kernel_optimize_test/include/asm-x86/io_32.h

326 lines
9.1 KiB
C
Raw Normal View History

#ifndef _ASM_IO_H
#define _ASM_IO_H
#include <linux/string.h>
#include <linux/compiler.h>
/*
* This file contains the definitions for the x86 IO instructions
* inb/inw/inl/outb/outw/outl and the "string versions" of the same
* (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
* versions of the single-IO instructions (inb_p/inw_p/..).
*
* This file is not meant to be obfuscating: it's just complicated
* to (a) handle it all in a way that makes gcc able to optimize it
* as well as possible and (b) trying to avoid writing the same thing
* over and over again with slight variations and possibly making a
* mistake somewhere.
*/
/*
* Thanks to James van Artsdalen for a better timing-fix than
* the two short jumps: using outb's to a nonexistent port seems
* to guarantee better timings even on fast machines.
*
* On the other hand, I'd like to be sure of a non-existent port:
* I feel a bit unsafe about using 0x80 (should be safe, though)
*
* Linus
*/
/*
* Bit simplified and optimized by Jan Hubicka
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
*
* isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
* isa_read[wl] and isa_write[wl] fixed
* - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*/
#define IO_SPACE_LIMIT 0xffff
#define XQUAD_PORTIO_BASE 0xfe400000
#define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */
#ifdef __KERNEL__
#include <asm-generic/iomap.h>
#include <linux/vmalloc.h>
/*
* 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
/**
* 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(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 __va(address);
}
/*
* Change "struct page" to physical address.
*/
#define page_to_phys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
/**
* ioremap - map bus memory into CPU space
* @offset: 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.
*
* If the area you are trying to map is a PCI BAR you should have a
* look at pci_iomap().
*/
extern void __iomem *ioremap_nocache(unsigned long offset, unsigned long size);
extern void __iomem *ioremap_cache(unsigned long offset, unsigned long size);
/*
* The default ioremap() behavior is non-cached:
*/
static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
{
return ioremap_nocache(offset, size);
}
extern void iounmap(volatile void __iomem *addr);
/*
* early_ioremap() and early_iounmap() are for temporary early boot-time
* mappings, before the real ioremap() is functional.
* A boot-time mapping is currently limited to at most 16 pages.
*/
extern void early_ioremap_init(void);
extern void early_ioremap_clear(void);
extern void early_ioremap_reset(void);
extern void *early_ioremap(unsigned long offset, unsigned long size);
extern void early_iounmap(void *addr, unsigned long size);
extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
/* Use early IO mappings for DMI because it's initialized early */
#define dmi_ioremap early_ioremap
#define dmi_iounmap early_iounmap
#define dmi_alloc alloc_bootmem
/*
* ISA I/O bus memory addresses are 1:1 with the physical address.
*/
#define isa_virt_to_bus virt_to_phys
#define isa_page_to_bus page_to_phys
#define isa_bus_to_virt phys_to_virt
/*
* However PCI ones are not necessarily 1:1 and therefore these interfaces
* are forbidden in portable PCI drivers.
*
* Allow them on x86 for legacy drivers, though.
*/
#define virt_to_bus virt_to_phys
#define bus_to_virt phys_to_virt
/*
* readX/writeX() are used to access memory mapped devices. On some
* architectures the memory mapped IO stuff needs to be accessed
* differently. On the x86 architecture, we just read/write the
* memory location directly.
*/
static inline unsigned char readb(const volatile void __iomem *addr)
{
return *(volatile unsigned char __force *) addr;
}
static inline unsigned short readw(const volatile void __iomem *addr)
{
return *(volatile unsigned short __force *) addr;
}
static inline unsigned int readl(const volatile void __iomem *addr)
{
return *(volatile unsigned int __force *) addr;
}
#define readb_relaxed(addr) readb(addr)
#define readw_relaxed(addr) readw(addr)
#define readl_relaxed(addr) readl(addr)
#define __raw_readb readb
#define __raw_readw readw
#define __raw_readl readl
static inline void writeb(unsigned char b, volatile void __iomem *addr)
{
*(volatile unsigned char __force *) addr = b;
}
static inline void writew(unsigned short b, volatile void __iomem *addr)
{
*(volatile unsigned short __force *) addr = b;
}
static inline void writel(unsigned int b, volatile void __iomem *addr)
{
*(volatile unsigned int __force *) addr = b;
}
#define __raw_writeb writeb
#define __raw_writew writew
#define __raw_writel writel
#define mmiowb()
static inline void
memset_io(volatile void __iomem *addr, unsigned char val, int count)
{
memset((void __force *)addr, val, count);
}
static inline void
memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
{
__memcpy(dst, (const void __force *)src, count);
}
static inline void
memcpy_toio(volatile void __iomem *dst, const void *src, int count)
{
__memcpy((void __force *)dst, src, count);
}
/*
* ISA space is 'always mapped' on a typical x86 system, no need to
* explicitly ioremap() it. The fact that the ISA IO space is mapped
* to PAGE_OFFSET is pure coincidence - it does not mean ISA values
* are physical addresses. The following constant pointer can be
* used as the IO-area pointer (it can be iounmapped as well, so the
* analogy with PCI is quite large):
*/
#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
/*
* Cache management
*
* This needed for two cases
* 1. Out of order aware processors
* 2. Accidentally out of order processors (PPro errata #51)
*/
#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
static inline void flush_write_buffers(void)
{
__asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory");
}
#else
#define flush_write_buffers() do { } while (0)
#endif
#endif /* __KERNEL__ */
x86: provide a DMI based port 0x80 I/O delay override. x86: provide a DMI based port 0x80 I/O delay override. Certain (HP) laptops experience trouble from our port 0x80 I/O delay writes. This patch provides for a DMI based switch to the "alternate diagnostic port" 0xed (as used by some BIOSes as well) for these. David P. Reed confirmed that port 0xed works for him and provides a proper delay. The symptoms of _not_ working are a hanging machine, with "hwclock" use being a direct trigger. Earlier versions of this attempted to simply use udelay(2), with the 2 being a value tested to be a nicely conservative upper-bound with help from many on the linux-kernel mailinglist but that approach has two problems. First, pre-loops_per_jiffy calibration (which is post PIT init while some implementations of the PIT are actually one of the historically problematic devices that need the delay) udelay() isn't particularly well-defined. We could initialise loops_per_jiffy conservatively (and based on CPU family so as to not unduly delay old machines) which would sort of work, but... Second, delaying isn't the only effect that a write to port 0x80 has. It's also a PCI posting barrier which some devices may be explicitly or implicitly relying on. Alan Cox did a survey and found evidence that additionally some drivers may be racy on SMP without the bus locking outb. Switching to an inb() makes the timing too unpredictable and as such, this DMI based switch should be the safest approach for now. Any more invasive changes should get more rigid testing first. It's moreover only very few machines with the problem and a DMI based hack seems to fit that situation. This also introduces a command-line parameter "io_delay" to override the DMI based choice again: io_delay=<standard|alternate> where "standard" means using the standard port 0x80 and "alternate" port 0xed. This retains the udelay method as a config (CONFIG_UDELAY_IO_DELAY) and command-line ("io_delay=udelay") choice for testing purposes as well. This does not change the io_delay() in the boot code which is using the same port 0x80 I/O delay but those do not appear to be a problem as David P. Reed reported the problem was already gone after using the udelay version. He moreover reported that booting with "acpi=off" also fixed things and seeing as how ACPI isn't touched until after this DMI based I/O port switch I believe it's safe to leave the ones in the boot code be. The DMI strings from David's HP Pavilion dv9000z are in there already and we need to get/verify the DMI info from other machines with the problem, notably the HP Pavilion dv6000z. This patch is partly based on earlier patches from Pavel Machek and David P. Reed. Signed-off-by: Rene Herman <rene.herman@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 20:30:05 +08:00
extern void native_io_delay(void);
extern int io_delay_type;
extern void io_delay_init(void);
#if defined(CONFIG_PARAVIRT)
#include <asm/paravirt.h>
#else
static inline void slow_down_io(void) {
native_io_delay();
#ifdef REALLY_SLOW_IO
native_io_delay();
native_io_delay();
native_io_delay();
#endif
}
#endif
#define __BUILDIO(bwl,bw,type) \
static inline void out##bwl(unsigned type value, int port) { \
out##bwl##_local(value, port); \
} \
static inline unsigned type in##bwl(int port) { \
return in##bwl##_local(port); \
}
#define BUILDIO(bwl,bw,type) \
static inline void out##bwl##_local(unsigned type value, int port) { \
__asm__ __volatile__("out" #bwl " %" #bw "0, %w1" : : "a"(value), "Nd"(port)); \
} \
static inline unsigned type in##bwl##_local(int port) { \
unsigned type value; \
__asm__ __volatile__("in" #bwl " %w1, %" #bw "0" : "=a"(value) : "Nd"(port)); \
return value; \
} \
static inline void out##bwl##_local_p(unsigned type value, int port) { \
out##bwl##_local(value, port); \
slow_down_io(); \
} \
static inline unsigned type in##bwl##_local_p(int port) { \
unsigned type value = in##bwl##_local(port); \
slow_down_io(); \
return value; \
} \
__BUILDIO(bwl,bw,type) \
static inline void out##bwl##_p(unsigned type value, int port) { \
out##bwl(value, port); \
slow_down_io(); \
} \
static inline unsigned type in##bwl##_p(int port) { \
unsigned type value = in##bwl(port); \
slow_down_io(); \
return value; \
} \
static inline void outs##bwl(int port, const void *addr, unsigned long count) { \
__asm__ __volatile__("rep; outs" #bwl : "+S"(addr), "+c"(count) : "d"(port)); \
} \
static inline void ins##bwl(int port, void *addr, unsigned long count) { \
__asm__ __volatile__("rep; ins" #bwl : "+D"(addr), "+c"(count) : "d"(port)); \
}
BUILDIO(b,b,char)
BUILDIO(w,w,short)
BUILDIO(l,,int)
#endif