OpenCloudOS-Kernel/arch/sparc/kernel/ktlb.S

263 lines
5.5 KiB
ArmAsm
Raw Normal View History

/* arch/sparc64/kernel/ktlb.S: Kernel mapping TLB miss handling.
*
* Copyright (C) 1995, 1997, 2005, 2008 David S. Miller <davem@davemloft.net>
* Copyright (C) 1996 Eddie C. Dost (ecd@brainaid.de)
* Copyright (C) 1996 Miguel de Icaza (miguel@nuclecu.unam.mx)
* Copyright (C) 1996,98,99 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
*/
#include <asm/head.h>
#include <asm/asi.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/tsb.h>
.text
.align 32
kvmap_itlb:
/* g6: TAG TARGET */
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_IMMU, %g4
/* sun4v_itlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
kvmap_itlb_4v:
/* Catch kernel NULL pointer calls. */
sethi %hi(PAGE_SIZE), %g5
cmp %g4, %g5
blu,pn %xcc, kvmap_itlb_longpath
nop
KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_itlb_load)
kvmap_itlb_tsb_miss:
sethi %hi(LOW_OBP_ADDRESS), %g5
cmp %g4, %g5
blu,pn %xcc, kvmap_itlb_vmalloc_addr
mov 0x1, %g5
sllx %g5, 32, %g5
cmp %g4, %g5
blu,pn %xcc, kvmap_itlb_obp
nop
kvmap_itlb_vmalloc_addr:
KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath)
TSB_LOCK_TAG(%g1, %g2, %g7)
TSB_WRITE(%g1, %g5, %g6)
/* fallthrough to TLB load */
kvmap_itlb_load:
661: stxa %g5, [%g0] ASI_ITLB_DATA_IN
retry
.section .sun4v_2insn_patch, "ax"
.word 661b
nop
nop
.previous
/* For sun4v the ASI_ITLB_DATA_IN store and the retry
* instruction get nop'd out and we get here to branch
* to the sun4v tlb load code. The registers are setup
* as follows:
*
* %g4: vaddr
* %g5: PTE
* %g6: TAG
*
* The sun4v TLB load wants the PTE in %g3 so we fix that
* up here.
*/
ba,pt %xcc, sun4v_itlb_load
mov %g5, %g3
kvmap_itlb_longpath:
661: rdpr %pstate, %g5
wrpr %g5, PSTATE_AG | PSTATE_MG, %pstate
.section .sun4v_2insn_patch, "ax"
.word 661b
SET_GL(1)
nop
.previous
rdpr %tpc, %g5
ba,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_ITLB, %g4
kvmap_itlb_obp:
OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_itlb_longpath)
TSB_LOCK_TAG(%g1, %g2, %g7)
TSB_WRITE(%g1, %g5, %g6)
ba,pt %xcc, kvmap_itlb_load
nop
kvmap_dtlb_obp:
OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_dtlb_longpath)
TSB_LOCK_TAG(%g1, %g2, %g7)
TSB_WRITE(%g1, %g5, %g6)
ba,pt %xcc, kvmap_dtlb_load
nop
[SPARC64]: Fix boot failures on SunBlade-150 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>
2005-10-13 03:22:46 +08:00
sparc64: Fix physical memory management regressions with large max_phys_bits. If max_phys_bits needs to be > 43 (f.e. for T4 chips), things like DEBUG_PAGEALLOC stop working because the 3-level page tables only can cover up to 43 bits. Another problem is that when we increased MAX_PHYS_ADDRESS_BITS up to 47, several statically allocated tables became enormous. Compounding this is that we will need to support up to 49 bits of physical addressing for M7 chips. The two tables in question are sparc64_valid_addr_bitmap and kpte_linear_bitmap. The first holds a bitmap, with 1 bit for each 4MB chunk of physical memory, indicating whether that chunk actually exists in the machine and is valid. The second table is a set of 2-bit values which tell how large of a mapping (4MB, 256MB, 2GB, 16GB, respectively) we can use at each 256MB chunk of ram in the system. These tables are huge and take up an enormous amount of the BSS section of the sparc64 kernel image. Specifically, the sparc64_valid_addr_bitmap is 4MB, and the kpte_linear_bitmap is 128K. So let's solve the space wastage and the DEBUG_PAGEALLOC problem at the same time, by using the kernel page tables (as designed) to manage this information. We have to keep using large mappings when DEBUG_PAGEALLOC is disabled, and we do this by encoding huge PMDs and PUDs. On a T4-2 with 256GB of ram the kernel page table takes up 16K with DEBUG_PAGEALLOC disabled and 256MB with it enabled. Furthermore, this memory is dynamically allocated at run time rather than coded statically into the kernel image. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Bob Picco <bob.picco@oracle.com>
2014-09-25 11:56:11 +08:00
kvmap_linear_early:
sethi %hi(kern_linear_pte_xor), %g7
ldx [%g7 + %lo(kern_linear_pte_xor)], %g2
ba,pt %xcc, kvmap_dtlb_tsb4m_load
xor %g2, %g4, %g5
.align 32
kvmap_dtlb_tsb4m_load:
TSB_LOCK_TAG(%g1, %g2, %g7)
TSB_WRITE(%g1, %g5, %g6)
ba,pt %xcc, kvmap_dtlb_load
nop
kvmap_dtlb:
/* %g6: TAG TARGET */
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_DMMU, %g4
/* sun4v_dtlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
kvmap_dtlb_4v:
brgez,pn %g4, kvmap_dtlb_nonlinear
nop
#ifdef CONFIG_DEBUG_PAGEALLOC
/* Index through the base page size TSB even for linear
* mappings when using page allocation debugging.
*/
KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load)
#else
/* Correct TAG_TARGET is already in %g6, check 4mb TSB. */
KERN_TSB4M_LOOKUP_TL1(%g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load)
#endif
sparc64: Fix physical memory management regressions with large max_phys_bits. If max_phys_bits needs to be > 43 (f.e. for T4 chips), things like DEBUG_PAGEALLOC stop working because the 3-level page tables only can cover up to 43 bits. Another problem is that when we increased MAX_PHYS_ADDRESS_BITS up to 47, several statically allocated tables became enormous. Compounding this is that we will need to support up to 49 bits of physical addressing for M7 chips. The two tables in question are sparc64_valid_addr_bitmap and kpte_linear_bitmap. The first holds a bitmap, with 1 bit for each 4MB chunk of physical memory, indicating whether that chunk actually exists in the machine and is valid. The second table is a set of 2-bit values which tell how large of a mapping (4MB, 256MB, 2GB, 16GB, respectively) we can use at each 256MB chunk of ram in the system. These tables are huge and take up an enormous amount of the BSS section of the sparc64 kernel image. Specifically, the sparc64_valid_addr_bitmap is 4MB, and the kpte_linear_bitmap is 128K. So let's solve the space wastage and the DEBUG_PAGEALLOC problem at the same time, by using the kernel page tables (as designed) to manage this information. We have to keep using large mappings when DEBUG_PAGEALLOC is disabled, and we do this by encoding huge PMDs and PUDs. On a T4-2 with 256GB of ram the kernel page table takes up 16K with DEBUG_PAGEALLOC disabled and 256MB with it enabled. Furthermore, this memory is dynamically allocated at run time rather than coded statically into the kernel image. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Bob Picco <bob.picco@oracle.com>
2014-09-25 11:56:11 +08:00
/* Linear mapping TSB lookup failed. Fallthrough to kernel
* page table based lookup.
*/
.globl kvmap_linear_patch
kvmap_linear_patch:
sparc64: Fix physical memory management regressions with large max_phys_bits. If max_phys_bits needs to be > 43 (f.e. for T4 chips), things like DEBUG_PAGEALLOC stop working because the 3-level page tables only can cover up to 43 bits. Another problem is that when we increased MAX_PHYS_ADDRESS_BITS up to 47, several statically allocated tables became enormous. Compounding this is that we will need to support up to 49 bits of physical addressing for M7 chips. The two tables in question are sparc64_valid_addr_bitmap and kpte_linear_bitmap. The first holds a bitmap, with 1 bit for each 4MB chunk of physical memory, indicating whether that chunk actually exists in the machine and is valid. The second table is a set of 2-bit values which tell how large of a mapping (4MB, 256MB, 2GB, 16GB, respectively) we can use at each 256MB chunk of ram in the system. These tables are huge and take up an enormous amount of the BSS section of the sparc64 kernel image. Specifically, the sparc64_valid_addr_bitmap is 4MB, and the kpte_linear_bitmap is 128K. So let's solve the space wastage and the DEBUG_PAGEALLOC problem at the same time, by using the kernel page tables (as designed) to manage this information. We have to keep using large mappings when DEBUG_PAGEALLOC is disabled, and we do this by encoding huge PMDs and PUDs. On a T4-2 with 256GB of ram the kernel page table takes up 16K with DEBUG_PAGEALLOC disabled and 256MB with it enabled. Furthermore, this memory is dynamically allocated at run time rather than coded statically into the kernel image. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Bob Picco <bob.picco@oracle.com>
2014-09-25 11:56:11 +08:00
ba,a,pt %xcc, kvmap_linear_early
kvmap_dtlb_vmalloc_addr:
KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
TSB_LOCK_TAG(%g1, %g2, %g7)
TSB_WRITE(%g1, %g5, %g6)
/* fallthrough to TLB load */
kvmap_dtlb_load:
661: stxa %g5, [%g0] ASI_DTLB_DATA_IN ! Reload TLB
retry
.section .sun4v_2insn_patch, "ax"
.word 661b
nop
nop
.previous
/* For sun4v the ASI_DTLB_DATA_IN store and the retry
* instruction get nop'd out and we get here to branch
* to the sun4v tlb load code. The registers are setup
* as follows:
*
* %g4: vaddr
* %g5: PTE
* %g6: TAG
*
* The sun4v TLB load wants the PTE in %g3 so we fix that
* up here.
*/
ba,pt %xcc, sun4v_dtlb_load
mov %g5, %g3
#ifdef CONFIG_SPARSEMEM_VMEMMAP
kvmap_vmemmap:
sub %g4, %g5, %g5
srlx %g5, ILOG2_4MB, %g5
sethi %hi(vmemmap_table), %g1
sllx %g5, 3, %g5
or %g1, %lo(vmemmap_table), %g1
ba,pt %xcc, kvmap_dtlb_load
ldx [%g1 + %g5], %g5
#endif
kvmap_dtlb_nonlinear:
/* Catch kernel NULL pointer derefs. */
sethi %hi(PAGE_SIZE), %g5
cmp %g4, %g5
bleu,pn %xcc, kvmap_dtlb_longpath
nop
#ifdef CONFIG_SPARSEMEM_VMEMMAP
/* Do not use the TSB for vmemmap. */
mov (VMEMMAP_BASE >> 40), %g5
sllx %g5, 40, %g5
cmp %g4,%g5
bgeu,pn %xcc, kvmap_vmemmap
nop
#endif
KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load)
kvmap_dtlb_tsbmiss:
sethi %hi(MODULES_VADDR), %g5
cmp %g4, %g5
blu,pn %xcc, kvmap_dtlb_longpath
mov (VMALLOC_END >> 40), %g5
sllx %g5, 40, %g5
cmp %g4, %g5
bgeu,pn %xcc, kvmap_dtlb_longpath
nop
kvmap_check_obp:
sethi %hi(LOW_OBP_ADDRESS), %g5
cmp %g4, %g5
blu,pn %xcc, kvmap_dtlb_vmalloc_addr
mov 0x1, %g5
sllx %g5, 32, %g5
cmp %g4, %g5
blu,pn %xcc, kvmap_dtlb_obp
nop
ba,pt %xcc, kvmap_dtlb_vmalloc_addr
nop
kvmap_dtlb_longpath:
661: rdpr %pstate, %g5
wrpr %g5, PSTATE_AG | PSTATE_MG, %pstate
.section .sun4v_2insn_patch, "ax"
.word 661b
SET_GL(1)
ldxa [%g0] ASI_SCRATCHPAD, %g5
.previous
rdpr %tl, %g3
cmp %g3, 1
661: mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_DMMU, %g5
.section .sun4v_2insn_patch, "ax"
.word 661b
ldx [%g5 + HV_FAULT_D_ADDR_OFFSET], %g5
nop
.previous
be,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_DTLB, %g4
ba,pt %xcc, winfix_trampoline
nop