Merge tag 'v3.5'

Linux 3.5

* tag 'v3.5': (1242 commits)
  Linux 3.5
  Remove SYSTEM_SUSPEND_DISK system state
  kdb: Switch to nolock variants of kmsg_dump functions
  printk: Implement some unlocked kmsg_dump functions
  printk: Remove kdb_syslog_data
  kdb: Revive dmesg command
  dm raid1: set discard_zeroes_data_unsupported
  dm thin: do not send discards to shared blocks
  dm raid1: fix crash with mirror recovery and discard
  pnfs-obj: Fix __r4w_get_page when offset is beyond i_size
  pnfs-obj: don't leak objio_state if ore_write/read fails
  ore: Unlock r4w pages in exact reverse order of locking
  ore: Remove support of partial IO request (NFS crash)
  ore: Fix NFS crash by supporting any unaligned RAID IO
  UBIFS: fix a bug in empty space fix-up
  cx25821: Remove bad strcpy to read-only char*
  HID: hid-multitouch: add support for Zytronic panels
  MIPS: PCI: Move fixups from __init to __devinit.
  MIPS: Fix bug.h MIPS build regression
  MIPS: sync-r4k: remove redundant irq operation
  ...

4 files changed, 82 insertions, 8 deletions

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 106c4c0ebccd..655878bcc96d 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -228,7 +228,7 @@ static pte_t **consistent_pte;
 
 #define DEFAULT_CONSISTENT_DMA_SIZE SZ_2M
 
-unsigned long consistent_base = CONSISTENT_END - DEFAULT_CONSISTENT_DMA_SIZE;
+static unsigned long consistent_base = CONSISTENT_END - DEFAULT_CONSISTENT_DMA_SIZE;
 
 void __init init_consistent_dma_size(unsigned long size)
 {
@@ -321,7 +321,7 @@ static struct arm_vmregion_head coherent_head = {
 	.vm_list	= LIST_HEAD_INIT(coherent_head.vm_list),
 };
 
-size_t coherent_pool_size = DEFAULT_CONSISTENT_DMA_SIZE / 8;
+static size_t coherent_pool_size = DEFAULT_CONSISTENT_DMA_SIZE / 8;
 
 static int __init early_coherent_pool(char *p)
 {
@@ -1067,7 +1067,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t
 		return NULL;
 
 	while (count) {
-		int j, order = __ffs(count);
+		int j, order = __fls(count);
 
 		pages[i] = alloc_pages(gfp | __GFP_NOWARN, order);
 		while (!pages[i] && order)
@@ -1091,7 +1091,7 @@ error:
 	while (--i)
 		if (pages[i])
 			__free_pages(pages[i], 0);
-	if (array_size < PAGE_SIZE)
+	if (array_size <= PAGE_SIZE)
 		kfree(pages);
 	else
 		vfree(pages);
@@ -1106,7 +1106,7 @@ static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t s
 	for (i = 0; i < count; i++)
 		if (pages[i])
 			__free_pages(pages[i], 0);
-	if (array_size < PAGE_SIZE)
+	if (array_size <= PAGE_SIZE)
 		kfree(pages);
 	else
 		vfree(pages);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index c21d06c7dd7e..f54d59219764 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -212,7 +212,7 @@ EXPORT_SYMBOL(arm_dma_zone_size);
  * allocations.  This must be the smallest DMA mask in the system,
  * so a successful GFP_DMA allocation will always satisfy this.
  */
-u32 arm_dma_limit;
+phys_addr_t arm_dma_limit;
 
 static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole,
 	unsigned long dma_size)
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 93dc0c17cdcb..2e8a1efdf7b8 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -62,9 +62,9 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 #endif
 
 #ifdef CONFIG_ZONE_DMA
-extern u32 arm_dma_limit;
+extern phys_addr_t arm_dma_limit;
 #else
-#define arm_dma_limit ((u32)~0)
+#define arm_dma_limit ((phys_addr_t)~0)
 #endif
 
 extern phys_addr_t arm_lowmem_limit;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index e5dad60b558b..cf4528d51774 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -791,6 +791,79 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 	}
 }
 
+#ifndef CONFIG_ARM_LPAE
+
+/*
+ * The Linux PMD is made of two consecutive section entries covering 2MB
+ * (see definition in include/asm/pgtable-2level.h).  However a call to
+ * create_mapping() may optimize static mappings by using individual
+ * 1MB section mappings.  This leaves the actual PMD potentially half
+ * initialized if the top or bottom section entry isn't used, leaving it
+ * open to problems if a subsequent ioremap() or vmalloc() tries to use
+ * the virtual space left free by that unused section entry.
+ *
+ * Let's avoid the issue by inserting dummy vm entries covering the unused
+ * PMD halves once the static mappings are in place.
+ */
+
+static void __init pmd_empty_section_gap(unsigned long addr)
+{
+	struct vm_struct *vm;
+
+	vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm));
+	vm->addr = (void *)addr;
+	vm->size = SECTION_SIZE;
+	vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING;
+	vm->caller = pmd_empty_section_gap;
+	vm_area_add_early(vm);
+}
+
+static void __init fill_pmd_gaps(void)
+{
+	struct vm_struct *vm;
+	unsigned long addr, next = 0;
+	pmd_t *pmd;
+
+	/* we're still single threaded hence no lock needed here */
+	for (vm = vmlist; vm; vm = vm->next) {
+		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
+			continue;
+		addr = (unsigned long)vm->addr;
+		if (addr < next)
+			continue;
+
+		/*
+		 * Check if this vm starts on an odd section boundary.
+		 * If so and the first section entry for this PMD is free
+		 * then we block the corresponding virtual address.
+		 */
+		if ((addr & ~PMD_MASK) == SECTION_SIZE) {
+			pmd = pmd_off_k(addr);
+			if (pmd_none(*pmd))
+				pmd_empty_section_gap(addr & PMD_MASK);
+		}
+
+		/*
+		 * Then check if this vm ends on an odd section boundary.
+		 * If so and the second section entry for this PMD is empty
+		 * then we block the corresponding virtual address.
+		 */
+		addr += vm->size;
+		if ((addr & ~PMD_MASK) == SECTION_SIZE) {
+			pmd = pmd_off_k(addr) + 1;
+			if (pmd_none(*pmd))
+				pmd_empty_section_gap(addr);
+		}
+
+		/* no need to look at any vm entry until we hit the next PMD */
+		next = (addr + PMD_SIZE - 1) & PMD_MASK;
+	}
+}
+
+#else
+#define fill_pmd_gaps() do { } while (0)
+#endif
+
 static void * __initdata vmalloc_min =
 	(void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET);
 
@@ -1072,6 +1145,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 */
 	if (mdesc->map_io)
 		mdesc->map_io();
+	fill_pmd_gaps();
 
 	/*
 	 * Finally flush the caches and tlb to ensure that we're in a