linux_dsm_epyc7002/arch/s390/kernel/base.S
Martin Schwidefsky ce3dc44749 s390: add support for virtually mapped kernel stacks
With virtually mapped kernel stacks the kernel stack overflow detection
is now fault based, every stack has a guard page in the vmalloc space.
The panic_stack is renamed to nodat_stack and is used for all function
that need to run without DAT, e.g. memcpy_real or do_start_kdump.

The main effect is a reduction in the kernel image size as with vmap
stacks the old style overflow checking that adds two instructions per
function is not needed anymore. Result from bloat-o-meter:

add/remove: 20/1 grow/shrink: 13/26854 up/down: 2198/-216240 (-214042)

In regard to performance the micro-benchmark for fork has a hit of a
few microseconds, allocating 4 pages in vmalloc space is more expensive
compare to an order-2 page allocation. But with real workload I could
not find a noticeable difference.

Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2018-10-09 11:20:57 +02:00

150 lines
3.2 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
/*
* arch/s390/kernel/base.S
*
* Copyright IBM Corp. 2006, 2007
* Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
* Michael Holzheu <holzheu@de.ibm.com>
*/
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/nospec-insn.h>
#include <asm/ptrace.h>
#include <asm/sigp.h>
GEN_BR_THUNK %r9
GEN_BR_THUNK %r14
ENTRY(s390_base_mcck_handler)
basr %r13,0
0: lg %r15,__LC_NODAT_STACK # load panic stack
aghi %r15,-STACK_FRAME_OVERHEAD
larl %r1,s390_base_mcck_handler_fn
lg %r9,0(%r1)
ltgr %r9,%r9
jz 1f
BASR_EX %r14,%r9
1: la %r1,4095
lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
lpswe __LC_MCK_OLD_PSW
.section .bss
.align 8
.globl s390_base_mcck_handler_fn
s390_base_mcck_handler_fn:
.quad 0
.previous
ENTRY(s390_base_ext_handler)
stmg %r0,%r15,__LC_SAVE_AREA_ASYNC
basr %r13,0
0: aghi %r15,-STACK_FRAME_OVERHEAD
larl %r1,s390_base_ext_handler_fn
lg %r9,0(%r1)
ltgr %r9,%r9
jz 1f
BASR_EX %r14,%r9
1: lmg %r0,%r15,__LC_SAVE_AREA_ASYNC
ni __LC_EXT_OLD_PSW+1,0xfd # clear wait state bit
lpswe __LC_EXT_OLD_PSW
.section .bss
.align 8
.globl s390_base_ext_handler_fn
s390_base_ext_handler_fn:
.quad 0
.previous
ENTRY(s390_base_pgm_handler)
stmg %r0,%r15,__LC_SAVE_AREA_SYNC
basr %r13,0
0: aghi %r15,-STACK_FRAME_OVERHEAD
larl %r1,s390_base_pgm_handler_fn
lg %r9,0(%r1)
ltgr %r9,%r9
jz 1f
BASR_EX %r14,%r9
lmg %r0,%r15,__LC_SAVE_AREA_SYNC
lpswe __LC_PGM_OLD_PSW
1: lpswe disabled_wait_psw-0b(%r13)
.align 8
disabled_wait_psw:
.quad 0x0002000180000000,0x0000000000000000 + s390_base_pgm_handler
.section .bss
.align 8
.globl s390_base_pgm_handler_fn
s390_base_pgm_handler_fn:
.quad 0
.previous
#
# Calls diag 308 subcode 1 and continues execution
#
ENTRY(diag308_reset)
larl %r4,.Lctlregs # Save control registers
stctg %c0,%c15,0(%r4)
lg %r2,0(%r4) # Disable lowcore protection
nilh %r2,0xefff
larl %r4,.Lctlreg0
stg %r2,0(%r4)
lctlg %c0,%c0,0(%r4)
larl %r4,.Lfpctl # Floating point control register
stfpc 0(%r4)
larl %r4,.Lprefix # Save prefix register
stpx 0(%r4)
larl %r4,.Lprefix_zero # Set prefix register to 0
spx 0(%r4)
larl %r4,.Lcontinue_psw # Save PSW flags
epsw %r2,%r3
stm %r2,%r3,0(%r4)
larl %r4,.Lrestart_psw # Setup restart PSW at absolute 0
lghi %r3,0
lg %r4,0(%r4) # Save PSW
sturg %r4,%r3 # Use sturg, because of large pages
lghi %r1,1
lghi %r0,0
diag %r0,%r1,0x308
.Lrestart_part2:
lhi %r0,0 # Load r0 with zero
lhi %r1,2 # Use mode 2 = ESAME (dump)
sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to ESAME mode
sam64 # Switch to 64 bit addressing mode
larl %r4,.Lctlregs # Restore control registers
lctlg %c0,%c15,0(%r4)
larl %r4,.Lfpctl # Restore floating point ctl register
lfpc 0(%r4)
larl %r4,.Lprefix # Restore prefix register
spx 0(%r4)
larl %r4,.Lcontinue_psw # Restore PSW flags
lpswe 0(%r4)
.Lcontinue:
BR_EX %r14
.align 16
.Lrestart_psw:
.long 0x00080000,0x80000000 + .Lrestart_part2
.section .data..nosave,"aw",@progbits
.align 8
.Lcontinue_psw:
.quad 0,.Lcontinue
.previous
.section .bss
.align 8
.Lctlreg0:
.quad 0
.Lctlregs:
.rept 16
.quad 0
.endr
.Lfpctl:
.long 0
.Lprefix:
.long 0
.Lprefix_zero:
.long 0
.previous