lisa/android_kernel_xiaomi_sm8350
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
5e41486c40
android_kernel_xiaomi_sm8350/include/asm-powerpc/io.h
Trent Piepho 0f3d6bcd39 powerpc: Improve (in|out)_[bl]eXX() asm code 
Since commit 4cb3cee03d the code generated
for the in_beXX() and out_beXX() mmio functions has been sub-optimal.

The out_leXX() family of functions are created with the macro
DEF_MMIO_OUT_LE() while the out_beXX() family are created with
DEF_MMIO_OUT_BE().  In what was perhaps a bit too much macro use, both of
these macros are in turn created via the macro DEF_MMIO_OUT().

For the LE versions, eventually they boil down to an asm that will look
something like this:
asm("sync; stwbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr));

The issue is that the "stwbrx" instruction only comes in an indexed, or
'x', version, in which the address is represented by the sum of two
registers (the "0,%2").  Unfortunately, gcc doesn't have a constraint for
an indexed memory reference.  The "m" constraint allows both indexed and
offset, i.e. register plus constant, memory references and there is no
"stwbr" version for offset references.  "m" also allows updating addresses
and there is no 'u' version of "stwbrx" like there is with "stwux".

The unused first operand to the asm is just to tell gcc that *addr is an
output of the asm.  The address used is passed in a single register via the
third asm operand, and the index register is just hard coded as 0.  This
means gcc is forced to put the address in a single register and can't use
index addressing, e.g. if one has the data in register 9, a base address in
register 3 and an index in register 4, gcc must emit code like "add 11,4,3;
stwbrx 9,0,11" instead of just "stwbrx 9,4,3".  This costs an extra add
instruction and another register.

For gcc 4.0 and older, there doesn't appear to be anything that can be
done.  But for 4.1 and newer, there is a 'Z' constraint.  It does not allow
"updating" addresses, but does allow both indexed and offset addresses.
However, the only allowed constant offset is 0.  We can then use the
undocumented 'y' operand modifier, which causes gcc to convert "0(reg)"
into the equivilient "0,reg" format that can be used with stwbrx.

This brings us the to problem with the BE version.  In this case, the "stw"
instruction does have both indexed and non-indexed versions.  The final asm
ends up looking like this:
asm("sync; stw%U0%X0 %1,%0" : "=m" (*addr) : "r" (val), "r" (addr));

The undocumented codes "%U0" and "%0X" will generate a 'u' if the memory
reference should be an auto-updating one, and an 'x' if the memory
reference is indexed, respectively.  The third operand is unused, it's just
there because asm the code is reused from the LE version.  However, gcc
does not know this, and generates unnecessary code to stick addr in a
register!  To use the example from the LE version, gcc will generate "add
11,4,3; stwx 9,4,3".  It is able to use the indexed address "4,3" for the
"stwx", but still thinks it needs to put 4+3 into register 11, which will
never be used.

This also ends up happening a lot for the offset addressing mode, where
common code like this:  out_be32(&device_registers->some_register, data);
uses an instruction like "stw 9, 42(3)", where register 3 has the pointer
device_registers and 42 is the offset of some_register in that structure.
gcc will be forced to generate the unnecessary instruction "addi 11, 3, 42"
to put the address into a single (unused) register.

The in_* versions end up having these exact same problems as well.

Signed-off-by: Trent Piepho <tpiepho@freescale.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Andreas Schwab <schwab@suse.de>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-09 13:54:36 +10:00

785 lines
25 KiB
C
Raw Blame History

#ifndef _ASM_POWERPC_IO_H
#define _ASM_POWERPC_IO_H
#ifdef __KERNEL__
/*
* 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.
*/
/* Check of existence of legacy devices */
extern int check_legacy_ioport(unsigned long base_port);
#define I8042_DATA_REG 0x60
#define FDC_BASE 0x3f0
/* only relevant for PReP */
#define _PIDXR 0x279
#define _PNPWRP 0xa79
#define PNPBIOS_BASE 0xf000
#include <linux/device.h>
#include <linux/io.h>
#include <linux/compiler.h>
#include <asm/page.h>
#include <asm/byteorder.h>
#include <asm/synch.h>
#include <asm/delay.h>
#include <asm/mmu.h>
#include <asm-generic/iomap.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#endif
#define SIO_CONFIG_RA 0x398
#define SIO_CONFIG_RD 0x399
#define SLOW_DOWN_IO
/* 32 bits uses slightly different variables for the various IO
* bases. Most of this file only uses _IO_BASE though which we
* define properly based on the platform
*/
#ifndef CONFIG_PCI
#define _IO_BASE 0
#define _ISA_MEM_BASE 0
#define PCI_DRAM_OFFSET 0
#elif defined(CONFIG_PPC32)
#define _IO_BASE isa_io_base
#define _ISA_MEM_BASE isa_mem_base
#define PCI_DRAM_OFFSET pci_dram_offset
#else
#define _IO_BASE pci_io_base
#define _ISA_MEM_BASE isa_mem_base
#define PCI_DRAM_OFFSET 0
#endif
extern unsigned long isa_io_base;
extern unsigned long pci_io_base;
extern unsigned long pci_dram_offset;
extern resource_size_t isa_mem_base;
#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_INDIRECT_IO)
#error CONFIG_PPC_INDIRECT_IO is not yet supported on 32 bits
#endif
/*
*
* Low level MMIO accessors
*
* This provides the non-bus specific accessors to MMIO. Those are PowerPC
* specific and thus shouldn't be used in generic code. The accessors
* provided here are:
*
* in_8, in_le16, in_be16, in_le32, in_be32, in_le64, in_be64
* out_8, out_le16, out_be16, out_le32, out_be32, out_le64, out_be64
* _insb, _insw_ns, _insl_ns, _outsb, _outsw_ns, _outsl_ns
*
* Those operate directly on a kernel virtual address. Note that the prototype
* for the out_* accessors has the arguments in opposite order from the usual
* linux PCI accessors. Unlike those, they take the address first and the value
* next.
*
* Note: I might drop the _ns suffix on the stream operations soon as it is
* simply normal for stream operations to not swap in the first place.
*
*/
#ifdef CONFIG_PPC64
#define IO_SET_SYNC_FLAG() do { local_paca->io_sync = 1; } while(0)
#else
#define IO_SET_SYNC_FLAG()
#endif
/* gcc 4.0 and older doesn't have 'Z' constraint */
#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ == 0)
#define DEF_MMIO_IN_LE(name, size, insn) \
static inline u##size name(const volatile u##size __iomem *addr) \
{ \
u##size ret; \
__asm__ __volatile__("sync;"#insn" %0,0,%1;twi 0,%0,0;isync" \
: "=r" (ret) : "r" (addr), "m" (*addr) : "memory"); \
return ret; \
}
#define DEF_MMIO_OUT_LE(name, size, insn) \
static inline void name(volatile u##size __iomem *addr, u##size val) \
{ \
__asm__ __volatile__("sync;"#insn" %1,0,%2" \
: "=m" (*addr) : "r" (val), "r" (addr) : "memory"); \
IO_SET_SYNC_FLAG(); \
}
#else /* newer gcc */
#define DEF_MMIO_IN_LE(name, size, insn) \
static inline u##size name(const volatile u##size __iomem *addr) \
{ \
u##size ret; \
__asm__ __volatile__("sync;"#insn" %0,%y1;twi 0,%0,0;isync" \
: "=r" (ret) : "Z" (*addr) : "memory"); \
return ret; \
}
#define DEF_MMIO_OUT_LE(name, size, insn) \
static inline void name(volatile u##size __iomem *addr, u##size val) \
{ \
__asm__ __volatile__("sync;"#insn" %1,%y0" \
: "=Z" (*addr) : "r" (val) : "memory"); \
IO_SET_SYNC_FLAG(); \
}
#endif
#define DEF_MMIO_IN_BE(name, size, insn) \
static inline u##size name(const volatile u##size __iomem *addr) \
{ \
u##size ret; \
__asm__ __volatile__("sync;"#insn"%U1%X1 %0,%1;twi 0,%0,0;isync"\
: "=r" (ret) : "m" (*addr) : "memory"); \
return ret; \
}
#define DEF_MMIO_OUT_BE(name, size, insn) \
static inline void name(volatile u##size __iomem *addr, u##size val) \
{ \
__asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0" \
: "=m" (*addr) : "r" (val) : "memory"); \
IO_SET_SYNC_FLAG(); \
}
DEF_MMIO_IN_BE(in_8, 8, lbz);
DEF_MMIO_IN_BE(in_be16, 16, lhz);
DEF_MMIO_IN_BE(in_be32, 32, lwz);
DEF_MMIO_IN_LE(in_le16, 16, lhbrx);
DEF_MMIO_IN_LE(in_le32, 32, lwbrx);
DEF_MMIO_OUT_BE(out_8, 8, stb);
DEF_MMIO_OUT_BE(out_be16, 16, sth);
DEF_MMIO_OUT_BE(out_be32, 32, stw);
DEF_MMIO_OUT_LE(out_le16, 16, sthbrx);
DEF_MMIO_OUT_LE(out_le32, 32, stwbrx);
#ifdef __powerpc64__
DEF_MMIO_OUT_BE(out_be64, 64, std);
DEF_MMIO_IN_BE(in_be64, 64, ld);
/* There is no asm instructions for 64 bits reverse loads and stores */
static inline u64 in_le64(const volatile u64 __iomem *addr)
{
return swab64(in_be64(addr));
}
static inline void out_le64(volatile u64 __iomem *addr, u64 val)
{
out_be64(addr, swab64(val));
}
#endif /* __powerpc64__ */
/*
* Low level IO stream instructions are defined out of line for now
*/
extern void _insb(const volatile u8 __iomem *addr, void *buf, long count);
extern void _outsb(volatile u8 __iomem *addr,const void *buf,long count);
extern void _insw_ns(const volatile u16 __iomem *addr, void *buf, long count);
extern void _outsw_ns(volatile u16 __iomem *addr, const void *buf, long count);
extern void _insl_ns(const volatile u32 __iomem *addr, void *buf, long count);
extern void _outsl_ns(volatile u32 __iomem *addr, const void *buf, long count);
/* The _ns naming is historical and will be removed. For now, just #define
* the non _ns equivalent names
*/
#define _insw _insw_ns
#define _insl _insl_ns
#define _outsw _outsw_ns
#define _outsl _outsl_ns
/*
* memset_io, memcpy_toio, memcpy_fromio base implementations are out of line
*/
extern void _memset_io(volatile void __iomem *addr, int c, unsigned long n);
extern void _memcpy_fromio(void *dest, const volatile void __iomem *src,
unsigned long n);
extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
unsigned long n);
/*
*
* PCI and standard ISA accessors
*
* Those are globally defined linux accessors for devices on PCI or ISA
* busses. They follow the Linux defined semantics. The current implementation
* for PowerPC is as close as possible to the x86 version of these, and thus
* provides fairly heavy weight barriers for the non-raw versions
*
* In addition, they support a hook mechanism when CONFIG_PPC_INDIRECT_IO
* allowing the platform to provide its own implementation of some or all
* of the accessors.
*/
/*
* Include the EEH definitions when EEH is enabled only so they don't get
* in the way when building for 32 bits
*/
#ifdef CONFIG_EEH
#include <asm/eeh.h>
#endif
/* Shortcut to the MMIO argument pointer */
#define PCI_IO_ADDR volatile void __iomem *
/* Indirect IO address tokens:
*
* When CONFIG_PPC_INDIRECT_IO is set, the platform can provide hooks
* on all IOs. (Note that this is all 64 bits only for now)
*
* To help platforms who may need to differenciate MMIO addresses in
* their hooks, a bitfield is reserved for use by the platform near the
* top of MMIO addresses (not PIO, those have to cope the hard way).
*
* This bit field is 12 bits and is at the top of the IO virtual
* addresses PCI_IO_INDIRECT_TOKEN_MASK.
*
* The kernel virtual space is thus:
*
* 0xD000000000000000 : vmalloc
* 0xD000080000000000 : PCI PHB IO space
* 0xD000080080000000 : ioremap
* 0xD0000fffffffffff : end of ioremap region
*
* Since the top 4 bits are reserved as the region ID, we use thus
* the next 12 bits and keep 4 bits available for the future if the
* virtual address space is ever to be extended.
*
* The direct IO mapping operations will then mask off those bits
* before doing the actual access, though that only happen when
* CONFIG_PPC_INDIRECT_IO is set, thus be careful when you use that
* mechanism
*/
#ifdef CONFIG_PPC_INDIRECT_IO
#define PCI_IO_IND_TOKEN_MASK 0x0fff000000000000ul
#define PCI_IO_IND_TOKEN_SHIFT 48
#define PCI_FIX_ADDR(addr) \
((PCI_IO_ADDR)(((unsigned long)(addr)) & ~PCI_IO_IND_TOKEN_MASK))
#define PCI_GET_ADDR_TOKEN(addr) \
(((unsigned long)(addr) & PCI_IO_IND_TOKEN_MASK) >> \
PCI_IO_IND_TOKEN_SHIFT)
#define PCI_SET_ADDR_TOKEN(addr, token) \
do { \
unsigned long __a = (unsigned long)(addr); \
__a &= ~PCI_IO_IND_TOKEN_MASK; \
__a |= ((unsigned long)(token)) << PCI_IO_IND_TOKEN_SHIFT; \
(addr) = (void __iomem *)__a; \
} while(0)
#else
#define PCI_FIX_ADDR(addr) (addr)
#endif
/*
* Non ordered and non-swapping "raw" accessors
*/
static inline unsigned char __raw_readb(const volatile void __iomem *addr)
{
return *(volatile unsigned char __force *)PCI_FIX_ADDR(addr);
}
static inline unsigned short __raw_readw(const volatile void __iomem *addr)
{
return *(volatile unsigned short __force *)PCI_FIX_ADDR(addr);
}
static inline unsigned int __raw_readl(const volatile void __iomem *addr)
{
return *(volatile unsigned int __force *)PCI_FIX_ADDR(addr);
}
static inline void __raw_writeb(unsigned char v, volatile void __iomem *addr)
{
*(volatile unsigned char __force *)PCI_FIX_ADDR(addr) = v;
}
static inline void __raw_writew(unsigned short v, volatile void __iomem *addr)
{
*(volatile unsigned short __force *)PCI_FIX_ADDR(addr) = v;
}
static inline void __raw_writel(unsigned int v, volatile void __iomem *addr)
{
*(volatile unsigned int __force *)PCI_FIX_ADDR(addr) = v;
}
#ifdef __powerpc64__
static inline unsigned long __raw_readq(const volatile void __iomem *addr)
{
return *(volatile unsigned long __force *)PCI_FIX_ADDR(addr);
}
static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr)
{
*(volatile unsigned long __force *)PCI_FIX_ADDR(addr) = v;
}
#endif /* __powerpc64__ */
/*
*
* PCI PIO and MMIO accessors.
*
*
* On 32 bits, PIO operations have a recovery mechanism in case they trigger
* machine checks (which they occasionally do when probing non existing
* IO ports on some platforms, like PowerMac and 8xx).
* I always found it to be of dubious reliability and I am tempted to get
* rid of it one of these days. So if you think it's important to keep it,
* please voice up asap. We never had it for 64 bits and I do not intend
* to port it over
*/
#ifdef CONFIG_PPC32
#define __do_in_asm(name, op) \
static inline unsigned int name(unsigned int port) \
{ \
unsigned int x; \
__asm__ __volatile__( \
"sync\n" \
"0:" op " %0,0,%1\n" \
"1: twi 0,%0,0\n" \
"2: isync\n" \
"3: nop\n" \
"4:\n" \
".section .fixup,\"ax\"\n" \
"5: li %0,-1\n" \
" b 4b\n" \
".previous\n" \
".section __ex_table,\"a\"\n" \
" .align 2\n" \
" .long 0b,5b\n" \
" .long 1b,5b\n" \
" .long 2b,5b\n" \
" .long 3b,5b\n" \
".previous" \
: "=&r" (x) \
: "r" (port + _IO_BASE) \
: "memory"); \
return x; \
}
#define __do_out_asm(name, op) \
static inline void name(unsigned int val, unsigned int port) \
{ \
__asm__ __volatile__( \
"sync\n" \
"0:" op " %0,0,%1\n" \
"1: sync\n" \
"2:\n" \
".section __ex_table,\"a\"\n" \
" .align 2\n" \
" .long 0b,2b\n" \
" .long 1b,2b\n" \
".previous" \
: : "r" (val), "r" (port + _IO_BASE) \
: "memory"); \
}
__do_in_asm(_rec_inb, "lbzx")
__do_in_asm(_rec_inw, "lhbrx")
__do_in_asm(_rec_inl, "lwbrx")
__do_out_asm(_rec_outb, "stbx")
__do_out_asm(_rec_outw, "sthbrx")
__do_out_asm(_rec_outl, "stwbrx")
#endif /* CONFIG_PPC32 */
/* The "__do_*" operations below provide the actual "base" implementation
* for each of the defined acccessor. Some of them use the out_* functions
* directly, some of them still use EEH, though we might change that in the
* future. Those macros below provide the necessary argument swapping and
* handling of the IO base for PIO.
*
* They are themselves used by the macros that define the actual accessors
* and can be used by the hooks if any.
*
* Note that PIO operations are always defined in terms of their corresonding
* MMIO operations. That allows platforms like iSeries who want to modify the
* behaviour of both to only hook on the MMIO version and get both. It's also
* possible to hook directly at the toplevel PIO operation if they have to
* be handled differently
*/
#define __do_writeb(val, addr) out_8(PCI_FIX_ADDR(addr), val)
#define __do_writew(val, addr) out_le16(PCI_FIX_ADDR(addr), val)
#define __do_writel(val, addr) out_le32(PCI_FIX_ADDR(addr), val)
#define __do_writeq(val, addr) out_le64(PCI_FIX_ADDR(addr), val)
#define __do_writew_be(val, addr) out_be16(PCI_FIX_ADDR(addr), val)
#define __do_writel_be(val, addr) out_be32(PCI_FIX_ADDR(addr), val)
#define __do_writeq_be(val, addr) out_be64(PCI_FIX_ADDR(addr), val)
#ifdef CONFIG_EEH
#define __do_readb(addr) eeh_readb(PCI_FIX_ADDR(addr))
#define __do_readw(addr) eeh_readw(PCI_FIX_ADDR(addr))
#define __do_readl(addr) eeh_readl(PCI_FIX_ADDR(addr))
#define __do_readq(addr) eeh_readq(PCI_FIX_ADDR(addr))
#define __do_readw_be(addr) eeh_readw_be(PCI_FIX_ADDR(addr))
#define __do_readl_be(addr) eeh_readl_be(PCI_FIX_ADDR(addr))
#define __do_readq_be(addr) eeh_readq_be(PCI_FIX_ADDR(addr))
#else /* CONFIG_EEH */
#define __do_readb(addr) in_8(PCI_FIX_ADDR(addr))
#define __do_readw(addr) in_le16(PCI_FIX_ADDR(addr))
#define __do_readl(addr) in_le32(PCI_FIX_ADDR(addr))
#define __do_readq(addr) in_le64(PCI_FIX_ADDR(addr))
#define __do_readw_be(addr) in_be16(PCI_FIX_ADDR(addr))
#define __do_readl_be(addr) in_be32(PCI_FIX_ADDR(addr))
#define __do_readq_be(addr) in_be64(PCI_FIX_ADDR(addr))
#endif /* !defined(CONFIG_EEH) */
#ifdef CONFIG_PPC32
#define __do_outb(val, port) _rec_outb(val, port)
#define __do_outw(val, port) _rec_outw(val, port)
#define __do_outl(val, port) _rec_outl(val, port)
#define __do_inb(port) _rec_inb(port)
#define __do_inw(port) _rec_inw(port)
#define __do_inl(port) _rec_inl(port)
#else /* CONFIG_PPC32 */
#define __do_outb(val, port) writeb(val,(PCI_IO_ADDR)_IO_BASE+port);
#define __do_outw(val, port) writew(val,(PCI_IO_ADDR)_IO_BASE+port);
#define __do_outl(val, port) writel(val,(PCI_IO_ADDR)_IO_BASE+port);
#define __do_inb(port) readb((PCI_IO_ADDR)_IO_BASE + port);
#define __do_inw(port) readw((PCI_IO_ADDR)_IO_BASE + port);
#define __do_inl(port) readl((PCI_IO_ADDR)_IO_BASE + port);
#endif /* !CONFIG_PPC32 */
#ifdef CONFIG_EEH
#define __do_readsb(a, b, n) eeh_readsb(PCI_FIX_ADDR(a), (b), (n))
#define __do_readsw(a, b, n) eeh_readsw(PCI_FIX_ADDR(a), (b), (n))
#define __do_readsl(a, b, n) eeh_readsl(PCI_FIX_ADDR(a), (b), (n))
#else /* CONFIG_EEH */
#define __do_readsb(a, b, n) _insb(PCI_FIX_ADDR(a), (b), (n))
#define __do_readsw(a, b, n) _insw(PCI_FIX_ADDR(a), (b), (n))
#define __do_readsl(a, b, n) _insl(PCI_FIX_ADDR(a), (b), (n))
#endif /* !CONFIG_EEH */
#define __do_writesb(a, b, n) _outsb(PCI_FIX_ADDR(a),(b),(n))
#define __do_writesw(a, b, n) _outsw(PCI_FIX_ADDR(a),(b),(n))
#define __do_writesl(a, b, n) _outsl(PCI_FIX_ADDR(a),(b),(n))
#define __do_insb(p, b, n) readsb((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
#define __do_insw(p, b, n) readsw((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
#define __do_insl(p, b, n) readsl((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
#define __do_outsb(p, b, n) writesb((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
#define __do_outsw(p, b, n) writesw((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
#define __do_outsl(p, b, n) writesl((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
#define __do_memset_io(addr, c, n) \
_memset_io(PCI_FIX_ADDR(addr), c, n)
#define __do_memcpy_toio(dst, src, n) \
_memcpy_toio(PCI_FIX_ADDR(dst), src, n)
#ifdef CONFIG_EEH
#define __do_memcpy_fromio(dst, src, n) \
eeh_memcpy_fromio(dst, PCI_FIX_ADDR(src), n)
#else /* CONFIG_EEH */
#define __do_memcpy_fromio(dst, src, n) \
_memcpy_fromio(dst,PCI_FIX_ADDR(src),n)
#endif /* !CONFIG_EEH */
#ifdef CONFIG_PPC_INDIRECT_IO
#define DEF_PCI_HOOK(x) x
#else
#define DEF_PCI_HOOK(x) NULL
#endif
/* Structure containing all the hooks */
extern struct ppc_pci_io {
#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) ret (*name) at;
#define DEF_PCI_AC_NORET(name, at, al, space, aa) void (*name) at;
#include <asm/io-defs.h>
#undef DEF_PCI_AC_RET
#undef DEF_PCI_AC_NORET
} ppc_pci_io;
/* The inline wrappers */
#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \
static inline ret name at \
{ \
if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL) \
return ppc_pci_io.name al; \
return __do_##name al; \
}
#define DEF_PCI_AC_NORET(name, at, al, space, aa) \
static inline void name at \
{ \
if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL) \
ppc_pci_io.name al; \
else \
__do_##name al; \
}
#include <asm/io-defs.h>
#undef DEF_PCI_AC_RET
#undef DEF_PCI_AC_NORET
/* Some drivers check for the presence of readq & writeq with
* a #ifdef, so we make them happy here.
*/
#ifdef __powerpc64__
#define readq readq
#define writeq writeq
#endif
/*
* Convert a physical pointer to a virtual kernel pointer for /dev/mem
* access
*/
#define xlate_dev_mem_ptr(p) __va(p)
/*
* Convert a virtual cached pointer to an uncached pointer
*/
#define xlate_dev_kmem_ptr(p) p
/*
* We don't do relaxed operations yet, at least not with this semantic
*/
#define readb_relaxed(addr) readb(addr)
#define readw_relaxed(addr) readw(addr)
#define readl_relaxed(addr) readl(addr)
#define readq_relaxed(addr) readq(addr)
#ifdef CONFIG_PPC32
#define mmiowb()
#else
/*
* Enforce synchronisation of stores vs. spin_unlock
* (this does it explicitly, though our implementation of spin_unlock
* does it implicitely too)
*/
static inline void mmiowb(void)
{
unsigned long tmp;
__asm__ __volatile__("sync; li %0,0; stb %0,%1(13)"
: "=&r" (tmp) : "i" (offsetof(struct paca_struct, io_sync))
: "memory");
}
#endif /* !CONFIG_PPC32 */
static inline void iosync(void)
{
__asm__ __volatile__ ("sync" : : : "memory");
}
/* Enforce in-order execution of data I/O.
* No distinction between read/write on PPC; use eieio for all three.
* Those are fairly week though. They don't provide a barrier between
* MMIO and cacheable storage nor do they provide a barrier vs. locks,
* they only provide barriers between 2 __raw MMIO operations and
* possibly break write combining.
*/
#define iobarrier_rw() eieio()
#define iobarrier_r() eieio()
#define iobarrier_w() eieio()
/*
* output pause versions need a delay at least for the
* w83c105 ide controller in a p610.
*/
#define inb_p(port) inb(port)
#define outb_p(val, port) (udelay(1), outb((val), (port)))
#define inw_p(port) inw(port)
#define outw_p(val, port) (udelay(1), outw((val), (port)))
#define inl_p(port) inl(port)
#define outl_p(val, port) (udelay(1), outl((val), (port)))
#define IO_SPACE_LIMIT ~(0UL)
/**
* ioremap - map bus memory into CPU space
* @address: bus address of the memory
* @size: size of the resource to map
*
* ioremap performs a platform specific sequence of operations to
* make bus memory CPU accessible via the readb/readw/readl/writeb/
* writew/writel functions and the other mmio helpers. The returned
* address is not guaranteed to be usable directly as a virtual
* address.
*
* We provide a few variations of it:
*
* * ioremap is the standard one and provides non-cacheable guarded mappings
* and can be hooked by the platform via ppc_md
*
* * ioremap_flags allows to specify the page flags as an argument and can
* also be hooked by the platform via ppc_md
*
* * ioremap_nocache is identical to ioremap
*
* * iounmap undoes such a mapping and can be hooked
*
* * __ioremap_at (and the pending __iounmap_at) are low level functions to
* create hand-made mappings for use only by the PCI code and cannot
* currently be hooked. Must be page aligned.
*
* * __ioremap is the low level implementation used by ioremap and
* ioremap_flags and cannot be hooked (but can be used by a hook on one
* of the previous ones)
*
* * __iounmap, is the low level implementation used by iounmap and cannot
* be hooked (but can be used by a hook on iounmap)
*
*/
extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
extern void __iomem *ioremap_flags(phys_addr_t address, unsigned long size,
unsigned long flags);
#define ioremap_nocache(addr, size) ioremap((addr), (size))
extern void iounmap(volatile void __iomem *addr);
extern void __iomem *__ioremap(phys_addr_t, unsigned long size,
unsigned long flags);
extern void __iounmap(volatile void __iomem *addr);
extern void __iomem * __ioremap_at(phys_addr_t pa, void *ea,
unsigned long size, unsigned long flags);
extern void __iounmap_at(void *ea, unsigned long size);
/*
* When CONFIG_PPC_INDIRECT_IO is set, we use the generic iomap implementation
* which needs some additional definitions here. They basically allow PIO
* space overall to be 1GB. This will work as long as we never try to use
* iomap to map MMIO below 1GB which should be fine on ppc64
*/
#define HAVE_ARCH_PIO_SIZE 1
#define PIO_OFFSET 0x00000000UL
#define PIO_MASK (FULL_IO_SIZE - 1)
#define PIO_RESERVED (FULL_IO_SIZE)
#define mmio_read16be(addr) readw_be(addr)
#define mmio_read32be(addr) readl_be(addr)
#define mmio_write16be(val, addr) writew_be(val, addr)
#define mmio_write32be(val, addr) writel_be(val, addr)
#define mmio_insb(addr, dst, count) readsb(addr, dst, count)
#define mmio_insw(addr, dst, count) readsw(addr, dst, count)
#define mmio_insl(addr, dst, count) readsl(addr, dst, count)
#define mmio_outsb(addr, src, count) writesb(addr, src, count)
#define mmio_outsw(addr, src, count) writesw(addr, src, count)
#define mmio_outsl(addr, src, count) writesl(addr, src, count)
/**
* virt_to_phys - map virtual addresses to physical
* @address: address to remap
*
* The returned physical address is the physical (CPU) mapping for
* the memory address given. It is only valid to use this function on
* addresses directly mapped or allocated via kmalloc.
*
* This function does not give bus mappings for DMA transfers. In
* almost all conceivable cases a device driver should not be using
* this function
*/
static inline unsigned long virt_to_phys(volatile void * address)
{
return __pa((unsigned long)address);
}
/**
* phys_to_virt - map physical address to virtual
* @address: address to remap
*
* The returned virtual address is a current CPU mapping for
* the memory address given. It is only valid to use this function on
* addresses that have a kernel mapping
*
* This function does not handle bus mappings for DMA transfers. In
* almost all conceivable cases a device driver should not be using
* this function
*/
static inline void * phys_to_virt(unsigned long address)
{
return (void *)__va(address);
}
/*
* Change "struct page" to physical address.
*/
#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT)
/* We do NOT want virtual merging, it would put too much pressure on
* our iommu allocator. Instead, we want drivers to be smart enough
* to coalesce sglists that happen to have been mapped in a contiguous
* way by the iommu
*/
#define BIO_VMERGE_BOUNDARY 0
/*
* 32 bits still uses virt_to_bus() for it's implementation of DMA
* mappings se we have to keep it defined here. We also have some old
* drivers (shame shame shame) that use bus_to_virt() and haven't been
* fixed yet so I need to define it here.
*/
#ifdef CONFIG_PPC32
static inline unsigned long virt_to_bus(volatile void * address)
{
if (address == NULL)
return 0;
return __pa(address) + PCI_DRAM_OFFSET;
}
static inline void * bus_to_virt(unsigned long address)
{
if (address == 0)
return NULL;
return __va(address - PCI_DRAM_OFFSET);
}
#define page_to_bus(page) (page_to_phys(page) + PCI_DRAM_OFFSET)
#endif /* CONFIG_PPC32 */
/* access ports */
#define setbits32(_addr, _v) out_be32((_addr), in_be32(_addr) | (_v))
#define clrbits32(_addr, _v) out_be32((_addr), in_be32(_addr) & ~(_v))
#define setbits16(_addr, _v) out_be16((_addr), in_be16(_addr) | (_v))
#define clrbits16(_addr, _v) out_be16((_addr), in_be16(_addr) & ~(_v))
#define setbits8(_addr, _v) out_8((_addr), in_8(_addr) | (_v))
#define clrbits8(_addr, _v) out_8((_addr), in_8(_addr) & ~(_v))
/* Clear and set bits in one shot. These macros can be used to clear and
* set multiple bits in a register using a single read-modify-write. These
* macros can also be used to set a multiple-bit bit pattern using a mask,
* by specifying the mask in the 'clear' parameter and the new bit pattern
* in the 'set' parameter.
*/
#define clrsetbits(type, addr, clear, set) \
out_##type((addr), (in_##type(addr) & ~(clear)) | (set))
#ifdef __powerpc64__
#define clrsetbits_be64(addr, clear, set) clrsetbits(be64, addr, clear, set)
#define clrsetbits_le64(addr, clear, set) clrsetbits(le64, addr, clear, set)
#endif
#define clrsetbits_be32(addr, clear, set) clrsetbits(be32, addr, clear, set)
#define clrsetbits_le32(addr, clear, set) clrsetbits(le32, addr, clear, set)
#define clrsetbits_be16(addr, clear, set) clrsetbits(be16, addr, clear, set)
#define clrsetbits_le16(addr, clear, set) clrsetbits(le32, addr, clear, set)
#define clrsetbits_8(addr, clear, set) clrsetbits(8, addr, clear, set)
void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset,
size_t size, unsigned long flags);
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_IO_H */
Reference in New Issue View Git Blame Copy Permalink