arch/powerpc/mm/pgtable_64.c - maze/linux - Git at Google

 /*
  *  This file contains ioremap and related functions for 64-bit machines.
  *
  *  Derived from arch/ppc64/mm/init.c
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
  *
  *  Modifications by Paul Mackerras (PowerMac) (paulus@samba.org)
  *  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
  *
  *  Dave Engebretsen <engebret@us.ibm.com>
  *      Rework for PPC64 port.
  *
  *  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/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/export.h>
 #include <linux/types.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/stddef.h>
 #include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>

 #include <asm/pgalloc.h>
 #include <asm/page.h>
 #include <asm/prom.h>
 #include <asm/io.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/smp.h>
 #include <asm/machdep.h>
 #include <asm/tlb.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>
 #include <asm/sections.h>
 #include <asm/system.h>
 #include <asm/abs_addr.h>
 #include <asm/firmware.h>

 #include "mmu_decl.h"

 unsigned long ioremap_bot = IOREMAP_BASE;


 #ifdef CONFIG_PPC_MMU_NOHASH
 static void *early_alloc_pgtable(unsigned long size)
 {
 	void *pt;

 	if (init_bootmem_done)
 		pt = __alloc_bootmem(size, size, __pa(MAX_DMA_ADDRESS));
 	else
 		pt = __va(memblock_alloc_base(size, size,
 					 __pa(MAX_DMA_ADDRESS)));
 	memset(pt, 0, size);

 	return pt;
 }
 #endif /* CONFIG_PPC_MMU_NOHASH */

 /*
  * map_kernel_page currently only called by __ioremap
  * map_kernel_page adds an entry to the ioremap page table
  * and adds an entry to the HPT, possibly bolting it
  */
 int map_kernel_page(unsigned long ea, unsigned long pa, int flags)
 {
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;

 	if (slab_is_available()) {
 		pgdp = pgd_offset_k(ea);
 		pudp = pud_alloc(&init_mm, pgdp, ea);
 		if (!pudp)
 			return -ENOMEM;
 		pmdp = pmd_alloc(&init_mm, pudp, ea);
 		if (!pmdp)
 			return -ENOMEM;
 		ptep = pte_alloc_kernel(pmdp, ea);
 		if (!ptep)
 			return -ENOMEM;
 		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
 							  __pgprot(flags)));
 	} else {
 #ifdef CONFIG_PPC_MMU_NOHASH
 		/* Warning ! This will blow up if bootmem is not initialized
 		 * which our ppc64 code is keen to do that, we'll need to
 		 * fix it and/or be more careful
 		 */
 		pgdp = pgd_offset_k(ea);
 #ifdef PUD_TABLE_SIZE
 		if (pgd_none(*pgdp)) {
 			pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
 			BUG_ON(pudp == NULL);
 			pgd_populate(&init_mm, pgdp, pudp);
 		}
 #endif /* PUD_TABLE_SIZE */
 		pudp = pud_offset(pgdp, ea);
 		if (pud_none(*pudp)) {
 			pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
 			BUG_ON(pmdp == NULL);
 			pud_populate(&init_mm, pudp, pmdp);
 		}
 		pmdp = pmd_offset(pudp, ea);
 		if (!pmd_present(*pmdp)) {
 			ptep = early_alloc_pgtable(PAGE_SIZE);
 			BUG_ON(ptep == NULL);
 			pmd_populate_kernel(&init_mm, pmdp, ptep);
 		}
 		ptep = pte_offset_kernel(pmdp, ea);
 		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
 							  __pgprot(flags)));
 #else /* CONFIG_PPC_MMU_NOHASH */
 		/*
 		 * If the mm subsystem is not fully up, we cannot create a
 		 * linux page table entry for this mapping.  Simply bolt an
 		 * entry in the hardware page table.
 		 *
 		 */
 		if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags,
 				      mmu_io_psize, mmu_kernel_ssize)) {
 			printk(KERN_ERR "Failed to do bolted mapping IO "
 			       "memory at %016lx !\n", pa);
 			return -ENOMEM;
 		}
 #endif /* !CONFIG_PPC_MMU_NOHASH */
 	}
 	return 0;
 }


 /**
  * __ioremap_at - Low level function to establish the page tables
  *                for an IO mapping
  */
 void __iomem * __ioremap_at(phys_addr_t pa, void *ea, unsigned long size,
 			    unsigned long flags)
 {
 	unsigned long i;

 	/* Make sure we have the base flags */
 	if ((flags & _PAGE_PRESENT) == 0)
 		flags |= pgprot_val(PAGE_KERNEL);

 	/* Non-cacheable page cannot be coherent */
 	if (flags & _PAGE_NO_CACHE)
 		flags &= ~_PAGE_COHERENT;

 	/* We don't support the 4K PFN hack with ioremap */
 	if (flags & _PAGE_4K_PFN)
 		return NULL;

 	WARN_ON(pa & ~PAGE_MASK);
 	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
 	WARN_ON(size & ~PAGE_MASK);

 	for (i = 0; i < size; i += PAGE_SIZE)
 		if (map_kernel_page((unsigned long)ea+i, pa+i, flags))
 			return NULL;

 	return (void __iomem *)ea;
 }

 /**
  * __iounmap_from - Low level function to tear down the page tables
  *                  for an IO mapping. This is used for mappings that
  *                  are manipulated manually, like partial unmapping of
  *                  PCI IOs or ISA space.
  */
 void __iounmap_at(void *ea, unsigned long size)
 {
 	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
 	WARN_ON(size & ~PAGE_MASK);

 	unmap_kernel_range((unsigned long)ea, size);
 }

 void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
 				unsigned long flags, void *caller)
 {
 	phys_addr_t paligned;
 	void __iomem *ret;

 	/*
 	 * Choose an address to map it to.
 	 * Once the imalloc system is running, we use it.
 	 * Before that, we map using addresses going
 	 * up from ioremap_bot.  imalloc will use
 	 * the addresses from ioremap_bot through
 	 * IMALLOC_END
 	 *
 	 */
 	paligned = addr & PAGE_MASK;
 	size = PAGE_ALIGN(addr + size) - paligned;

 	if ((size == 0) || (paligned == 0))
 		return NULL;

 	if (mem_init_done) {
 		struct vm_struct *area;

 		area = __get_vm_area_caller(size, VM_IOREMAP,
 					    ioremap_bot, IOREMAP_END,
 					    caller);
 		if (area == NULL)
 			return NULL;

 		area->phys_addr = paligned;
 		ret = __ioremap_at(paligned, area->addr, size, flags);
 		if (!ret)
 			vunmap(area->addr);
 	} else {
 		ret = __ioremap_at(paligned, (void *)ioremap_bot, size, flags);
 		if (ret)
 			ioremap_bot += size;
 	}

 	if (ret)
 		ret += addr & ~PAGE_MASK;
 	return ret;
 }

 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(phys_addr_t addr, unsigned long size)
 {
 	unsigned long flags = _PAGE_NO_CACHE | _PAGE_GUARDED;
 	void *caller = __builtin_return_address(0);

 	if (ppc_md.ioremap)
 		return ppc_md.ioremap(addr, size, flags, caller);
 	return __ioremap_caller(addr, size, flags, caller);
 }

 void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size)
 {
 	unsigned long flags = _PAGE_NO_CACHE;
 	void *caller = __builtin_return_address(0);

 	if (ppc_md.ioremap)
 		return ppc_md.ioremap(addr, size, flags, caller);
 	return __ioremap_caller(addr, size, flags, caller);
 }

 void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
 			     unsigned long flags)
 {
 	void *caller = __builtin_return_address(0);

 	/* writeable implies dirty for kernel addresses */
 	if (flags & _PAGE_RW)
 		flags |= _PAGE_DIRTY;

 	/* 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

 	if (ppc_md.ioremap)
 		return ppc_md.ioremap(addr, size, flags, caller);
 	return __ioremap_caller(addr, size, flags, caller);
 }


 /*
  * Unmap an IO region and remove it from imalloc'd list.
  * Access to IO memory should be serialized by driver.
  */
 void __iounmap(volatile void __iomem *token)
 {
 	void *addr;

 	if (!mem_init_done)
 		return;

 	addr = (void *) ((unsigned long __force)
 			 PCI_FIX_ADDR(token) & PAGE_MASK);
 	if ((unsigned long)addr < ioremap_bot) {
 		printk(KERN_WARNING "Attempt to iounmap early bolted mapping"
 		       " at 0x%p\n", addr);
 		return;
 	}
 	vunmap(addr);
 }

 void iounmap(volatile void __iomem *token)
 {
 	if (ppc_md.iounmap)
 		ppc_md.iounmap(token);
 	else
 		__iounmap(token);
 }

 EXPORT_SYMBOL(ioremap);
 EXPORT_SYMBOL(ioremap_wc);
 EXPORT_SYMBOL(ioremap_prot);
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(__ioremap_at);
 EXPORT_SYMBOL(iounmap);
 EXPORT_SYMBOL(__iounmap);
 EXPORT_SYMBOL(__iounmap_at);
	/*
	* This file contains ioremap and related functions for 64-bit machines.
	*
	* Derived from arch/ppc64/mm/init.c
	* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
	*
	* Modifications by Paul Mackerras (PowerMac) (paulus@samba.org)
	* 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
	*
	* Dave Engebretsen <engebret@us.ibm.com>
	* Rework for PPC64 port.
	*
	* 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/signal.h>
	#include <linux/sched.h>
	#include <linux/kernel.h>
	#include <linux/errno.h>
	#include <linux/string.h>
	#include <linux/export.h>
	#include <linux/types.h>
	#include <linux/mman.h>
	#include <linux/mm.h>
	#include <linux/swap.h>
	#include <linux/stddef.h>
	#include <linux/vmalloc.h>
	#include <linux/init.h>
	#include <linux/bootmem.h>
	#include <linux/memblock.h>
	#include <linux/slab.h>

	#include <asm/pgalloc.h>
	#include <asm/page.h>
	#include <asm/prom.h>
	#include <asm/io.h>
	#include <asm/mmu_context.h>
	#include <asm/pgtable.h>
	#include <asm/mmu.h>
	#include <asm/smp.h>
	#include <asm/machdep.h>
	#include <asm/tlb.h>
	#include <asm/processor.h>
	#include <asm/cputable.h>
	#include <asm/sections.h>
	#include <asm/system.h>
	#include <asm/abs_addr.h>
	#include <asm/firmware.h>

	#include "mmu_decl.h"

	unsigned long ioremap_bot = IOREMAP_BASE;


	#ifdef CONFIG_PPC_MMU_NOHASH
	static void *early_alloc_pgtable(unsigned long size)
	{
	void *pt;

	if (init_bootmem_done)
	pt = __alloc_bootmem(size, size, __pa(MAX_DMA_ADDRESS));
	else
	pt = __va(memblock_alloc_base(size, size,
	__pa(MAX_DMA_ADDRESS)));
	memset(pt, 0, size);

	return pt;
	}
	#endif /* CONFIG_PPC_MMU_NOHASH */

	/*
	* map_kernel_page currently only called by __ioremap
	* map_kernel_page adds an entry to the ioremap page table
	* and adds an entry to the HPT, possibly bolting it
	*/
	int map_kernel_page(unsigned long ea, unsigned long pa, int flags)
	{
	pgd_t *pgdp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;

	if (slab_is_available()) {
	pgdp = pgd_offset_k(ea);
	pudp = pud_alloc(&init_mm, pgdp, ea);
	if (!pudp)
	return -ENOMEM;
	pmdp = pmd_alloc(&init_mm, pudp, ea);
	if (!pmdp)
	return -ENOMEM;
	ptep = pte_alloc_kernel(pmdp, ea);
	if (!ptep)
	return -ENOMEM;
	set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
	__pgprot(flags)));
	} else {
	#ifdef CONFIG_PPC_MMU_NOHASH
	/* Warning ! This will blow up if bootmem is not initialized
	* which our ppc64 code is keen to do that, we'll need to
	* fix it and/or be more careful
	*/
	pgdp = pgd_offset_k(ea);
	#ifdef PUD_TABLE_SIZE
	if (pgd_none(*pgdp)) {
	pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
	BUG_ON(pudp == NULL);
	pgd_populate(&init_mm, pgdp, pudp);
	}
	#endif /* PUD_TABLE_SIZE */
	pudp = pud_offset(pgdp, ea);
	if (pud_none(*pudp)) {
	pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
	BUG_ON(pmdp == NULL);
	pud_populate(&init_mm, pudp, pmdp);
	}
	pmdp = pmd_offset(pudp, ea);
	if (!pmd_present(*pmdp)) {
	ptep = early_alloc_pgtable(PAGE_SIZE);
	BUG_ON(ptep == NULL);
	pmd_populate_kernel(&init_mm, pmdp, ptep);
	}
	ptep = pte_offset_kernel(pmdp, ea);
	set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
	__pgprot(flags)));
	#else /* CONFIG_PPC_MMU_NOHASH */
	/*
	* If the mm subsystem is not fully up, we cannot create a
	* linux page table entry for this mapping. Simply bolt an
	* entry in the hardware page table.
	*
	*/
	if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags,
	mmu_io_psize, mmu_kernel_ssize)) {
	printk(KERN_ERR "Failed to do bolted mapping IO "
	"memory at %016lx !\n", pa);
	return -ENOMEM;
	}
	#endif /* !CONFIG_PPC_MMU_NOHASH */
	}
	return 0;
	}


	/**
	* __ioremap_at - Low level function to establish the page tables
	* for an IO mapping
	*/
	void __iomem * __ioremap_at(phys_addr_t pa, void *ea, unsigned long size,
	unsigned long flags)
	{
	unsigned long i;

	/* Make sure we have the base flags */
	if ((flags & _PAGE_PRESENT) == 0)
	flags \|= pgprot_val(PAGE_KERNEL);

	/* Non-cacheable page cannot be coherent */
	if (flags & _PAGE_NO_CACHE)
	flags &= ~_PAGE_COHERENT;

	/* We don't support the 4K PFN hack with ioremap */
	if (flags & _PAGE_4K_PFN)
	return NULL;

	WARN_ON(pa & ~PAGE_MASK);
	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
	WARN_ON(size & ~PAGE_MASK);

	for (i = 0; i < size; i += PAGE_SIZE)
	if (map_kernel_page((unsigned long)ea+i, pa+i, flags))
	return NULL;

	return (void __iomem *)ea;
	}

	/**
	* __iounmap_from - Low level function to tear down the page tables
	* for an IO mapping. This is used for mappings that
	* are manipulated manually, like partial unmapping of
	* PCI IOs or ISA space.
	*/
	void __iounmap_at(void *ea, unsigned long size)
	{
	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
	WARN_ON(size & ~PAGE_MASK);

	unmap_kernel_range((unsigned long)ea, size);
	}

	void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
	unsigned long flags, void *caller)
	{
	phys_addr_t paligned;
	void __iomem *ret;

	/*
	* Choose an address to map it to.
	* Once the imalloc system is running, we use it.
	* Before that, we map using addresses going
	* up from ioremap_bot. imalloc will use
	* the addresses from ioremap_bot through
	* IMALLOC_END
	*
	*/
	paligned = addr & PAGE_MASK;
	size = PAGE_ALIGN(addr + size) - paligned;

	if ((size == 0) \|\| (paligned == 0))
	return NULL;

	if (mem_init_done) {
	struct vm_struct *area;

	area = __get_vm_area_caller(size, VM_IOREMAP,
	ioremap_bot, IOREMAP_END,
	caller);
	if (area == NULL)
	return NULL;

	area->phys_addr = paligned;
	ret = __ioremap_at(paligned, area->addr, size, flags);
	if (!ret)
	vunmap(area->addr);
	} else {
	ret = __ioremap_at(paligned, (void *)ioremap_bot, size, flags);
	if (ret)
	ioremap_bot += size;
	}

	if (ret)
	ret += addr & ~PAGE_MASK;
	return ret;
	}

	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(phys_addr_t addr, unsigned long size)
	{
	unsigned long flags = _PAGE_NO_CACHE \| _PAGE_GUARDED;
	void *caller = __builtin_return_address(0);

	if (ppc_md.ioremap)
	return ppc_md.ioremap(addr, size, flags, caller);
	return __ioremap_caller(addr, size, flags, caller);
	}

	void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size)
	{
	unsigned long flags = _PAGE_NO_CACHE;
	void *caller = __builtin_return_address(0);

	if (ppc_md.ioremap)
	return ppc_md.ioremap(addr, size, flags, caller);
	return __ioremap_caller(addr, size, flags, caller);
	}

	void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
	unsigned long flags)
	{
	void *caller = __builtin_return_address(0);

	/* writeable implies dirty for kernel addresses */
	if (flags & _PAGE_RW)
	flags \|= _PAGE_DIRTY;

	/* 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

	if (ppc_md.ioremap)
	return ppc_md.ioremap(addr, size, flags, caller);
	return __ioremap_caller(addr, size, flags, caller);
	}


	/*
	* Unmap an IO region and remove it from imalloc'd list.
	* Access to IO memory should be serialized by driver.
	*/
	void __iounmap(volatile void __iomem *token)
	{
	void *addr;

	if (!mem_init_done)
	return;

	addr = (void *) ((unsigned long __force)
	PCI_FIX_ADDR(token) & PAGE_MASK);
	if ((unsigned long)addr < ioremap_bot) {
	printk(KERN_WARNING "Attempt to iounmap early bolted mapping"
	" at 0x%p\n", addr);
	return;
	}
	vunmap(addr);
	}

	void iounmap(volatile void __iomem *token)
	{
	if (ppc_md.iounmap)
	ppc_md.iounmap(token);
	else
	__iounmap(token);
	}

	EXPORT_SYMBOL(ioremap);
	EXPORT_SYMBOL(ioremap_wc);
	EXPORT_SYMBOL(ioremap_prot);
	EXPORT_SYMBOL(__ioremap);
	EXPORT_SYMBOL(__ioremap_at);
	EXPORT_SYMBOL(iounmap);
	EXPORT_SYMBOL(__iounmap);
	EXPORT_SYMBOL(__iounmap_at);