android_kernel_samsung_msm8976/arch/powerpc/kernel/misc.S
Paul Mackerras f007cacffc [POWERPC] Fix MMIO ops to provide expected barrier behaviour
This changes the writeX family of functions to have a sync instruction
before the MMIO store rather than after, because the generally expected
behaviour is that the device receiving the MMIO store can be guaranteed
to see the effects of any preceding writes to normal memory.

To preserve ordering between writeX and readX, and to preserve ordering
between preceding stores and the readX, the readX family of functions
have had an sync added before the load.

Although writeX followed by spin_unlock is not officially guaranteed
to keep the writeX inside the spin-locked region unless an mmiowb()
is used, there are currently drivers that depend on the previous
behaviour on powerpc, which was that the mmiowb wasn't actually required.
Therefore we have a per-cpu flag that is set by writeX, cleared by
__raw_spin_lock and mmiowb, and tested by __raw_spin_unlock.  If it is
set, __raw_spin_unlock does a sync and clears it.

This changes both 32-bit and 64-bit readX/writeX.  32-bit already has a
sync in __raw_spin_unlock (since lwsync doesn't exist on 32-bit), and thus
doesn't need the per-cpu flag.

Tested on G5 (PPC970) and POWER5.

Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-13 22:08:26 +10:00

204 lines
2.8 KiB
ArmAsm

/*
* This file contains miscellaneous low-level functions.
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
*
* Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
* and Paul Mackerras.
*
* Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
* PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <asm/ppc_asm.h>
.text
/*
* Returns (address we are running at) - (address we were linked at)
* for use before the text and data are mapped to KERNELBASE.
*/
_GLOBAL(reloc_offset)
mflr r0
bl 1f
1: mflr r3
LOAD_REG_IMMEDIATE(r4,1b)
subf r3,r4,r3
mtlr r0
blr
/*
* add_reloc_offset(x) returns x + reloc_offset().
*/
_GLOBAL(add_reloc_offset)
mflr r0
bl 1f
1: mflr r5
LOAD_REG_IMMEDIATE(r4,1b)
subf r5,r4,r5
add r3,r3,r5
mtlr r0
blr
/*
* I/O string operations
*
* insb(port, buf, len)
* outsb(port, buf, len)
* insw(port, buf, len)
* outsw(port, buf, len)
* insl(port, buf, len)
* outsl(port, buf, len)
* insw_ns(port, buf, len)
* outsw_ns(port, buf, len)
* insl_ns(port, buf, len)
* outsl_ns(port, buf, len)
*
* The *_ns versions don't do byte-swapping.
*/
_GLOBAL(_insb)
sync
cmpwi 0,r5,0
mtctr r5
subi r4,r4,1
blelr-
00: lbz r5,0(r3)
eieio
stbu r5,1(r4)
bdnz 00b
twi 0,r5,0
isync
blr
_GLOBAL(_outsb)
cmpwi 0,r5,0
mtctr r5
subi r4,r4,1
blelr-
sync
00: lbzu r5,1(r4)
stb r5,0(r3)
bdnz 00b
sync
blr
_GLOBAL(_insw)
sync
cmpwi 0,r5,0
mtctr r5
subi r4,r4,2
blelr-
00: lhbrx r5,0,r3
eieio
sthu r5,2(r4)
bdnz 00b
twi 0,r5,0
isync
blr
_GLOBAL(_outsw)
cmpwi 0,r5,0
mtctr r5
subi r4,r4,2
blelr-
sync
00: lhzu r5,2(r4)
sthbrx r5,0,r3
bdnz 00b
sync
blr
_GLOBAL(_insl)
sync
cmpwi 0,r5,0
mtctr r5
subi r4,r4,4
blelr-
00: lwbrx r5,0,r3
eieio
stwu r5,4(r4)
bdnz 00b
twi 0,r5,0
isync
blr
_GLOBAL(_outsl)
cmpwi 0,r5,0
mtctr r5
subi r4,r4,4
blelr-
sync
00: lwzu r5,4(r4)
stwbrx r5,0,r3
bdnz 00b
sync
blr
#ifdef CONFIG_PPC32
_GLOBAL(__ide_mm_insw)
#endif
_GLOBAL(_insw_ns)
sync
cmpwi 0,r5,0
mtctr r5
subi r4,r4,2
blelr-
00: lhz r5,0(r3)
eieio
sthu r5,2(r4)
bdnz 00b
twi 0,r5,0
isync
blr
#ifdef CONFIG_PPC32
_GLOBAL(__ide_mm_outsw)
#endif
_GLOBAL(_outsw_ns)
cmpwi 0,r5,0
mtctr r5
subi r4,r4,2
blelr-
sync
00: lhzu r5,2(r4)
sth r5,0(r3)
bdnz 00b
sync
blr
#ifdef CONFIG_PPC32
_GLOBAL(__ide_mm_insl)
#endif
_GLOBAL(_insl_ns)
sync
cmpwi 0,r5,0
mtctr r5
subi r4,r4,4
blelr-
00: lwz r5,0(r3)
eieio
stwu r5,4(r4)
bdnz 00b
twi 0,r5,0
isync
blr
#ifdef CONFIG_PPC32
_GLOBAL(__ide_mm_outsl)
#endif
_GLOBAL(_outsl_ns)
cmpwi 0,r5,0
mtctr r5
subi r4,r4,4
blelr-
sync
00: lwzu r5,4(r4)
stw r5,0(r3)
bdnz 00b
sync
blr