c9c1083074
The sequence to move over to the Linux trap tables from the firmware ones needs to be more air tight. It turns out that to be %100 safe we do need to be able to translate OBP mappings in our TLB miss handlers early. In order not to eat up a lot of kernel image memory with static page tables, just use the translations array in the OBP TLB miss handlers. That solves the bulk of the problem. Furthermore, to make sure the OBP TLB miss path will work even before the fixed MMU globals are loaded, explicitly load %g1 to TLB_SFSR at the beginning of the i-TLB and d-TLB miss handlers. To ease the OBP TLB miss walking of the prom_trans[] array, we sort it then delete all of the non-OBP entries in there (for example, there are entries for the kernel image itself which we're not interested in at all). We also save about 32K of kernel image size with this change. Not a bad side effect :-) There are still some reasons why trampoline.S can't use the setup_trap_table() yet. The most noteworthy are: 1) OBP boots secondary processors with non-bias'd stack for some reason. This is easily fixed by using a small bootup stack in the kernel image explicitly for this purpose. 2) Doing a firmware call via the normal C call prom_set_trap_table() goes through the whole OBP enter/exit sequence that saves and restores OBP and Linux kernel state in the MMUs. This path unfortunately does a "flush %g6" while loading up the OBP locked TLB entries for the firmware call. If we setup the %g6 in the trampoline.S code properly, that is in the PAGE_OFFSET linear mapping, but we're not on the kernel trap table yet so those addresses won't translate properly. One idea is to do a by-hand firmware call like we do in the early bootup code and elsewhere here in trampoline.S But this fails as well, as aparently the secondary processors are not booted with OBP's special locked TLB entries loaded. These are necessary for the firwmare to processes TLB misses correctly up until the point where we take over the trap table. This does need to be resolved at some point. Signed-off-by: David S. Miller <davem@davemloft.net>
80 lines
2.4 KiB
ArmAsm
80 lines
2.4 KiB
ArmAsm
/* $Id: itlb_base.S,v 1.12 2002/02/09 19:49:30 davem Exp $
|
|
* itlb_base.S: Front end to ITLB miss replacement strategy.
|
|
* This is included directly into the trap table.
|
|
*
|
|
* Copyright (C) 1996,1998 David S. Miller (davem@redhat.com)
|
|
* Copyright (C) 1997,1998 Jakub Jelinek (jj@ultra.linux.cz)
|
|
*/
|
|
|
|
#if PAGE_SHIFT == 13
|
|
/*
|
|
* To compute vpte offset, we need to do ((addr >> 13) << 3),
|
|
* which can be optimized to (addr >> 10) if bits 10/11/12 can
|
|
* be guaranteed to be 0 ... mmu_context.h does guarantee this
|
|
* by only using 10 bits in the hwcontext value.
|
|
*/
|
|
#define CREATE_VPTE_OFFSET1(r1, r2) \
|
|
srax r1, 10, r2
|
|
#define CREATE_VPTE_OFFSET2(r1, r2) nop
|
|
#else /* PAGE_SHIFT */
|
|
#define CREATE_VPTE_OFFSET1(r1, r2) \
|
|
srax r1, PAGE_SHIFT, r2
|
|
#define CREATE_VPTE_OFFSET2(r1, r2) \
|
|
sllx r2, 3, r2
|
|
#endif /* PAGE_SHIFT */
|
|
|
|
|
|
/* Ways we can get here:
|
|
*
|
|
* 1) Nucleus instruction misses from module code.
|
|
* 2) All user instruction misses.
|
|
*
|
|
* All real page faults merge their code paths to the
|
|
* sparc64_realfault_common label below.
|
|
*/
|
|
|
|
/* ITLB ** ICACHE line 1: Quick user TLB misses */
|
|
mov TLB_SFSR, %g1
|
|
ldxa [%g1 + %g1] ASI_IMMU, %g4 ! Get TAG_ACCESS
|
|
CREATE_VPTE_OFFSET1(%g4, %g6) ! Create VPTE offset
|
|
CREATE_VPTE_OFFSET2(%g4, %g6) ! Create VPTE offset
|
|
ldxa [%g3 + %g6] ASI_P, %g5 ! Load VPTE
|
|
1: brgez,pn %g5, 3f ! Not valid, branch out
|
|
sethi %hi(_PAGE_EXEC), %g4 ! Delay-slot
|
|
andcc %g5, %g4, %g0 ! Executable?
|
|
|
|
/* ITLB ** ICACHE line 2: Real faults */
|
|
be,pn %xcc, 3f ! Nope, branch.
|
|
nop ! Delay-slot
|
|
2: stxa %g5, [%g0] ASI_ITLB_DATA_IN ! Load PTE into TLB
|
|
retry ! Trap return
|
|
3: rdpr %pstate, %g4 ! Move into alt-globals
|
|
wrpr %g4, PSTATE_AG|PSTATE_MG, %pstate
|
|
rdpr %tpc, %g5 ! And load faulting VA
|
|
mov FAULT_CODE_ITLB, %g4 ! It was read from ITLB
|
|
|
|
/* ITLB ** ICACHE line 3: Finish faults */
|
|
sparc64_realfault_common: ! Called by dtlb_miss
|
|
stb %g4, [%g6 + TI_FAULT_CODE]
|
|
stx %g5, [%g6 + TI_FAULT_ADDR]
|
|
ba,pt %xcc, etrap ! Save state
|
|
1: rd %pc, %g7 ! ...
|
|
call do_sparc64_fault ! Call fault handler
|
|
add %sp, PTREGS_OFF, %o0! Compute pt_regs arg
|
|
ba,pt %xcc, rtrap_clr_l6 ! Restore cpu state
|
|
nop
|
|
|
|
/* ITLB ** ICACHE line 4: Window fixups */
|
|
winfix_trampoline:
|
|
rdpr %tpc, %g3 ! Prepare winfixup TNPC
|
|
or %g3, 0x7c, %g3 ! Compute branch offset
|
|
wrpr %g3, %tnpc ! Write it into TNPC
|
|
done ! Do it to it
|
|
nop
|
|
nop
|
|
nop
|
|
nop
|
|
|
|
#undef CREATE_VPTE_OFFSET1
|
|
#undef CREATE_VPTE_OFFSET2
|