x86/mm: Make in_compat_syscall() work during exec

The x86 mmap() code selects the mmap base for an allocation depending on
the bitness of the syscall. For 64bit sycalls it select mm->mmap_base and
for 32bit mm->mmap_compat_base.

On execve the registers of the task invoking exec() are copied to the child
pt_regs. So child->pt_regs->orig_ax contains the execve syscall number of the
parent.

exec() calls mmap() which in turn uses in_compat_syscall() to check whether
the mapping is for a 32bit or a 64bit task. The decision is made on the
following criteria:

  ia32	  child->thread.status & TS_COMPAT
   x32	  child->pt_regs.orig_ax & __X32_SYSCALL_BIT
  ia64	  !ia32 && !x32

child->thread.status is corretly set up in set_personality_*(), but the
syscall number in child->pt_regs.orig_ax is left unmodified.

Therefore the parent/child combinations work or fail in the following way:

Parent Child Child->thread_status  child->pt_regs.orig_ax  in_compat()  Works
ia64    ia64   TS_COMPAT == 0	   __X32_SYSCALL_BIT == 0     false       Y
ia64    ia32   TS_COMPAT == 1	   __X32_SYSCALL_BIT == 0     true        Y
ia64     x32   TS_COMPAT == 0	   __X32_SYSCALL_BIT == 0     false       N
ia32    ia64   TS_COMPAT == 0	   __X32_SYSCALL_BIT == 0     false       Y
ia32    ia32   TS_COMPAT == 1	   __X32_SYSCALL_BIT == 0     true        Y
ia32     x32   TS_COMPAT == 0	   __X32_SYSCALL_BIT == 0     false       N
 x32    ia64   TS_COMPAT == 0	   __X32_SYSCALL_BIT == 1     true        N
 x32    ia32   TS_COMPAT == 1	   __X32_SYSCALL_BIT == 1     true        Y
 x32     x32   TS_COMPAT == 0	   __X32_SYSCALL_BIT == 1     true        Y

Make set_personality_*() store the syscall number incl. __X32_SYSCALL_BIT
which corresponds to the newly started ELF executable in the childs
pt_regs, i.e. pretend that the exec was invoked from a task with the same
executable format.

So both thread.status and pt_regs.orig_ax correspond to the new ELF format
and in_compat_syscall() returns the correct result.

[ tglx: Rewrote changelog ]

Fixes: commit 1b028f784e8c ("x86/mm: Introduce mmap_compat_base() for 32-bit mmap()")
Reported-by: Adam Borowski <kilobyte@angband.pl>
Suggested-by: H. Peter Anvin <hpa@zytor.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Dmitry Safonov <dsafonov@virtuozzo.com>
Cc: 0x7f454c46@gmail.com
Cc: linux-mm@kvack.org
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/20170331111137.28170-1-dsafonov@virtuozzo.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ea1a618..825a1e4 100644 (file)
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -53,6 +53,11 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/vdso.h>
 #include <asm/intel_rdt.h>
+#include <asm/unistd.h>
+#ifdef CONFIG_IA32_EMULATION
+/* Not included via unistd.h */
+#include <asm/unistd_32_ia32.h>
+#endif
 
 __visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
 
@@ -494,6 +499,8 @@ void set_personality_64bit(void)
        clear_thread_flag(TIF_IA32);
        clear_thread_flag(TIF_ADDR32);
        clear_thread_flag(TIF_X32);
+       /* Pretend that this comes from a 64bit execve */
+       task_pt_regs(current)->orig_ax = __NR_execve;
 
        /* Ensure the corresponding mm is not marked. */
        if (current->mm)
@@ -506,32 +513,50 @@ void set_personality_64bit(void)
        current->personality &= ~READ_IMPLIES_EXEC;
 }
 
-void set_personality_ia32(bool x32)
+static void __set_personality_x32(void)
 {
-       /* inherit personality from parent */
+#ifdef CONFIG_X86_X32
+       clear_thread_flag(TIF_IA32);
+       set_thread_flag(TIF_X32);
+       if (current->mm)
+               current->mm->context.ia32_compat = TIF_X32;
+       current->personality &= ~READ_IMPLIES_EXEC;
+       /*
+        * in_compat_syscall() uses the presence of the x32 syscall bit
+        * flag to determine compat status.  The x86 mmap() code relies on
+        * the syscall bitness so set x32 syscall bit right here to make
+        * in_compat_syscall() work during exec().
+        *
+        * Pretend to come from a x32 execve.
+        */
+       task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT;
+       current->thread.status &= ~TS_COMPAT;
+#endif
+}
 
+static void __set_personality_ia32(void)
+{
+#ifdef CONFIG_IA32_EMULATION
+       set_thread_flag(TIF_IA32);
+       clear_thread_flag(TIF_X32);
+       if (current->mm)
+               current->mm->context.ia32_compat = TIF_IA32;
+       current->personality |= force_personality32;
+       /* Prepare the first "return" to user space */
+       task_pt_regs(current)->orig_ax = __NR_ia32_execve;
+       current->thread.status |= TS_COMPAT;
+#endif
+}
+
+void set_personality_ia32(bool x32)
+{
        /* Make sure to be in 32bit mode */
        set_thread_flag(TIF_ADDR32);
 
-       /* Mark the associated mm as containing 32-bit tasks. */
-       if (x32) {
-               clear_thread_flag(TIF_IA32);
-               set_thread_flag(TIF_X32);
-               if (current->mm)
-                       current->mm->context.ia32_compat = TIF_X32;
-               current->personality &= ~READ_IMPLIES_EXEC;
-               /* in_compat_syscall() uses the presence of the x32
-                  syscall bit flag to determine compat status */
-               current->thread.status &= ~TS_COMPAT;
-       } else {
-               set_thread_flag(TIF_IA32);
-               clear_thread_flag(TIF_X32);
-               if (current->mm)
-                       current->mm->context.ia32_compat = TIF_IA32;
-               current->personality |= force_personality32;
-               /* Prepare the first "return" to user space */
-               current->thread.status |= TS_COMPAT;
-       }
+       if (x32)
+               __set_personality_x32();
+       else
+               __set_personality_ia32();
 }
 EXPORT_SYMBOL_GPL(set_personality_ia32);