Merge http://lia64.bkbits.net/to-linus-2.5

into home.osdl.org:/home/torvalds/v2.5/linux

arch/ia64/Kconfig

@@ -220,24 +220,8 @@ config NUMA
 	  Access).  This option is for configuring high-end multiprocessor
 	  server systems.  If in doubt, say N.
 
-choice
-	prompt "Maximum Memory per NUMA Node" if NUMA && IA64_DIG
-	depends on NUMA && IA64_DIG
-	default IA64_NODESIZE_16GB
-
-config IA64_NODESIZE_16GB
-	bool "16GB"
-
-config IA64_NODESIZE_64GB
-	bool "64GB"
-
-config IA64_NODESIZE_256GB
-	bool "256GB"
-
-endchoice
-
 config DISCONTIGMEM
-	bool "Discontiguous memory support" if (IA64_DIG || IA64_SGI_SN2 || IA64_GENERIC) && NUMA
+	bool "Discontiguous memory support" if (IA64_DIG || IA64_SGI_SN2 || IA64_GENERIC) && NUMA && VIRTUAL_MEM_MAP
 	default y if (IA64_SGI_SN2 || IA64_GENERIC) && NUMA
 	help
 	  Say Y to support efficient handling of discontiguous physical memory,
@@ -250,14 +234,10 @@ config VIRTUAL_MEM_MAP
 	default y if !IA64_HP_SIM
 	help
 	  Say Y to compile the kernel with support for a virtual mem map.
-	  This is an alternate method of supporting large holes in the
-	  physical address space on non NUMA machines. Since the DISCONTIGMEM
-	  option is not supported on machines with the ZX1 chipset, this is
-	  the only way of supporting more than 1 Gb of memory on those
-	  machines. This code also only takes effect if a memory hole of
-	  greater than 1 Gb is found during boot, so it is safe to enable
-	  unless you require the DISCONTIGMEM option for your machine. If you
-	  are unsure, say Y.
+	  This code also only takes effect if a memory hole of greater than
+	  1 Gb is found during boot.  You must turn this option on if you
+	  require the DISCONTIGMEM option for your machine. If you are
+	  unsure, say Y.
 
 config IA64_MCA
 	bool "Enable IA-64 Machine Check Abort"

arch/ia64/Makefile

@@ -64,7 +64,7 @@ core-$(CONFIG_IA64_SGI_SN2)	+= arch/ia64/sn/
 drivers-$(CONFIG_PCI)		+= arch/ia64/pci/
 drivers-$(CONFIG_IA64_HP_SIM)	+= arch/ia64/hp/sim/
 drivers-$(CONFIG_IA64_HP_ZX1)	+= arch/ia64/hp/common/ arch/ia64/hp/zx1/
-drivers-$(CONFIG_IA64_GENERIC)	+= arch/ia64/hp/common/ arch/ia64/hp/zx1/ arch/ia64/hp/sim/
+drivers-$(CONFIG_IA64_GENERIC)	+= arch/ia64/hp/common/ arch/ia64/hp/zx1/ arch/ia64/hp/sim/ arch/ia64/sn/
 drivers-$(CONFIG_OPROFILE)	+= arch/ia64/oprofile/
 
 boot := arch/ia64/hp/sim/boot

arch/ia64/ia32/sys_ia32.c

@@ -2486,11 +2486,14 @@ static int
 putstat64 (struct stat64 *ubuf, struct kstat *kbuf)
 {
 	int err;
+	u64 hdev;
 
 	if (clear_user(ubuf, sizeof(*ubuf)))
 		return -EFAULT;
 
-	err  = __put_user(huge_encode_dev(kbuf->dev), &ubuf->st_dev);
+	hdev = huge_encode_dev(kbuf->dev);
+	err  = __put_user(hdev, (u32*)&ubuf->st_dev);
+	err |= __put_user(hdev >> 32, ((u32*)&ubuf->st_dev) + 1);
 	err |= __put_user(kbuf->ino, &ubuf->__st_ino);
 	err |= __put_user(kbuf->ino, &ubuf->st_ino_lo);
 	err |= __put_user(kbuf->ino >> 32, &ubuf->st_ino_hi);
@@ -2498,7 +2501,9 @@ putstat64 (struct stat64 *ubuf, struct kstat *kbuf)
 	err |= __put_user(kbuf->nlink, &ubuf->st_nlink);
 	err |= __put_user(kbuf->uid, &ubuf->st_uid);
 	err |= __put_user(kbuf->gid, &ubuf->st_gid);
-	err |= __put_user(huge_encode_dev(kbuf->rdev), &ubuf->st_rdev);
+	hdev = huge_encode_dev(kbuf->rdev);
+	err  = __put_user(hdev, (u32*)&ubuf->st_rdev);
+	err |= __put_user(hdev >> 32, ((u32*)&ubuf->st_rdev) + 1);
 	err |= __put_user(kbuf->size, &ubuf->st_size_lo);
 	err |= __put_user((kbuf->size >> 32), &ubuf->st_size_hi);
 	err |= __put_user(kbuf->atime.tv_sec, &ubuf->st_atime);
@@ -2724,8 +2729,8 @@ sys32_open (const char * filename, int flags, int mode)
 struct epoll_event32
 {
 	u32 events;
-	u64 data;
-} __attribute__((packed));
+	u32 data[2];
+}; 
 
 asmlinkage long
 sys32_epoll_ctl(int epfd, int op, int fd, struct epoll_event32 *event)
@@ -2740,10 +2745,10 @@ sys32_epoll_ctl(int epfd, int op, int fd, struct epoll_event32 *event)
 		return error;
 
 	__get_user(event64.events, &event->events);
-	__get_user(data_halfword, (u32*)(&event->data));
+	__get_user(data_halfword, &event->data[0]);
 	event64.data = data_halfword;
-	__get_user(data_halfword, ((u32*)(&event->data) + 1));
- 	event64.data |= ((u64)data_halfword) << 32;
+	__get_user(data_halfword, &event->data[1]);
+ 	event64.data |= (u64)data_halfword << 32;
 
 	set_fs(KERNEL_DS);
 	error = sys_epoll_ctl(epfd, op, fd, &event64);
@@ -2758,8 +2763,9 @@ sys32_epoll_wait(int epfd, struct epoll_event32 *events, int maxevents,
 {
 	struct epoll_event *events64 = NULL;
 	mm_segment_t old_fs = get_fs();
-	int error;
+	int error, numevents, size;
 	int evt_idx;
+	int do_free_pages = 0;
 
 	if (maxevents <= 0) {
 		return -EINVAL;
@@ -2770,43 +2776,45 @@ sys32_epoll_wait(int epfd, struct epoll_event32 *events, int maxevents,
 				 maxevents * sizeof(struct epoll_event32))))
 		return error;
 
-	/* Allocate the space needed for the intermediate copy */
-	events64 = kmalloc(maxevents * sizeof(struct epoll_event), GFP_KERNEL);
+	/* 
+ 	 * Allocate space for the intermediate copy.  If the space needed 
+	 * is large enough to cause kmalloc to fail, then try again with
+	 * __get_free_pages.
+	 */
+	size = maxevents * sizeof(struct epoll_event);
+	events64 = kmalloc(size, GFP_KERNEL);
 	if (events64 == NULL) {
-		return -ENOMEM;
-	}
-
-	/* Expand the 32-bit structures into the 64-bit structures */
-	for (evt_idx = 0; evt_idx < maxevents; evt_idx++) {
-		u32 data_halfword;
-		__get_user(events64[evt_idx].events, &events[evt_idx].events);
-		__get_user(data_halfword, (u32*)(&events[evt_idx].data));
-		events64[evt_idx].data = data_halfword;
-		__get_user(data_halfword, ((u32*)(&events[evt_idx].data) + 1));
-		events64[evt_idx].data |= ((u64)data_halfword) << 32;
+		events64 = (struct epoll_event *)
+				__get_free_pages(GFP_KERNEL, get_order(size));
+		if (events64 == NULL) 
+			return -ENOMEM;
+		do_free_pages = 1;
 	}
 
 	/* Do the system call */
 	set_fs(KERNEL_DS); /* copy_to/from_user should work on kernel mem*/
-	error = sys_epoll_wait(epfd, events64, maxevents, timeout);
+	numevents = sys_epoll_wait(epfd, events64, maxevents, timeout);
 	set_fs(old_fs);
 
 	/* Don't modify userspace memory if we're returning an error */
-	if (!error) {
+	if (numevents > 0) {
 		/* Translate the 64-bit structures back into the 32-bit
 		   structures */
-		for (evt_idx = 0; evt_idx < maxevents; evt_idx++) {
+		for (evt_idx = 0; evt_idx < numevents; evt_idx++) {
 			__put_user(events64[evt_idx].events,
 				   &events[evt_idx].events);
-			__put_user((u32)(events64[evt_idx].data),
-				   (u32*)(&events[evt_idx].data));
+			__put_user((u32)events64[evt_idx].data,
+				   &events[evt_idx].data[0]);
 			__put_user((u32)(events64[evt_idx].data >> 32),
-				   ((u32*)(&events[evt_idx].data) + 1));
+				   &events[evt_idx].data[1]);
 		}
 	}
 
-	kfree(events64);
-	return error;
+	if (do_free_pages)
+		free_pages((unsigned long) events64, get_order(size));
+	else
+		kfree(events64);
+	return numevents;
 }
 
 #ifdef	NOTYET  /* UNTESTED FOR IA64 FROM HERE DOWN */

arch/ia64/kernel/acpi.c

@@ -380,7 +380,7 @@ acpi_numa_processor_affinity_init (struct acpi_table_processor_affinity *pa)
 void __init
 acpi_numa_memory_affinity_init (struct acpi_table_memory_affinity *ma)
 {
-	unsigned long paddr, size, hole_size, min_hole_size;
+	unsigned long paddr, size;
 	u8 pxm;
 	struct node_memblk_s *p, *q, *pend;
 
@@ -402,34 +402,6 @@ acpi_numa_memory_affinity_init (struct acpi_table_memory_affinity *ma)
 	if (!ma->flags.enabled)
 		return;
 
-	/*
-	 * When the chunk is not the first one in the node, check distance
-	 * from the other chunks. When the hole is too huge ignore the chunk.
-	 * This restriction should be removed when multiple chunks per node
-	 * is supported.
-	 */
-	pend = &node_memblk[num_memblks];
-	min_hole_size = 0;
-	for (p = &node_memblk[0]; p < pend; p++) {
-		if (p->nid != pxm)
-			continue;
-		if (p->start_paddr < paddr)
-			hole_size = paddr - (p->start_paddr + p->size);
-		else
-			hole_size = p->start_paddr - (paddr + size);
-
-		if (!min_hole_size || hole_size < min_hole_size)
-			min_hole_size = hole_size;
-	}
-
-	if (min_hole_size) {
-		if (min_hole_size > size) {
-			printk(KERN_ERR "Too huge memory hole. Ignoring %ld MBytes at %lx\n",
-			       size/(1024*1024), paddr);
-			return;
-		}
-	}
-
 	/* record this node in proximity bitmap */
 	pxm_bit_set(pxm);
 
@@ -454,6 +426,12 @@ acpi_numa_arch_fixup (void)
 {
 	int i, j, node_from, node_to;
 
+	/* If there's no SRAT, fix the phys_id */
+	if (srat_num_cpus == 0) {
+		node_cpuid[0].phys_id = hard_smp_processor_id();
+		return;
+	}
+
 	/* calculate total number of nodes in system from PXM bitmap */
 	numnodes = 0;		/* init total nodes in system */
 
@@ -614,6 +592,12 @@ acpi_boot_init (void)
 
 	smp_build_cpu_map();
 # ifdef CONFIG_NUMA
+	if (srat_num_cpus == 0) {
+		int cpu, i = 1;
+		for (cpu = 0; cpu < smp_boot_data.cpu_count; cpu++)
+			if (smp_boot_data.cpu_phys_id[cpu] != hard_smp_processor_id())
+				node_cpuid[i++].phys_id = smp_boot_data.cpu_phys_id[cpu];
+	}
 	build_cpu_to_node_map();
 # endif
 #endif

arch/ia64/kernel/setup.c

@@ -101,7 +101,7 @@ int
 filter_rsvd_memory (unsigned long start, unsigned long end, void *arg)
 {
 	unsigned long range_start, range_end, prev_start;
-	void (*func)(unsigned long, unsigned long);
+	void (*func)(unsigned long, unsigned long, int);
 	int i;
 
 #if IGNORE_PFN0
@@ -122,11 +122,7 @@ filter_rsvd_memory (unsigned long start, unsigned long end, void *arg)
 		range_end   = min(end, rsvd_region[i].start);
 
 		if (range_start < range_end)
-#ifdef CONFIG_DISCONTIGMEM
-			call_pernode_memory(__pa(range_start), __pa(range_end), func);
-#else
-			(*func)(__pa(range_start), range_end - range_start);
-#endif
+			call_pernode_memory(__pa(range_start), range_end - range_start, func);
 
 		/* nothing more available in this segment */
 		if (range_end == end) return 0;
@@ -239,7 +235,6 @@ setup_arch (char **cmdline_p)
 	strlcpy(saved_command_line, *cmdline_p, sizeof(saved_command_line));
 
 	efi_init();
-	find_memory();
 
 #ifdef CONFIG_ACPI_BOOT
 	/* Initialize the ACPI boot-time table parser */
@@ -253,6 +248,8 @@ setup_arch (char **cmdline_p)
 # endif
 #endif /* CONFIG_APCI_BOOT */
 
+	find_memory();
+
 	/* process SAL system table: */
 	ia64_sal_init(efi.sal_systab);
 
@@ -544,28 +541,7 @@ cpu_init (void)
 	struct cpuinfo_ia64 *cpu_info;
 	void *cpu_data;
 
-#ifdef CONFIG_SMP
-	int cpu;
-
-	/*
-	 * get_free_pages() cannot be used before cpu_init() done.  BSP allocates
-	 * "NR_CPUS" pages for all CPUs to avoid that AP calls get_zeroed_page().
-	 */
-	if (smp_processor_id() == 0) {
-		cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS, PERCPU_PAGE_SIZE,
-					   __pa(MAX_DMA_ADDRESS));
-		for (cpu = 0; cpu < NR_CPUS; cpu++) {
-			memcpy(cpu_data, __phys_per_cpu_start, __per_cpu_end - __per_cpu_start);
-			__per_cpu_offset[cpu] = (char *) cpu_data - __per_cpu_start;
-			cpu_data += PERCPU_PAGE_SIZE;
-
-			per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
-		}
-	}
-	cpu_data = __per_cpu_start + __per_cpu_offset[smp_processor_id()];
-#else /* !CONFIG_SMP */
-	cpu_data = __phys_per_cpu_start;
-#endif /* !CONFIG_SMP */
+	cpu_data = per_cpu_init();
 
 	get_max_cacheline_size();
 
@@ -576,9 +552,6 @@ cpu_init (void)
 	 * accessing cpu_data() through the canonical per-CPU address.
 	 */
 	cpu_info = cpu_data + ((char *) &__ia64_per_cpu_var(cpu_info) - __per_cpu_start);
-#ifdef CONFIG_NUMA
-	cpu_info->node_data = get_node_data_ptr();
-#endif
 	identify_cpu(cpu_info);
 
 #ifdef CONFIG_MCKINLEY

arch/ia64/mm/contig.c

@@ -25,6 +25,10 @@
 #include <asm/pgtable.h>
 #include <asm/sections.h>
 
+#ifdef CONFIG_VIRTUAL_MEM_MAP
+static unsigned long num_dma_physpages;
+#endif
+
 /**
  * show_mem - display a memory statistics summary
  *
@@ -161,3 +165,133 @@ find_memory (void)
 
 	find_initrd();
 }
+
+#ifdef CONFIG_SMP
+/**
+ * per_cpu_init - setup per-cpu variables
+ *
+ * Allocate and setup per-cpu data areas.
+ */
+void *
+per_cpu_init (void)
+{
+	void *cpu_data;
+	int cpu;
+
+	/*
+	 * get_free_pages() cannot be used before cpu_init() done.  BSP
+	 * allocates "NR_CPUS" pages for all CPUs to avoid that AP calls
+	 * get_zeroed_page().
+	 */
+	if (smp_processor_id() == 0) {
+		cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS,
+					   PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+		for (cpu = 0; cpu < NR_CPUS; cpu++) {
+			memcpy(cpu_data, __phys_per_cpu_start, __per_cpu_end - __per_cpu_start);
+			__per_cpu_offset[cpu] = (char *) cpu_data - __per_cpu_start;
+			cpu_data += PERCPU_PAGE_SIZE;
+			per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
+		}
+	}
+	return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
+}
+#endif /* CONFIG_SMP */
+
+static int
+count_pages (u64 start, u64 end, void *arg)
+{
+	unsigned long *count = arg;
+
+	*count += (end - start) >> PAGE_SHIFT;
+	return 0;
+}
+
+#ifdef CONFIG_VIRTUAL_MEM_MAP
+static int
+count_dma_pages (u64 start, u64 end, void *arg)
+{
+	unsigned long *count = arg;
+
+	if (end <= MAX_DMA_ADDRESS)
+		*count += (end - start) >> PAGE_SHIFT;
+	return 0;
+}
+#endif
+
+/*
+ * Set up the page tables.
+ */
+
+void
+paging_init (void)
+{
+	unsigned long max_dma;
+	unsigned long zones_size[MAX_NR_ZONES];
+#ifdef CONFIG_VIRTUAL_MEM_MAP
+	unsigned long zholes_size[MAX_NR_ZONES];
+	unsigned long max_gap;
+#endif
+
+	/* initialize mem_map[] */
+
+	memset(zones_size, 0, sizeof(zones_size));
+
+	num_physpages = 0;
+	efi_memmap_walk(count_pages, &num_physpages);
+
+	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+
+#ifdef CONFIG_VIRTUAL_MEM_MAP
+	memset(zholes_size, 0, sizeof(zholes_size));
+
+	num_dma_physpages = 0;
+	efi_memmap_walk(count_dma_pages, &num_dma_physpages);
+
+	if (max_low_pfn < max_dma) {
+		zones_size[ZONE_DMA] = max_low_pfn;
+		zholes_size[ZONE_DMA] = max_low_pfn - num_dma_physpages;
+	} else {
+		zones_size[ZONE_DMA] = max_dma;
+		zholes_size[ZONE_DMA] = max_dma - num_dma_physpages;
+		if (num_physpages > num_dma_physpages) {
+			zones_size[ZONE_NORMAL] = max_low_pfn - max_dma;
+			zholes_size[ZONE_NORMAL] =
+				((max_low_pfn - max_dma) -
+				 (num_physpages - num_dma_physpages));
+		}
+	}
+
+	max_gap = 0;
+	efi_memmap_walk(find_largest_hole, (u64 *)&max_gap);
+	if (max_gap < LARGE_GAP) {
+		vmem_map = (struct page *) 0;
+		free_area_init_node(0, &contig_page_data, NULL, zones_size, 0,
+				    zholes_size);
+		mem_map = contig_page_data.node_mem_map;
+	} else {
+		unsigned long map_size;
+
+		/* allocate virtual_mem_map */
+
+		map_size = PAGE_ALIGN(max_low_pfn * sizeof(struct page));
+		vmalloc_end -= map_size;
+		vmem_map = (struct page *) vmalloc_end;
+		efi_memmap_walk(create_mem_map_page_table, 0);
+
+		free_area_init_node(0, &contig_page_data, vmem_map, zones_size,
+				    0, zholes_size);
+
+		mem_map = contig_page_data.node_mem_map;
+		printk("Virtual mem_map starts at 0x%p\n", mem_map);
+	}
+#else /* !CONFIG_VIRTUAL_MEM_MAP */
+	if (max_low_pfn < max_dma)
+		zones_size[ZONE_DMA] = max_low_pfn;
+	else {
+		zones_size[ZONE_DMA] = max_dma;
+		zones_size[ZONE_NORMAL] = max_low_pfn - max_dma;
+	}
+	free_area_init(zones_size);
+#endif /* !CONFIG_VIRTUAL_MEM_MAP */
+	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
+}

arch/ia64/mm/hugetlbpage.c

@@ -20,13 +20,46 @@
 
 #define TASK_HPAGE_BASE (REGION_HPAGE << REGION_SHIFT)
 
-static long    htlbpagemem;
-int     htlbpage_max;
-static long    htlbzone_pages;
+static long	htlbpagemem;
+int		htlbpage_max;
+static long	htlbzone_pages;
 
-static LIST_HEAD(htlbpage_freelist);
+static struct list_head hugepage_freelists[MAX_NUMNODES];
 static spinlock_t htlbpage_lock = SPIN_LOCK_UNLOCKED;
 
+static void enqueue_huge_page(struct page *page)
+{
+	list_add(&page->list,
+		&hugepage_freelists[page_zone(page)->zone_pgdat->node_id]);
+}
+
+static struct page *dequeue_huge_page(void)
+{
+	int nid = numa_node_id();
+	struct page *page = NULL;
+
+	if (list_empty(&hugepage_freelists[nid])) {
+		for (nid = 0; nid < MAX_NUMNODES; ++nid)
+			if (!list_empty(&hugepage_freelists[nid]))
+				break;
+	}
+	if (nid >= 0 && nid < MAX_NUMNODES &&
+	    !list_empty(&hugepage_freelists[nid])) {
+		page = list_entry(hugepage_freelists[nid].next, struct page, list);
+		list_del(&page->list);
+	}
+	return page;
+}
+
+static struct page *alloc_fresh_huge_page(void)
+{
+	static int nid = 0;
+	struct page *page;
+	page = alloc_pages_node(nid, GFP_HIGHUSER, HUGETLB_PAGE_ORDER);
+	nid = (nid + 1) % numnodes;
+	return page;
+}
+
 void free_huge_page(struct page *page);
 
 static struct page *alloc_hugetlb_page(void)
@@ -35,13 +68,11 @@ static struct page *alloc_hugetlb_page(void)
 	struct page *page;
 
 	spin_lock(&htlbpage_lock);
-	if (list_empty(&htlbpage_freelist)) {
+	page = dequeue_huge_page();
+	if (!page) {
 		spin_unlock(&htlbpage_lock);
 		return NULL;
 	}
-
-	page = list_entry(htlbpage_freelist.next, struct page, list);
-	list_del(&page->list);
 	htlbpagemem--;
 	spin_unlock(&htlbpage_lock);
 	set_page_count(page, 1);
@@ -228,7 +259,7 @@ void free_huge_page(struct page *page)
 	INIT_LIST_HEAD(&page->list);
 
 	spin_lock(&htlbpage_lock);
-	list_add(&page->list, &htlbpage_freelist);
+	enqueue_huge_page(page);
 	htlbpagemem++;
 	spin_unlock(&htlbpage_lock);
 }
@@ -371,7 +402,7 @@ int try_to_free_low(int count)
 
 	map = NULL;
 	spin_lock(&htlbpage_lock);
-	list_for_each(p, &htlbpage_freelist) {
+	list_for_each(p, &hugepage_freelists[0]) {
 		if (map) {
 			list_del(&map->list);
 			update_and_free_page(map);
@@ -408,11 +439,11 @@ int set_hugetlb_mem_size(int count)
 		return (int)htlbzone_pages;
 	if (lcount > 0) {	/* Increase the mem size. */
 		while (lcount--) {
-			page = alloc_pages(__GFP_HIGHMEM, HUGETLB_PAGE_ORDER);
+			page = alloc_fresh_huge_page();
 			if (page == NULL)
 				break;
 			spin_lock(&htlbpage_lock);
-			list_add(&page->list, &htlbpage_freelist);
+			enqueue_huge_page(page);
 			htlbpagemem++;
 			htlbzone_pages++;
 			spin_unlock(&htlbpage_lock);
@@ -449,17 +480,18 @@ __setup("hugepages=", hugetlb_setup);
 
 static int __init hugetlb_init(void)
 {
-	int i, j;
+	int i;
 	struct page *page;
 
+	for (i = 0; i < MAX_NUMNODES; ++i)
+		INIT_LIST_HEAD(&hugepage_freelists[i]);
+
 	for (i = 0; i < htlbpage_max; ++i) {
-		page = alloc_pages(__GFP_HIGHMEM, HUGETLB_PAGE_ORDER);
+		page = alloc_fresh_huge_page();
 		if (!page)
 			break;
-		for (j = 0; j < HPAGE_SIZE/PAGE_SIZE; ++j)
-			SetPageReserved(&page[j]);
 		spin_lock(&htlbpage_lock);
-		list_add(&page->list, &htlbpage_freelist);
+		enqueue_huge_page(page);
 		spin_unlock(&htlbpage_lock);
 	}
 	htlbpage_max = htlbpagemem = htlbzone_pages = i;

arch/ia64/mm/init.c

@@ -24,6 +24,7 @@
 #include <asm/ia32.h>
 #include <asm/io.h>
 #include <asm/machvec.h>
+#include <asm/numa.h>
 #include <asm/patch.h>
 #include <asm/pgalloc.h>
 #include <asm/sal.h>
@@ -40,10 +41,8 @@ extern void ia64_tlb_init (void);
 unsigned long MAX_DMA_ADDRESS = PAGE_OFFSET + 0x100000000UL;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-# define LARGE_GAP	0x40000000	/* Use virtual mem map if hole is > than this */
   unsigned long vmalloc_end = VMALLOC_END_INIT;
-  static struct page *vmem_map;
-  static unsigned long num_dma_physpages;
+  struct page *vmem_map;
 #endif
 
 static int pgt_cache_water[2] = { 25, 50 };
@@ -337,11 +336,12 @@ ia64_mmu_init (void *my_cpu_data)
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 
-static int
+int
 create_mem_map_page_table (u64 start, u64 end, void *arg)
 {
 	unsigned long address, start_page, end_page;
 	struct page *map_start, *map_end;
+	int node;
 	pgd_t *pgd;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -351,19 +351,20 @@ create_mem_map_page_table (u64 start, u64 end, void *arg)
 
 	start_page = (unsigned long) map_start & PAGE_MASK;
 	end_page = PAGE_ALIGN((unsigned long) map_end);
+	node = paddr_to_nid(__pa(start));
 
 	for (address = start_page; address < end_page; address += PAGE_SIZE) {
 		pgd = pgd_offset_k(address);
 		if (pgd_none(*pgd))
-			pgd_populate(&init_mm, pgd, alloc_bootmem_pages(PAGE_SIZE));
+			pgd_populate(&init_mm, pgd, alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE));
 		pmd = pmd_offset(pgd, address);
 
 		if (pmd_none(*pmd))
-			pmd_populate_kernel(&init_mm, pmd, alloc_bootmem_pages(PAGE_SIZE));
+			pmd_populate_kernel(&init_mm, pmd, alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE));
 		pte = pte_offset_kernel(pmd, address);
 
 		if (pte_none(*pte))
-			set_pte(pte, pfn_pte(__pa(alloc_bootmem_pages(PAGE_SIZE)) >> PAGE_SHIFT,
+			set_pte(pte, pfn_pte(__pa(alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE)) >> PAGE_SHIFT,
 					     PAGE_KERNEL));
 	}
 	return 0;
@@ -433,17 +434,7 @@ ia64_pfn_valid (unsigned long pfn)
 	return __get_user(byte, (char *) pfn_to_page(pfn)) == 0;
 }
 
-static int
-count_dma_pages (u64 start, u64 end, void *arg)
-{
-	unsigned long *count = arg;
-
-	if (end <= MAX_DMA_ADDRESS)
-		*count += (end - start) >> PAGE_SHIFT;
-	return 0;
-}
-
-static int
+int
 find_largest_hole (u64 start, u64 end, void *arg)
 {
 	u64 *max_gap = arg;
@@ -459,103 +450,6 @@ find_largest_hole (u64 start, u64 end, void *arg)
 }
 #endif /* CONFIG_VIRTUAL_MEM_MAP */
 
-static int
-count_pages (u64 start, u64 end, void *arg)
-{
-	unsigned long *count = arg;
-
-	*count += (end - start) >> PAGE_SHIFT;
-	return 0;
-}
-
-/*
- * Set up the page tables.
- */
-
-#ifdef CONFIG_DISCONTIGMEM
-void
-paging_init (void)
-{
-	extern void discontig_paging_init(void);
-
-	discontig_paging_init();
-	efi_memmap_walk(count_pages, &num_physpages);
-	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
-}
-#else /* !CONFIG_DISCONTIGMEM */
-void
-paging_init (void)
-{
-	unsigned long max_dma;
-	unsigned long zones_size[MAX_NR_ZONES];
-#  ifdef CONFIG_VIRTUAL_MEM_MAP
-	unsigned long zholes_size[MAX_NR_ZONES];
-	unsigned long max_gap;
-#  endif
-
-	/* initialize mem_map[] */
-
-	memset(zones_size, 0, sizeof(zones_size));
-
-	num_physpages = 0;
-	efi_memmap_walk(count_pages, &num_physpages);
-
-	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-
-#  ifdef CONFIG_VIRTUAL_MEM_MAP
-	memset(zholes_size, 0, sizeof(zholes_size));
-
-	num_dma_physpages = 0;
-	efi_memmap_walk(count_dma_pages, &num_dma_physpages);
-
-	if (max_low_pfn < max_dma) {
-		zones_size[ZONE_DMA] = max_low_pfn;
-		zholes_size[ZONE_DMA] = max_low_pfn - num_dma_physpages;
-	} else {
-		zones_size[ZONE_DMA] = max_dma;
-		zholes_size[ZONE_DMA] = max_dma - num_dma_physpages;
-		if (num_physpages > num_dma_physpages) {
-			zones_size[ZONE_NORMAL] = max_low_pfn - max_dma;
-			zholes_size[ZONE_NORMAL] = ((max_low_pfn - max_dma)
-						    - (num_physpages - num_dma_physpages));
-		}
-	}
-
-	max_gap = 0;
-	efi_memmap_walk(find_largest_hole, (u64 *)&max_gap);
-	if (max_gap < LARGE_GAP) {
-		vmem_map = (struct page *) 0;
-		free_area_init_node(0, &contig_page_data, NULL, zones_size, 0, zholes_size);
-		mem_map = contig_page_data.node_mem_map;
-	}
-	else {
-		unsigned long map_size;
-
-		/* allocate virtual_mem_map */
-
-		map_size = PAGE_ALIGN(max_low_pfn * sizeof(struct page));
-		vmalloc_end -= map_size;
-		vmem_map = (struct page *) vmalloc_end;
-		efi_memmap_walk(create_mem_map_page_table, 0);
-
-		free_area_init_node(0, &contig_page_data, vmem_map, zones_size, 0, zholes_size);
-
-		mem_map = contig_page_data.node_mem_map;
-		printk("Virtual mem_map starts at 0x%p\n", mem_map);
-	}
-#  else /* !CONFIG_VIRTUAL_MEM_MAP */
-	if (max_low_pfn < max_dma)
-		zones_size[ZONE_DMA] = max_low_pfn;
-	else {
-		zones_size[ZONE_DMA] = max_dma;
-		zones_size[ZONE_NORMAL] = max_low_pfn - max_dma;
-	}
-	free_area_init(zones_size);
-#  endif /* !CONFIG_VIRTUAL_MEM_MAP */
-	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
-}
-#endif /* !CONFIG_DISCONTIGMEM */
-
 static int
 count_reserved_pages (u64 start, u64 end, void *arg)
 {

arch/ia64/sn/io/machvec/pci_bus_cvlink.c

@@ -867,6 +867,9 @@ sn_pci_init (void)
 	int i = 0;
 	struct pci_controller *controller;
 
+	if (!ia64_platform_is("sn2"))
+	    return 0;
+
 	/*
 	 * set pci_raw_ops, etc.
 	 */

arch/ia64/sn/io/sn2/ml_SN_intr.c

@@ -285,7 +285,6 @@ static cpuid_t intr_cpu_choose_node(void)
 cpuid_t intr_heuristic(vertex_hdl_t dev, int req_bit, int *resp_bit)
 {
 	cpuid_t		cpuid;
-	cpuid_t		candidate = CPU_NONE;
 	vertex_hdl_t	pconn_vhdl;
 	pcibr_soft_t	pcibr_soft;
 	int 		bit;
@@ -293,30 +292,32 @@ cpuid_t intr_heuristic(vertex_hdl_t dev, int req_bit, int *resp_bit)
 	/* XXX: gross layering violation.. */
 	if (hwgraph_edge_get(dev, EDGE_LBL_PCI, &pconn_vhdl) == GRAPH_SUCCESS) {
 		pcibr_soft = pcibr_soft_get(pconn_vhdl);
-		if (pcibr_soft && pcibr_soft->bsi_err_intr)
-			candidate = ((hub_intr_t)pcibr_soft->bsi_err_intr)->i_cpuid;
-	}
-
-	if (candidate != CPU_NONE) {
-		/*
-		 * The cpu was chosen already when we assigned
-		 * the error interrupt.
-		 */
-		bit = intr_reserve_level(candidate, req_bit);
-		if (bit >= 0) {
-			*resp_bit = bit;
-			return candidate;
+		if (pcibr_soft && pcibr_soft->bsi_err_intr) {
+			/*
+			 * The cpu was chosen already when we assigned
+			 * the error interrupt.
+			 */
+			cpuid = ((hub_intr_t)pcibr_soft->bsi_err_intr)->i_cpuid;
+			goto done;
 		}
-
-		printk("Cannot target interrupt to target node (%ld).\n",candidate);
-		return CPU_NONE;
 	}
 
 	/*
 	 * Need to choose one.  Try the controlling c-brick first.
 	 */
 	cpuid = intr_cpu_choose_from_node(master_node_get(dev));
-	if (cpuid != CPU_NONE)
-		return cpuid;
-	return intr_cpu_choose_node();
+	if (cpuid == CPU_NONE)
+		cpuid = intr_cpu_choose_node();
+
+ done:
+	if (cpuid != CPU_NONE) {
+		bit = intr_reserve_level(cpuid, req_bit);
+		if (bit >= 0) {
+			*resp_bit = bit;
+			return cpuid;
+		}
+	}
+
+	printk("Cannot target interrupt to target cpu (%ld).\n", cpuid);
+	return CPU_NONE;
 }

arch/ia64/sn/kernel/setup.c

@@ -147,7 +147,6 @@ char drive_info[4*16];
  * Sets up an initial console to aid debugging.  Intended primarily
  * for bringup.  See start_kernel() in init/main.c.
  */
-#if defined(CONFIG_IA64_EARLY_PRINTK_SGI_SN) || defined(CONFIG_IA64_SGI_SN_SIM)
 
 void __init
 early_sn_setup(void)
@@ -189,7 +188,6 @@ early_sn_setup(void)
 		printk(KERN_DEBUG "early_sn_setup: setting master_node_bedrock_address to 0x%lx\n", master_node_bedrock_address);
 	}
 }
-#endif /* CONFIG_IA64_EARLY_PRINTK_SGI_SN */
 
 #ifdef CONFIG_IA64_MCA
 extern int platform_intr_list[];

include/asm-ia64/meminit.h

@@ -7,6 +7,8 @@
  * for more details.
  */
 
+#include <linux/config.h>
+
 /*
  * Entries defined so far:
  * 	- boot param structure itself
@@ -32,10 +34,27 @@ extern void reserve_memory (void);
 extern void find_initrd (void);
 extern int filter_rsvd_memory (unsigned long start, unsigned long end, void *arg);
 
+/*
+ * For rounding an address to the next IA64_GRANULE_SIZE or order
+ */
+#define GRANULEROUNDDOWN(n)	((n) & ~(IA64_GRANULE_SIZE-1))
+#define GRANULEROUNDUP(n)	(((n)+IA64_GRANULE_SIZE-1) & ~(IA64_GRANULE_SIZE-1))
+#define ORDERROUNDDOWN(n)	((n) & ~((PAGE_SIZE<<MAX_ORDER)-1))
+
 #ifdef CONFIG_DISCONTIGMEM
-extern void call_pernode_memory (unsigned long start, unsigned long end, void *arg);
+  extern void call_pernode_memory (unsigned long start, unsigned long len, void *func);
+#else
+# define call_pernode_memory(start, len, func)	(*func)(start, len, 0)
 #endif
 
 #define IGNORE_PFN0	1	/* XXX fix me: ignore pfn 0 until TLB miss handler is updated... */
 
+#ifdef CONFIG_VIRTUAL_MEM_MAP
+# define LARGE_GAP	0x40000000 /* Use virtual mem map if hole is > than this */
+  extern unsigned long vmalloc_end;
+  extern struct page *vmem_map;
+  extern int find_largest_hole (u64 start, u64 end, void *arg);
+  extern int create_mem_map_page_table (u64 start, u64 end, void *arg);
+#endif
+
 #endif /* meminit_h */

include/asm-ia64/mmzone.h

@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (c) 2000 Silicon Graphics, Inc.  All rights reserved.
+ * Copyright (c) 2000,2003 Silicon Graphics, Inc.  All rights reserved.
  * Copyright (c) 2002 NEC Corp.
  * Copyright (c) 2002 Erich Focht <efocht@ess.nec.de>
  * Copyright (c) 2002 Kimio Suganuma <k-suganuma@da.jp.nec.com>
@@ -12,148 +12,26 @@
 #define _ASM_IA64_MMZONE_H
 
 #include <linux/config.h>
-#include <linux/init.h>
-
-/*
- * Given a kaddr, find the base mem_map address for the start of the mem_map
- * entries for the bank containing the kaddr.
- */
-#define BANK_MEM_MAP_BASE(kaddr) local_node_data->bank_mem_map_base[BANK_MEM_MAP_INDEX(kaddr)]
-
-/*
- * Given a kaddr, this macro return the relative map number 
- * within the bank.
- */
-#define BANK_MAP_NR(kaddr) 	(BANK_OFFSET(kaddr) >> PAGE_SHIFT)
-
-/*
- * Given a pte, this macro returns a pointer to the page struct for the pte.
- */
-#define pte_page(pte)	virt_to_page(PAGE_OFFSET | (pte_val(pte)&_PFN_MASK))
-
-/*
- * Determine if a kaddr is a valid memory address of memory that
- * actually exists. 
- *
- * The check consists of 2 parts:
- *	- verify that the address is a region 7 address & does not 
- *	  contain any bits that preclude it from being a valid platform
- *	  memory address
- *	- verify that the chunk actually exists.
- *
- * Note that IO addresses are NOT considered valid addresses.
- *
- * Note, many platforms can simply check if kaddr exceeds a specific size.  
- *	(However, this won't work on SGI platforms since IO space is embedded 
- * 	within the range of valid memory addresses & nodes have holes in the 
- *	address range between banks). 
- */
-#define kern_addr_valid(kaddr)		({long _kav=(long)(kaddr);	\
-					VALID_MEM_KADDR(_kav);})
-
-/*
- * Given a kaddr, return a pointer to the page struct for the page.
- * If the kaddr does not represent RAM memory that potentially exists, return
- * a pointer the page struct for max_mapnr. IO addresses will
- * return the page for max_nr. Addresses in unpopulated RAM banks may
- * return undefined results OR may panic the system.
- *
- */
-#define virt_to_page(kaddr)	({long _kvtp=(long)(kaddr);	\
-				(VALID_MEM_KADDR(_kvtp))	\
-					? BANK_MEM_MAP_BASE(_kvtp) + BANK_MAP_NR(_kvtp)	\
-					: NULL;})
-
-/*
- * Given a page struct entry, return the physical address that the page struct represents.
- * Since IA64 has all memory in the DMA zone, the following works:
- */
-#define page_to_phys(page)	__pa(page_address(page))
-
-#define node_mem_map(nid)	(NODE_DATA(nid)->node_mem_map)
-
-#define node_localnr(pfn, nid)	((pfn) - NODE_DATA(nid)->node_start_pfn)
-
-#define pfn_to_page(pfn)	(struct page *)(node_mem_map(pfn_to_nid(pfn)) + node_localnr(pfn, pfn_to_nid(pfn)))
-
-#define pfn_to_nid(pfn)		 local_node_data->node_id_map[(pfn << PAGE_SHIFT) >> BANKSHIFT]
-
-#define page_to_pfn(page)	(long)((page - page_zone(page)->zone_mem_map) + page_zone(page)->zone_start_pfn)
-
-
-/*
- * pfn_valid should be made as fast as possible, and the current definition
- * is valid for machines that are NUMA, but still contiguous, which is what
- * is currently supported. A more generalised, but slower definition would
- * be something like this - mbligh:
- * ( pfn_to_pgdat(pfn) && (pfn < node_end_pfn(pfn_to_nid(pfn))) )
- */
-#define pfn_valid(pfn)          (pfn < max_low_pfn)
-extern unsigned long max_low_pfn;
-
-
-#if defined(CONFIG_IA64_DIG)
-
-/*
- * Platform definitions for DIG platform with contiguous memory.
- */
-#define MAX_PHYSNODE_ID	8		/* Maximum node number +1 */
-#define MAX_PHYS_MEMORY	(1UL << 40)	/* 1 TB */
-
-/*
- * Bank definitions.
- * Configurable settings for DIG: 512MB/bank:  16GB/node,
- *                               2048MB/bank:  64GB/node,
- *                               8192MB/bank: 256GB/node.
- */
-#define NR_BANKS_PER_NODE	32
-#if defined(CONFIG_IA64_NODESIZE_16GB)
-# define BANKSHIFT		29
-#elif defined(CONFIG_IA64_NODESIZE_64GB)
-# define BANKSHIFT		31
-#elif defined(CONFIG_IA64_NODESIZE_256GB)
-# define BANKSHIFT		33
-#else
-# error Unsupported bank and nodesize!
+#include <asm/page.h>
+#include <asm/meminit.h>
+
+#ifdef CONFIG_DISCONTIGMEM
+
+#ifdef CONFIG_IA64_DIG /* DIG systems are small */
+# define MAX_PHYSNODE_ID	8
+# define NR_NODES		8
+# define NR_MEMBLKS		(NR_NODES * 32)
+#else /* sn2 is the biggest case, so we use that if !DIG */
+# define MAX_PHYSNODE_ID	2048
+# define NR_NODES		256
+# define NR_MEMBLKS		(NR_NODES)
 #endif
-#define BANKSIZE		(1UL << BANKSHIFT)
 
-#elif defined(CONFIG_IA64_SGI_SN2)
-
-/*
- * SGI SN2 discontig definitions
- */
-#define MAX_PHYSNODE_ID	2048	/* 2048 node ids (also called nasid) */
-#define MAX_PHYS_MEMORY	(1UL << 49)
-
-#define NR_BANKS_PER_NODE	4
-#define BANKSHIFT		38
-#define SN2_NODE_SIZE		(64UL*1024*1024*1024)	/* 64GB per node */
-#define BANKSIZE		(SN2_NODE_SIZE/NR_BANKS_PER_NODE)
-
-#endif /* CONFIG_IA64_DIG */
-
-#if defined(CONFIG_IA64_DIG) || defined (CONFIG_IA64_SGI_SN2)
-/* Common defines for both platforms */
-#include <asm/numnodes.h>
-#define BANK_OFFSET(addr)	((unsigned long)(addr) & (BANKSIZE-1))
-#define NR_BANKS		(NR_BANKS_PER_NODE * (1 << NODES_SHIFT))
-#define NR_MEMBLKS		(NR_BANKS)
-
-/*
- * VALID_MEM_KADDR returns a boolean to indicate if a kaddr is
- * potentially a valid cacheable identity mapped RAM memory address.
- * Note that the RAM may or may not actually be present!!
- */
-#define VALID_MEM_KADDR(kaddr)	1
-
-/*
- * Given a nodeid & a bank number, find the address of the mem_map
- * entry for the first page of the bank.
- */
-#define BANK_MEM_MAP_INDEX(kaddr) \
-	(((unsigned long)(kaddr) & (MAX_PHYS_MEMORY-1)) >> BANKSHIFT)
+extern unsigned long max_low_pfn;
 
-#endif /* CONFIG_IA64_DIG || CONFIG_IA64_SGI_SN2 */
+#define pfn_valid(pfn)		(((pfn) < max_low_pfn) && ia64_pfn_valid(pfn))
+#define page_to_pfn(page)	((unsigned long) (page - vmem_map))
+#define pfn_to_page(pfn)	(vmem_map + (pfn))
 
+#endif /* CONFIG_DISCONTIGMEM */
 #endif /* _ASM_IA64_MMZONE_H */

include/asm-ia64/nodedata.h

@@ -11,9 +11,14 @@
 #ifndef _ASM_IA64_NODEDATA_H
 #define _ASM_IA64_NODEDATA_H
 
+#include <linux/config.h>
 #include <linux/numa.h>
+
+#include <asm/percpu.h>
 #include <asm/mmzone.h>
 
+#ifdef CONFIG_DISCONTIGMEM
+
 /*
  * Node Data. One of these structures is located on each node of a NUMA system.
  */
@@ -22,10 +27,7 @@ struct pglist_data;
 struct ia64_node_data {
 	short			active_cpu_count;
 	short			node;
-	struct pglist_data	*pg_data_ptrs[MAX_NUMNODES];
-	struct page		*bank_mem_map_base[NR_BANKS];
-	struct ia64_node_data	*node_data_ptrs[MAX_NUMNODES];
-	short			node_id_map[NR_BANKS];
+	struct pglist_data	*pg_data_ptrs[NR_NODES];
 };
 
 
@@ -34,41 +36,17 @@ struct ia64_node_data {
  */
 #define local_node_data		(local_cpu_data->node_data)
 
-
-/*
- * Return a pointer to the node_data structure for the specified node.
- */
-#define node_data(node)	(local_node_data->node_data_ptrs[node])
-
-/*
- * Get a pointer to the node_id/node_data for the current cpu.
- *    (boot time only)
- */
-extern int boot_get_local_nodeid(void);
-extern struct ia64_node_data *get_node_data_ptr(void);
-
 /*
  * Given a node id, return a pointer to the pg_data_t for the node.
- * The following 2 macros are similar. 
  *
  * NODE_DATA 	- should be used in all code not related to system
  *		  initialization. It uses pernode data structures to minimize
  *		  offnode memory references. However, these structure are not 
  *		  present during boot. This macro can be used once cpu_init
  *		  completes.
- *
- * BOOT_NODE_DATA
- *		- should be used during system initialization 
- *		  prior to freeing __initdata. It does not depend on the percpu
- *		  area being present.
- *
- * NOTE:   The names of these macros are misleading but are difficult to change
- *	   since they are used in generic linux & on other architecures.
  */
 #define NODE_DATA(nid)		(local_node_data->pg_data_ptrs[nid])
-#define BOOT_NODE_DATA(nid)	boot_get_pg_data_ptr((long)(nid))
 
-struct pglist_data;
-extern struct pglist_data * __init boot_get_pg_data_ptr(long);
+#endif /* CONFIG_DISCONTIGMEM */
 
 #endif /* _ASM_IA64_NODEDATA_H */

include/asm-ia64/numa.h

@@ -4,7 +4,7 @@
  * for more details.
  *
  * This file contains NUMA specific prototypes and definitions.
- * 
+ *
  * 2002/08/05 Erich Focht <efocht@ess.nec.de>
  *
  */
@@ -12,12 +12,17 @@
 #define _ASM_IA64_NUMA_H
 
 #include <linux/config.h>
-#include <linux/cpumask.h>
 
 #ifdef CONFIG_NUMA
 
-#include <linux/numa.h>
 #include <linux/cache.h>
+#include <linux/cache.h>
+#include <linux/cpumask.h>
+#include <linux/numa.h>
+#include <linux/smp.h>
+#include <linux/threads.h>
+
+#include <asm/mmzone.h>
 
 extern volatile char cpu_to_node_map[NR_CPUS] __cacheline_aligned;
 extern volatile cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned;
@@ -61,6 +66,10 @@ extern int paddr_to_nid(unsigned long paddr);
 
 #define local_nodeid (cpu_to_node_map[smp_processor_id()])
 
+#else /* !CONFIG_NUMA */
+
+#define paddr_to_nid(addr)	0
+
 #endif /* CONFIG_NUMA */
 
 #endif /* _ASM_IA64_NUMA_H */

include/asm-ia64/page.h

@@ -94,18 +94,20 @@ do {						\
 
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 
+#ifdef CONFIG_VIRTUAL_MEM_MAP
+extern int ia64_pfn_valid (unsigned long pfn);
+#else
+# define ia64_pfn_valid(pfn) 1
+#endif
+
 #ifndef CONFIG_DISCONTIGMEM
-# ifdef CONFIG_VIRTUAL_MEM_MAP
-   extern int ia64_pfn_valid (unsigned long pfn);
-#  define pfn_valid(pfn)	(((pfn) < max_mapnr) && ia64_pfn_valid(pfn))
-# else
-#  define pfn_valid(pfn)	((pfn) < max_mapnr)
-# endif
-#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#define pfn_valid(pfn)		(((pfn) < max_mapnr) && ia64_pfn_valid(pfn))
 #define page_to_pfn(page)	((unsigned long) (page - mem_map))
 #define pfn_to_page(pfn)	(mem_map + (pfn))
+#endif /* CONFIG_DISCONTIGMEM */
+
 #define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
-#endif
+#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 
 typedef union ia64_va {
 	struct {

include/asm-ia64/percpu.h

@@ -46,11 +46,13 @@ DECLARE_PER_CPU(unsigned long, local_per_cpu_offset);
 
 extern void percpu_modcopy(void *pcpudst, const void *src, unsigned long size);
 extern void setup_per_cpu_areas (void);
+extern void *per_cpu_init(void);
 
 #else /* ! SMP */
 
 #define per_cpu(var, cpu)			((void)cpu, per_cpu__##var)
 #define __get_cpu_var(var)			per_cpu__##var
+#define per_cpu_init()				(__phys_per_cpu_start)
 
 #endif	/* SMP */
 

include/asm-ia64/pgtable.h

@@ -174,7 +174,6 @@ ia64_phys_addr_valid (unsigned long addr)
 	return (addr & (local_cpu_data->unimpl_pa_mask)) == 0;
 }
 
-#ifndef CONFIG_DISCONTIGMEM
 /*
  * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
  * memory.  For the return value to be meaningful, ADDR must be >=
@@ -190,7 +189,6 @@ ia64_phys_addr_valid (unsigned long addr)
  */
 #define kern_addr_valid(addr)	(1)
 
-#endif
 
 /*
  * Now come the defines and routines to manage and access the three-level
@@ -240,10 +238,8 @@ ia64_phys_addr_valid (unsigned long addr)
 #define pte_none(pte) 			(!pte_val(pte))
 #define pte_present(pte)		(pte_val(pte) & (_PAGE_P | _PAGE_PROTNONE))
 #define pte_clear(pte)			(pte_val(*(pte)) = 0UL)
-#ifndef CONFIG_DISCONTIGMEM
 /* pte_page() returns the "struct page *" corresponding to the PTE: */
 #define pte_page(pte)			virt_to_page(((pte_val(pte) & _PFN_MASK) + PAGE_OFFSET))
-#endif
 
 #define pmd_none(pmd)			(!pmd_val(pmd))
 #define pmd_bad(pmd)			(!ia64_phys_addr_valid(pmd_val(pmd)))

include/asm-ia64/sn/nodepda.h

@@ -128,7 +128,7 @@ typedef struct irqpda_s irqpda_t;
  * Check if given a compact node id the corresponding node has all the
  * cpus disabled. 
  */
-#define is_headless_node(cnode)		(!any_online_cpu(node_to_cpumask(cnode)))
+#define is_headless_node(cnode)		(!node_to_cpu_mask[cnode])
 
 /*
  * Check if given a node vertex handle the corresponding node has all the

include/asm-ia64/uaccess.h

@@ -408,11 +408,7 @@ struct exception_table_entry {
 extern void handle_exception (struct pt_regs *regs, const struct exception_table_entry *e);
 extern const struct exception_table_entry *search_exception_tables (unsigned long addr);
 
-#ifdef GAS_HAS_LOCAL_TAGS
 # define SEARCH_EXCEPTION_TABLE(regs) search_exception_tables(regs->cr_iip + ia64_psr(regs)->ri)
-#else
-# define SEARCH_EXCEPTION_TABLE(regs) search_exception_tables(regs->cr_iip)
-#endif
 
 static inline int
 done_with_exception (struct pt_regs *regs)

include/asm-ia64/unistd.h

@@ -237,17 +237,17 @@
 #define __NR_epoll_wait			1245
 #define __NR_restart_syscall		1246
 #define __NR_semtimedop			1247
-#define __NR_sys_timer_create		1248
-#define __NR_sys_timer_settime		1249
-#define __NR_sys_timer_gettime		1250
-#define __NR_sys_timer_getoverrun	1251
-#define __NR_sys_timer_delete		1252
-#define __NR_sys_clock_settime		1253
-#define __NR_sys_clock_gettime		1254
-#define __NR_sys_clock_getres		1255
-#define __NR_sys_clock_nanosleep	1256
-#define __NR_sys_fstatfs64		1257
-#define __NR_sys_statfs64		1258
+#define __NR_timer_create		1248
+#define __NR_timer_settime		1249
+#define __NR_timer_gettime		1250
+#define __NR_timer_getoverrun		1251
+#define __NR_timer_delete		1252
+#define __NR_clock_settime		1253
+#define __NR_clock_gettime		1254
+#define __NR_clock_getres		1255
+#define __NR_clock_nanosleep		1256
+#define __NR_fstatfs64			1257
+#define __NR_statfs64			1258
 
 #ifdef __KERNEL__