linux/arch/sparc/kernel/sun4v_tlb_miss.S
Babu Moger 0ae2d26ffe arch/sparc: Avoid DCTI Couples
Avoid un-intended DCTI Couples. Use of DCTI couples is deprecated.
Also address the "Programming Note" for optimal performance.

Here is the complete text from Oracle SPARC Architecture Specs.

6.3.4.7 DCTI Couples
"A delayed control transfer instruction (DCTI) in the delay slot of
another DCTI is referred to as a “DCTI couple”. The use of DCTI couples
is deprecated in the Oracle SPARC Architecture; no new software should
place a DCTI in the delay slot of another DCTI, because on future Oracle
SPARC Architecture implementations DCTI couples may execute either
slowly or differently than the programmer assumes it will.

SPARC V8 and SPARC V9 Compatibility Note
The SPARC V8 architecture left behavior undefined for a DCTI couple. The
SPARC V9 architecture defined behavior in that case, but as of
UltraSPARC Architecture 2005, use of DCTI couples was deprecated.
Software should not expect high performance from DCTI couples, and
performance of DCTI couples should be expected to decline further in
future processors.

Programming Note
As noted in TABLE 6-5 on page 115, an annulled branch-always
(branch-always with a = 1) instruction is not architecturally a DCTI.
However, since not all implementations make that distinction, for
optimal performance, a DCTI should not be placed in the instruction word
immediately following an annulled branch-always instruction (BA,A or
BPA,A)."

Signed-off-by: Babu Moger <babu.moger@oracle.com>
Reviewed-by: Rob Gardner <rob.gardner@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-27 21:51:40 -07:00

437 lines
10 KiB
ArmAsm

/* sun4v_tlb_miss.S: Sun4v TLB miss handlers.
*
* Copyright (C) 2006 <davem@davemloft.net>
*/
.text
.align 32
/* Load ITLB fault information into VADDR and CTX, using BASE. */
#define LOAD_ITLB_INFO(BASE, VADDR, CTX) \
ldx [BASE + HV_FAULT_I_ADDR_OFFSET], VADDR; \
ldx [BASE + HV_FAULT_I_CTX_OFFSET], CTX;
/* Load DTLB fault information into VADDR and CTX, using BASE. */
#define LOAD_DTLB_INFO(BASE, VADDR, CTX) \
ldx [BASE + HV_FAULT_D_ADDR_OFFSET], VADDR; \
ldx [BASE + HV_FAULT_D_CTX_OFFSET], CTX;
/* DEST = (VADDR >> 22)
*
* Branch to ZERO_CTX_LABEL if context is zero.
*/
#define COMPUTE_TAG_TARGET(DEST, VADDR, CTX, ZERO_CTX_LABEL) \
srlx VADDR, 22, DEST; \
brz,pn CTX, ZERO_CTX_LABEL; \
nop;
/* Create TSB pointer. This is something like:
*
* index_mask = (512 << (tsb_reg & 0x7UL)) - 1UL;
* tsb_base = tsb_reg & ~0x7UL;
* tsb_index = ((vaddr >> HASH_SHIFT) & tsb_mask);
* tsb_ptr = tsb_base + (tsb_index * 16);
*/
#define COMPUTE_TSB_PTR(TSB_PTR, VADDR, HASH_SHIFT, TMP1, TMP2) \
and TSB_PTR, 0x7, TMP1; \
mov 512, TMP2; \
andn TSB_PTR, 0x7, TSB_PTR; \
sllx TMP2, TMP1, TMP2; \
srlx VADDR, HASH_SHIFT, TMP1; \
sub TMP2, 1, TMP2; \
and TMP1, TMP2, TMP1; \
sllx TMP1, 4, TMP1; \
add TSB_PTR, TMP1, TSB_PTR;
sun4v_itlb_miss:
/* Load MMU Miss base into %g2. */
ldxa [%g0] ASI_SCRATCHPAD, %g2
/* Load UTSB reg into %g1. */
mov SCRATCHPAD_UTSBREG1, %g1
ldxa [%g1] ASI_SCRATCHPAD, %g1
LOAD_ITLB_INFO(%g2, %g4, %g5)
COMPUTE_TAG_TARGET(%g6, %g4, %g5, kvmap_itlb_4v)
COMPUTE_TSB_PTR(%g1, %g4, PAGE_SHIFT, %g3, %g7)
/* Load TSB tag/pte into %g2/%g3 and compare the tag. */
ldda [%g1] ASI_QUAD_LDD_PHYS_4V, %g2
cmp %g2, %g6
bne,a,pn %xcc, tsb_miss_page_table_walk
mov FAULT_CODE_ITLB, %g3
andcc %g3, _PAGE_EXEC_4V, %g0
be,a,pn %xcc, tsb_do_fault
mov FAULT_CODE_ITLB, %g3
/* We have a valid entry, make hypervisor call to load
* I-TLB and return from trap.
*
* %g3: PTE
* %g4: vaddr
*/
sun4v_itlb_load:
ldxa [%g0] ASI_SCRATCHPAD, %g6
mov %o0, %g1 ! save %o0
mov %o1, %g2 ! save %o1
mov %o2, %g5 ! save %o2
mov %o3, %g7 ! save %o3
mov %g4, %o0 ! vaddr
ldx [%g6 + HV_FAULT_I_CTX_OFFSET], %o1 ! ctx
mov %g3, %o2 ! PTE
mov HV_MMU_IMMU, %o3 ! flags
ta HV_MMU_MAP_ADDR_TRAP
brnz,pn %o0, sun4v_itlb_error
mov %g2, %o1 ! restore %o1
mov %g1, %o0 ! restore %o0
mov %g5, %o2 ! restore %o2
mov %g7, %o3 ! restore %o3
retry
sun4v_dtlb_miss:
/* Load MMU Miss base into %g2. */
ldxa [%g0] ASI_SCRATCHPAD, %g2
/* Load UTSB reg into %g1. */
mov SCRATCHPAD_UTSBREG1, %g1
ldxa [%g1] ASI_SCRATCHPAD, %g1
LOAD_DTLB_INFO(%g2, %g4, %g5)
COMPUTE_TAG_TARGET(%g6, %g4, %g5, kvmap_dtlb_4v)
COMPUTE_TSB_PTR(%g1, %g4, PAGE_SHIFT, %g3, %g7)
/* Load TSB tag/pte into %g2/%g3 and compare the tag. */
ldda [%g1] ASI_QUAD_LDD_PHYS_4V, %g2
cmp %g2, %g6
bne,a,pn %xcc, tsb_miss_page_table_walk
mov FAULT_CODE_DTLB, %g3
/* We have a valid entry, make hypervisor call to load
* D-TLB and return from trap.
*
* %g3: PTE
* %g4: vaddr
*/
sun4v_dtlb_load:
ldxa [%g0] ASI_SCRATCHPAD, %g6
mov %o0, %g1 ! save %o0
mov %o1, %g2 ! save %o1
mov %o2, %g5 ! save %o2
mov %o3, %g7 ! save %o3
mov %g4, %o0 ! vaddr
ldx [%g6 + HV_FAULT_D_CTX_OFFSET], %o1 ! ctx
mov %g3, %o2 ! PTE
mov HV_MMU_DMMU, %o3 ! flags
ta HV_MMU_MAP_ADDR_TRAP
brnz,pn %o0, sun4v_dtlb_error
mov %g2, %o1 ! restore %o1
mov %g1, %o0 ! restore %o0
mov %g5, %o2 ! restore %o2
mov %g7, %o3 ! restore %o3
retry
sun4v_dtlb_prot:
SET_GL(1)
/* Load MMU Miss base into %g5. */
ldxa [%g0] ASI_SCRATCHPAD, %g5
ldx [%g5 + HV_FAULT_D_ADDR_OFFSET], %g5
rdpr %tl, %g1
cmp %g1, 1
bgu,pn %xcc, winfix_trampoline
mov FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4
ba,pt %xcc, sparc64_realfault_common
nop
/* Called from trap table:
* %g4: vaddr
* %g5: context
* %g6: TAG TARGET
*/
sun4v_itsb_miss:
mov SCRATCHPAD_UTSBREG1, %g1
ldxa [%g1] ASI_SCRATCHPAD, %g1
brz,pn %g5, kvmap_itlb_4v
mov FAULT_CODE_ITLB, %g3
ba,a,pt %xcc, sun4v_tsb_miss_common
/* Called from trap table:
* %g4: vaddr
* %g5: context
* %g6: TAG TARGET
*/
sun4v_dtsb_miss:
mov SCRATCHPAD_UTSBREG1, %g1
ldxa [%g1] ASI_SCRATCHPAD, %g1
brz,pn %g5, kvmap_dtlb_4v
mov FAULT_CODE_DTLB, %g3
/* fallthrough */
sun4v_tsb_miss_common:
COMPUTE_TSB_PTR(%g1, %g4, PAGE_SHIFT, %g5, %g7)
sub %g2, TRAP_PER_CPU_FAULT_INFO, %g2
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
mov SCRATCHPAD_UTSBREG2, %g5
ldxa [%g5] ASI_SCRATCHPAD, %g5
cmp %g5, -1
be,pt %xcc, 80f
nop
COMPUTE_TSB_PTR(%g5, %g4, REAL_HPAGE_SHIFT, %g2, %g7)
/* That clobbered %g2, reload it. */
ldxa [%g0] ASI_SCRATCHPAD, %g2
sub %g2, TRAP_PER_CPU_FAULT_INFO, %g2
80: stx %g5, [%g2 + TRAP_PER_CPU_TSB_HUGE_TEMP]
#endif
ba,pt %xcc, tsb_miss_page_table_walk_sun4v_fastpath
ldx [%g2 + TRAP_PER_CPU_PGD_PADDR], %g7
sun4v_itlb_error:
rdpr %tl, %g1
cmp %g1, 1
ble,pt %icc, sun4v_bad_ra
or %g0, FAULT_CODE_BAD_RA | FAULT_CODE_ITLB, %g1
sethi %hi(sun4v_err_itlb_vaddr), %g1
stx %g4, [%g1 + %lo(sun4v_err_itlb_vaddr)]
sethi %hi(sun4v_err_itlb_ctx), %g1
ldxa [%g0] ASI_SCRATCHPAD, %g6
ldx [%g6 + HV_FAULT_I_CTX_OFFSET], %o1
stx %o1, [%g1 + %lo(sun4v_err_itlb_ctx)]
sethi %hi(sun4v_err_itlb_pte), %g1
stx %g3, [%g1 + %lo(sun4v_err_itlb_pte)]
sethi %hi(sun4v_err_itlb_error), %g1
stx %o0, [%g1 + %lo(sun4v_err_itlb_error)]
sethi %hi(1f), %g7
rdpr %tl, %g4
ba,pt %xcc, etraptl1
1: or %g7, %lo(1f), %g7
mov %l4, %o1
call sun4v_itlb_error_report
add %sp, PTREGS_OFF, %o0
/* NOTREACHED */
sun4v_dtlb_error:
rdpr %tl, %g1
cmp %g1, 1
ble,pt %icc, sun4v_bad_ra
or %g0, FAULT_CODE_BAD_RA | FAULT_CODE_DTLB, %g1
sethi %hi(sun4v_err_dtlb_vaddr), %g1
stx %g4, [%g1 + %lo(sun4v_err_dtlb_vaddr)]
sethi %hi(sun4v_err_dtlb_ctx), %g1
ldxa [%g0] ASI_SCRATCHPAD, %g6
ldx [%g6 + HV_FAULT_D_CTX_OFFSET], %o1
stx %o1, [%g1 + %lo(sun4v_err_dtlb_ctx)]
sethi %hi(sun4v_err_dtlb_pte), %g1
stx %g3, [%g1 + %lo(sun4v_err_dtlb_pte)]
sethi %hi(sun4v_err_dtlb_error), %g1
stx %o0, [%g1 + %lo(sun4v_err_dtlb_error)]
sethi %hi(1f), %g7
rdpr %tl, %g4
ba,pt %xcc, etraptl1
1: or %g7, %lo(1f), %g7
mov %l4, %o1
call sun4v_dtlb_error_report
add %sp, PTREGS_OFF, %o0
/* NOTREACHED */
sun4v_bad_ra:
or %g0, %g4, %g5
ba,pt %xcc, sparc64_realfault_common
or %g1, %g0, %g4
/* NOTREACHED */
/* Instruction Access Exception, tl0. */
sun4v_iacc:
ldxa [%g0] ASI_SCRATCHPAD, %g2
ldx [%g2 + HV_FAULT_I_TYPE_OFFSET], %g3
ldx [%g2 + HV_FAULT_I_ADDR_OFFSET], %g4
ldx [%g2 + HV_FAULT_I_CTX_OFFSET], %g5
sllx %g3, 16, %g3
or %g5, %g3, %g5
ba,pt %xcc, etrap
rd %pc, %g7
mov %l4, %o1
mov %l5, %o2
call sun4v_insn_access_exception
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
/* Instruction Access Exception, tl1. */
sun4v_iacc_tl1:
ldxa [%g0] ASI_SCRATCHPAD, %g2
ldx [%g2 + HV_FAULT_I_TYPE_OFFSET], %g3
ldx [%g2 + HV_FAULT_I_ADDR_OFFSET], %g4
ldx [%g2 + HV_FAULT_I_CTX_OFFSET], %g5
sllx %g3, 16, %g3
or %g5, %g3, %g5
ba,pt %xcc, etraptl1
rd %pc, %g7
mov %l4, %o1
mov %l5, %o2
call sun4v_insn_access_exception_tl1
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
/* Data Access Exception, tl0. */
sun4v_dacc:
ldxa [%g0] ASI_SCRATCHPAD, %g2
ldx [%g2 + HV_FAULT_D_TYPE_OFFSET], %g3
ldx [%g2 + HV_FAULT_D_ADDR_OFFSET], %g4
ldx [%g2 + HV_FAULT_D_CTX_OFFSET], %g5
sllx %g3, 16, %g3
or %g5, %g3, %g5
ba,pt %xcc, etrap
rd %pc, %g7
mov %l4, %o1
mov %l5, %o2
call sun4v_data_access_exception
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
/* Data Access Exception, tl1. */
sun4v_dacc_tl1:
ldxa [%g0] ASI_SCRATCHPAD, %g2
ldx [%g2 + HV_FAULT_D_TYPE_OFFSET], %g3
ldx [%g2 + HV_FAULT_D_ADDR_OFFSET], %g4
ldx [%g2 + HV_FAULT_D_CTX_OFFSET], %g5
sllx %g3, 16, %g3
or %g5, %g3, %g5
ba,pt %xcc, etraptl1
rd %pc, %g7
mov %l4, %o1
mov %l5, %o2
call sun4v_data_access_exception_tl1
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
/* Memory Address Unaligned. */
sun4v_mna:
/* Window fixup? */
rdpr %tl, %g2
cmp %g2, 1
ble,pt %icc, 1f
nop
SET_GL(1)
ldxa [%g0] ASI_SCRATCHPAD, %g2
ldx [%g2 + HV_FAULT_D_ADDR_OFFSET], %g5
mov HV_FAULT_TYPE_UNALIGNED, %g3
ldx [%g2 + HV_FAULT_D_CTX_OFFSET], %g4
sllx %g3, 16, %g3
or %g4, %g3, %g4
ba,pt %xcc, winfix_mna
rdpr %tpc, %g3
/* not reached */
1: ldxa [%g0] ASI_SCRATCHPAD, %g2
mov HV_FAULT_TYPE_UNALIGNED, %g3
ldx [%g2 + HV_FAULT_D_ADDR_OFFSET], %g4
ldx [%g2 + HV_FAULT_D_CTX_OFFSET], %g5
sllx %g3, 16, %g3
or %g5, %g3, %g5
ba,pt %xcc, etrap
rd %pc, %g7
mov %l4, %o1
mov %l5, %o2
call sun4v_do_mna
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
nop
/* Privileged Action. */
sun4v_privact:
ba,pt %xcc, etrap
rd %pc, %g7
call do_privact
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
/* Unaligned ldd float, tl0. */
sun4v_lddfmna:
ldxa [%g0] ASI_SCRATCHPAD, %g2
ldx [%g2 + HV_FAULT_D_TYPE_OFFSET], %g3
ldx [%g2 + HV_FAULT_D_ADDR_OFFSET], %g4
ldx [%g2 + HV_FAULT_D_CTX_OFFSET], %g5
sllx %g3, 16, %g3
or %g5, %g3, %g5
ba,pt %xcc, etrap
rd %pc, %g7
mov %l4, %o1
mov %l5, %o2
call handle_lddfmna
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
/* Unaligned std float, tl0. */
sun4v_stdfmna:
ldxa [%g0] ASI_SCRATCHPAD, %g2
ldx [%g2 + HV_FAULT_D_TYPE_OFFSET], %g3
ldx [%g2 + HV_FAULT_D_ADDR_OFFSET], %g4
ldx [%g2 + HV_FAULT_D_CTX_OFFSET], %g5
sllx %g3, 16, %g3
or %g5, %g3, %g5
ba,pt %xcc, etrap
rd %pc, %g7
mov %l4, %o1
mov %l5, %o2
call handle_stdfmna
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
#define BRANCH_ALWAYS 0x10680000
#define NOP 0x01000000
#define SUN4V_DO_PATCH(OLD, NEW) \
sethi %hi(NEW), %g1; \
or %g1, %lo(NEW), %g1; \
sethi %hi(OLD), %g2; \
or %g2, %lo(OLD), %g2; \
sub %g1, %g2, %g1; \
sethi %hi(BRANCH_ALWAYS), %g3; \
sll %g1, 11, %g1; \
srl %g1, 11 + 2, %g1; \
or %g3, %lo(BRANCH_ALWAYS), %g3; \
or %g3, %g1, %g3; \
stw %g3, [%g2]; \
sethi %hi(NOP), %g3; \
or %g3, %lo(NOP), %g3; \
stw %g3, [%g2 + 0x4]; \
flush %g2;
.globl sun4v_patch_tlb_handlers
.type sun4v_patch_tlb_handlers,#function
sun4v_patch_tlb_handlers:
SUN4V_DO_PATCH(tl0_iamiss, sun4v_itlb_miss)
SUN4V_DO_PATCH(tl1_iamiss, sun4v_itlb_miss)
SUN4V_DO_PATCH(tl0_damiss, sun4v_dtlb_miss)
SUN4V_DO_PATCH(tl1_damiss, sun4v_dtlb_miss)
SUN4V_DO_PATCH(tl0_daprot, sun4v_dtlb_prot)
SUN4V_DO_PATCH(tl1_daprot, sun4v_dtlb_prot)
SUN4V_DO_PATCH(tl0_iax, sun4v_iacc)
SUN4V_DO_PATCH(tl1_iax, sun4v_iacc_tl1)
SUN4V_DO_PATCH(tl0_dax, sun4v_dacc)
SUN4V_DO_PATCH(tl1_dax, sun4v_dacc_tl1)
SUN4V_DO_PATCH(tl0_mna, sun4v_mna)
SUN4V_DO_PATCH(tl1_mna, sun4v_mna)
SUN4V_DO_PATCH(tl0_lddfmna, sun4v_lddfmna)
SUN4V_DO_PATCH(tl0_stdfmna, sun4v_stdfmna)
SUN4V_DO_PATCH(tl0_privact, sun4v_privact)
retl
nop
.size sun4v_patch_tlb_handlers,.-sun4v_patch_tlb_handlers