Linux-2.6.12-rc2v2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

12 files changed, 3171 insertions, 0 deletions

diff --git a/arch/i386/mm/Makefile b/arch/i386/mm/Makefile
new file mode 100644
index 00000000000..fc327250684
--- /dev/null
+++ b/arch/i386/mm/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the linux i386-specific parts of the memory manager.
+#
+
+obj-y	:= init.o pgtable.o fault.o ioremap.o extable.o pageattr.o mmap.o
+
+obj-$(CONFIG_DISCONTIGMEM)	+= discontig.o
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_HIGHMEM) += highmem.o
+obj-$(CONFIG_BOOT_IOREMAP) += boot_ioremap.o
diff --git a/arch/i386/mm/boot_ioremap.c b/arch/i386/mm/boot_ioremap.c
new file mode 100644
index 00000000000..523b30634e0
--- /dev/null
+++ b/arch/i386/mm/boot_ioremap.c
@@ -0,0 +1,97 @@
+/*
+ * arch/i386/mm/boot_ioremap.c
+ * 
+ * Re-map functions for early boot-time before paging_init() when the 
+ * boot-time pagetables are still in use
+ *
+ * Written by Dave Hansen <haveblue@us.ibm.com>
+ */
+
+
+/*
+ * We need to use the 2-level pagetable functions, but CONFIG_X86_PAE
+ * keeps that from happenning.  If anyone has a better way, I'm listening.
+ *
+ * boot_pte_t is defined only if this all works correctly
+ */
+
+#include <linux/config.h>
+#undef CONFIG_X86_PAE
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <linux/init.h>
+#include <linux/stddef.h>
+
+/* 
+ * I'm cheating here.  It is known that the two boot PTE pages are 
+ * allocated next to each other.  I'm pretending that they're just
+ * one big array. 
+ */
+
+#define BOOT_PTE_PTRS (PTRS_PER_PTE*2)
+#define boot_pte_index(address) \
+	     (((address) >> PAGE_SHIFT) & (BOOT_PTE_PTRS - 1))
+
+static inline boot_pte_t* boot_vaddr_to_pte(void *address)
+{
+	boot_pte_t* boot_pg = (boot_pte_t*)pg0;
+	return &boot_pg[boot_pte_index((unsigned long)address)];
+}
+
+/*
+ * This is only for a caller who is clever enough to page-align
+ * phys_addr and virtual_source, and who also has a preference
+ * about which virtual address from which to steal ptes
+ */
+static void __boot_ioremap(unsigned long phys_addr, unsigned long nrpages, 
+		    void* virtual_source)
+{
+	boot_pte_t* pte;
+	int i;
+	char *vaddr = virtual_source;
+
+	pte = boot_vaddr_to_pte(virtual_source);
+	for (i=0; i < nrpages; i++, phys_addr += PAGE_SIZE, pte++) {
+		set_pte(pte, pfn_pte(phys_addr>>PAGE_SHIFT, PAGE_KERNEL));
+		__flush_tlb_one(&vaddr[i*PAGE_SIZE]);
+	}
+}
+
+/* the virtual space we're going to remap comes from this array */
+#define BOOT_IOREMAP_PAGES 4
+#define BOOT_IOREMAP_SIZE (BOOT_IOREMAP_PAGES*PAGE_SIZE)
+static __initdata char boot_ioremap_space[BOOT_IOREMAP_SIZE]
+		       __attribute__ ((aligned (PAGE_SIZE)));
+
+/*
+ * This only applies to things which need to ioremap before paging_init()
+ * bt_ioremap() and plain ioremap() are both useless at this point.
+ * 
+ * When used, we're still using the boot-time pagetables, which only
+ * have 2 PTE pages mapping the first 8MB
+ *
+ * There is no unmap.  The boot-time PTE pages aren't used after boot.
+ * If you really want the space back, just remap it yourself.
+ * boot_ioremap(&ioremap_space-PAGE_OFFSET, BOOT_IOREMAP_SIZE)
+ */
+__init void* boot_ioremap(unsigned long phys_addr, unsigned long size)
+{
+	unsigned long last_addr, offset;
+	unsigned int nrpages;
+	
+	last_addr = phys_addr + size - 1;
+
+	/* page align the requested address */
+	offset = phys_addr & ~PAGE_MASK;
+	phys_addr &= PAGE_MASK;
+	size = PAGE_ALIGN(last_addr) - phys_addr;
+	
+	nrpages = size >> PAGE_SHIFT;
+	if (nrpages > BOOT_IOREMAP_PAGES)
+		return NULL;
+	
+	__boot_ioremap(phys_addr, nrpages, boot_ioremap_space);
+
+	return &boot_ioremap_space[offset];
+}
diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c
new file mode 100644
index 00000000000..1726b4096b1
--- /dev/null
+++ b/arch/i386/mm/discontig.c
@@ -0,0 +1,383 @@
+/*
+ * Written by: Patricia Gaughen <gone@us.ibm.com>, IBM Corporation
+ * August 2002: added remote node KVA remap - Martin J. Bligh 
+ *
+ * Copyright (C) 2002, IBM Corp.
+ *
+ * All rights reserved.          
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/bootmem.h>
+#include <linux/mmzone.h>
+#include <linux/highmem.h>
+#include <linux/initrd.h>
+#include <linux/nodemask.h>
+#include <asm/e820.h>
+#include <asm/setup.h>
+#include <asm/mmzone.h>
+#include <bios_ebda.h>
+
+struct pglist_data *node_data[MAX_NUMNODES];
+bootmem_data_t node0_bdata;
+
+/*
+ * numa interface - we expect the numa architecture specfic code to have
+ *                  populated the following initialisation.
+ *
+ * 1) node_online_map  - the map of all nodes configured (online) in the system
+ * 2) physnode_map     - the mapping between a pfn and owning node
+ * 3) node_start_pfn   - the starting page frame number for a node
+ * 3) node_end_pfn     - the ending page fram number for a node
+ */
+
+/*
+ * physnode_map keeps track of the physical memory layout of a generic
+ * numa node on a 256Mb break (each element of the array will
+ * represent 256Mb of memory and will be marked by the node id.  so,
+ * if the first gig is on node 0, and the second gig is on node 1
+ * physnode_map will contain:
+ *
+ *     physnode_map[0-3] = 0;
+ *     physnode_map[4-7] = 1;
+ *     physnode_map[8- ] = -1;
+ */
+s8 physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
+
+void memory_present(int nid, unsigned long start, unsigned long end)
+{
+	unsigned long pfn;
+
+	printk(KERN_INFO "Node: %d, start_pfn: %ld, end_pfn: %ld\n",
+			nid, start, end);
+	printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
+	printk(KERN_DEBUG "  ");
+	for (pfn = start; pfn < end; pfn += PAGES_PER_ELEMENT) {
+		physnode_map[pfn / PAGES_PER_ELEMENT] = nid;
+		printk("%ld ", pfn);
+	}
+	printk("\n");
+}
+
+unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
+					      unsigned long end_pfn)
+{
+	unsigned long nr_pages = end_pfn - start_pfn;
+
+	if (!nr_pages)
+		return 0;
+
+	return (nr_pages + 1) * sizeof(struct page);
+}
+
+unsigned long node_start_pfn[MAX_NUMNODES];
+unsigned long node_end_pfn[MAX_NUMNODES];
+
+extern unsigned long find_max_low_pfn(void);
+extern void find_max_pfn(void);
+extern void one_highpage_init(struct page *, int, int);
+
+extern struct e820map e820;
+extern unsigned long init_pg_tables_end;
+extern unsigned long highend_pfn, highstart_pfn;
+extern unsigned long max_low_pfn;
+extern unsigned long totalram_pages;
+extern unsigned long totalhigh_pages;
+
+#define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
+
+unsigned long node_remap_start_pfn[MAX_NUMNODES];
+unsigned long node_remap_size[MAX_NUMNODES];
+unsigned long node_remap_offset[MAX_NUMNODES];
+void *node_remap_start_vaddr[MAX_NUMNODES];
+void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
+
+/*
+ * FLAT - support for basic PC memory model with discontig enabled, essentially
+ *        a single node with all available processors in it with a flat
+ *        memory map.
+ */
+int __init get_memcfg_numa_flat(void)
+{
+	printk("NUMA - single node, flat memory mode\n");
+
+	/* Run the memory configuration and find the top of memory. */
+	find_max_pfn();
+	node_start_pfn[0] = 0;
+	node_end_pfn[0] = max_pfn;
+	memory_present(0, 0, max_pfn);
+
+        /* Indicate there is one node available. */
+	nodes_clear(node_online_map);
+	node_set_online(0);
+	return 1;
+}
+
+/*
+ * Find the highest page frame number we have available for the node
+ */
+static void __init find_max_pfn_node(int nid)
+{
+	if (node_end_pfn[nid] > max_pfn)
+		node_end_pfn[nid] = max_pfn;
+	/*
+	 * if a user has given mem=XXXX, then we need to make sure 
+	 * that the node _starts_ before that, too, not just ends
+	 */
+	if (node_start_pfn[nid] > max_pfn)
+		node_start_pfn[nid] = max_pfn;
+	if (node_start_pfn[nid] > node_end_pfn[nid])
+		BUG();
+}
+
+/* 
+ * Allocate memory for the pg_data_t for this node via a crude pre-bootmem
+ * method.  For node zero take this from the bottom of memory, for
+ * subsequent nodes place them at node_remap_start_vaddr which contains
+ * node local data in physically node local memory.  See setup_memory()
+ * for details.
+ */
+static void __init allocate_pgdat(int nid)
+{
+	if (nid && node_has_online_mem(nid))
+		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
+	else {
+		NODE_DATA(nid) = (pg_data_t *)(__va(min_low_pfn << PAGE_SHIFT));
+		min_low_pfn += PFN_UP(sizeof(pg_data_t));
+	}
+}
+
+void __init remap_numa_kva(void)
+{
+	void *vaddr;
+	unsigned long pfn;
+	int node;
+
+	for_each_online_node(node) {
+		if (node == 0)
+			continue;
+		for (pfn=0; pfn < node_remap_size[node]; pfn += PTRS_PER_PTE) {
+			vaddr = node_remap_start_vaddr[node]+(pfn<<PAGE_SHIFT);
+			set_pmd_pfn((ulong) vaddr, 
+				node_remap_start_pfn[node] + pfn, 
+				PAGE_KERNEL_LARGE);
+		}
+	}
+}
+
+static unsigned long calculate_numa_remap_pages(void)
+{
+	int nid;
+	unsigned long size, reserve_pages = 0;
+
+	for_each_online_node(nid) {
+		if (nid == 0)
+			continue;
+		if (!node_remap_size[nid])
+			continue;
+
+		/*
+		 * The acpi/srat node info can show hot-add memroy zones
+		 * where memory could be added but not currently present.
+		 */
+		if (node_start_pfn[nid] > max_pfn)
+			continue;
+		if (node_end_pfn[nid] > max_pfn)
+			node_end_pfn[nid] = max_pfn;
+
+		/* ensure the remap includes space for the pgdat. */
+		size = node_remap_size[nid] + sizeof(pg_data_t);
+
+		/* convert size to large (pmd size) pages, rounding up */
+		size = (size + LARGE_PAGE_BYTES - 1) / LARGE_PAGE_BYTES;
+		/* now the roundup is correct, convert to PAGE_SIZE pages */
+		size = size * PTRS_PER_PTE;
+		printk("Reserving %ld pages of KVA for lmem_map of node %d\n",
+				size, nid);
+		node_remap_size[nid] = size;
+		reserve_pages += size;
+		node_remap_offset[nid] = reserve_pages;
+		printk("Shrinking node %d from %ld pages to %ld pages\n",
+			nid, node_end_pfn[nid], node_end_pfn[nid] - size);
+		node_end_pfn[nid] -= size;
+		node_remap_start_pfn[nid] = node_end_pfn[nid];
+	}
+	printk("Reserving total of %ld pages for numa KVA remap\n",
+			reserve_pages);
+	return reserve_pages;
+}
+
+extern void setup_bootmem_allocator(void);
+unsigned long __init setup_memory(void)
+{
+	int nid;
+	unsigned long system_start_pfn, system_max_low_pfn;
+	unsigned long reserve_pages;
+
+	/*
+	 * When mapping a NUMA machine we allocate the node_mem_map arrays
+	 * from node local memory.  They are then mapped directly into KVA
+	 * between zone normal and vmalloc space.  Calculate the size of
+	 * this space and use it to adjust the boundry between ZONE_NORMAL
+	 * and ZONE_HIGHMEM.
+	 */
+	find_max_pfn();
+	get_memcfg_numa();
+
+	reserve_pages = calculate_numa_remap_pages();
+
+	/* partially used pages are not usable - thus round upwards */
+	system_start_pfn = min_low_pfn = PFN_UP(init_pg_tables_end);
+
+	system_max_low_pfn = max_low_pfn = find_max_low_pfn() - reserve_pages;
+	printk("reserve_pages = %ld find_max_low_pfn() ~ %ld\n",
+			reserve_pages, max_low_pfn + reserve_pages);
+	printk("max_pfn = %ld\n", max_pfn);
+#ifdef CONFIG_HIGHMEM
+	highstart_pfn = highend_pfn = max_pfn;
+	if (max_pfn > system_max_low_pfn)
+		highstart_pfn = system_max_low_pfn;
+	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
+	       pages_to_mb(highend_pfn - highstart_pfn));
+#endif
+	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
+			pages_to_mb(system_max_low_pfn));
+	printk("min_low_pfn = %ld, max_low_pfn = %ld, highstart_pfn = %ld\n", 
+			min_low_pfn, max_low_pfn, highstart_pfn);
+
+	printk("Low memory ends at vaddr %08lx\n",
+			(ulong) pfn_to_kaddr(max_low_pfn));
+	for_each_online_node(nid) {
+		node_remap_start_vaddr[nid] = pfn_to_kaddr(
+			(highstart_pfn + reserve_pages) - node_remap_offset[nid]);
+		allocate_pgdat(nid);
+		printk ("node %d will remap to vaddr %08lx - %08lx\n", nid,
+			(ulong) node_remap_start_vaddr[nid],
+			(ulong) pfn_to_kaddr(highstart_pfn + reserve_pages
+			    - node_remap_offset[nid] + node_remap_size[nid]));
+	}
+	printk("High memory starts at vaddr %08lx\n",
+			(ulong) pfn_to_kaddr(highstart_pfn));
+	vmalloc_earlyreserve = reserve_pages * PAGE_SIZE;
+	for_each_online_node(nid)
+		find_max_pfn_node(nid);
+
+	memset(NODE_DATA(0), 0, sizeof(struct pglist_data));
+	NODE_DATA(0)->bdata = &node0_bdata;
+	setup_bootmem_allocator();
+	return max_low_pfn;
+}
+
+void __init zone_sizes_init(void)
+{
+	int nid;
+
+	/*
+	 * Insert nodes into pgdat_list backward so they appear in order.
+	 * Clobber node 0's links and NULL out pgdat_list before starting.
+	 */
+	pgdat_list = NULL;
+	for (nid = MAX_NUMNODES - 1; nid >= 0; nid--) {
+		if (!node_online(nid))
+			continue;
+		NODE_DATA(nid)->pgdat_next = pgdat_list;
+		pgdat_list = NODE_DATA(nid);
+	}
+
+	for_each_online_node(nid) {
+		unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
+		unsigned long *zholes_size;
+		unsigned int max_dma;
+
+		unsigned long low = max_low_pfn;
+		unsigned long start = node_start_pfn[nid];
+		unsigned long high = node_end_pfn[nid];
+
+		max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+
+		if (node_has_online_mem(nid)){
+			if (start > low) {
+#ifdef CONFIG_HIGHMEM
+				BUG_ON(start > high);
+				zones_size[ZONE_HIGHMEM] = high - start;
+#endif
+			} else {
+				if (low < max_dma)
+					zones_size[ZONE_DMA] = low;
+				else {
+					BUG_ON(max_dma > low);
+					BUG_ON(low > high);
+					zones_size[ZONE_DMA] = max_dma;
+					zones_size[ZONE_NORMAL] = low - max_dma;
+#ifdef CONFIG_HIGHMEM
+					zones_size[ZONE_HIGHMEM] = high - low;
+#endif
+				}
+			}
+		}
+
+		zholes_size = get_zholes_size(nid);
+		/*
+		 * We let the lmem_map for node 0 be allocated from the
+		 * normal bootmem allocator, but other nodes come from the
+		 * remapped KVA area - mbligh
+		 */
+		if (!nid)
+			free_area_init_node(nid, NODE_DATA(nid),
+					zones_size, start, zholes_size);
+		else {
+			unsigned long lmem_map;
+			lmem_map = (unsigned long)node_remap_start_vaddr[nid];
+			lmem_map += sizeof(pg_data_t) + PAGE_SIZE - 1;
+			lmem_map &= PAGE_MASK;
+			NODE_DATA(nid)->node_mem_map = (struct page *)lmem_map;
+			free_area_init_node(nid, NODE_DATA(nid), zones_size,
+				start, zholes_size);
+		}
+	}
+	return;
+}
+
+void __init set_highmem_pages_init(int bad_ppro) 
+{
+#ifdef CONFIG_HIGHMEM
+	struct zone *zone;
+
+	for_each_zone(zone) {
+		unsigned long node_pfn, node_high_size, zone_start_pfn;
+		struct page * zone_mem_map;
+		
+		if (!is_highmem(zone))
+			continue;
+
+		printk("Initializing %s for node %d\n", zone->name,
+			zone->zone_pgdat->node_id);
+
+		node_high_size = zone->spanned_pages;
+		zone_mem_map = zone->zone_mem_map;
+		zone_start_pfn = zone->zone_start_pfn;
+
+		for (node_pfn = 0; node_pfn < node_high_size; node_pfn++) {
+			one_highpage_init((struct page *)(zone_mem_map + node_pfn),
+					  zone_start_pfn + node_pfn, bad_ppro);
+		}
+	}
+	totalram_pages += totalhigh_pages;
+#endif
+}
diff --git a/arch/i386/mm/extable.c b/arch/i386/mm/extable.c
new file mode 100644
index 00000000000..f706449319c
--- /dev/null
+++ b/arch/i386/mm/extable.c
@@ -0,0 +1,36 @@
+/*
+ * linux/arch/i386/mm/extable.c
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <asm/uaccess.h>
+
+int fixup_exception(struct pt_regs *regs)
+{
+	const struct exception_table_entry *fixup;
+
+#ifdef CONFIG_PNPBIOS
+	if (unlikely((regs->xcs & ~15) == (GDT_ENTRY_PNPBIOS_BASE << 3)))
+	{
+		extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp;
+		extern u32 pnp_bios_is_utter_crap;
+		pnp_bios_is_utter_crap = 1;
+		printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n");
+		__asm__ volatile(
+			"movl %0, %%esp\n\t"
+			"jmp *%1\n\t"
+			: : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip));
+		panic("do_trap: can't hit this");
+	}
+#endif
+
+	fixup = search_exception_tables(regs->eip);
+	if (fixup) {
+		regs->eip = fixup->fixup;
+		return 1;
+	}
+
+	return 0;
+}
diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c
new file mode 100644
index 00000000000..a509237c481
--- /dev/null
+++ b/arch/i386/mm/fault.c
@@ -0,0 +1,552 @@
+/*
+ *  linux/arch/i386/mm/fault.c
+ *
+ *  Copyright (C) 1995  Linus Torvalds
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h>		/* For unblank_screen() */
+#include <linux/highmem.h>
+#include <linux/module.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/desc.h>
+#include <asm/kdebug.h>
+
+extern void die(const char *,struct pt_regs *,long);
+
+/*
+ * Unlock any spinlocks which will prevent us from getting the
+ * message out 
+ */
+void bust_spinlocks(int yes)
+{
+	int loglevel_save = console_loglevel;
+
+	if (yes) {
+		oops_in_progress = 1;
+		return;
+	}
+#ifdef CONFIG_VT
+	unblank_screen();
+#endif
+	oops_in_progress = 0;
+	/*
+	 * OK, the message is on the console.  Now we call printk()
+	 * without oops_in_progress set so that printk will give klogd
+	 * a poke.  Hold onto your hats...
+	 */
+	console_loglevel = 15;		/* NMI oopser may have shut the console up */
+	printk(" ");
+	console_loglevel = loglevel_save;
+}
+
+/*
+ * Return EIP plus the CS segment base.  The segment limit is also
+ * adjusted, clamped to the kernel/user address space (whichever is
+ * appropriate), and returned in *eip_limit.
+ *
+ * The segment is checked, because it might have been changed by another
+ * task between the original faulting instruction and here.
+ *
+ * If CS is no longer a valid code segment, or if EIP is beyond the
+ * limit, or if it is a kernel address when CS is not a kernel segment,
+ * then the returned value will be greater than *eip_limit.
+ * 
+ * This is slow, but is very rarely executed.
+ */
+static inline unsigned long get_segment_eip(struct pt_regs *regs,
+					    unsigned long *eip_limit)
+{
+	unsigned long eip = regs->eip;
+	unsigned seg = regs->xcs & 0xffff;
+	u32 seg_ar, seg_limit, base, *desc;
+
+	/* The standard kernel/user address space limit. */
+	*eip_limit = (seg & 3) ? USER_DS.seg : KERNEL_DS.seg;
+
+	/* Unlikely, but must come before segment checks. */
+	if (unlikely((regs->eflags & VM_MASK) != 0))
+		return eip + (seg << 4);
+	
+	/* By far the most common cases. */
+	if (likely(seg == __USER_CS || seg == __KERNEL_CS))
+		return eip;
+
+	/* Check the segment exists, is within the current LDT/GDT size,
+	   that kernel/user (ring 0..3) has the appropriate privilege,
+	   that it's a code segment, and get the limit. */
+	__asm__ ("larl %3,%0; lsll %3,%1"
+		 : "=&r" (seg_ar), "=r" (seg_limit) : "0" (0), "rm" (seg));
+	if ((~seg_ar & 0x9800) || eip > seg_limit) {
+		*eip_limit = 0;
+		return 1;	 /* So that returned eip > *eip_limit. */
+	}
+
+	/* Get the GDT/LDT descriptor base. 
+	   When you look for races in this code remember that
+	   LDT and other horrors are only used in user space. */
+	if (seg & (1<<2)) {
+		/* Must lock the LDT while reading it. */
+		down(&current->mm->context.sem);
+		desc = current->mm->context.ldt;
+		desc = (void *)desc + (seg & ~7);
+	} else {
+		/* Must disable preemption while reading the GDT. */
+		desc = (u32 *)&per_cpu(cpu_gdt_table, get_cpu());
+		desc = (void *)desc + (seg & ~7);
+	}
+
+	/* Decode the code segment base from the descriptor */
+	base = get_desc_base((unsigned long *)desc);
+
+	if (seg & (1<<2)) { 
+		up(&current->mm->context.sem);
+	} else
+		put_cpu();
+
+	/* Adjust EIP and segment limit, and clamp at the kernel limit.
+	   It's legitimate for segments to wrap at 0xffffffff. */
+	seg_limit += base;
+	if (seg_limit < *eip_limit && seg_limit >= base)
+		*eip_limit = seg_limit;
+	return eip + base;
+}
+
+/* 
+ * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
+ * Check that here and ignore it.
+ */
+static int __is_prefetch(struct pt_regs *regs, unsigned long addr)
+{ 
+	unsigned long limit;
+	unsigned long instr = get_segment_eip (regs, &limit);
+	int scan_more = 1;
+	int prefetch = 0; 
+	int i;
+
+	for (i = 0; scan_more && i < 15; i++) { 
+		unsigned char opcode;
+		unsigned char instr_hi;
+		unsigned char instr_lo;
+
+		if (instr > limit)
+			break;
+		if (__get_user(opcode, (unsigned char *) instr))
+			break; 
+
+		instr_hi = opcode & 0xf0; 
+		instr_lo = opcode & 0x0f; 
+		instr++;
+
+		switch (instr_hi) { 
+		case 0x20:
+		case 0x30:
+			/* Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. */
+			scan_more = ((instr_lo & 7) == 0x6);
+			break;
+			
+		case 0x60:
+			/* 0x64 thru 0x67 are valid prefixes in all modes. */
+			scan_more = (instr_lo & 0xC) == 0x4;
+			break;		
+		case 0xF0:
+			/* 0xF0, 0xF2, and 0xF3 are valid prefixes */
+			scan_more = !instr_lo || (instr_lo>>1) == 1;
+			break;			
+		case 0x00:
+			/* Prefetch instruction is 0x0F0D or 0x0F18 */
+			scan_more = 0;
+			if (instr > limit)
+				break;
+			if (__get_user(opcode, (unsigned char *) instr)) 
+				break;
+			prefetch = (instr_lo == 0xF) &&
+				(opcode == 0x0D || opcode == 0x18);
+			break;			
+		default:
+			scan_more = 0;
+			break;
+		} 
+	}
+	return prefetch;
+}
+
+static inline int is_prefetch(struct pt_regs *regs, unsigned long addr,
+			      unsigned long error_code)
+{
+	if (unlikely(boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
+		     boot_cpu_data.x86 >= 6)) {
+		/* Catch an obscure case of prefetch inside an NX page. */
+		if (nx_enabled && (error_code & 16))
+			return 0;
+		return __is_prefetch(regs, addr);
+	}
+	return 0;
+} 
+
+fastcall void do_invalid_op(struct pt_regs *, unsigned long);
+
+/*
+ * This routine handles page faults.  It determines the address,
+ * and the problem, and then passes it off to one of the appropriate
+ * routines.
+ *
+ * error_code:
+ *	bit 0 == 0 means no page found, 1 means protection fault
+ *	bit 1 == 0 means read, 1 means write
+ *	bit 2 == 0 means kernel, 1 means user-mode
+ */
+fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code)
+{
+	struct task_struct *tsk;
+	struct mm_struct *mm;
+	struct vm_area_struct * vma;
+	unsigned long address;
+	unsigned long page;
+	int write;
+	siginfo_t info;
+
+	/* get the address */
+	__asm__("movl %%cr2,%0":"=r" (address));
+
+	if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
+					SIGSEGV) == NOTIFY_STOP)
+		return;
+	/* It's safe to allow irq's after cr2 has been saved */
+	if (regs->eflags & (X86_EFLAGS_IF|VM_MASK))
+		local_irq_enable();
+
+	tsk = current;
+
+	info.si_code = SEGV_MAPERR;
+
+	/*
+	 * We fault-in kernel-space virtual memory on-demand. The
+	 * 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 *
+	 * This verifies that the fault happens in kernel space
+	 * (error_code & 4) == 0, and that the fault was not a
+	 * protection error (error_code & 1) == 0.
+	 */
+	if (unlikely(address >= TASK_SIZE)) { 
+		if (!(error_code & 5))
+			goto vmalloc_fault;
+		/* 
+		 * Don't take the mm semaphore here. If we fixup a prefetch
+		 * fault we could otherwise deadlock.
+		 */
+		goto bad_area_nosemaphore;
+	} 
+
+	mm = tsk->mm;
+
+	/*
+	 * If we're in an interrupt, have no user context or are running in an
+	 * atomic region then we must not take the fault..
+	 */
+	if (in_atomic() || !mm)
+		goto bad_area_nosemaphore;
+
+	/* When running in the kernel we expect faults to occur only to
+	 * addresses in user space.  All other faults represent errors in the
+	 * kernel and should generate an OOPS.  Unfortunatly, in the case of an
+	 * erroneous fault occuring in a code path which already holds mmap_sem
+	 * we will deadlock attempting to validate the fault against the
+	 * address space.  Luckily the kernel only validly references user
+	 * space from well defined areas of code, which are listed in the
+	 * exceptions table.
+	 *
+	 * As the vast majority of faults will be valid we will only perform
+	 * the source reference check when there is a possibilty of a deadlock.
+	 * Attempt to lock the address space, if we cannot we then validate the
+	 * source.  If this is invalid we can skip the address space check,
+	 * thus avoiding the deadlock.
+	 */
+	if (!down_read_trylock(&mm->mmap_sem)) {
+		if ((error_code & 4) == 0 &&
+		    !search_exception_tables(regs->eip))
+			goto bad_area_nosemaphore;
+		down_read(&mm->mmap_sem);
+	}
+
+	vma = find_vma(mm, address);
+	if (!vma)
+		goto bad_area;
+	if (vma->vm_start <= address)
+		goto good_area;
+	if (!(vma->vm_flags & VM_GROWSDOWN))
+		goto bad_area;
+	if (error_code & 4) {
+		/*
+		 * accessing the stack below %esp is always a bug.
+		 * The "+ 32" is there due to some instructions (like
+		 * pusha) doing post-decrement on the stack and that
+		 * doesn't show up until later..
+		 */
+		if (address + 32 < regs->esp)
+			goto bad_area;
+	}
+	if (expand_stack(vma, address))
+		goto bad_area;
+/*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it..
+ */
+good_area:
+	info.si_code = SEGV_ACCERR;
+	write = 0;
+	switch (error_code & 3) {
+		default:	/* 3: write, present */
+#ifdef TEST_VERIFY_AREA
+			if (regs->cs == KERNEL_CS)
+				printk("WP fault at %08lx\n", regs->eip);
+#endif
+			/* fall through */
+		case 2:		/* write, not present */
+			if (!(vma->vm_flags & VM_WRITE))
+				goto bad_area;
+			write++;
+			break;
+		case 1:		/* read, present */
+			goto bad_area;
+		case 0:		/* read, not present */
+			if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+				goto bad_area;
+	}
+
+ survive:
+	/*
+	 * If for any reason at all we couldn't handle the fault,
+	 * make sure we exit gracefully rather than endlessly redo
+	 * the fault.
+	 */
+	switch (handle_mm_fault(mm, vma, address, write)) {
+		case VM_FAULT_MINOR:
+			tsk->min_flt++;
+			break;
+		case VM_FAULT_MAJOR:
+			tsk->maj_flt++;
+			break;
+		case VM_FAULT_SIGBUS:
+			goto do_sigbus;
+		case VM_FAULT_OOM:
+			goto out_of_memory;
+		default:
+			BUG();
+	}
+
+	/*
+	 * Did it hit the DOS screen memory VA from vm86 mode?
+	 */
+	if (regs->eflags & VM_MASK) {
+		unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT;
+		if (bit < 32)
+			tsk->thread.screen_bitmap |= 1 << bit;
+	}
+	up_read(&mm->mmap_sem);
+	return;
+
+/*
+ * Something tried to access memory that isn't in our memory map..
+ * Fix it, but check if it's kernel or user first..
+ */
+bad_area:
+	up_read(&mm->mmap_sem);
+
+bad_area_nosemaphore:
+	/* User mode accesses just cause a SIGSEGV */
+	if (error_code & 4) {
+		/* 
+		 * Valid to do another page fault here because this one came 
+		 * from user space.
+		 */
+		if (is_prefetch(regs, address, error_code))
+			return;
+
+		tsk->thread.cr2 = address;
+		/* Kernel addresses are always protection faults */
+		tsk->thread.error_code = error_code | (address >= TASK_SIZE);
+		tsk->thread.trap_no = 14;
+		info.si_signo = SIGSEGV;
+		info.si_errno = 0;
+		/* info.si_code has been set above */
+		info.si_addr = (void __user *)address;
+		force_sig_info(SIGSEGV, &info, tsk);
+		return;
+	}
+
+#ifdef CONFIG_X86_F00F_BUG
+	/*
+	 * Pentium F0 0F C7 C8 bug workaround.
+	 */
+	if (boot_cpu_data.f00f_bug) {
+		unsigned long nr;
+		
+		nr = (address - idt_descr.address) >> 3;
+
+		if (nr == 6) {
+			do_invalid_op(regs, 0);
+			return;
+		}
+	}
+#endif
+
+no_context:
+	/* Are we prepared to handle this kernel fault?  */
+	if (fixup_exception(regs))
+		return;
+
+	/* 
+	 * Valid to do another page fault here, because if this fault
+	 * had been triggered by is_prefetch fixup_exception would have 
+	 * handled it.
+	 */
+ 	if (is_prefetch(regs, address, error_code))
+ 		return;
+
+/*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+
+	bust_spinlocks(1);
+
+#ifdef CONFIG_X86_PAE
+	if (error_code & 16) {
+		pte_t *pte = lookup_address(address);
+
+		if (pte && pte_present(*pte) && !pte_exec_kernel(*pte))
+			printk(KERN_CRIT "kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", current->uid);
+	}
+#endif
+	if (address < PAGE_SIZE)
+		printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
+	else
+		printk(KERN_ALERT "Unable to handle kernel paging request");
+	printk(" at virtual address %08lx\n",address);
+	printk(KERN_ALERT " printing eip:\n");
+	printk("%08lx\n", regs->eip);
+	asm("movl %%cr3,%0":"=r" (page));
+	page = ((unsigned long *) __va(page))[address >> 22];
+	printk(KERN_ALERT "*pde = %08lx\n", page);
+	/*
+	 * We must not directly access the pte in the highpte
+	 * case, the page table might be allocated in highmem.
+	 * And lets rather not kmap-atomic the pte, just in case
+	 * it's allocated already.
+	 */
+#ifndef CONFIG_HIGHPTE
+	if (page & 1) {
+		page &= PAGE_MASK;
+		address &= 0x003ff000;
+		page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
+		printk(KERN_ALERT "*pte = %08lx\n", page);
+	}
+#endif
+	die("Oops", regs, error_code);
+	bust_spinlocks(0);
+	do_exit(SIGKILL);
+
+/*
+ * We ran out of memory, or some other thing happened to us that made
+ * us unable to handle the page fault gracefully.
+ */
+out_of_memory:
+	up_read(&mm->mmap_sem);
+	if (tsk->pid == 1) {
+		yield();
+		down_read(&mm->mmap_sem);
+		goto survive;
+	}
+	printk("VM: killing process %s\n", tsk->comm);
+	if (error_code & 4)
+		do_exit(SIGKILL);
+	goto no_context;
+
+do_sigbus:
+	up_read(&mm->mmap_sem);
+
+	/* Kernel mode? Handle exceptions