x86, efi: Calling __pa() with an ioremap()ed address is invalid

If we encounter an efi_memory_desc_t without EFI_MEMORY_WB set
in ->attribute we currently call set_memory_uc(), which in turn
calls __pa() on a potentially ioremap'd address.

On CONFIG_X86_32 this is invalid, resulting in the following
oops on some machines:

  BUG: unable to handle kernel paging request at f7f22280
  IP: [<c10257b9>] reserve_ram_pages_type+0x89/0x210
  [...]

  Call Trace:
   [<c104f8ca>] ? page_is_ram+0x1a/0x40
   [<c1025aff>] reserve_memtype+0xdf/0x2f0
   [<c1024dc9>] set_memory_uc+0x49/0xa0
   [<c19334d0>] efi_enter_virtual_mode+0x1c2/0x3aa
   [<c19216d4>] start_kernel+0x291/0x2f2
   [<c19211c7>] ? loglevel+0x1b/0x1b
   [<c19210bf>] i386_start_kernel+0xbf/0xc8

A better approach to this problem is to map the memory region
with the correct attributes from the start, instead of modifying
it after the fact. The uncached case can be handled by
ioremap_nocache() and the cached by ioremap_cache().

Despite first impressions, it's not possible to use
ioremap_cache() to map all cached memory regions on
CONFIG_X86_64 because EFI_RUNTIME_SERVICES_DATA regions really
don't like being mapped into the vmalloc space, as detailed in
the following bug report,

	https://bugzilla.redhat.com/show_bug.cgi?id=748516

Therefore, we need to ensure that any EFI_RUNTIME_SERVICES_DATA
regions are covered by the direct kernel mapping table on
CONFIG_X86_64. To accomplish this we now map E820_RESERVED_EFI
regions via the direct kernel mapping with the initial call to
init_memory_mapping() in setup_arch(), whereas previously these
regions wouldn't be mapped if they were after the last E820_RAM
region until efi_ioremap() was called. Doing it this way allows
us to delete efi_ioremap() completely.

Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Matthew Garrett <mjg@redhat.com>
Cc: Zhang Rui <rui.zhang@intel.com>
Cc: Huang Ying <huang.ying.caritas@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1321621751-3650-1-git-send-email-matt@console-pimps.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 18 insertions, 28 deletions

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 37718f0f053d..c9718a16be15 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -323,10 +323,13 @@ static void __init do_add_efi_memmap(void)
 		case EFI_UNUSABLE_MEMORY:
 			e820_type = E820_UNUSABLE;
 			break;
+		case EFI_RUNTIME_SERVICES_DATA:
+			e820_type = E820_RESERVED_EFI;
+			break;
 		default:
 			/*
 			 * EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE
-			 * EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO
+			 * EFI_MEMORY_MAPPED_IO
 			 * EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE
 			 */
 			e820_type = E820_RESERVED;
@@ -671,10 +674,21 @@ void __init efi_enter_virtual_mode(void)
 		end_pfn = PFN_UP(end);
 		if (end_pfn <= max_low_pfn_mapped
 		    || (end_pfn > (1UL << (32 - PAGE_SHIFT))
-			&& end_pfn <= max_pfn_mapped))
+			&& end_pfn <= max_pfn_mapped)) {
 			va = __va(md->phys_addr);
-		else
-			va = efi_ioremap(md->phys_addr, size, md->type);
+
+			if (!(md->attribute & EFI_MEMORY_WB)) {
+				addr = (u64) (unsigned long)va;
+				npages = md->num_pages;
+				memrange_efi_to_native(&addr, &npages);
+				set_memory_uc(addr, npages);
+			}
+		} else {
+			if (!(md->attribute & EFI_MEMORY_WB))
+				va = ioremap_nocache(md->phys_addr, size);
+			else
+				va = ioremap_cache(md->phys_addr, size);
+		}
 
 		md->virt_addr = (u64) (unsigned long) va;
 
@@ -684,13 +698,6 @@ void __init efi_enter_virtual_mode(void)
 			continue;
 		}
 
-		if (!(md->attribute & EFI_MEMORY_WB)) {
-			addr = md->virt_addr;
-			npages = md->num_pages;
-			memrange_efi_to_native(&addr, &npages);
-			set_memory_uc(addr, npages);
-		}
-
 		systab = (u64) (unsigned long) efi_phys.systab;
 		if (md->phys_addr <= systab && systab < end) {
 			systab += md->virt_addr - md->phys_addr;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac3aa54e2654..312250c6b2de 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -80,20 +80,3 @@ void __init efi_call_phys_epilog(void)
 	local_irq_restore(efi_flags);
 	early_code_mapping_set_exec(0);
 }
-
-void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
-				 u32 type)
-{
-	unsigned long last_map_pfn;
-
-	if (type == EFI_MEMORY_MAPPED_IO)
-		return ioremap(phys_addr, size);
-
-	last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
-	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
-		unsigned long top = last_map_pfn << PAGE_SHIFT;
-		efi_ioremap(top, size - (top - phys_addr), type);
-	}
-
-	return (void __iomem *)__va(phys_addr);
-}