Merge branch 'x86-entry-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 vsyscall updates from Thomas Gleixner:
 "Further hardening of the legacy vsyscall by providing support for
  execute only mode and switching the default to it.

  This prevents a certain class of attacks which rely on the vsyscall
  page being accessible at a fixed address in the canonical kernel
  address space"

* 'x86-entry-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  selftests/x86: Add a test for process_vm_readv() on the vsyscall page
  x86/vsyscall: Add __ro_after_init to global variables
  x86/vsyscall: Change the default vsyscall mode to xonly
  selftests/x86/vsyscall: Verify that vsyscall=none blocks execution
  x86/vsyscall: Document odd SIGSEGV error code for vsyscalls
  x86/vsyscall: Show something useful on a read fault
  x86/vsyscall: Add a new vsyscall=xonly mode
  Documentation/admin: Remove the vsyscall=native documentation
This commit is contained in:
Linus Torvalds
2019-07-08 11:42:09 -07:00
6 changed files with 174 additions and 53 deletions

View File

@@ -42,9 +42,11 @@
#define CREATE_TRACE_POINTS
#include "vsyscall_trace.h"
static enum { EMULATE, NONE } vsyscall_mode =
static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init =
#ifdef CONFIG_LEGACY_VSYSCALL_NONE
NONE;
#elif defined(CONFIG_LEGACY_VSYSCALL_XONLY)
XONLY;
#else
EMULATE;
#endif
@@ -54,6 +56,8 @@ static int __init vsyscall_setup(char *str)
if (str) {
if (!strcmp("emulate", str))
vsyscall_mode = EMULATE;
else if (!strcmp("xonly", str))
vsyscall_mode = XONLY;
else if (!strcmp("none", str))
vsyscall_mode = NONE;
else
@@ -113,7 +117,8 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
}
}
bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
bool emulate_vsyscall(unsigned long error_code,
struct pt_regs *regs, unsigned long address)
{
struct task_struct *tsk;
unsigned long caller;
@@ -122,6 +127,22 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
long ret;
unsigned long orig_dx;
/* Write faults or kernel-privilege faults never get fixed up. */
if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER)
return false;
if (!(error_code & X86_PF_INSTR)) {
/* Failed vsyscall read */
if (vsyscall_mode == EMULATE)
return false;
/*
* User code tried and failed to read the vsyscall page.
*/
warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround");
return false;
}
/*
* No point in checking CS -- the only way to get here is a user mode
* trap to a high address, which means that we're in 64-bit user code.
@@ -284,7 +305,7 @@ static const char *gate_vma_name(struct vm_area_struct *vma)
static const struct vm_operations_struct gate_vma_ops = {
.name = gate_vma_name,
};
static struct vm_area_struct gate_vma = {
static struct vm_area_struct gate_vma __ro_after_init = {
.vm_start = VSYSCALL_ADDR,
.vm_end = VSYSCALL_ADDR + PAGE_SIZE,
.vm_page_prot = PAGE_READONLY_EXEC,
@@ -357,12 +378,20 @@ void __init map_vsyscall(void)
extern char __vsyscall_page;
unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
if (vsyscall_mode != NONE) {
/*
* For full emulation, the page needs to exist for real. In
* execute-only mode, there is no PTE at all backing the vsyscall
* page.
*/
if (vsyscall_mode == EMULATE) {
__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
PAGE_KERNEL_VVAR);
set_vsyscall_pgtable_user_bits(swapper_pg_dir);
}
if (vsyscall_mode == XONLY)
gate_vma.vm_flags = VM_EXEC;
BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
(unsigned long)VSYSCALL_ADDR);
}