,
                return 0;
        }
 
-       if (!process_efi_entries(minimum, image_size))
+       /*
+        * During kexec handover only process KHO scratch areas that are known
+        * not to contain any data that must be preserved.
+        */
+       if (!process_kho_entries(minimum, image_size) &&
+           !process_efi_entries(minimum, image_size))
                process_e820_entries(minimum, image_size);
 
        phys_addr = slots_fetch_random();