mirror of
https://github.com/torvalds/linux.git
synced 2024-11-19 10:31:48 +00:00
7cafc0b8bf
We must handle data access exception as well as memory address unaligned exceptions from return from trap window fill faults, not just normal TLB misses. Otherwise we can get an OOPS that looks like this: ld-linux.so.2(36808): Kernel bad sw trap 5 [#1] CPU: 1 PID: 36808 Comm: ld-linux.so.2 Not tainted 4.6.0 #34 task: fff8000303be5c60 ti: fff8000301344000 task.ti: fff8000301344000 TSTATE: 0000004410001601 TPC: 0000000000a1a784 TNPC: 0000000000a1a788 Y: 00000002 Not tainted TPC: <do_sparc64_fault+0x5c4/0x700> g0: fff8000024fc8248 g1: 0000000000db04dc g2: 0000000000000000 g3: 0000000000000001 g4: fff8000303be5c60 g5: fff800030e672000 g6: fff8000301344000 g7: 0000000000000001 o0: 0000000000b95ee8 o1: 000000000000012b o2: 0000000000000000 o3: 0000000200b9b358 o4: 0000000000000000 o5: fff8000301344040 sp: fff80003013475c1 ret_pc: 0000000000a1a77c RPC: <do_sparc64_fault+0x5bc/0x700> l0: 00000000000007ff l1: 0000000000000000 l2: 000000000000005f l3: 0000000000000000 l4: fff8000301347e98 l5: fff8000024ff3060 l6: 0000000000000000 l7: 0000000000000000 i0: fff8000301347f60 i1: 0000000000102400 i2: 0000000000000000 i3: 0000000000000000 i4: 0000000000000000 i5: 0000000000000000 i6: fff80003013476a1 i7: 0000000000404d4c I7: <user_rtt_fill_fixup+0x6c/0x7c> Call Trace: [0000000000404d4c] user_rtt_fill_fixup+0x6c/0x7c The window trap handlers are slightly clever, the trap table entries for them are composed of two pieces of code. First comes the code that actually performs the window fill or spill trap handling, and then there are three instructions at the end which are for exception processing. The userland register window fill handler is: add %sp, STACK_BIAS + 0x00, %g1; \ ldxa [%g1 + %g0] ASI, %l0; \ mov 0x08, %g2; \ mov 0x10, %g3; \ ldxa [%g1 + %g2] ASI, %l1; \ mov 0x18, %g5; \ ldxa [%g1 + %g3] ASI, %l2; \ ldxa [%g1 + %g5] ASI, %l3; \ add %g1, 0x20, %g1; \ ldxa [%g1 + %g0] ASI, %l4; \ ldxa [%g1 + %g2] ASI, %l5; \ ldxa [%g1 + %g3] ASI, %l6; \ ldxa [%g1 + %g5] ASI, %l7; \ add %g1, 0x20, %g1; \ ldxa [%g1 + %g0] ASI, %i0; \ ldxa [%g1 + %g2] ASI, %i1; \ ldxa [%g1 + %g3] ASI, %i2; \ ldxa [%g1 + %g5] ASI, %i3; \ add %g1, 0x20, %g1; \ ldxa [%g1 + %g0] ASI, %i4; \ ldxa [%g1 + %g2] ASI, %i5; \ ldxa [%g1 + %g3] ASI, %i6; \ ldxa [%g1 + %g5] ASI, %i7; \ restored; \ retry; nop; nop; nop; nop; \ b,a,pt %xcc, fill_fixup_dax; \ b,a,pt %xcc, fill_fixup_mna; \ b,a,pt %xcc, fill_fixup; And the way this works is that if any of those memory accesses generate an exception, the exception handler can revector to one of those final three branch instructions depending upon which kind of exception the memory access took. In this way, the fault handler doesn't have to know if it was a spill or a fill that it's handling the fault for. It just always branches to the last instruction in the parent trap's handler. For example, for a regular fault, the code goes: winfix_trampoline: rdpr %tpc, %g3 or %g3, 0x7c, %g3 wrpr %g3, %tnpc done All window trap handlers are 0x80 aligned, so if we "or" 0x7c into the trap time program counter, we'll get that final instruction in the trap handler. On return from trap, we have to pull the register window in but we do this by hand instead of just executing a "restore" instruction for several reasons. The largest being that from Niagara and onward we simply don't have enough levels in the trap stack to fully resolve all possible exception cases of a window fault when we are already at trap level 1 (which we enter to get ready to return from the original trap). This is executed inline via the FILL_*_RTRAP handlers. rtrap_64.S's code branches directly to these to do the window fill by hand if necessary. Now if you look at them, we'll see at the end: ba,a,pt %xcc, user_rtt_fill_fixup; ba,a,pt %xcc, user_rtt_fill_fixup; ba,a,pt %xcc, user_rtt_fill_fixup; And oops, all three cases are handled like a fault. This doesn't work because each of these trap types (data access exception, memory address unaligned, and faults) store their auxiliary info in different registers to pass on to the C handler which does the real work. So in the case where the stack was unaligned, the unaligned trap handler sets up the arg registers one way, and then we branched to the fault handler which expects them setup another way. So the FAULT_TYPE_* value ends up basically being garbage, and randomly would generate the backtrace seen above. Reported-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
339 lines
8.8 KiB
ArmAsm
339 lines
8.8 KiB
ArmAsm
/*
|
|
* rtrap.S: Preparing for return from trap on Sparc V9.
|
|
*
|
|
* Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
|
|
* Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
|
|
*/
|
|
|
|
|
|
#include <asm/asi.h>
|
|
#include <asm/pstate.h>
|
|
#include <asm/ptrace.h>
|
|
#include <asm/spitfire.h>
|
|
#include <asm/head.h>
|
|
#include <asm/visasm.h>
|
|
#include <asm/processor.h>
|
|
|
|
#ifdef CONFIG_CONTEXT_TRACKING
|
|
# define SCHEDULE_USER schedule_user
|
|
#else
|
|
# define SCHEDULE_USER schedule
|
|
#endif
|
|
|
|
.text
|
|
.align 32
|
|
__handle_preemption:
|
|
call SCHEDULE_USER
|
|
wrpr %g0, RTRAP_PSTATE, %pstate
|
|
ba,pt %xcc, __handle_preemption_continue
|
|
wrpr %g0, RTRAP_PSTATE_IRQOFF, %pstate
|
|
|
|
__handle_user_windows:
|
|
call fault_in_user_windows
|
|
wrpr %g0, RTRAP_PSTATE, %pstate
|
|
ba,pt %xcc, __handle_preemption_continue
|
|
wrpr %g0, RTRAP_PSTATE_IRQOFF, %pstate
|
|
|
|
__handle_userfpu:
|
|
rd %fprs, %l5
|
|
andcc %l5, FPRS_FEF, %g0
|
|
sethi %hi(TSTATE_PEF), %o0
|
|
be,a,pn %icc, __handle_userfpu_continue
|
|
andn %l1, %o0, %l1
|
|
ba,a,pt %xcc, __handle_userfpu_continue
|
|
|
|
__handle_signal:
|
|
mov %l5, %o1
|
|
add %sp, PTREGS_OFF, %o0
|
|
mov %l0, %o2
|
|
call do_notify_resume
|
|
wrpr %g0, RTRAP_PSTATE, %pstate
|
|
wrpr %g0, RTRAP_PSTATE_IRQOFF, %pstate
|
|
|
|
/* Signal delivery can modify pt_regs tstate, so we must
|
|
* reload it.
|
|
*/
|
|
ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
|
|
sethi %hi(0xf << 20), %l4
|
|
and %l1, %l4, %l4
|
|
ba,pt %xcc, __handle_preemption_continue
|
|
andn %l1, %l4, %l1
|
|
|
|
/* When returning from a NMI (%pil==15) interrupt we want to
|
|
* avoid running softirqs, doing IRQ tracing, preempting, etc.
|
|
*/
|
|
.globl rtrap_nmi
|
|
rtrap_nmi: ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
|
|
sethi %hi(0xf << 20), %l4
|
|
and %l1, %l4, %l4
|
|
andn %l1, %l4, %l1
|
|
srl %l4, 20, %l4
|
|
ba,pt %xcc, rtrap_no_irq_enable
|
|
nop
|
|
/* Do not actually set the %pil here. We will do that
|
|
* below after we clear PSTATE_IE in the %pstate register.
|
|
* If we re-enable interrupts here, we can recurse down
|
|
* the hardirq stack potentially endlessly, causing a
|
|
* stack overflow.
|
|
*/
|
|
|
|
.align 64
|
|
.globl rtrap_irq, rtrap, irqsz_patchme, rtrap_xcall
|
|
rtrap_irq:
|
|
rtrap:
|
|
/* mm/ultra.S:xcall_report_regs KNOWS about this load. */
|
|
ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
|
|
rtrap_xcall:
|
|
sethi %hi(0xf << 20), %l4
|
|
and %l1, %l4, %l4
|
|
andn %l1, %l4, %l1
|
|
srl %l4, 20, %l4
|
|
#ifdef CONFIG_TRACE_IRQFLAGS
|
|
brnz,pn %l4, rtrap_no_irq_enable
|
|
nop
|
|
call trace_hardirqs_on
|
|
nop
|
|
/* Do not actually set the %pil here. We will do that
|
|
* below after we clear PSTATE_IE in the %pstate register.
|
|
* If we re-enable interrupts here, we can recurse down
|
|
* the hardirq stack potentially endlessly, causing a
|
|
* stack overflow.
|
|
*
|
|
* It is tempting to put this test and trace_hardirqs_on
|
|
* call at the 'rt_continue' label, but that will not work
|
|
* as that path hits unconditionally and we do not want to
|
|
* execute this in NMI return paths, for example.
|
|
*/
|
|
#endif
|
|
rtrap_no_irq_enable:
|
|
andcc %l1, TSTATE_PRIV, %l3
|
|
bne,pn %icc, to_kernel
|
|
nop
|
|
|
|
/* We must hold IRQs off and atomically test schedule+signal
|
|
* state, then hold them off all the way back to userspace.
|
|
* If we are returning to kernel, none of this matters. Note
|
|
* that we are disabling interrupts via PSTATE_IE, not using
|
|
* %pil.
|
|
*
|
|
* If we do not do this, there is a window where we would do
|
|
* the tests, later the signal/resched event arrives but we do
|
|
* not process it since we are still in kernel mode. It would
|
|
* take until the next local IRQ before the signal/resched
|
|
* event would be handled.
|
|
*
|
|
* This also means that if we have to deal with user
|
|
* windows, we have to redo all of these sched+signal checks
|
|
* with IRQs disabled.
|
|
*/
|
|
to_user: wrpr %g0, RTRAP_PSTATE_IRQOFF, %pstate
|
|
wrpr 0, %pil
|
|
__handle_preemption_continue:
|
|
ldx [%g6 + TI_FLAGS], %l0
|
|
sethi %hi(_TIF_USER_WORK_MASK), %o0
|
|
or %o0, %lo(_TIF_USER_WORK_MASK), %o0
|
|
andcc %l0, %o0, %g0
|
|
sethi %hi(TSTATE_PEF), %o0
|
|
be,pt %xcc, user_nowork
|
|
andcc %l1, %o0, %g0
|
|
andcc %l0, _TIF_NEED_RESCHED, %g0
|
|
bne,pn %xcc, __handle_preemption
|
|
andcc %l0, _TIF_DO_NOTIFY_RESUME_MASK, %g0
|
|
bne,pn %xcc, __handle_signal
|
|
ldub [%g6 + TI_WSAVED], %o2
|
|
brnz,pn %o2, __handle_user_windows
|
|
nop
|
|
sethi %hi(TSTATE_PEF), %o0
|
|
andcc %l1, %o0, %g0
|
|
|
|
/* This fpdepth clear is necessary for non-syscall rtraps only */
|
|
user_nowork:
|
|
bne,pn %xcc, __handle_userfpu
|
|
stb %g0, [%g6 + TI_FPDEPTH]
|
|
__handle_userfpu_continue:
|
|
|
|
rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1
|
|
ldx [%sp + PTREGS_OFF + PT_V9_G2], %g2
|
|
|
|
ldx [%sp + PTREGS_OFF + PT_V9_G3], %g3
|
|
ldx [%sp + PTREGS_OFF + PT_V9_G4], %g4
|
|
ldx [%sp + PTREGS_OFF + PT_V9_G5], %g5
|
|
brz,pt %l3, 1f
|
|
mov %g6, %l2
|
|
|
|
/* Must do this before thread reg is clobbered below. */
|
|
LOAD_PER_CPU_BASE(%g5, %g6, %i0, %i1, %i2)
|
|
1:
|
|
ldx [%sp + PTREGS_OFF + PT_V9_G6], %g6
|
|
ldx [%sp + PTREGS_OFF + PT_V9_G7], %g7
|
|
|
|
/* Normal globals are restored, go to trap globals. */
|
|
661: wrpr %g0, RTRAP_PSTATE_AG_IRQOFF, %pstate
|
|
nop
|
|
.section .sun4v_2insn_patch, "ax"
|
|
.word 661b
|
|
wrpr %g0, RTRAP_PSTATE_IRQOFF, %pstate
|
|
SET_GL(1)
|
|
.previous
|
|
|
|
mov %l2, %g6
|
|
|
|
ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0
|
|
ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1
|
|
|
|
ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2
|
|
ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3
|
|
ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4
|
|
ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5
|
|
ldx [%sp + PTREGS_OFF + PT_V9_I6], %i6
|
|
ldx [%sp + PTREGS_OFF + PT_V9_I7], %i7
|
|
ldx [%sp + PTREGS_OFF + PT_V9_TPC], %l2
|
|
ldx [%sp + PTREGS_OFF + PT_V9_TNPC], %o2
|
|
|
|
ld [%sp + PTREGS_OFF + PT_V9_Y], %o3
|
|
wr %o3, %g0, %y
|
|
wrpr %l4, 0x0, %pil
|
|
wrpr %g0, 0x1, %tl
|
|
andn %l1, TSTATE_SYSCALL, %l1
|
|
wrpr %l1, %g0, %tstate
|
|
wrpr %l2, %g0, %tpc
|
|
wrpr %o2, %g0, %tnpc
|
|
|
|
brnz,pn %l3, kern_rtt
|
|
mov PRIMARY_CONTEXT, %l7
|
|
|
|
661: ldxa [%l7 + %l7] ASI_DMMU, %l0
|
|
.section .sun4v_1insn_patch, "ax"
|
|
.word 661b
|
|
ldxa [%l7 + %l7] ASI_MMU, %l0
|
|
.previous
|
|
|
|
sethi %hi(sparc64_kern_pri_nuc_bits), %l1
|
|
ldx [%l1 + %lo(sparc64_kern_pri_nuc_bits)], %l1
|
|
or %l0, %l1, %l0
|
|
|
|
661: stxa %l0, [%l7] ASI_DMMU
|
|
.section .sun4v_1insn_patch, "ax"
|
|
.word 661b
|
|
stxa %l0, [%l7] ASI_MMU
|
|
.previous
|
|
|
|
sethi %hi(KERNBASE), %l7
|
|
flush %l7
|
|
rdpr %wstate, %l1
|
|
rdpr %otherwin, %l2
|
|
srl %l1, 3, %l1
|
|
|
|
wrpr %l2, %g0, %canrestore
|
|
wrpr %l1, %g0, %wstate
|
|
brnz,pt %l2, user_rtt_restore
|
|
wrpr %g0, %g0, %otherwin
|
|
|
|
ldx [%g6 + TI_FLAGS], %g3
|
|
wr %g0, ASI_AIUP, %asi
|
|
rdpr %cwp, %g1
|
|
andcc %g3, _TIF_32BIT, %g0
|
|
sub %g1, 1, %g1
|
|
bne,pt %xcc, user_rtt_fill_32bit
|
|
wrpr %g1, %cwp
|
|
ba,a,pt %xcc, user_rtt_fill_64bit
|
|
|
|
user_rtt_fill_fixup_dax:
|
|
ba,pt %xcc, user_rtt_fill_fixup_common
|
|
mov 1, %g3
|
|
|
|
user_rtt_fill_fixup_mna:
|
|
ba,pt %xcc, user_rtt_fill_fixup_common
|
|
mov 2, %g3
|
|
|
|
user_rtt_fill_fixup:
|
|
ba,pt %xcc, user_rtt_fill_fixup_common
|
|
clr %g3
|
|
|
|
user_rtt_pre_restore:
|
|
add %g1, 1, %g1
|
|
wrpr %g1, 0x0, %cwp
|
|
|
|
user_rtt_restore:
|
|
restore
|
|
rdpr %canrestore, %g1
|
|
wrpr %g1, 0x0, %cleanwin
|
|
retry
|
|
nop
|
|
|
|
kern_rtt: rdpr %canrestore, %g1
|
|
brz,pn %g1, kern_rtt_fill
|
|
nop
|
|
kern_rtt_restore:
|
|
stw %g0, [%sp + PTREGS_OFF + PT_V9_MAGIC]
|
|
restore
|
|
retry
|
|
|
|
to_kernel:
|
|
#ifdef CONFIG_PREEMPT
|
|
ldsw [%g6 + TI_PRE_COUNT], %l5
|
|
brnz %l5, kern_fpucheck
|
|
ldx [%g6 + TI_FLAGS], %l5
|
|
andcc %l5, _TIF_NEED_RESCHED, %g0
|
|
be,pt %xcc, kern_fpucheck
|
|
nop
|
|
cmp %l4, 0
|
|
bne,pn %xcc, kern_fpucheck
|
|
nop
|
|
call preempt_schedule_irq
|
|
nop
|
|
ba,pt %xcc, rtrap
|
|
#endif
|
|
kern_fpucheck: ldub [%g6 + TI_FPDEPTH], %l5
|
|
brz,pt %l5, rt_continue
|
|
srl %l5, 1, %o0
|
|
add %g6, TI_FPSAVED, %l6
|
|
ldub [%l6 + %o0], %l2
|
|
sub %l5, 2, %l5
|
|
|
|
add %g6, TI_GSR, %o1
|
|
andcc %l2, (FPRS_FEF|FPRS_DU), %g0
|
|
be,pt %icc, 2f
|
|
and %l2, FPRS_DL, %l6
|
|
andcc %l2, FPRS_FEF, %g0
|
|
be,pn %icc, 5f
|
|
sll %o0, 3, %o5
|
|
rd %fprs, %g1
|
|
|
|
wr %g1, FPRS_FEF, %fprs
|
|
ldx [%o1 + %o5], %g1
|
|
add %g6, TI_XFSR, %o1
|
|
sll %o0, 8, %o2
|
|
add %g6, TI_FPREGS, %o3
|
|
brz,pn %l6, 1f
|
|
add %g6, TI_FPREGS+0x40, %o4
|
|
|
|
membar #Sync
|
|
ldda [%o3 + %o2] ASI_BLK_P, %f0
|
|
ldda [%o4 + %o2] ASI_BLK_P, %f16
|
|
membar #Sync
|
|
1: andcc %l2, FPRS_DU, %g0
|
|
be,pn %icc, 1f
|
|
wr %g1, 0, %gsr
|
|
add %o2, 0x80, %o2
|
|
membar #Sync
|
|
ldda [%o3 + %o2] ASI_BLK_P, %f32
|
|
ldda [%o4 + %o2] ASI_BLK_P, %f48
|
|
1: membar #Sync
|
|
ldx [%o1 + %o5], %fsr
|
|
2: stb %l5, [%g6 + TI_FPDEPTH]
|
|
ba,pt %xcc, rt_continue
|
|
nop
|
|
5: wr %g0, FPRS_FEF, %fprs
|
|
sll %o0, 8, %o2
|
|
|
|
add %g6, TI_FPREGS+0x80, %o3
|
|
add %g6, TI_FPREGS+0xc0, %o4
|
|
membar #Sync
|
|
ldda [%o3 + %o2] ASI_BLK_P, %f32
|
|
ldda [%o4 + %o2] ASI_BLK_P, %f48
|
|
membar #Sync
|
|
wr %g0, FPRS_DU, %fprs
|
|
ba,pt %xcc, rt_continue
|
|
stb %l5, [%g6 + TI_FPDEPTH]
|