[tip:x86/mm] x86/mm: Define virtual memory map for 5-level paging

From: tip-bot for Kirill A. Shutemov
Date: Tue Apr 04 2017 - 04:37:32 EST

Commit-ID: 4c7c44837be77e2689c577abef155c4b5d873c82
Gitweb: http://git.kernel.org/tip/4c7c44837be77e2689c577abef155c4b5d873c82
Author: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
AuthorDate: Thu, 30 Mar 2017 11:07:27 +0300
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 4 Apr 2017 08:22:33 +0200

x86/mm: Define virtual memory map for 5-level paging

The first part of memory map (up to %esp fixup) simply scales existing
map for 4-level paging by factor of 9 -- number of bits addressed by
the additional page table level.

The rest of the map is unchanged.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: linux-arch@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Link: http://lkml.kernel.org/r/20170330080731.65421-4-kirill.shutemov@xxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
Documentation/x86/x86_64/mm.txt | 33 ++++++++++++++++++++++++++++++---
arch/x86/Kconfig | 1 +
arch/x86/include/asm/kasan.h | 9 ++++++---
arch/x86/include/asm/page_64_types.h | 10 ++++++++++
arch/x86/include/asm/pgtable_64_types.h | 6 ++++++
arch/x86/include/asm/sparsemem.h | 9 +++++++--
6 files changed, 60 insertions(+), 8 deletions(-)

diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index ee3f9c3..b0798e2 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -4,7 +4,7 @@
Virtual memory map with 4 level page tables:

0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
-hole caused by [48:63] sign extension
+hole caused by [47:63] sign extension
ffff800000000000 - ffff87ffffffffff (=43 bits) guard hole, reserved for hypervisor
ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
@@ -23,12 +23,39 @@ ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable)
ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole

+Virtual memory map with 5 level page tables:
+
+0000000000000000 - 00ffffffffffffff (=56 bits) user space, different per mm
+hole caused by [56:63] sign extension
+ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor
+ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory
+ff90000000000000 - ff91ffffffffffff (=49 bits) hole
+ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
+ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
+ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
+... unused hole ...
+ffd8000000000000 - fff7ffffffffffff (=53 bits) kasan shadow memory (8PB)
+... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
+ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
+... unused hole ...
+ffffffff80000000 - ffffffff9fffffff (=512 MB) kernel text mapping, from phys 0
+ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space
+ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
+
+Architecture defines a 64-bit virtual address. Implementations can support
+less. Currently supported are 48- and 57-bit virtual addresses. Bits 63
+through to the most-significant implemented bit are set to either all ones
+or all zero. This causes hole between user space and kernel addresses.
+
The direct mapping covers all memory in the system up to the highest
memory address (this means in some cases it can also include PCI memory
holes).

-vmalloc space is lazily synchronized into the different PML4 pages of
-the processes using the page fault handler, with init_level4_pgt as
+vmalloc space is lazily synchronized into the different PML4/PML5 pages of
+the processes using the page fault handler, with init_top_pgt as
reference.

Current X86-64 implementations support up to 46 bits of address space (64 TB),
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8977d9c..a641b90 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -291,6 +291,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
config KASAN_SHADOW_OFFSET
hex
depends on KASAN
+ default 0xdff8000000000000 if X86_5LEVEL
default 0xdffffc0000000000

config HAVE_INTEL_TXT
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index 1410b56..f527b02 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -11,9 +11,12 @@
* 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT
*/
#define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \
- (0xffff800000000000ULL >> 3))
-/* 47 bits for kernel address -> (47 - 3) bits for shadow */
-#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1ULL << (47 - 3)))
+ ((-1UL << __VIRTUAL_MASK_SHIFT) >> 3))
+/*
+ * 47 bits for kernel address -> (47 - 3) bits for shadow
+ * 56 bits for kernel address -> (56 - 3) bits for shadow
+ */
+#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1ULL << (__VIRTUAL_MASK_SHIFT - 3)))

#ifndef __ASSEMBLY__

diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 9215e05..3f5f08b 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -36,7 +36,12 @@
* hypervisor to fit. Choosing 16 slots here is arbitrary, but it's
* what Xen requires.
*/
+#ifdef CONFIG_X86_5LEVEL
+#define __PAGE_OFFSET_BASE _AC(0xff10000000000000, UL)
+#else
#define __PAGE_OFFSET_BASE _AC(0xffff880000000000, UL)
+#endif
+
#ifdef CONFIG_RANDOMIZE_MEMORY
#define __PAGE_OFFSET page_offset_base
#else
@@ -46,8 +51,13 @@
#define __START_KERNEL_map _AC(0xffffffff80000000, UL)

/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
+#ifdef CONFIG_X86_5LEVEL
+#define __PHYSICAL_MASK_SHIFT 52
+#define __VIRTUAL_MASK_SHIFT 56
+#else
#define __PHYSICAL_MASK_SHIFT 46
#define __VIRTUAL_MASK_SHIFT 47
+#endif

/*
* Kernel image size is limited to 1GiB due to the fixmap living in the
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 516593e6..4edc979 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -56,9 +56,15 @@ typedef struct { pteval_t pte; } pte_t;

/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#ifdef CONFIG_X86_5LEVEL
+#define VMALLOC_SIZE_TB _AC(16384, UL)
+#define __VMALLOC_BASE _AC(0xff92000000000000, UL)
+#define __VMEMMAP_BASE _AC(0xffd4000000000000, UL)
+#else
#define VMALLOC_SIZE_TB _AC(32, UL)
#define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
#define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
+#endif
#ifdef CONFIG_RANDOMIZE_MEMORY
#define VMALLOC_START vmalloc_base
#define VMEMMAP_START vmemmap_base
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 4517d6b..1f5bee2c 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -26,8 +26,13 @@
# endif
#else /* CONFIG_X86_32 */
# define SECTION_SIZE_BITS 27 /* matt - 128 is convenient right now */
-# define MAX_PHYSADDR_BITS 44
-# define MAX_PHYSMEM_BITS 46
+# ifdef CONFIG_X86_5LEVEL
+# define MAX_PHYSADDR_BITS 52
+# define MAX_PHYSMEM_BITS 52
+# else
+# define MAX_PHYSADDR_BITS 44
+# define MAX_PHYSMEM_BITS 46
+# endif
#endif

#endif /* CONFIG_SPARSEMEM */