mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-03 03:46:51 +07:00
e12401222f
This patch adds support for 256KB pages on ppc44x-based boards. For simplification of implementation with 256KB pages we still assume 2-level paging. As a side effect this leads to wasting extra memory space reserved for PTE tables: only 1/4 of pages allocated for PTEs are actually used. But this may be an acceptable trade-off to achieve the high performance we have with big PAGE_SIZEs in some applications (e.g. RAID). Also with 256KB PAGE_SIZE we increase THREAD_SIZE up to 32KB to minimize the risk of stack overflows in the cases of on-stack arrays, which size depends on the page size (e.g. multipage BIOs, NTFS, etc.). With 256KB PAGE_SIZE we need to decrease the PKMAP_ORDER at least down to 9, otherwise all high memory (2 ^ 10 * PAGE_SIZE == 256MB) we'll be occupied by PKMAP addresses leaving no place for vmalloc. We do not separate PKMAP_ORDER for 256K from 16K/64K PAGE_SIZE here; actually that value of 10 in support for 16K/64K had been selected rather intuitively. Thus now for all cases of PAGE_SIZE on ppc44x (including the default, 4KB, one) we have 512 pages for PKMAP. Because ELF standard supports only page sizes up to 64K, then you should use binutils later than 2.17.50.0.3 with '-zmax-page-size' set to 256K for building applications, which are to be run with the 256KB-page sized kernel. If using the older binutils, then you should patch them like follows: --- binutils/bfd/elf32-ppc.c.orig +++ binutils/bfd/elf32-ppc.c -#define ELF_MAXPAGESIZE 0x10000 +#define ELF_MAXPAGESIZE 0x40000 One more restriction we currently have with 256KB page sizes is inability to use shmem safely, so, for now, the 256KB is available only if you turn the CONFIG_SHMEM option off (another variant is to use BROKEN). Though, if you need shmem with 256KB pages, you can always remove the !SHMEM dependency in 'config PPC_256K_PAGES', and use the workaround available here: http://lkml.org/lkml/2008/12/19/20 Signed-off-by: Yuri Tikhonov <yur@emcraft.com> Signed-off-by: Ilya Yanok <yanok@emcraft.com> Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
242 lines
6.7 KiB
C
242 lines
6.7 KiB
C
#ifndef _ASM_POWERPC_PAGE_H
|
|
#define _ASM_POWERPC_PAGE_H
|
|
|
|
/*
|
|
* Copyright (C) 2001,2005 IBM Corporation.
|
|
*
|
|
* 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.
|
|
*/
|
|
|
|
#ifndef __ASSEMBLY__
|
|
#include <linux/types.h>
|
|
#else
|
|
#include <asm/types.h>
|
|
#endif
|
|
#include <asm/asm-compat.h>
|
|
#include <asm/kdump.h>
|
|
|
|
/*
|
|
* On regular PPC32 page size is 4K (but we support 4K/16K/64K/256K pages
|
|
* on PPC44x). For PPC64 we support either 4K or 64K software
|
|
* page size. When using 64K pages however, whether we are really supporting
|
|
* 64K pages in HW or not is irrelevant to those definitions.
|
|
*/
|
|
#if defined(CONFIG_PPC_256K_PAGES)
|
|
#define PAGE_SHIFT 18
|
|
#elif defined(CONFIG_PPC_64K_PAGES)
|
|
#define PAGE_SHIFT 16
|
|
#elif defined(CONFIG_PPC_16K_PAGES)
|
|
#define PAGE_SHIFT 14
|
|
#else
|
|
#define PAGE_SHIFT 12
|
|
#endif
|
|
|
|
#define PAGE_SIZE (ASM_CONST(1) << PAGE_SHIFT)
|
|
|
|
/* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
|
|
#define __HAVE_ARCH_GATE_AREA 1
|
|
|
|
/*
|
|
* Subtle: (1 << PAGE_SHIFT) is an int, not an unsigned long. So if we
|
|
* assign PAGE_MASK to a larger type it gets extended the way we want
|
|
* (i.e. with 1s in the high bits)
|
|
*/
|
|
#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1))
|
|
|
|
/*
|
|
* KERNELBASE is the virtual address of the start of the kernel, it's often
|
|
* the same as PAGE_OFFSET, but _might not be_.
|
|
*
|
|
* The kdump dump kernel is one example where KERNELBASE != PAGE_OFFSET.
|
|
*
|
|
* PAGE_OFFSET is the virtual address of the start of lowmem.
|
|
*
|
|
* PHYSICAL_START is the physical address of the start of the kernel.
|
|
*
|
|
* MEMORY_START is the physical address of the start of lowmem.
|
|
*
|
|
* KERNELBASE, PAGE_OFFSET, and PHYSICAL_START are all configurable on
|
|
* ppc32 and based on how they are set we determine MEMORY_START.
|
|
*
|
|
* For the linear mapping the following equation should be true:
|
|
* KERNELBASE - PAGE_OFFSET = PHYSICAL_START - MEMORY_START
|
|
*
|
|
* Also, KERNELBASE >= PAGE_OFFSET and PHYSICAL_START >= MEMORY_START
|
|
*
|
|
* There are two was to determine a physical address from a virtual one:
|
|
* va = pa + PAGE_OFFSET - MEMORY_START
|
|
* va = pa + KERNELBASE - PHYSICAL_START
|
|
*
|
|
* If you want to know something's offset from the start of the kernel you
|
|
* should subtract KERNELBASE.
|
|
*
|
|
* If you want to test if something's a kernel address, use is_kernel_addr().
|
|
*/
|
|
|
|
#define KERNELBASE ASM_CONST(CONFIG_KERNEL_START)
|
|
#define PAGE_OFFSET ASM_CONST(CONFIG_PAGE_OFFSET)
|
|
#define LOAD_OFFSET ASM_CONST((CONFIG_KERNEL_START-CONFIG_PHYSICAL_START))
|
|
|
|
#if defined(CONFIG_RELOCATABLE)
|
|
#ifndef __ASSEMBLY__
|
|
|
|
extern phys_addr_t memstart_addr;
|
|
extern phys_addr_t kernstart_addr;
|
|
#endif
|
|
#define PHYSICAL_START kernstart_addr
|
|
#else
|
|
#define PHYSICAL_START ASM_CONST(CONFIG_PHYSICAL_START)
|
|
#endif
|
|
|
|
#ifdef CONFIG_PPC64
|
|
#define MEMORY_START 0UL
|
|
#elif defined(CONFIG_RELOCATABLE)
|
|
#define MEMORY_START memstart_addr
|
|
#else
|
|
#define MEMORY_START (PHYSICAL_START + PAGE_OFFSET - KERNELBASE)
|
|
#endif
|
|
|
|
#ifdef CONFIG_FLATMEM
|
|
#define ARCH_PFN_OFFSET (MEMORY_START >> PAGE_SHIFT)
|
|
#define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && (pfn) < (ARCH_PFN_OFFSET + max_mapnr))
|
|
#endif
|
|
|
|
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
|
|
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
|
|
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
|
|
|
|
#define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - MEMORY_START))
|
|
#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET + MEMORY_START)
|
|
|
|
/*
|
|
* Unfortunately the PLT is in the BSS in the PPC32 ELF ABI,
|
|
* and needs to be executable. This means the whole heap ends
|
|
* up being executable.
|
|
*/
|
|
#define VM_DATA_DEFAULT_FLAGS32 (VM_READ | VM_WRITE | VM_EXEC | \
|
|
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
|
|
|
|
#define VM_DATA_DEFAULT_FLAGS64 (VM_READ | VM_WRITE | \
|
|
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
|
|
|
|
#ifdef __powerpc64__
|
|
#include <asm/page_64.h>
|
|
#else
|
|
#include <asm/page_32.h>
|
|
#endif
|
|
|
|
/* align addr on a size boundary - adjust address up/down if needed */
|
|
#define _ALIGN_UP(addr,size) (((addr)+((size)-1))&(~((size)-1)))
|
|
#define _ALIGN_DOWN(addr,size) ((addr)&(~((size)-1)))
|
|
|
|
/* align addr on a size boundary - adjust address up if needed */
|
|
#define _ALIGN(addr,size) _ALIGN_UP(addr,size)
|
|
|
|
/*
|
|
* Don't compare things with KERNELBASE or PAGE_OFFSET to test for
|
|
* "kernelness", use is_kernel_addr() - it should do what you want.
|
|
*/
|
|
#define is_kernel_addr(x) ((x) >= PAGE_OFFSET)
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#undef STRICT_MM_TYPECHECKS
|
|
|
|
#ifdef STRICT_MM_TYPECHECKS
|
|
/* These are used to make use of C type-checking. */
|
|
|
|
/* PTE level */
|
|
typedef struct { pte_basic_t pte; } pte_t;
|
|
#define pte_val(x) ((x).pte)
|
|
#define __pte(x) ((pte_t) { (x) })
|
|
|
|
/* 64k pages additionally define a bigger "real PTE" type that gathers
|
|
* the "second half" part of the PTE for pseudo 64k pages
|
|
*/
|
|
#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
|
|
typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
|
|
#else
|
|
typedef struct { pte_t pte; } real_pte_t;
|
|
#endif
|
|
|
|
/* PMD level */
|
|
#ifdef CONFIG_PPC64
|
|
typedef struct { unsigned long pmd; } pmd_t;
|
|
#define pmd_val(x) ((x).pmd)
|
|
#define __pmd(x) ((pmd_t) { (x) })
|
|
|
|
/* PUD level exusts only on 4k pages */
|
|
#ifndef CONFIG_PPC_64K_PAGES
|
|
typedef struct { unsigned long pud; } pud_t;
|
|
#define pud_val(x) ((x).pud)
|
|
#define __pud(x) ((pud_t) { (x) })
|
|
#endif /* !CONFIG_PPC_64K_PAGES */
|
|
#endif /* CONFIG_PPC64 */
|
|
|
|
/* PGD level */
|
|
typedef struct { unsigned long pgd; } pgd_t;
|
|
#define pgd_val(x) ((x).pgd)
|
|
#define __pgd(x) ((pgd_t) { (x) })
|
|
|
|
/* Page protection bits */
|
|
typedef struct { unsigned long pgprot; } pgprot_t;
|
|
#define pgprot_val(x) ((x).pgprot)
|
|
#define __pgprot(x) ((pgprot_t) { (x) })
|
|
|
|
#else
|
|
|
|
/*
|
|
* .. while these make it easier on the compiler
|
|
*/
|
|
|
|
typedef pte_basic_t pte_t;
|
|
#define pte_val(x) (x)
|
|
#define __pte(x) (x)
|
|
|
|
#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
|
|
typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
|
|
#else
|
|
typedef pte_t real_pte_t;
|
|
#endif
|
|
|
|
|
|
#ifdef CONFIG_PPC64
|
|
typedef unsigned long pmd_t;
|
|
#define pmd_val(x) (x)
|
|
#define __pmd(x) (x)
|
|
|
|
#ifndef CONFIG_PPC_64K_PAGES
|
|
typedef unsigned long pud_t;
|
|
#define pud_val(x) (x)
|
|
#define __pud(x) (x)
|
|
#endif /* !CONFIG_PPC_64K_PAGES */
|
|
#endif /* CONFIG_PPC64 */
|
|
|
|
typedef unsigned long pgd_t;
|
|
#define pgd_val(x) (x)
|
|
#define pgprot_val(x) (x)
|
|
|
|
typedef unsigned long pgprot_t;
|
|
#define __pgd(x) (x)
|
|
#define __pgprot(x) (x)
|
|
|
|
#endif
|
|
|
|
struct page;
|
|
extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
|
|
extern void copy_user_page(void *to, void *from, unsigned long vaddr,
|
|
struct page *p);
|
|
extern int page_is_ram(unsigned long pfn);
|
|
|
|
struct vm_area_struct;
|
|
|
|
typedef struct page *pgtable_t;
|
|
|
|
#include <asm-generic/memory_model.h>
|
|
#endif /* __ASSEMBLY__ */
|
|
|
|
#endif /* _ASM_POWERPC_PAGE_H */
|