AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-27 17:05:48 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
cba5e0ca05
linux_dsm_epyc7002/arch/sparc/kernel/etrap_64.S
Anthony Yznaga a7159a87a3 sparc64: speed up etrap/rtrap on NG2 and later processors 
For many sun4v processor types, reading or writing a privileged register
has a latency of 40 to 70 cycles.  Use a combination of the low-latency
allclean, otherw, normalw, and nop instructions in etrap and rtrap to
replace 2 rdpr and 5 wrpr instructions and improve etrap/rtrap
performance.  allclean, otherw, and normalw are available on NG2 and
later processors.

The average ticks to execute the flush windows trap ("ta 0x3") with and
without this patch on select platforms:

 CPU            Not patched     Patched    % Latency Reduction

 NG2            1762            1558            -11.58
 NG4            3619            3204            -11.47
 M7             3015            2624            -12.97
 SPARC64-X      829             770              -7.12

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-09 20:20:11 -07:00

259 lines
6.0 KiB
ArmAsm
Raw Blame History

/*
* etrap.S: Preparing for entry into the kernel on Sparc V9.
*
* Copyright (C) 1996, 1997 David S. Miller (davem@caip.rutgers.edu)
* Copyright (C) 1997, 1998, 1999 Jakub Jelinek (jj@ultra.linux.cz)
*/
#include <asm/asi.h>
#include <asm/pstate.h>
#include <asm/ptrace.h>
#include <asm/page.h>
#include <asm/spitfire.h>
#include <asm/head.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#define TASK_REGOFF (THREAD_SIZE-TRACEREG_SZ-STACKFRAME_SZ)
#define ETRAP_PSTATE1 (PSTATE_TSO | PSTATE_PRIV)
#define ETRAP_PSTATE2 \
(PSTATE_TSO | PSTATE_PEF | PSTATE_PRIV | PSTATE_IE)
/*
* On entry, %g7 is return address - 0x4.
* %g4 and %g5 will be preserved %l4 and %l5 respectively.
*/
.text
.align 64
.globl etrap_syscall, etrap, etrap_irq, etraptl1
etrap: rdpr %pil, %g2
etrap_irq: clr %g3
etrap_syscall: TRAP_LOAD_THREAD_REG(%g6, %g1)
rdpr %tstate, %g1
or %g1, %g3, %g1
sllx %g2, 20, %g3
andcc %g1, TSTATE_PRIV, %g0
or %g1, %g3, %g1
bne,pn %xcc, 1f
sub %sp, STACKFRAME_SZ+TRACEREG_SZ-STACK_BIAS, %g2
661: wrpr %g0, 7, %cleanwin
.section .fast_win_ctrl_1insn_patch, "ax"
.word 661b
.word 0x85880000 ! allclean
.previous
sethi %hi(TASK_REGOFF), %g2
sethi %hi(TSTATE_PEF), %g3
or %g2, %lo(TASK_REGOFF), %g2
and %g1, %g3, %g3
brnz,pn %g3, 1f
add %g6, %g2, %g2
wr %g0, 0, %fprs
1: rdpr %tpc, %g3
stx %g1, [%g2 + STACKFRAME_SZ + PT_V9_TSTATE]
rdpr %tnpc, %g1
stx %g3, [%g2 + STACKFRAME_SZ + PT_V9_TPC]
rd %y, %g3
stx %g1, [%g2 + STACKFRAME_SZ + PT_V9_TNPC]
rdpr %tt, %g1
st %g3, [%g2 + STACKFRAME_SZ + PT_V9_Y]
sethi %hi(PT_REGS_MAGIC), %g3
or %g3, %g1, %g1
st %g1, [%g2 + STACKFRAME_SZ + PT_V9_MAGIC]
rdpr %cansave, %g1
brnz,pt %g1, etrap_save
nop
rdpr %cwp, %g1
add %g1, 2, %g1
wrpr %g1, %cwp
be,pt %xcc, etrap_user_spill
mov ASI_AIUP, %g3
rdpr %otherwin, %g3
brz %g3, etrap_kernel_spill
mov ASI_AIUS, %g3
etrap_user_spill:
wr %g3, 0x0, %asi
ldx [%g6 + TI_FLAGS], %g3
and %g3, _TIF_32BIT, %g3
brnz,pt %g3, etrap_user_spill_32bit
nop
ba,a,pt %xcc, etrap_user_spill_64bit
etrap_save: save %g2, -STACK_BIAS, %sp
mov %g6, %l6
bne,pn %xcc, 3f
mov PRIMARY_CONTEXT, %l4
661: rdpr %canrestore, %g3
.section .fast_win_ctrl_1insn_patch, "ax"
.word 661b
nop
.previous
rdpr %wstate, %g2
661: wrpr %g0, 0, %canrestore
.section .fast_win_ctrl_1insn_patch, "ax"
.word 661b
nop
.previous
sll %g2, 3, %g2
/* Set TI_SYS_FPDEPTH to 1 and clear TI_SYS_NOERROR. */
mov 1, %l5
sth %l5, [%l6 + TI_SYS_NOERROR]
661: wrpr %g3, 0, %otherwin
.section .fast_win_ctrl_1insn_patch, "ax"
.word 661b
.word 0x87880000 ! otherw
.previous
wrpr %g2, 0, %wstate
sethi %hi(sparc64_kern_pri_context), %g2
ldx [%g2 + %lo(sparc64_kern_pri_context)], %g3
661: stxa %g3, [%l4] ASI_DMMU
.section .sun4v_1insn_patch, "ax"
.word 661b
stxa %g3, [%l4] ASI_MMU
.previous
sethi %hi(KERNBASE), %l4
flush %l4
mov ASI_AIUS, %l7
2: mov %g4, %l4
mov %g5, %l5
add %g7, 4, %l2
/* Go to trap time globals so we can save them. */
661: wrpr %g0, ETRAP_PSTATE1, %pstate
.section .sun4v_1insn_patch, "ax"
.word 661b
SET_GL(0)
.previous
stx %g1, [%sp + PTREGS_OFF + PT_V9_G1]
stx %g2, [%sp + PTREGS_OFF + PT_V9_G2]
sllx %l7, 24, %l7
stx %g3, [%sp + PTREGS_OFF + PT_V9_G3]
rdpr %cwp, %l0
stx %g4, [%sp + PTREGS_OFF + PT_V9_G4]
stx %g5, [%sp + PTREGS_OFF + PT_V9_G5]
stx %g6, [%sp + PTREGS_OFF + PT_V9_G6]
stx %g7, [%sp + PTREGS_OFF + PT_V9_G7]
or %l7, %l0, %l7
sethi %hi(TSTATE_TSO | TSTATE_PEF), %l0
or %l7, %l0, %l7
wrpr %l2, %tnpc
wrpr %l7, (TSTATE_PRIV | TSTATE_IE), %tstate
stx %i0, [%sp + PTREGS_OFF + PT_V9_I0]
stx %i1, [%sp + PTREGS_OFF + PT_V9_I1]
stx %i2, [%sp + PTREGS_OFF + PT_V9_I2]
stx %i3, [%sp + PTREGS_OFF + PT_V9_I3]
stx %i4, [%sp + PTREGS_OFF + PT_V9_I4]
stx %i5, [%sp + PTREGS_OFF + PT_V9_I5]
stx %i6, [%sp + PTREGS_OFF + PT_V9_I6]
mov %l6, %g6
stx %i7, [%sp + PTREGS_OFF + PT_V9_I7]
LOAD_PER_CPU_BASE(%g5, %g6, %g4, %g3, %l1)
ldx [%g6 + TI_TASK], %g4
done
3: mov ASI_P, %l7
ldub [%l6 + TI_FPDEPTH], %l5
add %l6, TI_FPSAVED + 1, %l4
srl %l5, 1, %l3
add %l5, 2, %l5
/* Set TI_SYS_FPDEPTH to %l5 and clear TI_SYS_NOERROR. */
sth %l5, [%l6 + TI_SYS_NOERROR]
ba,pt %xcc, 2b
stb %g0, [%l4 + %l3]
nop
etraptl1: /* Save tstate/tpc/tnpc of TL 1-->4 and the tl register itself.
* We place this right after pt_regs on the trap stack.
* The layout is:
* 0x00 TL1's TSTATE
* 0x08 TL1's TPC
* 0x10 TL1's TNPC
* 0x18 TL1's TT
* ...
* 0x58 TL4's TT
* 0x60 TL
*/
TRAP_LOAD_THREAD_REG(%g6, %g1)
sub %sp, ((4 * 8) * 4) + 8, %g2
rdpr %tl, %g1
wrpr %g0, 1, %tl
rdpr %tstate, %g3
stx %g3, [%g2 + STACK_BIAS + 0x00]
rdpr %tpc, %g3
stx %g3, [%g2 + STACK_BIAS + 0x08]
rdpr %tnpc, %g3
stx %g3, [%g2 + STACK_BIAS + 0x10]
rdpr %tt, %g3
stx %g3, [%g2 + STACK_BIAS + 0x18]
wrpr %g0, 2, %tl
rdpr %tstate, %g3
stx %g3, [%g2 + STACK_BIAS + 0x20]
rdpr %tpc, %g3
stx %g3, [%g2 + STACK_BIAS + 0x28]
rdpr %tnpc, %g3
stx %g3, [%g2 + STACK_BIAS + 0x30]
rdpr %tt, %g3
stx %g3, [%g2 + STACK_BIAS + 0x38]
sethi %hi(is_sun4v), %g3
lduw [%g3 + %lo(is_sun4v)], %g3
brnz,pn %g3, finish_tl1_capture
nop
wrpr %g0, 3, %tl
rdpr %tstate, %g3
stx %g3, [%g2 + STACK_BIAS + 0x40]
rdpr %tpc, %g3
stx %g3, [%g2 + STACK_BIAS + 0x48]
rdpr %tnpc, %g3
stx %g3, [%g2 + STACK_BIAS + 0x50]
rdpr %tt, %g3
stx %g3, [%g2 + STACK_BIAS + 0x58]
wrpr %g0, 4, %tl
rdpr %tstate, %g3
stx %g3, [%g2 + STACK_BIAS + 0x60]
rdpr %tpc, %g3
stx %g3, [%g2 + STACK_BIAS + 0x68]
rdpr %tnpc, %g3
stx %g3, [%g2 + STACK_BIAS + 0x70]
rdpr %tt, %g3
stx %g3, [%g2 + STACK_BIAS + 0x78]
stx %g1, [%g2 + STACK_BIAS + 0x80]
finish_tl1_capture:
wrpr %g0, 1, %tl
661: nop
.section .sun4v_1insn_patch, "ax"
.word 661b
SET_GL(1)
.previous
rdpr %tstate, %g1
sub %g2, STACKFRAME_SZ + TRACEREG_SZ - STACK_BIAS, %g2
ba,pt %xcc, 1b
andcc %g1, TSTATE_PRIV, %g0
#undef TASK_REGOFF
#undef ETRAP_PSTATE1
Reference in New Issue View Git Blame Copy Permalink