24 files changed, 187 insertions, 298 deletions

diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c
index 3d79ce281b67..0a0a0487b334 100644
--- a/arch/powerpc/mm/44x_mmu.c
+++ b/arch/powerpc/mm/44x_mmu.c
@@ -24,7 +24,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -104,7 +103,7 @@ unsigned long __init mmu_mapin_ram(void)
 
 	/* Determine number of entries necessary to cover lowmem */
 	pinned_tlbs = (unsigned int)
-		(_ALIGN(total_lowmem, PPC44x_PIN_SIZE) >> PPC44x_PIN_SHIFT);
+		(_ALIGN(total_lowmem, PPC_PIN_SIZE) >> PPC44x_PIN_SHIFT);
 
 	/* Write upper watermark to save location */
 	tlb_44x_hwater = PPC44x_LOW_SLOT - pinned_tlbs;
@@ -112,7 +111,7 @@ unsigned long __init mmu_mapin_ram(void)
 	/* If necessary, set additional pinned TLBs */
 	if (pinned_tlbs > 1)
 		for (i = (PPC44x_LOW_SLOT-(pinned_tlbs-1)); i < PPC44x_LOW_SLOT; i++) {
-			unsigned int phys_addr = (PPC44x_LOW_SLOT-i) * PPC44x_PIN_SIZE;
+			unsigned int phys_addr = (PPC44x_LOW_SLOT-i) * PPC_PIN_SIZE;
 			ppc44x_pin_tlb(i, phys_addr+PAGE_OFFSET, phys_addr);
 		}
 
diff --git a/arch/powerpc/mm/4xx_mmu.c b/arch/powerpc/mm/4xx_mmu.c
index 4d006aa1a0d1..838e09db71d9 100644
--- a/arch/powerpc/mm/4xx_mmu.c
+++ b/arch/powerpc/mm/4xx_mmu.c
@@ -21,7 +21,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index fdbba4206d59..e8fa50624b70 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -15,7 +15,6 @@
  *  2 of the License, or (at your option) any later version.
  */
 
-#include <linux/config.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -40,6 +39,40 @@
 #include <asm/kdebug.h>
 #include <asm/siginfo.h>
 
+#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)
+{
+	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
+
 /*
  * Check whether the instruction at regs->nip is a store using
  * an update addressing form which will update r1.
@@ -142,7 +175,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	is_write = error_code & ESR_DST;
 #endif /* CONFIG_4xx || CONFIG_BOOKE */
 
-	if (notify_die(DIE_PAGE_FAULT, "page_fault", regs, error_code,
+	if (notify_page_fault(DIE_PAGE_FAULT, "page_fault", regs, error_code,
 				11, SIGSEGV) == NOTIFY_STOP)
 		return 0;
 
@@ -300,7 +333,7 @@ good_area:
 		/* protection fault */
 		if (error_code & 0x08000000)
 			goto bad_area;
-		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
 			goto bad_area;
 	}
 
@@ -353,7 +386,7 @@ bad_area_nosemaphore:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 5d581bb3aa12..123da03ab118 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -26,7 +26,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 94255beeecd3..bd68df5fa78a 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -21,7 +21,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <asm/reg.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 52e914238959..9bc0a9c2b9bc 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -10,7 +10,6 @@
  * described in the kernel's COPYING file.
  */
 
-#include <linux/config.h>
 #include <asm/reg.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index a0f3cbd00d39..c90f124f3c71 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -520,7 +520,7 @@ static inline int tlb_batching_enabled(void)
 }
 #endif
 
-void hpte_init_native(void)
+void __init hpte_init_native(void)
 {
 	ppc_md.hpte_invalidate	= native_hpte_invalidate;
 	ppc_md.hpte_updatepp	= native_hpte_updatepp;
@@ -530,5 +530,4 @@ void hpte_init_native(void)
 	ppc_md.hpte_clear_all	= native_hpte_clear;
 	if (tlb_batching_enabled())
 		ppc_md.flush_hash_range = native_flush_hash_range;
-	htab_finish_init();
 }
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index d03fd2b4445e..1915661c2c81 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -21,7 +21,6 @@
 #undef DEBUG
 #undef DEBUG_LOW
 
-#include <linux/config.h>
 #include <linux/spinlock.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -167,34 +166,12 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		hash = hpt_hash(va, shift);
 		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
-		/* The crap below can be cleaned once ppd_md.probe() can
-		 * set up the hash callbacks, thus we can just used the
-		 * normal insert callback here.
-		 */
-#ifdef CONFIG_PPC_ISERIES
-		if (machine_is(iseries))
-			ret = iSeries_hpte_insert(hpteg, va,
-						  paddr,
-						  tmp_mode,
-						  HPTE_V_BOLTED,
-						  psize);
-		else
-#endif
-#ifdef CONFIG_PPC_PSERIES
-		if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR))
-			ret = pSeries_lpar_hpte_insert(hpteg, va,
-						       paddr,
-						       tmp_mode,
-						       HPTE_V_BOLTED,
-						       psize);
-		else
-#endif
-#ifdef CONFIG_PPC_MULTIPLATFORM
-			ret = native_hpte_insert(hpteg, va,
-						 paddr,
-						 tmp_mode, HPTE_V_BOLTED,
-						 psize);
-#endif
+		DBG("htab_bolt_mapping: calling %p\n", ppc_md.hpte_insert);
+
+		BUG_ON(!ppc_md.hpte_insert);
+		ret = ppc_md.hpte_insert(hpteg, va, paddr,
+				tmp_mode, HPTE_V_BOLTED, psize);
+
 		if (ret < 0)
 			break;
 	}
@@ -413,6 +390,41 @@ void create_section_mapping(unsigned long start, unsigned long end)
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
+static inline void make_bl(unsigned int *insn_addr, void *func)
+{
+	unsigned long funcp = *((unsigned long *)func);
+	int offset = funcp - (unsigned long)insn_addr;
+
+	*insn_addr = (unsigned int)(0x48000001 | (offset & 0x03fffffc));
+	flush_icache_range((unsigned long)insn_addr, 4+
+			   (unsigned long)insn_addr);
+}
+
+static void __init htab_finish_init(void)
+{
+	extern unsigned int *htab_call_hpte_insert1;
+	extern unsigned int *htab_call_hpte_insert2;
+	extern unsigned int *htab_call_hpte_remove;
+	extern unsigned int *htab_call_hpte_updatepp;
+
+#ifdef CONFIG_PPC_64K_PAGES
+	extern unsigned int *ht64_call_hpte_insert1;
+	extern unsigned int *ht64_call_hpte_insert2;
+	extern unsigned int *ht64_call_hpte_remove;
+	extern unsigned int *ht64_call_hpte_updatepp;
+
+	make_bl(ht64_call_hpte_insert1, ppc_md.hpte_insert);
+	make_bl(ht64_call_hpte_insert2, ppc_md.hpte_insert);
+	make_bl(ht64_call_hpte_remove, ppc_md.hpte_remove);
+	make_bl(ht64_call_hpte_updatepp, ppc_md.hpte_updatepp);
+#endif /* CONFIG_PPC_64K_PAGES */
+
+	make_bl(htab_call_hpte_insert1, ppc_md.hpte_insert);
+	make_bl(htab_call_hpte_insert2, ppc_md.hpte_insert);
+	make_bl(htab_call_hpte_remove, ppc_md.hpte_remove);
+	make_bl(htab_call_hpte_updatepp, ppc_md.hpte_updatepp);
+}
+
 void __init htab_initialize(void)
 {
 	unsigned long table;
@@ -525,6 +537,8 @@ void __init htab_initialize(void)
 					 mmu_linear_psize));
 	}
 
+	htab_finish_init();
+
 	DBG(" <- htab_initialize()\n");
 }
 #undef KB
@@ -787,16 +801,6 @@ void flush_hash_range(unsigned long number, int local)
 	}
 }
 
-static inline void make_bl(unsigned int *insn_addr, void *func)
-{
-	unsigned long funcp = *((unsigned long *)func);
-	int offset = funcp - (unsigned long)insn_addr;
-
-	*insn_addr = (unsigned int)(0x48000001 | (offset & 0x03fffffc));
-	flush_icache_range((unsigned long)insn_addr, 4+
-			   (unsigned long)insn_addr);
-}
-
 /*
  * low_hash_fault is called when we the low level hash code failed
  * to instert a PTE due to an hypervisor error
@@ -815,28 +819,3 @@ void low_hash_fault(struct pt_regs *regs, unsigned long address)
 	}
 	bad_page_fault(regs, address, SIGBUS);
 }
-
-void __init htab_finish_init(void)
-{
-	extern unsigned int *htab_call_hpte_insert1;
-	extern unsigned int *htab_call_hpte_insert2;
-	extern unsigned int *htab_call_hpte_remove;
-	extern unsigned int *htab_call_hpte_updatepp;
-
-#ifdef CONFIG_PPC_64K_PAGES
-	extern unsigned int *ht64_call_hpte_insert1;
-	extern unsigned int *ht64_call_hpte_insert2;
-	extern unsigned int *ht64_call_hpte_remove;
-	extern unsigned int *ht64_call_hpte_updatepp;
-
-	make_bl(ht64_call_hpte_insert1, ppc_md.hpte_insert);
-	make_bl(ht64_call_hpte_insert2, ppc_md.hpte_insert);
-	make_bl(ht64_call_hpte_remove, ppc_md.hpte_remove);
-	make_bl(ht64_call_hpte_updatepp, ppc_md.hpte_updatepp);
-#endif /* CONFIG_PPC_64K_PAGES */
-
-	make_bl(htab_call_hpte_insert1, ppc_md.hpte_insert);
-	make_bl(htab_call_hpte_insert2, ppc_md.hpte_insert);
-	make_bl(htab_call_hpte_remove, ppc_md.hpte_remove);
-	make_bl(htab_call_hpte_updatepp, ppc_md.hpte_updatepp);
-}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 266b8b2ceac9..5615acc29527 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -153,7 +153,7 @@ static void free_hugepte_range(struct mmu_gather *tlb, hugepd_t *hpdp)
 	hpdp->pd = 0;
 	tlb->need_flush = 1;
 	pgtable_free_tlb(tlb, pgtable_free_cache(hugepte, HUGEPTE_CACHE_NUM,
-						 HUGEPTE_TABLE_SIZE-1));
+						 PGF_CACHENUM_MASK));
 }
 
 #ifdef CONFIG_PPC_64K_PAGES
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index b57fb3a2b7bb..0e53ca8f02fb 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -18,7 +18,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 9e30f968c184..3ff374697e34 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -22,7 +22,6 @@
 
 #undef DEBUG
 
-#include <linux/config.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -41,6 +40,7 @@
 #include <linux/idr.h>
 #include <linux/nodemask.h>
 #include <linux/module.h>
+#include <linux/poison.h>
 
 #include <asm/pgalloc.h>
 #include <asm/page.h>
@@ -90,7 +90,7 @@ void free_initmem(void)
 
 	addr = (unsigned long)__init_begin;
 	for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
-		memset((void *)addr, 0xcc, PAGE_SIZE);
+		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
 		free_page(addr);
diff --git a/arch/powerpc/mm/lmb.c b/arch/powerpc/mm/lmb.c
index 8b6f522655a6..716a2906a24d 100644
--- a/arch/powerpc/mm/lmb.c
+++ b/arch/powerpc/mm/lmb.c
@@ -10,7 +10,6 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-#include <linux/config.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
@@ -321,7 +320,8 @@ void __init lmb_enforce_memory_limit(unsigned long memory_limit)
 		break;
 	}
 
-	lmb.rmo_size = lmb.memory.region[0].size;
+	if (lmb.memory.region[0].size < lmb.rmo_size)
+		lmb.rmo_size = lmb.memory.region[0].size;
 
 	/* And truncate any reserves above the limit also. */
 	for (i = 0; i < lmb.reserved.cnt; i++) {
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 69f3b9a20beb..16fe027bbc12 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -18,7 +18,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -114,15 +113,20 @@ void online_page(struct page *page)
 	num_physpages++;
 }
 
-int __devinit add_memory(u64 start, u64 size)
+#ifdef CONFIG_NUMA
+int memory_add_physaddr_to_nid(u64 start)
+{
+	return hot_add_scn_to_nid(start);
+}
+#endif
+
+int __devinit arch_add_memory(int nid, u64 start, u64 size)
 {
 	struct pglist_data *pgdata;
 	struct zone *zone;
-	int nid;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	nid = hot_add_scn_to_nid(start);
 	pgdata = NODE_DATA(nid);
 
 	start = (unsigned long)__va(start);
@@ -252,20 +256,22 @@ void __init do_init_bootmem(void)
 
 	boot_mapsize = init_bootmem(start >> PAGE_SHIFT, total_pages);
 
+	/* Add active regions with valid PFNs */
+	for (i = 0; i < lmb.memory.cnt; i++) {
+		unsigned long start_pfn, end_pfn;
+		start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT;
+		end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i);
+		add_active_range(0, start_pfn, end_pfn);
+	}
+
 	/* Add all physical memory to the bootmem map, mark each area
 	 * present.
 	 */
-	for (i = 0; i < lmb.memory.cnt; i++) {
-		unsigned long base = lmb.memory.region[i].base;
-		unsigned long size = lmb_size_bytes(&lmb.memory, i);
 #ifdef CONFIG_HIGHMEM
-		if (base >= total_lowmem)
-			continue;
-		if (base + size > total_lowmem)
-			size = total_lowmem - base;
+	free_bootmem_with_active_regions(0, total_lowmem >> PAGE_SHIFT);
+#else
+	free_bootmem_with_active_regions(0, max_pfn);
 #endif
-		free_bootmem(base, size);
-	}
 
 	/* reserve the sections we're already using */
 	for (i = 0; i < lmb.reserved.cnt; i++)
@@ -273,9 +279,8 @@ void __init do_init_bootmem(void)
 				lmb_size_bytes(&lmb.reserved, i));
 
 	/* XXX need to clip this if using highmem? */
-	for (i = 0; i < lmb.memory.cnt; i++)
-		memory_present(0, lmb_start_pfn(&lmb.memory, i),
-			       lmb_end_pfn(&lmb.memory, i));
+	sparse_memory_present_with_active_regions(0);
+
 	init_bootmem_done = 1;
 }
 
@@ -284,10 +289,9 @@ void __init do_init_bootmem(void)
  */
 void __init paging_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES];
-	unsigned long zholes_size[MAX_NR_ZONES];
 	unsigned long total_ram = lmb_phys_mem_size();
 	unsigned long top_of_ram = lmb_end_of_DRAM();
+	unsigned long max_zone_pfns[MAX_NR_ZONES];
 
 #ifdef CONFIG_HIGHMEM
 	map_page(PKMAP_BASE, 0, 0);	/* XXX gross */
@@ -303,26 +307,13 @@ void __init paging_init(void)
 	       top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
-	/*
-	 * All pages are DMA-able so we put them all in the DMA zone.
-	 */
-	memset(zones_size, 0, sizeof(zones_size));
-	memset(zholes_size, 0, sizeof(zholes_size));
-
-	zones_size[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
-	zholes_size[ZONE_DMA] = (top_of_ram - total_ram) >> PAGE_SHIFT;
-
 #ifdef CONFIG_HIGHMEM
-	zones_size[ZONE_DMA] = total_lowmem >> PAGE_SHIFT;
-	zones_size[ZONE_HIGHMEM] = (total_memory - total_lowmem) >> PAGE_SHIFT;
-	zholes_size[ZONE_HIGHMEM] = (top_of_ram - total_ram) >> PAGE_SHIFT;
+	max_zone_pfns[0] = total_lowmem >> PAGE_SHIFT;
+	max_zone_pfns[1] = top_of_ram >> PAGE_SHIFT;
 #else
-	zones_size[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
-	zholes_size[ZONE_DMA] = (top_of_ram - total_ram) >> PAGE_SHIFT;
-#endif /* CONFIG_HIGHMEM */
-
-	free_area_init_node(0, NODE_DATA(0), zones_size,
-			    __pa(PAGE_OFFSET) >> PAGE_SHIFT, zholes_size);
+	max_zone_pfns[0] = top_of_ram >> PAGE_SHIFT;
+#endif
+	free_area_init_nodes(max_zone_pfns);
 }
 #endif /* ! CONFIG_NEED_MULTIPLE_NODES */
 
diff --git a/arch/powerpc/mm/mmu_context_32.c b/arch/powerpc/mm/mmu_context_32.c
index e326e4249e1a..792086b01000 100644
--- a/arch/powerpc/mm/mmu_context_32.c
+++ b/arch/powerpc/mm/mmu_context_32.c
@@ -23,7 +23,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 
diff --git a/arch/powerpc/mm/mmu_context_64.c b/arch/powerpc/mm/mmu_context_64.c
index 65d18dca266f..90a06ac02d5e 100644
--- a/arch/powerpc/mm/mmu_context_64.c
+++ b/arch/powerpc/mm/mmu_context_64.c
@@ -10,7 +10,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -44,7 +43,9 @@ again:
 		return err;
 
 	if (index > MAX_CONTEXT) {
+		spin_lock(&mmu_context_lock);
 		idr_remove(&mmu_context_idr, index);
+		spin_unlock(&mmu_context_lock);
 		return -ENOMEM;
 	}
 
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index aa98cb3b59d8..43c272075e1a 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -39,96 +39,6 @@ static bootmem_data_t __initdata plat_node_bdata[MAX_NUMNODES];
 static int min_common_depth;
 static int n_mem_addr_cells, n_mem_size_cells;
 
-/*
- * We need somewhere to store start/end/node for each region until we have
- * allocated the real node_data structures.
- */
-#define MAX_REGIONS	(MAX_LMB_REGIONS*2)
-static struct {
-	unsigned long start_pfn;
-	unsigned long end_pfn;
-	int nid;
-} init_node_data[MAX_REGIONS] __initdata;
-
-int __init early_pfn_to_nid(unsigned long pfn)
-{
-	unsigned int i;
-
-	for (i = 0; init_node_data[i].end_pfn; i++) {
-		unsigned long start_pfn = init_node_data[i].start_pfn;
-		unsigned long end_pfn = init_node_data[i].end_pfn;
-
-		if ((start_pfn <= pfn) && (pfn < end_pfn))
-			return init_node_data[i].nid;
-	}
-
-	return -1;
-}
-
-void __init add_region(unsigned int nid, unsigned long start_pfn,
-		       unsigned long pages)
-{
-	unsigned int i;
-
-	dbg("add_region nid %d start_pfn 0x%lx pages 0x%lx\n",
-		nid, start_pfn, pages);
-
-	for (i = 0; init_node_data[i].end_pfn; i++) {
-		if (init_node_data[i].nid != nid)
-			continue;
-		if (init_node_data[i].end_pfn == start_pfn) {
-			init_node_data[i].end_pfn += pages;
-			return;
-		}
-		if (init_node_data[i].start_pfn == (start_pfn + pages)) {
-			init_node_data[i].start_pfn -= pages;
-			return;
-		}
-	}
-
-	/*
-	 * Leave last entry NULL so we dont iterate off the end (we use
-	 * entry.end_pfn to terminate the walk).
-	 */
-	if (i >= (MAX_REGIONS - 1)) {
-		printk(KERN_ERR "WARNING: too many memory regions in "
-				"numa code, truncating\n");
-		return;
-	}
-
-	init_node_data[i].start_pfn = start_pfn;
-	init_node_data[i].end_pfn = start_pfn + pages;
-	init_node_data[i].nid = nid;
-}
-
-/* We assume init_node_data has no overlapping regions */
-void __init get_region(unsigned int nid, unsigned long *start_pfn,
-		       unsigned long *end_pfn, unsigned long *pages_present)
-{
-	unsigned int i;
-
-	*start_pfn = -1UL;
-	*end_pfn = *pages_present = 0;
-
-	for (i = 0; init_node_data[i].end_pfn; i++) {
-		if (init_node_data[i].nid != nid)
-			continue;
-
-		*pages_present += init_node_data[i].end_pfn -
-			init_node_data[i].start_pfn;
-
-		if (init_node_data[i].start_pfn < *start_pfn)
-			*start_pfn = init_node_data[i].start_pfn;
-
-		if (init_node_data[i].end_pfn > *end_pfn)
-			*end_pfn = init_node_data[i].end_pfn;
-	}
-
-	/* We didnt find a matching region, return start/end as 0 */
-	if (*start_pfn == -1UL)
-		*start_pfn = 0;
-}
-
 static void __cpuinit map_cpu_to_node(int cpu, int node)
 {
 	numa_cpu_lookup_table[cpu] = node;
@@ -159,12 +69,12 @@ static struct device_node * __cpuinit find_cpu_node(unsigned int cpu)
 {
 	unsigned int hw_cpuid = get_hard_smp_processor_id(cpu);
 	struct device_node *cpu_node = NULL;
-	unsigned int *interrupt_server, *reg;
+	const unsigned int *interrupt_server, *reg;
 	int len;
 
 	while ((cpu_node = of_find_node_by_type(cpu_node, "cpu")) != NULL) {
 		/* Try interrupt server first */
-		interrupt_server = (unsigned int *)get_property(cpu_node,
+		interrupt_server = get_property(cpu_node,
 					"ibm,ppc-interrupt-server#s", &len);
 
 		len = len / sizeof(u32);
@@ -175,8 +85,7 @@ static struct device_node * __cpuinit find_cpu_node(unsigned int cpu)
 					return cpu_node;
 			}
 		} else {
-			reg = (unsigned int *)get_property(cpu_node,
-							   "reg", &len);
+			reg = get_property(cpu_node, "reg", &len);
 			if (reg && (len > 0) && (reg[0] == hw_cpuid))
 				return cpu_node;
 		}
@@ -186,9 +95,9 @@ static struct device_node * __cpuinit find_cpu_node(unsigned int cpu)
 }
 
 /* must hold reference to node during call */
-static int *of_get_associativity(struct device_node *dev)
+static const int *of_get_associativity(struct device_node *dev)
 {
-	return (unsigned int *)get_property(dev, "ibm,associativity", NULL);
+	return get_property(dev, "ibm,associativity", NULL);
 }
 
 /* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
@@ -197,7 +106,7 @@ static int *of_get_associativity(struct device_node *dev)
 static int of_node_to_nid_single(struct device_node *device)
 {
 	int nid = -1;
-	unsigned int *tmp;
+	const unsigned int *tmp;
 
 	if (min_common_depth == -1)
 		goto out;
@@ -255,7 +164,7 @@ EXPORT_SYMBOL_GPL(of_node_to_nid);
 static int __init find_min_common_depth(void)
 {
 	int depth;
-	unsigned int *ref_points;
+	const unsigned int *ref_points;
 	struct device_node *rtas_root;
 	unsigned int len;
 
@@ -270,7 +179,7 @@ static int __init find_min_common_depth(void)
 	 * configuration (should be all 0's) and the second is for a normal
 	 * NUMA configuration.
 	 */
-	ref_points = (unsigned int *)get_property(rtas_root,
+	ref_points = get_property(rtas_root,
 			"ibm,associativity-reference-points", &len);
 
 	if ((len >= 1) && ref_points) {
@@ -297,7 +206,7 @@ static void __init get_n_mem_cells(int *n_addr_cells, int *n_size_cells)
 	of_node_put(memory);
 }
 
-static unsigned long __devinit read_n_cells(int n, unsigned int **buf)
+static unsigned long __devinit read_n_cells(int n, const unsigned int **buf)
 {
 	unsigned long result = 0;
 
@@ -334,7 +243,7 @@ out:
 	return nid;
 }
 
-static int cpu_numa_callback(struct notifier_block *nfb,
+static int __cpuinit cpu_numa_callback(struct notifier_block *nfb,
 			     unsigned long action,
 			     void *hcpu)
 {
@@ -435,15 +344,13 @@ static int __init parse_numa_properties(void)
 		unsigned long size;
 		int nid;
 		int ranges;
-		unsigned int *memcell_buf;
+		const unsigned int *memcell_buf;
 		unsigned int len;
 
-		memcell_buf = (unsigned int *)get_property(memory,
+		memcell_buf = get_property(memory,
 			"linux,usable-memory", &len);
 		if (!memcell_buf || len <= 0)
-			memcell_buf =
-				(unsigned int *)get_property(memory, "reg",
-					&len);
+			memcell_buf = get_property(memory, "reg", &len);
 		if (!memcell_buf || len <= 0)
 			continue;
 
@@ -471,8 +378,8 @@ new_range:
 				continue;
 		}
 
-		add_region(nid, start >> PAGE_SHIFT,
-			   size >> PAGE_SHIFT);
+		add_active_range(nid, start >> PAGE_SHIFT,
+				(start >> PAGE_SHIFT) + (size >> PAGE_SHIFT));
 
 		if (--ranges)
 			goto new_range;
@@ -485,6 +392,7 @@ static void __init setup_nonnuma(void)
 {
 	unsigned long top_of_ram = lmb_end_of_DRAM();
 	unsigned long total_ram = lmb_phys_mem_size();
+	unsigned long start_pfn, end_pfn;
 	unsigned int i;
 
 	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
@@ -492,9 +400,11 @@ static void __init setup_nonnuma(void)
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
 
-	for (i = 0; i < lmb.memory.cnt; ++i)
-		add_region(0, lmb.memory.region[i].base >> PAGE_SHIFT,
-			   lmb_size_pages(&lmb.memory, i));
+	for (i = 0; i < lmb.memory.cnt; ++i) {
+		start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT;
+		end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i);
+		add_active_range(0, start_pfn, end_pfn);
+	}
 	node_set_online(0);
 }
 
@@ -609,14 +519,15 @@ static void __init *careful_allocation(int nid, unsigned long size,
 	return (void *)ret;
 }
 
+static struct notifier_block __cpuinitdata ppc64_numa_nb = {
+	.notifier_call = cpu_numa_callback,
+	.priority = 1 /* Must run before sched domains notifier. */
+};
+
 void __init do_init_bootmem(void)
 {
 	int nid;
 	unsigned int i;
-	static struct notifier_block ppc64_numa_nb = {
-		.notifier_call = cpu_numa_callback,
-		.priority = 1 /* Must run before sched domains notifier. */
-	};
 
 	min_low_pfn = 0;
 	max_low_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT;
@@ -632,11 +543,11 @@ void __init do_init_bootmem(void)
 			  (void *)(unsigned long)boot_cpuid);
 
 	for_each_online_node(nid) {
-		unsigned long start_pfn, end_pfn, pages_present;
+		unsigned long start_pfn, end_pfn;
 		unsigned long bootmem_paddr;
 		unsigned long bootmap_pages;
 
-		get_region(nid, &start_pfn, &end_pfn, &pages_present);
+		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 
 		/* Allocate the node structure node local if possible */
 		NODE_DATA(nid) = careful_allocation(nid,
@@ -669,19 +580,7 @@ void __init do_init_bootmem(void)
 		init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
 				  start_pfn, end_pfn);
 
-		/* Add free regions on this node */
-		for (i = 0; init_node_data[i].end_pfn; i++) {
-			unsigned long start, end;
-
-			if (init_node_data[i].nid != nid)
-				continue;
-
-			start = init_node_data[i].start_pfn << PAGE_SHIFT;
-			end = init_node_data[i].end_pfn << PAGE_SHIFT;
-
-			dbg("free_bootmem %lx %lx\n", start, end - start);
-  			free_bootmem_node(NODE_DATA(nid), start, end - start);
-		}
+		free_bootmem_with_active_regions(nid, end_pfn);
 
 		/* Mark reserved regions on this node */
 		for (i = 0; i < lmb.reserved.cnt; i++) {
@@ -712,44 +611,16 @@ void __init do_init_bootmem(void)
 			}
 		}
 
-		/* Add regions into sparsemem */
-		for (i = 0; init_node_data[i].end_pfn; i++) {
-			unsigned long start, end;
-
-			if (init_node_data[i].nid != nid)
-				continue;
-
-			start = init_node_data[i].start_pfn;
-			end = init_node_data[i].end_pfn;
-
-			memory_present(nid, start, end);
-		}
+		sparse_memory_present_with_active_regions(nid);
 	}
 }
 
 void __init paging_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES];
-	unsigned long zholes_size[MAX_NR_ZONES];
-	int nid;
-
-	memset(zones_size, 0, sizeof(zones_size));
-	memset(zholes_size, 0, sizeof(zholes_size));
-
-	for_each_online_node(nid) {
-		unsigned long start_pfn, end_pfn, pages_present;
-
-		get_region(nid, &start_pfn, &end_pfn, &pages_present);
-
-		zones_size[ZONE_DMA] = end_pfn - start_pfn;
-		zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] - pages_present;
-
-		dbg("free_area_init node %d %lx %lx (hole: %lx)\n", nid,
-		    zones_size[ZONE_DMA], start_pfn, zholes_size[ZONE_DMA]);
-
-		free_area_init_node(nid, NODE_DATA(nid), zones_size, start_pfn,
-				    zholes_size);
-	}
+	unsigned long max_zone_pfns[MAX_NR_ZONES] = {
+				lmb_end_of_DRAM() >> PAGE_SHIFT
+	};
+	free_area_init_nodes(max_zone_pfns);
 }
 
 static int __init early_numa(char *p)
@@ -786,10 +657,10 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 	while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
 		unsigned long start, size;
 		int ranges;
-		unsigned int *memcell_buf;
+		const unsigned int *memcell_buf;
 		unsigned int len;
 
-		memcell_buf = (unsigned int *)get_property(memory, "reg", &len);
+		memcell_buf = get_property(memory, "reg", &len);
 		if (!memcell_buf || len <= 0)
 			continue;
 
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 90628601fac7..8fcacb0239da 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -20,7 +20,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/types.h>
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 7b278d83739e..b1da03165496 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -22,7 +22,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 2ed43a493b31..7cceb2c44cb9 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -23,7 +23,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/init.h>
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 6a8bf6c6000e..d3733912adb4 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -16,13 +16,14 @@
 
 #undef DEBUG
 
-#include <linux/config.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/paca.h>
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
+#include <asm/smp.h>
+#include <linux/compiler.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -51,9 +52,32 @@ static inline unsigned long mk_vsid_data(unsigned long ea, unsigned long flags)
 	return (get_kernel_vsid(ea) << SLB_VSID_SHIFT) | flags;
 }
 
-static inline void create_slbe(unsigned long ea, unsigned long flags,
-			       unsigned long entry)
+static inline void slb_shadow_update(unsigned long esid, unsigned long vsid,
+				     unsigned long entry)
 {
+	/*
+	 * Clear the ESID first so the entry is not valid while we are
+	 * updating it.
+	 */
+	get_slb_shadow()->save_area[entry].esid = 0;
+	barrier();
+	get_slb_shadow()->save_area[entry].vsid = vsid;
+	barrier();
+	get_slb_shadow()->save_area[entry].esid = esid;
+
+}
+
+static inline void create_shadowed_slbe(unsigned long ea, unsigned long flags,
+					unsigned long entry)
+{
+	/*
+	 * Updating the shadow buffer before writing the SLB ensures
+	 * we don't get a stale entry here if we get preempted by PHYP
+	 * between these two statements.
+	 */
+	slb_shadow_update(mk_esid_data(ea, entry), mk_vsid_data(ea, flags),
+			  entry);
+
 	asm volatile("slbmte  %0,%1" :
 		     : "r" (mk_vsid_data(ea, flags)),
 		       "r" (mk_esid_data(ea, entry))
@@ -78,6 +102,10 @@ void slb_flush_and_rebolt(void)
 	if ((ksp_esid_data & ESID_MASK) == PAGE_OFFSET)
 		ksp_esid_data &= ~SLB_ESID_V;
 
+	/* Only third entry (stack) may change here so only resave that */
+	slb_shadow_update(ksp_esid_data,
+			  mk_vsid_data(ksp_esid_data, lflags), 2);
+
 	/* We need to do this all in asm, so we're sure we don't touch
 	 * the stack between the slbia and rebolting it. */
 	asm volatile("isync\n"
@@ -210,9 +238,9 @@ void slb_initialize(void)
 	asm volatile("isync":::"memory");
 	asm volatile("slbmte  %0,%0"::"r" (0) : "memory");
 	asm volatile("isync; slbia; isync":::"memory");
-	create_slbe(PAGE_OFFSET, lflags, 0);
+	create_shadowed_slbe(PAGE_OFFSET, lflags, 0);
 
-	create_slbe(VMALLOC_START, vflags, 1);
+	create_shadowed_slbe(VMALLOC_START, vflags, 1);
 
 	/* We don't bolt the stack for the time being - we're in boot,
 	 * so the stack is in the bolted segment.  By the time it goes
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 8548dcf8ef8b..dbc1abbde038 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -14,7 +14,6 @@
  *  2 of the License, or (at your option) any later version.
  */
 
-#include <linux/config.h>
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
index 691320c90b78..eeeacab548e6 100644
--- a/arch/powerpc/mm/stab.c
+++ b/arch/powerpc/mm/stab.c
@@ -12,7 +12,6 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-#include <linux/config.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
diff --git a/arch/powerpc/mm/tlb_32.c b/arch/powerpc/mm/tlb_32.c
index 02eb23e036d5..925ff70be8ba 100644
--- a/arch/powerpc/mm/tlb_32.c
+++ b/arch/powerpc/mm/tlb_32.c
@@ -23,7 +23,6 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/init.h>
diff --git a/arch/powerpc/mm/tlb_64.c b/arch/powerpc/mm/tlb_64.c
index e7449b068c82..b58baa65c4a7 100644
--- a/arch/powerpc/mm/tlb_64.c
+++ b/arch/powerpc/mm/tlb_64.c
@@ -22,7 +22,6 @@
  *  2 of the License, or (at your option) any later version.
  */
 
-#include <linux/config.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/init.h>
@@ -147,6 +146,7 @@ void hpte_update(struct mm_struct *mm, unsigned long addr,
 		psize = mmu_huge_psize;
 #else
 		BUG();
+		psize = pte_pagesize_index(pte); /* shutup gcc */
 #endif
 	} else
 		psize = pte_pagesize_index(pte);