ARM: 7735/2: Preserve the user r/w register TPIDRURW on context switch and fork

Since commit 6a1c53124aa1 the user writeable TLS register was zeroed to
prevent it from being used as a covert channel between two tasks.

There are more and more applications coming to Windows RT,
Wine could support them, but mostly they expect to have
the thread environment block (TEB) in TPIDRURW.

This patch preserves that register per thread instead of clearing it.
Unlike the TPIDRURO, which is already switched, the TPIDRURW
can be updated from userspace so needs careful treatment in the case that we
modify TPIDRURW and call fork(). To avoid this we must always read
TPIDRURW in copy_thread.

Signed-off-by: André Hentschel <[e-mail]>
Signed-off-by: Will Deacon <[e-mail]>
Signed-off-by: Jonathan Austin <[e-mail]>
Signed-off-by: Russell King <[e-mail]>

arch/arm/include/asm/thread_info.h

···
 	struct cpu_context_save	cpu_context;	/* cpu context */
 	__u32			syscall;	/* syscall number */
 	__u8			used_cp[16];	/* thread used copro */
-	unsigned long		tp_value;
+	unsigned long		tp_value[2];	/* TLS registers */
 #ifdef CONFIG_CRUNCH
 	struct crunch_state	crunchstate;
 #endif

arch/arm/include/asm/tls.h

···
 #define __ASMARM_TLS_H
 
 #ifdef __ASSEMBLY__
-	.macro set_tls_none, tp, tmp1, tmp2
+#include <asm/asm-offsets.h>
+	.macro switch_tls_none, base, tp, tpuser, tmp1, tmp2
 	.endm
 
-	.macro set_tls_v6k, tp, tmp1, tmp2
+	.macro switch_tls_v6k, base, tp, tpuser, tmp1, tmp2
+	mrc	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
 	mcr	p15, 0, \tp, c13, c0, 3		@ set TLS register
-	mov	\tmp1, #0
-	mcr	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
+	mcr	p15, 0, \tpuser, c13, c0, 2	@ and the user r/w register
+	str	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
 	.endm
 
-	.macro set_tls_v6, tp, tmp1, tmp2
+	.macro switch_tls_v6, base, tp, tpuser, tmp1, tmp2
 	ldr	\tmp1, =elf_hwcap
 	ldr	\tmp1, [\tmp1, #0]
 	mov	\tmp2, #0xffff0fff
 	tst	\tmp1, #HWCAP_TLS		@ hardware TLS available?
-	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
-	movne	\tmp1, #0
-	mcrne	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
 	streq	\tp, [\tmp2, #-15]		@ set TLS value at 0xffff0ff0
+	mrcne	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
+	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
+	mcrne	p15, 0, \tpuser, c13, c0, 2	@ set user r/w register
+	strne	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
 	.endm
 
-	.macro set_tls_software, tp, tmp1, tmp2
+	.macro switch_tls_software, base, tp, tpuser, tmp1, tmp2
 	mov	\tmp1, #0xffff0fff
 	str	\tp, [\tmp1, #-15]		@ set TLS value at 0xffff0ff0
 	.endm
···
 #ifdef CONFIG_TLS_REG_EMUL
 #define tls_emu		1
 #define has_tls_reg		1
-#define set_tls		set_tls_none
+#define switch_tls	switch_tls_none
 #elif defined(CONFIG_CPU_V6)
 #define tls_emu		0
 #define has_tls_reg		(elf_hwcap & HWCAP_TLS)
-#define set_tls		set_tls_v6
+#define switch_tls	switch_tls_v6
 #elif defined(CONFIG_CPU_32v6K)
 #define tls_emu		0
 #define has_tls_reg		1
-#define set_tls		set_tls_v6k
+#define switch_tls	switch_tls_v6k
 #else
 #define tls_emu		0
 #define has_tls_reg		0
-#define set_tls		set_tls_software
+#define switch_tls	switch_tls_software
 #endif
 
+#ifndef __ASSEMBLY__
+static inline unsigned long get_tpuser(void)
+{
+	unsigned long reg = 0;
+
+	if (has_tls_reg && !tls_emu)
+		__asm__("mrc p15, 0, %0, c13, c0, 2" : "=r" (reg));
+
+	return reg;
+}
+#endif
 #endif	/* __ASMARM_TLS_H */

arch/arm/kernel/entry-armv.S

···
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	add	ip, r1, #TI_CPU_SAVE
-	ldr	r3, [r2, #TI_TP_VALUE]
  ARM(	stmia	ip!, {r4 - sl, fp, sp, lr} )	@ Store most regs on stack
  THUMB(	stmia	ip!, {r4 - sl, fp}	   )	@ Store most regs on stack
  THUMB(	str	sp, [ip], #4		   )
  THUMB(	str	lr, [ip], #4		   )
+	ldr	r4, [r2, #TI_TP_VALUE]
+	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
-	set_tls	r3, r4, r5
+	switch_tls r1, r4, r5, r3, r7
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
 	ldr	r7, [r2, #TI_TASK]
 	ldr	r8, =__stack_chk_guard

arch/arm/kernel/process.c

···
 #include <asm/thread_notify.h>
 #include <asm/stacktrace.h>
 #include <asm/mach/time.h>
+#include <asm/tls.h>
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #include <linux/stackprotector.h>
···
 	clear_ptrace_hw_breakpoint(p);
 
 	if (clone_flags & CLONE_SETTLS)
-		thread->tp_value = childregs->ARM_r3;
+		thread->tp_value[0] = childregs->ARM_r3;
+	thread->tp_value[1] = get_tpuser();
 
 	thread_notify(THREAD_NOTIFY_COPY, thread);
 

arch/arm/kernel/ptrace.c

···
 #endif
 
 		case PTRACE_GET_THREAD_AREA:
-			ret = put_user(task_thread_info(child)->tp_value,
+			ret = put_user(task_thread_info(child)->tp_value[0],
 				       datap);
 			break;
 

arch/arm/kernel/traps.c

···
 		return regs->ARM_r0;
 
 	case NR(set_tls):
-		thread->tp_value = regs->ARM_r0;
+		thread->tp_value[0] = regs->ARM_r0;
 		if (tls_emu)
 			return 0;
 		if (has_tls_reg) {
···
 	int reg = (instr >> 12) & 15;
 	if (reg == 15)
 		return 1;
-	regs->uregs[reg] = current_thread_info()->tp_value;
+	regs->uregs[reg] = current_thread_info()->tp_value[0];
 	regs->ARM_pc += 4;
 	return 0;
 }