X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=arch%2Fx86_64%2Fmm%2Finit-xen.c;h=7e9b0d40103f869f268688fa8263a82e045de54d;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=07a11ff737b90e1a45064a7c6cadab6267884ccc;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/arch/x86_64/mm/init-xen.c b/arch/x86_64/mm/init-xen.c index 07a11ff73..7e9b0d401 100644 --- a/arch/x86_64/mm/init-xen.c +++ b/arch/x86_64/mm/init-xen.c @@ -398,7 +398,6 @@ static __meminit void *alloc_static_page(unsigned long *phys) if (after_bootmem) { void *adr = (void *)get_zeroed_page(GFP_ATOMIC); - *phys = __pa(adr); return adr; } @@ -450,7 +449,6 @@ __init void *early_ioremap(unsigned long addr, unsigned long size) /* actually usually some more */ if (size >= LARGE_PAGE_SIZE) { - printk("SMBIOS area too long %lu\n", size); return NULL; } set_pmd(temp_mappings[0].pmd, __pmd(map | _KERNPG_TABLE | _PAGE_PSE)); @@ -472,13 +470,15 @@ __init void early_iounmap(void *addr, unsigned long size) #endif /* !CONFIG_XEN */ static void __meminit -phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end) +phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end) { - int i, k; + int i = pmd_index(address); + int k; - for (i = 0; i < PTRS_PER_PMD; pmd++, i++) { + for (; i < PTRS_PER_PMD; i++) { unsigned long pte_phys; pte_t *pte, *pte_save; + pmd_t *pmd = pmd_page + pmd_index(address); if (address >= end) { if (!after_bootmem) @@ -486,6 +486,10 @@ phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end) set_pmd(pmd, __pmd(0)); break; } + + if (pmd_val(*pmd)) + continue; + pte = alloc_static_page(&pte_phys); pte_save = pte; for (k = 0; k < PTRS_PER_PTE; pte++, k++, address += PTE_SIZE) { @@ -511,40 +515,36 @@ phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end) static void __meminit phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end) { - pmd_t *pmd = pmd_offset(pud, (unsigned long)__va(address)); - - if (pmd_none(*pmd)) { - spin_lock(&init_mm.page_table_lock); - phys_pmd_init(pmd, address, end); - spin_unlock(&init_mm.page_table_lock); - __flush_tlb_all(); - } + pmd_t *pmd = pmd_offset(pud,0); + spin_lock(&init_mm.page_table_lock); + phys_pmd_init(pmd, address, end); + spin_unlock(&init_mm.page_table_lock); + __flush_tlb_all(); } -static void __meminit phys_pud_init(pud_t *pud, unsigned long address, unsigned long end) +static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) { - long i = pud_index(address); + int i = pud_index(addr); - pud = pud + i; - if (after_bootmem && pud_val(*pud)) { - phys_pmd_update(pud, address, end); - return; - } - - for (; i < PTRS_PER_PUD; pud++, i++) { - unsigned long paddr, pmd_phys; + for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE ) { + unsigned long pmd_phys; + pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; - paddr = (address & PGDIR_MASK) + i*PUD_SIZE; - if (paddr >= end) + if (addr >= end) break; + if (pud_val(*pud)) { + phys_pmd_update(pud, addr, end); + continue; + } + pmd = alloc_static_page(&pmd_phys); early_make_page_readonly(pmd, XENFEAT_writable_page_tables); spin_lock(&init_mm.page_table_lock); set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE)); - phys_pmd_init(pmd, paddr, end); + phys_pmd_init(pmd, addr, end); spin_unlock(&init_mm.page_table_lock); } __flush_tlb(); @@ -748,78 +748,19 @@ void __cpuinit zap_low_mappings(int cpu) #endif } -/* Compute zone sizes for the DMA and DMA32 zones in a node. */ -__init void -size_zones(unsigned long *z, unsigned long *h, - unsigned long start_pfn, unsigned long end_pfn) -{ - int i; -#ifndef CONFIG_XEN - unsigned long w; -#endif - - for (i = 0; i < MAX_NR_ZONES; i++) - z[i] = 0; - -#ifndef CONFIG_XEN - if (start_pfn < MAX_DMA_PFN) - z[ZONE_DMA] = MAX_DMA_PFN - start_pfn; - if (start_pfn < MAX_DMA32_PFN) { - unsigned long dma32_pfn = MAX_DMA32_PFN; - if (dma32_pfn > end_pfn) - dma32_pfn = end_pfn; - z[ZONE_DMA32] = dma32_pfn - start_pfn; - } - z[ZONE_NORMAL] = end_pfn - start_pfn; - - /* Remove lower zones from higher ones. */ - w = 0; - for (i = 0; i < MAX_NR_ZONES; i++) { - if (z[i]) - z[i] -= w; - w += z[i]; - } - - /* Compute holes */ - w = start_pfn; - for (i = 0; i < MAX_NR_ZONES; i++) { - unsigned long s = w; - w += z[i]; - h[i] = e820_hole_size(s, w); - } - - /* Add the space pace needed for mem_map to the holes too. */ - for (i = 0; i < MAX_NR_ZONES; i++) - h[i] += (z[i] * sizeof(struct page)) / PAGE_SIZE; - - /* The 16MB DMA zone has the kernel and other misc mappings. - Account them too */ - if (h[ZONE_DMA]) { - h[ZONE_DMA] += dma_reserve; - if (h[ZONE_DMA] >= z[ZONE_DMA]) { - printk(KERN_WARNING - "Kernel too large and filling up ZONE_DMA?\n"); - h[ZONE_DMA] = z[ZONE_DMA]; - } - } -#else - z[ZONE_DMA] = end_pfn; - for (i = 0; i < MAX_NR_ZONES; i++) - h[i] = 0; -#endif -} - #ifndef CONFIG_NUMA void __init paging_init(void) { - unsigned long zones[MAX_NR_ZONES], holes[MAX_NR_ZONES]; int i; + unsigned long max_zone_pfns[MAX_NR_ZONES]; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + max_zone_pfns[ZONE_DMA] = end_pfn; + max_zone_pfns[ZONE_DMA32] = end_pfn; + max_zone_pfns[ZONE_NORMAL] = end_pfn; memory_present(0, 0, end_pfn); sparse_init(); - size_zones(zones, holes, 0, end_pfn); - free_area_init_node(0, NODE_DATA(0), zones, - __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes); + free_area_init_nodes(max_zone_pfns); /* Switch to the real shared_info page, and clear the * dummy page. */ @@ -877,7 +818,6 @@ void __init clear_kernel_mapping(unsigned long address, unsigned long size) /* * Memory hotplug specific functions */ - void online_page(struct page *page) { ClearPageReserved(page); @@ -888,19 +828,6 @@ void online_page(struct page *page) } #ifdef CONFIG_MEMORY_HOTPLUG -/* - * XXX: memory_add_physaddr_to_nid() is to find node id from physical address - * via probe interface of sysfs. If acpi notifies hot-add event, then it - * can tell node id by searching dsdt. But, probe interface doesn't have - * node id. So, return 0 as node id at this time. - */ -#ifdef CONFIG_NUMA -int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -#endif - /* * Memory is added always to NORMAL zone. This means you will never get * additional DMA/DMA32 memory. @@ -908,17 +835,17 @@ int memory_add_physaddr_to_nid(u64 start) int arch_add_memory(int nid, u64 start, u64 size) { struct pglist_data *pgdat = NODE_DATA(nid); - struct zone *zone = pgdat->node_zones + MAX_NR_ZONES-2; + struct zone *zone = pgdat->node_zones + ZONE_NORMAL; unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int ret; + init_memory_mapping(start, (start + size -1)); + ret = __add_pages(zone, start_pfn, nr_pages); if (ret) goto error; - init_memory_mapping(start, (start + size -1)); - return ret; error: printk("%s: Problem encountered in __add_pages!\n", __func__); @@ -932,7 +859,17 @@ int remove_memory(u64 start, u64 size) } EXPORT_SYMBOL_GPL(remove_memory); -#else /* CONFIG_MEMORY_HOTPLUG */ +#if !defined(CONFIG_ACPI_NUMA) && defined(CONFIG_NUMA) +int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); +#endif + +#endif /* CONFIG_MEMORY_HOTPLUG */ + +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE /* * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance, * just online the pages. @@ -958,7 +895,7 @@ int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages) } return err; } -#endif /* CONFIG_MEMORY_HOTPLUG */ +#endif static inline int page_is_ram (unsigned long pagenr) { @@ -1001,12 +938,6 @@ void __init mem_init(void) pci_iommu_alloc(); - /* How many end-of-memory variables you have, grandma! */ - max_low_pfn = end_pfn; - max_pfn = end_pfn; - num_physpages = end_pfn; - high_memory = (void *) __va(end_pfn * PAGE_SIZE); - /* clear the zero-page */ memset(empty_zero_page, 0, PAGE_SIZE); @@ -1024,7 +955,9 @@ void __init mem_init(void) init_page_count(&mem_map[pfn]); totalram_pages++; } - reservedpages = end_pfn - totalram_pages - e820_hole_size(0, end_pfn); + reservedpages = end_pfn - totalram_pages - + absent_pages_in_range(0, end_pfn); + after_bootmem = 1; @@ -1063,7 +996,6 @@ void __init mem_init(void) void free_init_pages(char *what, unsigned long begin, unsigned long end) { -#ifdef __DO_LATER__ unsigned long addr; if (begin >= end) @@ -1078,14 +1010,13 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end) free_page(addr); totalram_pages++; } -#endif } void free_initmem(void) { -#ifdef __DO_LATER__ memset(__initdata_begin, POISON_FREE_INITDATA, __initdata_end - __initdata_begin); +#ifdef __DO_LATER__ free_init_pages("unused kernel memory", (unsigned long)(&__init_begin), (unsigned long)(&__init_end)); @@ -1103,6 +1034,7 @@ void mark_rodata_ro(void) printk ("Write protecting the kernel read-only data: %luk\n", (__end_rodata - __start_rodata) >> 10); + /* * change_page_attr_addr() requires a global_flush_tlb() call after it. * We do this after the printk so that if something went wrong in the @@ -1122,15 +1054,30 @@ void free_initrd_mem(unsigned long start, unsigned long end) void __init reserve_bootmem_generic(unsigned long phys, unsigned len) { - /* Should check here against the e820 map to avoid double free */ #ifdef CONFIG_NUMA int nid = phys_to_nid(phys); +#endif + unsigned long pfn = phys >> PAGE_SHIFT; + if (pfn >= end_pfn) { + /* This can happen with kdump kernels when accessing firmware + tables. */ + if (pfn < end_pfn_map) + return; + printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %u\n", + phys, len); + return; + } + + /* Should check here against the e820 map to avoid double free */ +#ifdef CONFIG_NUMA reserve_bootmem_node(NODE_DATA(nid), phys, len); #else reserve_bootmem(phys, len); #endif - if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) + if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) { dma_reserve += len / PAGE_SIZE; + set_dma_reserve(dma_reserve); + } } int kern_addr_valid(unsigned long addr) @@ -1189,14 +1136,15 @@ static __init int x8664_sysctl_init(void) __initcall(x8664_sysctl_init); #endif -/* A pseudo VMAs to allow ptrace access for the vsyscall page. This only +/* A pseudo VMA to allow ptrace access for the vsyscall page. This only covers the 64bit vsyscall page now. 32bit has a real VMA now and does not need special handling anymore. */ static struct vm_area_struct gate_vma = { .vm_start = VSYSCALL_START, - .vm_end = VSYSCALL_END, - .vm_page_prot = PAGE_READONLY + .vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES << PAGE_SHIFT), + .vm_page_prot = PAGE_READONLY_EXEC, + .vm_flags = VM_READ | VM_EXEC }; struct vm_area_struct *get_gate_vma(struct task_struct *tsk)