Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

4 files changed, 41 insertions, 33 deletions

diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 4314b39b6fa..ad123bced40 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -30,11 +30,11 @@
 #if defined(CONFIG_40x) || defined(CONFIG_8xx)
 static inline void _tlbil_all(void)
 {
-	asm volatile ("sync; tlbia; isync" : : : "memory")
+	asm volatile ("sync; tlbia; isync" : : : "memory");
 }
 static inline void _tlbil_pid(unsigned int pid)
 {
-	asm volatile ("sync; tlbia; isync" : : : "memory")
+	asm volatile ("sync; tlbia; isync" : : : "memory");
 }
 #else /* CONFIG_40x || CONFIG_8xx */
 extern void _tlbil_all(void);
@@ -47,7 +47,7 @@ extern void _tlbil_pid(unsigned int pid);
 #ifdef CONFIG_8xx
 static inline void _tlbil_va(unsigned long address, unsigned int pid)
 {
-	asm volatile ("tlbie %0; sync" : : "r" (address) : "memory")
+	asm volatile ("tlbie %0; sync" : : "r" (address) : "memory");
 }
 #else /* CONFIG_8xx */
 extern void _tlbil_va(unsigned long address, unsigned int pid);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index cf81049e1e5..7393bd76d69 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -822,42 +822,50 @@ static void __init dump_numa_memory_topology(void)
  * required. nid is the preferred node and end is the physical address of
  * the highest address in the node.
  *
- * Returns the physical address of the memory.
+ * Returns the virtual address of the memory.
  */
-static void __init *careful_allocation(int nid, unsigned long size,
+static void __init *careful_zallocation(int nid, unsigned long size,
 				       unsigned long align,
 				       unsigned long end_pfn)
 {
+	void *ret;
 	int new_nid;
-	unsigned long ret = __lmb_alloc_base(size, align, end_pfn << PAGE_SHIFT);
+	unsigned long ret_paddr;
+
+	ret_paddr = __lmb_alloc_base(size, align, end_pfn << PAGE_SHIFT);
 
 	/* retry over all memory */
-	if (!ret)
-		ret = __lmb_alloc_base(size, align, lmb_end_of_DRAM());
+	if (!ret_paddr)
+		ret_paddr = __lmb_alloc_base(size, align, lmb_end_of_DRAM());
 
-	if (!ret)
-		panic("numa.c: cannot allocate %lu bytes on node %d",
+	if (!ret_paddr)
+		panic("numa.c: cannot allocate %lu bytes for node %d",
 		      size, nid);
 
+	ret = __va(ret_paddr);
+
 	/*
-	 * If the memory came from a previously allocated node, we must
-	 * retry with the bootmem allocator.
+	 * We initialize the nodes in numeric order: 0, 1, 2...
+	 * and hand over control from the LMB allocator to the
+	 * bootmem allocator.  If this function is called for
+	 * node 5, then we know that all nodes <5 are using the
+	 * bootmem allocator instead of the LMB allocator.
+	 *
+	 * So, check the nid from which this allocation came
+	 * and double check to see if we need to use bootmem
+	 * instead of the LMB.  We don't free the LMB memory
+	 * since it would be useless.
 	 */
-	new_nid = early_pfn_to_nid(ret >> PAGE_SHIFT);
+	new_nid = early_pfn_to_nid(ret_paddr >> PAGE_SHIFT);
 	if (new_nid < nid) {
-		ret = (unsigned long)__alloc_bootmem_node(NODE_DATA(new_nid),
+		ret = __alloc_bootmem_node(NODE_DATA(new_nid),
 				size, align, 0);
 
-		if (!ret)
-			panic("numa.c: cannot allocate %lu bytes on node %d",
-			      size, new_nid);
-
-		ret = __pa(ret);
-
-		dbg("alloc_bootmem %lx %lx\n", ret, size);
+		dbg("alloc_bootmem %p %lx\n", ret, size);
 	}
 
-	return (void *)ret;
+	memset(ret, 0, size);
+	return ret;
 }
 
 static struct notifier_block __cpuinitdata ppc64_numa_nb = {
@@ -952,7 +960,7 @@ void __init do_init_bootmem(void)
 
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
-		unsigned long bootmem_paddr;
+		void *bootmem_vaddr;
 		unsigned long bootmap_pages;
 
 		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
@@ -964,11 +972,9 @@ void __init do_init_bootmem(void)
 		 * previous nodes' bootmem to be initialized and have
 		 * all reserved areas marked.
 		 */
-		NODE_DATA(nid) = careful_allocation(nid,
+		NODE_DATA(nid) = careful_zallocation(nid,
 					sizeof(struct pglist_data),
 					SMP_CACHE_BYTES, end_pfn);
-		NODE_DATA(nid) = __va(NODE_DATA(nid));
-		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
 
   		dbg("node %d\n", nid);
 		dbg("NODE_DATA() = %p\n", NODE_DATA(nid));
@@ -984,20 +990,20 @@ void __init do_init_bootmem(void)
   		dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT);
 
 		bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-		bootmem_paddr = (unsigned long)careful_allocation(nid,
+		bootmem_vaddr = careful_zallocation(nid,
 					bootmap_pages << PAGE_SHIFT,
 					PAGE_SIZE, end_pfn);
-		memset(__va(bootmem_paddr), 0, bootmap_pages << PAGE_SHIFT);
 
-		dbg("bootmap_paddr = %lx\n", bootmem_paddr);
+		dbg("bootmap_vaddr = %p\n", bootmem_vaddr);
 
-		init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
+		init_bootmem_node(NODE_DATA(nid),
+				  __pa(bootmem_vaddr) >> PAGE_SHIFT,
 				  start_pfn, end_pfn);
 
 		free_bootmem_with_active_regions(nid, end_pfn);
 		/*
 		 * Be very careful about moving this around.  Future
-		 * calls to careful_allocation() depend on this getting
+		 * calls to careful_zallocation() depend on this getting
 		 * done correctly.
 		 */
 		mark_reserved_regions_for_nid(nid);
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 38ff35f2142..22972cd83cc 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -266,7 +266,8 @@ int map_page(unsigned long va, phys_addr_t pa, int flags)
 		/* The PTE should never be already set nor present in the
 		 * hash table
 		 */
-		BUG_ON(pte_val(*pg) & (_PAGE_PRESENT | _PAGE_HASHPTE));
+		BUG_ON((pte_val(*pg) & (_PAGE_PRESENT | _PAGE_HASHPTE)) &&
+		       flags);
 		set_pte_at(&init_mm, va, pg, pfn_pte(pa >> PAGE_SHIFT,
 						     __pgprot(flags)));
 	}
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 803a64c02b0..39ac22b13c7 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -189,8 +189,9 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 	smp_call_function(do_flush_tlb_mm_ipi, NULL, 1);
 	_tlbil_pid(0);
 	preempt_enable();
-#endif
+#else
 	_tlbil_pid(0);
+#endif
 }
 EXPORT_SYMBOL(flush_tlb_kernel_range);