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

4 files changed, 105 insertions, 14 deletions

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index baf7c4f..4a47618 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -566,9 +566,9 @@ void __init paging_init(void)
 
 /*
  * Test if the WP bit works in supervisor mode. It isn't supported on 386's
- * and also on some strange 486's (NexGen etc.). All 586+'s are OK. This
- * used to involve black magic jumps to work around some nasty CPU bugs,
- * but fortunately the switch to using exceptions got rid of all that.
+ * and also on some strange 486's. All 586+'s are OK. This used to involve
+ * black magic jumps to work around some nasty CPU bugs, but fortunately the
+ * switch to using exceptions got rid of all that.
  */
 static void __init test_wp_bit(void)
 {
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0cca626..5fbb865 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -810,7 +810,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 {
 #ifdef CONFIG_NUMA
-	int nid = phys_to_nid(phys);
+	int nid, next_nid;
 #endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
 
@@ -829,10 +829,16 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 
 	/* Should check here against the e820 map to avoid double free */
 #ifdef CONFIG_NUMA
-	reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	nid = phys_to_nid(phys);
+	next_nid = phys_to_nid(phys + len - 1);
+	if (nid == next_nid)
+		reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	else
+		reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #else
 	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #endif
+
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;
 		set_dma_reserve(dma_reserve);
@@ -926,6 +932,10 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
  */
+static long __meminitdata addr_start, addr_end;
+static void __meminitdata *p_start, *p_end;
+static int __meminitdata node_start;
+
 int __meminit
 vmemmap_populate(struct page *start_page, unsigned long size, int node)
 {
@@ -960,12 +970,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 							PAGE_KERNEL_LARGE);
 			set_pmd(pmd, __pmd(pte_val(entry)));
 
-			printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
-				addr, addr + PMD_SIZE - 1, p, node);
+			/* check to see if we have contiguous blocks */
+			if (p_end != p || node_start != node) {
+				if (p_start)
+					printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+						addr_start, addr_end-1, p_start, p_end-1, node_start);
+				addr_start = addr;
+				node_start = node;
+				p_start = p;
+			}
+			addr_end = addr + PMD_SIZE;
+			p_end = p + PMD_SIZE;
 		} else {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 		}
 	}
 	return 0;
 }
+
+void __meminit vmemmap_populate_print_last(void)
+{
+	if (p_start) {
+		printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+			addr_start, addr_end-1, p_start, p_end-1, node_start);
+		p_start = NULL;
+		p_end = NULL;
+		node_start = 0;
+	}
+}
 #endif
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 9a68922..c5066d5 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -196,6 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 	unsigned long bootmap_start, nodedata_phys;
 	void *bootmap;
 	const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
+	int nid;
 
 	start = round_up(start, ZONE_ALIGN);
 
@@ -218,9 +219,19 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
 	NODE_DATA(nodeid)->node_spanned_pages = end_pfn - start_pfn;
 
-	/* Find a place for the bootmem map */
+	/*
+	 * Find a place for the bootmem map
+	 * nodedata_phys could be on other nodes by alloc_bootmem,
+	 * so need to sure bootmap_start not to be small, otherwise
+	 * early_node_mem will get that with find_e820_area instead
+	 * of alloc_bootmem, that could clash with reserved range
+	 */
 	bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-	bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+	nid = phys_to_nid(nodedata_phys);
+	if (nid == nodeid)
+		bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+	else
+		bootmap_start = round_up(start, PAGE_SIZE);
 	/*
 	 * SMP_CAHCE_BYTES could be enough, but init_bootmem_node like
 	 * to use that to align to PAGE_SIZE
@@ -245,10 +256,29 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 
 	free_bootmem_with_active_regions(nodeid, end);
 
-	reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size,
-			BOOTMEM_DEFAULT);
-	reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
-			bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+	/*
+	 * convert early reserve to bootmem reserve earlier
+	 * otherwise early_node_mem could use early reserved mem
+	 * on previous node
+	 */
+	early_res_to_bootmem(start, end);
+
+	/*
+	 * in some case early_node_mem could use alloc_bootmem
+	 * to get range on other node, don't reserve that again
+	 */
+	if (nid != nodeid)
+		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
+	else
+		reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys,
+					pgdat_size, BOOTMEM_DEFAULT);
+	nid = phys_to_nid(bootmap_start);
+	if (nid != nodeid)
+		printk(KERN_INFO "    bootmap(%d) on node %d\n", nodeid, nid);
+	else
+		reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
+				 bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+
 #ifdef CONFIG_ACPI_NUMA
 	srat_reserve_add_area(nodeid);
 #endif
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index ef8b64b..e7ca7fc 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -16,6 +16,7 @@
 #include <asm/msr.h>
 #include <asm/tlbflush.h>
 #include <asm/processor.h>
+#include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/pat.h>
 #include <asm/e820.h>
@@ -334,7 +335,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 				break;
 			}
 
-			printk("Overlap at 0x%Lx-0x%Lx\n",
+			pr_debug("Overlap at 0x%Lx-0x%Lx\n",
 			       saved_ptr->start, saved_ptr->end);
 			/* No conflict. Go ahead and add this new entry */
 			list_add(&new_entry->nd, saved_ptr->nd.prev);
@@ -477,6 +478,33 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 	return vma_prot;
 }
 
+#ifdef CONFIG_NONPROMISC_DEVMEM
+/* This check is done in drivers/char/mem.c in case of NONPROMISC_DEVMEM*/
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+	return 1;
+}
+#else
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+	u64 from = ((u64)pfn) << PAGE_SHIFT;
+	u64 to = from + size;
+	u64 cursor = from;
+
+	while (cursor < to) {
+		if (!devmem_is_allowed(pfn)) {
+			printk(KERN_INFO
+		"Program %s tried to access /dev/mem between %Lx->%Lx.\n",
+				current->comm, from, to);
+			return 0;
+		}
+		cursor += PAGE_SIZE;
+		pfn++;
+	}
+	return 1;
+}
+#endif /* CONFIG_NONPROMISC_DEVMEM */
+
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t *vma_prot)
 {
@@ -485,6 +513,9 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	unsigned long ret_flags;
 	int retval;
 
+	if (!range_is_allowed(pfn, size))
+		return 0;
+
 	if (file->f_flags & O_SYNC) {
 		flags = _PAGE_CACHE_UC;
 	}