mirror of
https://github.com/torvalds/linux
synced 2024-10-05 19:02:12 +00:00
a372acfac5
On a live running system (VoIP gateway for Air Trafic Control), over a 10 minutes period (with 277s idle), we get 87 millions DTLB misses and approximatly 35 secondes are spent in DTLB handler. This represents 5.8% of the overall time and even 10.8% of the non-idle time. Among those 87 millions DTLB misses, 15% are on user addresses and 85% are on kernel addresses. And within the kernel addresses, 93% are on addresses from the linear address space and only 7% are on addresses from the virtual address space. MPC8xx has no BATs but it has 8Mb page size. This patch implements mapping of kernel RAM using 8Mb pages, on the same model as what is done on the 40x. In 4k pages mode, each PGD entry maps a 4Mb area: we map every two entries to the same 8Mb physical page. In each second entry, we add 4Mb to the page physical address to ease life of the FixupDAR routine. This is just ignored by HW. In 16k pages mode, each PGD entry maps a 64Mb area: each PGD entry will point to the first page of the area. The DTLB handler adds the 3 bits from EPN to map the correct page. With this patch applied, we now get only 13 millions TLB misses during the 10 minutes period. The idle time has increased to 313s and the overall time spent in DTLB miss handler is 6.3s, which represents 1% of the overall time and 2.2% of non-idle time. Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Scott Wood <oss@buserror.net>
162 lines
4.5 KiB
C
162 lines
4.5 KiB
C
/*
|
|
* Declarations of procedures and variables shared between files
|
|
* in arch/ppc/mm/.
|
|
*
|
|
* Derived from arch/ppc/mm/init.c:
|
|
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
|
|
*
|
|
* Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
|
|
* and Cort Dougan (PReP) (cort@cs.nmt.edu)
|
|
* Copyright (C) 1996 Paul Mackerras
|
|
*
|
|
* Derived from "arch/i386/mm/init.c"
|
|
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
|
|
*
|
|
* 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 <linux/mm.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/mmu.h>
|
|
|
|
#ifdef CONFIG_PPC_MMU_NOHASH
|
|
|
|
/*
|
|
* On 40x and 8xx, we directly inline tlbia and tlbivax
|
|
*/
|
|
#if defined(CONFIG_40x) || defined(CONFIG_8xx)
|
|
static inline void _tlbil_all(void)
|
|
{
|
|
asm volatile ("sync; tlbia; isync" : : : "memory");
|
|
}
|
|
static inline void _tlbil_pid(unsigned int pid)
|
|
{
|
|
asm volatile ("sync; tlbia; isync" : : : "memory");
|
|
}
|
|
#define _tlbil_pid_noind(pid) _tlbil_pid(pid)
|
|
|
|
#else /* CONFIG_40x || CONFIG_8xx */
|
|
extern void _tlbil_all(void);
|
|
extern void _tlbil_pid(unsigned int pid);
|
|
#ifdef CONFIG_PPC_BOOK3E
|
|
extern void _tlbil_pid_noind(unsigned int pid);
|
|
#else
|
|
#define _tlbil_pid_noind(pid) _tlbil_pid(pid)
|
|
#endif
|
|
#endif /* !(CONFIG_40x || CONFIG_8xx) */
|
|
|
|
/*
|
|
* On 8xx, we directly inline tlbie, on others, it's extern
|
|
*/
|
|
#ifdef CONFIG_8xx
|
|
static inline void _tlbil_va(unsigned long address, unsigned int pid,
|
|
unsigned int tsize, unsigned int ind)
|
|
{
|
|
asm volatile ("tlbie %0; sync" : : "r" (address) : "memory");
|
|
}
|
|
#elif defined(CONFIG_PPC_BOOK3E)
|
|
extern void _tlbil_va(unsigned long address, unsigned int pid,
|
|
unsigned int tsize, unsigned int ind);
|
|
#else
|
|
extern void __tlbil_va(unsigned long address, unsigned int pid);
|
|
static inline void _tlbil_va(unsigned long address, unsigned int pid,
|
|
unsigned int tsize, unsigned int ind)
|
|
{
|
|
__tlbil_va(address, pid);
|
|
}
|
|
#endif /* CONFIG_8xx */
|
|
|
|
#if defined(CONFIG_PPC_BOOK3E) || defined(CONFIG_PPC_47x)
|
|
extern void _tlbivax_bcast(unsigned long address, unsigned int pid,
|
|
unsigned int tsize, unsigned int ind);
|
|
#else
|
|
static inline void _tlbivax_bcast(unsigned long address, unsigned int pid,
|
|
unsigned int tsize, unsigned int ind)
|
|
{
|
|
BUG();
|
|
}
|
|
#endif
|
|
|
|
#else /* CONFIG_PPC_MMU_NOHASH */
|
|
|
|
extern void hash_preload(struct mm_struct *mm, unsigned long ea,
|
|
unsigned long access, unsigned long trap);
|
|
|
|
|
|
extern void _tlbie(unsigned long address);
|
|
extern void _tlbia(void);
|
|
|
|
#endif /* CONFIG_PPC_MMU_NOHASH */
|
|
|
|
#ifdef CONFIG_PPC32
|
|
|
|
extern void mapin_ram(void);
|
|
extern int map_page(unsigned long va, phys_addr_t pa, int flags);
|
|
extern void setbat(int index, unsigned long virt, phys_addr_t phys,
|
|
unsigned int size, pgprot_t prot);
|
|
|
|
extern int __map_without_bats;
|
|
extern int __allow_ioremap_reserved;
|
|
extern unsigned long ioremap_base;
|
|
extern unsigned int rtas_data, rtas_size;
|
|
|
|
struct hash_pte;
|
|
extern struct hash_pte *Hash, *Hash_end;
|
|
extern unsigned long Hash_size, Hash_mask;
|
|
|
|
#endif /* CONFIG_PPC32 */
|
|
|
|
#ifdef CONFIG_PPC64
|
|
extern int map_kernel_page(unsigned long ea, unsigned long pa,
|
|
unsigned long flags);
|
|
#endif /* CONFIG_PPC64 */
|
|
|
|
extern unsigned long ioremap_bot;
|
|
extern unsigned long __max_low_memory;
|
|
extern phys_addr_t __initial_memory_limit_addr;
|
|
extern phys_addr_t total_memory;
|
|
extern phys_addr_t total_lowmem;
|
|
extern phys_addr_t memstart_addr;
|
|
extern phys_addr_t lowmem_end_addr;
|
|
|
|
#ifdef CONFIG_WII
|
|
extern unsigned long wii_hole_start;
|
|
extern unsigned long wii_hole_size;
|
|
|
|
extern unsigned long wii_mmu_mapin_mem2(unsigned long top);
|
|
extern void wii_memory_fixups(void);
|
|
#endif
|
|
|
|
/* ...and now those things that may be slightly different between processor
|
|
* architectures. -- Dan
|
|
*/
|
|
#ifdef CONFIG_PPC32
|
|
extern void MMU_init_hw(void);
|
|
extern unsigned long mmu_mapin_ram(unsigned long top);
|
|
#endif
|
|
|
|
#ifdef CONFIG_PPC_FSL_BOOK3E
|
|
extern unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx,
|
|
bool dryrun);
|
|
extern unsigned long calc_cam_sz(unsigned long ram, unsigned long virt,
|
|
phys_addr_t phys);
|
|
#ifdef CONFIG_PPC32
|
|
extern void adjust_total_lowmem(void);
|
|
extern int switch_to_as1(void);
|
|
extern void restore_to_as0(int esel, int offset, void *dt_ptr, int bootcpu);
|
|
#endif
|
|
extern void loadcam_entry(unsigned int index);
|
|
extern void loadcam_multi(int first_idx, int num, int tmp_idx);
|
|
|
|
struct tlbcam {
|
|
u32 MAS0;
|
|
u32 MAS1;
|
|
unsigned long MAS2;
|
|
u32 MAS3;
|
|
u32 MAS7;
|
|
};
|
|
#endif
|