1
0
Fork 0
alistair23-linux/include/asm-mips/page.h

182 lines
4.7 KiB
C
Raw Normal View History

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 1994 - 1999, 2000, 03 Ralf Baechle
* Copyright (C) 1999, 2000 Silicon Graphics, Inc.
*/
#ifndef _ASM_PAGE_H
#define _ASM_PAGE_H
#ifdef __KERNEL__
#include <spaces.h>
/*
* PAGE_SHIFT determines the page size
*/
#ifdef CONFIG_PAGE_SIZE_4KB
#define PAGE_SHIFT 12
#endif
#ifdef CONFIG_PAGE_SIZE_8KB
#define PAGE_SHIFT 13
#endif
#ifdef CONFIG_PAGE_SIZE_16KB
#define PAGE_SHIFT 14
#endif
#ifdef CONFIG_PAGE_SIZE_64KB
#define PAGE_SHIFT 16
#endif
#define PAGE_SIZE (1UL << PAGE_SHIFT)
#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1))
#ifndef __ASSEMBLY__
[MIPS] Retire flush_icache_page from mm use. On the 34K the redundant cache operations were causing excessive stalls resulting in realtime code running on the second VPE missing its deadline. For all other platforms this patch is just a significant performance improvment as illustrated by below benchmark numbers. Processor, Processes - times in microseconds - smaller is better ------------------------------------------------------------------------------ Host OS Mhz null null open slct sig sig fork exec sh call I/O stat clos TCP inst hndl proc proc proc --------- ------------- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- 25Kf 2.6.18-rc4 533 0.49 1.16 7.57 33.4 30.5 1.34 12.4 5497 17.K 54.K 25Kf 2.6.18-rc4-p 533 0.49 1.16 6.68 23.0 30.7 1.36 8.55 5030 16.K 48.K 4Kc 2.6.18-rc4 80 4.21 15.0 131. 289. 261. 16.5 258. 18.K 70.K 227K 4Kc 2.6.18-rc4-p 80 4.34 13.1 128. 285. 262. 18.2 258. 12.K 52.K 176K 34Kc 2.6.18-rc4 40 5.01 14.0 61.6 90.0 477. 17.9 94.7 29.K 108K 342K 34Kc 2.6.18-rc4-p 40 4.98 13.9 61.2 89.7 475. 17.6 93.7 8758 44.K 158K BCM1480 2.6.18-rc4 700 0.28 0.60 3.68 5.92 16.0 0.78 5.08 931. 3163 15.K BCM1480 2.6.18-rc4-p 700 0.28 0.61 3.65 5.85 16.0 0.79 5.20 395. 1464 8385 TX49-16K 2.6.18-rc3 197 0.73 2.41 19.0 37.8 82.9 2.94 17.5 4438 14.K 56.K TX49-16K 2.6.18-rc3-p 197 0.73 2.40 19.9 36.3 82.9 2.94 23.4 2577 9103 38.K TX49-32K 2.6.18-rc3 396 0.36 1.19 6.80 11.8 41.0 1.46 8.17 2738 8465 32.K TX49-32K 2.6.18-rc3-p 396 0.36 1.19 6.82 10.2 41.0 1.46 8.18 1330 4638 18.K Original patch by me with enhancements by Atsushi Nemoto. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
2006-08-12 09:40:08 -06:00
#include <asm/cpu-features.h>
extern void clear_page(void * page);
extern void copy_page(void * to, void * from);
extern unsigned long shm_align_mask;
static inline unsigned long pages_do_alias(unsigned long addr1,
unsigned long addr2)
{
return (addr1 ^ addr2) & shm_align_mask;
}
struct page;
static inline void clear_user_page(void *addr, unsigned long vaddr,
struct page *page)
{
extern void (*flush_data_cache_page)(unsigned long addr);
clear_page(addr);
[MIPS] Retire flush_icache_page from mm use. On the 34K the redundant cache operations were causing excessive stalls resulting in realtime code running on the second VPE missing its deadline. For all other platforms this patch is just a significant performance improvment as illustrated by below benchmark numbers. Processor, Processes - times in microseconds - smaller is better ------------------------------------------------------------------------------ Host OS Mhz null null open slct sig sig fork exec sh call I/O stat clos TCP inst hndl proc proc proc --------- ------------- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- 25Kf 2.6.18-rc4 533 0.49 1.16 7.57 33.4 30.5 1.34 12.4 5497 17.K 54.K 25Kf 2.6.18-rc4-p 533 0.49 1.16 6.68 23.0 30.7 1.36 8.55 5030 16.K 48.K 4Kc 2.6.18-rc4 80 4.21 15.0 131. 289. 261. 16.5 258. 18.K 70.K 227K 4Kc 2.6.18-rc4-p 80 4.34 13.1 128. 285. 262. 18.2 258. 12.K 52.K 176K 34Kc 2.6.18-rc4 40 5.01 14.0 61.6 90.0 477. 17.9 94.7 29.K 108K 342K 34Kc 2.6.18-rc4-p 40 4.98 13.9 61.2 89.7 475. 17.6 93.7 8758 44.K 158K BCM1480 2.6.18-rc4 700 0.28 0.60 3.68 5.92 16.0 0.78 5.08 931. 3163 15.K BCM1480 2.6.18-rc4-p 700 0.28 0.61 3.65 5.85 16.0 0.79 5.20 395. 1464 8385 TX49-16K 2.6.18-rc3 197 0.73 2.41 19.0 37.8 82.9 2.94 17.5 4438 14.K 56.K TX49-16K 2.6.18-rc3-p 197 0.73 2.40 19.9 36.3 82.9 2.94 23.4 2577 9103 38.K TX49-32K 2.6.18-rc3 396 0.36 1.19 6.80 11.8 41.0 1.46 8.17 2738 8465 32.K TX49-32K 2.6.18-rc3-p 396 0.36 1.19 6.82 10.2 41.0 1.46 8.18 1330 4638 18.K Original patch by me with enhancements by Atsushi Nemoto. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
2006-08-12 09:40:08 -06:00
if (pages_do_alias((unsigned long) addr, vaddr & PAGE_MASK))
flush_data_cache_page((unsigned long)addr);
}
static inline void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
struct page *to)
{
extern void (*flush_data_cache_page)(unsigned long addr);
copy_page(vto, vfrom);
[MIPS] Retire flush_icache_page from mm use. On the 34K the redundant cache operations were causing excessive stalls resulting in realtime code running on the second VPE missing its deadline. For all other platforms this patch is just a significant performance improvment as illustrated by below benchmark numbers. Processor, Processes - times in microseconds - smaller is better ------------------------------------------------------------------------------ Host OS Mhz null null open slct sig sig fork exec sh call I/O stat clos TCP inst hndl proc proc proc --------- ------------- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- 25Kf 2.6.18-rc4 533 0.49 1.16 7.57 33.4 30.5 1.34 12.4 5497 17.K 54.K 25Kf 2.6.18-rc4-p 533 0.49 1.16 6.68 23.0 30.7 1.36 8.55 5030 16.K 48.K 4Kc 2.6.18-rc4 80 4.21 15.0 131. 289. 261. 16.5 258. 18.K 70.K 227K 4Kc 2.6.18-rc4-p 80 4.34 13.1 128. 285. 262. 18.2 258. 12.K 52.K 176K 34Kc 2.6.18-rc4 40 5.01 14.0 61.6 90.0 477. 17.9 94.7 29.K 108K 342K 34Kc 2.6.18-rc4-p 40 4.98 13.9 61.2 89.7 475. 17.6 93.7 8758 44.K 158K BCM1480 2.6.18-rc4 700 0.28 0.60 3.68 5.92 16.0 0.78 5.08 931. 3163 15.K BCM1480 2.6.18-rc4-p 700 0.28 0.61 3.65 5.85 16.0 0.79 5.20 395. 1464 8385 TX49-16K 2.6.18-rc3 197 0.73 2.41 19.0 37.8 82.9 2.94 17.5 4438 14.K 56.K TX49-16K 2.6.18-rc3-p 197 0.73 2.40 19.9 36.3 82.9 2.94 23.4 2577 9103 38.K TX49-32K 2.6.18-rc3 396 0.36 1.19 6.80 11.8 41.0 1.46 8.17 2738 8465 32.K TX49-32K 2.6.18-rc3-p 396 0.36 1.19 6.82 10.2 41.0 1.46 8.18 1330 4638 18.K Original patch by me with enhancements by Atsushi Nemoto. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
2006-08-12 09:40:08 -06:00
if (!cpu_has_ic_fills_f_dc ||
pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK))
flush_data_cache_page((unsigned long)vto);
}
/*
* These are used to make use of C type-checking..
*/
#ifdef CONFIG_64BIT_PHYS_ADDR
#ifdef CONFIG_CPU_MIPS32
typedef struct { unsigned long pte_low, pte_high; } pte_t;
#define pte_val(x) ((x).pte_low | ((unsigned long long)(x).pte_high << 32))
#define __pte(x) ({ pte_t __pte = {(x), ((unsigned long long)(x)) >> 32}; __pte; })
#else
typedef struct { unsigned long long pte; } pte_t;
#define pte_val(x) ((x).pte)
#define __pte(x) ((pte_t) { (x) } )
#endif
#else
typedef struct { unsigned long pte; } pte_t;
#define pte_val(x) ((x).pte)
#define __pte(x) ((pte_t) { (x) } )
#endif
/*
* For 3-level pagetables we defines these ourselves, for 2-level the
* definitions are supplied by <asm-generic/pgtable-nopmd.h>.
*/
#ifdef CONFIG_64BIT
typedef struct { unsigned long pmd; } pmd_t;
#define pmd_val(x) ((x).pmd)
#define __pmd(x) ((pmd_t) { (x) } )
#endif
/*
* Right now we don't support 4-level pagetables, so all pud-related
* definitions come from <asm-generic/pgtable-nopud.h>.
*/
/*
* Finall the top of the hierarchy, the pgd
*/
typedef struct { unsigned long pgd; } pgd_t;
#define pgd_val(x) ((x).pgd)
#define __pgd(x) ((pgd_t) { (x) } )
/*
* Manipulate page protection bits
*/
typedef struct { unsigned long pgprot; } pgprot_t;
#define pgprot_val(x) ((x).pgprot)
#define __pgprot(x) ((pgprot_t) { (x) } )
/*
* On R4000-style MMUs where a TLB entry is mapping a adjacent even / odd
* pair of pages we only have a single global bit per pair of pages. When
* writing to the TLB make sure we always have the bit set for both pages
* or none. This macro is used to access the `buddy' of the pte we're just
* working on.
*/
#define ptep_buddy(x) ((pte_t *)((unsigned long)(x) ^ sizeof(pte_t)))
#endif /* !__ASSEMBLY__ */
/* to align the pointer to the (next) page boundary */
#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK)
#define __pa(x) ((unsigned long) (x) - PAGE_OFFSET)
#define __va(x) ((void *)((unsigned long) (x) + PAGE_OFFSET))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
#ifdef CONFIG_FLATMEM
#define pfn_valid(pfn) ((pfn) < max_mapnr)
#elif defined(CONFIG_SPARSEMEM)
/* pfn_valid is defined in linux/mmzone.h */
#elif defined(CONFIG_NEED_MULTIPLE_NODES)
#define pfn_valid(pfn) \
({ \
unsigned long __pfn = (pfn); \
int __n = pfn_to_nid(__pfn); \
((__n >= 0) ? (__pfn < NODE_DATA(__n)->node_start_pfn + \
NODE_DATA(__n)->node_spanned_pages) \
: 0); \
})
#endif
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
#define UNCAC_ADDR(addr) ((addr) - PAGE_OFFSET + UNCAC_BASE)
#define CAC_ADDR(addr) ((addr) - UNCAC_BASE + PAGE_OFFSET)
#ifdef CONFIG_LIMITED_DMA
#define WANT_PAGE_VIRTUAL
#endif
#include <asm-generic/memory_model.h>
#include <asm-generic/page.h>
#endif /* defined (__KERNEL__) */
#endif /* _ASM_PAGE_H */