s390: restore address space when returning to user space

Unbalanced set_fs usages (e.g. early exit from a function and a
forgotten set_fs(USER_DS) call) may lead to a situation where the
secondary asce is the kernel space asce when returning to user
space. This would allow user space to modify kernel space at will.

This would only be possible with the above mentioned kernel bug,
however we can detect this and fix the secondary asce before returning
to user space.

Therefore a new TIF_ASCE_SECONDARY which is used within set_fs. When
returning to user space check if TIF_ASCE_SECONDARY is set, which
would indicate a bug. If it is set print a message to the console,
fixup the secondary asce, and then return to user space.

This is similar to what is being discussed for x86 and arm:
"[RFC] syscalls: Restore address limit after a syscall".

Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

3 files changed, 32 insertions, 11 deletions

diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index ae7d1a230abf..dff2152350a7 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -50,7 +50,8 @@ _TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 		   _TIF_UPROBE)
 _TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		   _TIF_SYSCALL_TRACEPOINT)
-_CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE_PRIMARY | _CIF_FPU)
+_CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE_PRIMARY | \
+		   _CIF_ASCE_SECONDARY | _CIF_FPU)
 _PIF_WORK	= (_PIF_PER_TRAP)
 
 #define BASED(name) name-cleanup_critical(%r13)
@@ -339,8 +340,8 @@ ENTRY(system_call)
 	jo	.Lsysc_notify_resume
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
 	jo	.Lsysc_vxrs
-	TSTMSK	__LC_CPU_FLAGS,_CIF_ASCE_PRIMARY
-	jo	.Lsysc_asce_primary
+	TSTMSK	__LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
+	jnz	.Lsysc_asce
 	j	.Lsysc_return		# beware of critical section cleanup
 
 #
@@ -358,12 +359,15 @@ ENTRY(system_call)
 	jg	s390_handle_mcck	# TIF bit will be cleared by handler
 
 #
-# _CIF_ASCE_PRIMARY is set, load user space asce
+# _CIF_ASCE_PRIMARY and/or CIF_ASCE_SECONDARY set, load user space asce
 #
-.Lsysc_asce_primary:
+.Lsysc_asce:
 	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE_PRIMARY
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
-	j	.Lsysc_return
+	TSTMSK	__LC_CPU_FLAGS,_CIF_ASCE_SECONDARY
+	jz	.Lsysc_return
+	larl	%r14,.Lsysc_return
+	jg	set_fs_fixup
 
 #
 # CIF_FPU is set, restore floating-point controls and floating-point registers.
@@ -661,8 +665,8 @@ ENTRY(io_int_handler)
 	jo	.Lio_notify_resume
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
 	jo	.Lio_vxrs
-	TSTMSK	__LC_CPU_FLAGS,_CIF_ASCE_PRIMARY
-	jo	.Lio_asce_primary
+	TSTMSK	__LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
+	jnz	.Lio_asce
 	j	.Lio_return		# beware of critical section cleanup
 
 #
@@ -675,12 +679,15 @@ ENTRY(io_int_handler)
 	j	.Lio_return
 
 #
-# _CIF_ASCE_PRIMARY is set, load user space asce
+# _CIF_ASCE_PRIMARY and/or CIF_ASCE_SECONDARY set, load user space asce
 #
-.Lio_asce_primary:
+.Lio_asce:
 	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE_PRIMARY
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
-	j	.Lio_return
+	TSTMSK	__LC_CPU_FLAGS,_CIF_ASCE_SECONDARY
+	jz	.Lio_return
+	larl	%r14,.Lio_return
+	jg	set_fs_fixup
 
 #
 # CIF_FPU is set, restore floating-point controls and floating-point registers.
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index e79f030dd276..33f901865326 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -80,5 +80,6 @@ long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
 DECLARE_PER_CPU(u64, mt_cycles[8]);
 
 void verify_facilities(void);
+void set_fs_fixup(void);
 
 #endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index c5b86b4a1a8b..a49dc2bdeb17 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -234,3 +234,16 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 	ret = PAGE_ALIGN(mm->brk + brk_rnd());
 	return (ret > mm->brk) ? ret : mm->brk;
 }
+
+void set_fs_fixup(void)
+{
+	struct pt_regs *regs = current_pt_regs();
+	static bool warned;
+
+	set_fs(USER_DS);
+	if (warned)
+		return;
+	WARN(1, "Unbalanced set_fs - int code: 0x%x\n", regs->int_code);
+	show_registers(regs);
+	warned = true;
+}