diff options
Diffstat (limited to 'arch/arm/kernel/entry-armv.S')
| -rw-r--r-- | arch/arm/kernel/entry-armv.S | 815 |
1 files changed, 367 insertions, 448 deletions
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index e8d88567680..52a949a8077 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -15,35 +15,70 @@ * that causes it to save wrong values... Be aware! */ +#include <asm/assembler.h> #include <asm/memory.h> #include <asm/glue-df.h> #include <asm/glue-pf.h> #include <asm/vfpmacros.h> +#ifndef CONFIG_MULTI_IRQ_HANDLER #include <mach/entry-macro.S> +#endif #include <asm/thread_notify.h> #include <asm/unwind.h> #include <asm/unistd.h> #include <asm/tls.h> +#include <asm/system_info.h> #include "entry-header.S" #include <asm/entry-macro-multi.S> /* - * Interrupt handling. Preserves r7, r8, r9 + * Interrupt handling. */ .macro irq_handler #ifdef CONFIG_MULTI_IRQ_HANDLER - ldr r5, =handle_arch_irq + ldr r1, =handle_arch_irq mov r0, sp - ldr r5, [r5] adr lr, BSYM(9997f) - teq r5, #0 - movne pc, r5 -#endif + ldr pc, [r1] +#else arch_irq_handler_default +#endif 9997: .endm + .macro pabt_helper + @ PABORT handler takes pt_regs in r2, fault address in r4 and psr in r5 +#ifdef MULTI_PABORT + ldr ip, .LCprocfns + mov lr, pc + ldr pc, [ip, #PROCESSOR_PABT_FUNC] +#else + bl CPU_PABORT_HANDLER +#endif + .endm + + .macro dabt_helper + + @ + @ Call the processor-specific abort handler: + @ + @ r2 - pt_regs + @ r4 - aborted context pc + @ r5 - aborted context psr + @ + @ The abort handler must return the aborted address in r0, and + @ the fault status register in r1. r9 must be preserved. + @ +#ifdef MULTI_DABORT + ldr ip, .LCprocfns + mov lr, pc + ldr pc, [ip, #PROCESSOR_DABT_FUNC] +#else + bl CPU_DABORT_HANDLER +#endif + .endm + #ifdef CONFIG_KPROBES .section .kprobes.text,"ax",%progbits #else @@ -126,106 +161,58 @@ ENDPROC(__und_invalid) SPFIX( subeq sp, sp, #4 ) stmia sp, {r1 - r12} - ldmia r0, {r1 - r3} - add r5, sp, #S_SP - 4 @ here for interlock avoidance - mov r4, #-1 @ "" "" "" "" - add r0, sp, #(S_FRAME_SIZE + \stack_hole - 4) - SPFIX( addeq r0, r0, #4 ) - str r1, [sp, #-4]! @ save the "real" r0 copied + ldmia r0, {r3 - r5} + add r7, sp, #S_SP - 4 @ here for interlock avoidance + mov r6, #-1 @ "" "" "" "" + add r2, sp, #(S_FRAME_SIZE + \stack_hole - 4) + SPFIX( addeq r2, r2, #4 ) + str r3, [sp, #-4]! @ save the "real" r0 copied @ from the exception stack - mov r1, lr + mov r3, lr @ @ We are now ready to fill in the remaining blanks on the stack: @ - @ r0 - sp_svc - @ r1 - lr_svc - @ r2 - lr_<exception>, already fixed up for correct return/restart - @ r3 - spsr_<exception> - @ r4 - orig_r0 (see pt_regs definition in ptrace.h) + @ r2 - sp_svc + @ r3 - lr_svc + @ r4 - lr_<exception>, already fixed up for correct return/restart + @ r5 - spsr_<exception> + @ r6 - orig_r0 (see pt_regs definition in ptrace.h) @ - stmia r5, {r0 - r4} + stmia r7, {r2 - r6} + +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif .endm .align 5 __dabt_svc: svc_entry - - @ - @ get ready to re-enable interrupts if appropriate - @ - mrs r9, cpsr - tst r3, #PSR_I_BIT - biceq r9, r9, #PSR_I_BIT - - @ - @ Call the processor-specific abort handler: - @ - @ r2 - aborted context pc - @ r3 - aborted context cpsr - @ - @ The abort handler must return the aborted address in r0, and - @ the fault status register in r1. r9 must be preserved. - @ -#ifdef MULTI_DABORT - ldr r4, .LCprocfns - mov lr, pc - ldr pc, [r4, #PROCESSOR_DABT_FUNC] -#else - bl CPU_DABORT_HANDLER -#endif - - @ - @ set desired IRQ state, then call main handler - @ - debug_entry r1 - msr cpsr_c, r9 mov r2, sp - bl do_DataAbort - - @ - @ IRQs off again before pulling preserved data off the stack - @ - disable_irq_notrace - - @ - @ restore SPSR and restart the instruction - @ - ldr r2, [sp, #S_PSR] - svc_exit r2 @ return from exception + dabt_helper + THUMB( ldr r5, [sp, #S_PSR] ) @ potentially updated CPSR + svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__dabt_svc) .align 5 __irq_svc: svc_entry + irq_handler -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif #ifdef CONFIG_PREEMPT get_thread_info tsk ldr r8, [tsk, #TI_PREEMPT] @ get preempt count - add r7, r8, #1 @ increment it - str r7, [tsk, #TI_PREEMPT] -#endif - - irq_handler -#ifdef CONFIG_PREEMPT - str r8, [tsk, #TI_PREEMPT] @ restore preempt count ldr r0, [tsk, #TI_FLAGS] @ get flags teq r8, #0 @ if preempt count != 0 movne r0, #0 @ force flags to 0 tst r0, #_TIF_NEED_RESCHED blne svc_preempt #endif - ldr r4, [sp, #S_PSR] @ irqs are already disabled -#ifdef CONFIG_TRACE_IRQFLAGS - tst r4, #PSR_I_BIT - bleq trace_hardirqs_on -#endif - svc_exit r4 @ return from exception + + svc_exit r5, irq = 1 @ return from exception UNWIND(.fnend ) ENDPROC(__irq_svc) @@ -241,6 +228,19 @@ svc_preempt: b 1b #endif +__und_fault: + @ Correct the PC such that it is pointing at the instruction + @ which caused the fault. If the faulting instruction was ARM + @ the PC will be pointing at the next instruction, and have to + @ subtract 4. Otherwise, it is Thumb, and the PC will be + @ pointing at the second half of the Thumb instruction. We + @ have to subtract 2. + ldr r2, [r0, #S_PC] + sub r2, r2, r1 + str r2, [r0, #S_PC] + b do_undefinstr +ENDPROC(__und_fault) + .align 5 __und_svc: #ifdef CONFIG_KPROBES @@ -251,7 +251,6 @@ __und_svc: #else svc_entry #endif - @ @ call emulation code, which returns using r9 if it has emulated @ the instruction, or the more conventional lr if we are to treat @@ -259,68 +258,39 @@ __und_svc: @ @ r0 - instruction @ -#ifndef CONFIG_THUMB2_KERNEL - ldr r0, [r2, #-4] +#ifndef CONFIG_THUMB2_KERNEL + ldr r0, [r4, #-4] #else - ldrh r0, [r2, #-2] @ Thumb instruction at LR - 2 - and r9, r0, #0xf800 - cmp r9, #0xe800 @ 32-bit instruction if xx >= 0 - ldrhhs r9, [r2] @ bottom 16 bits - orrhs r0, r9, r0, lsl #16 + mov r1, #2 + ldrh r0, [r4, #-2] @ Thumb instruction at LR - 2 + cmp r0, #0xe800 @ 32-bit instruction if xx >= 0 + blo __und_svc_fault + ldrh r9, [r4] @ bottom 16 bits + add r4, r4, #2 + str r4, [sp, #S_PC] + orr r0, r9, r0, lsl #16 #endif - adr r9, BSYM(1f) + adr r9, BSYM(__und_svc_finish) + mov r2, r4 bl call_fpe + mov r1, #4 @ PC correction to apply +__und_svc_fault: mov r0, sp @ struct pt_regs *regs - bl do_undefinstr + bl __und_fault - @ - @ IRQs off again before pulling preserved data off the stack - @ -1: disable_irq_notrace - - @ - @ restore SPSR and restart the instruction - @ - ldr r2, [sp, #S_PSR] @ Get SVC cpsr - svc_exit r2 @ return from exception +__und_svc_finish: + ldr r5, [sp, #S_PSR] @ Get SVC cpsr + svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__und_svc) .align 5 __pabt_svc: svc_entry - - @ - @ re-enable interrupts if appropriate - @ - mrs r9, cpsr - tst r3, #PSR_I_BIT - biceq r9, r9, #PSR_I_BIT - - mov r0, r2 @ pass address of aborted instruction. -#ifdef MULTI_PABORT - ldr r4, .LCprocfns - mov lr, pc - ldr pc, [r4, #PROCESSOR_PABT_FUNC] -#else - bl CPU_PABORT_HANDLER -#endif - debug_entry r1 - msr cpsr_c, r9 @ Maybe enable interrupts mov r2, sp @ regs - bl do_PrefetchAbort @ call abort handler - - @ - @ IRQs off again before pulling preserved data off the stack - @ - disable_irq_notrace - - @ - @ restore SPSR and restart the instruction - @ - ldr r2, [sp, #S_PSR] - svc_exit r2 @ return from exception + pabt_helper + svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__pabt_svc) @@ -351,39 +321,45 @@ ENDPROC(__pabt_svc) ARM( stmib sp, {r1 - r12} ) THUMB( stmia sp, {r0 - r12} ) - ldmia r0, {r1 - r3} + ldmia r0, {r3 - r5} add r0, sp, #S_PC @ here for interlock avoidance - mov r4, #-1 @ "" "" "" "" + mov r6, #-1 @ "" "" "" "" - str r1, [sp] @ save the "real" r0 copied + str r3, [sp] @ save the "real" r0 copied @ from the exception stack @ @ We are now ready to fill in the remaining blanks on the stack: @ - @ r2 - lr_<exception>, already fixed up for correct return/restart - @ r3 - spsr_<exception> - @ r4 - orig_r0 (see pt_regs definition in ptrace.h) + @ r4 - lr_<exception>, already fixed up for correct return/restart + @ r5 - spsr_<exception> + @ r6 - orig_r0 (see pt_regs definition in ptrace.h) @ @ Also, separately save sp_usr and lr_usr @ - stmia r0, {r2 - r4} + stmia r0, {r4 - r6} ARM( stmdb r0, {sp, lr}^ ) THUMB( store_user_sp_lr r0, r1, S_SP - S_PC ) @ @ Enable the alignment trap while in kernel mode @ - alignment_trap r0 + alignment_trap r0, .LCcralign @ @ Clear FP to mark the first stack frame @ zero_fp + +#ifdef CONFIG_IRQSOFF_TRACER + bl trace_hardirqs_off +#endif + ct_user_exit save = 0 .endm .macro kuser_cmpxchg_check -#if __LINUX_ARM_ARCH__ < 6 && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG) +#if !defined(CONFIG_CPU_32v6K) && defined(CONFIG_KUSER_HELPERS) && \ + !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG) #ifndef CONFIG_MMU #warning "NPTL on non MMU needs fixing" #else @@ -391,8 +367,8 @@ ENDPROC(__pabt_svc) @ if it was interrupted in a critical region. Here we @ perform a quick test inline since it should be false @ 99.9999% of the time. The rest is done out of line. - cmp r2, #TASK_SIZE - blhs kuser_cmpxchg_fixup + cmp r4, #TASK_SIZE + blhs kuser_cmpxchg64_fixup #endif #endif .endm @@ -401,32 +377,9 @@ ENDPROC(__pabt_svc) __dabt_usr: usr_entry kuser_cmpxchg_check - - @ - @ Call the processor-specific abort handler: - @ - @ r2 - aborted context pc - @ r3 - aborted context cpsr - @ - @ The abort handler must return the aborted address in r0, and - @ the fault status register in r1. - @ -#ifdef MULTI_DABORT - ldr r4, .LCprocfns - mov lr, pc - ldr pc, [r4, #PROCESSOR_DABT_FUNC] -#else - bl CPU_DABORT_HANDLER -#endif - - @ - @ IRQs on, then call the main handler - @ - debug_entry r1 - enable_irq mov r2, sp - adr lr, BSYM(ret_from_exception) - b do_DataAbort + dabt_helper + b ret_from_exception UNWIND(.fnend ) ENDPROC(__dabt_usr) @@ -434,26 +387,10 @@ ENDPROC(__dabt_usr) __irq_usr: usr_entry kuser_cmpxchg_check - - get_thread_info tsk -#ifdef CONFIG_PREEMPT - ldr r8, [tsk, #TI_PREEMPT] @ get preempt count - add r7, r8, #1 @ increment it - str r7, [tsk, #TI_PREEMPT] -#endif - irq_handler -#ifdef CONFIG_PREEMPT - ldr r0, [tsk, #TI_PREEMPT] - str r8, [tsk, #TI_PREEMPT] - teq r0, r7 - ARM( strne r0, [r0, -r0] ) - THUMB( movne r0, #0 ) - THUMB( strne r0, [r0] ) -#endif - + get_thread_info tsk mov why, #0 - b ret_to_user + b ret_to_user_from_irq UNWIND(.fnend ) ENDPROC(__irq_usr) @@ -463,55 +400,101 @@ ENDPROC(__irq_usr) __und_usr: usr_entry + mov r2, r4 + mov r3, r5 + + @ r2 = regs->ARM_pc, which is either 2 or 4 bytes ahead of the + @ faulting instruction depending on Thumb mode. + @ r3 = regs->ARM_cpsr @ - @ fall through to the emulation code, which returns using r9 if - @ it has emulated the instruction, or the more conventional lr - @ if we are to treat this as a real undefined instruction - @ - @ r0 - instruction + @ The emulation code returns using r9 if it has emulated the + @ instruction, or the more conventional lr if we are to treat + @ this as a real undefined instruction @ adr r9, BSYM(ret_from_exception) - adr lr, BSYM(__und_usr_unknown) + + @ IRQs must be enabled before attempting to read the instruction from + @ user space since that could cause a page/translation fault if the + @ page table was modified by another CPU. + enable_irq + tst r3, #PSR_T_BIT @ Thumb mode? - itet eq @ explicit IT needed for the 1f label - subeq r4, r2, #4 @ ARM instr at LR - 4 - subne r4, r2, #2 @ Thumb instr at LR - 2 -1: ldreqt r0, [r4] -#ifdef CONFIG_CPU_ENDIAN_BE8 - reveq r0, r0 @ little endian instruction -#endif - beq call_fpe + bne __und_usr_thumb + sub r4, r2, #4 @ ARM instr at LR - 4 +1: ldrt r0, [r4] + ARM_BE8(rev r0, r0) @ little endian instruction + + @ r0 = 32-bit ARM instruction which caused the exception + @ r2 = PC value for the following instruction (:= regs->ARM_pc) + @ r4 = PC value for the faulting instruction + @ lr = 32-bit undefined instruction function + adr lr, BSYM(__und_usr_fault_32) + b call_fpe + +__und_usr_thumb: @ Thumb instruction -#if __LINUX_ARM_ARCH__ >= 7 -2: - ARM( ldrht r5, [r4], #2 ) - THUMB( ldrht r5, [r4] ) - THUMB( add r4, r4, #2 ) - and r0, r5, #0xf800 @ mask bits 111x x... .... .... - cmp r0, #0xe800 @ 32bit instruction if xx != 0 - blo __und_usr_unknown -3: ldrht r0, [r4] + sub r4, r2, #2 @ First half of thumb instr at LR - 2 +#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7 +/* + * Thumb-2 instruction handling. Note that because pre-v6 and >= v6 platforms + * can never be supported in a single kernel, this code is not applicable at + * all when __LINUX_ARM_ARCH__ < 6. This allows simplifying assumptions to be + * made about .arch directives. + */ +#if __LINUX_ARM_ARCH__ < 7 +/* If the target CPU may not be Thumb-2-capable, a run-time check is needed: */ +#define NEED_CPU_ARCHITECTURE + ldr r5, .LCcpu_architecture + ldr r5, [r5] + cmp r5, #CPU_ARCH_ARMv7 + blo __und_usr_fault_16 @ 16bit undefined instruction +/* + * The following code won't get run unless the running CPU really is v7, so + * coding round the lack of ldrht on older arches is pointless. Temporarily + * override the assembler target arch with the minimum required instead: + */ + .arch armv6t2 +#endif +2: ldrht r5, [r4] +ARM_BE8(rev16 r5, r5) @ little endian instruction + cmp r5, #0xe800 @ 32bit instruction if xx != 0 + blo __und_usr_fault_16 @ 16bit undefined instruction +3: ldrht r0, [r2] +ARM_BE8(rev16 r0, r0) @ little endian instruction add r2, r2, #2 @ r2 is PC + 2, make it PC + 4 + str r2, [sp, #S_PC] @ it's a 2x16bit instr, update orr r0, r0, r5, lsl #16 + adr lr, BSYM(__und_usr_fault_32) + @ r0 = the two 16-bit Thumb instructions which caused the exception + @ r2 = PC value for the following Thumb instruction (:= regs->ARM_pc) + @ r4 = PC value for the first 16-bit Thumb instruction + @ lr = 32bit undefined instruction function + +#if __LINUX_ARM_ARCH__ < 7 +/* If the target arch was overridden, change it back: */ +#ifdef CONFIG_CPU_32v6K + .arch armv6k #else - b __und_usr_unknown + .arch armv6 #endif - UNWIND(.fnend ) +#endif /* __LINUX_ARM_ARCH__ < 7 */ +#else /* !(CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7) */ + b __und_usr_fault_16 +#endif + UNWIND(.fnend) ENDPROC(__und_usr) - @ - @ fallthrough to call_fpe - @ - /* - * The out of line fixup for the ldrt above. + * The out of line fixup for the ldrt instructions above. */ .pushsection .fixup, "ax" -4: mov pc, r9 + .align 2 +4: str r4, [sp, #S_PC] @ retry current instruction + mov pc, r9 .popsection .pushsection __ex_table,"a" .long 1b, 4b -#if __LINUX_ARM_ARCH__ >= 7 +#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7 .long 2b, 4b .long 3b, 4b #endif @@ -535,31 +518,32 @@ ENDPROC(__und_usr) * NEON handler code. * * Emulators may wish to make use of the following registers: - * r0 = instruction opcode. - * r2 = PC+4 + * r0 = instruction opcode (32-bit ARM or two 16-bit Thumb) + * r2 = PC value to resume execution after successful emulation * r9 = normal "successful" return address - * r10 = this threads thread_info structure. + * r10 = this threads thread_info structure * lr = unrecognised instruction return address + * IRQs enabled, FIQs enabled. */ @ @ Fall-through from Thumb-2 __und_usr @ #ifdef CONFIG_NEON + get_thread_info r10 @ get current thread adr r6, .LCneon_thumb_opcodes b 2f #endif call_fpe: + get_thread_info r10 @ get current thread #ifdef CONFIG_NEON adr r6, .LCneon_arm_opcodes -2: - ldr r7, [r6], #4 @ mask value - cmp r7, #0 @ end mask? - beq 1f - and r8, r0, r7 +2: ldr r5, [r6], #4 @ mask value ldr r7, [r6], #4 @ opcode bits matching in mask + cmp r5, #0 @ end mask? + beq 1f + and r8, r0, r5 cmp r8, r7 @ NEON instruction? bne 2b - get_thread_info r10 mov r7, #1 strb r7, [r10, #TI_USED_CP + 10] @ mark CP#10 as used strb r7, [r10, #TI_USED_CP + 11] @ mark CP#11 as used @@ -568,12 +552,7 @@ call_fpe: #endif tst r0, #0x08000000 @ only CDP/CPRT/LDC/STC have bit 27 tstne r0, #0x04000000 @ bit 26 set on both ARM and Thumb-2 -#if defined(CONFIG_CPU_ARM610) || defined(CONFIG_CPU_ARM710) - and r8, r0, #0x0f000000 @ mask out op-code bits - teqne r8, #0x0f000000 @ SWI (ARM6/7 bug)? -#endif moveq pc, lr - get_thread_info r10 @ get current thread and r8, r0, #0x00000f00 @ mask out CP number THUMB( lsr r8, r8, #8 ) mov r7, #1 @@ -620,6 +599,12 @@ call_fpe: movw_pc lr @ CP#14 (Debug) movw_pc lr @ CP#15 (Control) +#ifdef NEED_CPU_ARCHITECTURE + .align 2 +.LCcpu_architecture: + .word __cpu_architecture +#endif + #ifdef CONFIG_NEON .align 6 @@ -645,7 +630,6 @@ call_fpe: #endif do_fpe: - enable_irq ldr r4, .LCfp add r10, r10, #TI_FPSTATE @ r10 = workspace ldr pc, [r4] @ Call FP module USR entry point @@ -668,29 +652,22 @@ ENTRY(no_fp) mov pc, lr ENDPROC(no_fp) -__und_usr_unknown: - enable_irq - mov r0, sp +__und_usr_fault_32: + mov r1, #4 + b 1f +__und_usr_fault_16: + mov r1, #2 +1: mov r0, sp adr lr, BSYM(ret_from_exception) - b do_undefinstr -ENDPROC(__und_usr_unknown) + b __und_fault +ENDPROC(__und_usr_fault_32) +ENDPROC(__und_usr_fault_16) .align 5 __pabt_usr: usr_entry - - mov r0, r2 @ pass address of aborted instruction. -#ifdef MULTI_PABORT - ldr r4, .LCprocfns - mov lr, pc - ldr pc, [r4, #PROCESSOR_PABT_FUNC] -#else - bl CPU_PABORT_HANDLER -#endif - debug_entry r1 - enable_irq @ Enable interrupts mov r2, sp @ regs - bl do_PrefetchAbort @ call abort handler + pabt_helper UNWIND(.fnend ) /* fall through */ /* @@ -715,15 +692,16 @@ ENTRY(__switch_to) 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 @@ -754,31 +732,12 @@ ENDPROC(__switch_to) /* * User helpers. * - * These are segment of kernel provided user code reachable from user space - * at a fixed address in kernel memory. This is used to provide user space - * with some operations which require kernel help because of unimplemented - * native feature and/or instructions in many ARM CPUs. The idea is for - * this code to be executed directly in user mode for best efficiency but - * which is too intimate with the kernel counter part to be left to user - * libraries. In fact this code might even differ from one CPU to another - * depending on the available instruction set and restrictions like on - * SMP systems. In other words, the kernel reserves the right to change - * this code as needed without warning. Only the entry points and their - * results are guaranteed to be stable. - * * Each segment is 32-byte aligned and will be moved to the top of the high * vector page. New segments (if ever needed) must be added in front of * existing ones. This mechanism should be used only for things that are * really small and justified, and not be abused freely. * - * User space is expected to implement those things inline when optimizing - * for a processor that has the necessary native support, but only if such - * resulting binaries are already to be incompatible with earlier ARM - * processors due to the use of unsupported instructions other than what - * is provided here. In other words don't make binaries unable to run on - * earlier processors just for the sake of not using these kernel helpers - * if your compiled code is not going to use the new instructions for other - * purpose. + * See Documentation/arm/kernel_user_helpers.txt for formal definitions. */ THUMB( .arm ) @@ -790,101 +749,115 @@ ENDPROC(__switch_to) #endif .endm + .macro kuser_pad, sym, size + .if (. - \sym) & 3 + .rept 4 - (. - \sym) & 3 + .byte 0 + .endr + .endif + .rept (\size - (. - \sym)) / 4 + .word 0xe7fddef1 + .endr + .endm + +#ifdef CONFIG_KUSER_HELPERS .align 5 .globl __kuser_helper_start __kuser_helper_start: /* - * Reference prototype: - * - * void __kernel_memory_barrier(void) - * - * Input: - * - * lr = return address - * - * Output: - * - * none - * - * Clobbered: - * - * none - * - * Definition and user space usage example: - * - * typedef void (__kernel_dmb_t)(void); - * #define __kernel_dmb (*(__kernel_dmb_t *)0xffff0fa0) - * - * Apply any needed memory barrier to preserve consistency with data modified - * manually and __kuser_cmpxchg usage. - * - * This could be used as follows: - * - * #define __kernel_dmb() \ - * asm volatile ( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #95" \ - * : : : "r0", "lr","cc" ) + * Due to the length of some sequences, __kuser_cmpxchg64 spans 2 regular + * kuser "slots", therefore 0xffff0f80 is not used as a valid entry point. */ -__kuser_memory_barrier: @ 0xffff0fa0 +__kuser_cmpxchg64: @ 0xffff0f60 + +#if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG) + + /* + * Poor you. No fast solution possible... + * The kernel itself must perform the operation. + * A special ghost syscall is used for that (see traps.c). + */ + stmfd sp!, {r7, lr} + ldr r7, 1f @ it's 20 bits + swi __ARM_NR_cmpxchg64 + ldmfd sp!, {r7, pc} +1: .word __ARM_NR_cmpxchg64 + +#elif defined(CONFIG_CPU_32v6K) + + stmfd sp!, {r4, r5, r6, r7} + ldrd r4, r5, [r0] @ load old val + ldrd r6, r7, [r1] @ load new val + smp_dmb arm +1: ldrexd r0, r1, [r2] @ load current val + eors r3, r0, r4 @ compare with oldval (1) + eoreqs r3, r1, r5 @ compare with oldval (2) + strexdeq r3, r6, r7, [r2] @ store newval if eq + teqeq r3, #1 @ success? + beq 1b @ if no then retry smp_dmb arm + rsbs r0, r3, #0 @ set returned val and C flag + ldmfd sp!, {r4, r5, r6, r7} usr_ret lr - .align 5 +#elif !defined(CONFIG_SMP) -/* - * Reference prototype: - * - * int __kernel_cmpxchg(int oldval, int newval, int *ptr) - * - * Input: - * - * r0 = oldval - * r1 = newval - * r2 = ptr - * lr = return address - * - * Output: - * - * r0 = returned value (zero or non-zero) - * C flag = set if r0 == 0, clear if r0 != 0 - * - * Clobbered: - * - * r3, ip, flags - * - * Definition and user space usage example: - * - * typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); - * #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) - * - * Atomically store newval in *ptr if *ptr is equal to oldval for user space. - * Return zero if *ptr was changed or non-zero if no exchange happened. - * The C flag is also set if *ptr was changed to allow for assembly - * optimization in the calling code. - * - * Notes: - * - * - This routine already includes memory barriers as needed. - * - * For example, a user space atomic_add implementation could look like this: - * - * #define atomic_add(ptr, val) \ - * ({ register unsigned int *__ptr asm("r2") = (ptr); \ - * register unsigned int __result asm("r1"); \ - * asm volatile ( \ - * "1: @ atomic_add\n\t" \ - * "ldr r0, [r2]\n\t" \ - * "mov r3, #0xffff0fff\n\t" \ - * "add lr, pc, #4\n\t" \ - * "add r1, r0, %2\n\t" \ - * "add pc, r3, #(0xffff0fc0 - 0xffff0fff)\n\t" \ - * "bcc 1b" \ - * : "=&r" (__result) \ - * : "r" (__ptr), "rIL" (val) \ - * : "r0","r3","ip","lr","cc","memory" ); \ - * __result; }) - */ +#ifdef CONFIG_MMU + + /* + * The only thing that can break atomicity in this cmpxchg64 + * implementation is either an IRQ or a data abort exception + * causing another process/thread to be scheduled in the middle of + * the critical sequence. The same strategy as for cmpxchg is used. + */ + stmfd sp!, {r4, r5, r6, lr} + ldmia r0, {r4, r5} @ load old val + ldmia r1, {r6, lr} @ load new val +1: ldmia r2, {r0, r1} @ load current val + eors r3, r0, r4 @ compare with oldval (1) + eoreqs r3, r1, r5 @ compare with oldval (2) +2: stmeqia r2, {r6, lr} @ store newval if eq + rsbs r0, r3, #0 @ set return val and C flag + ldmfd sp!, {r4, r5, r6, pc} + + .text +kuser_cmpxchg64_fixup: + @ Called from kuser_cmpxchg_fixup. + @ r4 = address of interrupted insn (must be preserved). + @ sp = saved regs. r7 and r8 are clobbered. + @ 1b = first critical insn, 2b = last critical insn. + @ If r4 >= 1b and r4 <= 2b then saved pc_usr is set to 1b. + mov r7, #0xffff0fff + sub r7, r7, #(0xffff0fff - (0xffff0f60 + (1b - __kuser_cmpxchg64))) + subs r8, r4, r7 + rsbcss r8, r8, #(2b - 1b) + strcs r7, [sp, #S_PC] +#if __LINUX_ARM_ARCH__ < 6 + bcc kuser_cmpxchg32_fixup +#endif + mov pc, lr + .previous + +#else +#warning "NPTL on non MMU needs fixing" + mov r0, #-1 + adds r0, r0, #0 + usr_ret lr +#endif + +#else +#error "incoherent kernel configuration" +#endif + + kuser_pad __kuser_cmpxchg64, 64 + +__kuser_memory_barrier: @ 0xffff0fa0 + smp_dmb arm + usr_ret lr + + kuser_pad __kuser_memory_barrier, 32 __kuser_cmpxchg: @ 0xffff0fc0 @@ -921,15 +894,15 @@ __kuser_cmpxchg: @ 0xffff0fc0 usr_ret lr .text -kuser_cmpxchg_fixup: +kuser_cmpxchg32_fixup: @ Called from kuser_cmpxchg_check macro. - @ r2 = address of interrupted insn (must be preserved). + @ r4 = address of interrupted insn (must be preserved). @ sp = saved regs. r7 and r8 are clobbered. @ 1b = first critical insn, 2b = last critical insn. - @ If r2 >= 1b and r2 <= 2b then saved pc_usr is set to 1b. + @ If r4 >= 1b and r4 <= 2b then saved pc_usr is set to 1b. mov r7, #0xffff0fff sub r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg))) - subs r8, r2, r7 + subs r8, r4, r7 rsbcss r8, r8, #(2b - 1b) strcs r7, [sp, #S_PC] mov pc, lr @@ -957,76 +930,33 @@ kuser_cmpxchg_fixup: #endif - .align 5 - -/* - * Reference prototype: - * - * int __kernel_get_tls(void) - * - * Input: - * - * lr = return address - * - * Output: - * - * r0 = TLS value - * - * Clobbered: - * - * none - * - * Definition and user space usage example: - * - * typedef int (__kernel_get_tls_t)(void); - * #define __kernel_get_tls (*(__kernel_get_tls_t *)0xffff0fe0) - * - * Get the TLS value as previously set via the __ARM_NR_set_tls syscall. - * - * This could be used as follows: - * - * #define __kernel_get_tls() \ - * ({ register unsigned int __val asm("r0"); \ - * asm( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #31" \ - * : "=r" (__val) : : "lr","cc" ); \ - * __val; }) - */ + kuser_pad __kuser_cmpxchg, 32 __kuser_get_tls: @ 0xffff0fe0 ldr r0, [pc, #(16 - 8)] @ read TLS, set in kuser_get_tls_init usr_ret lr mrc p15, 0, r0, c13, c0, 3 @ 0xffff0fe8 hardware TLS code - .rep 4 + kuser_pad __kuser_get_tls, 16 + .rep 3 .word 0 @ 0xffff0ff0 software TLS value, then .endr @ pad up to __kuser_helper_version -/* - * Reference declaration: - * - * extern unsigned int __kernel_helper_version; - * - * Definition and user space usage example: - * - * #define __kernel_helper_version (*(unsigned int *)0xffff0ffc) - * - * User space may read this to determine the curent number of helpers - * available. - */ - __kuser_helper_version: @ 0xffff0ffc .word ((__kuser_helper_end - __kuser_helper_start) >> 5) .globl __kuser_helper_end __kuser_helper_end: +#endif + THUMB( .thumb ) /* * Vector stubs. * - * This code is copied to 0xffff0200 so we can use branches in the - * vectors, rather than ldr's. Note that this code must not - * exceed 0x300 bytes. + * This code is copied to 0xffff1000 so we can use branches in the + * vectors, rather than ldr's. Note that this code must not exceed + * a page size. * * Common stub entry macro: * Enter in IRQ mode, spsr = SVC/USR CPSR, lr = SVC/USR PC @@ -1073,8 +1003,17 @@ ENDPROC(vector_\name) 1: .endm - .globl __stubs_start + .section .stubs, "ax", %progbits __stubs_start: + @ This must be the first word + .word vector_swi + +vector_rst: + ARM( swi SYS_ERROR0 ) + THUMB( svc #0 ) + THUMB( nop ) + b vector_und + /* * Interrupt dispatcher */ @@ -1169,6 +1108,16 @@ __stubs_start: .align 5 /*============================================================================= + * Address exception handler + *----------------------------------------------------------------------------- + * These aren't too critical. + * (they're not supposed to happen, and won't happen in 32-bit data mode). + */ + +vector_addrexcptn: + b vector_addrexcptn + +/*============================================================================= * Undefined FIQs *----------------------------------------------------------------------------- * Enter in FIQ mode, spsr = ANY CPSR, lr = ANY PC @@ -1179,57 +1128,27 @@ __stubs_start: * get out of that mode without clobbering one register. */ vector_fiq: - disable_fiq subs pc, lr, #4 -/*============================================================================= - * Address exception handler - *----------------------------------------------------------------------------- - * These aren't too critical. - * (they're not supposed to happen, and won't happen in 32-bit data mode). - */ - -vector_addrexcptn: - b vector_addrexcptn - -/* - * We group all the following data together to optimise - * for CPUs with separate I & D caches. - */ - .align 5 + .globl vector_fiq_offset + .equ vector_fiq_offset, vector_fiq -.LCvswi: - .word vector_swi - - .globl __stubs_end -__stubs_end: - - .equ stubs_offset, __vectors_start + 0x200 - __stubs_start - - .globl __vectors_start + .section .vectors, "ax", %progbits __vectors_start: - ARM( swi SYS_ERROR0 ) - THUMB( svc #0 ) - THUMB( nop ) - W(b) vector_und + stubs_offset - W(ldr) pc, .LCvswi + stubs_offset - W(b) vector_pabt + stubs_offset - W(b) vector_dabt + stubs_offset - W(b) vector_addrexcptn + stubs_offset - W(b) vector_irq + stubs_offset - W(b) vector_fiq + stubs_offset - - .globl __vectors_end -__vectors_end: + W(b) vector_rst + W(b) vector_und + W(ldr) pc, __vectors_start + 0x1000 + W(b) vector_pabt + W(b) vector_dabt + W(b) vector_addrexcptn + W(b) vector_irq + W(b) vector_fiq .data .globl cr_alignment - .globl cr_no_alignment cr_alignment: .space 4 -cr_no_alignment: - .space 4 #ifdef CONFIG_MULTI_IRQ_HANDLER .globl handle_arch_irq |