arm64/kernel: kaslr: reduce module randomization range to 2 GB

The following commit

  7290d58095 ("module: use relative references for __ksymtab entries")

updated the ksymtab handling of some KASLR capable architectures
so that ksymtab entries are emitted as pairs of 32-bit relative
references. This reduces the size of the entries, but more
importantly, it gets rid of statically assigned absolute
addresses, which require fixing up at boot time if the kernel
is self relocating (which takes a 24 byte RELA entry for each
member of the ksymtab struct).

Since ksymtab entries are always part of the same module as the
symbol they export, it was assumed at the time that a 32-bit
relative reference is always sufficient to capture the offset
between a ksymtab entry and its target symbol.

Unfortunately, this is not always true: in the case of per-CPU
variables, a per-CPU variable's base address (which usually differs
from the actual address of any of its per-CPU copies) is allocated
in the vicinity of the ..data.percpu section in the core kernel
(i.e., in the per-CPU reserved region which follows the section
containing the core kernel's statically allocated per-CPU variables).

Since we randomize the module space over a 4 GB window covering
the core kernel (based on the -/+ 4 GB range of an ADRP/ADD pair),
we may end up putting the core kernel out of the -/+ 2 GB range of
32-bit relative references of module ksymtab entries that refer to
per-CPU variables.

So reduce the module randomization range a bit further. We lose
1 bit of randomization this way, but this is something we can
tolerate.

Cc: <stable@vger.kernel.org> # v4.19+
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/kernel/kaslr.c

@@ -145,15 +145,15 @@ u64 __init kaslr_early_init(u64 dt_phys)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) {
 		/*
-		 * Randomize the module region over a 4 GB window covering the
+		 * Randomize the module region over a 2 GB window covering the
 		 * kernel. This reduces the risk of modules leaking information
 		 * about the address of the kernel itself, but results in
 		 * branches between modules and the core kernel that are
 		 * resolved via PLTs. (Branches between modules will be
 		 * resolved normally.)
 		 */
-		module_range = SZ_4G - (u64)(_end - _stext);
+		module_range = SZ_2G - (u64)(_end - _stext);
-		module_alloc_base = max((u64)_end + offset - SZ_4G,
+		module_alloc_base = max((u64)_end + offset - SZ_2G,
 					(u64)MODULES_VADDR);
 	} else {
 		/*

arch/arm64/kernel/module.c

@@ -56,7 +56,7 @@ void *module_alloc(unsigned long size)
 		 * can simply omit this fallback in that case.
 		 */
 		p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
-				module_alloc_base + SZ_4G, GFP_KERNEL,
+				module_alloc_base + SZ_2G, GFP_KERNEL,
 				PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
 				__builtin_return_address(0));