x86/fpu: Reinitialize FPU registers if restoring FPU state fails

Userspace can change the FPU state of a task using the ptrace() or
rt_sigreturn() system calls.  Because reserved bits in the FPU state can
cause the XRSTOR instruction to fail, the kernel has to carefully
validate that no reserved bits or other invalid values are being set.

Unfortunately, there have been bugs in this validation code.  For
example, we were not checking that the 'xcomp_bv' field in the
xstate_header was 0.  As-is, such bugs are exploitable to read the FPU
registers of other processes on the system.  To do so, an attacker can
create a task, assign to it an invalid FPU state, then spin in a loop
and monitor the values of the FPU registers.  Because the task's FPU
registers are not being restored, sometimes the FPU registers will have
the values from another process.

This is likely to continue to be a problem in the future because the
validation done by the CPU instructions like XRSTOR is not immediately
visible to kernel developers.  Nor will invalid FPU states ever be
encountered during ordinary use --- they will only be seen during
fuzzing or exploits.  There can even be reserved bits outside the
xstate_header which are easy to forget about.  For example, the MXCSR
register contains reserved bits, which were not validated by the
KVM_SET_XSAVE ioctl until commit a575813 ("KVM: x86: Fix load
damaged SSEx MXCSR register").

Therefore, mitigate this class of vulnerability by restoring the FPU
registers from init_fpstate if restoring from the task's state fails.

We actually used to do this, but it was (perhaps unwisely) removed by
commit 9ccc27a ("x86/fpu: Remove error return values from
copy_kernel_to_*regs() functions").  This new patch is also a bit
different.  First, it only clears the registers, not also the bad
in-memory state; this is simpler and makes it easier to make the
mitigation cover all callers of __copy_kernel_to_fpregs().  Second, it
does the register clearing in an exception handler so that no extra
instructions are added to context switches.  In fact, we *remove*
instructions, since previously we were always zeroing the register
containing 'err' even if CONFIG_X86_DEBUG_FPU was disabled.

Signed-off-by: Eric Biggers <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Dmitry Vyukov <[email protected]>
Cc: Eric Biggers <[email protected]>
Cc: Fenghua Yu <[email protected]>
Cc: Kevin Hao <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Michael Halcrow <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Wanpeng Li <[email protected]>
Cc: Yu-cheng Yu <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: ebiggers

arch/x86/include/asm/fpu/internal.h

@@ -120,20 +120,11 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu);
 	err;								\
 })
 
-#define check_insn(insn, output, input...)				\
-({									\
-	int err;							\
+#define kernel_insn(insn, output, input...)				\
 	asm volatile("1:" #insn "\n\t"					\
 		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:  movl $-1,%[err]\n"				\
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : [err] "=r" (err), output				\
-		     : "0"(0), input);					\
-	err;								\
-})
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore)	\
+		     : output : input)
 
 static inline int copy_fregs_to_user(struct fregs_state __user *fx)
 {
@@ -153,20 +144,16 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
 
 static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
 {
-	int err;
-
 	if (IS_ENABLED(CONFIG_X86_32)) {
-		err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+		kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 	} else {
 		if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) {
-			err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+			kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
 		} else {
 			/* See comment in copy_fxregs_to_kernel() below. */
-			err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+			kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
 		}
 	}
-	/* Copying from a kernel buffer to FPU registers should never fail: */
-	WARN_ON_FPU(err);
 }
 
 static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
@@ -183,9 +170,7 @@ static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
 
 static inline void copy_kernel_to_fregs(struct fregs_state *fx)
 {
-	int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	WARN_ON_FPU(err);
+	kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
 static inline int copy_user_to_fregs(struct fregs_state __user *fx)
@@ -281,18 +266,13 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
  * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
  * XSAVE area format.
  */
-#define XSTATE_XRESTORE(st, lmask, hmask, err)				\
+#define XSTATE_XRESTORE(st, lmask, hmask)				\
 	asm volatile(ALTERNATIVE(XRSTOR,				\
 				 XRSTORS, X86_FEATURE_XSAVES)		\
 		     "\n"						\
-		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
-		     ".pushsection .fixup,\"ax\"\n"			\
-		     "4: movl $-2, %[err]\n"				\
-		     "jmp 3b\n"						\
-		     ".popsection\n"					\
-		     _ASM_EXTABLE(661b, 4b)				\
-		     : [err] "=r" (err)					\
+		     _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\
+		     :							\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
@@ -336,7 +316,10 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
 
-	/* We should never fault when copying from a kernel buffer: */
+	/*
+	 * We should never fault when copying from a kernel buffer, and the FPU
+	 * state we set at boot time should be valid.
+	 */
 	WARN_ON_FPU(err);
 }
 
@@ -365,12 +348,8 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
 {
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err;
-
-	XSTATE_XRESTORE(xstate, lmask, hmask, err);
 
-	/* We should never fault when copying from a kernel buffer: */
-	WARN_ON_FPU(err);
+	XSTATE_XRESTORE(xstate, lmask, hmask);
 }
 
 /*

arch/x86/mm/extable.c

@@ -2,6 +2,7 @@
 #include <linux/uaccess.h>
 #include <linux/sched/debug.h>
 
+#include <asm/fpu/internal.h>
 #include <asm/traps.h>
 #include <asm/kdebug.h>
 
@@ -78,6 +79,29 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL_GPL(ex_handler_refcount);
 
+/*
+ * Handler for when we fail to restore a task's FPU state.  We should never get
+ * here because the FPU state of a task using the FPU (task->thread.fpu.state)
+ * should always be valid.  However, past bugs have allowed userspace to set
+ * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
+ * These caused XRSTOR to fail when switching to the task, leaking the FPU
+ * registers of the task previously executing on the CPU.  Mitigate this class
+ * of vulnerability by restoring from the initial state (essentially, zeroing
+ * out all the FPU registers) if we can't restore from the task's FPU state.
+ */
+bool ex_handler_fprestore(const struct exception_table_entry *fixup,
+			  struct pt_regs *regs, int trapnr)
+{
+	regs->ip = ex_fixup_addr(fixup);
+
+	WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.",
+		  (void *)instruction_pointer(regs));
+
+	__copy_kernel_to_fpregs(&init_fpstate, -1);
+	return true;
+}
+EXPORT_SYMBOL_GPL(ex_handler_fprestore);
+
 bool ex_handler_ext(const struct exception_table_entry *fixup,
 		   struct pt_regs *regs, int trapnr)
 {