From: David Miller <davem@xxxxxxxxxxxxx> Date: Fri, 27 May 2016 15:51:37 -0700 (PDT) > I'm trying to figure out the same thing myself. Ok, mystery solved. The basic problem is that we don't handle unaligned stacks on return to userspace %100 properly. We would also no handle a stack whose access would trigger a bus error or similar. A little background: 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: #define FILL_1_GENERIC(ASI) \ 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 loads or stores 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. For example, for a regular fault, the code goes: winfix_trampoline: rdpr %tpc, %g3 ! Prepare winfixup TNPC or %g3, 0x7c, %g3 ! Compute branch offset wrpr %g3, %tnpc ! Write it into TNPC done ! Trap return 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; 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 setup the arg registers one way, and then we branched to the fault handler. So the FAULT_TYPE_* value was basically garbage, and randomly would generate the backtrace that you saw. This is the fix I am testing right now: ==================== >From d645a0376b0010cd60ae5651b3b84a56f5b0e5a4 Mon Sep 17 00:00:00 2001 From: "David S. Miller" <davem@xxxxxxxxxxxxx> Date: Sat, 28 May 2016 20:41:12 -0700 Subject: [PATCH 2/2] sparc64: Fix return from trap window fill crashes. 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. Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx> --- arch/sparc/include/asm/ttable.h | 8 ++-- arch/sparc/kernel/Makefile | 1 + arch/sparc/kernel/rtrap_64.S | 57 ++++-------------------- arch/sparc/kernel/urtt_fill.S | 98 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 112 insertions(+), 52 deletions(-) create mode 100644 arch/sparc/kernel/urtt_fill.S diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h index 71b5a67..781b9f1 100644 --- a/arch/sparc/include/asm/ttable.h +++ b/arch/sparc/include/asm/ttable.h @@ -589,8 +589,8 @@ user_rtt_fill_64bit: \ restored; \ nop; nop; nop; nop; nop; nop; \ nop; nop; nop; nop; nop; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ + ba,a,pt %xcc, user_rtt_fill_fixup_dax; \ + ba,a,pt %xcc, user_rtt_fill_fixup_mna; \ ba,a,pt %xcc, user_rtt_fill_fixup; @@ -652,8 +652,8 @@ user_rtt_fill_32bit: \ restored; \ nop; nop; nop; nop; nop; \ nop; nop; nop; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ + ba,a,pt %xcc, user_rtt_fill_fixup_dax; \ + ba,a,pt %xcc, user_rtt_fill_fixup_mna; \ ba,a,pt %xcc, user_rtt_fill_fixup; diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index 7cf9c6e..fdb1332 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -21,6 +21,7 @@ CFLAGS_REMOVE_perf_event.o := -pg CFLAGS_REMOVE_pcr.o := -pg endif +obj-$(CONFIG_SPARC64) += urtt_fill.o obj-$(CONFIG_SPARC32) += entry.o wof.o wuf.o obj-$(CONFIG_SPARC32) += etrap_32.o obj-$(CONFIG_SPARC32) += rtrap_32.o diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index d08bdaf..216948c 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -14,10 +14,6 @@ #include <asm/visasm.h> #include <asm/processor.h> -#define RTRAP_PSTATE (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE) -#define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV) -#define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG) - #ifdef CONFIG_CONTEXT_TRACKING # define SCHEDULE_USER schedule_user #else @@ -242,52 +238,17 @@ rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 wrpr %g1, %cwp ba,a,pt %xcc, user_rtt_fill_64bit -user_rtt_fill_fixup: - rdpr %cwp, %g1 - add %g1, 1, %g1 - wrpr %g1, 0x0, %cwp - - rdpr %wstate, %g2 - sll %g2, 3, %g2 - wrpr %g2, 0x0, %wstate - - /* We know %canrestore and %otherwin are both zero. */ - - sethi %hi(sparc64_kern_pri_context), %g2 - ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2 - mov PRIMARY_CONTEXT, %g1 - -661: stxa %g2, [%g1] ASI_DMMU - .section .sun4v_1insn_patch, "ax" - .word 661b - stxa %g2, [%g1] ASI_MMU - .previous - - sethi %hi(KERNBASE), %g1 - flush %g1 +user_rtt_fill_fixup_dax: + ba,pt %xcc, user_rtt_fill_fixup_common + mov 1, %g3 - or %g4, FAULT_CODE_WINFIXUP, %g4 - stb %g4, [%g6 + TI_FAULT_CODE] - stx %g5, [%g6 + TI_FAULT_ADDR] +user_rtt_fill_fixup_mna: + ba,pt %xcc, user_rtt_fill_fixup_common + mov 2, %g3 - mov %g6, %l1 - wrpr %g0, 0x0, %tl - -661: nop - .section .sun4v_1insn_patch, "ax" - .word 661b - SET_GL(0) - .previous - - wrpr %g0, RTRAP_PSTATE, %pstate - - mov %l1, %g6 - ldx [%g6 + TI_TASK], %g4 - LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3) - call do_sparc64_fault - add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop +user_rtt_fill_fixup: + ba,pt %xcc, user_rtt_fill_fixup_common + clr %g3 user_rtt_pre_restore: add %g1, 1, %g1 diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S new file mode 100644 index 0000000..5604a2b --- /dev/null +++ b/arch/sparc/kernel/urtt_fill.S @@ -0,0 +1,98 @@ +#include <asm/thread_info.h> +#include <asm/trap_block.h> +#include <asm/spitfire.h> +#include <asm/ptrace.h> +#include <asm/head.h> + + .text + .align 8 + .globl user_rtt_fill_fixup_common +user_rtt_fill_fixup_common: + rdpr %cwp, %g1 + add %g1, 1, %g1 + wrpr %g1, 0x0, %cwp + + rdpr %wstate, %g2 + sll %g2, 3, %g2 + wrpr %g2, 0x0, %wstate + + /* We know %canrestore and %otherwin are both zero. */ + + sethi %hi(sparc64_kern_pri_context), %g2 + ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2 + mov PRIMARY_CONTEXT, %g1 + +661: stxa %g2, [%g1] ASI_DMMU + .section .sun4v_1insn_patch, "ax" + .word 661b + stxa %g2, [%g1] ASI_MMU + .previous + + sethi %hi(KERNBASE), %g1 + flush %g1 + + mov %g4, %l4 + mov %g5, %l5 + brnz,pn %g3, 1f + mov %g3, %l3 + + or %g4, FAULT_CODE_WINFIXUP, %g4 + stb %g4, [%g6 + TI_FAULT_CODE] + stx %g5, [%g6 + TI_FAULT_ADDR] +1: + mov %g6, %l1 + wrpr %g0, 0x0, %tl + +661: nop + .section .sun4v_1insn_patch, "ax" + .word 661b + SET_GL(0) + .previous + + wrpr %g0, RTRAP_PSTATE, %pstate + + mov %l1, %g6 + ldx [%g6 + TI_TASK], %g4 + LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3) + + brnz,pn %l3, 1f + nop + + call do_sparc64_fault + add %sp, PTREGS_OFF, %o0 + ba,pt %xcc, rtrap + nop + +1: cmp %g3, 2 + bne,pn %xcc, 2f + nop + + sethi %hi(tlb_type), %g1 + lduw [%g1 + %lo(tlb_type)], %g1 + cmp %g1, 3 + bne,pt %icc, 1f + add %sp, PTREGS_OFF, %o0 + mov %l4, %o2 + call sun4v_do_mna + mov %l5, %o1 + ba,a,pt %xcc, rtrap +1: mov %l4, %o1 + mov %l5, %o2 + call mem_address_unaligned + nop + ba,a,pt %xcc, rtrap + +2: sethi %hi(tlb_type), %g1 + mov %l4, %o1 + lduw [%g1 + %lo(tlb_type)], %g1 + mov %l5, %o2 + cmp %g1, 3 + bne,pt %icc, 1f + add %sp, PTREGS_OFF, %o0 + call sun4v_data_access_exception + nop + ba,a,pt %xcc, rtrap + +1: call spitfire_data_access_exception + nop + ba,a,pt %xcc, rtrap -- 2.1.2.532.g19b5d50 -- To unsubscribe from this list: send the line "unsubscribe sparclinux" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
