From 62b5f7d013fc455b8db26cf01e421f4c0d264b92 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:40 -0800 Subject: mm/core, x86/mm/pkeys: Add execute-only protection keys support Protection keys provide new page-based protection in hardware. But, they have an interesting attribute: they only affect data accesses and never affect instruction fetches. That means that if we set up some memory which is set as "access-disabled" via protection keys, we can still execute from it. This patch uses protection keys to set up mappings to do just that. If a user calls: mmap(..., PROT_EXEC); or mprotect(ptr, sz, PROT_EXEC); (note PROT_EXEC-only without PROT_READ/WRITE), the kernel will notice this, and set a special protection key on the memory. It also sets the appropriate bits in the Protection Keys User Rights (PKRU) register so that the memory becomes unreadable and unwritable. I haven't found any userspace that does this today. With this facility in place, we expect userspace to move to use it eventually. Userspace _could_ start doing this today. Any PROT_EXEC calls get converted to PROT_READ inside the kernel, and would transparently be upgraded to "true" PROT_EXEC with this code. IOW, userspace never has to do any PROT_EXEC runtime detection. This feature provides enhanced protection against leaking executable memory contents. This helps thwart attacks which are attempting to find ROP gadgets on the fly. But, the security provided by this approach is not comprehensive. The PKRU register which controls access permissions is a normal user register writable from unprivileged userspace. An attacker who can execute the 'wrpkru' instruction can easily disable the protection provided by this feature. The protection key that is used for execute-only support is permanently dedicated at compile time. This is fine for now because there is currently no API to set a protection key other than this one. Despite there being a constant PKRU value across the entire system, we do not set it unless this feature is in use in a process. That is to preserve the PKRU XSAVE 'init state', which can lead to faster context switches. PKRU *is* a user register and the kernel is modifying it. That means that code doing: pkru = rdpkru() pkru |= 0x100; mmap(..., PROT_EXEC); wrpkru(pkru); could lose the bits in PKRU that enforce execute-only permissions. To avoid this, we suggest avoiding ever calling mmap() or mprotect() when the PKRU value is expected to be unstable. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Aneesh Kumar K.V Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Chen Gang Cc: Dan Williams Cc: Dave Chinner Cc: Dave Hansen Cc: David Hildenbrand Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Kees Cook Cc: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Linus Torvalds Cc: Mel Gorman Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Piotr Kwapulinski Cc: Rik van Riel Cc: Stephen Smalley Cc: Vladimir Murzin Cc: Will Deacon Cc: keescook@google.com Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210240.CB4BB5CA@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- mm/mmap.c | 10 +++++++++- mm/mprotect.c | 8 ++++---- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index 784d2d6142a2..0175b7d055f0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -1270,6 +1271,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long pgoff, unsigned long *populate) { struct mm_struct *mm = current->mm; + int pkey = 0; *populate = 0; @@ -1309,11 +1311,17 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (offset_in_page(addr)) return addr; + if (prot == PROT_EXEC) { + pkey = execute_only_pkey(mm); + if (pkey < 0) + pkey = 0; + } + /* Do simple checking here so the lower-level routines won't have * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ - vm_flags |= calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(flags) | + vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; if (flags & MAP_LOCKED) diff --git a/mm/mprotect.c b/mm/mprotect.c index 3790c8bee380..fa37c4cd973a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -354,7 +355,7 @@ fail: SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, unsigned long, prot) { - unsigned long vm_flags, nstart, end, tmp, reqprot; + unsigned long nstart, end, tmp, reqprot; struct vm_area_struct *vma, *prev; int error = -EINVAL; const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP); @@ -380,8 +381,6 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) prot |= PROT_EXEC; - vm_flags = calc_vm_prot_bits(prot, 0); - down_write(¤t->mm->mmap_sem); vma = find_vma(current->mm, start); @@ -411,10 +410,11 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, for (nstart = start ; ; ) { unsigned long newflags; + int pkey = arch_override_mprotect_pkey(vma, prot, -1); /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ - newflags = vm_flags; + newflags = calc_vm_prot_bits(prot, pkey); newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC)); /* newflags >> 4 shift VM_MAY% in place of VM_% */ -- cgit v1.2.3