From: Paul Mackerras Date: Mon, 31 Oct 2005 02:37:12 +0000 (+1100) Subject: Merge ../linux-2.6 by hand X-Git-Tag: v2.6.15-rc1~59^2~15 X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=23fd07750a789a66fe88cf173d52a18f1a387da4;p=linux-2.6 Merge ../linux-2.6 by hand --- 23fd07750a789a66fe88cf173d52a18f1a387da4 diff --cc arch/powerpc/mm/mem.c index e43e8ef700,0000000000..117b00012e mode 100644,000000..100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@@ -1,484 -1,0 +1,564 @@@ +/* + * PowerPC version + * 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 + * Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk). + * PPC44x/36-bit changes by Matt Porter (mporter@mvista.com) + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#ifdef CONFIG_PPC64 +#include +#endif + +#include "mmu_decl.h" + +#ifndef CPU_FTR_COHERENT_ICACHE +#define CPU_FTR_COHERENT_ICACHE 0 /* XXX for now */ +#define CPU_FTR_NOEXECUTE 0 +#endif + +int init_bootmem_done; +int mem_init_done; +unsigned long memory_limit; + +/* + * This is called by /dev/mem to know if a given address has to + * be mapped non-cacheable or not + */ +int page_is_ram(unsigned long pfn) +{ + unsigned long paddr = (pfn << PAGE_SHIFT); + +#ifndef CONFIG_PPC64 /* XXX for now */ + return paddr < __pa(high_memory); +#else + int i; + for (i=0; i < lmb.memory.cnt; i++) { + unsigned long base; + + base = lmb.memory.region[i].base; + + if ((paddr >= base) && + (paddr < (base + lmb.memory.region[i].size))) { + return 1; + } + } + + return 0; +#endif +} +EXPORT_SYMBOL(page_is_ram); + +pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot) +{ + if (ppc_md.phys_mem_access_prot) + return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot); + + if (!page_is_ram(pfn)) + vma_prot = __pgprot(pgprot_val(vma_prot) + | _PAGE_GUARDED | _PAGE_NO_CACHE); + return vma_prot; +} +EXPORT_SYMBOL(phys_mem_access_prot); + ++#ifdef CONFIG_MEMORY_HOTPLUG ++ ++void online_page(struct page *page) ++{ ++ ClearPageReserved(page); ++ free_cold_page(page); ++ totalram_pages++; ++ num_physpages++; ++} ++ ++/* ++ * This works only for the non-NUMA case. Later, we'll need a lookup ++ * to convert from real physical addresses to nid, that doesn't use ++ * pfn_to_nid(). ++ */ ++int __devinit add_memory(u64 start, u64 size) ++{ ++ struct pglist_data *pgdata = NODE_DATA(0); ++ struct zone *zone; ++ unsigned long start_pfn = start >> PAGE_SHIFT; ++ unsigned long nr_pages = size >> PAGE_SHIFT; ++ ++ /* this should work for most non-highmem platforms */ ++ zone = pgdata->node_zones; ++ ++ return __add_pages(zone, start_pfn, nr_pages); ++ ++ return 0; ++} ++ ++/* ++ * First pass at this code will check to determine if the remove ++ * request is within the RMO. Do not allow removal within the RMO. ++ */ ++int __devinit remove_memory(u64 start, u64 size) ++{ ++ struct zone *zone; ++ unsigned long start_pfn, end_pfn, nr_pages; ++ ++ start_pfn = start >> PAGE_SHIFT; ++ nr_pages = size >> PAGE_SHIFT; ++ end_pfn = start_pfn + nr_pages; ++ ++ printk("%s(): Attempting to remove memoy in range " ++ "%lx to %lx\n", __func__, start, start+size); ++ /* ++ * check for range within RMO ++ */ ++ zone = page_zone(pfn_to_page(start_pfn)); ++ ++ printk("%s(): memory will be removed from " ++ "the %s zone\n", __func__, zone->name); ++ ++ /* ++ * not handling removing memory ranges that ++ * overlap multiple zones yet ++ */ ++ if (end_pfn > (zone->zone_start_pfn + zone->spanned_pages)) ++ goto overlap; ++ ++ /* make sure it is NOT in RMO */ ++ if ((start < lmb.rmo_size) || ((start+size) < lmb.rmo_size)) { ++ printk("%s(): range to be removed must NOT be in RMO!\n", ++ __func__); ++ goto in_rmo; ++ } ++ ++ return __remove_pages(zone, start_pfn, nr_pages); ++ ++overlap: ++ printk("%s(): memory range to be removed overlaps " ++ "multiple zones!!!\n", __func__); ++in_rmo: ++ return -1; ++} ++#endif /* CONFIG_MEMORY_HOTPLUG */ ++ +void show_mem(void) +{ + unsigned long total = 0, reserved = 0; + unsigned long shared = 0, cached = 0; + unsigned long highmem = 0; + struct page *page; + pg_data_t *pgdat; + unsigned long i; + + printk("Mem-info:\n"); + show_free_areas(); + printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); + for_each_pgdat(pgdat) { ++ unsigned long flags; ++ pgdat_resize_lock(pgdat, &flags); + for (i = 0; i < pgdat->node_spanned_pages; i++) { + page = pgdat_page_nr(pgdat, i); + total++; + if (PageHighMem(page)) + highmem++; + if (PageReserved(page)) + reserved++; + else if (PageSwapCache(page)) + cached++; + else if (page_count(page)) + shared += page_count(page) - 1; + } ++ pgdat_resize_unlock(pgdat, &flags); + } + printk("%ld pages of RAM\n", total); +#ifdef CONFIG_HIGHMEM + printk("%ld pages of HIGHMEM\n", highmem); +#endif + printk("%ld reserved pages\n", reserved); + printk("%ld pages shared\n", shared); + printk("%ld pages swap cached\n", cached); +} + +/* + * Initialize the bootmem system and give it all the memory we + * have available. If we are using highmem, we only put the + * lowmem into the bootmem system. + */ +#ifndef CONFIG_NEED_MULTIPLE_NODES +void __init do_init_bootmem(void) +{ + unsigned long i; + unsigned long start, bootmap_pages; + unsigned long total_pages; + int boot_mapsize; + + max_pfn = total_pages = lmb_end_of_DRAM() >> PAGE_SHIFT; +#ifdef CONFIG_HIGHMEM + total_pages = total_lowmem >> PAGE_SHIFT; +#endif + + /* + * Find an area to use for the bootmem bitmap. Calculate the size of + * bitmap required as (Total Memory) / PAGE_SIZE / BITS_PER_BYTE. + * Add 1 additional page in case the address isn't page-aligned. + */ + bootmap_pages = bootmem_bootmap_pages(total_pages); + + start = lmb_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE); + BUG_ON(!start); + + boot_mapsize = init_bootmem(start >> PAGE_SHIFT, total_pages); + + /* Add all physical memory to the bootmem map, mark each area + * present. + */ + for (i = 0; i < lmb.memory.cnt; i++) { + unsigned long base = lmb.memory.region[i].base; + unsigned long size = lmb_size_bytes(&lmb.memory, i); +#ifdef CONFIG_HIGHMEM + if (base >= total_lowmem) + continue; + if (base + size > total_lowmem) + size = total_lowmem - base; +#endif + free_bootmem(base, size); + } + + /* reserve the sections we're already using */ + for (i = 0; i < lmb.reserved.cnt; i++) + reserve_bootmem(lmb.reserved.region[i].base, + lmb_size_bytes(&lmb.reserved, i)); + + /* XXX need to clip this if using highmem? */ + for (i = 0; i < lmb.memory.cnt; i++) + memory_present(0, lmb_start_pfn(&lmb.memory, i), + lmb_end_pfn(&lmb.memory, i)); + init_bootmem_done = 1; +} + +/* + * paging_init() sets up the page tables - in fact we've already done this. + */ +void __init paging_init(void) +{ + unsigned long zones_size[MAX_NR_ZONES]; + unsigned long zholes_size[MAX_NR_ZONES]; + unsigned long total_ram = lmb_phys_mem_size(); + unsigned long top_of_ram = lmb_end_of_DRAM(); + +#ifdef CONFIG_HIGHMEM + map_page(PKMAP_BASE, 0, 0); /* XXX gross */ + pkmap_page_table = pte_offset_kernel(pmd_offset(pgd_offset_k + (PKMAP_BASE), PKMAP_BASE), PKMAP_BASE); + map_page(KMAP_FIX_BEGIN, 0, 0); /* XXX gross */ + kmap_pte = pte_offset_kernel(pmd_offset(pgd_offset_k + (KMAP_FIX_BEGIN), KMAP_FIX_BEGIN), KMAP_FIX_BEGIN); + kmap_prot = PAGE_KERNEL; +#endif /* CONFIG_HIGHMEM */ + + printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n", + top_of_ram, total_ram); + printk(KERN_INFO "Memory hole size: %ldMB\n", + (top_of_ram - total_ram) >> 20); + /* + * All pages are DMA-able so we put them all in the DMA zone. + */ + memset(zones_size, 0, sizeof(zones_size)); + memset(zholes_size, 0, sizeof(zholes_size)); + + zones_size[ZONE_DMA] = top_of_ram >> PAGE_SHIFT; + zholes_size[ZONE_DMA] = (top_of_ram - total_ram) >> PAGE_SHIFT; + +#ifdef CONFIG_HIGHMEM + zones_size[ZONE_DMA] = total_lowmem >> PAGE_SHIFT; + zones_size[ZONE_HIGHMEM] = (total_memory - total_lowmem) >> PAGE_SHIFT; + zholes_size[ZONE_HIGHMEM] = (top_of_ram - total_ram) >> PAGE_SHIFT; +#else + zones_size[ZONE_DMA] = top_of_ram >> PAGE_SHIFT; + zholes_size[ZONE_DMA] = (top_of_ram - total_ram) >> PAGE_SHIFT; +#endif /* CONFIG_HIGHMEM */ + + free_area_init_node(0, NODE_DATA(0), zones_size, + __pa(PAGE_OFFSET) >> PAGE_SHIFT, zholes_size); +} +#endif /* ! CONFIG_NEED_MULTIPLE_NODES */ + +void __init mem_init(void) +{ +#ifdef CONFIG_NEED_MULTIPLE_NODES + int nid; +#endif + pg_data_t *pgdat; + unsigned long i; + struct page *page; + unsigned long reservedpages = 0, codesize, initsize, datasize, bsssize; + + num_physpages = max_pfn; /* RAM is assumed contiguous */ + high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); + +#ifdef CONFIG_NEED_MULTIPLE_NODES + for_each_online_node(nid) { + if (NODE_DATA(nid)->node_spanned_pages != 0) { + printk("freeing bootmem node %x\n", nid); + totalram_pages += + free_all_bootmem_node(NODE_DATA(nid)); + } + } +#else + max_mapnr = num_physpages; + totalram_pages += free_all_bootmem(); +#endif + for_each_pgdat(pgdat) { + for (i = 0; i < pgdat->node_spanned_pages; i++) { + page = pgdat_page_nr(pgdat, i); + if (PageReserved(page)) + reservedpages++; + } + } + + codesize = (unsigned long)&_sdata - (unsigned long)&_stext; + datasize = (unsigned long)&__init_begin - (unsigned long)&_sdata; + initsize = (unsigned long)&__init_end - (unsigned long)&__init_begin; + bsssize = (unsigned long)&__bss_stop - (unsigned long)&__bss_start; + +#ifdef CONFIG_HIGHMEM + { + unsigned long pfn, highmem_mapnr; + + highmem_mapnr = total_lowmem >> PAGE_SHIFT; + for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) { + struct page *page = pfn_to_page(pfn); + + ClearPageReserved(page); + set_page_count(page, 1); + __free_page(page); + totalhigh_pages++; + } + totalram_pages += totalhigh_pages; + printk(KERN_INFO "High memory: %luk\n", + totalhigh_pages << (PAGE_SHIFT-10)); + } +#endif /* CONFIG_HIGHMEM */ + + printk(KERN_INFO "Memory: %luk/%luk available (%luk kernel code, " + "%luk reserved, %luk data, %luk bss, %luk init)\n", + (unsigned long)nr_free_pages() << (PAGE_SHIFT-10), + num_physpages << (PAGE_SHIFT-10), + codesize >> 10, + reservedpages << (PAGE_SHIFT-10), + datasize >> 10, + bsssize >> 10, + initsize >> 10); + + mem_init_done = 1; + +#ifdef CONFIG_PPC64 + /* Initialize the vDSO */ + vdso_init(); +#endif +} + +/* + * This is called when a page has been modified by the kernel. + * It just marks the page as not i-cache clean. We do the i-cache + * flush later when the page is given to a user process, if necessary. + */ +void flush_dcache_page(struct page *page) +{ + if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) + return; + /* avoid an atomic op if possible */ + if (test_bit(PG_arch_1, &page->flags)) + clear_bit(PG_arch_1, &page->flags); +} +EXPORT_SYMBOL(flush_dcache_page); + +void flush_dcache_icache_page(struct page *page) +{ +#ifdef CONFIG_BOOKE + void *start = kmap_atomic(page, KM_PPC_SYNC_ICACHE); + __flush_dcache_icache(start); + kunmap_atomic(start, KM_PPC_SYNC_ICACHE); +#elif defined(CONFIG_8xx) || defined(CONFIG_PPC64) + /* On 8xx there is no need to kmap since highmem is not supported */ + __flush_dcache_icache(page_address(page)); +#else + __flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT); +#endif + +} +void clear_user_page(void *page, unsigned long vaddr, struct page *pg) +{ + clear_page(page); + + if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) + return; + /* + * We shouldnt have to do this, but some versions of glibc + * require it (ld.so assumes zero filled pages are icache clean) + * - Anton + */ + + /* avoid an atomic op if possible */ + if (test_bit(PG_arch_1, &pg->flags)) + clear_bit(PG_arch_1, &pg->flags); +} +EXPORT_SYMBOL(clear_user_page); + +void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, + struct page *pg) +{ + copy_page(vto, vfrom); + + /* + * We should be able to use the following optimisation, however + * there are two problems. + * Firstly a bug in some versions of binutils meant PLT sections + * were not marked executable. + * Secondly the first word in the GOT section is blrl, used + * to establish the GOT address. Until recently the GOT was + * not marked executable. + * - Anton + */ +#if 0 + if (!vma->vm_file && ((vma->vm_flags & VM_EXEC) == 0)) + return; +#endif + + if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) + return; + + /* avoid an atomic op if possible */ + if (test_bit(PG_arch_1, &pg->flags)) + clear_bit(PG_arch_1, &pg->flags); +} + +void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, + unsigned long addr, int len) +{ + unsigned long maddr; + + maddr = (unsigned long) kmap(page) + (addr & ~PAGE_MASK); + flush_icache_range(maddr, maddr + len); + kunmap(page); +} +EXPORT_SYMBOL(flush_icache_user_range); + +/* + * This is called at the end of handling a user page fault, when the + * fault has been handled by updating a PTE in the linux page tables. + * We use it to preload an HPTE into the hash table corresponding to + * the updated linux PTE. + * + * This must always be called with the mm->page_table_lock held + */ +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, + pte_t pte) +{ + /* handle i-cache coherency */ + unsigned long pfn = pte_pfn(pte); +#ifdef CONFIG_PPC32 + pmd_t *pmd; +#else + unsigned long vsid; + void *pgdir; + pte_t *ptep; + int local = 0; + cpumask_t tmp; + unsigned long flags; +#endif + + /* handle i-cache coherency */ + if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE) && + !cpu_has_feature(CPU_FTR_NOEXECUTE) && + pfn_valid(pfn)) { + struct page *page = pfn_to_page(pfn); + if (!PageReserved(page) + && !test_bit(PG_arch_1, &page->flags)) { + if (vma->vm_mm == current->active_mm) { +#ifdef CONFIG_8xx + /* On 8xx, cache control instructions (particularly + * "dcbst" from flush_dcache_icache) fault as write + * operation if there is an unpopulated TLB entry + * for the address in question. To workaround that, + * we invalidate the TLB here, thus avoiding dcbst + * misbehaviour. + */ + _tlbie(address); +#endif + __flush_dcache_icache((void *) address); + } else + flush_dcache_icache_page(page); + set_bit(PG_arch_1, &page->flags); + } + } + +#ifdef CONFIG_PPC_STD_MMU + /* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */ + if (!pte_young(pte) || address >= TASK_SIZE) + return; +#ifdef CONFIG_PPC32 + if (Hash == 0) + return; + pmd = pmd_offset(pgd_offset(vma->vm_mm, address), address); + if (!pmd_none(*pmd)) + add_hash_page(vma->vm_mm->context, address, pmd_val(*pmd)); +#else + pgdir = vma->vm_mm->pgd; + if (pgdir == NULL) + return; + + ptep = find_linux_pte(pgdir, address); + if (!ptep) + return; + + vsid = get_vsid(vma->vm_mm->context.id, address); + + local_irq_save(flags); + tmp = cpumask_of_cpu(smp_processor_id()); + if (cpus_equal(vma->vm_mm->cpu_vm_mask, tmp)) + local = 1; + + __hash_page(address, 0, vsid, ptep, 0x300, local); + local_irq_restore(flags); +#endif +#endif +} diff --cc arch/powerpc/mm/pgtable_64.c index 484d24f920,0000000000..b79a782061 mode 100644,000000..100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@@ -1,349 -1,0 +1,347 @@@ +/* + * 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 + * Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk). + * + * Derived from "arch/i386/mm/init.c" + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * + * Dave Engebretsen + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +unsigned long ioremap_bot = IMALLOC_BASE; +static unsigned long phbs_io_bot = PHBS_IO_BASE; + +#ifdef CONFIG_PPC_ISERIES + +void __iomem *ioremap(unsigned long addr, unsigned long size) +{ + return (void __iomem *)addr; +} + +extern void __iomem *__ioremap(unsigned long addr, unsigned long size, + unsigned long flags) +{ + return (void __iomem *)addr; +} + +void iounmap(volatile void __iomem *addr) +{ + return; +} + +#else + +/* + * map_io_page currently only called by __ioremap + * map_io_page adds an entry to the ioremap page table + * and adds an entry to the HPT, possibly bolting it + */ +static int map_io_page(unsigned long ea, unsigned long pa, int flags) +{ + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + unsigned long vsid; + + if (mem_init_done) { - spin_lock(&init_mm.page_table_lock); + 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(&init_mm, pmdp, ea); ++ ptep = pte_alloc_kernel(pmdp, ea); + if (!ptep) + return -ENOMEM; + set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, + __pgprot(flags))); - spin_unlock(&init_mm.page_table_lock); + } else { + unsigned long va, vpn, hash, hpteg; + + /* + * 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. + */ + vsid = get_kernel_vsid(ea); + va = (vsid << 28) | (ea & 0xFFFFFFF); + vpn = va >> PAGE_SHIFT; + + hash = hpt_hash(vpn, 0); + + hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); + + /* Panic if a pte grpup is full */ + if (ppc_md.hpte_insert(hpteg, va, pa >> PAGE_SHIFT, + HPTE_V_BOLTED, + _PAGE_NO_CACHE|_PAGE_GUARDED|PP_RWXX) + == -1) { + panic("map_io_page: could not insert mapping"); + } + } + return 0; +} + + +static void __iomem * __ioremap_com(unsigned long addr, unsigned long pa, + unsigned long ea, unsigned long size, + unsigned long flags) +{ + unsigned long i; + + if ((flags & _PAGE_PRESENT) == 0) + flags |= pgprot_val(PAGE_KERNEL); + + for (i = 0; i < size; i += PAGE_SIZE) + if (map_io_page(ea+i, pa+i, flags)) + return NULL; + + return (void __iomem *) (ea + (addr & ~PAGE_MASK)); +} + + +void __iomem * +ioremap(unsigned long addr, unsigned long size) +{ + return __ioremap(addr, size, _PAGE_NO_CACHE | _PAGE_GUARDED); +} + +void __iomem * __ioremap(unsigned long addr, unsigned long size, + unsigned long flags) +{ + unsigned long pa, ea; + 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 + * + */ + pa = addr & PAGE_MASK; + size = PAGE_ALIGN(addr + size) - pa; + + if (size == 0) + return NULL; + + if (mem_init_done) { + struct vm_struct *area; + area = im_get_free_area(size); + if (area == NULL) + return NULL; + ea = (unsigned long)(area->addr); + ret = __ioremap_com(addr, pa, ea, size, flags); + if (!ret) + im_free(area->addr); + } else { + ea = ioremap_bot; + ret = __ioremap_com(addr, pa, ea, size, flags); + if (ret) + ioremap_bot += size; + } + return ret; +} + +#define IS_PAGE_ALIGNED(_val) ((_val) == ((_val) & PAGE_MASK)) + +int __ioremap_explicit(unsigned long pa, unsigned long ea, + unsigned long size, unsigned long flags) +{ + struct vm_struct *area; + void __iomem *ret; + + /* For now, require page-aligned values for pa, ea, and size */ + if (!IS_PAGE_ALIGNED(pa) || !IS_PAGE_ALIGNED(ea) || + !IS_PAGE_ALIGNED(size)) { + printk(KERN_ERR "unaligned value in %s\n", __FUNCTION__); + return 1; + } + + if (!mem_init_done) { + /* Two things to consider in this case: + * 1) No records will be kept (imalloc, etc) that the region + * has been remapped + * 2) It won't be easy to iounmap() the region later (because + * of 1) + */ + ; + } else { + area = im_get_area(ea, size, + IM_REGION_UNUSED|IM_REGION_SUBSET|IM_REGION_EXISTS); + if (area == NULL) { + /* Expected when PHB-dlpar is in play */ + return 1; + } + if (ea != (unsigned long) area->addr) { + printk(KERN_ERR "unexpected addr return from " + "im_get_area\n"); + return 1; + } + } + + ret = __ioremap_com(pa, pa, ea, size, flags); + if (ret == NULL) { + printk(KERN_ERR "ioremap_explicit() allocation failure !\n"); + return 1; + } + if (ret != (void *) ea) { + printk(KERN_ERR "__ioremap_com() returned unexpected addr\n"); + return 1; + } + + return 0; +} + +/* + * Unmap an IO region and remove it from imalloc'd list. + * Access to IO memory should be serialized by driver. + * This code is modeled after vmalloc code - unmap_vm_area() + * + * XXX what about calls before mem_init_done (ie python_countermeasures()) + */ +void iounmap(volatile void __iomem *token) +{ + void *addr; + + if (!mem_init_done) + return; + + addr = (void *) ((unsigned long __force) token & PAGE_MASK); + + im_free(addr); +} + +static int iounmap_subset_regions(unsigned long addr, unsigned long size) +{ + struct vm_struct *area; + + /* Check whether subsets of this region exist */ + area = im_get_area(addr, size, IM_REGION_SUPERSET); + if (area == NULL) + return 1; + + while (area) { + iounmap((void __iomem *) area->addr); + area = im_get_area(addr, size, + IM_REGION_SUPERSET); + } + + return 0; +} + +int iounmap_explicit(volatile void __iomem *start, unsigned long size) +{ + struct vm_struct *area; + unsigned long addr; + int rc; + + addr = (unsigned long __force) start & PAGE_MASK; + + /* Verify that the region either exists or is a subset of an existing + * region. In the latter case, split the parent region to create + * the exact region + */ + area = im_get_area(addr, size, + IM_REGION_EXISTS | IM_REGION_SUBSET); + if (area == NULL) { + /* Determine whether subset regions exist. If so, unmap */ + rc = iounmap_subset_regions(addr, size); + if (rc) { + printk(KERN_ERR + "%s() cannot unmap nonexistent range 0x%lx\n", + __FUNCTION__, addr); + return 1; + } + } else { + iounmap((void __iomem *) area->addr); + } + /* + * FIXME! This can't be right: + iounmap(area->addr); + * Maybe it should be "iounmap(area);" + */ + return 0; +} + +#endif + +EXPORT_SYMBOL(ioremap); +EXPORT_SYMBOL(__ioremap); +EXPORT_SYMBOL(iounmap); + +void __iomem * reserve_phb_iospace(unsigned long size) +{ + void __iomem *virt_addr; + + if (phbs_io_bot >= IMALLOC_BASE) + panic("reserve_phb_iospace(): phb io space overflow\n"); + + virt_addr = (void __iomem *) phbs_io_bot; + phbs_io_bot += size; + + return virt_addr; +} diff --cc include/asm-powerpc/rwsem.h index 0a5b83a3c9,7a647fae37..79bae4933b --- a/include/asm-powerpc/rwsem.h +++ b/include/asm-powerpc/rwsem.h @@@ -159,5 -163,10 +159,10 @@@ static inline int rwsem_atomic_update(i return atomic_add_return(delta, (atomic_t *)(&sem->count)); } + static inline int rwsem_is_locked(struct rw_semaphore *sem) + { + return (sem->count != 0); + } + -#endif /* __KERNEL__ */ -#endif /* _PPC_RWSEM_XADD_H */ +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_RWSEM_H */ diff --cc include/asm-powerpc/unistd.h index c2d039e338,404c143e64..0991dfceef --- a/include/asm-powerpc/unistd.h +++ b/include/asm-powerpc/unistd.h @@@ -477,19 -461,21 +477,18 @@@ int sys_execve(unsigned long a0, unsign unsigned long a3, unsigned long a4, unsigned long a5, struct pt_regs *regs); int sys_clone(unsigned long clone_flags, unsigned long usp, - int __user *parent_tidp, void __user *child_threadptr, - int __user *child_tidp, int p6, - struct pt_regs *regs); -int sys_fork(int p1, int p2, int p3, int p4, int p5, int p6, + int __user *parent_tidp, void __user *child_threadptr, + int __user *child_tidp, int p6, struct pt_regs *regs); +int sys_fork(unsigned long p1, unsigned long p2, unsigned long p3, + unsigned long p4, unsigned long p5, unsigned long p6, struct pt_regs *regs); -int sys_vfork(int p1, int p2, int p3, int p4, int p5, int p6, +int sys_vfork(unsigned long p1, unsigned long p2, unsigned long p3, + unsigned long p4, unsigned long p5, unsigned long p6, struct pt_regs *regs); int sys_pipe(int __user *fildes); - int sys_ptrace(long request, long pid, long addr, long data); struct sigaction; -long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ +long sys_rt_sigaction(int sig, const struct sigaction __user *act, + struct sigaction __user *oact, size_t sigsetsize); /* * "Conditional" syscalls