From 8715ce033eb37f539e73b1570bf56404b21d46cd Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Thu, 25 Apr 2019 17:11:31 -0700 Subject: x86/modules: Avoid breaking W^X while loading modules [ Upstream commit f2c65fb3221adc6b73b0549fc7ba892022db9797 ] When modules and BPF filters are loaded, there is a time window in which some memory is both writable and executable. An attacker that has already found another vulnerability (e.g., a dangling pointer) might be able to exploit this behavior to overwrite kernel code. Prevent having writable executable PTEs in this stage. In addition, avoiding having W+X mappings can also slightly simplify the patching of modules code on initialization (e.g., by alternatives and static-key), as would be done in the next patch. This was actually the main motivation for this patch. To avoid having W+X mappings, set them initially as RW (NX) and after they are set as RO set them as X as well. Setting them as executable is done as a separate step to avoid one core in which the old PTE is cached (hence writable), and another which sees the updated PTE (executable), which would break the W^X protection. Suggested-by: Thomas Gleixner Suggested-by: Andy Lutomirski Signed-off-by: Nadav Amit Signed-off-by: Rick Edgecombe Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Jessica Yu Cc: Kees Cook Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Rik van Riel Link: https://lkml.kernel.org/r/20190426001143.4983-12-namit@vmware.com Signed-off-by: Ingo Molnar Signed-off-by: Sasha Levin --- arch/x86/kernel/alternative.c | 28 +++++++++++++++++++++------- arch/x86/kernel/module.c | 2 +- 2 files changed, 22 insertions(+), 8 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b9d5e7c9ef43..918a23704c0c 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -662,15 +662,29 @@ void __init alternative_instructions(void) * handlers seeing an inconsistent instruction while you patch. */ void *__init_or_module text_poke_early(void *addr, const void *opcode, - size_t len) + size_t len) { unsigned long flags; - local_irq_save(flags); - memcpy(addr, opcode, len); - local_irq_restore(flags); - sync_core(); - /* Could also do a CLFLUSH here to speed up CPU recovery; but - that causes hangs on some VIA CPUs. */ + + if (boot_cpu_has(X86_FEATURE_NX) && + is_module_text_address((unsigned long)addr)) { + /* + * Modules text is marked initially as non-executable, so the + * code cannot be running and speculative code-fetches are + * prevented. Just change the code. + */ + memcpy(addr, opcode, len); + } else { + local_irq_save(flags); + memcpy(addr, opcode, len); + local_irq_restore(flags); + sync_core(); + + /* + * Could also do a CLFLUSH here to speed up CPU recovery; but + * that causes hangs on some VIA CPUs. + */ + } return addr; } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index f58336af095c..6645f123419c 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -87,7 +87,7 @@ void *module_alloc(unsigned long size) p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), MODULES_END, GFP_KERNEL, - PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); if (p && (kasan_module_alloc(p, size) < 0)) { vfree(p); -- cgit v1.2.3