OpenCloudOS-Kernel/arch/tile/kernel/intvec_64.S

1300 lines
35 KiB
ArmAsm

/*
* Copyright 2011 Tilera Corporation. All Rights Reserved.
*
* 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, version 2.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for
* more details.
*
* Linux interrupt vectors.
*/
#include <linux/linkage.h>
#include <linux/errno.h>
#include <linux/unistd.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
#include <asm/irqflags.h>
#include <asm/asm-offsets.h>
#include <asm/types.h>
#include <asm/signal.h>
#include <hv/hypervisor.h>
#include <arch/abi.h>
#include <arch/interrupts.h>
#include <arch/spr_def.h>
#ifdef CONFIG_PREEMPT
# error "No support for kernel preemption currently"
#endif
#define PTREGS_PTR(reg, ptreg) addli reg, sp, C_ABI_SAVE_AREA_SIZE + (ptreg)
#define PTREGS_OFFSET_SYSCALL PTREGS_OFFSET_REG(TREG_SYSCALL_NR)
.macro push_reg reg, ptr=sp, delta=-8
{
st \ptr, \reg
addli \ptr, \ptr, \delta
}
.endm
.macro pop_reg reg, ptr=sp, delta=8
{
ld \reg, \ptr
addli \ptr, \ptr, \delta
}
.endm
.macro pop_reg_zero reg, zreg, ptr=sp, delta=8
{
move \zreg, zero
ld \reg, \ptr
addi \ptr, \ptr, \delta
}
.endm
.macro push_extra_callee_saves reg
PTREGS_PTR(\reg, PTREGS_OFFSET_REG(51))
push_reg r51, \reg
push_reg r50, \reg
push_reg r49, \reg
push_reg r48, \reg
push_reg r47, \reg
push_reg r46, \reg
push_reg r45, \reg
push_reg r44, \reg
push_reg r43, \reg
push_reg r42, \reg
push_reg r41, \reg
push_reg r40, \reg
push_reg r39, \reg
push_reg r38, \reg
push_reg r37, \reg
push_reg r36, \reg
push_reg r35, \reg
push_reg r34, \reg, PTREGS_OFFSET_BASE - PTREGS_OFFSET_REG(34)
.endm
.macro panic str
.pushsection .rodata, "a"
1:
.asciz "\str"
.popsection
{
moveli r0, hw2_last(1b)
}
{
shl16insli r0, r0, hw1(1b)
}
{
shl16insli r0, r0, hw0(1b)
jal panic
}
.endm
#ifdef __COLLECT_LINKER_FEEDBACK__
.pushsection .text.intvec_feedback,"ax"
intvec_feedback:
.popsection
#endif
/*
* Default interrupt handler.
*
* vecnum is where we'll put this code.
* c_routine is the C routine we'll call.
*
* The C routine is passed two arguments:
* - A pointer to the pt_regs state.
* - The interrupt vector number.
*
* The "processing" argument specifies the code for processing
* the interrupt. Defaults to "handle_interrupt".
*/
.macro int_hand vecnum, vecname, c_routine, processing=handle_interrupt
.org (\vecnum << 8)
intvec_\vecname:
/* Temporarily save a register so we have somewhere to work. */
mtspr SPR_SYSTEM_SAVE_K_1, r0
mfspr r0, SPR_EX_CONTEXT_K_1
andi r0, r0, SPR_EX_CONTEXT_1_1__PL_MASK /* mask off ICS */
.ifc \vecnum, INT_DOUBLE_FAULT
/*
* For double-faults from user-space, fall through to the normal
* register save and stack setup path. Otherwise, it's the
* hypervisor giving us one last chance to dump diagnostics, and we
* branch to the kernel_double_fault routine to do so.
*/
beqz r0, 1f
j _kernel_double_fault
1:
.else
/*
* If we're coming from user-space, then set sp to the top of
* the kernel stack. Otherwise, assume sp is already valid.
*/
{
bnez r0, 0f
move r0, sp
}
.endif
.ifc \c_routine, do_page_fault
/*
* The page_fault handler may be downcalled directly by the
* hypervisor even when Linux is running and has ICS set.
*
* In this case the contents of EX_CONTEXT_K_1 reflect the
* previous fault and can't be relied on to choose whether or
* not to reinitialize the stack pointer. So we add a test
* to see whether SYSTEM_SAVE_K_2 has the high bit set,
* and if so we don't reinitialize sp, since we must be coming
* from Linux. (In fact the precise case is !(val & ~1),
* but any Linux PC has to have the high bit set.)
*
* Note that the hypervisor *always* sets SYSTEM_SAVE_K_2 for
* any path that turns into a downcall to one of our TLB handlers.
*
* FIXME: if we end up never using this path, perhaps we should
* prevent the hypervisor from generating downcalls in this case.
* The advantage of getting a downcall is we can panic in Linux.
*/
mfspr r0, SPR_SYSTEM_SAVE_K_2
{
bltz r0, 0f /* high bit in S_S_1_2 is for a PC to use */
move r0, sp
}
.endif
/*
* SYSTEM_SAVE_K_0 holds the cpu number in the low bits, and
* the current stack top in the higher bits. So we recover
* our stack top by just masking off the low bits, then
* point sp at the top aligned address on the actual stack page.
*/
mfspr r0, SPR_SYSTEM_SAVE_K_0
mm r0, zero, LOG2_THREAD_SIZE, 63
0:
/*
* Align the stack mod 64 so we can properly predict what
* cache lines we need to write-hint to reduce memory fetch
* latency as we enter the kernel. The layout of memory is
* as follows, with cache line 0 at the lowest VA, and cache
* line 8 just below the r0 value this "andi" computes.
* Note that we never write to cache line 8, and we skip
* cache lines 1-3 for syscalls.
*
* cache line 8: ptregs padding (two words)
* cache line 7: sp, lr, pc, ex1, faultnum, orig_r0, flags, cmpexch
* cache line 6: r46...r53 (tp)
* cache line 5: r38...r45
* cache line 4: r30...r37
* cache line 3: r22...r29
* cache line 2: r14...r21
* cache line 1: r6...r13
* cache line 0: 2 x frame, r0..r5
*/
andi r0, r0, -64
/*
* Push the first four registers on the stack, so that we can set
* them to vector-unique values before we jump to the common code.
*
* Registers are pushed on the stack as a struct pt_regs,
* with the sp initially just above the struct, and when we're
* done, sp points to the base of the struct, minus
* C_ABI_SAVE_AREA_SIZE, so we can directly jal to C code.
*
* This routine saves just the first four registers, plus the
* stack context so we can do proper backtracing right away,
* and defers to handle_interrupt to save the rest.
* The backtracer needs pc, ex1, lr, sp, r52, and faultnum,
* and needs sp set to its final location at the bottom of
* the stack frame.
*/
addli r0, r0, PTREGS_OFFSET_LR - (PTREGS_SIZE + KSTK_PTREGS_GAP)
wh64 r0 /* cache line 7 */
{
st r0, lr
addli r0, r0, PTREGS_OFFSET_SP - PTREGS_OFFSET_LR
}
{
st r0, sp
addli sp, r0, PTREGS_OFFSET_REG(52) - PTREGS_OFFSET_SP
}
wh64 sp /* cache line 6 */
{
st sp, r52
addli sp, sp, PTREGS_OFFSET_REG(1) - PTREGS_OFFSET_REG(52)
}
wh64 sp /* cache line 0 */
{
st sp, r1
addli sp, sp, PTREGS_OFFSET_REG(2) - PTREGS_OFFSET_REG(1)
}
{
st sp, r2
addli sp, sp, PTREGS_OFFSET_REG(3) - PTREGS_OFFSET_REG(2)
}
{
st sp, r3
addli sp, sp, PTREGS_OFFSET_PC - PTREGS_OFFSET_REG(3)
}
mfspr r0, SPR_EX_CONTEXT_K_0
.ifc \processing,handle_syscall
/*
* Bump the saved PC by one bundle so that when we return, we won't
* execute the same swint instruction again. We need to do this while
* we're in the critical section.
*/
addi r0, r0, 8
.endif
{
st sp, r0
addli sp, sp, PTREGS_OFFSET_EX1 - PTREGS_OFFSET_PC
}
mfspr r0, SPR_EX_CONTEXT_K_1
{
st sp, r0
addi sp, sp, PTREGS_OFFSET_FAULTNUM - PTREGS_OFFSET_EX1
/*
* Use r0 for syscalls so it's a temporary; use r1 for interrupts
* so that it gets passed through unchanged to the handler routine.
* Note that the .if conditional confusingly spans bundles.
*/
.ifc \processing,handle_syscall
movei r0, \vecnum
}
{
st sp, r0
.else
movei r1, \vecnum
}
{
st sp, r1
.endif
addli sp, sp, PTREGS_OFFSET_REG(0) - PTREGS_OFFSET_FAULTNUM
}
mfspr r0, SPR_SYSTEM_SAVE_K_1 /* Original r0 */
{
st sp, r0
addi sp, sp, -PTREGS_OFFSET_REG(0) - 8
}
{
st sp, zero /* write zero into "Next SP" frame pointer */
addi sp, sp, -8 /* leave SP pointing at bottom of frame */
}
.ifc \processing,handle_syscall
j handle_syscall
.else
/* Capture per-interrupt SPR context to registers. */
.ifc \c_routine, do_page_fault
mfspr r2, SPR_SYSTEM_SAVE_K_3 /* address of page fault */
mfspr r3, SPR_SYSTEM_SAVE_K_2 /* info about page fault */
.else
.ifc \vecnum, INT_ILL_TRANS
mfspr r2, ILL_TRANS_REASON
.else
.ifc \vecnum, INT_DOUBLE_FAULT
mfspr r2, SPR_SYSTEM_SAVE_K_2 /* double fault info from HV */
.else
.ifc \c_routine, do_trap
mfspr r2, GPV_REASON
.else
.ifc \c_routine, op_handle_perf_interrupt
mfspr r2, PERF_COUNT_STS
#if CHIP_HAS_AUX_PERF_COUNTERS()
.else
.ifc \c_routine, op_handle_aux_perf_interrupt
mfspr r2, AUX_PERF_COUNT_STS
.endif
#endif
.endif
.endif
.endif
.endif
.endif
/* Put function pointer in r0 */
moveli r0, hw2_last(\c_routine)
shl16insli r0, r0, hw1(\c_routine)
{
shl16insli r0, r0, hw0(\c_routine)
j \processing
}
.endif
ENDPROC(intvec_\vecname)
#ifdef __COLLECT_LINKER_FEEDBACK__
.pushsection .text.intvec_feedback,"ax"
.org (\vecnum << 5)
FEEDBACK_ENTER_EXPLICIT(intvec_\vecname, .intrpt1, 1 << 8)
jrp lr
.popsection
#endif
.endm
/*
* Save the rest of the registers that we didn't save in the actual
* vector itself. We can't use r0-r10 inclusive here.
*/
.macro finish_interrupt_save, function
/* If it's a syscall, save a proper orig_r0, otherwise just zero. */
PTREGS_PTR(r52, PTREGS_OFFSET_ORIG_R0)
{
.ifc \function,handle_syscall
st r52, r0
.else
st r52, zero
.endif
PTREGS_PTR(r52, PTREGS_OFFSET_TP)
}
st r52, tp
{
mfspr tp, CMPEXCH_VALUE
PTREGS_PTR(r52, PTREGS_OFFSET_CMPEXCH)
}
/*
* For ordinary syscalls, we save neither caller- nor callee-
* save registers, since the syscall invoker doesn't expect the
* caller-saves to be saved, and the called kernel functions will
* take care of saving the callee-saves for us.
*
* For interrupts we save just the caller-save registers. Saving
* them is required (since the "caller" can't save them). Again,
* the called kernel functions will restore the callee-save
* registers for us appropriately.
*
* On return, we normally restore nothing special for syscalls,
* and just the caller-save registers for interrupts.
*
* However, there are some important caveats to all this:
*
* - We always save a few callee-save registers to give us
* some scratchpad registers to carry across function calls.
*
* - fork/vfork/etc require us to save all the callee-save
* registers, which we do in PTREGS_SYSCALL_ALL_REGS, below.
*
* - We always save r0..r5 and r10 for syscalls, since we need
* to reload them a bit later for the actual kernel call, and
* since we might need them for -ERESTARTNOINTR, etc.
*
* - Before invoking a signal handler, we save the unsaved
* callee-save registers so they are visible to the
* signal handler or any ptracer.
*
* - If the unsaved callee-save registers are modified, we set
* a bit in pt_regs so we know to reload them from pt_regs
* and not just rely on the kernel function unwinding.
* (Done for ptrace register writes and SA_SIGINFO handler.)
*/
{
st r52, tp
PTREGS_PTR(r52, PTREGS_OFFSET_REG(33))
}
wh64 r52 /* cache line 4 */
push_reg r33, r52
push_reg r32, r52
push_reg r31, r52
.ifc \function,handle_syscall
push_reg r30, r52, PTREGS_OFFSET_SYSCALL - PTREGS_OFFSET_REG(30)
push_reg TREG_SYSCALL_NR_NAME, r52, \
PTREGS_OFFSET_REG(5) - PTREGS_OFFSET_SYSCALL
.else
push_reg r30, r52, PTREGS_OFFSET_REG(29) - PTREGS_OFFSET_REG(30)
wh64 r52 /* cache line 3 */
push_reg r29, r52
push_reg r28, r52
push_reg r27, r52
push_reg r26, r52
push_reg r25, r52
push_reg r24, r52
push_reg r23, r52
push_reg r22, r52
wh64 r52 /* cache line 2 */
push_reg r21, r52
push_reg r20, r52
push_reg r19, r52
push_reg r18, r52
push_reg r17, r52
push_reg r16, r52
push_reg r15, r52
push_reg r14, r52
wh64 r52 /* cache line 1 */
push_reg r13, r52
push_reg r12, r52
push_reg r11, r52
push_reg r10, r52
push_reg r9, r52
push_reg r8, r52
push_reg r7, r52
push_reg r6, r52
.endif
push_reg r5, r52
st r52, r4
/*
* If we will be returning to the kernel, we will need to
* reset the interrupt masks to the state they had before.
* Set DISABLE_IRQ in flags iff we came from PL1 with irqs disabled.
*/
mfspr r32, SPR_EX_CONTEXT_K_1
{
andi r32, r32, SPR_EX_CONTEXT_1_1__PL_MASK /* mask off ICS */
PTREGS_PTR(r21, PTREGS_OFFSET_FLAGS)
}
beqzt r32, 1f /* zero if from user space */
IRQS_DISABLED(r32) /* zero if irqs enabled */
#if PT_FLAGS_DISABLE_IRQ != 1
# error Value of IRQS_DISABLED used to set PT_FLAGS_DISABLE_IRQ; fix
#endif
1:
.ifnc \function,handle_syscall
/* Record the fact that we saved the caller-save registers above. */
ori r32, r32, PT_FLAGS_CALLER_SAVES
.endif
st r21, r32
/*
* we've captured enough state to the stack (including in
* particular our EX_CONTEXT state) that we can now release
* the interrupt critical section and replace it with our
* standard "interrupts disabled" mask value. This allows
* synchronous interrupts (and profile interrupts) to punch
* through from this point onwards.
*
* It's important that no code before this point touch memory
* other than our own stack (to keep the invariant that this
* is all that gets touched under ICS), and that no code after
* this point reference any interrupt-specific SPR, in particular
* the EX_CONTEXT_K_ values.
*/
.ifc \function,handle_nmi
IRQ_DISABLE_ALL(r20)
.else
IRQ_DISABLE(r20, r21)
.endif
mtspr INTERRUPT_CRITICAL_SECTION, zero
/* Load tp with our per-cpu offset. */
#ifdef CONFIG_SMP
{
mfspr r20, SPR_SYSTEM_SAVE_K_0
moveli r21, hw2_last(__per_cpu_offset)
}
{
shl16insli r21, r21, hw1(__per_cpu_offset)
bfextu r20, r20, 0, LOG2_THREAD_SIZE-1
}
shl16insli r21, r21, hw0(__per_cpu_offset)
shl3add r20, r20, r21
ld tp, r20
#else
move tp, zero
#endif
#ifdef __COLLECT_LINKER_FEEDBACK__
/*
* Notify the feedback routines that we were in the
* appropriate fixed interrupt vector area. Note that we
* still have ICS set at this point, so we can't invoke any
* atomic operations or we will panic. The feedback
* routines internally preserve r0..r10 and r30 up.
*/
.ifnc \function,handle_syscall
shli r20, r1, 5
.else
moveli r20, INT_SWINT_1 << 5
.endif
moveli r21, hw2_last(intvec_feedback)
shl16insli r21, r21, hw1(intvec_feedback)
shl16insli r21, r21, hw0(intvec_feedback)
add r20, r20, r21
jalr r20
/* And now notify the feedback routines that we are here. */
FEEDBACK_ENTER(\function)
#endif
/*
* Prepare the first 256 stack bytes to be rapidly accessible
* without having to fetch the background data.
*/
addi r52, sp, -64
{
wh64 r52
addi r52, r52, -64
}
{
wh64 r52
addi r52, r52, -64
}
{
wh64 r52
addi r52, r52, -64
}
wh64 r52
#ifdef CONFIG_TRACE_IRQFLAGS
.ifnc \function,handle_nmi
/*
* We finally have enough state set up to notify the irq
* tracing code that irqs were disabled on entry to the handler.
* The TRACE_IRQS_OFF call clobbers registers r0-r29.
* For syscalls, we already have the register state saved away
* on the stack, so we don't bother to do any register saves here,
* and later we pop the registers back off the kernel stack.
* For interrupt handlers, save r0-r3 in callee-saved registers.
*/
.ifnc \function,handle_syscall
{ move r30, r0; move r31, r1 }
{ move r32, r2; move r33, r3 }
.endif
TRACE_IRQS_OFF
.ifnc \function,handle_syscall
{ move r0, r30; move r1, r31 }
{ move r2, r32; move r3, r33 }
.endif
.endif
#endif
.endm
/*
* Redispatch a downcall.
*/
.macro dc_dispatch vecnum, vecname
.org (\vecnum << 8)
intvec_\vecname:
j hv_downcall_dispatch
ENDPROC(intvec_\vecname)
.endm
/*
* Common code for most interrupts. The C function we're eventually
* going to is in r0, and the faultnum is in r1; the original
* values for those registers are on the stack.
*/
.pushsection .text.handle_interrupt,"ax"
handle_interrupt:
finish_interrupt_save handle_interrupt
/* Jump to the C routine; it should enable irqs as soon as possible. */
{
jalr r0
PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
}
FEEDBACK_REENTER(handle_interrupt)
{
movei r30, 0 /* not an NMI */
j interrupt_return
}
STD_ENDPROC(handle_interrupt)
/*
* This routine takes a boolean in r30 indicating if this is an NMI.
* If so, we also expect a boolean in r31 indicating whether to
* re-enable the oprofile interrupts.
*
* Note that .Lresume_userspace is jumped to directly in several
* places, and we need to make sure r30 is set correctly in those
* callers as well.
*/
STD_ENTRY(interrupt_return)
/* If we're resuming to kernel space, don't check thread flags. */
{
bnez r30, .Lrestore_all /* NMIs don't special-case user-space */
PTREGS_PTR(r29, PTREGS_OFFSET_EX1)
}
ld r29, r29
andi r29, r29, SPR_EX_CONTEXT_1_1__PL_MASK /* mask off ICS */
{
beqzt r29, .Lresume_userspace
PTREGS_PTR(r29, PTREGS_OFFSET_PC)
}
/* If we're resuming to _cpu_idle_nap, bump PC forward by 8. */
moveli r27, hw2_last(_cpu_idle_nap)
{
ld r28, r29
shl16insli r27, r27, hw1(_cpu_idle_nap)
}
{
shl16insli r27, r27, hw0(_cpu_idle_nap)
}
{
cmpeq r27, r27, r28
}
{
blbc r27, .Lrestore_all
addi r28, r28, 8
}
st r29, r28
j .Lrestore_all
.Lresume_userspace:
FEEDBACK_REENTER(interrupt_return)
/*
* Use r33 to hold whether we have already loaded the callee-saves
* into ptregs. We don't want to do it twice in this loop, since
* then we'd clobber whatever changes are made by ptrace, etc.
*/
{
movei r33, 0
move r32, sp
}
/* Get base of stack in r32. */
EXTRACT_THREAD_INFO(r32)
.Lretry_work_pending:
/*
* Disable interrupts so as to make sure we don't
* miss an interrupt that sets any of the thread flags (like
* need_resched or sigpending) between sampling and the iret.
* Routines like schedule() or do_signal() may re-enable
* interrupts before returning.
*/
IRQ_DISABLE(r20, r21)
TRACE_IRQS_OFF /* Note: clobbers registers r0-r29 */
/* Check to see if there is any work to do before returning to user. */
{
addi r29, r32, THREAD_INFO_FLAGS_OFFSET
moveli r1, hw1_last(_TIF_ALLWORK_MASK)
}
{
ld r29, r29
shl16insli r1, r1, hw0(_TIF_ALLWORK_MASK)
}
and r1, r29, r1
beqzt r1, .Lrestore_all
/*
* Make sure we have all the registers saved for signal
* handling or notify-resume. Call out to C code to figure out
* exactly what we need to do for each flag bit, then if
* necessary, reload the flags and recheck.
*/
{
PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
bnez r33, 1f
}
push_extra_callee_saves r0
movei r33, 1
1: jal do_work_pending
bnez r0, .Lretry_work_pending
/*
* In the NMI case we
* omit the call to single_process_check_nohz, which normally checks
* to see if we should start or stop the scheduler tick, because
* we can't call arbitrary Linux code from an NMI context.
* We always call the homecache TLB deferral code to re-trigger
* the deferral mechanism.
*
* The other chunk of responsibility this code has is to reset the
* interrupt masks appropriately to reset irqs and NMIs. We have
* to call TRACE_IRQS_OFF and TRACE_IRQS_ON to support all the
* lockdep-type stuff, but we can't set ICS until afterwards, since
* ICS can only be used in very tight chunks of code to avoid
* tripping over various assertions that it is off.
*/
.Lrestore_all:
PTREGS_PTR(r0, PTREGS_OFFSET_EX1)
{
ld r0, r0
PTREGS_PTR(r32, PTREGS_OFFSET_FLAGS)
}
{
andi r0, r0, SPR_EX_CONTEXT_1_1__PL_MASK
ld r32, r32
}
bnez r0, 1f
j 2f
#if PT_FLAGS_DISABLE_IRQ != 1
# error Assuming PT_FLAGS_DISABLE_IRQ == 1 so we can use blbct below
#endif
1: blbct r32, 2f
IRQ_DISABLE(r20,r21)
TRACE_IRQS_OFF
movei r0, 1
mtspr INTERRUPT_CRITICAL_SECTION, r0
beqzt r30, .Lrestore_regs
j 3f
2: TRACE_IRQS_ON
IRQ_ENABLE_LOAD(r20, r21)
movei r0, 1
mtspr INTERRUPT_CRITICAL_SECTION, r0
IRQ_ENABLE_APPLY(r20, r21)
beqzt r30, .Lrestore_regs
3:
/*
* We now commit to returning from this interrupt, since we will be
* doing things like setting EX_CONTEXT SPRs and unwinding the stack
* frame. No calls should be made to any other code after this point.
* This code should only be entered with ICS set.
* r32 must still be set to ptregs.flags.
* We launch loads to each cache line separately first, so we can
* get some parallelism out of the memory subsystem.
* We start zeroing caller-saved registers throughout, since
* that will save some cycles if this turns out to be a syscall.
*/
.Lrestore_regs:
/*
* Rotate so we have one high bit and one low bit to test.
* - low bit says whether to restore all the callee-saved registers,
* or just r30-r33, and r52 up.
* - high bit (i.e. sign bit) says whether to restore all the
* caller-saved registers, or just r0.
*/
#if PT_FLAGS_CALLER_SAVES != 2 || PT_FLAGS_RESTORE_REGS != 4
# error Rotate trick does not work :-)
#endif
{
rotli r20, r32, 62
PTREGS_PTR(sp, PTREGS_OFFSET_REG(0))
}
/*
* Load cache lines 0, 4, 6 and 7, in that order, then use
* the last loaded value, which makes it likely that the other
* cache lines have also loaded, at which point we should be
* able to safely read all the remaining words on those cache
* lines without waiting for the memory subsystem.
*/
pop_reg r0, sp, PTREGS_OFFSET_REG(30) - PTREGS_OFFSET_REG(0)
pop_reg r30, sp, PTREGS_OFFSET_REG(52) - PTREGS_OFFSET_REG(30)
pop_reg_zero r52, r3, sp, PTREGS_OFFSET_CMPEXCH - PTREGS_OFFSET_REG(52)
pop_reg_zero r21, r27, sp, PTREGS_OFFSET_EX1 - PTREGS_OFFSET_CMPEXCH
pop_reg_zero lr, r2, sp, PTREGS_OFFSET_PC - PTREGS_OFFSET_EX1
{
mtspr CMPEXCH_VALUE, r21
move r4, zero
}
pop_reg r21, sp, PTREGS_OFFSET_REG(31) - PTREGS_OFFSET_PC
{
mtspr SPR_EX_CONTEXT_K_1, lr
andi lr, lr, SPR_EX_CONTEXT_1_1__PL_MASK /* mask off ICS */
}
{
mtspr SPR_EX_CONTEXT_K_0, r21
move r5, zero
}
/* Restore callee-saveds that we actually use. */
pop_reg_zero r31, r6
pop_reg_zero r32, r7
pop_reg_zero r33, r8, sp, PTREGS_OFFSET_REG(29) - PTREGS_OFFSET_REG(33)
/*
* If we modified other callee-saveds, restore them now.
* This is rare, but could be via ptrace or signal handler.
*/
{
move r9, zero
blbs r20, .Lrestore_callees
}
.Lcontinue_restore_regs:
/* Check if we're returning from a syscall. */
{
move r10, zero
bltzt r20, 1f /* no, so go restore callee-save registers */
}
/*
* Check if we're returning to userspace.
* Note that if we're not, we don't worry about zeroing everything.
*/
{
addli sp, sp, PTREGS_OFFSET_LR - PTREGS_OFFSET_REG(29)
bnez lr, .Lkernel_return
}
/*
* On return from syscall, we've restored r0 from pt_regs, but we
* clear the remainder of the caller-saved registers. We could
* restore the syscall arguments, but there's not much point,
* and it ensures user programs aren't trying to use the
* caller-saves if we clear them, as well as avoiding leaking
* kernel pointers into userspace.
*/
pop_reg_zero lr, r11, sp, PTREGS_OFFSET_TP - PTREGS_OFFSET_LR
pop_reg_zero tp, r12, sp, PTREGS_OFFSET_SP - PTREGS_OFFSET_TP
{
ld sp, sp
move r13, zero
move r14, zero
}
{ move r15, zero; move r16, zero }
{ move r17, zero; move r18, zero }
{ move r19, zero; move r20, zero }
{ move r21, zero; move r22, zero }
{ move r23, zero; move r24, zero }
{ move r25, zero; move r26, zero }
/* Set r1 to errno if we are returning an error, otherwise zero. */
{
moveli r29, 4096
sub r1, zero, r0
}
{
move r28, zero
cmpltu r29, r1, r29
}
{
mnz r1, r29, r1
move r29, zero
}
iret
/*
* Not a syscall, so restore caller-saved registers.
* First kick off loads for cache lines 1-3, which we're touching
* for the first time here.
*/
.align 64
1: pop_reg r29, sp, PTREGS_OFFSET_REG(21) - PTREGS_OFFSET_REG(29)
pop_reg r21, sp, PTREGS_OFFSET_REG(13) - PTREGS_OFFSET_REG(21)
pop_reg r13, sp, PTREGS_OFFSET_REG(1) - PTREGS_OFFSET_REG(13)
pop_reg r1
pop_reg r2
pop_reg r3
pop_reg r4
pop_reg r5
pop_reg r6
pop_reg r7
pop_reg r8
pop_reg r9
pop_reg r10
pop_reg r11
pop_reg r12, sp, 16
/* r13 already restored above */
pop_reg r14
pop_reg r15
pop_reg r16
pop_reg r17
pop_reg r18
pop_reg r19
pop_reg r20, sp, 16
/* r21 already restored above */
pop_reg r22
pop_reg r23
pop_reg r24
pop_reg r25
pop_reg r26
pop_reg r27
pop_reg r28, sp, PTREGS_OFFSET_LR - PTREGS_OFFSET_REG(28)
/* r29 already restored above */
bnez lr, .Lkernel_return
pop_reg lr, sp, PTREGS_OFFSET_TP - PTREGS_OFFSET_LR
pop_reg tp, sp, PTREGS_OFFSET_SP - PTREGS_OFFSET_TP
ld sp, sp
iret
/*
* We can't restore tp when in kernel mode, since a thread might
* have migrated from another cpu and brought a stale tp value.
*/
.Lkernel_return:
pop_reg lr, sp, PTREGS_OFFSET_SP - PTREGS_OFFSET_LR
ld sp, sp
iret
/* Restore callee-saved registers from r34 to r51. */
.Lrestore_callees:
addli sp, sp, PTREGS_OFFSET_REG(34) - PTREGS_OFFSET_REG(29)
pop_reg r34
pop_reg r35
pop_reg r36
pop_reg r37
pop_reg r38
pop_reg r39
pop_reg r40
pop_reg r41
pop_reg r42
pop_reg r43
pop_reg r44
pop_reg r45
pop_reg r46
pop_reg r47
pop_reg r48
pop_reg r49
pop_reg r50
pop_reg r51, sp, PTREGS_OFFSET_REG(29) - PTREGS_OFFSET_REG(51)
j .Lcontinue_restore_regs
STD_ENDPROC(interrupt_return)
/*
* "NMI" interrupts mask ALL interrupts before calling the
* handler, and don't check thread flags, etc., on the way
* back out. In general, the only things we do here for NMIs
* are register save/restore and dataplane kernel-TLB management.
* We don't (for example) deal with start/stop of the sched tick.
*/
.pushsection .text.handle_nmi,"ax"
handle_nmi:
finish_interrupt_save handle_nmi
{
jalr r0
PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
}
FEEDBACK_REENTER(handle_nmi)
{
movei r30, 1
move r31, r0
}
j interrupt_return
STD_ENDPROC(handle_nmi)
/*
* Parallel code for syscalls to handle_interrupt.
*/
.pushsection .text.handle_syscall,"ax"
handle_syscall:
finish_interrupt_save handle_syscall
/* Enable irqs. */
TRACE_IRQS_ON
IRQ_ENABLE(r20, r21)
/* Bump the counter for syscalls made on this tile. */
moveli r20, hw2_last(irq_stat + IRQ_CPUSTAT_SYSCALL_COUNT_OFFSET)
shl16insli r20, r20, hw1(irq_stat + IRQ_CPUSTAT_SYSCALL_COUNT_OFFSET)
shl16insli r20, r20, hw0(irq_stat + IRQ_CPUSTAT_SYSCALL_COUNT_OFFSET)
add r20, r20, tp
ld4s r21, r20
{
addi r21, r21, 1
move r31, sp
}
{
st4 r20, r21
EXTRACT_THREAD_INFO(r31)
}
/* Trace syscalls, if requested. */
addi r31, r31, THREAD_INFO_FLAGS_OFFSET
ld r30, r31
andi r30, r30, _TIF_SYSCALL_TRACE
{
addi r30, r31, THREAD_INFO_STATUS_OFFSET - THREAD_INFO_FLAGS_OFFSET
beqzt r30, .Lrestore_syscall_regs
}
jal do_syscall_trace
FEEDBACK_REENTER(handle_syscall)
/*
* We always reload our registers from the stack at this
* point. They might be valid, if we didn't build with
* TRACE_IRQFLAGS, and this isn't a dataplane tile, and we're not
* doing syscall tracing, but there are enough cases now that it
* seems simplest just to do the reload unconditionally.
*/
.Lrestore_syscall_regs:
{
ld r30, r30
PTREGS_PTR(r11, PTREGS_OFFSET_REG(0))
}
pop_reg r0, r11
pop_reg r1, r11
pop_reg r2, r11
pop_reg r3, r11
pop_reg r4, r11
pop_reg r5, r11, PTREGS_OFFSET_SYSCALL - PTREGS_OFFSET_REG(5)
{
ld TREG_SYSCALL_NR_NAME, r11
moveli r21, __NR_syscalls
}
/* Ensure that the syscall number is within the legal range. */
{
moveli r20, hw2(sys_call_table)
blbs r30, .Lcompat_syscall
}
{
cmpltu r21, TREG_SYSCALL_NR_NAME, r21
shl16insli r20, r20, hw1(sys_call_table)
}
{
blbc r21, .Linvalid_syscall
shl16insli r20, r20, hw0(sys_call_table)
}
.Lload_syscall_pointer:
shl3add r20, TREG_SYSCALL_NR_NAME, r20
ld r20, r20
/* Jump to syscall handler. */
jalr r20
.Lhandle_syscall_link: /* value of "lr" after "jalr r20" above */
/*
* Write our r0 onto the stack so it gets restored instead
* of whatever the user had there before.
* In compat mode, sign-extend r0 before storing it.
*/
{
PTREGS_PTR(r29, PTREGS_OFFSET_REG(0))
blbct r30, 1f
}
addxi r0, r0, 0
1: st r29, r0
.Lsyscall_sigreturn_skip:
FEEDBACK_REENTER(handle_syscall)
/* Do syscall trace again, if requested. */
ld r30, r31
andi r0, r30, _TIF_SYSCALL_TRACE
{
andi r0, r30, _TIF_SINGLESTEP
beqzt r0, 1f
}
jal do_syscall_trace
FEEDBACK_REENTER(handle_syscall)
andi r0, r30, _TIF_SINGLESTEP
1: beqzt r0, 2f
/* Single stepping -- notify ptrace. */
{
movei r0, SIGTRAP
jal ptrace_notify
}
FEEDBACK_REENTER(handle_syscall)
2: {
movei r30, 0 /* not an NMI */
j .Lresume_userspace /* jump into middle of interrupt_return */
}
.Lcompat_syscall:
/*
* Load the base of the compat syscall table in r20, and
* range-check the syscall number (duplicated from 64-bit path).
* Sign-extend all the user's passed arguments to make them consistent.
* Also save the original "r(n)" values away in "r(11+n)" in
* case the syscall table entry wants to validate them.
*/
moveli r20, hw2(compat_sys_call_table)
{
cmpltu r21, TREG_SYSCALL_NR_NAME, r21
shl16insli r20, r20, hw1(compat_sys_call_table)
}
{
blbc r21, .Linvalid_syscall
shl16insli r20, r20, hw0(compat_sys_call_table)
}
{ move r11, r0; addxi r0, r0, 0 }
{ move r12, r1; addxi r1, r1, 0 }
{ move r13, r2; addxi r2, r2, 0 }
{ move r14, r3; addxi r3, r3, 0 }
{ move r15, r4; addxi r4, r4, 0 }
{ move r16, r5; addxi r5, r5, 0 }
j .Lload_syscall_pointer
.Linvalid_syscall:
/* Report an invalid syscall back to the user program */
{
PTREGS_PTR(r29, PTREGS_OFFSET_REG(0))
movei r28, -ENOSYS
}
st r29, r28
{
movei r30, 0 /* not an NMI */
j .Lresume_userspace /* jump into middle of interrupt_return */
}
STD_ENDPROC(handle_syscall)
/* Return the address for oprofile to suppress in backtraces. */
STD_ENTRY_SECTION(handle_syscall_link_address, .text.handle_syscall)
lnk r0
{
addli r0, r0, .Lhandle_syscall_link - .
jrp lr
}
STD_ENDPROC(handle_syscall_link_address)
STD_ENTRY(ret_from_fork)
jal sim_notify_fork
jal schedule_tail
FEEDBACK_REENTER(ret_from_fork)
{
movei r30, 0 /* not an NMI */
j .Lresume_userspace /* jump into middle of interrupt_return */
}
STD_ENDPROC(ret_from_fork)
STD_ENTRY(ret_from_kernel_thread)
jal sim_notify_fork
jal schedule_tail
FEEDBACK_REENTER(ret_from_fork)
{
move r0, r31
jalr r30
}
FEEDBACK_REENTER(ret_from_kernel_thread)
{
movei r30, 0 /* not an NMI */
j .Lresume_userspace /* jump into middle of interrupt_return */
}
STD_ENDPROC(ret_from_kernel_thread)
/* Various stub interrupt handlers and syscall handlers */
STD_ENTRY_LOCAL(_kernel_double_fault)
mfspr r1, SPR_EX_CONTEXT_K_0
move r2, lr
move r3, sp
move r4, r52
addi sp, sp, -C_ABI_SAVE_AREA_SIZE
j kernel_double_fault
STD_ENDPROC(_kernel_double_fault)
STD_ENTRY_LOCAL(bad_intr)
mfspr r2, SPR_EX_CONTEXT_K_0
panic "Unhandled interrupt %#x: PC %#lx"
STD_ENDPROC(bad_intr)
/*
* Special-case sigreturn to not write r0 to the stack on return.
* This is technically more efficient, but it also avoids difficulties
* in the 64-bit OS when handling 32-bit compat code, since we must not
* sign-extend r0 for the sigreturn return-value case.
*/
#define PTREGS_SYSCALL_SIGRETURN(x, reg) \
STD_ENTRY(_##x); \
addli lr, lr, .Lsyscall_sigreturn_skip - .Lhandle_syscall_link; \
{ \
PTREGS_PTR(reg, PTREGS_OFFSET_BASE); \
j x \
}; \
STD_ENDPROC(_##x)
PTREGS_SYSCALL_SIGRETURN(sys_rt_sigreturn, r0)
#ifdef CONFIG_COMPAT
PTREGS_SYSCALL_SIGRETURN(compat_sys_rt_sigreturn, r0)
#endif
/* Save additional callee-saves to pt_regs and jump to standard function. */
STD_ENTRY(_sys_clone)
push_extra_callee_saves r4
j sys_clone
STD_ENDPROC(_sys_clone)
/* The single-step support may need to read all the registers. */
int_unalign:
push_extra_callee_saves r0
j do_trap
/* Fill the return address stack with nonzero entries. */
STD_ENTRY(fill_ra_stack)
{
move r0, lr
jal 1f
}
1: jal 2f
2: jal 3f
3: jal 4f
4: jrp r0
STD_ENDPROC(fill_ra_stack)
/* Include .intrpt1 array of interrupt vectors */
.section ".intrpt1", "ax"
#define op_handle_perf_interrupt bad_intr
#define op_handle_aux_perf_interrupt bad_intr
#ifndef CONFIG_HARDWALL
#define do_hardwall_trap bad_intr
#endif
int_hand INT_MEM_ERROR, MEM_ERROR, do_trap
int_hand INT_SINGLE_STEP_3, SINGLE_STEP_3, bad_intr
#if CONFIG_KERNEL_PL == 2
int_hand INT_SINGLE_STEP_2, SINGLE_STEP_2, gx_singlestep_handle
int_hand INT_SINGLE_STEP_1, SINGLE_STEP_1, bad_intr
#else
int_hand INT_SINGLE_STEP_2, SINGLE_STEP_2, bad_intr
int_hand INT_SINGLE_STEP_1, SINGLE_STEP_1, gx_singlestep_handle
#endif
int_hand INT_SINGLE_STEP_0, SINGLE_STEP_0, bad_intr
int_hand INT_IDN_COMPLETE, IDN_COMPLETE, bad_intr
int_hand INT_UDN_COMPLETE, UDN_COMPLETE, bad_intr
int_hand INT_ITLB_MISS, ITLB_MISS, do_page_fault
int_hand INT_ILL, ILL, do_trap
int_hand INT_GPV, GPV, do_trap
int_hand INT_IDN_ACCESS, IDN_ACCESS, do_trap
int_hand INT_UDN_ACCESS, UDN_ACCESS, do_trap
int_hand INT_SWINT_3, SWINT_3, do_trap
int_hand INT_SWINT_2, SWINT_2, do_trap
int_hand INT_SWINT_1, SWINT_1, SYSCALL, handle_syscall
int_hand INT_SWINT_0, SWINT_0, do_trap
int_hand INT_ILL_TRANS, ILL_TRANS, do_trap
int_hand INT_UNALIGN_DATA, UNALIGN_DATA, int_unalign
int_hand INT_DTLB_MISS, DTLB_MISS, do_page_fault
int_hand INT_DTLB_ACCESS, DTLB_ACCESS, do_page_fault
int_hand INT_IDN_FIREWALL, IDN_FIREWALL, do_hardwall_trap
int_hand INT_UDN_FIREWALL, UDN_FIREWALL, do_hardwall_trap
int_hand INT_TILE_TIMER, TILE_TIMER, do_timer_interrupt
int_hand INT_IDN_TIMER, IDN_TIMER, bad_intr
int_hand INT_UDN_TIMER, UDN_TIMER, bad_intr
int_hand INT_IDN_AVAIL, IDN_AVAIL, bad_intr
int_hand INT_UDN_AVAIL, UDN_AVAIL, bad_intr
int_hand INT_IPI_3, IPI_3, bad_intr
#if CONFIG_KERNEL_PL == 2
int_hand INT_IPI_2, IPI_2, tile_dev_intr
int_hand INT_IPI_1, IPI_1, bad_intr
#else
int_hand INT_IPI_2, IPI_2, bad_intr
int_hand INT_IPI_1, IPI_1, tile_dev_intr
#endif
int_hand INT_IPI_0, IPI_0, bad_intr
int_hand INT_PERF_COUNT, PERF_COUNT, \
op_handle_perf_interrupt, handle_nmi
int_hand INT_AUX_PERF_COUNT, AUX_PERF_COUNT, \
op_handle_perf_interrupt, handle_nmi
int_hand INT_INTCTRL_3, INTCTRL_3, bad_intr
#if CONFIG_KERNEL_PL == 2
dc_dispatch INT_INTCTRL_2, INTCTRL_2
int_hand INT_INTCTRL_1, INTCTRL_1, bad_intr
#else
int_hand INT_INTCTRL_2, INTCTRL_2, bad_intr
dc_dispatch INT_INTCTRL_1, INTCTRL_1
#endif
int_hand INT_INTCTRL_0, INTCTRL_0, bad_intr
int_hand INT_MESSAGE_RCV_DWNCL, MESSAGE_RCV_DWNCL, \
hv_message_intr
int_hand INT_DEV_INTR_DWNCL, DEV_INTR_DWNCL, bad_intr
int_hand INT_I_ASID, I_ASID, bad_intr
int_hand INT_D_ASID, D_ASID, bad_intr
int_hand INT_DOUBLE_FAULT, DOUBLE_FAULT, do_trap
/* Synthetic interrupt delivered only by the simulator */
int_hand INT_BREAKPOINT, BREAKPOINT, do_breakpoint