Auto-update from upstream

5 files changed, 139 insertions, 120 deletions

diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 58c93a30348c..6ea642beaaee 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -68,8 +68,6 @@ EXPORT_SYMBOL(pm_power_off);
 unsigned char acpi_kbd_controller_present = 1;
 unsigned char acpi_legacy_devices;
 
-static unsigned int __initdata acpi_madt_rev;
-
 unsigned int acpi_cpei_override;
 unsigned int acpi_cpei_phys_cpuid;
 
@@ -243,6 +241,8 @@ acpi_parse_iosapic(acpi_table_entry_header * header, const unsigned long end)
 	return iosapic_init(iosapic->address, iosapic->global_irq_base);
 }
 
+static unsigned int __initdata acpi_madt_rev;
+
 static int __init
 acpi_parse_plat_int_src(acpi_table_entry_header * header,
 			const unsigned long end)
@@ -415,9 +415,6 @@ static int __initdata srat_num_cpus;	/* number of cpus */
 static u32 __devinitdata pxm_flag[PXM_FLAG_LEN];
 #define pxm_bit_set(bit)	(set_bit(bit,(void *)pxm_flag))
 #define pxm_bit_test(bit)	(test_bit(bit,(void *)pxm_flag))
-/* maps to convert between proximity domain and logical node ID */
-int __devinitdata pxm_to_nid_map[MAX_PXM_DOMAINS];
-int __initdata nid_to_pxm_map[MAX_NUMNODES];
 static struct acpi_table_slit __initdata *slit_table;
 
 static int get_processor_proximity_domain(struct acpi_table_processor_affinity *pa)
@@ -533,22 +530,17 @@ void __init acpi_numa_arch_fixup(void)
 	 * MCD - This can probably be dropped now.  No need for pxm ID to node ID
 	 * mapping with sparse node numbering iff MAX_PXM_DOMAINS <= MAX_NUMNODES.
 	 */
-	/* calculate total number of nodes in system from PXM bitmap */
-	memset(pxm_to_nid_map, -1, sizeof(pxm_to_nid_map));
-	memset(nid_to_pxm_map, -1, sizeof(nid_to_pxm_map));
 	nodes_clear(node_online_map);
 	for (i = 0; i < MAX_PXM_DOMAINS; i++) {
 		if (pxm_bit_test(i)) {
-			int nid = num_online_nodes();
-			pxm_to_nid_map[i] = nid;
-			nid_to_pxm_map[nid] = i;
+			int nid = acpi_map_pxm_to_node(i);
 			node_set_online(nid);
 		}
 	}
 
 	/* set logical node id in memory chunk structure */
 	for (i = 0; i < num_node_memblks; i++)
-		node_memblk[i].nid = pxm_to_nid_map[node_memblk[i].nid];
+		node_memblk[i].nid = pxm_to_node(node_memblk[i].nid);
 
 	/* assign memory bank numbers for each chunk on each node */
 	for_each_online_node(i) {
@@ -562,7 +554,7 @@ void __init acpi_numa_arch_fixup(void)
 
 	/* set logical node id in cpu structure */
 	for (i = 0; i < srat_num_cpus; i++)
-		node_cpuid[i].nid = pxm_to_nid_map[node_cpuid[i].nid];
+		node_cpuid[i].nid = pxm_to_node(node_cpuid[i].nid);
 
 	printk(KERN_INFO "Number of logical nodes in system = %d\n",
 	       num_online_nodes());
@@ -575,11 +567,11 @@ void __init acpi_numa_arch_fixup(void)
 	for (i = 0; i < slit_table->localities; i++) {
 		if (!pxm_bit_test(i))
 			continue;
-		node_from = pxm_to_nid_map[i];
+		node_from = pxm_to_node(i);
 		for (j = 0; j < slit_table->localities; j++) {
 			if (!pxm_bit_test(j))
 				continue;
-			node_to = pxm_to_nid_map[j];
+			node_to = pxm_to_node(j);
 			node_distance(node_from, node_to) =
 			    slit_table->entry[i * slit_table->localities + j];
 		}
@@ -785,9 +777,9 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, long physid)
 
 	/*
 	 * Assuming that the container driver would have set the proximity
-	 * domain and would have initialized pxm_to_nid_map[pxm_id] && pxm_flag
+	 * domain and would have initialized pxm_to_node(pxm_id) && pxm_flag
 	 */
-	node_cpuid[cpu].nid = (pxm_id < 0) ? 0 : pxm_to_nid_map[pxm_id];
+	node_cpuid[cpu].nid = (pxm_id < 0) ? 0 : pxm_to_node(pxm_id);
 
 	node_cpuid[cpu].phys_id = physid;
 #endif
@@ -966,7 +958,7 @@ acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret)
 	if (pxm < 0)
 		return AE_OK;
 
-	node = pxm_to_nid_map[pxm];
+	node = pxm_to_node(pxm);
 
 	if (node >= MAX_NUMNODES || !node_online(node) ||
 	    cpus_empty(node_to_cpumask(node)))
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index bcb80ca5cf40..32c999f58d12 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1584,7 +1584,7 @@ sys_call_table:
 	data8 sys_keyctl
 	data8 sys_ioprio_set
 	data8 sys_ioprio_get			// 1275
-	data8 sys_ni_syscall
+	data8 sys_move_pages
 	data8 sys_inotify_init
 	data8 sys_inotify_add_watch
 	data8 sys_inotify_rm_watch
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 6c4d59fd0364..ef9a2b49307a 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -46,6 +46,10 @@
 
 #define IRQ_DEBUG	0
 
+/* These can be overridden in platform_irq_init */
+int ia64_first_device_vector = IA64_DEF_FIRST_DEVICE_VECTOR;
+int ia64_last_device_vector = IA64_DEF_LAST_DEVICE_VECTOR;
+
 /* default base addr of IPI table */
 void __iomem *ipi_base_addr = ((void __iomem *)
 			       (__IA64_UNCACHED_OFFSET | IA64_IPI_DEFAULT_BASE_ADDR));
@@ -60,7 +64,7 @@ __u8 isa_irq_to_vector_map[16] = {
 };
 EXPORT_SYMBOL(isa_irq_to_vector_map);
 
-static unsigned long ia64_vector_mask[BITS_TO_LONGS(IA64_NUM_DEVICE_VECTORS)];
+static unsigned long ia64_vector_mask[BITS_TO_LONGS(IA64_MAX_DEVICE_VECTORS)];
 
 int
 assign_irq_vector (int irq)
@@ -89,6 +93,19 @@ free_irq_vector (int vector)
 		printk(KERN_WARNING "%s: double free!\n", __FUNCTION__);
 }
 
+int
+reserve_irq_vector (int vector)
+{
+	int pos;
+
+	if (vector < IA64_FIRST_DEVICE_VECTOR ||
+	    vector > IA64_LAST_DEVICE_VECTOR)
+		return -EINVAL;
+
+	pos = vector - IA64_FIRST_DEVICE_VECTOR;
+	return test_and_set_bit(pos, ia64_vector_mask);
+}
+
 #ifdef CONFIG_SMP
 #	define IS_RESCHEDULE(vec)	(vec == IA64_IPI_RESCHEDULE)
 #else
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 077f21216b65..6d7bc8ff7b3a 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -532,7 +532,6 @@ static ctl_table pfm_sysctl_root[] = {
 static struct ctl_table_header *pfm_sysctl_header;
 
 static int pfm_context_unload(pfm_context_t *ctx, void *arg, int count, struct pt_regs *regs);
-static int pfm_flush(struct file *filp);
 
 #define pfm_get_cpu_var(v)		__ia64_per_cpu_var(v)
 #define pfm_get_cpu_data(a,b)		per_cpu(a, b)
@@ -595,10 +594,11 @@ pfm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 }
 
 
-static struct super_block *
-pfmfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data)
+static int
+pfmfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data,
+	     struct vfsmount *mnt)
 {
-	return get_sb_pseudo(fs_type, "pfm:", NULL, PFMFS_MAGIC);
+	return get_sb_pseudo(fs_type, "pfm:", NULL, PFMFS_MAGIC, mnt);
 }
 
 static struct file_system_type pfm_fs_type = {
@@ -1773,7 +1773,7 @@ pfm_syswide_cleanup_other_cpu(pfm_context_t *ctx)
  * When caller is self-monitoring, the context is unloaded.
  */
 static int
-pfm_flush(struct file *filp)
+pfm_flush(struct file *filp, fl_owner_t id)
 {
 	pfm_context_t *ctx;
 	struct task_struct *task;
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index fcd2bad0286f..5f03b9e524dd 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2001-2005 Silicon Graphics, Inc.  All rights reserved.
+ * Copyright (C) 2001-2006 Silicon Graphics, Inc.  All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of version 2 of the GNU General Public License
@@ -29,15 +29,8 @@
 #include <asm/tlbflush.h>
 #include <asm/sn/arch.h>
 
-#define DEBUG	0
 
-#if DEBUG
-#define dprintk			printk
-#else
-#define dprintk(x...)		do { } while (0)
-#endif
-
-void __init efi_memmap_walk_uc (efi_freemem_callback_t callback);
+extern void __init efi_memmap_walk_uc(efi_freemem_callback_t, void *);
 
 #define MAX_UNCACHED_GRANULES	5
 static int allocated_granules;
@@ -60,6 +53,7 @@ static void uncached_ipi_visibility(void *data)
 static void uncached_ipi_mc_drain(void *data)
 {
 	int status;
+
 	status = ia64_pal_mc_drain();
 	if (status)
 		printk(KERN_WARNING "ia64_pal_mc_drain() failed with %i on "
@@ -67,30 +61,35 @@ static void uncached_ipi_mc_drain(void *data)
 }
 
 
-static unsigned long
-uncached_get_new_chunk(struct gen_pool *poolp)
+/*
+ * Add a new chunk of uncached memory pages to the specified pool.
+ *
+ * @pool: pool to add new chunk of uncached memory to
+ * @nid: node id of node to allocate memory from, or -1
+ *
+ * This is accomplished by first allocating a granule of cached memory pages
+ * and then converting them to uncached memory pages.
+ */
+static int uncached_add_chunk(struct gen_pool *pool, int nid)
 {
 	struct page *page;
-	void *tmp;
 	int status, i;
-	unsigned long addr, node;
+	unsigned long c_addr, uc_addr;
 
 	if (allocated_granules >= MAX_UNCACHED_GRANULES)
-		return 0;
+		return -1;
+
+	/* attempt to allocate a granule's worth of cached memory pages */
 
-	node = poolp->private;
-	page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO,
+	page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO,
 				IA64_GRANULE_SHIFT-PAGE_SHIFT);
+	if (!page)
+		return -1;
 
-	dprintk(KERN_INFO "get_new_chunk page %p, addr %lx\n",
-		page, (unsigned long)(page-vmem_map) << PAGE_SHIFT);
+	/* convert the memory pages from cached to uncached */
 
-	/*
-	 * Do magic if no mem on local node! XXX
-	 */
-	if (!page)
-		return 0;
-	tmp = page_address(page);
+	c_addr = (unsigned long)page_address(page);
+	uc_addr = c_addr - PAGE_OFFSET + __IA64_UNCACHED_OFFSET;
 
 	/*
 	 * There's a small race here where it's possible for someone to
@@ -100,76 +99,90 @@ uncached_get_new_chunk(struct gen_pool *poolp)
 	for (i = 0; i < (IA64_GRANULE_SIZE / PAGE_SIZE); i++)
 		SetPageUncached(&page[i]);
 
-	flush_tlb_kernel_range(tmp, tmp + IA64_GRANULE_SIZE);
+	flush_tlb_kernel_range(uc_addr, uc_adddr + IA64_GRANULE_SIZE);
 
 	status = ia64_pal_prefetch_visibility(PAL_VISIBILITY_PHYSICAL);
-
-	dprintk(KERN_INFO "pal_prefetch_visibility() returns %i on cpu %i\n",
-		status, raw_smp_processor_id());
-
 	if (!status) {
 		status = smp_call_function(uncached_ipi_visibility, NULL, 0, 1);
 		if (status)
-			printk(KERN_WARNING "smp_call_function failed for "
-			       "uncached_ipi_visibility! (%i)\n", status);
+			goto failed;
 	}
 
+	preempt_disable();
+
 	if (ia64_platform_is("sn2"))
-		sn_flush_all_caches((unsigned long)tmp, IA64_GRANULE_SIZE);
+		sn_flush_all_caches(uc_addr, IA64_GRANULE_SIZE);
 	else
-		flush_icache_range((unsigned long)tmp,
-				   (unsigned long)tmp+IA64_GRANULE_SIZE);
+		flush_icache_range(uc_addr, uc_addr + IA64_GRANULE_SIZE);
+
+	/* flush the just introduced uncached translation from the TLB */
+	local_flush_tlb_all();
+
+	preempt_enable();
 
 	ia64_pal_mc_drain();
 	status = smp_call_function(uncached_ipi_mc_drain, NULL, 0, 1);
 	if (status)
-		printk(KERN_WARNING "smp_call_function failed for "
-		       "uncached_ipi_mc_drain! (%i)\n", status);
+		goto failed;
 
-	addr = (unsigned long)tmp - PAGE_OFFSET + __IA64_UNCACHED_OFFSET;
+	/*
+	 * The chunk of memory pages has been converted to uncached so now we
+	 * can add it to the pool.
+	 */
+	status = gen_pool_add(pool, uc_addr, IA64_GRANULE_SIZE, nid);
+	if (status)
+		goto failed;
 
 	allocated_granules++;
-	return addr;
+	return 0;
+
+	/* failed to convert or add the chunk so give it back to the kernel */
+failed:
+	for (i = 0; i < (IA64_GRANULE_SIZE / PAGE_SIZE); i++)
+		ClearPageUncached(&page[i]);
+
+	free_pages(c_addr, IA64_GRANULE_SHIFT-PAGE_SHIFT);
+	return -1;
 }
 
 
 /*
  * uncached_alloc_page
  *
+ * @starting_nid: node id of node to start with, or -1
+ *
  * Allocate 1 uncached page. Allocates on the requested node. If no
  * uncached pages are available on the requested node, roundrobin starting
- * with higher nodes.
+ * with the next higher node.
  */
-unsigned long
-uncached_alloc_page(int nid)
+unsigned long uncached_alloc_page(int starting_nid)
 {
-	unsigned long maddr;
+	unsigned long uc_addr;
+	struct gen_pool *pool;
+	int nid;
 
-	maddr = gen_pool_alloc(uncached_pool[nid], PAGE_SIZE);
+	if (unlikely(starting_nid >= MAX_NUMNODES))
+		return 0;
 
-	dprintk(KERN_DEBUG "uncached_alloc_page returns %lx on node %i\n",
-		maddr, nid);
+	if (starting_nid < 0)
+		starting_nid = numa_node_id();
+	nid = starting_nid;
 
-	/*
-	 * If no memory is availble on our local node, try the
-	 * remaining nodes in the system.
-	 */
-	if (!maddr) {
-		int i;
-
-		for (i = MAX_NUMNODES - 1; i >= 0; i--) {
-			if (i == nid || !node_online(i))
-				continue;
-			maddr = gen_pool_alloc(uncached_pool[i], PAGE_SIZE);
-			dprintk(KERN_DEBUG "uncached_alloc_page alternate search "
-				"returns %lx on node %i\n", maddr, i);
-			if (maddr) {
-				break;
-			}
-		}
-	}
+	do {
+		if (!node_online(nid))
+			continue;
+		pool = uncached_pool[nid];
+		if (pool == NULL)
+			continue;
+		do {
+			uc_addr = gen_pool_alloc(pool, PAGE_SIZE);
+			if (uc_addr != 0)
+				return uc_addr;
+		} while (uncached_add_chunk(pool, nid) == 0);
+
+	} while ((nid = (nid + 1) % MAX_NUMNODES) != starting_nid);
 
-	return maddr;
+	return 0;
 }
 EXPORT_SYMBOL(uncached_alloc_page);
 
@@ -177,21 +190,22 @@ EXPORT_SYMBOL(uncached_alloc_page);
 /*
  * uncached_free_page
  *
+ * @uc_addr: uncached address of page to free
+ *
  * Free a single uncached page.
  */
-void
-uncached_free_page(unsigned long maddr)
+void uncached_free_page(unsigned long uc_addr)
 {
-	int node;
-
-	node = paddr_to_nid(maddr - __IA64_UNCACHED_OFFSET);
+	int nid = paddr_to_nid(uc_addr - __IA64_UNCACHED_OFFSET);
+	struct gen_pool *pool = uncached_pool[nid];
 
-	dprintk(KERN_DEBUG "uncached_free_page(%lx) on node %i\n", maddr, node);
+	if (unlikely(pool == NULL))
+		return;
 
-	if ((maddr & (0XFUL << 60)) != __IA64_UNCACHED_OFFSET)
-		panic("uncached_free_page invalid address %lx\n", maddr);
+	if ((uc_addr & (0XFUL << 60)) != __IA64_UNCACHED_OFFSET)
+		panic("uncached_free_page invalid address %lx\n", uc_addr);
 
-	gen_pool_free(uncached_pool[node], maddr, PAGE_SIZE);
+	gen_pool_free(pool, uc_addr, PAGE_SIZE);
 }
 EXPORT_SYMBOL(uncached_free_page);
 
@@ -199,43 +213,39 @@ EXPORT_SYMBOL(uncached_free_page);
 /*
  * uncached_build_memmap,
  *
+ * @uc_start: uncached starting address of a chunk of uncached memory
+ * @uc_end: uncached ending address of a chunk of uncached memory
+ * @arg: ignored, (NULL argument passed in on call to efi_memmap_walk_uc())
+ *
  * Called at boot time to build a map of pages that can be used for
  * memory special operations.
  */
-static int __init
-uncached_build_memmap(unsigned long start, unsigned long end, void *arg)
+static int __init uncached_build_memmap(unsigned long uc_start,
+					unsigned long uc_end, void *arg)
 {
-	long length = end - start;
-	int node;
-
-	dprintk(KERN_ERR "uncached_build_memmap(%lx %lx)\n", start, end);
+	int nid = paddr_to_nid(uc_start - __IA64_UNCACHED_OFFSET);
+	struct gen_pool *pool = uncached_pool[nid];
+	size_t size = uc_end - uc_start;
 
 	touch_softlockup_watchdog();
-	memset((char *)start, 0, length);
 
-	node = paddr_to_nid(start - __IA64_UNCACHED_OFFSET);
-
-	for (; start < end ; start += PAGE_SIZE) {
-		dprintk(KERN_INFO "sticking %lx into the pool!\n", start);
-		gen_pool_free(uncached_pool[node], start, PAGE_SIZE);
+	if (pool != NULL) {
+		memset((char *)uc_start, 0, size);
+		(void) gen_pool_add(pool, uc_start, size, nid);
 	}
-
 	return 0;
 }
 
 
-static int __init uncached_init(void) {
-	int i;
+static int __init uncached_init(void)
+{
+	int nid;
 
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		if (!node_online(i))
-			continue;
-		uncached_pool[i] = gen_pool_create(0, IA64_GRANULE_SHIFT,
-						   &uncached_get_new_chunk, i);
+	for_each_online_node(nid) {
+		uncached_pool[nid] = gen_pool_create(PAGE_SHIFT, nid);
 	}
 
-	efi_memmap_walk_uc(uncached_build_memmap);
-
+	efi_memmap_walk_uc(uncached_build_memmap, NULL);
 	return 0;
 }