Pull mem-attribute into release branch

3 files changed, 107 insertions, 19 deletions

diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index f45f91d38ca..78d29b79947 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -660,6 +660,29 @@ efi_memory_descriptor (unsigned long phys_addr)
 	return NULL;
 }
 
+static int
+efi_memmap_intersects (unsigned long phys_addr, unsigned long size)
+{
+	void *efi_map_start, *efi_map_end, *p;
+	efi_memory_desc_t *md;
+	u64 efi_desc_size;
+	unsigned long end;
+
+	efi_map_start = __va(ia64_boot_param->efi_memmap);
+	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
+	efi_desc_size = ia64_boot_param->efi_memdesc_size;
+
+	end = phys_addr + size;
+
+	for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
+		md = p;
+
+		if (md->phys_addr < end && efi_md_end(md) > phys_addr)
+			return 1;
+	}
+	return 0;
+}
+
 u32
 efi_mem_type (unsigned long phys_addr)
 {
@@ -766,11 +789,28 @@ valid_phys_addr_range (unsigned long phys_addr, unsigned long size)
 int
 valid_mmap_phys_addr_range (unsigned long pfn, unsigned long size)
 {
+	unsigned long phys_addr = pfn << PAGE_SHIFT;
+	u64 attr;
+
+	attr = efi_mem_attribute(phys_addr, size);
+
 	/*
-	 * MMIO regions are often missing from the EFI memory map.
-	 * We must allow mmap of them for programs like X, so we
-	 * currently can't do any useful validation.
+	 * /dev/mem mmap uses normal user pages, so we don't need the entire
+	 * granule, but the entire region we're mapping must support the same
+	 * attribute.
 	 */
+	if (attr & EFI_MEMORY_WB || attr & EFI_MEMORY_UC)
+		return 1;
+
+	/*
+	 * Intel firmware doesn't tell us about all the MMIO regions, so
+	 * in general we have to allow mmap requests.  But if EFI *does*
+	 * tell us about anything inside this region, we should deny it.
+	 * The user can always map a smaller region to avoid the overlap.
+	 */
+	if (efi_memmap_intersects(phys_addr, size))
+		return 0;
+
 	return 1;
 }
 
diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c
index 4280c074d64..2a140627dfd 100644
--- a/arch/ia64/mm/ioremap.c
+++ b/arch/ia64/mm/ioremap.c
@@ -1,5 +1,5 @@
 /*
- * (c) Copyright 2006 Hewlett-Packard Development Company, L.P.
+ * (c) Copyright 2006, 2007 Hewlett-Packard Development Company, L.P.
  *	Bjorn Helgaas <bjorn.helgaas@hp.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -10,51 +10,101 @@
 #include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/efi.h>
+#include <linux/io.h>
+#include <linux/vmalloc.h>
 #include <asm/io.h>
 #include <asm/meminit.h>
 
 static inline void __iomem *
-__ioremap (unsigned long offset, unsigned long size)
+__ioremap (unsigned long phys_addr)
 {
-	return (void __iomem *) (__IA64_UNCACHED_OFFSET | offset);
+	return (void __iomem *) (__IA64_UNCACHED_OFFSET | phys_addr);
 }
 
 void __iomem *
-ioremap (unsigned long offset, unsigned long size)
+ioremap (unsigned long phys_addr, unsigned long size)
 {
+	void __iomem *addr;
+	struct vm_struct *area;
+	unsigned long offset;
+	pgprot_t prot;
 	u64 attr;
 	unsigned long gran_base, gran_size;
+	unsigned long page_base;
 
 	/*
 	 * For things in kern_memmap, we must use the same attribute
 	 * as the rest of the kernel.  For more details, see
 	 * Documentation/ia64/aliasing.txt.
 	 */
-	attr = kern_mem_attribute(offset, size);
+	attr = kern_mem_attribute(phys_addr, size);
 	if (attr & EFI_MEMORY_WB)
-		return (void __iomem *) phys_to_virt(offset);
+		return (void __iomem *) phys_to_virt(phys_addr);
 	else if (attr & EFI_MEMORY_UC)
-		return __ioremap(offset, size);
+		return __ioremap(phys_addr);
 
 	/*
 	 * Some chipsets don't support UC access to memory.  If
 	 * WB is supported for the whole granule, we prefer that.
 	 */
-	gran_base = GRANULEROUNDDOWN(offset);
-	gran_size = GRANULEROUNDUP(offset + size) - gran_base;
+	gran_base = GRANULEROUNDDOWN(phys_addr);
+	gran_size = GRANULEROUNDUP(phys_addr + size) - gran_base;
 	if (efi_mem_attribute(gran_base, gran_size) & EFI_MEMORY_WB)
-		return (void __iomem *) phys_to_virt(offset);
+		return (void __iomem *) phys_to_virt(phys_addr);
 
-	return __ioremap(offset, size);
+	/*
+	 * WB is not supported for the whole granule, so we can't use
+	 * the region 7 identity mapping.  If we can safely cover the
+	 * area with kernel page table mappings, we can use those
+	 * instead.
+	 */
+	page_base = phys_addr & PAGE_MASK;
+	size = PAGE_ALIGN(phys_addr + size) - page_base;
+	if (efi_mem_attribute(page_base, size) & EFI_MEMORY_WB) {
+		prot = PAGE_KERNEL;
+
+		/*
+		 * Mappings have to be page-aligned
+		 */
+		offset = phys_addr & ~PAGE_MASK;
+		phys_addr &= PAGE_MASK;
+
+		/*
+		 * Ok, go for it..
+		 */
+		area = get_vm_area(size, VM_IOREMAP);
+		if (!area)
+			return NULL;
+
+		area->phys_addr = phys_addr;
+		addr = (void __iomem *) area->addr;
+		if (ioremap_page_range((unsigned long) addr,
+				(unsigned long) addr + size, phys_addr, prot)) {
+			vunmap((void __force *) addr);
+			return NULL;
+		}
+
+		return (void __iomem *) (offset + (char __iomem *)addr);
+	}
+
+	return __ioremap(phys_addr);
 }
 EXPORT_SYMBOL(ioremap);
 
 void __iomem *
-ioremap_nocache (unsigned long offset, unsigned long size)
+ioremap_nocache (unsigned long phys_addr, unsigned long size)
 {
-	if (kern_mem_attribute(offset, size) & EFI_MEMORY_WB)
+	if (kern_mem_attribute(phys_addr, size) & EFI_MEMORY_WB)
 		return NULL;
 
-	return __ioremap(offset, size);
+	return __ioremap(phys_addr);
 }
 EXPORT_SYMBOL(ioremap_nocache);
+
+void
+iounmap (volatile void __iomem *addr)
+{
+	if (REGION_NUMBER(addr) == RGN_GATE)
+		vunmap((void *) ((unsigned long) addr & PAGE_MASK));
+}
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 0e83f3b419b..9f635896d25 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -659,8 +659,6 @@ pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma)
 		return -EINVAL;
 	prot = phys_mem_access_prot(NULL, vma->vm_pgoff, size,
 				    vma->vm_page_prot);
-	if (pgprot_val(prot) != pgprot_val(pgprot_noncached(vma->vm_page_prot)))
-		return -EINVAL;
 
 	addr = pci_get_legacy_mem(bus);
 	if (IS_ERR(addr))