linux/arch/s390/kernel/head.S
Heiko Carstens 4ae803253e s390/bitops: optimize set_bit() for constant values
Since zEC12 we have the interlocked-access facility 2 which allows to
use the instructions ni/oi/xi to update a single byte in storage with
compare-and-swap semantics.
So change set_bit(), clear_bit() and change_bit() to generate such code
instead of a compare-and-swap loop (or using the load-and-* instruction
family), if possible.
This reduces the text segment by yet another 8KB (defconfig).

Alternatively the long displacement variants niy/oiy/xiy could have
been used, but the extended displacement field is usually not needed
and therefore would only increase the size of the text segment again.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-10-24 17:16:53 +02:00

502 lines
13 KiB
ArmAsm

/*
* Copyright IBM Corp. 1999, 2010
*
* Author(s): Hartmut Penner <hp@de.ibm.com>
* Martin Schwidefsky <schwidefsky@de.ibm.com>
* Rob van der Heij <rvdhei@iae.nl>
* Heiko Carstens <heiko.carstens@de.ibm.com>
*
* There are 5 different IPL methods
* 1) load the image directly into ram at address 0 and do an PSW restart
* 2) linload will load the image from address 0x10000 to memory 0x10000
* and start the code thru LPSW 0x0008000080010000 (VM only, deprecated)
* 3) generate the tape ipl header, store the generated image on a tape
* and ipl from it
* In case of SL tape you need to IPL 5 times to get past VOL1 etc
* 4) generate the vm reader ipl header, move the generated image to the
* VM reader (use option NOH!) and do a ipl from reader (VM only)
* 5) direct call of start by the SALIPL loader
* We use the cpuid to distinguish between VM and native ipl
* params for kernel are pushed to 0x10400 (see setup.h)
*
*/
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/page.h>
#ifdef CONFIG_64BIT
#define ARCH_OFFSET 4
#else
#define ARCH_OFFSET 0
#endif
__HEAD
#define IPL_BS 0x730
.org 0
.long 0x00080000,0x80000000+iplstart # The first 24 bytes are loaded
.long 0x02000018,0x60000050 # by ipl to addresses 0-23.
.long 0x02000068,0x60000050 # (a PSW and two CCWs).
.fill 80-24,1,0x40 # bytes 24-79 are discarded !!
.long 0x020000f0,0x60000050 # The next 160 byte are loaded
.long 0x02000140,0x60000050 # to addresses 0x18-0xb7
.long 0x02000190,0x60000050 # They form the continuation
.long 0x020001e0,0x60000050 # of the CCW program started
.long 0x02000230,0x60000050 # by ipl and load the range
.long 0x02000280,0x60000050 # 0x0f0-0x730 from the image
.long 0x020002d0,0x60000050 # to the range 0x0f0-0x730
.long 0x02000320,0x60000050 # in memory. At the end of
.long 0x02000370,0x60000050 # the channel program the PSW
.long 0x020003c0,0x60000050 # at location 0 is loaded.
.long 0x02000410,0x60000050 # Initial processing starts
.long 0x02000460,0x60000050 # at 0x200 = iplstart.
.long 0x020004b0,0x60000050
.long 0x02000500,0x60000050
.long 0x02000550,0x60000050
.long 0x020005a0,0x60000050
.long 0x020005f0,0x60000050
.long 0x02000640,0x60000050
.long 0x02000690,0x60000050
.long 0x020006e0,0x20000050
.org 0x200
#
# subroutine to set architecture mode
#
.Lsetmode:
#ifdef CONFIG_64BIT
mvi __LC_AR_MODE_ID,1 # set esame flag
slr %r0,%r0 # set cpuid to zero
lhi %r1,2 # mode 2 = esame (dump)
sigp %r1,%r0,0x12 # switch to esame mode
bras %r13,0f
.fill 16,4,0x0
0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs
sam31 # switch to 31 bit addressing mode
#else
mvi __LC_AR_MODE_ID,0 # set ESA flag (mode 0)
#endif
br %r14
#
# subroutine to wait for end I/O
#
.Lirqwait:
#ifdef CONFIG_64BIT
mvc 0x1f0(16),.Lnewpsw # set up IO interrupt psw
lpsw .Lwaitpsw
.Lioint:
br %r14
.align 8
.Lnewpsw:
.quad 0x0000000080000000,.Lioint
#else
mvc 0x78(8),.Lnewpsw # set up IO interrupt psw
lpsw .Lwaitpsw
.Lioint:
br %r14
.align 8
.Lnewpsw:
.long 0x00080000,0x80000000+.Lioint
#endif
.Lwaitpsw:
.long 0x020a0000,0x80000000+.Lioint
#
# subroutine for loading cards from the reader
#
.Lloader:
la %r4,0(%r14)
la %r3,.Lorb # r2 = address of orb into r2
la %r5,.Lirb # r4 = address of irb
la %r6,.Lccws
la %r7,20
.Linit:
st %r2,4(%r6) # initialize CCW data addresses
la %r2,0x50(%r2)
la %r6,8(%r6)
bct 7,.Linit
lctl %c6,%c6,.Lcr6 # set IO subclass mask
slr %r2,%r2
.Lldlp:
ssch 0(%r3) # load chunk of 1600 bytes
bnz .Llderr
.Lwait4irq:
bas %r14,.Lirqwait
c %r1,0xb8 # compare subchannel number
bne .Lwait4irq
tsch 0(%r5)
slr %r0,%r0
ic %r0,8(%r5) # get device status
chi %r0,8 # channel end ?
be .Lcont
chi %r0,12 # channel end + device end ?
be .Lcont
l %r0,4(%r5)
s %r0,8(%r3) # r0/8 = number of ccws executed
mhi %r0,10 # *10 = number of bytes in ccws
lh %r3,10(%r5) # get residual count
sr %r0,%r3 # #ccws*80-residual=#bytes read
ar %r2,%r0
br %r4 # r2 contains the total size
.Lcont:
ahi %r2,0x640 # add 0x640 to total size
la %r6,.Lccws
la %r7,20
.Lincr:
l %r0,4(%r6) # update CCW data addresses
ahi %r0,0x640
st %r0,4(%r6)
ahi %r6,8
bct 7,.Lincr
b .Lldlp
.Llderr:
lpsw .Lcrash
.align 8
.Lorb: .long 0x00000000,0x0080ff00,.Lccws
.Lirb: .long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
.Lcr6: .long 0xff000000
.Lloadp:.long 0,0
.align 8
.Lcrash:.long 0x000a0000,0x00000000
.align 8
.Lccws: .rept 19
.long 0x02600050,0x00000000
.endr
.long 0x02200050,0x00000000
iplstart:
bas %r14,.Lsetmode # Immediately switch to 64 bit mode
lh %r1,0xb8 # test if subchannel number
bct %r1,.Lnoload # is valid
l %r1,0xb8 # load ipl subchannel number
la %r2,IPL_BS # load start address
bas %r14,.Lloader # load rest of ipl image
l %r12,.Lparm # pointer to parameter area
st %r1,IPL_DEVICE+ARCH_OFFSET-PARMAREA(%r12) # save ipl device number
#
# load parameter file from ipl device
#
.Lagain1:
l %r2,.Linitrd # ramdisk loc. is temp
bas %r14,.Lloader # load parameter file
ltr %r2,%r2 # got anything ?
bz .Lnopf
chi %r2,895
bnh .Lnotrunc
la %r2,895
.Lnotrunc:
l %r4,.Linitrd
clc 0(3,%r4),.L_hdr # if it is HDRx
bz .Lagain1 # skip dataset header
clc 0(3,%r4),.L_eof # if it is EOFx
bz .Lagain1 # skip dateset trailer
la %r5,0(%r4,%r2)
lr %r3,%r2
la %r3,COMMAND_LINE-PARMAREA(%r12) # load adr. of command line
mvc 0(256,%r3),0(%r4)
mvc 256(256,%r3),256(%r4)
mvc 512(256,%r3),512(%r4)
mvc 768(122,%r3),768(%r4)
slr %r0,%r0
b .Lcntlp
.Ldelspc:
ic %r0,0(%r2,%r3)
chi %r0,0x20 # is it a space ?
be .Lcntlp
ahi %r2,1
b .Leolp
.Lcntlp:
brct %r2,.Ldelspc
.Leolp:
slr %r0,%r0
stc %r0,0(%r2,%r3) # terminate buffer
.Lnopf:
#
# load ramdisk from ipl device
#
.Lagain2:
l %r2,.Linitrd # addr of ramdisk
st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12)
bas %r14,.Lloader # load ramdisk
st %r2,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r12) # store size of rd
ltr %r2,%r2
bnz .Lrdcont
st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # no ramdisk found
.Lrdcont:
l %r2,.Linitrd
clc 0(3,%r2),.L_hdr # skip HDRx and EOFx
bz .Lagain2
clc 0(3,%r2),.L_eof
bz .Lagain2
#
# reset files in VM reader
#
stidp .Lcpuid # store cpuid
tm .Lcpuid,0xff # running VM ?
bno .Lnoreset
la %r2,.Lreset
lhi %r3,26
diag %r2,%r3,8
la %r5,.Lirb
stsch 0(%r5) # check if irq is pending
tm 30(%r5),0x0f # by verifying if any of the
bnz .Lwaitforirq # activity or status control
tm 31(%r5),0xff # bits is set in the schib
bz .Lnoreset
.Lwaitforirq:
bas %r14,.Lirqwait # wait for IO interrupt
c %r1,0xb8 # compare subchannel number
bne .Lwaitforirq
la %r5,.Lirb
tsch 0(%r5)
.Lnoreset:
b .Lnoload
#
# everything loaded, go for it
#
.Lnoload:
l %r1,.Lstartup
br %r1
.Linitrd:.long _end # default address of initrd
.Lparm: .long PARMAREA
.Lstartup: .long startup
.Lreset:.byte 0xc3,0xc8,0xc1,0xd5,0xc7,0xc5,0x40,0xd9,0xc4,0xd9,0x40
.byte 0xc1,0xd3,0xd3,0x40,0xd2,0xc5,0xc5,0xd7,0x40,0xd5,0xd6
.byte 0xc8,0xd6,0xd3,0xc4 # "change rdr all keep nohold"
.L_eof: .long 0xc5d6c600 /* C'EOF' */
.L_hdr: .long 0xc8c4d900 /* C'HDR' */
.align 8
.Lcpuid:.fill 8,1,0
#
# SALIPL loader support. Based on a patch by Rob van der Heij.
# This entry point is called directly from the SALIPL loader and
# doesn't need a builtin ipl record.
#
.org 0x800
ENTRY(start)
stm %r0,%r15,0x07b0 # store registers
bas %r14,.Lsetmode # Immediately switch to 64 bit mode
basr %r12,%r0
.base:
l %r11,.parm
l %r8,.cmd # pointer to command buffer
ltr %r9,%r9 # do we have SALIPL parameters?
bp .sk8x8
mvc 0(64,%r8),0x00b0 # copy saved registers
xc 64(240-64,%r8),0(%r8) # remainder of buffer
tr 0(64,%r8),.lowcase
b .gotr
.sk8x8:
mvc 0(240,%r8),0(%r9) # copy iplparms into buffer
.gotr:
slr %r0,%r0
st %r0,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r11)
st %r0,INITRD_START+ARCH_OFFSET-PARMAREA(%r11)
j startup # continue with startup
.cmd: .long COMMAND_LINE # address of command line buffer
.parm: .long PARMAREA
.lowcase:
.byte 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07
.byte 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f
.byte 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17
.byte 0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f
.byte 0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27
.byte 0x28,0x29,0x2a,0x2b,0x2c,0x2d,0x2e,0x2f
.byte 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37
.byte 0x38,0x39,0x3a,0x3b,0x3c,0x3d,0x3e,0x3f
.byte 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47
.byte 0x48,0x49,0x4a,0x4b,0x4c,0x4d,0x4e,0x4f
.byte 0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57
.byte 0x58,0x59,0x5a,0x5b,0x5c,0x5d,0x5e,0x5f
.byte 0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67
.byte 0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f
.byte 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77
.byte 0x78,0x79,0x7a,0x7b,0x7c,0x7d,0x7e,0x7f
.byte 0x80,0x81,0x82,0x83,0x84,0x85,0x86,0x87
.byte 0x88,0x89,0x8a,0x8b,0x8c,0x8d,0x8e,0x8f
.byte 0x90,0x91,0x92,0x93,0x94,0x95,0x96,0x97
.byte 0x98,0x99,0x9a,0x9b,0x9c,0x9d,0x9e,0x9f
.byte 0xa0,0xa1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7
.byte 0xa8,0xa9,0xaa,0xab,0xac,0xad,0xae,0xaf
.byte 0xb0,0xb1,0xb2,0xb3,0xb4,0xb5,0xb6,0xb7
.byte 0xb8,0xb9,0xba,0xbb,0xbc,0xbd,0xbe,0xbf
.byte 0xc0,0x81,0x82,0x83,0x84,0x85,0x86,0x87 # .abcdefg
.byte 0x88,0x89,0xca,0xcb,0xcc,0xcd,0xce,0xcf # hi
.byte 0xd0,0x91,0x92,0x93,0x94,0x95,0x96,0x97 # .jklmnop
.byte 0x98,0x99,0xda,0xdb,0xdc,0xdd,0xde,0xdf # qr
.byte 0xe0,0xe1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7 # ..stuvwx
.byte 0xa8,0xa9,0xea,0xeb,0xec,0xed,0xee,0xef # yz
.byte 0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7
.byte 0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff
#
# startup-code at 0x10000, running in absolute addressing mode
# this is called either by the ipl loader or directly by PSW restart
# or linload or SALIPL
#
.org 0x10000
ENTRY(startup)
j .Lep_startup_normal
.org 0x10008
#
# This is a list of s390 kernel entry points. At address 0x1000f the number of
# valid entry points is stored.
#
# IMPORTANT: Do not change this table, it is s390 kernel ABI!
#
.ascii "S390EP"
.byte 0x00,0x01
#
# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
#
.org 0x10010
ENTRY(startup_kdump)
j .Lep_startup_kdump
.Lep_startup_normal:
#ifdef CONFIG_64BIT
mvi __LC_AR_MODE_ID,1 # set esame flag
slr %r0,%r0 # set cpuid to zero
lhi %r1,2 # mode 2 = esame (dump)
sigp %r1,%r0,0x12 # switch to esame mode
bras %r13,0f
.fill 16,4,0x0
0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs
sam31 # switch to 31 bit addressing mode
#else
mvi __LC_AR_MODE_ID,0 # set ESA flag (mode 0)
#endif
basr %r13,0 # get base
.LPG0:
xc 0x200(256),0x200 # partially clear lowcore
xc 0x300(256),0x300
xc 0xe00(256),0xe00
stck __LC_LAST_UPDATE_CLOCK
spt 6f-.LPG0(%r13)
mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
xc __LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
#ifndef CONFIG_MARCH_G5
# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
.insn s,0xb2b10000,__LC_STFL_FAC_LIST # store facility list
tm __LC_STFL_FAC_LIST,0x01 # stfle available ?
jz 0f
la %r0,1
.insn s,0xb2b00000,__LC_STFL_FAC_LIST # store facility list extended
# verify if all required facilities are supported by the machine
0: la %r1,__LC_STFL_FAC_LIST
la %r2,3f+8-.LPG0(%r13)
l %r3,0(%r2)
1: l %r0,0(%r1)
n %r0,4(%r2)
cl %r0,4(%r2)
jne 2f
la %r1,4(%r1)
la %r2,4(%r2)
ahi %r3,-1
jnz 1b
j 4f
2: l %r15,.Lstack-.LPG0(%r13)
ahi %r15,-96
la %r2,.Lals_string-.LPG0(%r13)
l %r3,.Lsclp_print-.LPG0(%r13)
basr %r14,%r3
lpsw 3f-.LPG0(%r13) # machine type not good enough, crash
.Lals_string:
.asciz "The Linux kernel requires more recent processor hardware"
.Lsclp_print:
.long _sclp_print_early
.Lstack:
.long 0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
.align 16
3: .long 0x000a0000,0x8badcccc
# List of facilities that are required. If not all facilities are present
# the kernel will crash. Format is number of facility words with bits set,
# followed by the facility words.
#if defined(CONFIG_64BIT)
#if defined(CONFIG_MARCH_ZEC12)
.long 3, 0xc100efe3, 0xf46ce800, 0x00400000
#elif defined(CONFIG_MARCH_Z196)
.long 2, 0xc100efe3, 0xf46c0000
#elif defined(CONFIG_MARCH_Z10)
.long 2, 0xc100efe3, 0xf0680000
#elif defined(CONFIG_MARCH_Z9_109)
.long 1, 0xc100efc3
#elif defined(CONFIG_MARCH_Z990)
.long 1, 0xc0002000
#elif defined(CONFIG_MARCH_Z900)
.long 1, 0xc0000000
#endif
#else
#if defined(CONFIG_MARCH_ZEC12)
.long 1, 0x8100c880
#elif defined(CONFIG_MARCH_Z196)
.long 1, 0x8100c880
#elif defined(CONFIG_MARCH_Z10)
.long 1, 0x8100c880
#elif defined(CONFIG_MARCH_Z9_109)
.long 1, 0x8100c880
#elif defined(CONFIG_MARCH_Z990)
.long 1, 0x80002000
#elif defined(CONFIG_MARCH_Z900)
.long 1, 0x80000000
#endif
#endif
4:
#endif
#ifdef CONFIG_64BIT
/* Continue with 64bit startup code in head64.S */
sam64 # switch to 64 bit mode
jg startup_continue
#else
/* Continue with 31bit startup code in head31.S */
l %r13,5f-.LPG0(%r13)
b 0(%r13)
.align 8
5: .long startup_continue
#endif
.align 8
6: .long 0x7fffffff,0xffffffff
#include "head_kdump.S"
#
# params at 10400 (setup.h)
#
.org PARMAREA
.long 0,0 # IPL_DEVICE
.long 0,0 # INITRD_START
.long 0,0 # INITRD_SIZE
.long 0,0 # OLDMEM_BASE
.long 0,0 # OLDMEM_SIZE
.org COMMAND_LINE
.byte "root=/dev/ram0 ro"
.byte 0
.org 0x11000