[PATCHv2] arm: Preserve TPIDRURW on context switch
André Hentschel
nerv at dawncrow.de
Tue Apr 23 18:42:22 EDT 2013
Am 23.04.2013 11:15, schrieb Will Deacon:
> On Mon, Apr 22, 2013 at 10:07:35PM +0100, André Hentschel wrote:
>> Am 22.04.2013 17:18, schrieb Will Deacon:
>>> On Mon, Apr 22, 2013 at 03:36:16PM +0100, Russell King - ARM Linux wrote:
>>>> On Fri, Apr 19, 2013 at 05:54:35PM +0200, André Hentschel wrote:
>>>>> From: =?UTF-8?q?Andr=C3=A9=20Hentschel?= <nerv at dawncrow.de>
>>>>>
>>>>> There are more and more applications coming to WinRT, Wine could support them,
>>>>> but mostly they expect to have the thread environment block (TEB) in TPIDRURW.
>>>>> This register must be preserved per thread instead of being cleared.
>>>>>
>>>>> Signed-off-by: André Hentschel <nerv at dawncrow.de>
>>>>
>>>> This actually makes things less efficient all round, because you
>>>> now use the value immediately after loading, which means it will cause
>>>> pipeline stalls, certainly on older CPUs.
>>>>
>>>> Could you please rework the patch to try avoiding soo many modifications
>>>> to the way things have been done here?
>>>
>>> copy_thread also needs updating so that the *register* value for the parent
>>> is copied to the child, since the parent may have written the register
>>> after the last context-switch, meaning that tp_value is out-of-date.
>>
>> Thank you both for reviewing.
>>
>> I guess you mostly mean "ldr r6, [r2, #TI_CPU_DOMAIN]".
>> I just thought about old CPUs and remembered again that we at Wine
>> need that patch only on v7 (and later). So is it ok to introduce a set_tls_v7
>> in tls.h and make use of CONFIG_CPU_V7 compile-time check in
>> the changed files and in the copy_thread function?
>
> No, we should support this feature on any CPU with the TPIDRURW register,
> otherwise it's going to get really confusing for userspace.
Sure, remembered that today.
>> Do i need any further flag checks in copy_thread or can i use the
>> compile-time check to add unconditional code?
>
> You could introduce `get' tls functions, which don't do anything for CPUs
> without the relevant registers.
Before i have another round of testing and patch formatting/sending,
what about the untested patch below?
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index cddda1f..bb5b48d 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -58,7 +58,7 @@ struct thread_info {
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];
#ifdef CONFIG_CRUNCH
struct crunch_state crunchstate;
#endif
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index 73409e6..1c10163 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -2,13 +2,30 @@
#define __ASMARM_TLS_H
#ifdef __ASSEMBLY__
+ .macro get_tls2_none, tp, tmp1
+ .endm
+
+ .macro get_tls2_v6k, tp, tmp1
+ mrc p15, 0, \tmp1, c13, c0, 2 @ get user r/w TLS register
+ str \tmp1, [\tp, #4]
+ .endm
+
+ .macro get_tls2_v6, tp, tmp1
+ ldr \tmp1, =elf_hwcap
+ ldr \tmp1, [\tmp1, #0]
+ tst \tmp1, #HWCAP_TLS @ hardware TLS available?
+ mrcne p15, 0, \tmp1, c13, c0, 2 @ get user r/w TLS register
+ strne \tmp1, [\tp, #4]
+ .endm
+
+
.macro set_tls_none, tp, tmp1, tmp2
.endm
.macro set_tls_v6k, tp, tmp1, tmp2
- 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
+ ldrd \tmp1, \tmp2, [\tp]
+ mcr p15, 0, \tmp1, c13, c0, 3 @ set user r/o TLS register
+ mcr p15, 0, \tmp2, c13, c0, 2 @ set user r/w TLS register
.endm
.macro set_tls_v6, tp, tmp1, tmp2
@@ -16,33 +33,39 @@
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
+ ldrdne \tmp1, \tmp2, [\tp]
+ ldreq \tmp1, [\tp]
+ mcrne p15, 0, \tmp1, c13, c0, 3 @ yes, set user r/o TLS register
+ mcrne p15, 0, \tmp2, c13, c0, 2 @ set user r/w TLS register
+ streq \tmp1, [\tmp2, #-15] @ set TLS value at 0xffff0ff0
.endm
.macro set_tls_software, tp, tmp1, tmp2
- mov \tmp1, #0xffff0fff
- str \tp, [\tmp1, #-15] @ set TLS value at 0xffff0ff0
+ ldr \tmp1, [\tp]
+ mov \tmp2, #0xffff0fff
+ str \tmp1, [\tmp2, #-15] @ set TLS value at 0xffff0ff0
.endm
#endif
#ifdef CONFIG_TLS_REG_EMUL
#define tls_emu 1
#define has_tls_reg 1
+#define get_tls2 get_tls2_none
#define set_tls set_tls_none
#elif defined(CONFIG_CPU_V6)
#define tls_emu 0
#define has_tls_reg (elf_hwcap & HWCAP_TLS)
+#define get_tls2 get_tls2_v6
#define set_tls set_tls_v6
#elif defined(CONFIG_CPU_32v6K)
#define tls_emu 0
#define has_tls_reg 1
+#define get_tls2 get_tls2_v6k
#define set_tls set_tls_v6k
#else
#define tls_emu 0
#define has_tls_reg 0
+#define get_tls2 get_tls2_none
#define set_tls set_tls_software
#endif
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 0f82098..097686b 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -728,7 +728,7 @@ ENTRY(__switch_to)
UNWIND(.fnstart )
UNWIND(.cantunwind )
add ip, r1, #TI_CPU_SAVE
- ldr r3, [r2, #TI_TP_VALUE]
+ add r3, r1, #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 )
@@ -736,6 +736,8 @@ ENTRY(__switch_to)
#ifdef CONFIG_CPU_USE_DOMAINS
ldr r6, [r2, #TI_CPU_DOMAIN]
#endif
+ get_tls2 r3, r4
+ add r3, r2, #TI_TP_VALUE
set_tls r3, r4, r5
#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
ldr r7, [r2, #TI_TASK]
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 047d3e4..6138eb1 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -395,7 +395,8 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
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] = current_thread_info()->tp_value[1];
thread_notify(THREAD_NOTIFY_COPY, thread);
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 03deeff..2bc1514 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -849,7 +849,7 @@ long arch_ptrace(struct task_struct *child, long request,
#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;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 1c08911..f9d6259 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -588,7 +588,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
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) {
@@ -706,7 +706,7 @@ static int get_tp_trap(struct pt_regs *regs, unsigned int instr)
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;
}
More information about the linux-arm-kernel
mailing list