Commit f22fecaf authored by Andy Lutomirski's avatar Andy Lutomirski Committed by Borislav Petkov
Browse files

x86/ptrace: Clean up PTRACE_GETREGS/PTRACE_PUTREGS regset selection 



task_user_regset_view() has nonsensical semantics, but those semantics
appear to be relied on by existing users of PTRACE_GETREGSET and
PTRACE_SETREGSET.  (See added comments below for details.)

It shouldn't be used for PTRACE_GETREGS or PTRACE_SETREGS, though. A
native 64-bit ptrace() call and an x32 ptrace() call using GETREGS
or SETREGS wants the 64-bit regset views, and a 32-bit ptrace() call
(native or compat) should use the 32-bit regset.

task_user_regset_view() almost does this except that it will
malfunction if a ptracer is itself ptraced and the outer ptracer
modifies CS on entry to a ptrace() syscall.  Hopefully that has never
happened.  (The compat ptrace() code already hardcoded the 32-bit
regset, so this change has no effect on that path.)

Improve the situation and deobfuscate the code by hardcoding the
64-bit view in the x32 ptrace() and selecting the view based on the
kernel config in the native ptrace().

I tried to figure out the history behind this API. I naïvely assumed
that PTRAGE_GETREGSET and PTRACE_SETREGSET were ancient APIs that
predated compat, but no. They were introduced by

  2225a122 ("ptrace: Add support for generic PTRACE_GETREGSET/PTRACE_SETREGSET")

in 2010, and they are simply a poor design.  ELF core dumps have the
ELF e_machine field and a bunch of register sets in ELF notes, and the
pair (e_machine, NT_XXX) indicates the format of the regset blob.  But
the new PTRACE_GET/SETREGSET API coopted the NT_XXX numbering without
any way to specify which e_machine was in effect.  This is especially
bad on x86, where a process can freely switch between 32-bit and
64-bit mode, and, in fact, the PTRAGE_SETREGSET call itself can cause
this switch to happen.  Oops.

Signed-off-by: default avatarAndy Lutomirski <luto@kernel.org>
Signed-off-by: default avatarBorislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/9daa791d0c7eaebd59c5bc2b2af1b0e7bebe707d.1612375698.git.luto@kernel.org
parent 8ece53ef

arch/x86/kernel/ptrace.c

+38 −8
Original line number Diff line number Diff line
@@ -704,6 +704,9 @@ void ptrace_disable(struct task_struct *child) 
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION

static const struct user_regset_view user_x86_32_view; /* Initialized below. */

#endif

#ifdef CONFIG_X86_64

static const struct user_regset_view user_x86_64_view; /* Initialized below. */

#endif



long arch_ptrace(struct task_struct *child, long request,

		 unsigned long addr, unsigned long data)
@@ -711,6 +714,14 @@ long arch_ptrace(struct task_struct *child, long request, 
	int ret;

	unsigned long __user *datap = (unsigned long __user *)data;



#ifdef CONFIG_X86_64

	/* This is native 64-bit ptrace() */

	const struct user_regset_view *regset_view = &user_x86_64_view;

#else

	/* This is native 32-bit ptrace() */

	const struct user_regset_view *regset_view = &user_x86_32_view;

#endif



	switch (request) {

	/* read the word at location addr in the USER area. */

	case PTRACE_PEEKUSR: {
@@ -749,28 +760,28 @@ long arch_ptrace(struct task_struct *child, long request, 


	case PTRACE_GETREGS:	/* Get all gp regs from the child. */

		return copy_regset_to_user(child,

					   task_user_regset_view(current),

					   regset_view,

					   REGSET_GENERAL,

					   0, sizeof(struct user_regs_struct),

					   datap);



	case PTRACE_SETREGS:	/* Set all gp regs in the child. */

		return copy_regset_from_user(child,

					     task_user_regset_view(current),

					     regset_view,

					     REGSET_GENERAL,

					     0, sizeof(struct user_regs_struct),

					     datap);



	case PTRACE_GETFPREGS:	/* Get the child FPU state. */

		return copy_regset_to_user(child,

					   task_user_regset_view(current),

					   regset_view,

					   REGSET_FP,

					   0, sizeof(struct user_i387_struct),

					   datap);



	case PTRACE_SETFPREGS:	/* Set the child FPU state. */

		return copy_regset_from_user(child,

					     task_user_regset_view(current),

					     regset_view,

					     REGSET_FP,

					     0, sizeof(struct user_i387_struct),

					     datap);
@@ -1152,28 +1163,28 @@ static long x32_arch_ptrace(struct task_struct *child, 


	case PTRACE_GETREGS:	/* Get all gp regs from the child. */

		return copy_regset_to_user(child,

					   task_user_regset_view(current),

					   &user_x86_64_view,

					   REGSET_GENERAL,

					   0, sizeof(struct user_regs_struct),

					   datap);



	case PTRACE_SETREGS:	/* Set all gp regs in the child. */

		return copy_regset_from_user(child,

					     task_user_regset_view(current),

					     &user_x86_64_view,

					     REGSET_GENERAL,

					     0, sizeof(struct user_regs_struct),

					     datap);



	case PTRACE_GETFPREGS:	/* Get the child FPU state. */

		return copy_regset_to_user(child,

					   task_user_regset_view(current),

					   &user_x86_64_view,

					   REGSET_FP,

					   0, sizeof(struct user_i387_struct),

					   datap);



	case PTRACE_SETFPREGS:	/* Set the child FPU state. */

		return copy_regset_from_user(child,

					     task_user_regset_view(current),

					     &user_x86_64_view,

					     REGSET_FP,

					     0, sizeof(struct user_i387_struct),

					     datap);
@@ -1309,6 +1320,25 @@ void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask) 
	xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask;

}



/*

 * This is used by the core dump code to decide which regset to dump.  The

 * core dump code writes out the resulting .e_machine and the corresponding

 * regsets.  This is suboptimal if the task is messing around with its CS.L

 * field, but at worst the core dump will end up missing some information.

 *

 * Unfortunately, it is also used by the broken PTRACE_GETREGSET and

 * PTRACE_SETREGSET APIs.  These APIs look at the .regsets field but have

 * no way to make sure that the e_machine they use matches the caller's

 * expectations.  The result is that the data format returned by

 * PTRACE_GETREGSET depends on the returned CS field (and even the offset

 * of the returned CS field depends on its value!) and the data format

 * accepted by PTRACE_SETREGSET is determined by the old CS value.  The

 * upshot is that it is basically impossible to use these APIs correctly.

 *

 * The best way to fix it in the long run would probably be to add new

 * improved ptrace() APIs to read and write registers reliably, possibly by

 * allowing userspace to select the ELF e_machine variant that they expect.

 */

const struct user_regset_view *task_user_regset_view(struct task_struct *task)

{

#ifdef CONFIG_IA32_EMULATION