linux/arch/powerpc/kernel/entry_64.S
Cyril Bur 6e669f085d powerpc: Fix unrecoverable SLB miss during restore_math()
Commit 70fe3d9 "powerpc: Restore FPU/VEC/VSX if previously used" introduces a
call to restore_math() late in the syscall return path, after MSR_RI has been
cleared. The MSR_RI flag is used to indicate whether the kernel can take
another exception or not. A cleared MSR_RI flag indicates that the kernel
cannot.

Unfortunately when a machine is under SLB pressure an SLB miss can occur
in restore_math() which (with MSR_RI cleared) leads to an unrecoverable
exception.

  Unrecoverable exception 4100 at c0000000000088d8
  cpu 0x0: Vector: 4100  at [c0000003fa473b20]
      pc: c0000000000088d8: .load_vr_state+0x70/0x110
      lr: c00000000000f710: .restore_math+0x130/0x188
      sp: c0000003fa473da0
     msr: 9000000002003030
    current = 0xc0000007f876f180
    paca    = 0xc00000000fff0000	 softe: 0	 irq_happened: 0x01
      pid   = 1944, comm = K08umountfs
  [link register   ] c00000000000f710 .restore_math+0x130/0x188
  [c0000003fa473da0] c0000003fa473e30 (unreliable)
  [c0000003fa473e30] c000000000007b6c system_call+0x84/0xfc

The clearing of MSR_RI is actually an optimisation to avoid multiple MSR
writes, what must be disabled are interrupts. See comment in entry_64.S:

  /*
   * For performance reasons we clear RI the same time that we
   * clear EE. We only need to clear RI just before we restore r13
   * below, but batching it with EE saves us one expensive mtmsrd call.
   * We have to be careful to restore RI if we branch anywhere from
   * here (eg syscall_exit_work).
   */

At the point of calling restore_math() r13 has not been restored, as such, the
quick fix of turning MSR_RI back on for the call to restore_math() will
eliminate the occurrence of an unrecoverable exception.

We'd like to do a better fix in future.

Fixes: 70fe3d980f ("powerpc: Restore FPU/VEC/VSX if previously used")
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-03-16 15:23:02 +11:00

1445 lines
33 KiB
ArmAsm

/*
* PowerPC version
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
* Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
* Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
* Adapted for Power Macintosh by Paul Mackerras.
* Low-level exception handlers and MMU support
* rewritten by Paul Mackerras.
* Copyright (C) 1996 Paul Mackerras.
* MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
*
* This file contains the system call entry code, context switch
* code, and exception/interrupt return code for PowerPC.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/errno.h>
#include <linux/err.h>
#include <asm/unistd.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/thread_info.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/cputable.h>
#include <asm/firmware.h>
#include <asm/bug.h>
#include <asm/ptrace.h>
#include <asm/irqflags.h>
#include <asm/ftrace.h>
#include <asm/hw_irq.h>
#include <asm/context_tracking.h>
#include <asm/tm.h>
/*
* System calls.
*/
.section ".toc","aw"
SYS_CALL_TABLE:
.tc sys_call_table[TC],sys_call_table
/* This value is used to mark exception frames on the stack. */
exception_marker:
.tc ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER
.section ".text"
.align 7
.globl system_call_common
system_call_common:
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
bne tabort_syscall
END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
andi. r10,r12,MSR_PR
mr r10,r1
addi r1,r1,-INT_FRAME_SIZE
beq- 1f
ld r1,PACAKSAVE(r13)
1: std r10,0(r1)
std r11,_NIP(r1)
std r12,_MSR(r1)
std r0,GPR0(r1)
std r10,GPR1(r1)
beq 2f /* if from kernel mode */
ACCOUNT_CPU_USER_ENTRY(r10, r11)
2: std r2,GPR2(r1)
std r3,GPR3(r1)
mfcr r2
std r4,GPR4(r1)
std r5,GPR5(r1)
std r6,GPR6(r1)
std r7,GPR7(r1)
std r8,GPR8(r1)
li r11,0
std r11,GPR9(r1)
std r11,GPR10(r1)
std r11,GPR11(r1)
std r11,GPR12(r1)
std r11,_XER(r1)
std r11,_CTR(r1)
std r9,GPR13(r1)
mflr r10
/*
* This clears CR0.SO (bit 28), which is the error indication on
* return from this system call.
*/
rldimi r2,r11,28,(63-28)
li r11,0xc01
std r10,_LINK(r1)
std r11,_TRAP(r1)
std r3,ORIG_GPR3(r1)
std r2,_CCR(r1)
ld r2,PACATOC(r13)
addi r9,r1,STACK_FRAME_OVERHEAD
ld r11,exception_marker@toc(r2)
std r11,-16(r9) /* "regshere" marker */
#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR)
BEGIN_FW_FTR_SECTION
beq 33f
/* if from user, see if there are any DTL entries to process */
ld r10,PACALPPACAPTR(r13) /* get ptr to VPA */
ld r11,PACA_DTL_RIDX(r13) /* get log read index */
addi r10,r10,LPPACA_DTLIDX
LDX_BE r10,0,r10 /* get log write index */
cmpd cr1,r11,r10
beq+ cr1,33f
bl accumulate_stolen_time
REST_GPR(0,r1)
REST_4GPRS(3,r1)
REST_2GPRS(7,r1)
addi r9,r1,STACK_FRAME_OVERHEAD
33:
END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE && CONFIG_PPC_SPLPAR */
/*
* A syscall should always be called with interrupts enabled
* so we just unconditionally hard-enable here. When some kind
* of irq tracing is used, we additionally check that condition
* is correct
*/
#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_BUG)
lbz r10,PACASOFTIRQEN(r13)
xori r10,r10,1
1: tdnei r10,0
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
#endif
#ifdef CONFIG_PPC_BOOK3E
wrteei 1
#else
ld r11,PACAKMSR(r13)
ori r11,r11,MSR_EE
mtmsrd r11,1
#endif /* CONFIG_PPC_BOOK3E */
/* We do need to set SOFTE in the stack frame or the return
* from interrupt will be painful
*/
li r10,1
std r10,SOFTE(r1)
CURRENT_THREAD_INFO(r11, r1)
ld r10,TI_FLAGS(r11)
andi. r11,r10,_TIF_SYSCALL_DOTRACE
bne syscall_dotrace /* does not return */
cmpldi 0,r0,NR_syscalls
bge- syscall_enosys
system_call: /* label this so stack traces look sane */
/*
* Need to vector to 32 Bit or default sys_call_table here,
* based on caller's run-mode / personality.
*/
ld r11,SYS_CALL_TABLE@toc(2)
andi. r10,r10,_TIF_32BIT
beq 15f
addi r11,r11,8 /* use 32-bit syscall entries */
clrldi r3,r3,32
clrldi r4,r4,32
clrldi r5,r5,32
clrldi r6,r6,32
clrldi r7,r7,32
clrldi r8,r8,32
15:
slwi r0,r0,4
ldx r12,r11,r0 /* Fetch system call handler [ptr] */
mtctr r12
bctrl /* Call handler */
.Lsyscall_exit:
std r3,RESULT(r1)
CURRENT_THREAD_INFO(r12, r1)
ld r8,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3S
/* No MSR:RI on BookE */
andi. r10,r8,MSR_RI
beq- unrecov_restore
#endif
/*
* Disable interrupts so current_thread_info()->flags can't change,
* and so that we don't get interrupted after loading SRR0/1.
*/
#ifdef CONFIG_PPC_BOOK3E
wrteei 0
#else
ld r10,PACAKMSR(r13)
/*
* For performance reasons we clear RI the same time that we
* clear EE. We only need to clear RI just before we restore r13
* below, but batching it with EE saves us one expensive mtmsrd call.
* We have to be careful to restore RI if we branch anywhere from
* here (eg syscall_exit_work).
*/
li r9,MSR_RI
andc r11,r10,r9
mtmsrd r11,1
#endif /* CONFIG_PPC_BOOK3E */
ld r9,TI_FLAGS(r12)
li r11,-MAX_ERRNO
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
bne- syscall_exit_work
andi. r0,r8,MSR_FP
beq 2f
#ifdef CONFIG_ALTIVEC
andis. r0,r8,MSR_VEC@h
bne 3f
#endif
2: addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_BOOK3S
mtmsrd r10,1 /* Restore RI */
#endif
bl restore_math
#ifdef CONFIG_PPC_BOOK3S
ld r10,PACAKMSR(r13)
li r9,MSR_RI
andc r11,r10,r9 /* Re-clear RI */
mtmsrd r11,1
#endif
ld r8,_MSR(r1)
ld r3,RESULT(r1)
li r11,-MAX_ERRNO
3: cmpld r3,r11
ld r5,_CCR(r1)
bge- syscall_error
.Lsyscall_error_cont:
ld r7,_NIP(r1)
BEGIN_FTR_SECTION
stdcx. r0,0,r1 /* to clear the reservation */
END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
andi. r6,r8,MSR_PR
ld r4,_LINK(r1)
beq- 1f
ACCOUNT_CPU_USER_EXIT(r11, r12)
BEGIN_FTR_SECTION
HMT_MEDIUM_LOW
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
ld r13,GPR13(r1) /* only restore r13 if returning to usermode */
1: ld r2,GPR2(r1)
ld r1,GPR1(r1)
mtlr r4
mtcr r5
mtspr SPRN_SRR0,r7
mtspr SPRN_SRR1,r8
RFI
b . /* prevent speculative execution */
syscall_error:
oris r5,r5,0x1000 /* Set SO bit in CR */
neg r3,r3
std r5,_CCR(r1)
b .Lsyscall_error_cont
/* Traced system call support */
syscall_dotrace:
bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_syscall_trace_enter
/*
* We use the return value of do_syscall_trace_enter() as the syscall
* number. If the syscall was rejected for any reason do_syscall_trace_enter()
* returns an invalid syscall number and the test below against
* NR_syscalls will fail.
*/
mr r0,r3
/* Restore argument registers just clobbered and/or possibly changed. */
ld r3,GPR3(r1)
ld r4,GPR4(r1)
ld r5,GPR5(r1)
ld r6,GPR6(r1)
ld r7,GPR7(r1)
ld r8,GPR8(r1)
/* Repopulate r9 and r10 for the system_call path */
addi r9,r1,STACK_FRAME_OVERHEAD
CURRENT_THREAD_INFO(r10, r1)
ld r10,TI_FLAGS(r10)
cmpldi r0,NR_syscalls
blt+ system_call
/* Return code is already in r3 thanks to do_syscall_trace_enter() */
b .Lsyscall_exit
syscall_enosys:
li r3,-ENOSYS
b .Lsyscall_exit
syscall_exit_work:
#ifdef CONFIG_PPC_BOOK3S
mtmsrd r10,1 /* Restore RI */
#endif
/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
If TIF_NOERROR is set, just save r3 as it is. */
andi. r0,r9,_TIF_RESTOREALL
beq+ 0f
REST_NVGPRS(r1)
b 2f
0: cmpld r3,r11 /* r11 is -MAX_ERRNO */
blt+ 1f
andi. r0,r9,_TIF_NOERROR
bne- 1f
ld r5,_CCR(r1)
neg r3,r3
oris r5,r5,0x1000 /* Set SO bit in CR */
std r5,_CCR(r1)
1: std r3,GPR3(r1)
2: andi. r0,r9,(_TIF_PERSYSCALL_MASK)
beq 4f
/* Clear per-syscall TIF flags if any are set. */
li r11,_TIF_PERSYSCALL_MASK
addi r12,r12,TI_FLAGS
3: ldarx r10,0,r12
andc r10,r10,r11
stdcx. r10,0,r12
bne- 3b
subi r12,r12,TI_FLAGS
4: /* Anything else left to do? */
BEGIN_FTR_SECTION
lis r3,INIT_PPR@highest /* Set thread.ppr = 3 */
ld r10,PACACURRENT(r13)
sldi r3,r3,32 /* bits 11-13 are used for ppr */
std r3,TASKTHREADPPR(r10)
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
beq ret_from_except_lite
/* Re-enable interrupts */
#ifdef CONFIG_PPC_BOOK3E
wrteei 1
#else
ld r10,PACAKMSR(r13)
ori r10,r10,MSR_EE
mtmsrd r10,1
#endif /* CONFIG_PPC_BOOK3E */
bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_syscall_trace_leave
b ret_from_except
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
tabort_syscall:
/* Firstly we need to enable TM in the kernel */
mfmsr r10
li r13, 1
rldimi r10, r13, MSR_TM_LG, 63-MSR_TM_LG
mtmsrd r10, 0
/* tabort, this dooms the transaction, nothing else */
li r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
TABORT(R13)
/*
* Return directly to userspace. We have corrupted user register state,
* but userspace will never see that register state. Execution will
* resume after the tbegin of the aborted transaction with the
* checkpointed register state.
*/
li r13, MSR_RI
andc r10, r10, r13
mtmsrd r10, 1
mtspr SPRN_SRR0, r11
mtspr SPRN_SRR1, r12
rfid
b . /* prevent speculative execution */
#endif
/* Save non-volatile GPRs, if not already saved. */
_GLOBAL(save_nvgprs)
ld r11,_TRAP(r1)
andi. r0,r11,1
beqlr-
SAVE_NVGPRS(r1)
clrrdi r0,r11,1
std r0,_TRAP(r1)
blr
/*
* The sigsuspend and rt_sigsuspend system calls can call do_signal
* and thus put the process into the stopped state where we might
* want to examine its user state with ptrace. Therefore we need
* to save all the nonvolatile registers (r14 - r31) before calling
* the C code. Similarly, fork, vfork and clone need the full
* register state on the stack so that it can be copied to the child.
*/
_GLOBAL(ppc_fork)
bl save_nvgprs
bl sys_fork
b .Lsyscall_exit
_GLOBAL(ppc_vfork)
bl save_nvgprs
bl sys_vfork
b .Lsyscall_exit
_GLOBAL(ppc_clone)
bl save_nvgprs
bl sys_clone
b .Lsyscall_exit
_GLOBAL(ppc32_swapcontext)
bl save_nvgprs
bl compat_sys_swapcontext
b .Lsyscall_exit
_GLOBAL(ppc64_swapcontext)
bl save_nvgprs
bl sys_swapcontext
b .Lsyscall_exit
_GLOBAL(ppc_switch_endian)
bl save_nvgprs
bl sys_switch_endian
b .Lsyscall_exit
_GLOBAL(ret_from_fork)
bl schedule_tail
REST_NVGPRS(r1)
li r3,0
b .Lsyscall_exit
_GLOBAL(ret_from_kernel_thread)
bl schedule_tail
REST_NVGPRS(r1)
mtlr r14
mr r3,r15
#if defined(_CALL_ELF) && _CALL_ELF == 2
mr r12,r14
#endif
blrl
li r3,0
b .Lsyscall_exit
/*
* This routine switches between two different tasks. The process
* state of one is saved on its kernel stack. Then the state
* of the other is restored from its kernel stack. The memory
* management hardware is updated to the second process's state.
* Finally, we can return to the second process, via ret_from_except.
* On entry, r3 points to the THREAD for the current task, r4
* points to the THREAD for the new task.
*
* Note: there are two ways to get to the "going out" portion
* of this code; either by coming in via the entry (_switch)
* or via "fork" which must set up an environment equivalent
* to the "_switch" path. If you change this you'll have to change
* the fork code also.
*
* The code which creates the new task context is in 'copy_thread'
* in arch/powerpc/kernel/process.c
*/
.align 7
_GLOBAL(_switch)
mflr r0
std r0,16(r1)
stdu r1,-SWITCH_FRAME_SIZE(r1)
/* r3-r13 are caller saved -- Cort */
SAVE_8GPRS(14, r1)
SAVE_10GPRS(22, r1)
std r0,_NIP(r1) /* Return to switch caller */
mfcr r23
std r23,_CCR(r1)
std r1,KSP(r3) /* Set old stack pointer */
#ifdef CONFIG_SMP
/* We need a sync somewhere here to make sure that if the
* previous task gets rescheduled on another CPU, it sees all
* stores it has performed on this one.
*/
sync
#endif /* CONFIG_SMP */
/*
* If we optimise away the clear of the reservation in system
* calls because we know the CPU tracks the address of the
* reservation, then we need to clear it here to cover the
* case that the kernel context switch path has no larx
* instructions.
*/
BEGIN_FTR_SECTION
ldarx r6,0,r1
END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS)
#ifdef CONFIG_PPC_BOOK3S
/* Cancel all explict user streams as they will have no use after context
* switch and will stop the HW from creating streams itself
*/
DCBT_STOP_ALL_STREAM_IDS(r6)
#endif
addi r6,r4,-THREAD /* Convert THREAD to 'current' */
std r6,PACACURRENT(r13) /* Set new 'current' */
ld r8,KSP(r4) /* new stack pointer */
#ifdef CONFIG_PPC_BOOK3S
BEGIN_FTR_SECTION
clrrdi r6,r8,28 /* get its ESID */
clrrdi r9,r1,28 /* get current sp ESID */
FTR_SECTION_ELSE
clrrdi r6,r8,40 /* get its 1T ESID */
clrrdi r9,r1,40 /* get current sp 1T ESID */
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_1T_SEGMENT)
clrldi. r0,r6,2 /* is new ESID c00000000? */
cmpd cr1,r6,r9 /* or is new ESID the same as current ESID? */
cror eq,4*cr1+eq,eq
beq 2f /* if yes, don't slbie it */
/* Bolt in the new stack SLB entry */
ld r7,KSP_VSID(r4) /* Get new stack's VSID */
oris r0,r6,(SLB_ESID_V)@h
ori r0,r0,(SLB_NUM_BOLTED-1)@l
BEGIN_FTR_SECTION
li r9,MMU_SEGSIZE_1T /* insert B field */
oris r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h
rldimi r7,r9,SLB_VSID_SSIZE_SHIFT,0
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
/* Update the last bolted SLB. No write barriers are needed
* here, provided we only update the current CPU's SLB shadow
* buffer.
*/
ld r9,PACA_SLBSHADOWPTR(r13)
li r12,0
std r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */
li r12,SLBSHADOW_STACKVSID
STDX_BE r7,r12,r9 /* Save VSID */
li r12,SLBSHADOW_STACKESID
STDX_BE r0,r12,r9 /* Save ESID */
/* No need to check for MMU_FTR_NO_SLBIE_B here, since when
* we have 1TB segments, the only CPUs known to have the errata
* only support less than 1TB of system memory and we'll never
* actually hit this code path.
*/
slbie r6
slbie r6 /* Workaround POWER5 < DD2.1 issue */
slbmte r7,r0
isync
2:
#endif /* !CONFIG_PPC_BOOK3S */
CURRENT_THREAD_INFO(r7, r8) /* base of new stack */
/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
because we don't need to leave the 288-byte ABI gap at the
top of the kernel stack. */
addi r7,r7,THREAD_SIZE-SWITCH_FRAME_SIZE
mr r1,r8 /* start using new stack pointer */
std r7,PACAKSAVE(r13)
ld r6,_CCR(r1)
mtcrf 0xFF,r6
/* r3-r13 are destroyed -- Cort */
REST_8GPRS(14, r1)
REST_10GPRS(22, r1)
/* convert old thread to its task_struct for return value */
addi r3,r3,-THREAD
ld r7,_NIP(r1) /* Return to _switch caller in new task */
mtlr r7
addi r1,r1,SWITCH_FRAME_SIZE
blr
.align 7
_GLOBAL(ret_from_except)
ld r11,_TRAP(r1)
andi. r0,r11,1
bne ret_from_except_lite
REST_NVGPRS(r1)
_GLOBAL(ret_from_except_lite)
/*
* Disable interrupts so that current_thread_info()->flags
* can't change between when we test it and when we return
* from the interrupt.
*/
#ifdef CONFIG_PPC_BOOK3E
wrteei 0
#else
ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */
mtmsrd r10,1 /* Update machine state */
#endif /* CONFIG_PPC_BOOK3E */
CURRENT_THREAD_INFO(r9, r1)
ld r3,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3E
ld r10,PACACURRENT(r13)
#endif /* CONFIG_PPC_BOOK3E */
ld r4,TI_FLAGS(r9)
andi. r3,r3,MSR_PR
beq resume_kernel
#ifdef CONFIG_PPC_BOOK3E
lwz r3,(THREAD+THREAD_DBCR0)(r10)
#endif /* CONFIG_PPC_BOOK3E */
/* Check current_thread_info()->flags */
andi. r0,r4,_TIF_USER_WORK_MASK
bne 1f
#ifdef CONFIG_PPC_BOOK3E
/*
* Check to see if the dbcr0 register is set up to debug.
* Use the internal debug mode bit to do this.
*/
andis. r0,r3,DBCR0_IDM@h
beq restore
mfmsr r0
rlwinm r0,r0,0,~MSR_DE /* Clear MSR.DE */
mtmsr r0
mtspr SPRN_DBCR0,r3
li r10, -1
mtspr SPRN_DBSR,r10
b restore
#else
addi r3,r1,STACK_FRAME_OVERHEAD
bl restore_math
b restore
#endif
1: andi. r0,r4,_TIF_NEED_RESCHED
beq 2f
bl restore_interrupts
SCHEDULE_USER
b ret_from_except_lite
2:
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
andi. r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM
bne 3f /* only restore TM if nothing else to do */
addi r3,r1,STACK_FRAME_OVERHEAD
bl restore_tm_state
b restore
3:
#endif
bl save_nvgprs
/*
* Use a non volatile GPR to save and restore our thread_info flags
* across the call to restore_interrupts.
*/
mr r30,r4
bl restore_interrupts
mr r4,r30
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_notify_resume
b ret_from_except
resume_kernel:
/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
andis. r8,r4,_TIF_EMULATE_STACK_STORE@h
beq+ 1f
addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */
lwz r3,GPR1(r1)
subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */
mr r4,r1 /* src: current exception frame */
mr r1,r3 /* Reroute the trampoline frame to r1 */
/* Copy from the original to the trampoline. */
li r5,INT_FRAME_SIZE/8 /* size: INT_FRAME_SIZE */
li r6,0 /* start offset: 0 */
mtctr r5
2: ldx r0,r6,r4
stdx r0,r6,r3
addi r6,r6,8
bdnz 2b
/* Do real store operation to complete stwu */
lwz r5,GPR1(r1)
std r8,0(r5)
/* Clear _TIF_EMULATE_STACK_STORE flag */
lis r11,_TIF_EMULATE_STACK_STORE@h
addi r5,r9,TI_FLAGS
0: ldarx r4,0,r5
andc r4,r4,r11
stdcx. r4,0,r5
bne- 0b
1:
#ifdef CONFIG_PREEMPT
/* Check if we need to preempt */
andi. r0,r4,_TIF_NEED_RESCHED
beq+ restore
/* Check that preempt_count() == 0 and interrupts are enabled */
lwz r8,TI_PREEMPT(r9)
cmpwi cr1,r8,0
ld r0,SOFTE(r1)
cmpdi r0,0
crandc eq,cr1*4+eq,eq
bne restore
/*
* Here we are preempting the current task. We want to make
* sure we are soft-disabled first and reconcile irq state.
*/
RECONCILE_IRQ_STATE(r3,r4)
1: bl preempt_schedule_irq
/* Re-test flags and eventually loop */
CURRENT_THREAD_INFO(r9, r1)
ld r4,TI_FLAGS(r9)
andi. r0,r4,_TIF_NEED_RESCHED
bne 1b
/*
* arch_local_irq_restore() from preempt_schedule_irq above may
* enable hard interrupt but we really should disable interrupts
* when we return from the interrupt, and so that we don't get
* interrupted after loading SRR0/1.
*/
#ifdef CONFIG_PPC_BOOK3E
wrteei 0
#else
ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */
mtmsrd r10,1 /* Update machine state */
#endif /* CONFIG_PPC_BOOK3E */
#endif /* CONFIG_PREEMPT */
.globl fast_exc_return_irq
fast_exc_return_irq:
restore:
/*
* This is the main kernel exit path. First we check if we
* are about to re-enable interrupts
*/
ld r5,SOFTE(r1)
lbz r6,PACASOFTIRQEN(r13)
cmpwi cr0,r5,0
beq restore_irq_off
/* We are enabling, were we already enabled ? Yes, just return */
cmpwi cr0,r6,1
beq cr0,do_restore
/*
* We are about to soft-enable interrupts (we are hard disabled
* at this point). We check if there's anything that needs to
* be replayed first.
*/
lbz r0,PACAIRQHAPPENED(r13)
cmpwi cr0,r0,0
bne- restore_check_irq_replay
/*
* Get here when nothing happened while soft-disabled, just
* soft-enable and move-on. We will hard-enable as a side
* effect of rfi
*/
restore_no_replay:
TRACE_ENABLE_INTS
li r0,1
stb r0,PACASOFTIRQEN(r13);
/*
* Final return path. BookE is handled in a different file
*/
do_restore:
#ifdef CONFIG_PPC_BOOK3E
b exception_return_book3e
#else
/*
* Clear the reservation. If we know the CPU tracks the address of
* the reservation then we can potentially save some cycles and use
* a larx. On POWER6 and POWER7 this is significantly faster.
*/
BEGIN_FTR_SECTION
stdcx. r0,0,r1 /* to clear the reservation */
FTR_SECTION_ELSE
ldarx r4,0,r1
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
/*
* Some code path such as load_up_fpu or altivec return directly
* here. They run entirely hard disabled and do not alter the
* interrupt state. They also don't use lwarx/stwcx. and thus
* are known not to leave dangling reservations.
*/
.globl fast_exception_return
fast_exception_return:
ld r3,_MSR(r1)
ld r4,_CTR(r1)
ld r0,_LINK(r1)
mtctr r4
mtlr r0
ld r4,_XER(r1)
mtspr SPRN_XER,r4
REST_8GPRS(5, r1)
andi. r0,r3,MSR_RI
beq- unrecov_restore
/* Load PPR from thread struct before we clear MSR:RI */
BEGIN_FTR_SECTION
ld r2,PACACURRENT(r13)
ld r2,TASKTHREADPPR(r2)
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/*
* Clear RI before restoring r13. If we are returning to
* userspace and we take an exception after restoring r13,
* we end up corrupting the userspace r13 value.
*/
ld r4,PACAKMSR(r13) /* Get kernel MSR without EE */
andc r4,r4,r0 /* r0 contains MSR_RI here */
mtmsrd r4,1
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/* TM debug */
std r3, PACATMSCRATCH(r13) /* Stash returned-to MSR */
#endif
/*
* r13 is our per cpu area, only restore it if we are returning to
* userspace the value stored in the stack frame may belong to
* another CPU.
*/
andi. r0,r3,MSR_PR
beq 1f
BEGIN_FTR_SECTION
mtspr SPRN_PPR,r2 /* Restore PPR */
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
ACCOUNT_CPU_USER_EXIT(r2, r4)
REST_GPR(13, r1)
1:
mtspr SPRN_SRR1,r3
ld r2,_CCR(r1)
mtcrf 0xFF,r2
ld r2,_NIP(r1)
mtspr SPRN_SRR0,r2
ld r0,GPR0(r1)
ld r2,GPR2(r1)
ld r3,GPR3(r1)
ld r4,GPR4(r1)
ld r1,GPR1(r1)
rfid
b . /* prevent speculative execution */
#endif /* CONFIG_PPC_BOOK3E */
/*
* We are returning to a context with interrupts soft disabled.
*
* However, we may also about to hard enable, so we need to
* make sure that in this case, we also clear PACA_IRQ_HARD_DIS
* or that bit can get out of sync and bad things will happen
*/
restore_irq_off:
ld r3,_MSR(r1)
lbz r7,PACAIRQHAPPENED(r13)
andi. r0,r3,MSR_EE
beq 1f
rlwinm r7,r7,0,~PACA_IRQ_HARD_DIS
stb r7,PACAIRQHAPPENED(r13)
1: li r0,0
stb r0,PACASOFTIRQEN(r13);
TRACE_DISABLE_INTS
b do_restore
/*
* Something did happen, check if a re-emit is needed
* (this also clears paca->irq_happened)
*/
restore_check_irq_replay:
/* XXX: We could implement a fast path here where we check
* for irq_happened being just 0x01, in which case we can
* clear it and return. That means that we would potentially
* miss a decrementer having wrapped all the way around.
*
* Still, this might be useful for things like hash_page
*/
bl __check_irq_replay
cmpwi cr0,r3,0
beq restore_no_replay
/*
* We need to re-emit an interrupt. We do so by re-using our
* existing exception frame. We first change the trap value,
* but we need to ensure we preserve the low nibble of it
*/
ld r4,_TRAP(r1)
clrldi r4,r4,60
or r4,r4,r3
std r4,_TRAP(r1)
/*
* Then find the right handler and call it. Interrupts are
* still soft-disabled and we keep them that way.
*/
cmpwi cr0,r3,0x500
bne 1f
addi r3,r1,STACK_FRAME_OVERHEAD;
bl do_IRQ
b ret_from_except
1: cmpwi cr0,r3,0xe60
bne 1f
addi r3,r1,STACK_FRAME_OVERHEAD;
bl handle_hmi_exception
b ret_from_except
1: cmpwi cr0,r3,0x900
bne 1f
addi r3,r1,STACK_FRAME_OVERHEAD;
bl timer_interrupt
b ret_from_except
#ifdef CONFIG_PPC_DOORBELL
1:
#ifdef CONFIG_PPC_BOOK3E
cmpwi cr0,r3,0x280
#else
BEGIN_FTR_SECTION
cmpwi cr0,r3,0xe80
FTR_SECTION_ELSE
cmpwi cr0,r3,0xa00
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
#endif /* CONFIG_PPC_BOOK3E */
bne 1f
addi r3,r1,STACK_FRAME_OVERHEAD;
bl doorbell_exception
b ret_from_except
#endif /* CONFIG_PPC_DOORBELL */
1: b ret_from_except /* What else to do here ? */
unrecov_restore:
addi r3,r1,STACK_FRAME_OVERHEAD
bl unrecoverable_exception
b unrecov_restore
#ifdef CONFIG_PPC_RTAS
/*
* On CHRP, the Run-Time Abstraction Services (RTAS) have to be
* called with the MMU off.
*
* In addition, we need to be in 32b mode, at least for now.
*
* Note: r3 is an input parameter to rtas, so don't trash it...
*/
_GLOBAL(enter_rtas)
mflr r0
std r0,16(r1)
stdu r1,-RTAS_FRAME_SIZE(r1) /* Save SP and create stack space. */
/* Because RTAS is running in 32b mode, it clobbers the high order half
* of all registers that it saves. We therefore save those registers
* RTAS might touch to the stack. (r0, r3-r13 are caller saved)
*/
SAVE_GPR(2, r1) /* Save the TOC */
SAVE_GPR(13, r1) /* Save paca */
SAVE_8GPRS(14, r1) /* Save the non-volatiles */
SAVE_10GPRS(22, r1) /* ditto */
mfcr r4
std r4,_CCR(r1)
mfctr r5
std r5,_CTR(r1)
mfspr r6,SPRN_XER
std r6,_XER(r1)
mfdar r7
std r7,_DAR(r1)
mfdsisr r8
std r8,_DSISR(r1)
/* Temporary workaround to clear CR until RTAS can be modified to
* ignore all bits.
*/
li r0,0
mtcr r0
#ifdef CONFIG_BUG
/* There is no way it is acceptable to get here with interrupts enabled,
* check it with the asm equivalent of WARN_ON
*/
lbz r0,PACASOFTIRQEN(r13)
1: tdnei r0,0
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
#endif
/* Hard-disable interrupts */
mfmsr r6
rldicl r7,r6,48,1
rotldi r7,r7,16
mtmsrd r7,1
/* Unfortunately, the stack pointer and the MSR are also clobbered,
* so they are saved in the PACA which allows us to restore
* our original state after RTAS returns.
*/
std r1,PACAR1(r13)
std r6,PACASAVEDMSR(r13)
/* Setup our real return addr */
LOAD_REG_ADDR(r4,rtas_return_loc)
clrldi r4,r4,2 /* convert to realmode address */
mtlr r4
li r0,0
ori r0,r0,MSR_EE|MSR_SE|MSR_BE|MSR_RI
andc r0,r6,r0
li r9,1
rldicr r9,r9,MSR_SF_LG,(63-MSR_SF_LG)
ori r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI|MSR_LE
andc r6,r0,r9
sync /* disable interrupts so SRR0/1 */
mtmsrd r0 /* don't get trashed */
LOAD_REG_ADDR(r4, rtas)
ld r5,RTASENTRY(r4) /* get the rtas->entry value */
ld r4,RTASBASE(r4) /* get the rtas->base value */
mtspr SPRN_SRR0,r5
mtspr SPRN_SRR1,r6
rfid
b . /* prevent speculative execution */
rtas_return_loc:
FIXUP_ENDIAN
/* relocation is off at this point */
GET_PACA(r4)
clrldi r4,r4,2 /* convert to realmode address */
bcl 20,31,$+4
0: mflr r3
ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */
mfmsr r6
li r0,MSR_RI
andc r6,r6,r0
sync
mtmsrd r6
ld r1,PACAR1(r4) /* Restore our SP */
ld r4,PACASAVEDMSR(r4) /* Restore our MSR */
mtspr SPRN_SRR0,r3
mtspr SPRN_SRR1,r4
rfid
b . /* prevent speculative execution */
.align 3
1: .llong rtas_restore_regs
rtas_restore_regs:
/* relocation is on at this point */
REST_GPR(2, r1) /* Restore the TOC */
REST_GPR(13, r1) /* Restore paca */
REST_8GPRS(14, r1) /* Restore the non-volatiles */
REST_10GPRS(22, r1) /* ditto */
GET_PACA(r13)
ld r4,_CCR(r1)
mtcr r4
ld r5,_CTR(r1)
mtctr r5
ld r6,_XER(r1)
mtspr SPRN_XER,r6
ld r7,_DAR(r1)
mtdar r7
ld r8,_DSISR(r1)
mtdsisr r8
addi r1,r1,RTAS_FRAME_SIZE /* Unstack our frame */
ld r0,16(r1) /* get return address */
mtlr r0
blr /* return to caller */
#endif /* CONFIG_PPC_RTAS */
_GLOBAL(enter_prom)
mflr r0
std r0,16(r1)
stdu r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */
/* Because PROM is running in 32b mode, it clobbers the high order half
* of all registers that it saves. We therefore save those registers
* PROM might touch to the stack. (r0, r3-r13 are caller saved)
*/
SAVE_GPR(2, r1)
SAVE_GPR(13, r1)
SAVE_8GPRS(14, r1)
SAVE_10GPRS(22, r1)
mfcr r10
mfmsr r11
std r10,_CCR(r1)
std r11,_MSR(r1)
/* Put PROM address in SRR0 */
mtsrr0 r4
/* Setup our trampoline return addr in LR */
bcl 20,31,$+4
0: mflr r4
addi r4,r4,(1f - 0b)
mtlr r4
/* Prepare a 32-bit mode big endian MSR
*/
#ifdef CONFIG_PPC_BOOK3E
rlwinm r11,r11,0,1,31
mtsrr1 r11
rfi
#else /* CONFIG_PPC_BOOK3E */
LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE)
andc r11,r11,r12
mtsrr1 r11
rfid
#endif /* CONFIG_PPC_BOOK3E */
1: /* Return from OF */
FIXUP_ENDIAN
/* Just make sure that r1 top 32 bits didn't get
* corrupt by OF
*/
rldicl r1,r1,0,32
/* Restore the MSR (back to 64 bits) */
ld r0,_MSR(r1)
MTMSRD(r0)
isync
/* Restore other registers */
REST_GPR(2, r1)
REST_GPR(13, r1)
REST_8GPRS(14, r1)
REST_10GPRS(22, r1)
ld r4,_CCR(r1)
mtcr r4
addi r1,r1,PROM_FRAME_SIZE
ld r0,16(r1)
mtlr r0
blr
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
_GLOBAL(mcount)
_GLOBAL(_mcount)
mflr r12
mtctr r12
mtlr r0
bctr
#ifndef CC_USING_MPROFILE_KERNEL
_GLOBAL_TOC(ftrace_caller)
/* Taken from output of objdump from lib64/glibc */
mflr r3
ld r11, 0(r1)
stdu r1, -112(r1)
std r3, 128(r1)
ld r4, 16(r11)
subi r3, r3, MCOUNT_INSN_SIZE
.globl ftrace_call
ftrace_call:
bl ftrace_stub
nop
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.globl ftrace_graph_call
ftrace_graph_call:
b ftrace_graph_stub
_GLOBAL(ftrace_graph_stub)
#endif
ld r0, 128(r1)
mtlr r0
addi r1, r1, 112
#else /* CC_USING_MPROFILE_KERNEL */
/*
*
* ftrace_caller() is the function that replaces _mcount() when ftrace is
* active.
*
* We arrive here after a function A calls function B, and we are the trace
* function for B. When we enter r1 points to A's stack frame, B has not yet
* had a chance to allocate one yet.
*
* Additionally r2 may point either to the TOC for A, or B, depending on
* whether B did a TOC setup sequence before calling us.
*
* On entry the LR points back to the _mcount() call site, and r0 holds the
* saved LR as it was on entry to B, ie. the original return address at the
* call site in A.
*
* Our job is to save the register state into a struct pt_regs (on the stack)
* and then arrange for the ftrace function to be called.
*/
_GLOBAL(ftrace_caller)
/* Save the original return address in A's stack frame */
std r0,LRSAVE(r1)
/* Create our stack frame + pt_regs */
stdu r1,-SWITCH_FRAME_SIZE(r1)
/* Save all gprs to pt_regs */
SAVE_8GPRS(0,r1)
SAVE_8GPRS(8,r1)
SAVE_8GPRS(16,r1)
SAVE_8GPRS(24,r1)
/* Load special regs for save below */
mfmsr r8
mfctr r9
mfxer r10
mfcr r11
/* Get the _mcount() call site out of LR */
mflr r7
/* Save it as pt_regs->nip & pt_regs->link */
std r7, _NIP(r1)
std r7, _LINK(r1)
/* Save callee's TOC in the ABI compliant location */
std r2, 24(r1)
ld r2,PACATOC(r13) /* get kernel TOC in r2 */
addis r3,r2,function_trace_op@toc@ha
addi r3,r3,function_trace_op@toc@l
ld r5,0(r3)
/* Calculate ip from nip-4 into r3 for call below */
subi r3, r7, MCOUNT_INSN_SIZE
/* Put the original return address in r4 as parent_ip */
mr r4, r0
/* Save special regs */
std r8, _MSR(r1)
std r9, _CTR(r1)
std r10, _XER(r1)
std r11, _CCR(r1)
/* Load &pt_regs in r6 for call below */
addi r6, r1 ,STACK_FRAME_OVERHEAD
/* ftrace_call(r3, r4, r5, r6) */
.globl ftrace_call
ftrace_call:
bl ftrace_stub
nop
/* Load ctr with the possibly modified NIP */
ld r3, _NIP(r1)
mtctr r3
/* Restore gprs */
REST_8GPRS(0,r1)
REST_8GPRS(8,r1)
REST_8GPRS(16,r1)
REST_8GPRS(24,r1)
/* Restore callee's TOC */
ld r2, 24(r1)
/* Pop our stack frame */
addi r1, r1, SWITCH_FRAME_SIZE
/* Restore original LR for return to B */
ld r0, LRSAVE(r1)
mtlr r0
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
stdu r1, -112(r1)
.globl ftrace_graph_call
ftrace_graph_call:
b ftrace_graph_stub
_GLOBAL(ftrace_graph_stub)
addi r1, r1, 112
#endif
ld r0,LRSAVE(r1) /* restore callee's lr at _mcount site */
mtlr r0
bctr /* jump after _mcount site */
#endif /* CC_USING_MPROFILE_KERNEL */
_GLOBAL(ftrace_stub)
blr
#else
_GLOBAL_TOC(_mcount)
/* Taken from output of objdump from lib64/glibc */
mflr r3
ld r11, 0(r1)
stdu r1, -112(r1)
std r3, 128(r1)
ld r4, 16(r11)
subi r3, r3, MCOUNT_INSN_SIZE
LOAD_REG_ADDR(r5,ftrace_trace_function)
ld r5,0(r5)
ld r5,0(r5)
mtctr r5
bctrl
nop
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
b ftrace_graph_caller
#endif
ld r0, 128(r1)
mtlr r0
addi r1, r1, 112
_GLOBAL(ftrace_stub)
blr
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
#ifndef CC_USING_MPROFILE_KERNEL
_GLOBAL(ftrace_graph_caller)
/* load r4 with local address */
ld r4, 128(r1)
subi r4, r4, MCOUNT_INSN_SIZE
/* Grab the LR out of the caller stack frame */
ld r11, 112(r1)
ld r3, 16(r11)
bl prepare_ftrace_return
nop
/*
* prepare_ftrace_return gives us the address we divert to.
* Change the LR in the callers stack frame to this.
*/
ld r11, 112(r1)
std r3, 16(r11)
ld r0, 128(r1)
mtlr r0
addi r1, r1, 112
blr
#else /* CC_USING_MPROFILE_KERNEL */
_GLOBAL(ftrace_graph_caller)
/* with -mprofile-kernel, parameter regs are still alive at _mcount */
std r10, 104(r1)
std r9, 96(r1)
std r8, 88(r1)
std r7, 80(r1)
std r6, 72(r1)
std r5, 64(r1)
std r4, 56(r1)
std r3, 48(r1)
/* Save callee's TOC in the ABI compliant location */
std r2, 24(r1)
ld r2, PACATOC(r13) /* get kernel TOC in r2 */
mfctr r4 /* ftrace_caller has moved local addr here */
std r4, 40(r1)
mflr r3 /* ftrace_caller has restored LR from stack */
subi r4, r4, MCOUNT_INSN_SIZE
bl prepare_ftrace_return
nop
/*
* prepare_ftrace_return gives us the address we divert to.
* Change the LR to this.
*/
mtlr r3
ld r0, 40(r1)
mtctr r0
ld r10, 104(r1)
ld r9, 96(r1)
ld r8, 88(r1)
ld r7, 80(r1)
ld r6, 72(r1)
ld r5, 64(r1)
ld r4, 56(r1)
ld r3, 48(r1)
/* Restore callee's TOC */
ld r2, 24(r1)
addi r1, r1, 112
mflr r0
std r0, LRSAVE(r1)
bctr
#endif /* CC_USING_MPROFILE_KERNEL */
_GLOBAL(return_to_handler)
/* need to save return values */
std r4, -32(r1)
std r3, -24(r1)
/* save TOC */
std r2, -16(r1)
std r31, -8(r1)
mr r31, r1
stdu r1, -112(r1)
/*
* We might be called from a module.
* Switch to our TOC to run inside the core kernel.
*/
ld r2, PACATOC(r13)
bl ftrace_return_to_handler
nop
/* return value has real return address */
mtlr r3
ld r1, 0(r1)
ld r4, -32(r1)
ld r3, -24(r1)
ld r2, -16(r1)
ld r31, -8(r1)
/* Jump back to real return address */
blr
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
#endif /* CONFIG_FUNCTION_TRACER */