diff options
Diffstat (limited to '')
| -rw-r--r-- | arch/arm/kernel/entry-armv.S | 359 |
1 files changed, 238 insertions, 121 deletions
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 77f54830554c..c39303e5c234 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -19,40 +19,50 @@ #include <asm/glue-df.h> #include <asm/glue-pf.h> #include <asm/vfpmacros.h> -#ifndef CONFIG_GENERIC_IRQ_MULTI_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 <asm/uaccess-asm.h> #include "entry-header.S" -#include <asm/entry-macro-multi.S> #include <asm/probes.h> /* * Interrupt handling. */ - .macro irq_handler -#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER - ldr r1, =handle_arch_irq - mov r0, sp - badr lr, 9997f - ldr pc, [r1] -#else - arch_irq_handler_default + .macro irq_handler, from_user:req + mov r1, sp + ldr_this_cpu r2, irq_stack_ptr, r2, r3 + .if \from_user == 0 + @ + @ If we took the interrupt while running in the kernel, we may already + @ be using the IRQ stack, so revert to the original value in that case. + @ + subs r3, r2, r1 @ SP above bottom of IRQ stack? + rsbscs r3, r3, #THREAD_SIZE @ ... and below the top? +#ifdef CONFIG_VMAP_STACK + ldr_va r3, high_memory, cc @ End of the linear region + cmpcc r3, r1 @ Stack pointer was below it? #endif -9997: + bcc 0f @ If not, switch to the IRQ stack + mov r0, r1 + bl generic_handle_arch_irq + b 1f +0: + .endif + + mov_l r0, generic_handle_arch_irq + bl call_with_stack +1: .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] + ldr_va ip, processor, offset=PROCESSOR_PABT_FUNC + bl_r ip #else bl CPU_PABORT_HANDLER #endif @@ -71,9 +81,8 @@ @ 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] + ldr_va ip, processor, offset=PROCESSOR_DABT_FUNC + bl_r ip #else bl CPU_DABORT_HANDLER #endif @@ -142,27 +151,35 @@ ENDPROC(__und_invalid) #define SPFIX(code...) #endif - .macro svc_entry, stack_hole=0, trace=1, uaccess=1 + .macro svc_entry, stack_hole=0, trace=1, uaccess=1, overflow_check=1 UNWIND(.fnstart ) - UNWIND(.save {r0 - pc} ) - sub sp, sp, #(SVC_REGS_SIZE + \stack_hole - 4) + sub sp, sp, #(SVC_REGS_SIZE + \stack_hole) + THUMB( add sp, r1 ) @ get SP in a GPR without + THUMB( sub r1, sp, r1 ) @ using a temp register + + .if \overflow_check + UNWIND(.save {r0 - pc} ) + do_overflow_check (SVC_REGS_SIZE + \stack_hole) + .endif + #ifdef CONFIG_THUMB2_KERNEL - SPFIX( str r0, [sp] ) @ temporarily saved - SPFIX( mov r0, sp ) - SPFIX( tst r0, #4 ) @ test original stack alignment - SPFIX( ldr r0, [sp] ) @ restored + tst r1, #4 @ test stack pointer alignment + sub r1, sp, r1 @ restore original R1 + sub sp, r1 @ restore original SP #else SPFIX( tst sp, #4 ) #endif - SPFIX( subeq sp, sp, #4 ) - stmia sp, {r1 - r12} + SPFIX( subne sp, sp, #4 ) + + ARM( stmib sp, {r1 - r12} ) + THUMB( stmia sp, {r0 - r12} ) @ No STMIB in Thumb-2 ldmia r0, {r3 - r5} - add r7, sp, #S_SP - 4 @ here for interlock avoidance + add r7, sp, #S_SP @ here for interlock avoidance mov r6, #-1 @ "" "" "" "" - add r2, sp, #(SVC_REGS_SIZE + \stack_hole - 4) - SPFIX( addeq r2, r2, #4 ) - str r3, [sp, #-4]! @ save the "real" r0 copied + add r2, sp, #(SVC_REGS_SIZE + \stack_hole) + SPFIX( addne r2, r2, #4 ) + str r3, [sp] @ save the "real" r0 copied @ from the exception stack mov r3, lr @@ -179,15 +196,7 @@ ENDPROC(__und_invalid) stmia r7, {r2 - r6} get_thread_info tsk - ldr r0, [tsk, #TI_ADDR_LIMIT] - mov r1, #TASK_SIZE - str r1, [tsk, #TI_ADDR_LIMIT] - str r0, [sp, #SVC_ADDR_LIMIT] - - uaccess_save r0 - .if \uaccess - uaccess_disable r0 - .endif + uaccess_entry tsk, r0, r1, r2, \uaccess .if \trace #ifdef CONFIG_TRACE_IRQFLAGS @@ -209,7 +218,7 @@ ENDPROC(__dabt_svc) .align 5 __irq_svc: svc_entry - irq_handler + irq_handler from_user=0 #ifdef CONFIG_PREEMPTION ldr r8, [tsk, #TI_PREEMPT] @ get preempt count @@ -259,31 +268,10 @@ __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 - @ this as a real undefined instruction - @ - @ r0 - instruction - @ -#ifndef CONFIG_THUMB2_KERNEL - ldr r0, [r4, #-4] -#else - 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 - badr r9, __und_svc_finish - mov r2, r4 - bl call_fpe mov r1, #4 @ PC correction to apply -__und_svc_fault: + THUMB( tst r5, #PSR_T_BIT ) @ exception taken in Thumb mode? + THUMB( movne r1, #2 ) @ if so, fix up PC correction mov r0, sp @ struct pt_regs *regs bl __und_fault @@ -312,16 +300,6 @@ __fiq_svc: UNWIND(.fnend ) ENDPROC(__fiq_svc) - .align 5 -.LCcralign: - .word cr_alignment -#ifdef MULTI_DABORT -.LCprocfns: - .word processor -#endif -.LCfp: - .word fp_enter - /* * Abort mode handlers */ @@ -380,7 +358,7 @@ ENDPROC(__fiq_abt) THUMB( stmia sp, {r0 - r12} ) ATRAP( mrc p15, 0, r7, c1, c0, 0) - ATRAP( ldr r8, .LCcralign) + ATRAP( ldr_va r8, cr_alignment) ldmia r0, {r3 - r5} add r0, sp, #S_PC @ here for interlock avoidance @@ -389,8 +367,6 @@ ENDPROC(__fiq_abt) str r3, [sp] @ save the "real" r0 copied @ from the exception stack - ATRAP( ldr r8, [r8, #0]) - @ @ We are now ready to fill in the remaining blanks on the stack: @ @@ -412,6 +388,8 @@ ENDPROC(__fiq_abt) ATRAP( teq r8, r7) ATRAP( mcrne p15, 0, r8, c1, c0, 0) + reload_current r7, r8 + @ @ Clear FP to mark the first stack frame @ @@ -434,7 +412,8 @@ ENDPROC(__fiq_abt) @ 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 r4, #TASK_SIZE + ldr r0, =TASK_SIZE + cmp r4, r0 blhs kuser_cmpxchg64_fixup #endif #endif @@ -454,7 +433,7 @@ ENDPROC(__dabt_usr) __irq_usr: usr_entry kuser_cmpxchg_check - irq_handler + irq_handler from_user=1 get_thread_info tsk mov why, #0 b ret_to_user_from_irq @@ -512,9 +491,7 @@ __und_usr_thumb: */ #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] + ldr_va r5, cpu_architecture cmp r5, #CPU_ARCH_ARMv7 blo __und_usr_fault_16 @ 16bit undefined instruction /* @@ -624,11 +601,9 @@ call_fpe: tstne r0, #0x04000000 @ bit 26 set on both ARM and Thumb-2 reteq lr and r8, r0, #0x00000f00 @ mask out CP number - THUMB( lsr r8, r8, #8 ) mov r7, #1 - add r6, r10, #TI_USED_CP - ARM( strb r7, [r6, r8, lsr #8] ) @ set appropriate used_cp[] - THUMB( strb r7, [r6, r8] ) @ set appropriate used_cp[] + add r6, r10, r8, lsr #8 @ add used_cp[] array offset first + strb r7, [r6, #TI_USED_CP] @ set appropriate used_cp[] #ifdef CONFIG_IWMMXT @ Test if we need to give access to iWMMXt coprocessors ldr r5, [r10, #TI_FLAGS] @@ -637,7 +612,7 @@ call_fpe: bcs iwmmxt_task_enable #endif ARM( add pc, pc, r8, lsr #6 ) - THUMB( lsl r8, r8, #2 ) + THUMB( lsr r8, r8, #6 ) THUMB( add pc, r8 ) nop @@ -645,15 +620,9 @@ call_fpe: W(b) do_fpe @ CP#1 (FPE) W(b) do_fpe @ CP#2 (FPE) ret.w lr @ CP#3 -#ifdef CONFIG_CRUNCH - b crunch_task_enable @ CP#4 (MaverickCrunch) - b crunch_task_enable @ CP#5 (MaverickCrunch) - b crunch_task_enable @ CP#6 (MaverickCrunch) -#else ret.w lr @ CP#4 ret.w lr @ CP#5 ret.w lr @ CP#6 -#endif ret.w lr @ CP#7 ret.w lr @ CP#8 ret.w lr @ CP#9 @@ -669,12 +638,6 @@ call_fpe: ret.w lr @ CP#14 (Debug) ret.w lr @ CP#15 (Control) -#ifdef NEED_CPU_ARCHITECTURE - .align 2 -.LCcpu_architecture: - .word __cpu_architecture -#endif - #ifdef CONFIG_NEON .align 6 @@ -700,9 +663,8 @@ call_fpe: #endif do_fpe: - ldr r4, .LCfp add r10, r10, #TI_FPSTATE @ r10 = workspace - ldr pc, [r4] @ Call FP module USR entry point + ldr_va pc, fp_enter, tmp=r4 @ Call FP module USR entry point /* * The FP module is called with these registers set: @@ -788,14 +750,17 @@ ENTRY(__switch_to) ldr r6, [r2, #TI_CPU_DOMAIN] #endif switch_tls r1, r4, r5, r3, r7 -#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) - ldr r7, [r2, #TI_TASK] +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) && \ + !defined(CONFIG_STACKPROTECTOR_PER_TASK) ldr r8, =__stack_chk_guard .if (TSK_STACK_CANARY > IMM12_MASK) - add r7, r7, #TSK_STACK_CANARY & ~IMM12_MASK + add r9, r2, #TSK_STACK_CANARY & ~IMM12_MASK + ldr r9, [r9, #TSK_STACK_CANARY & IMM12_MASK] + .else + ldr r9, [r2, #TSK_STACK_CANARY & IMM12_MASK] .endif - ldr r7, [r7, #TSK_STACK_CANARY & IMM12_MASK] #endif + mov r7, r2 @ Preserve 'next' #ifdef CONFIG_CPU_USE_DOMAINS mcr p15, 0, r6, c3, c0, 0 @ Set domain register #endif @@ -804,18 +769,102 @@ ENTRY(__switch_to) ldr r0, =thread_notify_head mov r1, #THREAD_NOTIFY_SWITCH bl atomic_notifier_call_chain -#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) - str r7, [r8] +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) && \ + !defined(CONFIG_STACKPROTECTOR_PER_TASK) + str r9, [r8] #endif - THUMB( mov ip, r4 ) mov r0, r5 - ARM( ldmia r4, {r4 - sl, fp, sp, pc} ) @ Load all regs saved previously - THUMB( ldmia ip!, {r4 - sl, fp} ) @ Load all regs saved previously - THUMB( ldr sp, [ip], #4 ) - THUMB( ldr pc, [ip] ) +#if !defined(CONFIG_THUMB2_KERNEL) && !defined(CONFIG_VMAP_STACK) + set_current r7, r8 + ldmia r4, {r4 - sl, fp, sp, pc} @ Load all regs saved previously +#else + mov r1, r7 + ldmia r4, {r4 - sl, fp, ip, lr} @ Load all regs saved previously +#ifdef CONFIG_VMAP_STACK + @ + @ Do a dummy read from the new stack while running from the old one so + @ that we can rely on do_translation_fault() to fix up any stale PMD + @ entries covering the vmalloc region. + @ + ldr r2, [ip] +#endif + + @ When CONFIG_THREAD_INFO_IN_TASK=n, the update of SP itself is what + @ effectuates the task switch, as that is what causes the observable + @ values of current and current_thread_info to change. When + @ CONFIG_THREAD_INFO_IN_TASK=y, setting current (and therefore + @ current_thread_info) is done explicitly, and the update of SP just + @ switches us to another stack, with few other side effects. In order + @ to prevent this distinction from causing any inconsistencies, let's + @ keep the 'set_current' call as close as we can to the update of SP. + set_current r1, r2 + mov sp, ip + ret lr +#endif UNWIND(.fnend ) ENDPROC(__switch_to) +#ifdef CONFIG_VMAP_STACK + .text + .align 2 +__bad_stack: + @ + @ We've just detected an overflow. We need to load the address of this + @ CPU's overflow stack into the stack pointer register. We have only one + @ scratch register so let's use a sequence of ADDs including one + @ involving the PC, and decorate them with PC-relative group + @ relocations. As these are ARM only, switch to ARM mode first. + @ + @ We enter here with IP clobbered and its value stashed on the mode + @ stack. + @ +THUMB( bx pc ) +THUMB( nop ) +THUMB( .arm ) + ldr_this_cpu_armv6 ip, overflow_stack_ptr + + str sp, [ip, #-4]! @ Preserve original SP value + mov sp, ip @ Switch to overflow stack + pop {ip} @ Original SP in IP + +#if defined(CONFIG_UNWINDER_FRAME_POINTER) && defined(CONFIG_CC_IS_GCC) + mov ip, ip @ mov expected by unwinder + push {fp, ip, lr, pc} @ GCC flavor frame record +#else + str ip, [sp, #-8]! @ store original SP + push {fpreg, lr} @ Clang flavor frame record +#endif +UNWIND( ldr ip, [r0, #4] ) @ load exception LR +UNWIND( str ip, [sp, #12] ) @ store in the frame record + ldr ip, [r0, #12] @ reload IP + + @ Store the original GPRs to the new stack. + svc_entry uaccess=0, overflow_check=0 + +UNWIND( .save {sp, pc} ) +UNWIND( .save {fpreg, lr} ) +UNWIND( .setfp fpreg, sp ) + + ldr fpreg, [sp, #S_SP] @ Add our frame record + @ to the linked list +#if defined(CONFIG_UNWINDER_FRAME_POINTER) && defined(CONFIG_CC_IS_GCC) + ldr r1, [fp, #4] @ reload SP at entry + add fp, fp, #12 +#else + ldr r1, [fpreg, #8] +#endif + str r1, [sp, #S_SP] @ store in pt_regs + + @ Stash the regs for handle_bad_stack + mov r0, sp + + @ Time to die + bl handle_bad_stack + nop +UNWIND( .fnend ) +ENDPROC(__bad_stack) +#endif + __INIT /* @@ -1029,17 +1078,23 @@ __kuser_helper_end: */ .macro vector_stub, name, mode, correction=0 .align 5 +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +vector_bhb_bpiall_\name: + mcr p15, 0, r0, c7, c5, 6 @ BPIALL + @ isb not needed due to "movs pc, lr" in the vector stub + @ which gives a "context synchronisation". +#endif vector_\name: .if \correction sub lr, lr, #\correction .endif - @ - @ Save r0, lr_<exception> (parent PC) and spsr_<exception> - @ (parent CPSR) - @ + @ Save r0, lr_<exception> (parent PC) stmia sp, {r0, lr} @ save r0, lr + + @ Save spsr_<exception> (parent CPSR) +.Lvec_\name: mrs lr, spsr str lr, [sp, #8] @ save spsr @@ -1061,14 +1116,47 @@ vector_\name: movs pc, lr @ branch to handler in SVC mode ENDPROC(vector_\name) +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .subsection 1 + .align 5 +vector_bhb_loop8_\name: + .if \correction + sub lr, lr, #\correction + .endif + + @ Save r0, lr_<exception> (parent PC) + stmia sp, {r0, lr} + + @ bhb workaround + mov r0, #8 +3: W(b) . + 4 + subs r0, r0, #1 + bne 3b + dsb nsh + @ isb not needed due to "movs pc, lr" in the vector stub + @ which gives a "context synchronisation". + b .Lvec_\name +ENDPROC(vector_bhb_loop8_\name) + .previous +#endif + .align 2 @ handler addresses follow this label 1: .endm .section .stubs, "ax", %progbits - @ This must be the first word + @ These need to remain at the start of the section so that + @ they are in range of the 'SWI' entries in the vector tables + @ located 4k down. +.L__vector_swi: .word vector_swi +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +.L__vector_bhb_loop8_swi: + .word vector_bhb_loop8_swi +.L__vector_bhb_bpiall_swi: + .word vector_bhb_bpiall_swi +#endif vector_rst: ARM( swi SYS_ERROR0 ) @@ -1183,8 +1271,10 @@ vector_addrexcptn: * FIQ "NMI" handler *----------------------------------------------------------------------------- * Handle a FIQ using the SVC stack allowing FIQ act like NMI on x86 - * systems. + * systems. This must be the last vector stub, so lets place it in its own + * subsection. */ + .subsection 2 vector_stub fiq, FIQ_MODE, 4 .long __fiq_usr @ 0 (USR_26 / USR_32) @@ -1207,16 +1297,43 @@ vector_addrexcptn: .globl vector_fiq .section .vectors, "ax", %progbits -.L__vectors_start: W(b) vector_rst W(b) vector_und - W(ldr) pc, .L__vectors_start + 0x1000 +ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_swi ) +THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_swi ) + W(ldr) pc, . W(b) vector_pabt W(b) vector_dabt W(b) vector_addrexcptn W(b) vector_irq W(b) vector_fiq +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .section .vectors.bhb.loop8, "ax", %progbits + W(b) vector_rst + W(b) vector_bhb_loop8_und +ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_bhb_loop8_swi ) +THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_bhb_loop8_swi ) + W(ldr) pc, . + W(b) vector_bhb_loop8_pabt + W(b) vector_bhb_loop8_dabt + W(b) vector_addrexcptn + W(b) vector_bhb_loop8_irq + W(b) vector_bhb_loop8_fiq + + .section .vectors.bhb.bpiall, "ax", %progbits + W(b) vector_rst + W(b) vector_bhb_bpiall_und +ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_bhb_bpiall_swi ) +THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_bhb_bpiall_swi ) + W(ldr) pc, . + W(b) vector_bhb_bpiall_pabt + W(b) vector_bhb_bpiall_dabt + W(b) vector_addrexcptn + W(b) vector_bhb_bpiall_irq + W(b) vector_bhb_bpiall_fiq +#endif + .data .align 2 |