Merge ../linux-2.6/

Conflicts:

	drivers/scsi/aacraid/comminit.c

Fixed up by removing the now renamed CONFIG_IOMMU option from
aacraid

Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>

3 files changed, 112 insertions, 61 deletions

diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index 55250593d8c..08dc696f54e 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -41,6 +41,41 @@
 #define PF_RSVD	(1<<3)
 #define PF_INSTR	(1<<4)
 
+#ifdef CONFIG_KPROBES
+ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain);
+
+/* Hook to register for page fault notifications */
+int register_page_fault_notifier(struct notifier_block *nb)
+{
+	vmalloc_sync_all();
+	return atomic_notifier_chain_register(&notify_page_fault_chain, nb);
+}
+
+int unregister_page_fault_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&notify_page_fault_chain, nb);
+}
+
+static inline int notify_page_fault(enum die_val val, const char *str,
+			struct pt_regs *regs, long err, int trap, int sig)
+{
+	struct die_args args = {
+		.regs = regs,
+		.str = str,
+		.err = err,
+		.trapnr = trap,
+		.signr = sig
+	};
+	return atomic_notifier_call_chain(&notify_page_fault_chain, val, &args);
+}
+#else
+static inline int notify_page_fault(enum die_val val, const char *str,
+			struct pt_regs *regs, long err, int trap, int sig)
+{
+	return NOTIFY_DONE;
+}
+#endif
+
 void bust_spinlocks(int yes)
 {
 	int loglevel_save = console_loglevel;
@@ -160,7 +195,7 @@ void dump_pagetable(unsigned long address)
 	printk("PGD %lx ", pgd_val(*pgd));
 	if (!pgd_present(*pgd)) goto ret; 
 
-	pud = __pud_offset_k((pud_t *)pgd_page(*pgd), address);
+	pud = pud_offset(pgd, address);
 	if (bad_address(pud)) goto bad;
 	printk("PUD %lx ", pud_val(*pud));
 	if (!pud_present(*pud))	goto ret;
@@ -348,7 +383,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 			if (vmalloc_fault(address) >= 0)
 				return;
 		}
-		if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
+		if (notify_page_fault(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
 						SIGSEGV) == NOTIFY_STOP)
 			return;
 		/*
@@ -358,7 +393,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 		goto bad_area_nosemaphore;
 	}
 
-	if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
+	if (notify_page_fault(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
 					SIGSEGV) == NOTIFY_STOP)
 		return;
 
@@ -410,8 +445,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	if (!(vma->vm_flags & VM_GROWSDOWN))
 		goto bad_area;
 	if (error_code & 4) {
-		// XXX: align red zone size with ABI 
-		if (address + 128 < regs->rsp)
+		/* Allow userspace just enough access below the stack pointer
+		 * to let the 'enter' instruction work.
+		 */
+		if (address + 65536 + 32 * sizeof(unsigned long) < regs->rsp)
 			goto bad_area;
 	}
 	if (expand_stack(vma, address))
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index 4ba34e95d83..95bd232ff0c 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -23,6 +23,7 @@
 #include <linux/bootmem.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
+#include <linux/poison.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/memory_hotplug.h>
@@ -41,8 +42,6 @@
 #include <asm/proto.h>
 #include <asm/smp.h>
 #include <asm/sections.h>
-#include <asm/dma-mapping.h>
-#include <asm/swiotlb.h>
 
 #ifndef Dprintk
 #define Dprintk(x...)
@@ -90,8 +89,6 @@ void show_mem(void)
 	printk(KERN_INFO "%lu pages swap cached\n",cached);
 }
 
-/* References to section boundaries */
-
 int after_bootmem;
 
 static __init void *spp_getpage(void)
@@ -261,9 +258,10 @@ phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end)
 	for (i = 0; i < PTRS_PER_PMD; pmd++, i++, address += PMD_SIZE) {
 		unsigned long entry;
 
-		if (address > end) {
-			for (; i < PTRS_PER_PMD; i++, pmd++)
-				set_pmd(pmd, __pmd(0));
+		if (address >= end) {
+			if (!after_bootmem)
+				for (; i < PTRS_PER_PMD; i++, pmd++)
+					set_pmd(pmd, __pmd(0));
 			break;
 		}
 		entry = _PAGE_NX|_PAGE_PSE|_KERNPG_TABLE|_PAGE_GLOBAL|address;
@@ -341,7 +339,8 @@ static void __init find_early_table_space(unsigned long end)
 	table_end = table_start;
 
 	early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n",
-		end, table_start << PAGE_SHIFT, table_end << PAGE_SHIFT);
+		end, table_start << PAGE_SHIFT,
+		(table_start << PAGE_SHIFT) + tables);
 }
 
 /* Setup the direct mapping of the physical memory at PAGE_OFFSET.
@@ -372,7 +371,7 @@ void __meminit init_memory_mapping(unsigned long start, unsigned long end)
 		pud_t *pud;
 
 		if (after_bootmem)
-			pud = pud_offset_k(pgd, start & PGDIR_MASK);
+			pud = pud_offset(pgd, start & PGDIR_MASK);
 		else
 			pud = alloc_low_page(&map, &pud_phys);
 
@@ -508,8 +507,6 @@ void __init clear_kernel_mapping(unsigned long address, unsigned long size)
 /*
  * Memory hotplug specific functions
  */
-#if defined(CONFIG_ACPI_HOTPLUG_MEMORY) || defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)
-
 void online_page(struct page *page)
 {
 	ClearPageReserved(page);
@@ -519,31 +516,17 @@ void online_page(struct page *page)
 	num_physpages++;
 }
 
-#ifndef CONFIG_MEMORY_HOTPLUG
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
- * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
- * just online the pages.
+ * 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.
  */
-int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
+#ifdef CONFIG_NUMA
+int memory_add_physaddr_to_nid(u64 start)
 {
-	int err = -EIO;
-	unsigned long pfn;
-	unsigned long total = 0, mem = 0;
-	for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
-		if (pfn_valid(pfn)) {
-			online_page(pfn_to_page(pfn));
-			err = 0;
-			mem++;
-		}
-		total++;
-	}
-	if (!err) {
-		z->spanned_pages += total;
-		z->present_pages += mem;
-		z->zone_pgdat->node_spanned_pages += total;
-		z->zone_pgdat->node_present_pages += mem;
-	}
-	return err;
+	return 0;
 }
 #endif
 
@@ -551,9 +534,9 @@ int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
  * Memory is added always to NORMAL zone. This means you will never get
  * additional DMA/DMA32 memory.
  */
-int add_memory(u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size)
 {
-	struct pglist_data *pgdat = NODE_DATA(0);
+	struct pglist_data *pgdat = NODE_DATA(nid);
 	struct zone *zone = pgdat->node_zones + MAX_NR_ZONES-2;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -570,7 +553,7 @@ error:
 	printk("%s: Problem encountered in __add_pages!\n", __func__);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(add_memory);
+EXPORT_SYMBOL_GPL(arch_add_memory);
 
 int remove_memory(u64 start, u64 size)
 {
@@ -578,7 +561,33 @@ int remove_memory(u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(remove_memory);
 
-#endif
+#else /* CONFIG_MEMORY_HOTPLUG */
+/*
+ * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
+ * just online the pages.
+ */
+int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
+{
+	int err = -EIO;
+	unsigned long pfn;
+	unsigned long total = 0, mem = 0;
+	for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
+		if (pfn_valid(pfn)) {
+			online_page(pfn_to_page(pfn));
+			err = 0;
+			mem++;
+		}
+		total++;
+	}
+	if (!err) {
+		z->spanned_pages += total;
+		z->present_pages += mem;
+		z->zone_pgdat->node_spanned_pages += total;
+		z->zone_pgdat->node_present_pages += mem;
+	}
+	return err;
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
 			 kcore_vsyscall;
@@ -587,10 +596,7 @@ void __init mem_init(void)
 {
 	long codesize, reservedpages, datasize, initsize;
 
-#ifdef CONFIG_SWIOTLB
-	pci_swiotlb_init();
-#endif
-	no_iommu_init();
+	pci_iommu_alloc();
 
 	/* How many end-of-memory variables you have, grandma! */
 	max_low_pfn = end_pfn;
@@ -644,20 +650,31 @@ void __init mem_init(void)
 #endif
 }
 
-void free_initmem(void)
+void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
 	unsigned long addr;
 
-	addr = (unsigned long)(&__init_begin);
-	for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
+	if (begin >= end)
+		return;
+
+	printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
+	for (addr = begin; addr < end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE); 
+		memset((void *)(addr & ~(PAGE_SIZE-1)),
+			POISON_FREE_INITMEM, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
-	memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin);
-	printk ("Freeing unused kernel memory: %luk freed\n", (__init_end - __init_begin) >> 10);
+}
+
+void free_initmem(void)
+{
+	memset(__initdata_begin, POISON_FREE_INITDATA,
+		__initdata_end - __initdata_begin);
+	free_init_pages("unused kernel memory",
+			(unsigned long)(&__init_begin),
+			(unsigned long)(&__init_end));
 }
 
 #ifdef CONFIG_DEBUG_RODATA
@@ -686,15 +703,7 @@ void mark_rodata_ro(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (start >= end)
-		return;
-	printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages++;
-	}
+	free_init_pages("initrd memory", start, end);
 }
 #endif
 
diff --git a/arch/x86_64/mm/ioremap.c b/arch/x86_64/mm/ioremap.c
index ae207064201..45d7d823c3b 100644
--- a/arch/x86_64/mm/ioremap.c
+++ b/arch/x86_64/mm/ioremap.c
@@ -11,6 +11,7 @@
 #include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/module.h>
 #include <asm/io.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
@@ -219,6 +220,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
 	}
 	return (__force void __iomem *) (offset + (char *)addr);
 }
+EXPORT_SYMBOL(__ioremap);
 
 /**
  * ioremap_nocache     -   map bus memory into CPU space
@@ -246,6 +248,7 @@ void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size)
 {
 	return __ioremap(phys_addr, size, _PAGE_PCD);
 }
+EXPORT_SYMBOL(ioremap_nocache);
 
 /**
  * iounmap - Free a IO remapping
@@ -291,3 +294,5 @@ void iounmap(volatile void __iomem *addr)
 	BUG_ON(p != o || o == NULL);
 	kfree(p); 
 }
+EXPORT_SYMBOL(iounmap);
+