linux_dsm_epyc7002/arch/powerpc/mm/pgtable_32.c

457 lines
11 KiB
C
Raw Normal View History

/*
* This file contains the routines setting up the linux page tables.
* -- paulus
*
* 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/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/memblock.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/fixmap.h>
#include <asm/io.h>
#include <asm/setup.h>
#include "mmu_decl.h"
unsigned long ioremap_base;
unsigned long ioremap_bot;
EXPORT_SYMBOL(ioremap_bot); /* aka VMALLOC_END */
#if defined(CONFIG_6xx) || defined(CONFIG_POWER3)
#define HAVE_BATS 1
#endif
#if defined(CONFIG_FSL_BOOKE)
#define HAVE_TLBCAM 1
#endif
extern char etext[], _stext[];
#ifdef HAVE_BATS
extern phys_addr_t v_mapped_by_bats(unsigned long va);
extern unsigned long p_mapped_by_bats(phys_addr_t pa);
void setbat(int index, unsigned long virt, phys_addr_t phys,
unsigned int size, int flags);
#else /* !HAVE_BATS */
#define v_mapped_by_bats(x) (0UL)
#define p_mapped_by_bats(x) (0UL)
#endif /* HAVE_BATS */
#ifdef HAVE_TLBCAM
extern unsigned int tlbcam_index;
extern phys_addr_t v_mapped_by_tlbcam(unsigned long va);
extern unsigned long p_mapped_by_tlbcam(phys_addr_t pa);
#else /* !HAVE_TLBCAM */
#define v_mapped_by_tlbcam(x) (0UL)
#define p_mapped_by_tlbcam(x) (0UL)
#endif /* HAVE_TLBCAM */
#define PGDIR_ORDER (32 + PGD_T_LOG2 - PGDIR_SHIFT)
pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *ret;
/* pgdir take page or two with 4K pages and a page fraction otherwise */
#ifndef CONFIG_PPC_4K_PAGES
ret = kzalloc(1 << PGDIR_ORDER, GFP_KERNEL);
#else
ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
PGDIR_ORDER - PAGE_SHIFT);
#endif
return ret;
}
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
#ifndef CONFIG_PPC_4K_PAGES
kfree((void *)pgd);
#else
free_pages((unsigned long)pgd, PGDIR_ORDER - PAGE_SHIFT);
#endif
}
__init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
pte_t *pte;
extern int mem_init_done;
extern void *early_get_page(void);
if (mem_init_done) {
pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
} else {
pte = (pte_t *)early_get_page();
if (pte)
clear_page(pte);
}
return pte;
}
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 19:22:04 +07:00
pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
struct page *ptepage;
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 19:22:04 +07:00
gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
ptepage = alloc_pages(flags, 0);
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 19:22:04 +07:00
if (!ptepage)
return NULL;
pgtable_page_ctor(ptepage);
return ptepage;
}
void __iomem *
ioremap(phys_addr_t addr, unsigned long size)
{
return __ioremap_caller(addr, size, _PAGE_NO_CACHE | _PAGE_GUARDED,
__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap);
void __iomem *
ioremap_wc(phys_addr_t addr, unsigned long size)
{
return __ioremap_caller(addr, size, _PAGE_NO_CACHE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_wc);
void __iomem *
ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
{
/* writeable implies dirty for kernel addresses */
if (flags & _PAGE_RW)
flags |= _PAGE_DIRTY | _PAGE_HWWRITE;
/* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
flags &= ~(_PAGE_USER | _PAGE_EXEC);
#ifdef _PAGE_BAP_SR
/* _PAGE_USER contains _PAGE_BAP_SR on BookE using the new PTE format
* which means that we just cleared supervisor access... oops ;-) This
* restores it
*/
flags |= _PAGE_BAP_SR;
#endif
return __ioremap_caller(addr, size, flags, __builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_prot);
void __iomem *
__ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
{
return __ioremap_caller(addr, size, flags, __builtin_return_address(0));
}
void __iomem *
__ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
void *caller)
{
unsigned long v, i;
phys_addr_t p;
int err;
/* Make sure we have the base flags */
if ((flags & _PAGE_PRESENT) == 0)
flags |= PAGE_KERNEL;
/* Non-cacheable page cannot be coherent */
if (flags & _PAGE_NO_CACHE)
flags &= ~_PAGE_COHERENT;
/*
* Choose an address to map it to.
* Once the vmalloc system is running, we use it.
* Before then, we use space going down from ioremap_base
* (ioremap_bot records where we're up to).
*/
p = addr & PAGE_MASK;
size = PAGE_ALIGN(addr + size) - p;
/*
* If the address lies within the first 16 MB, assume it's in ISA
* memory space
*/
if (p < 16*1024*1024)
p += _ISA_MEM_BASE;
#ifndef CONFIG_CRASH_DUMP
/*
* Don't allow anybody to remap normal RAM that we're using.
* mem_init() sets high_memory so only do the check after that.
*/
if (mem_init_done && (p < virt_to_phys(high_memory)) &&
!(__allow_ioremap_reserved && memblock_is_region_reserved(p, size))) {
printk("__ioremap(): phys addr 0x%llx is RAM lr %pf\n",
(unsigned long long)p, __builtin_return_address(0));
return NULL;
}
#endif
if (size == 0)
return NULL;
/*
* Is it already mapped? Perhaps overlapped by a previous
* BAT mapping. If the whole area is mapped then we're done,
* otherwise remap it since we want to keep the virt addrs for
* each request contiguous.
*
* We make the assumption here that if the bottom and top
* of the range we want are mapped then it's mapped to the
* same virt address (and this is contiguous).
* -- Cort
*/
if ((v = p_mapped_by_bats(p)) /*&& p_mapped_by_bats(p+size-1)*/ )
goto out;
if ((v = p_mapped_by_tlbcam(p)))
goto out;
if (mem_init_done) {
struct vm_struct *area;
area = get_vm_area_caller(size, VM_IOREMAP, caller);
if (area == 0)
return NULL;
area->phys_addr = p;
v = (unsigned long) area->addr;
} else {
v = (ioremap_bot -= size);
}
/*
* Should check if it is a candidate for a BAT mapping
*/
err = 0;
for (i = 0; i < size && err == 0; i += PAGE_SIZE)
err = map_page(v+i, p+i, flags);
if (err) {
if (mem_init_done)
vunmap((void *)v);
return NULL;
}
out:
return (void __iomem *) (v + ((unsigned long)addr & ~PAGE_MASK));
}
EXPORT_SYMBOL(__ioremap);
void iounmap(volatile void __iomem *addr)
{
/*
* If mapped by BATs then there is nothing to do.
* Calling vfree() generates a benign warning.
*/
if (v_mapped_by_bats((unsigned long)addr)) return;
if (addr > high_memory && (unsigned long) addr < ioremap_bot)
vunmap((void *) (PAGE_MASK & (unsigned long)addr));
}
EXPORT_SYMBOL(iounmap);
int map_page(unsigned long va, phys_addr_t pa, int flags)
{
pmd_t *pd;
pte_t *pg;
int err = -ENOMEM;
/* Use upper 10 bits of VA to index the first level map */
pd = pmd_offset(pud_offset(pgd_offset_k(va), va), va);
/* Use middle 10 bits of VA to index the second-level map */
pg = pte_alloc_kernel(pd, va);
if (pg != 0) {
err = 0;
/* The PTE should never be already set nor present in the
* hash table
*/
BUG_ON((pte_val(*pg) & (_PAGE_PRESENT | _PAGE_HASHPTE)) &&
flags);
set_pte_at(&init_mm, va, pg, pfn_pte(pa >> PAGE_SHIFT,
__pgprot(flags)));
}
return err;
}
/*
* Map in a chunk of physical memory starting at start.
*/
void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
{
unsigned long v, s, f;
phys_addr_t p;
int ktext;
s = offset;
v = PAGE_OFFSET + s;
p = memstart_addr + s;
for (; s < top; s += PAGE_SIZE) {
ktext = ((char *) v >= _stext && (char *) v < etext);
f = ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL;
map_page(v, p, f);
#ifdef CONFIG_PPC_STD_MMU_32
if (ktext)
hash_preload(&init_mm, v, 0, 0x300);
#endif
v += PAGE_SIZE;
p += PAGE_SIZE;
}
}
void __init mapin_ram(void)
{
unsigned long s, top;
#ifndef CONFIG_WII
top = total_lowmem;
s = mmu_mapin_ram(top);
__mapin_ram_chunk(s, top);
#else
if (!wii_hole_size) {
s = mmu_mapin_ram(total_lowmem);
__mapin_ram_chunk(s, total_lowmem);
} else {
top = wii_hole_start;
s = mmu_mapin_ram(top);
__mapin_ram_chunk(s, top);
top = memblock_end_of_DRAM();
s = wii_mmu_mapin_mem2(top);
__mapin_ram_chunk(s, top);
}
#endif
}
/* Scan the real Linux page tables and return a PTE pointer for
* a virtual address in a context.
* Returns true (1) if PTE was found, zero otherwise. The pointer to
* the PTE pointer is unmodified if PTE is not found.
*/
int
get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, pmd_t **pmdp)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
int retval = 0;
pgd = pgd_offset(mm, addr & PAGE_MASK);
if (pgd) {
pud = pud_offset(pgd, addr & PAGE_MASK);
if (pud && pud_present(*pud)) {
pmd = pmd_offset(pud, addr & PAGE_MASK);
if (pmd_present(*pmd)) {
pte = pte_offset_map(pmd, addr & PAGE_MASK);
if (pte) {
retval = 1;
*ptep = pte;
if (pmdp)
*pmdp = pmd;
/* XXX caller needs to do pte_unmap, yuck */
}
}
}
}
return(retval);
}
#ifdef CONFIG_DEBUG_PAGEALLOC
static int __change_page_attr(struct page *page, pgprot_t prot)
{
pte_t *kpte;
pmd_t *kpmd;
unsigned long address;
BUG_ON(PageHighMem(page));
address = (unsigned long)page_address(page);
if (v_mapped_by_bats(address) || v_mapped_by_tlbcam(address))
return 0;
if (!get_pteptr(&init_mm, address, &kpte, &kpmd))
return -EINVAL;
__set_pte_at(&init_mm, address, kpte, mk_pte(page, prot), 0);
wmb();
flush_tlb_page(NULL, address);
pte_unmap(kpte);
return 0;
}
/*
* Change the page attributes of an page in the linear mapping.
*
* THIS CONFLICTS WITH BAT MAPPINGS, DEBUG USE ONLY
*/
static int change_page_attr(struct page *page, int numpages, pgprot_t prot)
{
int i, err = 0;
unsigned long flags;
local_irq_save(flags);
for (i = 0; i < numpages; i++, page++) {
err = __change_page_attr(page, prot);
if (err)
break;
}
local_irq_restore(flags);
return err;
}
void kernel_map_pages(struct page *page, int numpages, int enable)
{
if (PageHighMem(page))
return;
change_page_attr(page, numpages, enable ? PAGE_KERNEL : __pgprot(0));
}
#endif /* CONFIG_DEBUG_PAGEALLOC */
static int fixmaps;
void __set_fixmap (enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags)
{
unsigned long address = __fix_to_virt(idx);
if (idx >= __end_of_fixed_addresses) {
BUG();
return;
}
map_page(address, phys, pgprot_val(flags));
fixmaps++;
}
void __this_fixmap_does_not_exist(void)
{
WARN_ON(1);
}